{"images": [{"license": 3, "file_name": "000000147459.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000147459.jpg", "height": 519, "width": 640, "date_captured": "2013-11-20 06:28:24", "flickr_url": "http://farm3.staticflickr.com/2667/4139634288_6630819c8f_z.jpg", "id": 147459}, {"license": 1, "file_name": "000000466949.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000466949.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 16:08:46", "flickr_url": "http://farm9.staticflickr.com/8356/8334972919_5c22a76106_z.jpg", "id": 466949}, {"license": 7, "file_name": "000000376838.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000376838.jpg", "height": 377, "width": 500, "date_captured": "2013-11-16 04:37:44", "flickr_url": "http://farm4.staticflickr.com/3181/2677558151_0a22104546_z.jpg", "id": 376838}, {"license": 1, "file_name": "000000344073.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000344073.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 17:21:34", "flickr_url": "http://farm9.staticflickr.com/8292/7566705630_810eed3c67_z.jpg", "id": 344073}, {"license": 3, "file_name": "000000516106.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000516106.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 07:56:01", "flickr_url": "http://farm4.staticflickr.com/3762/9765383941_391b7966c7_z.jpg", "id": 516106}, {"license": 1, "file_name": "000000213005.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000213005.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 21:40:15", "flickr_url": "http://farm8.staticflickr.com/7188/7109425763_0b2c7af955_z.jpg", "id": 213005}, {"license": 4, "file_name": "000000368659.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000368659.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 18:41:52", "flickr_url": "http://farm9.staticflickr.com/8287/7735837950_63c61182f3_z.jpg", "id": 368659}, {"license": 1, "file_name": "000000278549.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000278549.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 14:11:06", "flickr_url": "http://farm4.staticflickr.com/3063/2915908617_7a034020f3_z.jpg", "id": 278549}, {"license": 3, "file_name": "000000032801.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032801.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 13:40:17", "flickr_url": "http://farm2.staticflickr.com/1274/976616199_8432efef7b_z.jpg", "id": 32801}, {"license": 5, "file_name": "000000581670.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000581670.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 17:44:29", "flickr_url": "http://farm3.staticflickr.com/2513/3928632798_b6d61187ca_z.jpg", "id": 581670}, {"license": 4, "file_name": "000000229415.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000229415.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 12:56:28", "flickr_url": "http://farm9.staticflickr.com/8375/8505620041_be73c38a0c_z.jpg", "id": 229415}, {"license": 1, "file_name": "000000385066.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000385066.jpg", "height": 283, "width": 500, "date_captured": "2013-11-15 07:40:59", "flickr_url": "http://farm4.staticflickr.com/3024/2589543297_a8f780f454_z.jpg", "id": 385066}, {"license": 1, "file_name": "000000401455.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000401455.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 23:23:52", "flickr_url": "http://farm6.staticflickr.com/5143/5625255521_263ceeef37_z.jpg", "id": 401455}, {"license": 4, "file_name": "000000032818.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032818.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 18:31:41", "flickr_url": "http://farm3.staticflickr.com/2687/4113654209_89d3764850_z.jpg", "id": 32818}, {"license": 1, "file_name": "000000008300.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000008300.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 18:50:23", "flickr_url": "http://farm5.staticflickr.com/4096/4886294163_d651a7c11f_z.jpg", "id": 8300}, {"license": 1, "file_name": "000000376941.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000376941.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 06:27:39", "flickr_url": "http://farm1.staticflickr.com/51/125293475_ff682de84d_z.jpg", "id": 376941}, {"license": 1, "file_name": "000000024689.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000024689.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 01:16:28", "flickr_url": "http://farm8.staticflickr.com/7459/9380323064_b47bba7f03_z.jpg", "id": 24689}, {"license": 5, "file_name": "000000360570.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000360570.jpg", "height": 424, "width": 640, "date_captured": "2013-11-14 17:44:26", "flickr_url": "http://farm4.staticflickr.com/3385/3248737123_cf22d720ea_z.jpg", "id": 360570}, {"license": 3, "file_name": "000000163985.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000163985.jpg", "height": 360, "width": 640, "date_captured": "2013-11-19 20:43:49", "flickr_url": "http://farm9.staticflickr.com/8321/7910202208_a7c1546900_z.jpg", "id": 163985}, {"license": 1, "file_name": "000000106652.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000106652.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 01:41:43", "flickr_url": "http://farm8.staticflickr.com/7154/6750622153_b38875cf45_z.jpg", "id": 106652}, {"license": 1, "file_name": "000000106660.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000106660.jpg", "height": 640, "width": 480, "date_captured": "2013-11-14 18:39:05", "flickr_url": "http://farm3.staticflickr.com/2637/4186866388_f11cec793b_z.jpg", "id": 106660}, {"license": 5, "file_name": "000000393394.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000393394.jpg", "height": 333, "width": 500, "date_captured": "2013-11-20 23:21:50", "flickr_url": "http://farm3.staticflickr.com/2584/4173704278_becc3454cb_z.jpg", "id": 393394}, {"license": 4, "file_name": "000000377017.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000377017.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 07:38:00", "flickr_url": "http://farm1.staticflickr.com/149/351828095_8c3ea7c526_z.jpg", "id": 377017}, {"license": 2, "file_name": "000000377019.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000377019.jpg", "height": 375, "width": 500, "date_captured": "2013-11-21 19:14:49", "flickr_url": "http://farm3.staticflickr.com/2377/2201282344_513146e097_z.jpg", "id": 377019}, {"license": 1, "file_name": "000000524476.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000524476.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 22:09:15", "flickr_url": "http://farm4.staticflickr.com/3571/3507404726_dab7693f27_z.jpg", "id": 524476}, {"license": 2, "file_name": "000000090310.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000090310.jpg", "height": 395, "width": 640, "date_captured": "2013-11-18 12:43:45", "flickr_url": "http://farm3.staticflickr.com/2871/9640890847_27b90a7ec5_z.jpg", "id": 90310}, {"license": 3, "file_name": "000000205000.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205000.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 01:23:13", "flickr_url": "http://farm1.staticflickr.com/124/383223097_d74677ebcf_z.jpg", "id": 205000}, {"license": 1, "file_name": "000000131277.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000131277.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:16:41", "flickr_url": "http://farm1.staticflickr.com/215/467372969_24e27628ed_z.jpg", "id": 131277}, {"license": 6, "file_name": "000000254176.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000254176.jpg", "height": 335, "width": 500, "date_captured": "2013-11-15 13:05:20", "flickr_url": "http://farm4.staticflickr.com/3622/3525460746_cc63c3c45a_z.jpg", "id": 254176}, {"license": 1, "file_name": "000000532711.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000532711.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 04:22:49", "flickr_url": "http://farm6.staticflickr.com/5146/5557341466_b097d06fee_z.jpg", "id": 532711}, {"license": 1, "file_name": "000000024808.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000024808.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 10:59:14", "flickr_url": "http://farm6.staticflickr.com/5141/5765569681_c44ec4325c_z.jpg", "id": 24808}, {"license": 4, "file_name": "000000033017.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000033017.jpg", "height": 640, "width": 470, "date_captured": "2013-11-15 11:33:26", "flickr_url": "http://farm8.staticflickr.com/7147/6615636479_1d254f7c85_z.jpg", "id": 33017}, {"license": 6, "file_name": "000000213241.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000213241.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 20:19:53", "flickr_url": "http://farm1.staticflickr.com/115/284203511_90c4e77082_z.jpg", "id": 213241}, {"license": 1, "file_name": "000000147710.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000147710.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 11:45:14", "flickr_url": "http://farm1.staticflickr.com/53/124177164_36bafdeff5_z.jpg", "id": 147710}, {"license": 1, "file_name": "000000499966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000499966.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:44:43", "flickr_url": "http://farm5.staticflickr.com/4130/5211358527_3ea21324d9_z.jpg", "id": 499966}, {"license": 4, "file_name": "000000532744.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000532744.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 17:16:45", "flickr_url": "http://farm4.staticflickr.com/3221/2676984227_4e21c387a5_z.jpg", "id": 532744}, {"license": 1, "file_name": "000000041233.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000041233.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 20:46:12", "flickr_url": "http://farm8.staticflickr.com/7116/7124747149_7de9ce6802_z.jpg", "id": 41233}, {"license": 3, "file_name": "000000442641.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000442641.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 20:40:51", "flickr_url": "http://farm1.staticflickr.com/22/32713544_ab9691f553_z.jpg", "id": 442641}, {"license": 1, "file_name": "000000237853.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000237853.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 00:47:02", "flickr_url": "http://farm4.staticflickr.com/3101/3237159405_2530304691_z.jpg", "id": 237853}, {"license": 4, "file_name": "000000229678.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000229678.jpg", "height": 500, "width": 375, "date_captured": "2013-11-15 14:28:06", "flickr_url": "http://farm1.staticflickr.com/117/250924093_57d1dfb8de_z.jpg", "id": 229678}, {"license": 1, "file_name": "000000475441.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000475441.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 17:47:30", "flickr_url": "http://farm3.staticflickr.com/2838/9540386280_c4a1e26b8c_z.jpg", "id": 475441}, {"license": 4, "file_name": "000000000309.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000000309.jpg", "height": 600, "width": 600, "date_captured": "2013-11-18 09:06:40", "flickr_url": "http://farm5.staticflickr.com/4125/5083164728_e4746a3f25_z.jpg", "id": 309}, {"license": 1, "file_name": "000000459082.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000459082.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 22:14:02", "flickr_url": "http://farm8.staticflickr.com/7411/8753279532_60e193260d_z.jpg", "id": 459082}, {"license": 4, "file_name": "000000205131.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205131.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 14:48:49", "flickr_url": "http://farm9.staticflickr.com/8050/8131656200_fe4be02289_z.jpg", "id": 205131}, {"license": 1, "file_name": "000000500057.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000500057.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 21:39:59", "flickr_url": "http://farm9.staticflickr.com/8208/8169455725_f5b5022858_z.jpg", "id": 500057}, {"license": 2, "file_name": "000000450914.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000450914.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 18:12:25", "flickr_url": "http://farm6.staticflickr.com/5137/5453555611_29f95902f5_z.jpg", "id": 450914}, {"license": 3, "file_name": "000000565608.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000565608.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 11:37:04", "flickr_url": "http://farm1.staticflickr.com/37/80608765_a6a2b062cb_z.jpg", "id": 565608}, {"license": 1, "file_name": "000000123247.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000123247.jpg", "height": 380, "width": 640, "date_captured": "2013-11-19 19:10:34", "flickr_url": "http://farm7.staticflickr.com/6202/6128058346_67951e8951_z.jpg", "id": 123247}, {"license": 6, "file_name": "000000131449.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000131449.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 16:21:00", "flickr_url": "http://farm9.staticflickr.com/8424/7719656988_2d73668a28_z.jpg", "id": 131449}, {"license": 2, "file_name": "000000041357.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000041357.jpg", "height": 430, "width": 640, "date_captured": "2013-11-19 22:54:40", "flickr_url": "http://farm6.staticflickr.com/5213/5414950536_139fb8702d_z.jpg", "id": 41357}, {"license": 3, "file_name": "000000205202.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205202.jpg", "height": 483, "width": 640, "date_captured": "2013-11-24 01:48:01", "flickr_url": "http://farm8.staticflickr.com/7265/8151212568_3614d71a48_z.jpg", "id": 205202}, {"license": 1, "file_name": "000000237976.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000237976.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 06:10:30", "flickr_url": "http://farm9.staticflickr.com/8470/8117166908_d94b2cec36_z.jpg", "id": 237976}, {"license": 2, "file_name": "000000311706.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000311706.jpg", "height": 375, "width": 500, "date_captured": "2013-11-22 00:18:54", "flickr_url": "http://farm1.staticflickr.com/112/316823996_50ed73fe8d_z.jpg", "id": 311706}, {"license": 2, "file_name": "000000491936.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000491936.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:53:22", "flickr_url": "http://farm9.staticflickr.com/8097/8592972681_afb52a9c80_z.jpg", "id": 491936}, {"license": 1, "file_name": "000000565664.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000565664.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 17:09:22", "flickr_url": "http://farm6.staticflickr.com/5487/9051185801_24e0dc9a85_z.jpg", "id": 565664}, {"license": 3, "file_name": "000000287140.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000287140.jpg", "height": 425, "width": 640, "date_captured": "2013-11-15 19:58:53", "flickr_url": "http://farm8.staticflickr.com/7229/7325668646_605349b419_z.jpg", "id": 287140}, {"license": 3, "file_name": "000000205223.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205223.jpg", "height": 238, "width": 640, "date_captured": "2013-11-18 04:09:35", "flickr_url": "http://farm5.staticflickr.com/4038/4589439433_ddda971c3c_z.jpg", "id": 205223}, {"license": 1, "file_name": "000000213419.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000213419.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 00:48:09", "flickr_url": "http://farm3.staticflickr.com/2773/4220854292_894c532bb2_z.jpg", "id": 213419}, {"license": 5, "file_name": "000000074156.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074156.jpg", "height": 423, "width": 640, "date_captured": "2013-11-17 14:19:07", "flickr_url": "http://farm3.staticflickr.com/2542/4509207410_1a34034ac0_z.jpg", "id": 74156}, {"license": 2, "file_name": "000000483766.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000483766.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 09:39:51", "flickr_url": "http://farm4.staticflickr.com/3261/3136532749_12caa87474_z.jpg", "id": 483766}, {"license": 6, "file_name": "000000229825.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000229825.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 03:35:13", "flickr_url": "http://farm4.staticflickr.com/3206/2847084660_7859227faf_z.jpg", "id": 229825}, {"license": 5, "file_name": "000000459201.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000459201.jpg", "height": 348, "width": 500, "date_captured": "2013-11-18 19:56:23", "flickr_url": "http://farm4.staticflickr.com/3446/3183888646_fc661d4b9f_z.jpg", "id": 459201}, {"license": 1, "file_name": "000000016836.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000016836.jpg", "height": 640, "width": 478, "date_captured": "2013-11-20 14:56:56", "flickr_url": "http://farm6.staticflickr.com/5217/5388029087_3a613cdfd5_z.jpg", "id": 16836}, {"license": 3, "file_name": "000000090569.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000090569.jpg", "height": 427, "width": 640, "date_captured": "2013-11-25 20:21:19", "flickr_url": "http://farm3.staticflickr.com/2521/3832777388_6709f68e0e_z.jpg", "id": 90569}, {"license": 1, "file_name": "000000295370.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000295370.jpg", "height": 640, "width": 640, "date_captured": "2013-11-18 13:26:03", "flickr_url": "http://farm6.staticflickr.com/5450/8772406576_ea542cd695_z.jpg", "id": 295370}, {"license": 1, "file_name": "000000090573.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000090573.jpg", "height": 458, "width": 640, "date_captured": "2013-11-20 23:30:54", "flickr_url": "http://farm8.staticflickr.com/7047/6826564342_703c721fac_z.jpg", "id": 90573}, {"license": 5, "file_name": "000000074201.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074201.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 06:11:09", "flickr_url": "http://farm4.staticflickr.com/3207/3053046327_b29922a167_z.jpg", "id": 74201}, {"license": 1, "file_name": "000000074217.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074217.jpg", "height": 363, "width": 640, "date_captured": "2013-11-15 12:54:43", "flickr_url": "http://farm4.staticflickr.com/3662/3357808213_2663346f42_z.jpg", "id": 74217}, {"license": 2, "file_name": "000000377329.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000377329.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 22:40:36", "flickr_url": "http://farm6.staticflickr.com/5461/7067813441_85587ea83a_z.jpg", "id": 377329}, {"license": 6, "file_name": "000000066034.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000066034.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:23:40", "flickr_url": "http://farm3.staticflickr.com/2778/4149057714_5f88b281e0_z.jpg", "id": 66034}, {"license": 2, "file_name": "000000500214.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000500214.jpg", "height": 400, "width": 640, "date_captured": "2013-11-18 07:24:36", "flickr_url": "http://farm3.staticflickr.com/2535/5830220619_af35bd3eb6_z.jpg", "id": 500214}, {"license": 4, "file_name": "000000549377.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000549377.jpg", "height": 479, "width": 640, "date_captured": "2013-11-17 05:27:05", "flickr_url": "http://farm4.staticflickr.com/3700/9530564007_29eca8ac2b_z.jpg", "id": 549377}, {"license": 3, "file_name": "000000131587.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000131587.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 23:53:18", "flickr_url": "http://farm4.staticflickr.com/3063/2965717202_eb5f458e85_z.jpg", "id": 131587}, {"license": 3, "file_name": "000000475651.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000475651.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 09:24:36", "flickr_url": "http://farm5.staticflickr.com/4056/4670396022_f1f366ac45_z.jpg", "id": 475651}, {"license": 5, "file_name": "000000492040.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000492040.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 18:36:10", "flickr_url": "http://farm8.staticflickr.com/7382/8726129677_7cf8facc7e_z.jpg", "id": 492040}, {"license": 1, "file_name": "000000156170.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000156170.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 13:36:14", "flickr_url": "http://farm1.staticflickr.com/169/412519217_ab9d39958b_z.jpg", "id": 156170}, {"license": 4, "file_name": "000000401962.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000401962.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 13:13:47", "flickr_url": "http://farm4.staticflickr.com/3069/2618671987_f72c3497dd_z.jpg", "id": 401962}, {"license": 3, "file_name": "000000082484.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000082484.jpg", "height": 346, "width": 500, "date_captured": "2013-11-17 16:19:57", "flickr_url": "http://farm1.staticflickr.com/132/389826399_5218fa291f_z.jpg", "id": 82484}, {"license": 4, "file_name": "000000533050.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000533050.jpg", "height": 436, "width": 640, "date_captured": "2013-11-17 03:28:10", "flickr_url": "http://farm9.staticflickr.com/8271/10239759933_b12be6b840_z.jpg", "id": 533050}, {"license": 2, "file_name": "000000401982.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000401982.jpg", "height": 346, "width": 640, "date_captured": "2013-11-19 21:25:46", "flickr_url": "http://farm2.staticflickr.com/1003/906313842_8664f6b01d_z.jpg", "id": 401982}, {"license": 4, "file_name": "000000524866.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000524866.jpg", "height": 405, "width": 640, "date_captured": "2013-11-24 04:02:05", "flickr_url": "http://farm2.staticflickr.com/1162/5103679466_287d32457e_z.jpg", "id": 524866}, {"license": 3, "file_name": "000000287302.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000287302.jpg", "height": 557, "width": 640, "date_captured": "2013-11-18 19:49:25", "flickr_url": "http://farm4.staticflickr.com/3317/3312734423_78b4dc828f_z.jpg", "id": 287302}, {"license": 3, "file_name": "000000541255.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000541255.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 20:34:37", "flickr_url": "http://farm4.staticflickr.com/3543/3321618624_d91e82c495_z.jpg", "id": 541255}, {"license": 3, "file_name": "000000303703.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000303703.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 14:34:43", "flickr_url": "http://farm5.staticflickr.com/4026/4291065855_4ecb650fc1_z.jpg", "id": 303703}, {"license": 3, "file_name": "000000229990.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000229990.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 23:00:50", "flickr_url": "http://farm3.staticflickr.com/2788/4522058182_6a3db61060_z.jpg", "id": 229990}, {"license": 5, "file_name": "000000238187.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000238187.jpg", "height": 500, "width": 375, "date_captured": "2013-11-19 18:16:26", "flickr_url": "http://farm4.staticflickr.com/3133/2393085431_f25ae75305_z.jpg", "id": 238187}, {"license": 5, "file_name": "000000074356.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074356.jpg", "height": 640, "width": 427, "date_captured": "2013-11-14 19:02:14", "flickr_url": "http://farm9.staticflickr.com/8371/8518496804_f83f621843_z.jpg", "id": 74356}, {"license": 6, "file_name": "000000549499.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000549499.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 12:24:58", "flickr_url": "http://farm9.staticflickr.com/8530/8669584007_25dfd66956_z.jpg", "id": 549499}, {"license": 5, "file_name": "000000524925.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000524925.jpg", "height": 441, "width": 640, "date_captured": "2013-11-16 05:46:58", "flickr_url": "http://farm5.staticflickr.com/4075/4922312122_6bb5da68df_z.jpg", "id": 524925}, {"license": 3, "file_name": "000000213652.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000213652.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 11:47:43", "flickr_url": "http://farm4.staticflickr.com/3149/2703952211_182336b480_z.jpg", "id": 213652}, {"license": 3, "file_name": "000000008856.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000008856.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 00:15:40", "flickr_url": "http://farm1.staticflickr.com/132/320328615_bf1d955729_z.jpg", "id": 8856}, {"license": 1, "file_name": "000000541338.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000541338.jpg", "height": 428, "width": 640, "date_captured": "2013-11-25 07:52:07", "flickr_url": "http://farm4.staticflickr.com/3785/9912774624_de2740267e_z.jpg", "id": 541338}, {"license": 4, "file_name": "000000524966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000524966.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 20:25:18", "flickr_url": "http://farm9.staticflickr.com/8062/8282173174_3935ef7f85_z.jpg", "id": 524966}, {"license": 1, "file_name": "000000385704.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000385704.jpg", "height": 640, "width": 426, "date_captured": "2013-11-18 05:10:18", "flickr_url": "http://farm4.staticflickr.com/3420/3711896022_f337d163e9_z.jpg", "id": 385704}, {"license": 5, "file_name": "000000197289.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000197289.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 22:59:36", "flickr_url": "http://farm3.staticflickr.com/2568/4067184235_8f50348047_z.jpg", "id": 197289}, {"license": 5, "file_name": "000000221880.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000221880.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 03:44:45", "flickr_url": "http://farm6.staticflickr.com/5281/5281078237_0e616b0707_z.jpg", "id": 221880}, {"license": 5, "file_name": "000000295613.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000295613.jpg", "height": 454, "width": 640, "date_captured": "2013-11-24 06:26:02", "flickr_url": "http://farm5.staticflickr.com/4096/4884408964_5303ab612b_z.jpg", "id": 295613}, {"license": 5, "file_name": "000000418500.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000418500.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 15:21:21", "flickr_url": "http://farm6.staticflickr.com/5444/7424366588_75f0c271c0_z.jpg", "id": 418500}, {"license": 1, "file_name": "000000426705.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000426705.jpg", "height": 500, "width": 500, "date_captured": "2013-11-14 20:15:28", "flickr_url": "http://farm3.staticflickr.com/2717/4458740285_c0907ab827_z.jpg", "id": 426705}, {"license": 1, "file_name": "000000451283.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000451283.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 19:06:57", "flickr_url": "http://farm7.staticflickr.com/6201/6111208522_f7428b3e84_z.jpg", "id": 451283}, {"license": 1, "file_name": "000000500440.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000500440.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:05:04", "flickr_url": "http://farm4.staticflickr.com/3115/3119197510_0869cf3063_z.jpg", "id": 500440}, {"license": 3, "file_name": "000000549599.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000549599.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 22:19:56", "flickr_url": "http://farm9.staticflickr.com/8435/7833436986_f4b5a1e05e_z.jpg", "id": 549599}, {"license": 4, "file_name": "000000533220.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000533220.jpg", "height": 427, "width": 640, "date_captured": "2013-11-25 08:01:30", "flickr_url": "http://farm3.staticflickr.com/2894/9702951890_326d11c1d9_z.jpg", "id": 533220}, {"license": 6, "file_name": "000000221927.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000221927.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 13:16:23", "flickr_url": "http://farm4.staticflickr.com/3071/2856691346_1f4d1e5a6d_z.jpg", "id": 221927}, {"license": 1, "file_name": "000000525039.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000525039.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 16:39:07", "flickr_url": "http://farm4.staticflickr.com/3194/2958863866_ff8bfeccce_z.jpg", "id": 525039}, {"license": 5, "file_name": "000000443136.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000443136.jpg", "height": 480, "width": 640, "date_captured": "2013-11-23 03:36:57", "flickr_url": "http://farm3.staticflickr.com/2712/4107751697_5e40555972_z.jpg", "id": 443136}, {"license": 3, "file_name": "000000041730.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000041730.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 21:30:11", "flickr_url": "http://farm5.staticflickr.com/4013/4396940149_d0fe11b272_z.jpg", "id": 41730}, {"license": 3, "file_name": "000000254726.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000254726.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 14:28:32", "flickr_url": "http://farm9.staticflickr.com/8309/8065318488_870ea368e3_z.jpg", "id": 254726}, {"license": 1, "file_name": "000000418569.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000418569.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 14:05:48", "flickr_url": "http://farm1.staticflickr.com/46/143952780_5834ff5c79_z.jpg", "id": 418569}, {"license": 1, "file_name": "000000181009.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000181009.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 07:01:04", "flickr_url": "http://farm4.staticflickr.com/3191/2883873186_bfaf92685f_z.jpg", "id": 181009}, {"license": 1, "file_name": "000000516889.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000516889.jpg", "height": 476, "width": 640, "date_captured": "2013-11-18 04:36:09", "flickr_url": "http://farm9.staticflickr.com/8526/8522264692_33c7e209bc_z.jpg", "id": 516889}, {"license": 3, "file_name": "000000000795.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000000795.jpg", "height": 332, "width": 500, "date_captured": "2013-11-17 05:15:31", "flickr_url": "http://farm1.staticflickr.com/37/82279191_b4058303b4_z.jpg", "id": 795}, {"license": 1, "file_name": "000000033581.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000033581.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 03:37:05", "flickr_url": "http://farm4.staticflickr.com/3242/2621102896_ba9ca07b1f_z.jpg", "id": 33581}, {"license": 2, "file_name": "000000467760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000467760.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 15:14:48", "flickr_url": "http://farm1.staticflickr.com/65/210204460_61189bf98b_z.jpg", "id": 467760}, {"license": 4, "file_name": "000000115505.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000115505.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 11:23:30", "flickr_url": "http://farm6.staticflickr.com/5109/5679351381_6e3c35742f_z.jpg", "id": 115505}, {"license": 1, "file_name": "000000074549.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074549.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 00:45:53", "flickr_url": "http://farm9.staticflickr.com/8196/8086165620_8a56bc5b04_z.jpg", "id": 74549}, {"license": 4, "file_name": "000000066376.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000066376.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 20:42:38", "flickr_url": "http://farm5.staticflickr.com/4060/4388897791_fa94acc441_z.jpg", "id": 66376}, {"license": 1, "file_name": "000000475980.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000475980.jpg", "height": 500, "width": 375, "date_captured": "2013-11-14 23:42:02", "flickr_url": "http://farm1.staticflickr.com/250/459100806_26eef30ae0_z.jpg", "id": 475980}, {"license": 3, "file_name": "000000074577.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074577.jpg", "height": 640, "width": 426, "date_captured": "2013-11-20 13:29:45", "flickr_url": "http://farm3.staticflickr.com/2285/2372627765_4259a8c534_z.jpg", "id": 74577}, {"license": 5, "file_name": "000000435029.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000435029.jpg", "height": 428, "width": 640, "date_captured": "2013-11-18 16:09:38", "flickr_url": "http://farm3.staticflickr.com/2634/3832738067_4da77975fe_z.jpg", "id": 435029}, {"license": 2, "file_name": "000000426838.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000426838.jpg", "height": 502, "width": 640, "date_captured": "2013-11-19 20:45:29", "flickr_url": "http://farm3.staticflickr.com/2422/3816575453_7dd121353d_z.jpg", "id": 426838}, {"license": 1, "file_name": "000000402264.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000402264.jpg", "height": 267, "width": 640, "date_captured": "2013-11-14 16:28:23", "flickr_url": "http://farm1.staticflickr.com/74/214720035_2e3a2fa296_z.jpg", "id": 402264}, {"license": 2, "file_name": "000000041818.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000041818.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 20:22:46", "flickr_url": "http://farm8.staticflickr.com/7019/6751914653_733658a42f_z.jpg", "id": 41818}, {"license": 6, "file_name": "000000369509.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000369509.jpg", "height": 640, "width": 425, "date_captured": "2013-11-24 01:46:26", "flickr_url": "http://farm7.staticflickr.com/6081/6101256047_2aeece2d50_z.jpg", "id": 369509}, {"license": 3, "file_name": "000000508780.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000508780.jpg", "height": 640, "width": 425, "date_captured": "2013-11-20 00:47:22", "flickr_url": "http://farm9.staticflickr.com/8176/8017561357_139abbfa7e_z.jpg", "id": 508780}, {"license": 1, "file_name": "000000025455.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000025455.jpg", "height": 427, "width": 640, "date_captured": "2013-11-22 23:29:31", "flickr_url": "http://farm1.staticflickr.com/23/27884425_a844fef55e_z.jpg", "id": 25455}, {"license": 1, "file_name": "000000246641.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000246641.jpg", "height": 360, "width": 640, "date_captured": "2013-11-20 01:20:20", "flickr_url": "http://farm2.staticflickr.com/1162/4595681817_ac04c21e57_z.jpg", "id": 246641}, {"license": 3, "file_name": "000000525180.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000525180.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 22:11:44", "flickr_url": "http://farm8.staticflickr.com/7280/6881077872_661d62841d_z.jpg", "id": 525180}, {"license": 3, "file_name": "000000426877.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000426877.jpg", "height": 640, "width": 444, "date_captured": "2013-11-18 14:52:30", "flickr_url": "http://farm8.staticflickr.com/7189/6900214937_cd2ba7992c_z.jpg", "id": 426877}, {"license": 6, "file_name": "000000189330.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000189330.jpg", "height": 431, "width": 640, "date_captured": "2013-11-16 18:13:20", "flickr_url": "http://farm9.staticflickr.com/8103/8528320781_4470528fe3_z.jpg", "id": 189330}, {"license": 1, "file_name": "000000197525.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000197525.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 01:42:34", "flickr_url": "http://farm9.staticflickr.com/8100/8545885372_cf4c07548b_z.jpg", "id": 197525}, {"license": 1, "file_name": "000000107425.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000107425.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 05:00:20", "flickr_url": "http://farm4.staticflickr.com/3101/3198879324_b8aa1b38a9_z.jpg", "id": 107425}, {"license": 3, "file_name": "000000074663.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074663.jpg", "height": 640, "width": 486, "date_captured": "2013-11-16 23:17:56", "flickr_url": "http://farm4.staticflickr.com/3510/3224066762_9b8d127470_z.jpg", "id": 74663}, {"license": 1, "file_name": "000000287659.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000287659.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 21:39:48", "flickr_url": "http://farm5.staticflickr.com/4121/4929319058_b9465bb06d_z.jpg", "id": 287659}, {"license": 3, "file_name": "000000140210.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000140210.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 20:43:47", "flickr_url": "http://farm1.staticflickr.com/187/455827561_e22d24e326_z.jpg", "id": 140210}, {"license": 4, "file_name": "000000050101.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000050101.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 19:06:35", "flickr_url": "http://farm5.staticflickr.com/4047/4628888987_d76fdbd4e2_z.jpg", "id": 50101}, {"license": 3, "file_name": "000000500662.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000500662.jpg", "height": 640, "width": 501, "date_captured": "2013-11-18 08:36:33", "flickr_url": "http://farm7.staticflickr.com/6121/5978166081_39036448a7_z.jpg", "id": 500662}, {"license": 1, "file_name": "000000205757.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205757.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 12:24:25", "flickr_url": "http://farm4.staticflickr.com/3274/2293946604_46b774793b_z.jpg", "id": 205757}, {"license": 6, "file_name": "000000156608.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000156608.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 19:29:19", "flickr_url": "http://farm4.staticflickr.com/3055/2856425201_5ffa2717e8_z.jpg", "id": 156608}, {"license": 1, "file_name": "000000066518.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000066518.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 15:27:35", "flickr_url": "http://farm7.staticflickr.com/6028/5968095602_f6e639b2f0_z.jpg", "id": 66518}, {"license": 1, "file_name": "000000312282.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000312282.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 01:24:24", "flickr_url": "http://farm4.staticflickr.com/3266/3188963060_5f842d49a8_z.jpg", "id": 312282}, {"license": 4, "file_name": "000000246753.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000246753.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 17:55:04", "flickr_url": "http://farm6.staticflickr.com/5209/5268520127_125b705297_z.jpg", "id": 246753}, {"license": 3, "file_name": "000000205794.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000205794.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 21:49:51", "flickr_url": "http://farm6.staticflickr.com/5146/5588496653_765fb0a725_z.jpg", "id": 205794}, {"license": 3, "file_name": "000000009185.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000009185.jpg", "height": 428, "width": 640, "date_captured": "2013-11-19 18:40:29", "flickr_url": "http://farm3.staticflickr.com/2779/4350207908_dfc6a53d23_z.jpg", "id": 9185}, {"license": 4, "file_name": "000000517095.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000517095.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 01:32:44", "flickr_url": "http://farm8.staticflickr.com/7402/9205354550_b8ac9e65ae_z.jpg", "id": 517095}, {"license": 5, "file_name": "000000173032.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000173032.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 06:04:42", "flickr_url": "http://farm1.staticflickr.com/91/222782664_c0391b90ef_z.jpg", "id": 173032}, {"license": 3, "file_name": "000000222199.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000222199.jpg", "height": 373, "width": 640, "date_captured": "2013-11-16 17:39:58", "flickr_url": "http://farm8.staticflickr.com/7353/9127169928_f55aea59b0_z.jpg", "id": 222199}, {"license": 3, "file_name": "000000353282.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000353282.jpg", "height": 428, "width": 640, "date_captured": "2013-11-19 22:53:49", "flickr_url": "http://farm3.staticflickr.com/2294/2443416580_b236613547_z.jpg", "id": 353282}, {"license": 1, "file_name": "000000517123.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000517123.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 23:21:07", "flickr_url": "http://farm6.staticflickr.com/5183/5774369702_5fc864234b_z.jpg", "id": 517123}, {"license": 5, "file_name": "000000263176.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000263176.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 06:21:33", "flickr_url": "http://farm8.staticflickr.com/7389/9435717049_ecc6dfb1d1_z.jpg", "id": 263176}, {"license": 3, "file_name": "000000402448.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000402448.jpg", "height": 414, "width": 640, "date_captured": "2013-11-20 17:30:19", "flickr_url": "http://farm9.staticflickr.com/8070/8206912027_d728c70632_z.jpg", "id": 402448}, {"license": 1, "file_name": "000000484369.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000484369.jpg", "height": 473, "width": 640, "date_captured": "2013-11-24 14:57:22", "flickr_url": "http://farm9.staticflickr.com/8179/7890410470_3870421174_z.jpg", "id": 484369}, {"license": 1, "file_name": "000000443410.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000443410.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 00:54:14", "flickr_url": "http://farm3.staticflickr.com/2691/4280031324_4b204a7877_z.jpg", "id": 443410}, {"license": 5, "file_name": "000000328727.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000328727.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 02:33:05", "flickr_url": "http://farm7.staticflickr.com/6084/6130602355_69056e61db_z.jpg", "id": 328727}, {"license": 2, "file_name": "000000566301.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000566301.jpg", "height": 640, "width": 425, "date_captured": "2013-11-20 23:57:36", "flickr_url": "http://farm6.staticflickr.com/5174/5453733317_04f6a5628a_z.jpg", "id": 566301}, {"license": 2, "file_name": "000000418847.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000418847.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 05:36:32", "flickr_url": "http://farm6.staticflickr.com/5548/9484385539_6e7b29bfec_z.jpg", "id": 418847}, {"license": 4, "file_name": "000000295970.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000295970.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 15:09:46", "flickr_url": "http://farm3.staticflickr.com/2244/2366161067_78c538f556_z.jpg", "id": 295970}, {"license": 3, "file_name": "000000058403.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000058403.jpg", "height": 429, "width": 640, "date_captured": "2013-11-15 14:49:04", "flickr_url": "http://farm3.staticflickr.com/2359/2538174930_245b91af0e_z.jpg", "id": 58403}, {"license": 4, "file_name": "000000230436.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000230436.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 04:21:32", "flickr_url": "http://farm3.staticflickr.com/2361/1602209016_2c53e0d4dc_z.jpg", "id": 230436}, {"license": 4, "file_name": "000000238630.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000238630.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 22:30:57", "flickr_url": "http://farm3.staticflickr.com/2804/4521479626_949bd736fa_z.jpg", "id": 238630}, {"license": 2, "file_name": "000000255016.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000255016.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 19:56:06", "flickr_url": "http://farm2.staticflickr.com/1391/1272237768_c1146108aa_z.jpg", "id": 255016}, {"license": 1, "file_name": "000000566319.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000566319.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 13:36:40", "flickr_url": "http://farm1.staticflickr.com/194/487442988_66059f8510_z.jpg", "id": 566319}, {"license": 1, "file_name": "000000083000.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083000.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 17:03:42", "flickr_url": "http://farm8.staticflickr.com/7210/6889113893_abe3963d88_z.jpg", "id": 83000}, {"license": 3, "file_name": "000000083005.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083005.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 04:14:06", "flickr_url": "http://farm3.staticflickr.com/2402/1796869491_e110e21a5f_z.jpg", "id": 83005}, {"license": 2, "file_name": "000000533568.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000533568.jpg", "height": 375, "width": 500, "date_captured": "2013-11-22 02:45:13", "flickr_url": "http://farm4.staticflickr.com/3551/3466740983_0ea1f2269d_z.jpg", "id": 533568}, {"license": 1, "file_name": "000000164935.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000164935.jpg", "height": 422, "width": 640, "date_captured": "2013-11-16 23:26:31", "flickr_url": "http://farm5.staticflickr.com/4136/4889933491_8a876ef0b0_z.jpg", "id": 164935}, {"license": 3, "file_name": "000000238667.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000238667.jpg", "height": 453, "width": 640, "date_captured": "2013-11-18 20:07:19", "flickr_url": "http://farm4.staticflickr.com/3656/3474428646_e37d1ed078_z.jpg", "id": 238667}, {"license": 4, "file_name": "000000492638.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000492638.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 22:33:33", "flickr_url": "http://farm3.staticflickr.com/2395/2139829759_3bff1fb807_z.jpg", "id": 492638}, {"license": 3, "file_name": "000000574563.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000574563.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 16:24:32", "flickr_url": "http://farm1.staticflickr.com/21/32958955_24d47837f2_z.jpg", "id": 574563}, {"license": 4, "file_name": "000000320611.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000320611.jpg", "height": 481, "width": 640, "date_captured": "2013-11-21 23:14:06", "flickr_url": "http://farm3.staticflickr.com/2266/5762596299_6d066f8b1c_z.jpg", "id": 320611}, {"license": 6, "file_name": "000000066669.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000066669.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 21:05:42", "flickr_url": "http://farm4.staticflickr.com/3325/3274392233_a9d55f2400_z.jpg", "id": 66669}, {"license": 1, "file_name": "000000099451.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000099451.jpg", "height": 375, "width": 500, "date_captured": "2013-11-21 22:09:21", "flickr_url": "http://farm3.staticflickr.com/2163/2657585799_d9554345a7_z.jpg", "id": 99451}, {"license": 3, "file_name": "000000271488.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000271488.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 18:11:35", "flickr_url": "http://farm1.staticflickr.com/184/380682230_aa985d1ba6_z.jpg", "id": 271488}, {"license": 1, "file_name": "000000246927.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000246927.jpg", "height": 428, "width": 640, "date_captured": "2013-11-25 08:22:08", "flickr_url": "http://farm6.staticflickr.com/5446/9402968432_864aa64b8a_z.jpg", "id": 246927}, {"license": 3, "file_name": "000000181393.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000181393.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 17:23:58", "flickr_url": "http://farm9.staticflickr.com/8361/8307417479_cac1cea7f3_z.jpg", "id": 181393}, {"license": 5, "file_name": "000000468117.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000468117.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 05:13:06", "flickr_url": "http://farm1.staticflickr.com/253/452597713_dffb41d407_z.jpg", "id": 468117}, {"license": 1, "file_name": "000000156823.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000156823.jpg", "height": 640, "width": 442, "date_captured": "2013-11-16 16:49:25", "flickr_url": "http://farm5.staticflickr.com/4085/5222724075_1eba4046d4_z.jpg", "id": 156823}, {"license": 3, "file_name": "000000386211.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000386211.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 05:37:38", "flickr_url": "http://farm1.staticflickr.com/51/146238184_5c42a0d822_z.jpg", "id": 386211}, {"license": 3, "file_name": "000000230570.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000230570.jpg", "height": 640, "width": 427, "date_captured": "2013-11-20 19:27:28", "flickr_url": "http://farm3.staticflickr.com/2265/2488152271_5100b2def2_z.jpg", "id": 230570}, {"license": 3, "file_name": "000000418989.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000418989.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 18:24:38", "flickr_url": "http://farm6.staticflickr.com/5022/5585512762_8be301776c_z.jpg", "id": 418989}, {"license": 1, "file_name": "000000074945.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000074945.jpg", "height": 512, "width": 640, "date_captured": "2013-11-17 04:43:34", "flickr_url": "http://farm3.staticflickr.com/2474/4047780321_6b4c1f0847_z.jpg", "id": 74945}, {"license": 2, "file_name": "000000558276.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000558276.jpg", "height": 640, "width": 427, "date_captured": "2013-11-24 15:18:11", "flickr_url": "http://farm5.staticflickr.com/4051/4245846169_6aa2cd2e3f_z.jpg", "id": 558276}, {"license": 2, "file_name": "000000033991.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000033991.jpg", "height": 640, "width": 511, "date_captured": "2013-11-18 08:54:05", "flickr_url": "http://farm5.staticflickr.com/4105/4968676874_2153293b24_z.jpg", "id": 33991}, {"license": 4, "file_name": "000000033992.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000033992.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 03:57:24", "flickr_url": "http://farm4.staticflickr.com/3824/9981337745_bde573a213_z.jpg", "id": 33992}, {"license": 3, "file_name": "000000320721.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000320721.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 01:10:56", "flickr_url": "http://farm3.staticflickr.com/2003/1505059061_41f6d4071a_z.jpg", "id": 320721}, {"license": 4, "file_name": "000000443604.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000443604.jpg", "height": 425, "width": 640, "date_captured": "2013-11-18 10:27:25", "flickr_url": "http://farm7.staticflickr.com/6119/6329387850_67072b0800_z.jpg", "id": 443604}, {"license": 2, "file_name": "000000419028.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000419028.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 19:24:43", "flickr_url": "http://farm3.staticflickr.com/2644/3940753879_492a397411_z.jpg", "id": 419028}, {"license": 1, "file_name": "000000566488.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000566488.jpg", "height": 640, "width": 466, "date_captured": "2013-11-19 22:34:53", "flickr_url": "http://farm7.staticflickr.com/6044/6274713852_97cb0a3b8f_z.jpg", "id": 566488}, {"license": 1, "file_name": "000000050410.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000050410.jpg", "height": 640, "width": 360, "date_captured": "2013-11-20 16:19:35", "flickr_url": "http://farm6.staticflickr.com/5298/5478018499_fa7f421526_z.jpg", "id": 50410}, {"license": 1, "file_name": "000000001261.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000001261.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 21:50:52", "flickr_url": "http://farm9.staticflickr.com/8205/8237881890_52891af127_z.jpg", "id": 1261}, {"license": 2, "file_name": "000000206062.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000206062.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 22:34:56", "flickr_url": "http://farm7.staticflickr.com/6164/6184348347_9b6a1a915e_z.jpg", "id": 206062}, {"license": 5, "file_name": "000000541938.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000541938.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 19:54:34", "flickr_url": "http://farm9.staticflickr.com/8261/8664684149_f173fa75a8_z.jpg", "id": 541938}, {"license": 3, "file_name": "000000468219.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000468219.jpg", "height": 446, "width": 640, "date_captured": "2013-11-18 01:58:28", "flickr_url": "http://farm7.staticflickr.com/6191/6046759662_0542b5cd49_z.jpg", "id": 468219}, {"license": 4, "file_name": "000000541949.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000541949.jpg", "height": 612, "width": 640, "date_captured": "2013-11-18 05:41:52", "flickr_url": "http://farm4.staticflickr.com/3428/3316007804_8c7c902263_z.jpg", "id": 541949}, {"license": 3, "file_name": "000000451842.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000451842.jpg", "height": 619, "width": 640, "date_captured": "2013-11-21 03:13:46", "flickr_url": "http://farm8.staticflickr.com/7122/7463263902_901f6d3467_z.jpg", "id": 451842}, {"license": 2, "file_name": "000000124169.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000124169.jpg", "height": 304, "width": 640, "date_captured": "2013-11-23 19:13:41", "flickr_url": "http://farm2.staticflickr.com/1178/674685743_88c81312b4_z.jpg", "id": 124169}, {"license": 1, "file_name": "000000304408.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000304408.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:18:23", "flickr_url": "http://farm3.staticflickr.com/2664/3865150567_d9334a4ed3_z.jpg", "id": 304408}, {"license": 2, "file_name": "000000427301.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000427301.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 03:47:01", "flickr_url": "http://farm6.staticflickr.com/5205/5299680508_3e4a9553a6_z.jpg", "id": 427301}, {"license": 1, "file_name": "000000419110.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000419110.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 06:30:28", "flickr_url": "http://farm8.staticflickr.com/7026/6666459735_9ae8384ba0_z.jpg", "id": 419110}, {"license": 1, "file_name": "000000369961.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000369961.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 15:08:47", "flickr_url": "http://farm7.staticflickr.com/6207/6043665997_ccb2fac440_z.jpg", "id": 369961}, {"license": 1, "file_name": "000000320834.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000320834.jpg", "height": 375, "width": 500, "date_captured": "2013-11-25 21:00:52", "flickr_url": "http://farm4.staticflickr.com/3151/2385465177_6425d44d25_z.jpg", "id": 320834}, {"license": 3, "file_name": "000000042308.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000042308.jpg", "height": 334, "width": 500, "date_captured": "2013-11-20 08:11:11", "flickr_url": "http://farm2.staticflickr.com/1297/1023737913_d5349652c6_z.jpg", "id": 42308}, {"license": 3, "file_name": "000000116040.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000116040.jpg", "height": 640, "width": 503, "date_captured": "2013-11-16 03:32:01", "flickr_url": "http://farm6.staticflickr.com/5150/5561287263_1089909060_z.jpg", "id": 116040}, {"license": 2, "file_name": "000000132430.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000132430.jpg", "height": 333, "width": 500, "date_captured": "2013-11-16 16:10:27", "flickr_url": "http://farm1.staticflickr.com/53/116917353_8136e6d8dc_z.jpg", "id": 132430}, {"license": 1, "file_name": "000000492882.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000492882.jpg", "height": 428, "width": 640, "date_captured": "2013-11-16 14:46:57", "flickr_url": "http://farm8.staticflickr.com/7267/7613226414_6565290cb3_z.jpg", "id": 492882}, {"license": 4, "file_name": "000000443741.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000443741.jpg", "height": 500, "width": 331, "date_captured": "2013-11-18 05:17:16", "flickr_url": "http://farm3.staticflickr.com/2468/3682022892_16c628ec92_z.jpg", "id": 443741}, {"license": 1, "file_name": "000000492894.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000492894.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 15:26:46", "flickr_url": "http://farm8.staticflickr.com/7420/8718043946_f66428df0e_z.jpg", "id": 492894}, {"license": 4, "file_name": "000000517492.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000517492.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 16:16:28", "flickr_url": "http://farm6.staticflickr.com/5026/5641379794_505a8efa72_z.jpg", "id": 517492}, {"license": 3, "file_name": "000000206198.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000206198.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 21:11:29", "flickr_url": "http://farm3.staticflickr.com/2099/2434491001_53cfe54e33_z.jpg", "id": 206198}, {"license": 3, "file_name": "000000001407.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000001407.jpg", "height": 640, "width": 428, "date_captured": "2013-11-21 03:14:52", "flickr_url": "http://farm8.staticflickr.com/7263/7474595800_019d6b1be2_z.jpg", "id": 1407}, {"license": 6, "file_name": "000000189836.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000189836.jpg", "height": 512, "width": 640, "date_captured": "2013-11-17 15:46:37", "flickr_url": "http://farm4.staticflickr.com/3390/3604819004_ab428031c6_z.jpg", "id": 189836}, {"license": 3, "file_name": "000000247181.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000247181.jpg", "height": 332, "width": 500, "date_captured": "2013-11-22 01:32:42", "flickr_url": "http://farm3.staticflickr.com/2517/3996909972_dab666b678_z.jpg", "id": 247181}, {"license": 2, "file_name": "000000468373.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000468373.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 02:53:02", "flickr_url": "http://farm9.staticflickr.com/8504/8297816219_e86f6faa91_z.jpg", "id": 468373}, {"license": 3, "file_name": "000000550308.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000550308.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 20:11:37", "flickr_url": "http://farm2.staticflickr.com/1356/639076577_29e5ae207f_z.jpg", "id": 550308}, {"license": 4, "file_name": "000000050601.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000050601.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 14:30:23", "flickr_url": "http://farm8.staticflickr.com/7034/6718712331_39aacdd563_z.jpg", "id": 50601}, {"license": 1, "file_name": "000000181681.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000181681.jpg", "height": 600, "width": 400, "date_captured": "2013-11-18 13:51:01", "flickr_url": "http://farm9.staticflickr.com/8188/8085165214_063c413a7f_z.jpg", "id": 181681}, {"license": 4, "file_name": "000000501177.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000501177.jpg", "height": 612, "width": 612, "date_captured": "2013-11-24 05:46:52", "flickr_url": "http://farm9.staticflickr.com/8360/8330917219_abd3b6fe78_z.jpg", "id": 501177}, {"license": 1, "file_name": "000000427461.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000427461.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 12:04:06", "flickr_url": "http://farm2.staticflickr.com/1101/935926778_4163af10eb_z.jpg", "id": 427461}, {"license": 2, "file_name": "000000427467.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000427467.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 13:58:43", "flickr_url": "http://farm3.staticflickr.com/2655/4118613758_09be0b7d1c_z.jpg", "id": 427467}, {"license": 2, "file_name": "000000361939.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000361939.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 02:17:16", "flickr_url": "http://farm1.staticflickr.com/35/116385857_7d866b07d4_z.jpg", "id": 361939}, {"license": 3, "file_name": "000000222676.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000222676.jpg", "height": 486, "width": 640, "date_captured": "2013-11-21 01:36:03", "flickr_url": "http://farm6.staticflickr.com/5234/5811676472_c84883346a_z.jpg", "id": 222676}, {"license": 3, "file_name": "000000189915.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000189915.jpg", "height": 428, "width": 640, "date_captured": "2013-11-16 17:31:11", "flickr_url": "http://farm2.staticflickr.com/1161/526778851_0c7c28cad1_z.jpg", "id": 189915}, {"license": 2, "file_name": "000000435681.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000435681.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 14:08:45", "flickr_url": "http://farm6.staticflickr.com/5518/9679032277_84aba683e3_z.jpg", "id": 435681}, {"license": 3, "file_name": "000000288234.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000288234.jpg", "height": 424, "width": 640, "date_captured": "2013-11-19 19:52:17", "flickr_url": "http://farm5.staticflickr.com/4015/4430385527_3b50bee271_z.jpg", "id": 288234}, {"license": 3, "file_name": "000000476651.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000476651.jpg", "height": 428, "width": 640, "date_captured": "2013-11-23 03:38:32", "flickr_url": "http://farm4.staticflickr.com/3352/3260759059_12a0e690b8_z.jpg", "id": 476651}, {"license": 7, "file_name": "000000230893.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000230893.jpg", "height": 377, "width": 500, "date_captured": "2013-11-15 08:56:28", "flickr_url": "http://farm4.staticflickr.com/3022/2742078423_6e29179862_z.jpg", "id": 230893}, {"license": 2, "file_name": "000000058864.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000058864.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 01:09:04", "flickr_url": "http://farm4.staticflickr.com/3788/9136191075_d60a0f74d1_z.jpg", "id": 58864}, {"license": 2, "file_name": "000000280051.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000280051.jpg", "height": 640, "width": 509, "date_captured": "2013-11-17 04:34:03", "flickr_url": "http://farm5.staticflickr.com/4057/4660972213_da4974b240_z.jpg", "id": 280051}, {"license": 2, "file_name": "000000148983.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000148983.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 19:55:30", "flickr_url": "http://farm1.staticflickr.com/104/251580577_6089f18fee_z.jpg", "id": 148983}, {"license": 1, "file_name": "000000419324.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000419324.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:37:44", "flickr_url": "http://farm1.staticflickr.com/175/369947712_1bc72168ef_z.jpg", "id": 419324}, {"license": 1, "file_name": "000000157190.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000157190.jpg", "height": 400, "width": 500, "date_captured": "2013-11-24 12:46:17", "flickr_url": "http://farm3.staticflickr.com/2069/2171007168_eecf50f8f3_z.jpg", "id": 157190}, {"license": 2, "file_name": "000000443916.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000443916.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 13:15:51", "flickr_url": "http://farm5.staticflickr.com/4127/5090290985_1924bc031c_z.jpg", "id": 443916}, {"license": 5, "file_name": "000000140821.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000140821.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 02:10:32", "flickr_url": "http://farm7.staticflickr.com/6172/6167841768_909207ea4f_z.jpg", "id": 140821}, {"license": 1, "file_name": "000000321066.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000321066.jpg", "height": 431, "width": 640, "date_captured": "2013-11-18 03:40:08", "flickr_url": "http://farm4.staticflickr.com/3670/10061457363_776c0e7354_z.jpg", "id": 321066}, {"license": 2, "file_name": "000000017962.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000017962.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 23:44:18", "flickr_url": "http://farm5.staticflickr.com/4069/4718506924_e461c688a6_z.jpg", "id": 17962}, {"license": 1, "file_name": "000000288310.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000288310.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 09:45:31", "flickr_url": "http://farm9.staticflickr.com/8369/8574919547_22bc0617cc_z.jpg", "id": 288310}, {"license": 1, "file_name": "000000566847.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000566847.jpg", "height": 640, "width": 427, "date_captured": "2013-11-16 17:46:02", "flickr_url": "http://farm7.staticflickr.com/6015/5954650663_2a6588a79f_z.jpg", "id": 566847}, {"license": 1, "file_name": "000000263744.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000263744.jpg", "height": 375, "width": 500, "date_captured": "2013-11-15 17:04:31", "flickr_url": "http://farm4.staticflickr.com/3254/2770412386_e02a44ba2c_z.jpg", "id": 263744}, {"license": 4, "file_name": "000000419396.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000419396.jpg", "height": 320, "width": 640, "date_captured": "2013-11-24 18:29:59", "flickr_url": "http://farm6.staticflickr.com/5519/9150885379_9464f810a2_z.jpg", "id": 419396}, {"license": 1, "file_name": "000000460362.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000460362.jpg", "height": 425, "width": 640, "date_captured": "2013-11-23 02:54:36", "flickr_url": "http://farm5.staticflickr.com/4051/4497885040_da36da42d9_z.jpg", "id": 460362}, {"license": 3, "file_name": "000000017997.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000017997.jpg", "height": 327, "width": 640, "date_captured": "2013-11-16 18:35:36", "flickr_url": "http://farm5.staticflickr.com/4088/4982468286_1cd6fc9c23_z.jpg", "id": 17997}, {"license": 1, "file_name": "000000534107.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000534107.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 14:49:19", "flickr_url": "http://farm3.staticflickr.com/2583/3747299613_fecc96e0ff_z.jpg", "id": 534107}, {"license": 2, "file_name": "000000009822.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000009822.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 15:53:01", "flickr_url": "http://farm4.staticflickr.com/3003/2544661482_44c6436016_z.jpg", "id": 9822}, {"license": 5, "file_name": "000000411238.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000411238.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 04:40:51", "flickr_url": "http://farm5.staticflickr.com/4005/4472138085_dd31cc3a47_z.jpg", "id": 411238}, {"license": 3, "file_name": "000000083561.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083561.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 15:33:39", "flickr_url": "http://farm4.staticflickr.com/3716/9054215713_5ed78451ce_z.jpg", "id": 83561}, {"license": 1, "file_name": "000000304757.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000304757.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 05:11:31", "flickr_url": "http://farm4.staticflickr.com/3174/3028108279_46051c769d_z.jpg", "id": 304757}, {"license": 1, "file_name": "000000468602.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000468602.jpg", "height": 433, "width": 640, "date_captured": "2013-11-16 16:21:16", "flickr_url": "http://farm4.staticflickr.com/3196/3061831679_052e4d61e9_z.jpg", "id": 468602}, {"license": 4, "file_name": "000000329339.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000329339.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 23:34:29", "flickr_url": "http://farm9.staticflickr.com/8323/8440288246_ff982d991a_z.jpg", "id": 329339}, {"license": 4, "file_name": "000000280191.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000280191.jpg", "height": 429, "width": 640, "date_captured": "2013-11-16 21:31:07", "flickr_url": "http://farm8.staticflickr.com/7450/8761820602_78d8831695_z.jpg", "id": 280191}, {"license": 4, "file_name": "000000444033.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000444033.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 01:48:44", "flickr_url": "http://farm9.staticflickr.com/8468/8410544710_22e3b7783d_z.jpg", "id": 444033}, {"license": 1, "file_name": "000000444036.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000444036.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 19:43:51", "flickr_url": "http://farm3.staticflickr.com/2009/2106822996_cb2a413b6a_z.jpg", "id": 444036}, {"license": 4, "file_name": "000000452229.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000452229.jpg", "height": 426, "width": 640, "date_captured": "2013-11-25 19:35:12", "flickr_url": "http://farm7.staticflickr.com/6129/5969078587_d8a83dcac1_z.jpg", "id": 452229}, {"license": 4, "file_name": "000000198277.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000198277.jpg", "height": 612, "width": 612, "date_captured": "2013-11-18 05:15:32", "flickr_url": "http://farm8.staticflickr.com/7079/7160667672_d2f5548fee_z.jpg", "id": 198277}, {"license": 3, "file_name": "000000427654.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000427654.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 19:52:30", "flickr_url": "http://farm9.staticflickr.com/8227/8573027781_f2a0c1a32a_z.jpg", "id": 427654}, {"license": 7, "file_name": "000000132746.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000132746.jpg", "height": 454, "width": 640, "date_captured": "2013-11-16 05:53:54", "flickr_url": "http://farm9.staticflickr.com/8249/8617752810_c9578b0ecf_z.jpg", "id": 132746}, {"license": 3, "file_name": "000000534155.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000534155.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 12:14:12", "flickr_url": "http://farm4.staticflickr.com/3677/9027257300_7016bce81a_z.jpg", "id": 534155}, {"license": 3, "file_name": "000000083605.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083605.jpg", "height": 600, "width": 400, "date_captured": "2013-11-20 05:33:26", "flickr_url": "http://farm5.staticflickr.com/4041/4688261816_80d5656b19_z.jpg", "id": 83605}, {"license": 1, "file_name": "000000485014.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000485014.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:22:17", "flickr_url": "http://farm1.staticflickr.com/231/501339766_b8ff45f22a_z.jpg", "id": 485014}, {"license": 4, "file_name": "000000124569.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000124569.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 07:29:30", "flickr_url": "http://farm4.staticflickr.com/3352/3579293014_83e90f61fb_z.jpg", "id": 124569}, {"license": 3, "file_name": "000000411289.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000411289.jpg", "height": 360, "width": 640, "date_captured": "2013-11-17 02:15:23", "flickr_url": "http://farm9.staticflickr.com/8497/8309392445_2a49b6bd89_z.jpg", "id": 411289}, {"license": 4, "file_name": "000000280228.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000280228.jpg", "height": 319, "width": 480, "date_captured": "2013-11-15 13:58:20", "flickr_url": "http://farm1.staticflickr.com/123/362075383_389976d3cb_z.jpg", "id": 280228}, {"license": 1, "file_name": "000000181929.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000181929.jpg", "height": 426, "width": 640, "date_captured": "2013-11-24 06:00:27", "flickr_url": "http://farm9.staticflickr.com/8353/8326947948_fdce3e332c_z.jpg", "id": 181929}, {"license": 3, "file_name": "000000018093.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000018093.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 10:42:04", "flickr_url": "http://farm4.staticflickr.com/3004/2802287399_57d99740dc_z.jpg", "id": 18093}, {"license": 2, "file_name": "000000321209.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000321209.jpg", "height": 326, "width": 500, "date_captured": "2013-11-14 12:31:22", "flickr_url": "http://farm3.staticflickr.com/2354/2088022281_db1ed5b2c1_z.jpg", "id": 321209}, {"license": 5, "file_name": "000000083641.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083641.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 16:13:45", "flickr_url": "http://farm1.staticflickr.com/79/278778556_265bc2e8b9_z.jpg", "id": 83641}, {"license": 1, "file_name": "000000149180.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000149180.jpg", "height": 360, "width": 640, "date_captured": "2013-11-18 13:39:13", "flickr_url": "http://farm5.staticflickr.com/4136/4931750629_7a53c38531_z.jpg", "id": 149180}, {"license": 3, "file_name": "000000100034.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100034.jpg", "height": 628, "width": 640, "date_captured": "2013-11-21 04:55:52", "flickr_url": "http://farm2.staticflickr.com/1275/5190617934_5ec028c202_z.jpg", "id": 100034}, {"license": 5, "file_name": "000000149202.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000149202.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 16:34:45", "flickr_url": "http://farm5.staticflickr.com/4071/4589834910_541cc220d9_z.jpg", "id": 149202}, {"license": 3, "file_name": "000000558804.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000558804.jpg", "height": 494, "width": 640, "date_captured": "2013-11-23 01:20:33", "flickr_url": "http://farm4.staticflickr.com/3329/5818354248_8105a192fc_z.jpg", "id": 558804}, {"license": 1, "file_name": "000000337621.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000337621.jpg", "height": 264, "width": 640, "date_captured": "2013-11-17 03:23:51", "flickr_url": "http://farm1.staticflickr.com/173/453333536_5a96180f39_z.jpg", "id": 337621}, {"license": 2, "file_name": "000000558824.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000558824.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 12:42:55", "flickr_url": "http://farm9.staticflickr.com/8373/8538840419_8b9627d4b4_z.jpg", "id": 558824}, {"license": 3, "file_name": "000000542442.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000542442.jpg", "height": 321, "width": 500, "date_captured": "2013-11-18 04:22:40", "flickr_url": "http://farm5.staticflickr.com/4002/4388038953_2c6c080d0f_z.jpg", "id": 542442}, {"license": 1, "file_name": "000000501493.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000501493.jpg", "height": 250, "width": 640, "date_captured": "2013-11-18 04:01:17", "flickr_url": "http://farm8.staticflickr.com/7334/9882133354_f734421a8e_z.jpg", "id": 501493}, {"license": 1, "file_name": "000000222977.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000222977.jpg", "height": 439, "width": 640, "date_captured": "2013-11-19 23:39:39", "flickr_url": "http://farm5.staticflickr.com/4133/4831314319_f2155a9893_z.jpg", "id": 222977}, {"license": 1, "file_name": "000000313091.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313091.jpg", "height": 532, "width": 640, "date_captured": "2013-11-16 18:12:03", "flickr_url": "http://farm6.staticflickr.com/5252/5508248367_0c304b5e9a_z.jpg", "id": 313091}, {"license": 5, "file_name": "000000395013.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000395013.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 20:16:25", "flickr_url": "http://farm8.staticflickr.com/7078/7284940092_55480c8eb3_z.jpg", "id": 395013}, {"license": 3, "file_name": "000000124694.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000124694.jpg", "height": 496, "width": 640, "date_captured": "2013-11-16 20:43:57", "flickr_url": "http://farm9.staticflickr.com/8329/8357273489_acfbbfcf32_z.jpg", "id": 124694}, {"license": 4, "file_name": "000000132889.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000132889.jpg", "height": 428, "width": 640, "date_captured": "2013-11-23 03:09:59", "flickr_url": "http://farm5.staticflickr.com/4001/4341588196_b06d6e84ce_z.jpg", "id": 132889}, {"license": 1, "file_name": "000000345882.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000345882.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 22:46:37", "flickr_url": "http://farm3.staticflickr.com/2008/4509260706_686d3f9abc_z.jpg", "id": 345882}, {"license": 5, "file_name": "000000272155.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000272155.jpg", "height": 352, "width": 500, "date_captured": "2013-11-15 18:19:02", "flickr_url": "http://farm1.staticflickr.com/61/202619841_1544566502_z.jpg", "id": 272155}, {"license": 3, "file_name": "000000067356.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000067356.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 15:51:51", "flickr_url": "http://farm6.staticflickr.com/5094/5520121593_44a1a4aac4_z.jpg", "id": 67356}, {"license": 1, "file_name": "000000427805.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000427805.jpg", "height": 612, "width": 612, "date_captured": "2013-11-24 18:47:11", "flickr_url": "http://farm8.staticflickr.com/7234/7173814495_e663dd3e51_z.jpg", "id": 427805}, {"license": 5, "file_name": "000000329502.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000329502.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 14:12:14", "flickr_url": "http://farm4.staticflickr.com/3081/2591654178_419653a9a8_z.jpg", "id": 329502}, {"license": 4, "file_name": "000000370461.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000370461.jpg", "height": 401, "width": 640, "date_captured": "2013-11-18 19:21:52", "flickr_url": "http://farm3.staticflickr.com/2548/3801544010_e2c89cd25b_z.jpg", "id": 370461}, {"license": 1, "file_name": "000000091933.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000091933.jpg", "height": 640, "width": 426, "date_captured": "2013-11-16 20:35:26", "flickr_url": "http://farm3.staticflickr.com/2699/4439197156_dd392d04c5_z.jpg", "id": 91933}, {"license": 3, "file_name": "000000517920.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000517920.jpg", "height": 640, "width": 427, "date_captured": "2013-11-17 11:10:48", "flickr_url": "http://farm1.staticflickr.com/154/435809936_2c4420a0cc_z.jpg", "id": 517920}, {"license": 1, "file_name": "000000223023.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000223023.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 04:36:54", "flickr_url": "http://farm6.staticflickr.com/5022/5621453800_8b1253d473_z.jpg", "id": 223023}, {"license": 3, "file_name": "000000509746.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000509746.jpg", "height": 531, "width": 640, "date_captured": "2013-11-18 03:12:45", "flickr_url": "http://farm7.staticflickr.com/6038/6247473577_45cd0d0059_z.jpg", "id": 509746}, {"license": 3, "file_name": "000000485173.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000485173.jpg", "height": 479, "width": 640, "date_captured": "2013-11-15 21:27:50", "flickr_url": "http://farm1.staticflickr.com/229/521703180_9c716d7226_z.jpg", "id": 485173}, {"license": 2, "file_name": "000000026421.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000026421.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 18:53:52", "flickr_url": "http://farm2.staticflickr.com/1213/4726134596_2223a703c3_z.jpg", "id": 26421}, {"license": 2, "file_name": "000000296760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000296760.jpg", "height": 400, "width": 500, "date_captured": "2013-11-20 20:39:33", "flickr_url": "http://farm4.staticflickr.com/3010/2623844239_a5b003cd92_z.jpg", "id": 296760}, {"license": 4, "file_name": "000000436025.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000436025.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:20:53", "flickr_url": "http://farm2.staticflickr.com/1203/543696514_e1ccb44491_z.jpg", "id": 436025}, {"license": 3, "file_name": "000000141121.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141121.jpg", "height": 311, "width": 500, "date_captured": "2013-11-20 04:06:43", "flickr_url": "http://farm5.staticflickr.com/4052/4416558059_c43fdc92ae_z.jpg", "id": 141121}, {"license": 1, "file_name": "000000329543.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000329543.jpg", "height": 459, "width": 640, "date_captured": "2013-11-14 22:12:13", "flickr_url": "http://farm8.staticflickr.com/7051/7068077909_c36070b42f_z.jpg", "id": 329543}, {"license": 2, "file_name": "000000264016.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000264016.jpg", "height": 332, "width": 500, "date_captured": "2013-11-24 22:04:20", "flickr_url": "http://farm1.staticflickr.com/104/282254758_17eba162d0_z.jpg", "id": 264016}, {"license": 1, "file_name": "000000517985.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000517985.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 21:35:19", "flickr_url": "http://farm6.staticflickr.com/5207/5378593030_20bfd516da_z.jpg", "id": 517985}, {"license": 6, "file_name": "000000313186.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313186.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 15:13:09", "flickr_url": "http://farm8.staticflickr.com/7023/6581521641_36c8e2e296_z.jpg", "id": 313186}, {"license": 1, "file_name": "000000075621.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000075621.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 21:27:30", "flickr_url": "http://farm3.staticflickr.com/2814/9216432747_d44a16cf28_z.jpg", "id": 75621}, {"license": 1, "file_name": "000000550760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000550760.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 20:20:08", "flickr_url": "http://farm7.staticflickr.com/6044/6301505016_6e27121ce9_z.jpg", "id": 550760}, {"license": 4, "file_name": "000000124786.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000124786.jpg", "height": 640, "width": 478, "date_captured": "2013-11-16 22:33:06", "flickr_url": "http://farm8.staticflickr.com/7312/9561931061_ca6d5c6a84_z.jpg", "id": 124786}, {"license": 3, "file_name": "000000034680.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000034680.jpg", "height": 291, "width": 640, "date_captured": "2013-11-18 16:18:01", "flickr_url": "http://farm4.staticflickr.com/3625/3562202168_34d30c3d8d_z.jpg", "id": 34680}, {"license": 2, "file_name": "000000313209.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313209.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 07:45:58", "flickr_url": "http://farm1.staticflickr.com/90/279238792_dddaad71e7_z.jpg", "id": 313209}, {"license": 4, "file_name": "000000264058.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000264058.jpg", "height": 400, "width": 640, "date_captured": "2013-11-20 21:41:49", "flickr_url": "http://farm9.staticflickr.com/8293/7745444350_b584cf99d6_z.jpg", "id": 264058}, {"license": 4, "file_name": "000000345981.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000345981.jpg", "height": 640, "width": 480, "date_captured": "2013-11-19 19:45:30", "flickr_url": "http://farm9.staticflickr.com/8123/8656838024_c5da7a9eb3_z.jpg", "id": 345981}, {"license": 3, "file_name": "000000419714.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000419714.jpg", "height": 448, "width": 500, "date_captured": "2013-11-18 20:57:37", "flickr_url": "http://farm1.staticflickr.com/62/197284431_5bbef9aa95_z.jpg", "id": 419714}, {"license": 1, "file_name": "000000329616.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000329616.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:45:14", "flickr_url": "http://farm3.staticflickr.com/2509/3932265738_8ea40af323_z.jpg", "id": 329616}, {"license": 1, "file_name": "000000337808.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000337808.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 00:08:34", "flickr_url": "http://farm6.staticflickr.com/5218/5530064355_2d4e919804_z.jpg", "id": 337808}, {"license": 3, "file_name": "000000141207.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141207.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 15:36:13", "flickr_url": "http://farm9.staticflickr.com/8212/8277019017_cf2ff3c6e1_z.jpg", "id": 141207}, {"license": 3, "file_name": "000000378791.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000378791.jpg", "height": 500, "width": 359, "date_captured": "2013-11-17 01:52:59", "flickr_url": "http://farm1.staticflickr.com/51/143425112_e0f45b0640_z.jpg", "id": 378791}, {"license": 1, "file_name": "000000346026.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000346026.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 14:15:42", "flickr_url": "http://farm8.staticflickr.com/7030/6632918007_b0de83581e_z.jpg", "id": 346026}, {"license": 1, "file_name": "000000034739.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000034739.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 02:52:47", "flickr_url": "http://farm4.staticflickr.com/3544/3419565872_c44d40b95c_z.jpg", "id": 34739}, {"license": 4, "file_name": "000000444344.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000444344.jpg", "height": 360, "width": 640, "date_captured": "2013-11-14 16:46:28", "flickr_url": "http://farm5.staticflickr.com/4081/4929208140_4f26f427a0_z.jpg", "id": 444344}, {"license": 1, "file_name": "000000444346.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000444346.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 12:15:11", "flickr_url": "http://farm1.staticflickr.com/230/499938318_cdadac6a73_z.jpg", "id": 444346}, {"license": 4, "file_name": "000000223165.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000223165.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 14:27:03", "flickr_url": "http://farm8.staticflickr.com/7279/8153872946_fe17ccf772_z.jpg", "id": 223165}, {"license": 6, "file_name": "000000001994.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000001994.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 19:26:01", "flickr_url": "http://farm9.staticflickr.com/8313/8011709650_e73f9c1d3d_z.jpg", "id": 1994}, {"license": 1, "file_name": "000000108499.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000108499.jpg", "height": 444, "width": 640, "date_captured": "2013-11-19 19:13:35", "flickr_url": "http://farm3.staticflickr.com/2040/3528451824_fbd289984e_z.jpg", "id": 108499}, {"license": 3, "file_name": "000000452565.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000452565.jpg", "height": 640, "width": 640, "date_captured": "2013-11-24 04:48:10", "flickr_url": "http://farm7.staticflickr.com/6092/6869763388_91c61d2747_z.jpg", "id": 452565}, {"license": 4, "file_name": "000000100312.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100312.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 04:41:19", "flickr_url": "http://farm9.staticflickr.com/8508/8585682516_2a9af8ee5e_z.jpg", "id": 100312}, {"license": 1, "file_name": "000000509914.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000509914.jpg", "height": 428, "width": 640, "date_captured": "2013-11-15 17:03:55", "flickr_url": "http://farm8.staticflickr.com/7081/7262071994_f3e281b2ff_z.jpg", "id": 509914}, {"license": 3, "file_name": "000000239596.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000239596.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 15:33:24", "flickr_url": "http://farm7.staticflickr.com/6178/6145855238_1326978b11_z.jpg", "id": 239596}, {"license": 3, "file_name": "000000329724.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000329724.jpg", "height": 640, "width": 427, "date_captured": "2013-11-21 01:56:43", "flickr_url": "http://farm9.staticflickr.com/8209/8230615386_00bf3b5213_z.jpg", "id": 329724}, {"license": 3, "file_name": "000000083968.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000083968.jpg", "height": 323, "width": 640, "date_captured": "2013-11-22 02:21:25", "flickr_url": "http://farm3.staticflickr.com/2450/3590114920_bb7e715561_z.jpg", "id": 83968}, {"license": 3, "file_name": "000000321539.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000321539.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 01:02:22", "flickr_url": "http://farm5.staticflickr.com/4087/5100398292_4a722e40a2_z.jpg", "id": 321539}, {"license": 3, "file_name": "000000411653.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000411653.jpg", "height": 484, "width": 500, "date_captured": "2013-11-24 22:06:41", "flickr_url": "http://farm1.staticflickr.com/8/7513320_55d5f918fa_z.jpg", "id": 411653}, {"license": 1, "file_name": "000000501773.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000501773.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 02:38:20", "flickr_url": "http://farm9.staticflickr.com/8040/7903529460_f4057ab3b7_z.jpg", "id": 501773}, {"license": 2, "file_name": "000000370727.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000370727.jpg", "height": 500, "width": 375, "date_captured": "2013-11-20 13:52:47", "flickr_url": "http://farm5.staticflickr.com/4022/4422991913_4bedff67cb_z.jpg", "id": 370727}, {"license": 4, "file_name": "000000018473.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000018473.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 16:13:48", "flickr_url": "http://farm9.staticflickr.com/8324/8381578539_6fb088c60a_z.jpg", "id": 18473}, {"license": 1, "file_name": "000000149556.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000149556.jpg", "height": 375, "width": 500, "date_captured": "2013-11-23 20:14:50", "flickr_url": "http://farm1.staticflickr.com/53/148134100_f5fbabd3dd_z.jpg", "id": 149556}, {"license": 1, "file_name": "000000297019.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000297019.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 20:53:49", "flickr_url": "http://farm4.staticflickr.com/3367/3493955094_dfbb22d7e6_z.jpg", "id": 297019}, {"license": 1, "file_name": "000000550972.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000550972.jpg", "height": 360, "width": 640, "date_captured": "2013-11-18 07:07:24", "flickr_url": "http://farm7.staticflickr.com/6082/6026101860_c086bf78f4_z.jpg", "id": 550972}, {"license": 4, "file_name": "000000075841.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000075841.jpg", "height": 640, "width": 392, "date_captured": "2013-11-21 01:49:59", "flickr_url": "http://farm4.staticflickr.com/3395/3201994265_713db37fac_z.jpg", "id": 75841}, {"license": 2, "file_name": "000000305219.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000305219.jpg", "height": 443, "width": 640, "date_captured": "2013-11-18 03:32:55", "flickr_url": "http://farm2.staticflickr.com/1227/798031535_32dfe88ec5_z.jpg", "id": 305219}, {"license": 1, "file_name": "000000510027.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000510027.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 22:17:38", "flickr_url": "http://farm1.staticflickr.com/196/443461402_0e917c0a4e_z.jpg", "id": 510027}, {"license": 1, "file_name": "000000354391.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000354391.jpg", "height": 640, "width": 383, "date_captured": "2013-11-18 03:45:53", "flickr_url": "http://farm6.staticflickr.com/5125/5307152352_edf7165498_z.jpg", "id": 354391}, {"license": 3, "file_name": "000000313437.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313437.jpg", "height": 640, "width": 640, "date_captured": "2013-11-16 22:06:52", "flickr_url": "http://farm8.staticflickr.com/7019/6493512011_52ca8c4154_z.jpg", "id": 313437}, {"license": 1, "file_name": "000000116832.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000116832.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 22:20:49", "flickr_url": "http://farm1.staticflickr.com/28/40438242_8433a7627b_z.jpg", "id": 116832}, {"license": 2, "file_name": "000000428149.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000428149.jpg", "height": 270, "width": 500, "date_captured": "2013-11-15 09:12:28", "flickr_url": "http://farm4.staticflickr.com/3027/2511380888_7da724dfde_z.jpg", "id": 428149}, {"license": 3, "file_name": "000000198785.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000198785.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 15:48:06", "flickr_url": "http://farm5.staticflickr.com/4120/4900725169_4fd49e4f76_z.jpg", "id": 198785}, {"license": 2, "file_name": "000000411778.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000411778.jpg", "height": 640, "width": 456, "date_captured": "2013-11-16 23:20:22", "flickr_url": "http://farm4.staticflickr.com/3389/3336417704_24b31f2eff_z.jpg", "id": 411778}, {"license": 3, "file_name": "000000100485.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100485.jpg", "height": 424, "width": 640, "date_captured": "2013-11-18 11:28:49", "flickr_url": "http://farm9.staticflickr.com/8541/8669667227_606cc6623f_z.jpg", "id": 100485}, {"license": 4, "file_name": "000000182406.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000182406.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:39:24", "flickr_url": "http://farm1.staticflickr.com/73/198080354_9f09e4e6cc_z.jpg", "id": 182406}, {"license": 1, "file_name": "000000493707.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000493707.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 04:30:22", "flickr_url": "http://farm6.staticflickr.com/5173/5515709138_6ddded84ed_z.jpg", "id": 493707}, {"license": 1, "file_name": "000000354444.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000354444.jpg", "height": 640, "width": 494, "date_captured": "2013-11-15 06:49:08", "flickr_url": "http://farm3.staticflickr.com/2723/4430135596_2ce9379f2a_z.jpg", "id": 354444}, {"license": 1, "file_name": "000000395425.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000395425.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 14:30:40", "flickr_url": "http://farm6.staticflickr.com/5350/6938511678_26d2203834_z.jpg", "id": 395425}, {"license": 1, "file_name": "000000362657.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000362657.jpg", "height": 640, "width": 424, "date_captured": "2013-11-17 10:43:04", "flickr_url": "http://farm1.staticflickr.com/211/463651418_cc1b0aee6b_z.jpg", "id": 362657}, {"license": 2, "file_name": "000000092323.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000092323.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 12:55:36", "flickr_url": "http://farm3.staticflickr.com/2324/2409607978_4cdb8812b4_z.jpg", "id": 92323}, {"license": 1, "file_name": "000000395432.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000395432.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 00:10:07", "flickr_url": "http://farm4.staticflickr.com/3272/2920113318_49f715dd4f_z.jpg", "id": 395432}, {"license": 1, "file_name": "000000493760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000493760.jpg", "height": 508, "width": 640, "date_captured": "2013-11-17 14:14:12", "flickr_url": "http://farm1.staticflickr.com/52/114273554_9de072cbb0_z.jpg", "id": 493760}, {"license": 5, "file_name": "000000084162.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000084162.jpg", "height": 360, "width": 640, "date_captured": "2013-11-18 03:35:10", "flickr_url": "http://farm4.staticflickr.com/3726/10131940315_e8b4e6602e_z.jpg", "id": 84162}, {"license": 1, "file_name": "000000387293.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000387293.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 00:20:32", "flickr_url": "http://farm4.staticflickr.com/3061/2864187576_0df3f49e3d_z.jpg", "id": 387293}, {"license": 4, "file_name": "000000223459.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000223459.jpg", "height": 524, "width": 640, "date_captured": "2013-11-16 14:10:51", "flickr_url": "http://farm9.staticflickr.com/8483/8247944445_55294d19c1_z.jpg", "id": 223459}, {"license": 4, "file_name": "000000559331.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000559331.jpg", "height": 500, "width": 371, "date_captured": "2013-11-20 08:04:34", "flickr_url": "http://farm4.staticflickr.com/3407/3521536501_03ddafe044_z.jpg", "id": 559331}, {"license": 4, "file_name": "000000321766.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000321766.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 17:08:59", "flickr_url": "http://farm9.staticflickr.com/8155/7672768196_da9c0ee2cc_z.jpg", "id": 321766}, {"license": 5, "file_name": "000000346344.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000346344.jpg", "height": 500, "width": 375, "date_captured": "2013-11-16 15:00:51", "flickr_url": "http://farm1.staticflickr.com/197/511517004_45f49fac1a_z.jpg", "id": 346344}, {"license": 3, "file_name": "000000067835.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000067835.jpg", "height": 512, "width": 640, "date_captured": "2013-11-19 23:10:20", "flickr_url": "http://farm4.staticflickr.com/3715/9192723340_c87fa1f680_z.jpg", "id": 67835}, {"license": 3, "file_name": "000000100611.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100611.jpg", "height": 640, "width": 480, "date_captured": "2013-11-23 04:27:59", "flickr_url": "http://farm4.staticflickr.com/3434/3747366463_f6d308ce30_z.jpg", "id": 100611}, {"license": 3, "file_name": "000000125193.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000125193.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 07:10:13", "flickr_url": "http://farm3.staticflickr.com/2600/3900638510_c48f796195_z.jpg", "id": 125193}, {"license": 4, "file_name": "000000190732.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000190732.jpg", "height": 337, "width": 504, "date_captured": "2013-11-20 20:48:50", "flickr_url": "http://farm9.staticflickr.com/8323/8110123858_5d9a9c31ee_z.jpg", "id": 190732}, {"license": 5, "file_name": "000000141581.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141581.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 06:51:54", "flickr_url": "http://farm4.staticflickr.com/3565/3280842586_20aaa0784e_z.jpg", "id": 141581}, {"license": 3, "file_name": "000000575768.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000575768.jpg", "height": 484, "width": 640, "date_captured": "2013-11-17 00:35:16", "flickr_url": "http://farm5.staticflickr.com/4083/4961547647_d75d5f03b0_z.jpg", "id": 575768}, {"license": 4, "file_name": "000000141603.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141603.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 15:40:41", "flickr_url": "http://farm3.staticflickr.com/2888/9016820354_32348cef65_z.jpg", "id": 141603}, {"license": 2, "file_name": "000000469293.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000469293.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 21:13:54", "flickr_url": "http://farm9.staticflickr.com/8090/8475698394_e70441a207_z.jpg", "id": 469293}, {"license": 3, "file_name": "000000100667.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100667.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 20:26:00", "flickr_url": "http://farm8.staticflickr.com/7240/7255200652_21d6ba8cf4_z.jpg", "id": 100667}, {"license": 4, "file_name": "000000338242.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000338242.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 21:08:02", "flickr_url": "http://farm4.staticflickr.com/3142/2936832895_d7d726be2f_z.jpg", "id": 338242}, {"license": 1, "file_name": "000000551244.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000551244.jpg", "height": 640, "width": 428, "date_captured": "2013-11-21 02:23:40", "flickr_url": "http://farm9.staticflickr.com/8027/7308973512_e14e4ab802_z.jpg", "id": 551244}, {"license": 4, "file_name": "000000002411.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000002411.jpg", "height": 478, "width": 640, "date_captured": "2013-11-20 22:45:15", "flickr_url": "http://farm9.staticflickr.com/8434/7840444748_4844e2a931_z.jpg", "id": 2411}, {"license": 3, "file_name": "000000133486.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000133486.jpg", "height": 640, "width": 427, "date_captured": "2013-11-14 22:42:22", "flickr_url": "http://farm8.staticflickr.com/7182/6900091413_6352223d92_z.jpg", "id": 133486}, {"license": 1, "file_name": "000000182642.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000182642.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 14:49:56", "flickr_url": "http://farm5.staticflickr.com/4121/4802774112_3593d1bcd0_z.jpg", "id": 182642}, {"license": 6, "file_name": "000000502134.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000502134.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 17:55:50", "flickr_url": "http://farm9.staticflickr.com/8488/8277035209_0ba20088a2_z.jpg", "id": 502134}, {"license": 4, "file_name": "000000428407.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000428407.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 18:20:10", "flickr_url": "http://farm4.staticflickr.com/3655/3619974019_7117d91a12_z.jpg", "id": 428407}, {"license": 2, "file_name": "000000526713.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000526713.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 12:22:59", "flickr_url": "http://farm6.staticflickr.com/5257/5473596427_6c0116a4ae_z.jpg", "id": 526713}, {"license": 4, "file_name": "000000313724.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313724.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 14:27:30", "flickr_url": "http://farm8.staticflickr.com/7038/6923938221_3a6ae47d7d_z.jpg", "id": 313724}, {"license": 2, "file_name": "000000018819.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000018819.jpg", "height": 425, "width": 640, "date_captured": "2013-11-15 06:35:04", "flickr_url": "http://farm5.staticflickr.com/4051/4713035049_7cf7f0e19a_z.jpg", "id": 18819}, {"license": 2, "file_name": "000000502153.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000502153.jpg", "height": 359, "width": 640, "date_captured": "2013-11-17 16:03:53", "flickr_url": "http://farm8.staticflickr.com/7254/6942410638_7ea87ef19f_z.jpg", "id": 502153}, {"license": 3, "file_name": "000000477580.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000477580.jpg", "height": 425, "width": 640, "date_captured": "2013-11-20 04:09:54", "flickr_url": "http://farm3.staticflickr.com/2268/5818094969_71170f81fb_z.jpg", "id": 477580}, {"license": 6, "file_name": "000000215436.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000215436.jpg", "height": 500, "width": 375, "date_captured": "2013-11-16 23:21:24", "flickr_url": "http://farm4.staticflickr.com/3174/2492637355_1b72b96aa3_z.jpg", "id": 215436}, {"license": 1, "file_name": "000000141711.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141711.jpg", "height": 512, "width": 640, "date_captured": "2013-11-20 06:09:43", "flickr_url": "http://farm4.staticflickr.com/3499/3886886719_8270dca9cd_z.jpg", "id": 141711}, {"license": 2, "file_name": "000000551316.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000551316.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 04:18:16", "flickr_url": "http://farm3.staticflickr.com/2706/4511463022_e2af379a28_z.jpg", "id": 551316}, {"license": 4, "file_name": "000000149921.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000149921.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 13:24:11", "flickr_url": "http://farm2.staticflickr.com/1363/1032822638_e6a92552a1_z.jpg", "id": 149921}, {"license": 3, "file_name": "000000100777.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100777.jpg", "height": 599, "width": 640, "date_captured": "2013-11-25 19:49:09", "flickr_url": "http://farm5.staticflickr.com/4018/5157844723_5bbe3322da_z.jpg", "id": 100777}, {"license": 1, "file_name": "000000371114.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000371114.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 19:24:12", "flickr_url": "http://farm1.staticflickr.com/60/157794643_5f4a3ea598_z.jpg", "id": 371114}, {"license": 4, "file_name": "000000182706.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000182706.jpg", "height": 428, "width": 640, "date_captured": "2013-11-19 00:50:45", "flickr_url": "http://farm4.staticflickr.com/3832/9469238922_ec2b7f3dff_z.jpg", "id": 182706}, {"license": 1, "file_name": "000000027070.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000027070.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 09:24:05", "flickr_url": "http://farm5.staticflickr.com/4071/4667238398_06cdcebb09_z.jpg", "id": 27070}, {"license": 5, "file_name": "000000346562.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000346562.jpg", "height": 385, "width": 640, "date_captured": "2013-11-16 20:25:22", "flickr_url": "http://farm6.staticflickr.com/5447/9617422325_3c44c6f228_z.jpg", "id": 346562}, {"license": 1, "file_name": "000000215493.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000215493.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 02:03:46", "flickr_url": "http://farm8.staticflickr.com/7404/8907542852_330112fcbf_z.jpg", "id": 215493}, {"license": 1, "file_name": "000000100812.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000100812.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 22:09:10", "flickr_url": "http://farm8.staticflickr.com/7239/7359107912_d31f0d967d_z.jpg", "id": 100812}, {"license": 4, "file_name": "000000305624.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000305624.jpg", "height": 351, "width": 640, "date_captured": "2013-11-16 14:05:55", "flickr_url": "http://farm9.staticflickr.com/8247/8610527967_65390aa76c_z.jpg", "id": 305624}, {"license": 2, "file_name": "000000158195.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000158195.jpg", "height": 640, "width": 428, "date_captured": "2013-11-22 03:01:15", "flickr_url": "http://farm5.staticflickr.com/4115/4947056379_53aa244b59_z.jpg", "id": 158195}, {"license": 5, "file_name": "000000035322.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000035322.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 20:44:25", "flickr_url": "http://farm9.staticflickr.com/8148/7006586012_4862671071_z.jpg", "id": 35322}, {"license": 3, "file_name": "000000092685.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000092685.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 08:53:57", "flickr_url": "http://farm6.staticflickr.com/5463/9155609020_89364f8515_z.jpg", "id": 92685}, {"license": 3, "file_name": "000000027149.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000027149.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 23:06:35", "flickr_url": "http://farm2.staticflickr.com/1403/869787213_1f7ea60a2f_z.jpg", "id": 27149}, {"license": 4, "file_name": "000000313873.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000313873.jpg", "height": 612, "width": 612, "date_captured": "2013-11-17 05:38:45", "flickr_url": "http://farm9.staticflickr.com/8147/6961324640_340ae06dd8_z.jpg", "id": 313873}, {"license": 2, "file_name": "000000215569.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000215569.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 20:28:31", "flickr_url": "http://farm3.staticflickr.com/2549/3682459597_455b827ae1_z.jpg", "id": 215569}, {"license": 5, "file_name": "000000043543.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000043543.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 13:29:01", "flickr_url": "http://farm4.staticflickr.com/3600/3301252329_4472a7776e_z.jpg", "id": 43543}, {"license": 2, "file_name": "000000412190.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000412190.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 22:17:14", "flickr_url": "http://farm1.staticflickr.com/106/290833278_5741ed6441_z.jpg", "id": 412190}, {"license": 4, "file_name": "000000109095.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000109095.jpg", "height": 478, "width": 640, "date_captured": "2013-11-17 05:10:06", "flickr_url": "http://farm9.staticflickr.com/8055/8419150229_bb8bdd5b5d_z.jpg", "id": 109095}, {"license": 1, "file_name": "000000412220.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000412220.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:22:06", "flickr_url": "http://farm8.staticflickr.com/7432/8724397550_024482c4d1_z.jpg", "id": 412220}, {"license": 2, "file_name": "000000436797.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000436797.jpg", "height": 478, "width": 640, "date_captured": "2013-11-16 17:54:15", "flickr_url": "http://farm8.staticflickr.com/7200/6925997162_30e66e8934_z.jpg", "id": 436797}, {"license": 1, "file_name": "000000322121.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000322121.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 18:02:40", "flickr_url": "http://farm3.staticflickr.com/2582/3758135075_39f059a017_z.jpg", "id": 322121}, {"license": 2, "file_name": "000000559700.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000559700.jpg", "height": 640, "width": 426, "date_captured": "2013-11-18 02:13:49", "flickr_url": "http://farm9.staticflickr.com/8064/8202671008_7e10bfd140_z.jpg", "id": 559700}, {"license": 4, "file_name": "000000223831.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000223831.jpg", "height": 386, "width": 500, "date_captured": "2013-11-24 05:06:22", "flickr_url": "http://farm2.staticflickr.com/1076/3166986512_312929eb54_z.jpg", "id": 223831}, {"license": 2, "file_name": "000000092760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000092760.jpg", "height": 333, "width": 500, "date_captured": "2013-11-20 12:01:19", "flickr_url": "http://farm4.staticflickr.com/3021/2757444023_d7a6c3d577_z.jpg", "id": 92760}, {"license": 5, "file_name": "000000043609.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000043609.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 16:21:55", "flickr_url": "http://farm2.staticflickr.com/1002/1053822021_53dcab6b7b_z.jpg", "id": 43609}, {"license": 1, "file_name": "000000240225.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240225.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:56:42", "flickr_url": "http://farm6.staticflickr.com/5348/10079006395_5e39f76280_z.jpg", "id": 240225}, {"license": 3, "file_name": "000000551524.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000551524.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 19:50:19", "flickr_url": "http://farm2.staticflickr.com/1215/5120491123_bc73f69b32_z.jpg", "id": 551524}, {"license": 4, "file_name": "000000174700.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000174700.jpg", "height": 478, "width": 640, "date_captured": "2013-11-18 10:32:26", "flickr_url": "http://farm8.staticflickr.com/7115/7700626264_1fe9b4cf20_z.jpg", "id": 174700}, {"license": 1, "file_name": "000000264821.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000264821.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 15:22:56", "flickr_url": "http://farm3.staticflickr.com/2691/4124463711_8740357650_z.jpg", "id": 264821}, {"license": 1, "file_name": "000000010870.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000010870.jpg", "height": 428, "width": 640, "date_captured": "2013-11-24 04:45:49", "flickr_url": "http://farm4.staticflickr.com/3591/3441466577_010868610d_z.jpg", "id": 10870}, {"license": 2, "file_name": "000000486014.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000486014.jpg", "height": 640, "width": 639, "date_captured": "2013-11-19 18:32:16", "flickr_url": "http://farm4.staticflickr.com/3210/2600912828_0718569366_z.jpg", "id": 486014}, {"license": 3, "file_name": "000000141952.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000141952.jpg", "height": 500, "width": 375, "date_captured": "2013-11-20 15:04:07", "flickr_url": "http://farm4.staticflickr.com/3138/3641107328_9b24767136_z.jpg", "id": 141952}, {"license": 1, "file_name": "000000551553.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000551553.jpg", "height": 268, "width": 480, "date_captured": "2013-11-15 21:29:05", "flickr_url": "http://farm8.staticflickr.com/7146/6629382795_c46b0e8b07_z.jpg", "id": 551553}, {"license": 2, "file_name": "000000043655.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000043655.jpg", "height": 383, "width": 640, "date_captured": "2013-11-17 20:32:43", "flickr_url": "http://farm5.staticflickr.com/4096/4914084872_6002cbc5d0_z.jpg", "id": 43655}, {"license": 3, "file_name": "000000051851.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000051851.jpg", "height": 431, "width": 640, "date_captured": "2013-11-15 06:02:13", "flickr_url": "http://farm5.staticflickr.com/4015/4649668091_d357aebdfa_z.jpg", "id": 51851}, {"license": 3, "file_name": "000000289425.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000289425.jpg", "height": 492, "width": 640, "date_captured": "2013-11-23 00:23:48", "flickr_url": "http://farm9.staticflickr.com/8262/8711345525_07709673c6_z.jpg", "id": 289425}, {"license": 5, "file_name": "000000510611.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000510611.jpg", "height": 500, "width": 375, "date_captured": "2013-11-17 00:57:54", "flickr_url": "http://farm3.staticflickr.com/2037/2234832210_feb2fc0552_z.jpg", "id": 510611}, {"license": 4, "file_name": "000000174749.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000174749.jpg", "height": 428, "width": 640, "date_captured": "2013-11-14 20:09:20", "flickr_url": "http://farm9.staticflickr.com/8201/8248734308_c6205d9a54_z.jpg", "id": 174749}, {"license": 4, "file_name": "000000371361.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000371361.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 22:24:27", "flickr_url": "http://farm6.staticflickr.com/5058/5505457649_ed49002365_z.jpg", "id": 371361}, {"license": 3, "file_name": "000000199331.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000199331.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 23:44:27", "flickr_url": "http://farm8.staticflickr.com/7154/6832556749_00f1d2b4d7_z.jpg", "id": 199331}, {"license": 3, "file_name": "000000404139.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000404139.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 17:50:03", "flickr_url": "http://farm4.staticflickr.com/3032/3075831233_a4e4a1d3ac_z.jpg", "id": 404139}, {"license": 1, "file_name": "000000494257.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000494257.jpg", "height": 375, "width": 500, "date_captured": "2013-11-21 01:38:24", "flickr_url": "http://farm1.staticflickr.com/80/258184422_cd0c281a27_z.jpg", "id": 494257}, {"license": 5, "file_name": "000000174774.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000174774.jpg", "height": 427, "width": 640, "date_captured": "2013-11-22 00:41:01", "flickr_url": "http://farm5.staticflickr.com/4040/4346100432_17bb736b45_z.jpg", "id": 174774}, {"license": 1, "file_name": "000000461494.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000461494.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 19:25:04", "flickr_url": "http://farm3.staticflickr.com/2840/10103250954_ac5d559750_z.jpg", "id": 461494}, {"license": 1, "file_name": "000000363190.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000363190.jpg", "height": 423, "width": 640, "date_captured": "2013-11-14 21:28:04", "flickr_url": "http://farm9.staticflickr.com/8018/7540757108_36cc3d3c5d_z.jpg", "id": 363190}, {"license": 1, "file_name": "000000207543.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000207543.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 04:18:08", "flickr_url": "http://farm6.staticflickr.com/5066/5657162447_d1838704a9_z.jpg", "id": 207543}, {"license": 5, "file_name": "000000142014.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000142014.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 23:09:40", "flickr_url": "http://farm1.staticflickr.com/56/150748594_3427488af8_z.jpg", "id": 142014}, {"license": 6, "file_name": "000000371392.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000371392.jpg", "height": 378, "width": 640, "date_captured": "2013-11-18 03:33:05", "flickr_url": "http://farm6.staticflickr.com/5215/5496153305_0e18432a97_z.jpg", "id": 371392}, {"license": 2, "file_name": "000000535234.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000535234.jpg", "height": 357, "width": 500, "date_captured": "2013-11-19 17:59:21", "flickr_url": "http://farm4.staticflickr.com/3342/3643666111_d4019e6c99_z.jpg", "id": 535234}, {"license": 1, "file_name": "000000445127.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000445127.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 01:31:53", "flickr_url": "http://farm5.staticflickr.com/4108/5437766760_5b648d43f6_z.jpg", "id": 445127}, {"license": 1, "file_name": "000000436941.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000436941.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 17:08:41", "flickr_url": "http://farm8.staticflickr.com/7331/8794840965_f38c1cdff8_z.jpg", "id": 436941}, {"license": 1, "file_name": "000000068305.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000068305.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 02:12:11", "flickr_url": "http://farm9.staticflickr.com/8239/8636588934_d8b2be8700_z.jpg", "id": 68305}, {"license": 6, "file_name": "000000125658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000125658.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 20:24:55", "flickr_url": "http://farm4.staticflickr.com/3701/9629585215_f8026e0c73_z.jpg", "id": 125658}, {"license": 3, "file_name": "000000183022.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000183022.jpg", "height": 420, "width": 640, "date_captured": "2013-11-16 01:57:36", "flickr_url": "http://farm8.staticflickr.com/7139/6941525384_9a893eda8e_z.jpg", "id": 183022}, {"license": 1, "file_name": "000000346876.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000346876.jpg", "height": 361, "width": 640, "date_captured": "2013-11-19 22:55:02", "flickr_url": "http://farm6.staticflickr.com/5133/5523071905_63e4726c39_z.jpg", "id": 346876}, {"license": 3, "file_name": "000000051965.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000051965.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 16:02:03", "flickr_url": "http://farm4.staticflickr.com/3721/9090126933_7397b1d3a5_z.jpg", "id": 51965}, {"license": 1, "file_name": "000000396042.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000396042.jpg", "height": 500, "width": 375, "date_captured": "2013-11-17 19:47:11", "flickr_url": "http://farm2.staticflickr.com/1160/871379369_2f6d0ec3b2_z.jpg", "id": 396042}, {"license": 3, "file_name": "000000101140.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000101140.jpg", "height": 333, "width": 500, "date_captured": "2013-11-15 10:21:56", "flickr_url": "http://farm3.staticflickr.com/2190/1589782798_04533433f6_z.jpg", "id": 101140}, {"license": 1, "file_name": "000000330516.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000330516.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 21:10:56", "flickr_url": "http://farm1.staticflickr.com/87/221729263_04573f904c_z.jpg", "id": 330516}, {"license": 1, "file_name": "000000174876.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000174876.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 22:49:36", "flickr_url": "http://farm8.staticflickr.com/7164/6844313317_3192603382_z.jpg", "id": 174876}, {"license": 2, "file_name": "000000092957.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000092957.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 21:07:50", "flickr_url": "http://farm8.staticflickr.com/7018/6676987315_d192bc01e6_z.jpg", "id": 92957}, {"license": 2, "file_name": "000000174892.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000174892.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 18:21:32", "flickr_url": "http://farm1.staticflickr.com/176/404597922_568ec6d9b9_z.jpg", "id": 174892}, {"license": 3, "file_name": "000000486193.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000486193.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 21:31:43", "flickr_url": "http://farm8.staticflickr.com/7029/6738507925_15e0ea6d64_z.jpg", "id": 486193}, {"license": 3, "file_name": "000000092988.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000092988.jpg", "height": 640, "width": 427, "date_captured": "2013-11-24 15:10:09", "flickr_url": "http://farm9.staticflickr.com/8057/8228431368_b0c0163a4c_z.jpg", "id": 92988}, {"license": 3, "file_name": "000000199485.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000199485.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 04:56:34", "flickr_url": "http://farm9.staticflickr.com/8214/8301238568_753c6ab993_z.jpg", "id": 199485}, {"license": 1, "file_name": "000000535358.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000535358.jpg", "height": 557, "width": 640, "date_captured": "2013-11-18 20:52:59", "flickr_url": "http://farm4.staticflickr.com/3825/8752711148_5c44fc83c1_z.jpg", "id": 535358}, {"license": 3, "file_name": "000000363331.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000363331.jpg", "height": 497, "width": 640, "date_captured": "2013-11-18 01:00:57", "flickr_url": "http://farm9.staticflickr.com/8026/7563092158_ee059975b8_z.jpg", "id": 363331}, {"license": 5, "file_name": "000000232263.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000232263.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 18:44:05", "flickr_url": "http://farm9.staticflickr.com/8229/8516059797_c6022b0302_z.jpg", "id": 232263}, {"license": 3, "file_name": "000000002892.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000002892.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 15:24:08", "flickr_url": "http://farm4.staticflickr.com/3546/3791886894_a48c569040_z.jpg", "id": 2892}, {"license": 4, "file_name": "000000125774.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000125774.jpg", "height": 640, "width": 611, "date_captured": "2013-11-22 17:43:09", "flickr_url": "http://farm4.staticflickr.com/3087/3190056364_a82d6b4ed4_z.jpg", "id": 125774}, {"license": 4, "file_name": "000000068430.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000068430.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 01:29:43", "flickr_url": "http://farm5.staticflickr.com/4152/5180562425_cfc9daf3f6_z.jpg", "id": 68430}, {"license": 4, "file_name": "000000453475.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000453475.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 21:45:58", "flickr_url": "http://farm3.staticflickr.com/2734/4431222049_26b632746a_z.jpg", "id": 453475}, {"license": 3, "file_name": "000000215908.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000215908.jpg", "height": 500, "width": 367, "date_captured": "2013-11-24 05:28:19", "flickr_url": "http://farm4.staticflickr.com/3167/2461039158_3afe33835d_z.jpg", "id": 215908}, {"license": 1, "file_name": "000000166762.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000166762.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 00:48:10", "flickr_url": "http://farm4.staticflickr.com/3102/2468756993_5860c90400_z.jpg", "id": 166762}, {"license": 3, "file_name": "000000322411.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000322411.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 21:11:43", "flickr_url": "http://farm3.staticflickr.com/2188/2491369482_64a0006988_z.jpg", "id": 322411}, {"license": 4, "file_name": "000000240500.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240500.jpg", "height": 640, "width": 618, "date_captured": "2013-11-16 14:21:24", "flickr_url": "http://farm4.staticflickr.com/3025/3057727948_fc877e4194_z.jpg", "id": 240500}, {"license": 4, "file_name": "000000281464.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000281464.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:28:17", "flickr_url": "http://farm6.staticflickr.com/5506/9770420026_8957558f9c_z.jpg", "id": 281464}, {"license": 4, "file_name": "000000535418.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000535418.jpg", "height": 481, "width": 640, "date_captured": "2013-11-18 12:54:32", "flickr_url": "http://farm8.staticflickr.com/7402/9608106312_f8b8722cbe_z.jpg", "id": 535418}, {"license": 5, "file_name": "000000568187.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000568187.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 10:52:54", "flickr_url": "http://farm5.staticflickr.com/4027/4377663947_4632f4f029_z.jpg", "id": 568187}, {"license": 5, "file_name": "000000338819.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000338819.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:10:03", "flickr_url": "http://farm8.staticflickr.com/7164/6673723427_2271940d49_z.jpg", "id": 338819}, {"license": 5, "file_name": "000000240521.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240521.jpg", "height": 640, "width": 424, "date_captured": "2013-11-18 04:27:33", "flickr_url": "http://farm3.staticflickr.com/2652/4143803573_a1ba500632_z.jpg", "id": 240521}, {"license": 4, "file_name": "000000445323.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000445323.jpg", "height": 390, "width": 640, "date_captured": "2013-11-18 00:49:22", "flickr_url": "http://farm8.staticflickr.com/7041/7017611799_88fc00eefb_z.jpg", "id": 445323}, {"license": 4, "file_name": "000000142225.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000142225.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 03:20:19", "flickr_url": "http://farm8.staticflickr.com/7098/7401540270_933c3897cc_z.jpg", "id": 142225}, {"license": 4, "file_name": "000000543642.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000543642.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 08:54:44", "flickr_url": "http://farm4.staticflickr.com/3549/3393849274_bd1146d7da_z.jpg", "id": 543642}, {"license": 3, "file_name": "000000527267.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000527267.jpg", "height": 640, "width": 426, "date_captured": "2013-11-19 21:04:39", "flickr_url": "http://farm5.staticflickr.com/4017/4717776000_a259d27505_z.jpg", "id": 527267}, {"license": 3, "file_name": "000000551869.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000551869.jpg", "height": 240, "width": 320, "date_captured": "2013-11-19 21:49:09", "flickr_url": "http://farm3.staticflickr.com/2579/3683617384_c40a8ffdca_z.jpg", "id": 551869}, {"license": 6, "file_name": "000000543678.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000543678.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 11:16:25", "flickr_url": "http://farm4.staticflickr.com/3195/2895311403_bc95704c68_z.jpg", "id": 543678}, {"license": 2, "file_name": "000000183236.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000183236.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 00:49:16", "flickr_url": "http://farm4.staticflickr.com/3263/2580978375_43b4ef0fd8_z.jpg", "id": 183236}, {"license": 2, "file_name": "000000256965.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000256965.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 14:27:25", "flickr_url": "http://farm8.staticflickr.com/7030/6834096625_7ebcc38190_z.jpg", "id": 256965}, {"license": 3, "file_name": "000000314319.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000314319.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 09:50:38", "flickr_url": "http://farm9.staticflickr.com/8012/6961015092_6c7aed7684_z.jpg", "id": 314319}, {"license": 5, "file_name": "000000420823.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000420823.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 06:32:28", "flickr_url": "http://farm9.staticflickr.com/8240/8654066718_0406e0e792_z.jpg", "id": 420823}, {"license": 4, "file_name": "000000330716.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000330716.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 18:46:51", "flickr_url": "http://farm8.staticflickr.com/7243/7170308897_c4564a06c3_z.jpg", "id": 330716}, {"license": 3, "file_name": "000000158686.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000158686.jpg", "height": 408, "width": 640, "date_captured": "2013-11-19 20:58:22", "flickr_url": "http://farm7.staticflickr.com/6052/6379459755_1b10073429_z.jpg", "id": 158686}, {"license": 4, "file_name": "000000437224.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000437224.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 12:23:24", "flickr_url": "http://farm4.staticflickr.com/3125/3235845341_2036d5d0fc_z.jpg", "id": 437224}, {"license": 3, "file_name": "000000527345.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000527345.jpg", "height": 640, "width": 640, "date_captured": "2013-11-25 08:32:00", "flickr_url": "http://farm3.staticflickr.com/2831/9333204182_e8ee9f2f37_z.jpg", "id": 527345}, {"license": 2, "file_name": "000000510976.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000510976.jpg", "height": 390, "width": 640, "date_captured": "2013-11-24 04:36:21", "flickr_url": "http://farm1.staticflickr.com/38/87047294_bdf85f8a64_z.jpg", "id": 510976}, {"license": 6, "file_name": "000000076802.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000076802.jpg", "height": 427, "width": 640, "date_captured": "2013-11-22 00:30:00", "flickr_url": "http://farm4.staticflickr.com/3409/4621458922_b0c650247e_z.jpg", "id": 76802}, {"license": 3, "file_name": "000000429059.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000429059.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 20:04:40", "flickr_url": "http://farm6.staticflickr.com/5248/5351750748_7aecb0d855_z.jpg", "id": 429059}, {"license": 1, "file_name": "000000175116.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000175116.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 20:16:28", "flickr_url": "http://farm3.staticflickr.com/2641/3846284144_965762ac40_z.jpg", "id": 175116}, {"license": 1, "file_name": "000000355345.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000355345.jpg", "height": 640, "width": 478, "date_captured": "2013-11-18 08:21:50", "flickr_url": "http://farm3.staticflickr.com/2867/9261653540_eebf3671ef_z.jpg", "id": 355345}, {"license": 6, "file_name": "000000011282.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000011282.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 15:00:36", "flickr_url": "http://farm5.staticflickr.com/4039/4646102624_c7b849c3c0_z.jpg", "id": 11282}, {"license": 3, "file_name": "000000265235.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000265235.jpg", "height": 383, "width": 640, "date_captured": "2013-11-19 18:05:34", "flickr_url": "http://farm4.staticflickr.com/3146/5843292964_e20d438d3b_z.jpg", "id": 265235}, {"license": 1, "file_name": "000000298014.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298014.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 14:33:29", "flickr_url": "http://farm3.staticflickr.com/2281/2449876080_192bdf6fed_z.jpg", "id": 298014}, {"license": 2, "file_name": "000000027679.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000027679.jpg", "height": 480, "width": 640, "date_captured": "2013-11-23 04:50:00", "flickr_url": "http://farm4.staticflickr.com/3640/3551492300_769f2c0209_z.jpg", "id": 27679}, {"license": 3, "file_name": "000000273439.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000273439.jpg", "height": 432, "width": 640, "date_captured": "2013-11-16 20:19:18", "flickr_url": "http://farm4.staticflickr.com/3735/9629769269_626662410e_z.jpg", "id": 273439}, {"license": 5, "file_name": "000000330785.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000330785.jpg", "height": 640, "width": 534, "date_captured": "2013-11-24 03:24:38", "flickr_url": "http://farm2.staticflickr.com/1025/1085930479_be9e746e97_z.jpg", "id": 330785}, {"license": 5, "file_name": "000000298017.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298017.jpg", "height": 500, "width": 375, "date_captured": "2013-11-14 12:41:07", "flickr_url": "http://farm1.staticflickr.com/80/247156354_480efc548c_z.jpg", "id": 298017}, {"license": 3, "file_name": "000000175142.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000175142.jpg", "height": 333, "width": 500, "date_captured": "2013-11-16 16:02:11", "flickr_url": "http://farm4.staticflickr.com/3143/2720449417_cc12eaf438_z.jpg", "id": 175142}, {"license": 5, "file_name": "000000019501.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000019501.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 20:36:42", "flickr_url": "http://farm5.staticflickr.com/4120/5415996925_607c3cfd65_z.jpg", "id": 19501}, {"license": 1, "file_name": "000000240689.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240689.jpg", "height": 425, "width": 640, "date_captured": "2013-11-22 14:53:36", "flickr_url": "http://farm9.staticflickr.com/8175/8074189559_cd72b043fb_z.jpg", "id": 240689}, {"license": 1, "file_name": "000000560180.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000560180.jpg", "height": 612, "width": 612, "date_captured": "2013-11-21 02:57:45", "flickr_url": "http://farm9.staticflickr.com/8457/7978703995_d3909af2ef_z.jpg", "id": 560180}, {"license": 6, "file_name": "000000199743.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000199743.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 04:44:59", "flickr_url": "http://farm9.staticflickr.com/8253/8709841088_5d012a1996_z.jpg", "id": 199743}, {"license": 1, "file_name": "000000166975.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000166975.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 10:44:40", "flickr_url": "http://farm1.staticflickr.com/189/496915297_d1283741f8_z.jpg", "id": 166975}, {"license": 2, "file_name": "000000470085.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000470085.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 09:51:24", "flickr_url": "http://farm5.staticflickr.com/4004/4539209944_fd0be3c265_z.jpg", "id": 470085}, {"license": 1, "file_name": "000000363593.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000363593.jpg", "height": 411, "width": 640, "date_captured": "2013-11-24 06:19:51", "flickr_url": "http://farm6.staticflickr.com/5166/5255769749_2391259d9a_z.jpg", "id": 363593}, {"license": 1, "file_name": "000000166985.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000166985.jpg", "height": 640, "width": 427, "date_captured": "2013-11-21 00:12:58", "flickr_url": "http://farm6.staticflickr.com/5205/5252632064_580ec07e42_z.jpg", "id": 166985}, {"license": 1, "file_name": "000000257102.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000257102.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 22:11:09", "flickr_url": "http://farm8.staticflickr.com/7240/6872015740_f050b99b32_z.jpg", "id": 257102}, {"license": 5, "file_name": "000000109654.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000109654.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 22:56:12", "flickr_url": "http://farm8.staticflickr.com/7145/6491150391_15649d760d_z.jpg", "id": 109654}, {"license": 2, "file_name": "000000216150.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000216150.jpg", "height": 407, "width": 500, "date_captured": "2013-11-15 04:23:46", "flickr_url": "http://farm3.staticflickr.com/2180/2189265811_fe7e496f85_z.jpg", "id": 216150}, {"license": 3, "file_name": "000000429143.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000429143.jpg", "height": 500, "width": 375, "date_captured": "2013-11-18 00:12:26", "flickr_url": "http://farm3.staticflickr.com/2585/3801615933_c308c0eb1a_z.jpg", "id": 429143}, {"license": 1, "file_name": "000000543838.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000543838.jpg", "height": 478, "width": 640, "date_captured": "2013-11-24 19:33:14", "flickr_url": "http://farm4.staticflickr.com/3395/3290000038_fa3e46c418_z.jpg", "id": 543838}, {"license": 1, "file_name": "000000142431.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000142431.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 20:26:45", "flickr_url": "http://farm6.staticflickr.com/5223/5883076070_b00afd9848_z.jpg", "id": 142431}, {"license": 2, "file_name": "000000183392.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000183392.jpg", "height": 640, "width": 481, "date_captured": "2013-11-25 00:02:57", "flickr_url": "http://farm9.staticflickr.com/8366/8463912641_93b046fefc_z.jpg", "id": 183392}, {"license": 5, "file_name": "000000445540.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000445540.jpg", "height": 640, "width": 640, "date_captured": "2013-11-24 08:06:43", "flickr_url": "http://farm9.staticflickr.com/8301/8012428488_298d996191_z.jpg", "id": 445540}, {"license": 1, "file_name": "000000035945.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000035945.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 22:03:40", "flickr_url": "http://farm3.staticflickr.com/2415/1715649695_eaafb54686_z.jpg", "id": 35945}, {"license": 1, "file_name": "000000003178.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000003178.jpg", "height": 443, "width": 640, "date_captured": "2013-11-16 16:44:56", "flickr_url": "http://farm9.staticflickr.com/8112/8647182451_050c325dae_z.jpg", "id": 3178}, {"license": 3, "file_name": "000000339051.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000339051.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 11:30:23", "flickr_url": "http://farm5.staticflickr.com/4001/4698725560_882d706c0a_z.jpg", "id": 339051}, {"license": 3, "file_name": "000000535666.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000535666.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 22:29:56", "flickr_url": "http://farm9.staticflickr.com/8034/7954332094_190ed92bd9_z.jpg", "id": 535666}, {"license": 4, "file_name": "000000101503.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000101503.jpg", "height": 640, "width": 426, "date_captured": "2013-11-20 15:24:26", "flickr_url": "http://farm5.staticflickr.com/4074/4921300936_79a4514e47_z.jpg", "id": 101503}, {"license": 1, "file_name": "000000183435.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000183435.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 22:23:53", "flickr_url": "http://farm3.staticflickr.com/2225/2125528722_5c4e4236fc_z.jpg", "id": 183435}, {"license": 3, "file_name": "000000011426.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000011426.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 18:26:19", "flickr_url": "http://farm9.staticflickr.com/8171/8024393881_6a04bdf0e0_z.jpg", "id": 11426}, {"license": 4, "file_name": "000000068786.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000068786.jpg", "height": 512, "width": 640, "date_captured": "2013-11-15 14:20:59", "flickr_url": "http://farm8.staticflickr.com/7024/6660195909_5d0675711d_z.jpg", "id": 68786}, {"license": 4, "file_name": "000000445628.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000445628.jpg", "height": 360, "width": 640, "date_captured": "2013-11-17 04:34:47", "flickr_url": "http://farm4.staticflickr.com/3724/9672056407_262ef8fd72_z.jpg", "id": 445628}, {"license": 1, "file_name": "000000273600.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000273600.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 08:46:09", "flickr_url": "http://farm4.staticflickr.com/3506/3231441225_02e13e1e12_z.jpg", "id": 273600}, {"license": 5, "file_name": "000000101573.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000101573.jpg", "height": 640, "width": 427, "date_captured": "2013-11-22 21:28:00", "flickr_url": "http://farm9.staticflickr.com/8290/7658197122_378a1839a1_z.jpg", "id": 101573}, {"license": 4, "file_name": "000000257243.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000257243.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 18:13:24", "flickr_url": "http://farm6.staticflickr.com/5070/5592187122_98e351f2de_z.jpg", "id": 257243}, {"license": 2, "file_name": "000000421086.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421086.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 08:26:28", "flickr_url": "http://farm4.staticflickr.com/3813/9399324231_90c7f7f1d1_z.jpg", "id": 421086}, {"license": 5, "file_name": "000000363752.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000363752.jpg", "height": 500, "width": 405, "date_captured": "2013-11-22 20:54:53", "flickr_url": "http://farm2.staticflickr.com/1292/1168154619_2b97ff067a_z.jpg", "id": 363752}, {"license": 1, "file_name": "000000044266.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000044266.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 00:27:20", "flickr_url": "http://farm4.staticflickr.com/3038/2369973750_9256f9c292_z.jpg", "id": 44266}, {"license": 3, "file_name": "000000503022.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000503022.jpg", "height": 640, "width": 480, "date_captured": "2013-11-19 22:23:33", "flickr_url": "http://farm5.staticflickr.com/4005/4622756180_d7afdfe9e2_z.jpg", "id": 503022}, {"license": 2, "file_name": "000000281840.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000281840.jpg", "height": 441, "width": 640, "date_captured": "2013-11-23 11:32:51", "flickr_url": "http://farm5.staticflickr.com/4045/4214979990_f2d2c46520_z.jpg", "id": 281840}, {"license": 6, "file_name": "000000421105.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421105.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 14:28:17", "flickr_url": "http://farm9.staticflickr.com/8036/8066779964_d84db3fb1f_z.jpg", "id": 421105}, {"license": 3, "file_name": "000000552184.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000552184.jpg", "height": 640, "width": 426, "date_captured": "2013-11-20 21:04:36", "flickr_url": "http://farm9.staticflickr.com/8473/8094816283_806f5209c9_z.jpg", "id": 552184}, {"license": 1, "file_name": "000000003320.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000003320.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 18:23:58", "flickr_url": "http://farm3.staticflickr.com/2398/2105736071_27dd81b78e_z.jpg", "id": 3320}, {"license": 3, "file_name": "000000175370.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000175370.jpg", "height": 389, "width": 640, "date_captured": "2013-11-20 12:43:39", "flickr_url": "http://farm4.staticflickr.com/3114/2536264940_cc01545064_z.jpg", "id": 175370}, {"license": 1, "file_name": "000000240911.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240911.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 10:02:55", "flickr_url": "http://farm8.staticflickr.com/7296/8733818911_9a39e7d1a9_z.jpg", "id": 240911}, {"license": 4, "file_name": "000000298262.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298262.jpg", "height": 640, "width": 640, "date_captured": "2013-11-18 09:57:46", "flickr_url": "http://farm8.staticflickr.com/7103/7140313057_c92d12355f_z.jpg", "id": 298262}, {"license": 1, "file_name": "000000199958.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000199958.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 19:01:40", "flickr_url": "http://farm6.staticflickr.com/5053/5402027481_2189c32a4d_z.jpg", "id": 199958}, {"license": 2, "file_name": "000000052518.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000052518.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 21:55:40", "flickr_url": "http://farm9.staticflickr.com/8162/7585220546_0609053641_z.jpg", "id": 52518}, {"license": 3, "file_name": "000000240961.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000240961.jpg", "height": 214, "width": 640, "date_captured": "2013-11-23 04:57:18", "flickr_url": "http://farm2.staticflickr.com/1387/1008115063_767c7d26a8_z.jpg", "id": 240961}, {"license": 4, "file_name": "000000535874.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000535874.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 21:38:55", "flickr_url": "http://farm9.staticflickr.com/8343/8196186471_01db6240f5_z.jpg", "id": 535874}, {"license": 4, "file_name": "000000200010.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000200010.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 04:01:49", "flickr_url": "http://farm8.staticflickr.com/7312/9179436631_bc7d873e3e_z.jpg", "id": 200010}, {"license": 4, "file_name": "000000339283.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000339283.jpg", "height": 425, "width": 640, "date_captured": "2013-11-19 19:19:26", "flickr_url": "http://farm3.staticflickr.com/2717/5848461637_4cef9c8ef3_z.jpg", "id": 339283}, {"license": 4, "file_name": "000000404826.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000404826.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:34:59", "flickr_url": "http://farm9.staticflickr.com/8154/7568060128_6f22246965_z.jpg", "id": 404826}, {"license": 4, "file_name": "000000314725.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000314725.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 21:10:55", "flickr_url": "http://farm3.staticflickr.com/2284/2172355975_1a0f4ea2dd_z.jpg", "id": 314725}, {"license": 3, "file_name": "000000208243.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000208243.jpg", "height": 433, "width": 640, "date_captured": "2013-11-15 19:22:37", "flickr_url": "http://farm5.staticflickr.com/4144/4834169102_d14daf8f89_z.jpg", "id": 208243}, {"license": 3, "file_name": "000000380284.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000380284.jpg", "height": 462, "width": 640, "date_captured": "2013-11-18 04:59:00", "flickr_url": "http://farm1.staticflickr.com/84/241948864_90cc7a888a_z.jpg", "id": 380284}, {"license": 4, "file_name": "000000306561.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000306561.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 04:27:57", "flickr_url": "http://farm3.staticflickr.com/2638/4236768192_3859d4d9ec_z.jpg", "id": 306561}, {"license": 4, "file_name": "000000445829.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000445829.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 01:31:58", "flickr_url": "http://farm3.staticflickr.com/2090/2245463273_c0aeabe0c9_z.jpg", "id": 445829}, {"license": 1, "file_name": "000000355717.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000355717.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 03:36:44", "flickr_url": "http://farm8.staticflickr.com/7271/6885518428_80cdea594c_z.jpg", "id": 355717}, {"license": 2, "file_name": "000000290185.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000290185.jpg", "height": 476, "width": 640, "date_captured": "2013-11-23 04:36:35", "flickr_url": "http://farm4.staticflickr.com/3513/3707779055_fc65fa0137_z.jpg", "id": 290185}, {"license": 4, "file_name": "000000568725.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000568725.jpg", "height": 426, "width": 640, "date_captured": "2013-11-24 03:22:42", "flickr_url": "http://farm4.staticflickr.com/3515/3276326308_07cd7036ac_z.jpg", "id": 568725}, {"license": 1, "file_name": "000000011673.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000011673.jpg", "height": 640, "width": 480, "date_captured": "2013-11-17 19:32:08", "flickr_url": "http://farm9.staticflickr.com/8324/8088237138_3894ed823e_z.jpg", "id": 11673}, {"license": 1, "file_name": "000000265625.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000265625.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 02:45:56", "flickr_url": "http://farm9.staticflickr.com/8285/7733120764_37d56a4798_z.jpg", "id": 265625}, {"license": 1, "file_name": "000000019874.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000019874.jpg", "height": 640, "width": 480, "date_captured": "2013-11-17 11:14:55", "flickr_url": "http://farm6.staticflickr.com/5260/5573418240_b76427c896_z.jpg", "id": 19874}, {"license": 1, "file_name": "000000404899.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000404899.jpg", "height": 510, "width": 640, "date_captured": "2013-11-24 10:04:01", "flickr_url": "http://farm9.staticflickr.com/8247/8587734221_fe87777c13_z.jpg", "id": 404899}, {"license": 4, "file_name": "000000404905.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000404905.jpg", "height": 640, "width": 478, "date_captured": "2013-11-24 14:23:11", "flickr_url": "http://farm8.staticflickr.com/7177/6808714994_49b6272256_z.jpg", "id": 404905}, {"license": 4, "file_name": "000000011690.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000011690.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 21:25:23", "flickr_url": "http://farm8.staticflickr.com/7034/6815187123_6f6d30ef26_z.jpg", "id": 11690}, {"license": 3, "file_name": "000000421298.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421298.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 18:29:46", "flickr_url": "http://farm4.staticflickr.com/3465/3370595134_efc9bfd247_z.jpg", "id": 421298}, {"license": 1, "file_name": "000000069047.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069047.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 16:57:06", "flickr_url": "http://farm3.staticflickr.com/2793/4399567042_c987f7118a_z.jpg", "id": 69047}, {"license": 3, "file_name": "000000101832.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000101832.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 22:39:28", "flickr_url": "http://farm1.staticflickr.com/25/67553328_87ec017911_z.jpg", "id": 101832}, {"license": 4, "file_name": "000000347596.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000347596.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 22:45:18", "flickr_url": "http://farm7.staticflickr.com/6193/6139521901_bd38ca258f_z.jpg", "id": 347596}, {"license": 4, "file_name": "000000568788.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000568788.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 14:16:27", "flickr_url": "http://farm2.staticflickr.com/1367/967049911_2b78eac663_z.jpg", "id": 568788}, {"license": 3, "file_name": "000000323030.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000323030.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 01:30:16", "flickr_url": "http://farm3.staticflickr.com/2059/2451038153_8bda1f05be_z.jpg", "id": 323030}, {"license": 5, "file_name": "000000224734.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000224734.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 05:59:06", "flickr_url": "http://farm9.staticflickr.com/8494/8294516819_48ee4d9bfc_z.jpg", "id": 224734}, {"license": 1, "file_name": "000000372198.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000372198.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 07:41:44", "flickr_url": "http://farm1.staticflickr.com/80/232410027_9c1cf31a62_z.jpg", "id": 372198}, {"license": 3, "file_name": "000000142825.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000142825.jpg", "height": 640, "width": 429, "date_captured": "2013-11-18 06:22:26", "flickr_url": "http://farm8.staticflickr.com/7049/6922742957_19fbce24ca_z.jpg", "id": 142825}, {"license": 1, "file_name": "000000183788.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000183788.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 20:56:51", "flickr_url": "http://farm4.staticflickr.com/3655/3369397985_00323a1916_z.jpg", "id": 183788}, {"license": 7, "file_name": "000000126447.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000126447.jpg", "height": 448, "width": 600, "date_captured": "2013-11-18 20:56:10", "flickr_url": "http://farm5.staticflickr.com/4050/4700016429_6eebedd5a5_z.jpg", "id": 126447}, {"license": 1, "file_name": "000000298481.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298481.jpg", "height": 640, "width": 424, "date_captured": "2013-11-23 15:45:35", "flickr_url": "http://farm8.staticflickr.com/7056/6929251287_8de8b3eb7e_z.jpg", "id": 298481}, {"license": 3, "file_name": "000000028154.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000028154.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 21:30:29", "flickr_url": "http://farm4.staticflickr.com/3131/3137437987_12056518ee_z.jpg", "id": 28154}, {"license": 4, "file_name": "000000011774.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000011774.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 22:55:18", "flickr_url": "http://farm9.staticflickr.com/8292/7869877062_1d03f6bd5f_z.jpg", "id": 11774}, {"license": 5, "file_name": "000000454144.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000454144.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 02:16:52", "flickr_url": "http://farm4.staticflickr.com/3596/3628597132_048fcc025a_z.jpg", "id": 454144}, {"license": 2, "file_name": "000000101892.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000101892.jpg", "height": 640, "width": 512, "date_captured": "2013-11-18 02:57:04", "flickr_url": "http://farm6.staticflickr.com/5187/5834817570_765f4dd951_z.jpg", "id": 101892}, {"license": 5, "file_name": "000000347655.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000347655.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 06:13:22", "flickr_url": "http://farm5.staticflickr.com/4017/4718105770_d1e72bc752_z.jpg", "id": 347655}, {"license": 1, "file_name": "000000568840.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000568840.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 14:43:44", "flickr_url": "http://farm7.staticflickr.com/6019/6282283585_9591634993_z.jpg", "id": 568840}, {"license": 2, "file_name": "000000241170.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000241170.jpg", "height": 612, "width": 612, "date_captured": "2013-11-22 10:39:42", "flickr_url": "http://farm6.staticflickr.com/5535/9552335007_9d554f585a_z.jpg", "id": 241170}, {"license": 1, "file_name": "000000077332.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000077332.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 20:54:56", "flickr_url": "http://farm7.staticflickr.com/6127/5946784924_63f5ab903f_z.jpg", "id": 77332}, {"license": 4, "file_name": "000000396825.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000396825.jpg", "height": 253, "width": 640, "date_captured": "2013-11-16 16:33:26", "flickr_url": "http://farm5.staticflickr.com/4131/4840808084_9a319b54fd_z.jpg", "id": 396825}, {"license": 4, "file_name": "000000085549.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000085549.jpg", "height": 640, "width": 488, "date_captured": "2013-11-18 08:03:06", "flickr_url": "http://farm7.staticflickr.com/6001/5920913948_220b710038_z.jpg", "id": 85549}, {"license": 1, "file_name": "000000290354.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000290354.jpg", "height": 425, "width": 640, "date_captured": "2013-11-14 12:32:22", "flickr_url": "http://farm6.staticflickr.com/5026/5644411533_95a9486d04_z.jpg", "id": 290354}, {"license": 1, "file_name": "000000560691.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000560691.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 13:49:17", "flickr_url": "http://farm9.staticflickr.com/8287/7881027376_2313b1de81_z.jpg", "id": 560691}, {"license": 3, "file_name": "000000527925.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000527925.jpg", "height": 524, "width": 640, "date_captured": "2013-11-17 19:24:43", "flickr_url": "http://farm1.staticflickr.com/48/141200438_e4384558ab_z.jpg", "id": 527925}, {"license": 1, "file_name": "000000323133.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000323133.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 06:13:06", "flickr_url": "http://farm5.staticflickr.com/4032/5168476672_ed25249f27_z.jpg", "id": 323133}, {"license": 4, "file_name": "000000233022.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000233022.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 17:04:27", "flickr_url": "http://farm3.staticflickr.com/2885/9371206882_9a5a9f2ef4_z.jpg", "id": 233022}, {"license": 1, "file_name": "000000159299.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000159299.jpg", "height": 425, "width": 640, "date_captured": "2013-11-21 02:11:52", "flickr_url": "http://farm9.staticflickr.com/8324/8077287072_298a3d7574_z.jpg", "id": 159299}, {"license": 2, "file_name": "000000077380.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000077380.jpg", "height": 456, "width": 640, "date_captured": "2013-11-16 23:53:11", "flickr_url": "http://farm4.staticflickr.com/3023/3007910221_1457a935b5_z.jpg", "id": 77380}, {"license": 3, "file_name": "000000028230.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000028230.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 16:17:48", "flickr_url": "http://farm5.staticflickr.com/4096/4765415890_41cd52b1a5_z.jpg", "id": 28230}, {"license": 3, "file_name": "000000126537.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000126537.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 14:23:15", "flickr_url": "http://farm9.staticflickr.com/8051/8093946886_40397e0ff1_z.jpg", "id": 126537}, {"license": 2, "file_name": "000000536146.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000536146.jpg", "height": 428, "width": 640, "date_captured": "2013-11-15 23:57:55", "flickr_url": "http://farm4.staticflickr.com/3155/3000311819_ccc205ec47_z.jpg", "id": 536146}, {"license": 3, "file_name": "000000044637.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000044637.jpg", "height": 333, "width": 500, "date_captured": "2013-11-17 10:40:29", "flickr_url": "http://farm3.staticflickr.com/2194/2403230831_a8dcd76dec_z.jpg", "id": 44637}, {"license": 1, "file_name": "000000454246.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000454246.jpg", "height": 284, "width": 640, "date_captured": "2013-11-19 02:50:53", "flickr_url": "http://farm9.staticflickr.com/8520/8635354410_4be16506c2_z.jpg", "id": 454246}, {"license": 4, "file_name": "000000560750.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000560750.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 19:19:26", "flickr_url": "http://farm3.staticflickr.com/2469/3987004931_5f35f0915f_z.jpg", "id": 560750}, {"license": 4, "file_name": "000000069231.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069231.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 00:13:31", "flickr_url": "http://farm9.staticflickr.com/8132/8942793695_f134bb7e11_z.jpg", "id": 69231}, {"license": 6, "file_name": "000000413297.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000413297.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 16:40:40", "flickr_url": "http://farm5.staticflickr.com/4001/4526613579_585172d9f4_z.jpg", "id": 413297}, {"license": 4, "file_name": "000000028281.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000028281.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 18:01:23", "flickr_url": "http://farm2.staticflickr.com/1018/5187802452_0c721ddc6c_z.jpg", "id": 28281}, {"license": 1, "file_name": "000000339579.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000339579.jpg", "height": 640, "width": 383, "date_captured": "2013-11-20 15:18:20", "flickr_url": "http://farm8.staticflickr.com/7021/6435727391_58e41b665d_z.jpg", "id": 339579}, {"license": 1, "file_name": "000000568962.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000568962.jpg", "height": 640, "width": 426, "date_captured": "2013-11-24 00:33:22", "flickr_url": "http://farm3.staticflickr.com/2510/3794826454_b14f4b92a6_z.jpg", "id": 568962}, {"license": 3, "file_name": "000000364169.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000364169.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 01:18:47", "flickr_url": "http://farm5.staticflickr.com/4092/4967608675_fe6b174c41_z.jpg", "id": 364169}, {"license": 7, "file_name": "000000192137.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000192137.jpg", "height": 346, "width": 640, "date_captured": "2013-11-16 12:52:20", "flickr_url": "http://farm9.staticflickr.com/8369/8580268995_bfe253e4fd_z.jpg", "id": 192137}, {"license": 4, "file_name": "000000118413.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000118413.jpg", "height": 381, "width": 640, "date_captured": "2013-11-24 07:50:42", "flickr_url": "http://farm1.staticflickr.com/21/92772389_196410c494_z.jpg", "id": 118413}, {"license": 2, "file_name": "000000102030.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000102030.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 23:01:00", "flickr_url": "http://farm7.staticflickr.com/6040/5881801144_95f71bf2f8_z.jpg", "id": 102030}, {"license": 2, "file_name": "000000298639.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298639.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 10:02:33", "flickr_url": "http://farm5.staticflickr.com/4066/4523100370_4b4fc6c349_z.jpg", "id": 298639}, {"license": 2, "file_name": "000000306837.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000306837.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 17:33:07", "flickr_url": "http://farm9.staticflickr.com/8317/7894419254_e5379bbd86_z.jpg", "id": 306837}, {"license": 3, "file_name": "000000331419.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000331419.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 14:05:41", "flickr_url": "http://farm8.staticflickr.com/7154/6592219329_9b58c9652e_z.jpg", "id": 331419}, {"license": 2, "file_name": "000000290460.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000290460.jpg", "height": 640, "width": 428, "date_captured": "2013-11-20 01:27:54", "flickr_url": "http://farm8.staticflickr.com/7026/6597443255_9329d421ff_z.jpg", "id": 290460}, {"license": 3, "file_name": "000000478899.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000478899.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 23:04:31", "flickr_url": "http://farm9.staticflickr.com/8376/8418854819_3137f62952_z.jpg", "id": 478899}, {"license": 1, "file_name": "000000536244.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000536244.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 11:06:10", "flickr_url": "http://farm6.staticflickr.com/5062/5653849926_78393b4af0_z.jpg", "id": 536244}, {"license": 3, "file_name": "000000577206.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000577206.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 22:11:29", "flickr_url": "http://farm6.staticflickr.com/5265/5619843107_a739c286f6_z.jpg", "id": 577206}, {"license": 3, "file_name": "000000036546.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000036546.jpg", "height": 458, "width": 640, "date_captured": "2013-11-16 14:01:00", "flickr_url": "http://farm1.staticflickr.com/250/459743480_40901a3f33_z.jpg", "id": 36546}, {"license": 1, "file_name": "000000569037.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000569037.jpg", "height": 500, "width": 328, "date_captured": "2013-11-25 20:50:45", "flickr_url": "http://farm4.staticflickr.com/3033/2831772480_0327e6d99a_z.jpg", "id": 569037}, {"license": 1, "file_name": "000000413391.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000413391.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 21:04:26", "flickr_url": "http://farm9.staticflickr.com/8174/8066743613_80332da992_z.jpg", "id": 413391}, {"license": 3, "file_name": "000000388823.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000388823.jpg", "height": 500, "width": 332, "date_captured": "2013-11-24 12:48:39", "flickr_url": "http://farm4.staticflickr.com/3139/3008954492_3824a39f3f_z.jpg", "id": 388823}, {"license": 4, "file_name": "000000577240.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000577240.jpg", "height": 424, "width": 640, "date_captured": "2013-11-22 20:57:52", "flickr_url": "http://farm9.staticflickr.com/8312/7957734894_8f786d19c5_z.jpg", "id": 577240}, {"license": 4, "file_name": "000000020188.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000020188.jpg", "height": 640, "width": 451, "date_captured": "2013-11-20 04:33:12", "flickr_url": "http://farm6.staticflickr.com/5060/5443344932_f8b2afd6b2_z.jpg", "id": 20188}, {"license": 3, "file_name": "000000577246.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000577246.jpg", "height": 513, "width": 640, "date_captured": "2013-11-20 04:08:00", "flickr_url": "http://farm3.staticflickr.com/2760/4376115299_120fbf9e5f_z.jpg", "id": 577246}, {"license": 3, "file_name": "000000036574.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000036574.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 07:32:51", "flickr_url": "http://farm3.staticflickr.com/2045/2622764000_bae1e956aa_z.jpg", "id": 36574}, {"license": 3, "file_name": "000000069344.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069344.jpg", "height": 640, "width": 640, "date_captured": "2013-11-20 21:50:57", "flickr_url": "http://farm9.staticflickr.com/8084/8261026887_11bbe6a619_z.jpg", "id": 69344}, {"license": 1, "file_name": "000000241392.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000241392.jpg", "height": 369, "width": 640, "date_captured": "2013-11-17 05:47:58", "flickr_url": "http://farm8.staticflickr.com/7384/9483224081_49ed1c6328_z.jpg", "id": 241392}, {"license": 2, "file_name": "000000421618.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421618.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 19:21:38", "flickr_url": "http://farm3.staticflickr.com/2613/4146009290_c22c2347f0_z.jpg", "id": 421618}, {"license": 3, "file_name": "000000102144.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000102144.jpg", "height": 329, "width": 640, "date_captured": "2013-11-24 15:11:04", "flickr_url": "http://farm5.staticflickr.com/4119/4937245744_42d5a0af24_z.jpg", "id": 102144}, {"license": 3, "file_name": "000000331520.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000331520.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 03:36:40", "flickr_url": "http://farm6.staticflickr.com/5108/5624782849_a7db8bf959_z.jpg", "id": 331520}, {"license": 3, "file_name": "000000347908.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000347908.jpg", "height": 391, "width": 500, "date_captured": "2013-11-22 22:41:14", "flickr_url": "http://farm4.staticflickr.com/3596/3411983335_bc97d12e33_z.jpg", "id": 347908}, {"license": 1, "file_name": "000000421643.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421643.jpg", "height": 640, "width": 427, "date_captured": "2013-11-21 22:13:41", "flickr_url": "http://farm3.staticflickr.com/2133/2374900041_387c543cfd_z.jpg", "id": 421643}, {"license": 4, "file_name": "000000306967.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000306967.jpg", "height": 425, "width": 640, "date_captured": "2013-11-22 21:31:00", "flickr_url": "http://farm3.staticflickr.com/2772/4482666103_b0b7cf54bb_z.jpg", "id": 306967}, {"license": 1, "file_name": "000000528151.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000528151.jpg", "height": 612, "width": 612, "date_captured": "2013-11-21 01:12:06", "flickr_url": "http://farm8.staticflickr.com/7313/9669217706_8a04dd3157_z.jpg", "id": 528151}, {"license": 1, "file_name": "000000241461.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000241461.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 21:58:22", "flickr_url": "http://farm8.staticflickr.com/7181/6929145459_8207470738_z.jpg", "id": 241461}, {"license": 5, "file_name": "000000438071.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000438071.jpg", "height": 427, "width": 640, "date_captured": "2013-11-25 19:47:28", "flickr_url": "http://farm6.staticflickr.com/5285/5221601867_a5d71f5665_z.jpg", "id": 438071}, {"license": 4, "file_name": "000000102208.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000102208.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 20:00:20", "flickr_url": "http://farm9.staticflickr.com/8071/8323874322_5537ab71ea_z.jpg", "id": 102208}, {"license": 6, "file_name": "000000020291.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000020291.jpg", "height": 640, "width": 427, "date_captured": "2013-11-25 20:14:00", "flickr_url": "http://farm3.staticflickr.com/2763/4397342301_778f0d6319_z.jpg", "id": 20291}, {"license": 1, "file_name": "000000347972.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000347972.jpg", "height": 640, "width": 480, "date_captured": "2013-11-17 07:11:42", "flickr_url": "http://farm8.staticflickr.com/7295/9611222492_2a20550eba_z.jpg", "id": 347972}, {"license": 3, "file_name": "000000388935.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000388935.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 21:18:06", "flickr_url": "http://farm3.staticflickr.com/2880/9284114410_0cb1af3305_z.jpg", "id": 388935}, {"license": 1, "file_name": "000000462664.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000462664.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 01:09:42", "flickr_url": "http://farm2.staticflickr.com/1383/1288559262_272888bdd0_z.jpg", "id": 462664}, {"license": 1, "file_name": "000000257867.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000257867.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 18:14:13", "flickr_url": "http://farm9.staticflickr.com/8399/8692998551_83863671e4_z.jpg", "id": 257867}, {"license": 3, "file_name": "000000372558.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000372558.jpg", "height": 401, "width": 640, "date_captured": "2013-11-18 01:01:59", "flickr_url": "http://farm4.staticflickr.com/3166/2796987959_fa87623035_z.jpg", "id": 372558}, {"license": 1, "file_name": "000000241491.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000241491.jpg", "height": 424, "width": 640, "date_captured": "2013-11-14 17:20:41", "flickr_url": "http://farm9.staticflickr.com/8053/8103459779_acfdb280b7_z.jpg", "id": 241491}, {"license": 5, "file_name": "000000544595.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000544595.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 12:40:52", "flickr_url": "http://farm5.staticflickr.com/4120/4922771825_0913aa9649_z.jpg", "id": 544595}, {"license": 1, "file_name": "000000315221.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000315221.jpg", "height": 353, "width": 640, "date_captured": "2013-11-16 23:19:46", "flickr_url": "http://farm5.staticflickr.com/4106/4995655411_453087c74c_z.jpg", "id": 315221}, {"license": 4, "file_name": "000000413556.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000413556.jpg", "height": 431, "width": 640, "date_captured": "2013-11-14 21:17:23", "flickr_url": "http://farm9.staticflickr.com/8390/8677889392_be5c30e3ff_z.jpg", "id": 413556}, {"license": 2, "file_name": "000000487284.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000487284.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 00:03:02", "flickr_url": "http://farm1.staticflickr.com/129/338053733_05180546d8_z.jpg", "id": 487284}, {"license": 3, "file_name": "000000036729.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000036729.jpg", "height": 486, "width": 640, "date_captured": "2013-11-20 23:47:29", "flickr_url": "http://farm5.staticflickr.com/4094/4790612044_ba4496b06a_z.jpg", "id": 36729}, {"license": 7, "file_name": "000000069500.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069500.jpg", "height": 453, "width": 640, "date_captured": "2013-11-18 06:43:14", "flickr_url": "http://farm7.staticflickr.com/6231/6210594287_68554bbaaf_z.jpg", "id": 69500}, {"license": 1, "file_name": "000000569214.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000569214.jpg", "height": 429, "width": 640, "date_captured": "2013-11-25 19:16:28", "flickr_url": "http://farm9.staticflickr.com/8202/8242812051_39012ddfb1_z.jpg", "id": 569214}, {"license": 1, "file_name": "000000520063.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000520063.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 04:55:11", "flickr_url": "http://farm3.staticflickr.com/2184/2104576445_99c5806ca2_z.jpg", "id": 520063}, {"license": 3, "file_name": "000000470912.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000470912.jpg", "height": 640, "width": 488, "date_captured": "2013-11-18 00:29:27", "flickr_url": "http://farm1.staticflickr.com/112/305401978_add5de02d6_z.jpg", "id": 470912}, {"license": 2, "file_name": "000000577416.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000577416.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 12:54:19", "flickr_url": "http://farm9.staticflickr.com/8459/8033444158_99fb3a5624_z.jpg", "id": 577416}, {"license": 1, "file_name": "000000307082.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000307082.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 18:55:03", "flickr_url": "http://farm9.staticflickr.com/8470/8444679052_be3bef9e23_z.jpg", "id": 307082}, {"license": 7, "file_name": "000000077709.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000077709.jpg", "height": 463, "width": 640, "date_captured": "2013-11-16 16:28:08", "flickr_url": "http://farm4.staticflickr.com/3280/3056778929_83fca18c1b_z.jpg", "id": 77709}, {"license": 4, "file_name": "000000380820.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000380820.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 00:24:41", "flickr_url": "http://farm5.staticflickr.com/4124/5200382476_9b368d20a3_z.jpg", "id": 380820}, {"license": 4, "file_name": "000000184224.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000184224.jpg", "height": 446, "width": 281, "date_captured": "2013-11-18 03:13:15", "flickr_url": "http://farm1.staticflickr.com/36/74052852_6cb62d31a1_z.jpg", "id": 184224}, {"license": 3, "file_name": "000000044960.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000044960.jpg", "height": 439, "width": 640, "date_captured": "2013-11-16 18:29:34", "flickr_url": "http://farm7.staticflickr.com/6159/6181076006_2b23552503_z.jpg", "id": 44960}, {"license": 1, "file_name": "000000331680.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000331680.jpg", "height": 499, "width": 640, "date_captured": "2013-11-18 21:54:45", "flickr_url": "http://farm1.staticflickr.com/98/272693422_22003a47cf_z.jpg", "id": 331680}, {"license": 3, "file_name": "000000520100.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000520100.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 01:28:50", "flickr_url": "http://farm2.staticflickr.com/1287/729087471_5ae703a032_z.jpg", "id": 520100}, {"license": 2, "file_name": "000000520112.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000520112.jpg", "height": 360, "width": 640, "date_captured": "2013-11-25 20:35:05", "flickr_url": "http://farm4.staticflickr.com/3399/3306053178_2e775151f5_z.jpg", "id": 520112}, {"license": 3, "file_name": "000000511930.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000511930.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 18:21:30", "flickr_url": "http://farm9.staticflickr.com/8237/8593028802_1676792446_z.jpg", "id": 511930}, {"license": 1, "file_name": "000000544701.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000544701.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 18:02:01", "flickr_url": "http://farm2.staticflickr.com/1022/1066578219_64c01bb790_z.jpg", "id": 544701}, {"license": 3, "file_name": "000000307136.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000307136.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 09:34:48", "flickr_url": "http://farm8.staticflickr.com/7111/7730771612_d985a96fae_z.jpg", "id": 307136}, {"license": 1, "file_name": "000000470977.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000470977.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 18:27:25", "flickr_url": "http://farm8.staticflickr.com/7145/6818998389_ec81a0ae8f_z.jpg", "id": 470977}, {"license": 3, "file_name": "000000069579.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069579.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 05:48:03", "flickr_url": "http://farm4.staticflickr.com/3210/2965821608_00931e467a_z.jpg", "id": 69579}, {"license": 1, "file_name": "000000298956.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000298956.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 18:48:46", "flickr_url": "http://farm5.staticflickr.com/4140/4898013096_6b76f658e7_z.jpg", "id": 298956}, {"license": 3, "file_name": "000000511967.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000511967.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 01:24:38", "flickr_url": "http://farm4.staticflickr.com/3545/3691943404_8c2bddd211_z.jpg", "id": 511967}, {"license": 1, "file_name": "000000143334.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000143334.jpg", "height": 640, "width": 640, "date_captured": "2013-11-14 19:52:43", "flickr_url": "http://farm6.staticflickr.com/5032/6910405524_b9d2d4152c_z.jpg", "id": 143334}, {"license": 5, "file_name": "000000053232.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000053232.jpg", "height": 335, "width": 500, "date_captured": "2013-11-20 20:49:08", "flickr_url": "http://farm3.staticflickr.com/2504/3857300101_1013689e12_z.jpg", "id": 53232}, {"license": 3, "file_name": "000000266228.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000266228.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 07:12:32", "flickr_url": "http://farm6.staticflickr.com/5330/9330741796_34ee405af7_z.jpg", "id": 266228}, {"license": 2, "file_name": "000000495609.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000495609.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 07:16:16", "flickr_url": "http://farm4.staticflickr.com/3312/5844918132_0cd4162a50_z.jpg", "id": 495609}, {"license": 7, "file_name": "000000421887.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000421887.jpg", "height": 640, "width": 486, "date_captured": "2013-11-16 04:30:50", "flickr_url": "http://farm3.staticflickr.com/2512/4010635681_bbba2c6503_z.jpg", "id": 421887}, {"license": 3, "file_name": "000000061460.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000061460.jpg", "height": 424, "width": 640, "date_captured": "2013-11-18 10:36:39", "flickr_url": "http://farm7.staticflickr.com/6062/6131381005_32eedc8b72_z.jpg", "id": 61460}, {"license": 3, "file_name": "000000258071.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000258071.jpg", "height": 424, "width": 640, "date_captured": "2013-11-24 20:53:06", "flickr_url": "http://farm4.staticflickr.com/3609/3424861467_bb3e0334b9_z.jpg", "id": 258071}, {"license": 4, "file_name": "000000159768.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000159768.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 07:40:43", "flickr_url": "http://farm4.staticflickr.com/3693/10057218455_0373c0bfb7_z.jpg", "id": 159768}, {"license": 3, "file_name": "000000102432.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000102432.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 14:04:37", "flickr_url": "http://farm2.staticflickr.com/1161/1153803728_ec213110e9_z.jpg", "id": 102432}, {"license": 6, "file_name": "000000389154.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000389154.jpg", "height": 389, "width": 640, "date_captured": "2013-11-16 12:02:08", "flickr_url": "http://farm9.staticflickr.com/8266/8667392108_85f064f233_z.jpg", "id": 389154}, {"license": 4, "file_name": "000000397362.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000397362.jpg", "height": 336, "width": 500, "date_captured": "2013-11-21 19:55:47", "flickr_url": "http://farm3.staticflickr.com/2615/4033228643_c3b0d9b890_z.jpg", "id": 397362}, {"license": 1, "file_name": "000000176179.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000176179.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 08:21:13", "flickr_url": "http://farm6.staticflickr.com/5284/5353125658_3a8d2d3062_z.jpg", "id": 176179}, {"license": 3, "file_name": "000000553021.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000553021.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 18:52:07", "flickr_url": "http://farm8.staticflickr.com/7214/6997091613_c25b0e7f4e_z.jpg", "id": 553021}, {"license": 3, "file_name": "000000323664.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000323664.jpg", "height": 500, "width": 333, "date_captured": "2013-11-21 23:50:21", "flickr_url": "http://farm1.staticflickr.com/232/450495245_1e32cebc15_z.jpg", "id": 323664}, {"license": 1, "file_name": "000000094300.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000094300.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 12:59:19", "flickr_url": "http://farm3.staticflickr.com/2594/4198283387_909448a65c_z.jpg", "id": 94300}, {"license": 1, "file_name": "000000471136.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000471136.jpg", "height": 425, "width": 640, "date_captured": "2013-11-18 07:53:48", "flickr_url": "http://farm6.staticflickr.com/5257/5497273896_3e215f3f47_z.jpg", "id": 471136}, {"license": 1, "file_name": "000000176229.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000176229.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 11:06:08", "flickr_url": "http://farm6.staticflickr.com/5184/5653285543_fb857aff7a_z.jpg", "id": 176229}, {"license": 4, "file_name": "000000110704.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000110704.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 23:53:44", "flickr_url": "http://farm5.staticflickr.com/4134/4773850969_5d34115fa6_z.jpg", "id": 110704}, {"license": 3, "file_name": "000000274547.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000274547.jpg", "height": 490, "width": 640, "date_captured": "2013-11-15 21:48:56", "flickr_url": "http://farm7.staticflickr.com/6173/6259993035_f7779dd209_z.jpg", "id": 274547}, {"license": 3, "file_name": "000000266369.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000266369.jpg", "height": 331, "width": 500, "date_captured": "2013-11-24 07:53:20", "flickr_url": "http://farm1.staticflickr.com/24/63494713_957c579ea9_z.jpg", "id": 266369}, {"license": 4, "file_name": "000000323728.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000323728.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 03:24:29", "flickr_url": "http://farm5.staticflickr.com/4060/4436860750_ed6f1f403c_z.jpg", "id": 323728}, {"license": 4, "file_name": "000000348315.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000348315.jpg", "height": 360, "width": 640, "date_captured": "2013-11-18 16:55:10", "flickr_url": "http://farm6.staticflickr.com/5526/9169429509_c11b2ee87c_z.jpg", "id": 348315}, {"license": 1, "file_name": "000000495776.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000495776.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 07:55:36", "flickr_url": "http://farm1.staticflickr.com/21/30368166_92245cce3f_z.jpg", "id": 495776}, {"license": 1, "file_name": "000000340129.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000340129.jpg", "height": 427, "width": 640, "date_captured": "2013-11-23 00:50:47", "flickr_url": "http://farm8.staticflickr.com/7236/7304272786_359bc882d8_z.jpg", "id": 340129}, {"license": 1, "file_name": "000000479396.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000479396.jpg", "height": 375, "width": 500, "date_captured": "2013-11-21 22:49:09", "flickr_url": "http://farm3.staticflickr.com/2138/2154761700_ee65b26d87_z.jpg", "id": 479396}, {"license": 3, "file_name": "000000045226.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000045226.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 18:24:22", "flickr_url": "http://farm9.staticflickr.com/8166/7495217196_ce8ce25fb9_z.jpg", "id": 45226}, {"license": 2, "file_name": "000000151729.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000151729.jpg", "height": 478, "width": 640, "date_captured": "2013-11-16 21:29:15", "flickr_url": "http://farm3.staticflickr.com/2865/9026420517_8a28e1c420_z.jpg", "id": 151729}, {"license": 5, "file_name": "000000356535.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000356535.jpg", "height": 428, "width": 640, "date_captured": "2013-11-18 05:40:07", "flickr_url": "http://farm8.staticflickr.com/7109/7445035638_309eda8c6a_z.jpg", "id": 356535}, {"license": 4, "file_name": "000000094392.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000094392.jpg", "height": 640, "width": 438, "date_captured": "2013-11-23 00:48:44", "flickr_url": "http://farm6.staticflickr.com/5235/7180807843_d61432e1c0_z.jpg", "id": 94392}, {"license": 2, "file_name": "000000069839.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000069839.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 15:04:59", "flickr_url": "http://farm8.staticflickr.com/7002/6449594363_c2493b02d3_z.jpg", "id": 69839}, {"license": 5, "file_name": "000000159957.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000159957.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 06:24:15", "flickr_url": "http://farm4.staticflickr.com/3395/3271007535_4f60fa43a1_z.jpg", "id": 159957}, {"license": 3, "file_name": "000000176342.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000176342.jpg", "height": 424, "width": 640, "date_captured": "2013-11-20 21:22:37", "flickr_url": "http://farm9.staticflickr.com/8233/8437787051_938f63999c_z.jpg", "id": 176342}, {"license": 1, "file_name": "000000127214.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000127214.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 06:12:49", "flickr_url": "http://farm8.staticflickr.com/7014/6747247879_36924d8653_z.jpg", "id": 127214}, {"license": 4, "file_name": "000000463101.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000463101.jpg", "height": 640, "width": 315, "date_captured": "2013-11-19 19:27:55", "flickr_url": "http://farm9.staticflickr.com/8061/8224442783_4d90fea891_z.jpg", "id": 463101}, {"license": 3, "file_name": "000000037122.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000037122.jpg", "height": 358, "width": 640, "date_captured": "2013-11-17 06:04:16", "flickr_url": "http://farm4.staticflickr.com/3823/9395595409_3211ed3b80_z.jpg", "id": 37122}, {"license": 3, "file_name": "000000364803.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000364803.jpg", "height": 463, "width": 640, "date_captured": "2013-11-20 01:49:10", "flickr_url": "http://farm3.staticflickr.com/2785/4298432020_9e0459c014_z.jpg", "id": 364803}, {"license": 4, "file_name": "000000102662.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000102662.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 18:57:24", "flickr_url": "http://farm7.staticflickr.com/6170/6150337850_bb9f2b9e0b_z.jpg", "id": 102662}, {"license": 3, "file_name": "000000454923.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000454923.jpg", "height": 335, "width": 500, "date_captured": "2013-11-24 08:33:06", "flickr_url": "http://farm3.staticflickr.com/2634/3962269479_2301ec54dc_z.jpg", "id": 454923}, {"license": 1, "file_name": "000000405777.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000405777.jpg", "height": 421, "width": 640, "date_captured": "2013-11-18 20:40:43", "flickr_url": "http://farm1.staticflickr.com/30/60662054_3dd1f7e9a6_z.jpg", "id": 405777}, {"license": 3, "file_name": "000000233746.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000233746.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 21:06:53", "flickr_url": "http://farm4.staticflickr.com/3344/3476848466_ee845618e9_z.jpg", "id": 233746}, {"license": 4, "file_name": "000000512282.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000512282.jpg", "height": 640, "width": 575, "date_captured": "2013-11-24 06:05:18", "flickr_url": "http://farm7.staticflickr.com/6110/6281521346_7d50321371_z.jpg", "id": 512282}, {"license": 4, "file_name": "000000045339.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000045339.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 13:10:36", "flickr_url": "http://farm3.staticflickr.com/2879/9504444910_f449fc962c_z.jpg", "id": 45339}, {"license": 3, "file_name": "000000381214.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000381214.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 05:18:35", "flickr_url": "http://farm3.staticflickr.com/2866/9634076907_866da99631_z.jpg", "id": 381214}, {"license": 1, "file_name": "000000020769.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000020769.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 16:34:36", "flickr_url": "http://farm4.staticflickr.com/3540/3378025208_6b799c3568_z.jpg", "id": 20769}, {"license": 1, "file_name": "000000037160.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000037160.jpg", "height": 365, "width": 640, "date_captured": "2013-11-18 02:27:28", "flickr_url": "http://farm4.staticflickr.com/3247/2531834490_57b0b87898_z.jpg", "id": 37160}, {"license": 1, "file_name": "000000151854.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000151854.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 07:55:02", "flickr_url": "http://farm1.staticflickr.com/24/55457233_9d72718453_z.jpg", "id": 151854}, {"license": 6, "file_name": "000000037169.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000037169.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 17:41:26", "flickr_url": "http://farm9.staticflickr.com/8328/8420217532_c5fee446b3_z.jpg", "id": 37169}, {"license": 5, "file_name": "000000127286.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000127286.jpg", "height": 360, "width": 640, "date_captured": "2013-11-18 19:16:02", "flickr_url": "http://farm3.staticflickr.com/2425/3998724598_f8eab5d279_z.jpg", "id": 127286}, {"license": 2, "file_name": "000000028988.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000028988.jpg", "height": 640, "width": 640, "date_captured": "2013-11-17 23:47:03", "flickr_url": "http://farm6.staticflickr.com/5230/5793645339_f9f32035f3_z.jpg", "id": 28988}, {"license": 1, "file_name": "000000561479.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000561479.jpg", "height": 426, "width": 640, "date_captured": "2013-11-23 20:13:36", "flickr_url": "http://farm1.staticflickr.com/75/194657320_4453308dae_z.jpg", "id": 561479}, {"license": 3, "file_name": "000000151893.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000151893.jpg", "height": 484, "width": 640, "date_captured": "2013-11-17 03:27:31", "flickr_url": "http://farm3.staticflickr.com/2861/10206253473_f125e318a7_z.jpg", "id": 151893}, {"license": 1, "file_name": "000000332133.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332133.jpg", "height": 495, "width": 640, "date_captured": "2013-11-19 23:43:02", "flickr_url": "http://farm4.staticflickr.com/3040/2843654471_5e044ff7c0_z.jpg", "id": 332133}, {"license": 5, "file_name": "000000422255.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000422255.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 01:04:35", "flickr_url": "http://farm4.staticflickr.com/3044/3111493410_7e14079755_z.jpg", "id": 422255}, {"license": 6, "file_name": "000000070000.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000070000.jpg", "height": 425, "width": 640, "date_captured": "2013-11-15 02:07:34", "flickr_url": "http://farm5.staticflickr.com/4125/4840262155_aa1fc6b90a_z.jpg", "id": 70000}, {"license": 1, "file_name": "000000233841.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000233841.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 15:20:18", "flickr_url": "http://farm5.staticflickr.com/4099/4851270882_1a0424ee8e_z.jpg", "id": 233841}, {"license": 4, "file_name": "000000135539.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000135539.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 13:18:00", "flickr_url": "http://farm3.staticflickr.com/2335/2426123758_8f3cf3b1c5_z.jpg", "id": 135539}, {"license": 3, "file_name": "000000323960.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000323960.jpg", "height": 434, "width": 640, "date_captured": "2013-11-15 11:55:35", "flickr_url": "http://farm9.staticflickr.com/8487/8177406454_9277e37d67_z.jpg", "id": 323960}, {"license": 3, "file_name": "000000545145.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000545145.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 00:59:36", "flickr_url": "http://farm5.staticflickr.com/4081/4789687594_949527fabf_z.jpg", "id": 545145}, {"license": 1, "file_name": "000000463224.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000463224.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 03:26:03", "flickr_url": "http://farm1.staticflickr.com/40/82915898_0135e40ee5_z.jpg", "id": 463224}, {"license": 5, "file_name": "000000504187.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000504187.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 20:51:15", "flickr_url": "http://farm3.staticflickr.com/2229/2488213767_1a54d3c258_z.jpg", "id": 504187}, {"license": 5, "file_name": "000000192891.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000192891.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 21:09:44", "flickr_url": "http://farm3.staticflickr.com/2674/4328177454_7072462c83_z.jpg", "id": 192891}, {"license": 3, "file_name": "000000004477.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000004477.jpg", "height": 506, "width": 640, "date_captured": "2013-11-18 03:51:57", "flickr_url": "http://farm8.staticflickr.com/7450/9591155503_4a60f3e1d2_z.jpg", "id": 4477}, {"license": 4, "file_name": "000000332158.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332158.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 07:58:42", "flickr_url": "http://farm4.staticflickr.com/3723/9302702376_37d57bab64_z.jpg", "id": 332158}, {"license": 3, "file_name": "000000438663.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000438663.jpg", "height": 584, "width": 640, "date_captured": "2013-11-17 20:24:36", "flickr_url": "http://farm8.staticflickr.com/7228/7354210182_d3f2e6dc27_z.jpg", "id": 438663}, {"license": 2, "file_name": "000000258440.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000258440.jpg", "height": 640, "width": 431, "date_captured": "2013-11-21 01:13:54", "flickr_url": "http://farm3.staticflickr.com/2628/3834207460_cd9d795f10_z.jpg", "id": 258440}, {"license": 1, "file_name": "000000094600.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000094600.jpg", "height": 640, "width": 478, "date_captured": "2013-11-24 18:33:06", "flickr_url": "http://farm6.staticflickr.com/5535/9105673699_aa1b58cf64_z.jpg", "id": 94600}, {"license": 4, "file_name": "000000520590.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000520590.jpg", "height": 640, "width": 427, "date_captured": "2013-11-24 07:05:32", "flickr_url": "http://farm4.staticflickr.com/3070/2676682939_ee9a9060d7_z.jpg", "id": 520590}, {"license": 3, "file_name": "000000561551.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000561551.jpg", "height": 437, "width": 640, "date_captured": "2013-11-18 04:46:18", "flickr_url": "http://farm8.staticflickr.com/7366/9699096880_ed9f100883_z.jpg", "id": 561551}, {"license": 2, "file_name": "000000094608.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000094608.jpg", "height": 340, "width": 640, "date_captured": "2013-11-16 03:56:53", "flickr_url": "http://farm6.staticflickr.com/5229/5670536029_1779c594b8_z.jpg", "id": 94608}, {"license": 3, "file_name": "000000569750.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000569750.jpg", "height": 454, "width": 640, "date_captured": "2013-11-16 15:28:19", "flickr_url": "http://farm8.staticflickr.com/7279/6972672320_61eaef58f3_z.jpg", "id": 569750}, {"license": 3, "file_name": "000000111000.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000111000.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 18:17:09", "flickr_url": "http://farm1.staticflickr.com/5/10749092_5485f0c5ad_z.jpg", "id": 111000}, {"license": 1, "file_name": "000000274853.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000274853.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 19:59:22", "flickr_url": "http://farm6.staticflickr.com/5184/5861324142_c9982e270b_z.jpg", "id": 274853}, {"license": 2, "file_name": "000000242090.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000242090.jpg", "height": 440, "width": 640, "date_captured": "2013-11-19 18:58:42", "flickr_url": "http://farm1.staticflickr.com/43/109674392_efc7d1cf2c_z.jpg", "id": 242090}, {"license": 5, "file_name": "000000332204.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332204.jpg", "height": 324, "width": 432, "date_captured": "2013-11-20 12:22:07", "flickr_url": "http://farm5.staticflickr.com/4052/5162428391_872f641b4a_z.jpg", "id": 332204}, {"license": 3, "file_name": "000000496053.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000496053.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 19:46:43", "flickr_url": "http://farm4.staticflickr.com/3298/3450370419_53220fe5bd_z.jpg", "id": 496053}, {"license": 2, "file_name": "000000020917.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000020917.jpg", "height": 413, "width": 640, "date_captured": "2013-11-20 01:45:37", "flickr_url": "http://farm1.staticflickr.com/238/457305857_4de1f24ecb_z.jpg", "id": 20917}, {"license": 3, "file_name": "000000160188.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000160188.jpg", "height": 448, "width": 640, "date_captured": "2013-11-20 01:22:29", "flickr_url": "http://farm7.staticflickr.com/6034/6866117932_aaf95bafc5_z.jpg", "id": 160188}, {"license": 1, "file_name": "000000111040.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000111040.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 06:11:50", "flickr_url": "http://farm4.staticflickr.com/3342/3561851886_cf3b1c8832_z.jpg", "id": 111040}, {"license": 2, "file_name": "000000397760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000397760.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 23:05:45", "flickr_url": "http://farm3.staticflickr.com/2673/5805660472_f6edff5211_z.jpg", "id": 397760}, {"license": 2, "file_name": "000000078274.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000078274.jpg", "height": 360, "width": 640, "date_captured": "2013-11-22 03:23:52", "flickr_url": "http://farm4.staticflickr.com/3187/3086663580_946cbc5d64_z.jpg", "id": 78274}, {"license": 1, "file_name": "000000258505.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000258505.jpg", "height": 476, "width": 640, "date_captured": "2013-11-22 02:35:38", "flickr_url": "http://farm7.staticflickr.com/6173/6262066131_2d33414b03_z.jpg", "id": 258505}, {"license": 3, "file_name": "000000119244.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000119244.jpg", "height": 479, "width": 640, "date_captured": "2013-11-19 21:08:12", "flickr_url": "http://farm8.staticflickr.com/7200/6974409207_9fc948f40f_z.jpg", "id": 119244}, {"license": 2, "file_name": "000000455117.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000455117.jpg", "height": 507, "width": 640, "date_captured": "2013-11-18 03:37:30", "flickr_url": "http://farm4.staticflickr.com/3748/9934064833_3c59f8e312_z.jpg", "id": 455117}, {"license": 1, "file_name": "000000209356.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000209356.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 13:44:46", "flickr_url": "http://farm6.staticflickr.com/5350/9342927035_7c0e5d8a42_z.jpg", "id": 209356}, {"license": 2, "file_name": "000000422354.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000422354.jpg", "height": 428, "width": 640, "date_captured": "2013-11-18 01:19:18", "flickr_url": "http://farm6.staticflickr.com/5110/5775929206_d54390439d_z.jpg", "id": 422354}, {"license": 1, "file_name": "000000430555.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000430555.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 22:55:29", "flickr_url": "http://farm6.staticflickr.com/5017/5387981229_d9efb3cb4f_z.jpg", "id": 430555}, {"license": 4, "file_name": "000000258538.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000258538.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 04:00:58", "flickr_url": "http://farm3.staticflickr.com/2130/2261809679_c1faf5772f_z.jpg", "id": 258538}, {"license": 3, "file_name": "000000094702.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000094702.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 01:32:44", "flickr_url": "http://farm4.staticflickr.com/3456/3983873976_ccd960cc30_z.jpg", "id": 94702}, {"license": 1, "file_name": "000000479734.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000479734.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 22:39:19", "flickr_url": "http://farm7.staticflickr.com/6200/6115638412_e144d8f601_z.jpg", "id": 479734}, {"license": 1, "file_name": "000000520696.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000520696.jpg", "height": 640, "width": 478, "date_captured": "2013-11-21 23:11:00", "flickr_url": "http://farm4.staticflickr.com/3551/5704960972_ef6c1aff11_z.jpg", "id": 520696}, {"license": 2, "file_name": "000000061951.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000061951.jpg", "height": 476, "width": 640, "date_captured": "2013-11-15 20:12:11", "flickr_url": "http://farm8.staticflickr.com/7153/6802984869_29f0598f49_z.jpg", "id": 61951}, {"license": 4, "file_name": "000000135694.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000135694.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 00:08:02", "flickr_url": "http://farm1.staticflickr.com/170/449652035_28e5b27b2c_z.jpg", "id": 135694}, {"license": 3, "file_name": "000000250387.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000250387.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 19:26:16", "flickr_url": "http://farm3.staticflickr.com/2644/3853327002_2f42cf0a99_z.jpg", "id": 250387}, {"license": 1, "file_name": "000000012824.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000012824.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 04:40:02", "flickr_url": "http://farm5.staticflickr.com/4009/4192307066_aab42e71c2_z.jpg", "id": 12824}, {"license": 5, "file_name": "000000569889.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000569889.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 16:46:08", "flickr_url": "http://farm5.staticflickr.com/4127/5057850392_2f0d29e659_z.jpg", "id": 569889}, {"license": 5, "file_name": "000000512561.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000512561.jpg", "height": 640, "width": 425, "date_captured": "2013-11-21 20:21:03", "flickr_url": "http://farm9.staticflickr.com/8437/7903233858_f7899e35b7_z.jpg", "id": 512561}, {"license": 4, "file_name": "000000356916.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000356916.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 19:48:58", "flickr_url": "http://farm4.staticflickr.com/3212/2664832048_52282ce599_z.jpg", "id": 356916}, {"license": 4, "file_name": "000000340535.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000340535.jpg", "height": 640, "width": 480, "date_captured": "2013-11-25 20:50:38", "flickr_url": "http://farm4.staticflickr.com/3159/2785838648_4621300bf9_z.jpg", "id": 340535}, {"license": 4, "file_name": "000000487992.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000487992.jpg", "height": 550, "width": 413, "date_captured": "2013-11-18 02:57:49", "flickr_url": "http://farm8.staticflickr.com/7069/6818511074_a0a7a9c634_z.jpg", "id": 487992}, {"license": 4, "file_name": "000000160313.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000160313.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 10:25:16", "flickr_url": "http://farm9.staticflickr.com/8119/8685686369_176f001baa_z.jpg", "id": 160313}, {"license": 1, "file_name": "000000209467.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000209467.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 03:26:14", "flickr_url": "http://farm4.staticflickr.com/3080/3118825412_ab6aa87c79_z.jpg", "id": 209467}, {"license": 2, "file_name": "000000266816.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000266816.jpg", "height": 432, "width": 640, "date_captured": "2013-11-16 23:08:54", "flickr_url": "http://farm5.staticflickr.com/4138/4930002673_1fa9370fe9_z.jpg", "id": 266816}, {"license": 1, "file_name": "000000332385.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332385.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 20:50:59", "flickr_url": "http://farm4.staticflickr.com/3147/2623162935_476e6e29de_z.jpg", "id": 332385}, {"license": 3, "file_name": "000000537196.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000537196.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 14:41:54", "flickr_url": "http://farm3.staticflickr.com/2443/3628369800_33becbf509_z.jpg", "id": 537196}, {"license": 4, "file_name": "000000389743.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000389743.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 03:24:06", "flickr_url": "http://farm8.staticflickr.com/7237/7326142898_bdbb6da08c_z.jpg", "id": 389743}, {"license": 3, "file_name": "000000045680.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000045680.jpg", "height": 500, "width": 375, "date_captured": "2013-11-22 19:13:04", "flickr_url": "http://farm2.staticflickr.com/1417/1118239917_226d75b2c2_z.jpg", "id": 45680}, {"license": 4, "file_name": "000000258679.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000258679.jpg", "height": 479, "width": 640, "date_captured": "2013-11-18 08:16:11", "flickr_url": "http://farm8.staticflickr.com/7157/6452452909_aeac7b0964_z.jpg", "id": 258679}, {"license": 3, "file_name": "000000160380.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000160380.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 12:13:52", "flickr_url": "http://farm8.staticflickr.com/7216/7254027236_e64bb080b1_z.jpg", "id": 160380}, {"license": 3, "file_name": "000000086654.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000086654.jpg", "height": 426, "width": 640, "date_captured": "2013-11-23 03:30:38", "flickr_url": "http://farm3.staticflickr.com/2496/4242791028_c575a81293_z.jpg", "id": 86654}, {"license": 4, "file_name": "000000209537.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000209537.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 23:35:35", "flickr_url": "http://farm9.staticflickr.com/8545/8713841843_15b698c42c_z.jpg", "id": 209537}, {"license": 2, "file_name": "000000488073.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000488073.jpg", "height": 432, "width": 288, "date_captured": "2013-11-22 22:51:34", "flickr_url": "http://farm4.staticflickr.com/3030/2514625629_ce34b46f24_z.jpg", "id": 488073}, {"license": 3, "file_name": "000000365205.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000365205.jpg", "height": 534, "width": 640, "date_captured": "2013-11-17 20:24:34", "flickr_url": "http://farm6.staticflickr.com/5207/5231502714_4d3c67cd36_z.jpg", "id": 365205}, {"license": 1, "file_name": "000000291493.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000291493.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:34:40", "flickr_url": "http://farm3.staticflickr.com/2451/4056686235_cae24c3dac_z.jpg", "id": 291493}, {"license": 7, "file_name": "000000332459.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332459.jpg", "height": 640, "width": 478, "date_captured": "2013-11-19 18:29:34", "flickr_url": "http://farm3.staticflickr.com/2806/9287614381_81e8326d1e_z.jpg", "id": 332459}, {"license": 5, "file_name": "000000152237.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000152237.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 01:09:48", "flickr_url": "http://farm9.staticflickr.com/8165/7618410948_fccd00f781_z.jpg", "id": 152237}, {"license": 6, "file_name": "000000365231.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000365231.jpg", "height": 318, "width": 640, "date_captured": "2013-11-17 05:56:19", "flickr_url": "http://farm3.staticflickr.com/2811/9439343006_705050ca36_z.jpg", "id": 365231}, {"license": 2, "file_name": "000000209603.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000209603.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 05:38:44", "flickr_url": "http://farm5.staticflickr.com/4029/4657819877_56f8da66fa_z.jpg", "id": 209603}, {"license": 1, "file_name": "000000004830.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000004830.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 06:04:30", "flickr_url": "http://farm7.staticflickr.com/6194/6074586695_356fc64c1d_z.jpg", "id": 4830}, {"license": 1, "file_name": "000000070380.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000070380.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 06:06:58", "flickr_url": "http://farm5.staticflickr.com/4084/5022239900_56f910164f_z.jpg", "id": 70380}, {"license": 1, "file_name": "000000537337.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000537337.jpg", "height": 375, "width": 500, "date_captured": "2013-11-17 21:06:39", "flickr_url": "http://farm1.staticflickr.com/43/97843490_c1fa85fa9d_z.jpg", "id": 537337}, {"license": 3, "file_name": "000000226046.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000226046.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 13:58:52", "flickr_url": "http://farm6.staticflickr.com/5441/9194878905_b8e56b1494_z.jpg", "id": 226046}, {"license": 3, "file_name": "000000398083.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000398083.jpg", "height": 640, "width": 478, "date_captured": "2013-11-19 19:25:35", "flickr_url": "http://farm6.staticflickr.com/5230/5723941613_045e895f72_z.jpg", "id": 398083}, {"license": 4, "file_name": "000000348935.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000348935.jpg", "height": 640, "width": 529, "date_captured": "2013-11-16 18:33:43", "flickr_url": "http://farm2.staticflickr.com/1376/5098548581_fc25a26fa3_z.jpg", "id": 348935}, {"license": 2, "file_name": "000000029473.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000029473.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 07:51:34", "flickr_url": "http://farm1.staticflickr.com/47/177395958_2c3148fcd8_z.jpg", "id": 29473}, {"license": 2, "file_name": "000000217893.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000217893.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 01:48:19", "flickr_url": "http://farm1.staticflickr.com/27/40239086_c772cc58ba_z.jpg", "id": 217893}, {"license": 4, "file_name": "000000365351.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000365351.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 20:55:20", "flickr_url": "http://farm5.staticflickr.com/4108/5434069257_0b154f3812_z.jpg", "id": 365351}, {"license": 3, "file_name": "000000095018.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000095018.jpg", "height": 452, "width": 640, "date_captured": "2013-11-22 23:03:32", "flickr_url": "http://farm2.staticflickr.com/1225/544310236_62ddc4fac7_z.jpg", "id": 95018}, {"license": 3, "file_name": "000000119604.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000119604.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 17:39:47", "flickr_url": "http://farm8.staticflickr.com/7288/9346709206_4078525a64_z.jpg", "id": 119604}, {"license": 3, "file_name": "000000062263.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000062263.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 01:18:43", "flickr_url": "http://farm9.staticflickr.com/8323/8094877139_d2eb4640e5_z.jpg", "id": 62263}, {"license": 5, "file_name": "000000381759.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000381759.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 21:26:30", "flickr_url": "http://farm8.staticflickr.com/7154/6796826455_b707bebed4_z.jpg", "id": 381759}, {"license": 1, "file_name": "000000480064.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000480064.jpg", "height": 354, "width": 640, "date_captured": "2013-11-16 20:11:37", "flickr_url": "http://farm6.staticflickr.com/5323/9729641847_14f817308d_z.jpg", "id": 480064}, {"license": 4, "file_name": "000000578369.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000578369.jpg", "height": 612, "width": 612, "date_captured": "2013-11-24 23:13:31", "flickr_url": "http://farm9.staticflickr.com/8255/8995912326_c3d324a967_z.jpg", "id": 578369}, {"license": 5, "file_name": "000000332613.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000332613.jpg", "height": 375, "width": 500, "date_captured": "2013-11-23 03:05:54", "flickr_url": "http://farm5.staticflickr.com/4031/4426910283_93a7eb81a7_z.jpg", "id": 332613}, {"license": 1, "file_name": "000000291658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000291658.jpg", "height": 640, "width": 480, "date_captured": "2013-11-17 11:18:54", "flickr_url": "http://farm9.staticflickr.com/8044/8104146878_04fa8e3bb9_z.jpg", "id": 291658}, {"license": 4, "file_name": "000000062295.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000062295.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 23:06:42", "flickr_url": "http://farm6.staticflickr.com/5127/5327079443_55c91f8469_z.jpg", "id": 62295}, {"license": 2, "file_name": "000000398172.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000398172.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 04:43:13", "flickr_url": "http://farm9.staticflickr.com/8496/8421807456_bdd344ec3c_z.jpg", "id": 398172}, {"license": 1, "file_name": "000000275297.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000275297.jpg", "height": 500, "width": 375, "date_captured": "2013-11-18 15:51:25", "flickr_url": "http://farm3.staticflickr.com/2792/4093445217_6fd68bd1fa_z.jpg", "id": 275297}, {"license": 1, "file_name": "000000447349.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000447349.jpg", "height": 500, "width": 375, "date_captured": "2013-11-24 02:55:59", "flickr_url": "http://farm3.staticflickr.com/2079/1566776347_1fdf7e75eb_z.jpg", "id": 447349}, {"license": 1, "file_name": "000000217978.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000217978.jpg", "height": 424, "width": 640, "date_captured": "2013-11-18 13:36:11", "flickr_url": "http://farm7.staticflickr.com/6147/5955314494_a1618c4fee_z.jpg", "id": 217978}, {"license": 6, "file_name": "000000177019.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000177019.jpg", "height": 329, "width": 640, "date_captured": "2013-11-15 14:48:49", "flickr_url": "http://farm5.staticflickr.com/4144/5031586645_7006fd476f_z.jpg", "id": 177019}, {"license": 1, "file_name": "000000226176.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000226176.jpg", "height": 438, "width": 640, "date_captured": "2013-11-15 14:49:54", "flickr_url": "http://farm6.staticflickr.com/5197/6917961294_4104e033d5_z.jpg", "id": 226176}, {"license": 5, "file_name": "000000119693.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000119693.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 20:58:29", "flickr_url": "http://farm4.staticflickr.com/3270/2675002699_c382c4673b_z.jpg", "id": 119693}, {"license": 1, "file_name": "000000447374.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000447374.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 12:49:54", "flickr_url": "http://farm5.staticflickr.com/4037/4161062823_ce1e40b956_z.jpg", "id": 447374}, {"license": 1, "file_name": "000000209809.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000209809.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 19:00:02", "flickr_url": "http://farm4.staticflickr.com/3275/2487102255_f2f55d8cb3_z.jpg", "id": 209809}, {"license": 3, "file_name": "000000136092.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000136092.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 08:37:01", "flickr_url": "http://farm3.staticflickr.com/2479/3631467922_417f2edeaa_z.jpg", "id": 136092}, {"license": 1, "file_name": "000000201634.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000201634.jpg", "height": 512, "width": 640, "date_captured": "2013-11-14 20:17:18", "flickr_url": "http://farm4.staticflickr.com/3001/2683482442_0d62ee2584_z.jpg", "id": 201634}, {"license": 1, "file_name": "000000119714.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000119714.jpg", "height": 612, "width": 612, "date_captured": "2013-11-21 04:25:16", "flickr_url": "http://farm6.staticflickr.com/5303/5600986011_21cbf2f1aa_z.jpg", "id": 119714}, {"license": 2, "file_name": "000000504744.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000504744.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 18:56:36", "flickr_url": "http://farm4.staticflickr.com/3589/3301905611_b73fd76d67_z.jpg", "id": 504744}, {"license": 1, "file_name": "000000562100.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000562100.jpg", "height": 481, "width": 640, "date_captured": "2013-11-19 18:18:32", "flickr_url": "http://farm5.staticflickr.com/4045/4405303375_a452070dc5_z.jpg", "id": 562100}, {"license": 3, "file_name": "000000283573.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000283573.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 23:04:02", "flickr_url": "http://farm2.staticflickr.com/1007/529686971_9e91e1b140_z.jpg", "id": 283573}, {"license": 1, "file_name": "000000095185.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000095185.jpg", "height": 612, "width": 612, "date_captured": "2013-11-14 21:39:48", "flickr_url": "http://farm9.staticflickr.com/8019/7381677182_78b17d408a_z.jpg", "id": 95185}, {"license": 2, "file_name": "000000578523.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000578523.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 05:58:35", "flickr_url": "http://farm3.staticflickr.com/2044/2136694312_6c159a8836_z.jpg", "id": 578523}, {"license": 2, "file_name": "000000373727.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000373727.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 21:55:22", "flickr_url": "http://farm8.staticflickr.com/7347/9322864093_0987d4b409_z.jpg", "id": 373727}, {"license": 5, "file_name": "000000381923.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000381923.jpg", "height": 640, "width": 425, "date_captured": "2013-11-21 05:01:45", "flickr_url": "http://farm5.staticflickr.com/4083/5077261977_ec87fc331e_z.jpg", "id": 381923}, {"license": 1, "file_name": "000000037862.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000037862.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 19:01:32", "flickr_url": "http://farm8.staticflickr.com/7041/6862172236_ccdb72fb79_z.jpg", "id": 37862}, {"license": 1, "file_name": "000000283624.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000283624.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 12:24:50", "flickr_url": "http://farm1.staticflickr.com/27/35568292_2671c6eb1a_z.jpg", "id": 283624}, {"license": 3, "file_name": "000000480240.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000480240.jpg", "height": 640, "width": 460, "date_captured": "2013-11-19 18:19:41", "flickr_url": "http://farm5.staticflickr.com/4024/4658678644_5b3ea3169f_z.jpg", "id": 480240}, {"license": 4, "file_name": "000000357362.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000357362.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 22:56:53", "flickr_url": "http://farm4.staticflickr.com/3073/5860135069_36f5ddcfb7_z.jpg", "id": 357362}, {"license": 3, "file_name": "000000562176.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000562176.jpg", "height": 341, "width": 640, "date_captured": "2013-11-15 15:36:42", "flickr_url": "http://farm8.staticflickr.com/7321/9170802006_2734814bd7_z.jpg", "id": 562176}, {"license": 3, "file_name": "000000103430.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000103430.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 09:12:07", "flickr_url": "http://farm1.staticflickr.com/78/277732222_2d8a9fffc8_z.jpg", "id": 103430}, {"license": 3, "file_name": "000000431112.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000431112.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 15:49:34", "flickr_url": "http://farm6.staticflickr.com/5143/5794895674_1a9cd74e37_z.jpg", "id": 431112}, {"license": 3, "file_name": "000000054282.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000054282.jpg", "height": 425, "width": 640, "date_captured": "2013-11-19 22:10:52", "flickr_url": "http://farm6.staticflickr.com/5069/5627014184_0ba6a25c19_z.jpg", "id": 54282}, {"license": 3, "file_name": "000000300047.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000300047.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 23:32:39", "flickr_url": "http://farm4.staticflickr.com/3618/3600052493_95b6688265_z.jpg", "id": 300047}, {"license": 2, "file_name": "000000234516.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000234516.jpg", "height": 350, "width": 416, "date_captured": "2013-11-17 15:02:28", "flickr_url": "http://farm9.staticflickr.com/8469/8120681934_3679f90947_z.jpg", "id": 234516}, {"license": 3, "file_name": "000000439325.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000439325.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:14:16", "flickr_url": "http://farm9.staticflickr.com/8036/8024561235_4e55801068_z.jpg", "id": 439325}, {"license": 3, "file_name": "000000545832.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000545832.jpg", "height": 485, "width": 640, "date_captured": "2013-11-17 11:16:38", "flickr_url": "http://farm4.staticflickr.com/3533/5772170785_8529e29b1a_z.jpg", "id": 545832}, {"license": 4, "file_name": "000000054318.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000054318.jpg", "height": 429, "width": 640, "date_captured": "2013-11-21 01:34:03", "flickr_url": "http://farm6.staticflickr.com/5465/7143168351_c89b01d3a3_z.jpg", "id": 54318}, {"license": 4, "file_name": "000000554031.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000554031.jpg", "height": 375, "width": 500, "date_captured": "2013-11-25 21:27:49", "flickr_url": "http://farm1.staticflickr.com/51/183207824_45c944d7e0_z.jpg", "id": 554031}, {"license": 1, "file_name": "000000259120.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000259120.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 23:32:21", "flickr_url": "http://farm1.staticflickr.com/155/424801853_1d8647d4e8_z.jpg", "id": 259120}, {"license": 5, "file_name": "000000291897.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000291897.jpg", "height": 360, "width": 640, "date_captured": "2013-11-20 12:06:14", "flickr_url": "http://farm4.staticflickr.com/3633/3620167733_00014815dd_z.jpg", "id": 291897}, {"license": 2, "file_name": "000000545850.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000545850.jpg", "height": 494, "width": 640, "date_captured": "2013-11-16 20:36:38", "flickr_url": "http://farm8.staticflickr.com/7364/9400125810_137d291662_z.jpg", "id": 545850}, {"license": 5, "file_name": "000000160852.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000160852.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 00:41:45", "flickr_url": "http://farm6.staticflickr.com/5082/5293549136_f388052301_z.jpg", "id": 160852}, {"license": 1, "file_name": "000000447574.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000447574.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 15:16:26", "flickr_url": "http://farm8.staticflickr.com/7026/6555105539_bee482c7bb_z.jpg", "id": 447574}, {"license": 4, "file_name": "000000070745.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000070745.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 06:43:30", "flickr_url": "http://farm7.staticflickr.com/6186/6122119090_21ee0d03fb_z.jpg", "id": 70745}, {"license": 3, "file_name": "000000021595.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000021595.jpg", "height": 478, "width": 640, "date_captured": "2013-11-21 04:58:39", "flickr_url": "http://farm5.staticflickr.com/4085/5185492295_b3de2b9427_z.jpg", "id": 21595}, {"license": 1, "file_name": "000000496732.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000496732.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 17:38:51", "flickr_url": "http://farm3.staticflickr.com/2423/3873807089_e7ab147d12_z.jpg", "id": 496732}, {"license": 5, "file_name": "000000357470.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000357470.jpg", "height": 423, "width": 640, "date_captured": "2013-11-17 21:56:17", "flickr_url": "http://farm4.staticflickr.com/3257/3254046150_8ba6543077_z.jpg", "id": 357470}, {"license": 4, "file_name": "000000160866.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000160866.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 20:40:28", "flickr_url": "http://farm5.staticflickr.com/4072/4700083100_6a2316faf6_z.jpg", "id": 160866}, {"license": 5, "file_name": "000000070755.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000070755.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 06:04:16", "flickr_url": "http://farm7.staticflickr.com/6200/6120486618_d898e2de55_z.jpg", "id": 70755}, {"license": 2, "file_name": "000000513124.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513124.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 21:06:44", "flickr_url": "http://farm3.staticflickr.com/2136/2539441771_5703371b4d_z.jpg", "id": 513124}, {"license": 3, "file_name": "000000521338.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000521338.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 00:52:28", "flickr_url": "http://farm8.staticflickr.com/7409/8812440350_eeb35cf032_z.jpg", "id": 521338}, {"license": 1, "file_name": "000000103556.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000103556.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 04:45:51", "flickr_url": "http://farm6.staticflickr.com/5211/5495849988_f17317b5de_z.jpg", "id": 103556}, {"license": 2, "file_name": "000000136331.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000136331.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 22:30:41", "flickr_url": "http://farm8.staticflickr.com/7345/9231451152_f48de4757c_z.jpg", "id": 136331}, {"license": 1, "file_name": "000000316557.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000316557.jpg", "height": 640, "width": 604, "date_captured": "2013-11-19 23:41:56", "flickr_url": "http://farm5.staticflickr.com/4118/4743038566_941571cf15_z.jpg", "id": 316557}, {"license": 4, "file_name": "000000193682.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000193682.jpg", "height": 640, "width": 424, "date_captured": "2013-11-21 03:09:39", "flickr_url": "http://farm8.staticflickr.com/7130/7680448560_8c7c9b7d41_z.jpg", "id": 193682}, {"license": 1, "file_name": "000000545948.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000545948.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 23:15:38", "flickr_url": "http://farm9.staticflickr.com/8228/8510186512_e503f333cb_z.jpg", "id": 545948}, {"license": 3, "file_name": "000000177314.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000177314.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 14:25:07", "flickr_url": "http://farm8.staticflickr.com/7153/6829836271_4137647f2d_z.jpg", "id": 177314}, {"license": 6, "file_name": "000000201897.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000201897.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 00:01:07", "flickr_url": "http://farm1.staticflickr.com/131/357054973_c0d4c16b46_z.jpg", "id": 201897}, {"license": 1, "file_name": "000000087214.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000087214.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 06:27:48", "flickr_url": "http://farm4.staticflickr.com/3585/3457544692_88b11f5b2f_z.jpg", "id": 87214}, {"license": 3, "file_name": "000000455874.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000455874.jpg", "height": 427, "width": 640, "date_captured": "2013-11-14 19:24:46", "flickr_url": "http://farm9.staticflickr.com/8510/8413358918_5624a56ee5_z.jpg", "id": 455874}, {"license": 2, "file_name": "000000480451.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000480451.jpg", "height": 640, "width": 425, "date_captured": "2013-11-21 05:37:22", "flickr_url": "http://farm5.staticflickr.com/4024/4498260036_e089da5551_z.jpg", "id": 480451}, {"license": 1, "file_name": "000000513221.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513221.jpg", "height": 428, "width": 640, "date_captured": "2013-11-20 21:14:06", "flickr_url": "http://farm9.staticflickr.com/8517/8475396084_489e9cee5c_z.jpg", "id": 513221}, {"license": 1, "file_name": "000000177353.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000177353.jpg", "height": 485, "width": 640, "date_captured": "2013-11-16 22:08:31", "flickr_url": "http://farm3.staticflickr.com/2648/3835010202_e4cb84334c_z.jpg", "id": 177353}, {"license": 5, "file_name": "000000275658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000275658.jpg", "height": 360, "width": 640, "date_captured": "2013-11-19 03:27:28", "flickr_url": "http://farm9.staticflickr.com/8088/8427404051_1c9f587f73_z.jpg", "id": 275658}, {"license": 3, "file_name": "000000234699.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000234699.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 17:07:23", "flickr_url": "http://farm4.staticflickr.com/3158/2865986124_b76dedb194_z.jpg", "id": 234699}, {"license": 1, "file_name": "000000529624.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000529624.jpg", "height": 640, "width": 640, "date_captured": "2013-11-21 04:18:34", "flickr_url": "http://farm6.staticflickr.com/5040/5882565072_e8613589e1_z.jpg", "id": 529624}, {"license": 1, "file_name": "000000226527.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000226527.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 18:21:07", "flickr_url": "http://farm6.staticflickr.com/5139/5387582395_c393afafe4_z.jpg", "id": 226527}, {"license": 2, "file_name": "000000349408.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000349408.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 21:44:56", "flickr_url": "http://farm9.staticflickr.com/8191/8087183558_908499507b_z.jpg", "id": 349408}, {"license": 1, "file_name": "000000316671.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000316671.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 01:39:51", "flickr_url": "http://farm2.staticflickr.com/1111/1390234722_d08661a7cb_z.jpg", "id": 316671}, {"license": 1, "file_name": "000000079111.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000079111.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 14:12:14", "flickr_url": "http://farm3.staticflickr.com/2681/4164657479_9409f79861_z.jpg", "id": 79111}, {"license": 3, "file_name": "000000161031.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000161031.jpg", "height": 333, "width": 500, "date_captured": "2013-11-20 14:36:27", "flickr_url": "http://farm3.staticflickr.com/2784/4252974942_27e4bdc9b3_z.jpg", "id": 161031}, {"license": 3, "file_name": "000000029962.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000029962.jpg", "height": 640, "width": 425, "date_captured": "2013-11-14 12:50:53", "flickr_url": "http://farm4.staticflickr.com/3207/5719448272_b36f303437_z.jpg", "id": 29962}, {"license": 5, "file_name": "000000210187.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000210187.jpg", "height": 457, "width": 640, "date_captured": "2013-11-20 15:06:01", "flickr_url": "http://farm5.staticflickr.com/4022/5075243220_f155efd192_z.jpg", "id": 210187}, {"license": 1, "file_name": "000000562456.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000562456.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 14:27:44", "flickr_url": "http://farm9.staticflickr.com/8210/8159937988_e428b9a0fc_z.jpg", "id": 562456}, {"license": 5, "file_name": "000000529689.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000529689.jpg", "height": 640, "width": 425, "date_captured": "2013-11-17 04:34:55", "flickr_url": "http://farm5.staticflickr.com/4082/4953885107_3cbb587247_z.jpg", "id": 529689}, {"license": 3, "file_name": "000000546078.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000546078.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 22:52:11", "flickr_url": "http://farm9.staticflickr.com/8242/8623203768_6a1f48ccde_z.jpg", "id": 546078}, {"license": 5, "file_name": "000000357663.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000357663.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 07:15:07", "flickr_url": "http://farm2.staticflickr.com/1078/1087162648_28314f1cbf_z.jpg", "id": 357663}, {"license": 3, "file_name": "000000095518.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000095518.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 13:25:19", "flickr_url": "http://farm8.staticflickr.com/7064/7132865345_9884f0e5e5_z.jpg", "id": 95518}, {"license": 3, "file_name": "000000062759.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000062759.jpg", "height": 640, "width": 425, "date_captured": "2013-11-19 20:47:09", "flickr_url": "http://farm8.staticflickr.com/7263/7478421714_f8ce0678a3_z.jpg", "id": 62759}, {"license": 1, "file_name": "000000562474.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000562474.jpg", "height": 392, "width": 640, "date_captured": "2013-11-24 15:25:17", "flickr_url": "http://farm3.staticflickr.com/2505/4005141340_be6199eab4_z.jpg", "id": 562474}, {"license": 3, "file_name": "000000054572.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000054572.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 14:06:52", "flickr_url": "http://farm9.staticflickr.com/8022/7526842856_ca6a8e3b4c_z.jpg", "id": 54572}, {"license": 5, "file_name": "000000234819.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000234819.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 21:27:43", "flickr_url": "http://farm8.staticflickr.com/7024/6663166583_97a0d6991c_z.jpg", "id": 234819}, {"license": 3, "file_name": "000000390474.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000390474.jpg", "height": 468, "width": 640, "date_captured": "2013-11-18 11:29:26", "flickr_url": "http://farm2.staticflickr.com/1353/1372648227_e0bd85b3ab_z.jpg", "id": 390474}, {"license": 3, "file_name": "000000152922.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000152922.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 08:07:30", "flickr_url": "http://farm4.staticflickr.com/3374/3318417101_2a85e556dc_z.jpg", "id": 152922}, {"license": 2, "file_name": "000000202076.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000202076.jpg", "height": 640, "width": 426, "date_captured": "2013-11-18 10:41:23", "flickr_url": "http://farm6.staticflickr.com/5067/5594038630_1c3cd75b77_z.jpg", "id": 202076}, {"license": 3, "file_name": "000000390496.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000390496.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 04:48:50", "flickr_url": "http://farm1.staticflickr.com/123/342159727_37b942d65e_z.jpg", "id": 390496}, {"license": 3, "file_name": "000000103778.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000103778.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 23:56:44", "flickr_url": "http://farm9.staticflickr.com/8237/8561389548_98dddccb3a_z.jpg", "id": 103778}, {"license": 3, "file_name": "000000210279.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000210279.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 17:29:38", "flickr_url": "http://farm9.staticflickr.com/8455/8047730039_72af8a1bb3_z.jpg", "id": 210279}, {"license": 3, "file_name": "000000259443.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000259443.jpg", "height": 360, "width": 640, "date_captured": "2013-11-21 02:14:12", "flickr_url": "http://farm4.staticflickr.com/3720/9296281270_b47cd37ce1_z.jpg", "id": 259443}, {"license": 1, "file_name": "000000243066.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000243066.jpg", "height": 500, "width": 333, "date_captured": "2013-11-20 06:53:59", "flickr_url": "http://farm4.staticflickr.com/3386/3477813665_9c1112db3d_z.jpg", "id": 243066}, {"license": 3, "file_name": "000000128398.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000128398.jpg", "height": 429, "width": 640, "date_captured": "2013-11-21 04:15:06", "flickr_url": "http://farm6.staticflickr.com/5104/5662007321_914c0194d8_z.jpg", "id": 128398}, {"license": 2, "file_name": "000000390565.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000390565.jpg", "height": 425, "width": 640, "date_captured": "2013-11-15 20:48:01", "flickr_url": "http://farm4.staticflickr.com/3799/9438438189_6b301d838d_z.jpg", "id": 390565}, {"license": 3, "file_name": "000000578990.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000578990.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 07:01:29", "flickr_url": "http://farm4.staticflickr.com/3536/3268020209_fbccd01dcc_z.jpg", "id": 578990}, {"license": 4, "file_name": "000000292271.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000292271.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 19:15:40", "flickr_url": "http://farm4.staticflickr.com/3536/3889833692_4da6615955_z.jpg", "id": 292271}, {"license": 3, "file_name": "000000423343.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000423343.jpg", "height": 375, "width": 500, "date_captured": "2013-11-23 20:22:05", "flickr_url": "http://farm1.staticflickr.com/67/183262362_2745f7dfc1_z.jpg", "id": 423343}, {"license": 2, "file_name": "000000259514.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000259514.jpg", "height": 440, "width": 640, "date_captured": "2013-11-24 01:31:26", "flickr_url": "http://farm3.staticflickr.com/2652/4088497658_9999629bbc_z.jpg", "id": 259514}, {"license": 1, "file_name": "000000071099.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000071099.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:02:43", "flickr_url": "http://farm9.staticflickr.com/8476/8364239417_af12d36114_z.jpg", "id": 71099}, {"license": 2, "file_name": "000000210363.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000210363.jpg", "height": 536, "width": 640, "date_captured": "2013-11-20 00:34:46", "flickr_url": "http://farm9.staticflickr.com/8508/8526841036_a105e1c7fe_z.jpg", "id": 210363}, {"license": 2, "file_name": "000000095676.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000095676.jpg", "height": 427, "width": 640, "date_captured": "2013-11-23 01:01:38", "flickr_url": "http://farm8.staticflickr.com/7060/6799287788_8bbde41fc5_z.jpg", "id": 95676}, {"license": 3, "file_name": "000000136651.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000136651.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 22:40:56", "flickr_url": "http://farm8.staticflickr.com/7264/6906835878_c2d159efbf_z.jpg", "id": 136651}, {"license": 3, "file_name": "000000275917.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000275917.jpg", "height": 531, "width": 640, "date_captured": "2013-11-20 06:44:54", "flickr_url": "http://farm3.staticflickr.com/2499/3869276354_c83ca221c3_z.jpg", "id": 275917}, {"license": 1, "file_name": "000000005587.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000005587.jpg", "height": 612, "width": 612, "date_captured": "2013-11-20 14:49:08", "flickr_url": "http://farm8.staticflickr.com/7250/7562029954_769f683222_z.jpg", "id": 5587}, {"license": 5, "file_name": "000000439765.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000439765.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 06:05:13", "flickr_url": "http://farm4.staticflickr.com/3106/3156796784_25e3933979_z.jpg", "id": 439765}, {"license": 5, "file_name": "000000292315.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000292315.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 20:53:41", "flickr_url": "http://farm4.staticflickr.com/3630/3457694758_5b756e4b9b_z.jpg", "id": 292315}, {"license": 4, "file_name": "000000128475.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000128475.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 16:54:03", "flickr_url": "http://farm4.staticflickr.com/3090/4561667437_109a8ed061_z.jpg", "id": 128475}, {"license": 5, "file_name": "000000087522.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000087522.jpg", "height": 640, "width": 480, "date_captured": "2013-11-19 21:54:27", "flickr_url": "http://farm4.staticflickr.com/3649/3481104770_ca99910eb6_z.jpg", "id": 87522}, {"license": 6, "file_name": "000000349686.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000349686.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 21:49:04", "flickr_url": "http://farm3.staticflickr.com/2448/3893322677_b5122c0f0b_z.jpg", "id": 349686}, {"license": 5, "file_name": "000000333302.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000333302.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 14:45:02", "flickr_url": "http://farm8.staticflickr.com/7161/6689004797_b853f52a67_z.jpg", "id": 333302}, {"license": 3, "file_name": "000000112122.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000112122.jpg", "height": 622, "width": 640, "date_captured": "2013-11-18 08:17:59", "flickr_url": "http://farm5.staticflickr.com/4034/4598013267_d98bbc9fa3_z.jpg", "id": 112122}, {"license": 1, "file_name": "000000538108.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000538108.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 08:46:13", "flickr_url": "http://farm6.staticflickr.com/5523/9146137666_53d9727261_z.jpg", "id": 538108}, {"license": 3, "file_name": "000000521726.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000521726.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 16:06:58", "flickr_url": "http://farm6.staticflickr.com/5006/5276586123_c03578c68e_z.jpg", "id": 521726}, {"license": 5, "file_name": "000000046592.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000046592.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 03:48:06", "flickr_url": "http://farm4.staticflickr.com/3311/3516874010_fb1d01ea4e_z.jpg", "id": 46592}, {"license": 2, "file_name": "000000226817.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000226817.jpg", "height": 429, "width": 640, "date_captured": "2013-11-21 21:05:05", "flickr_url": "http://farm4.staticflickr.com/3557/3323960437_acd6affb46_z.jpg", "id": 226817}, {"license": 1, "file_name": "000000382469.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000382469.jpg", "height": 529, "width": 640, "date_captured": "2013-11-18 03:36:07", "flickr_url": "http://farm3.staticflickr.com/2025/2198861535_69543b34ce_z.jpg", "id": 382469}, {"license": 2, "file_name": "000000529929.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000529929.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 17:53:58", "flickr_url": "http://farm3.staticflickr.com/2785/4378549086_90aa3e25eb_z.jpg", "id": 529929}, {"license": 4, "file_name": "000000030231.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000030231.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 12:08:29", "flickr_url": "http://farm4.staticflickr.com/3493/3743124203_949f6ebae7_z.jpg", "id": 30231}, {"license": 1, "file_name": "000000480797.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000480797.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 22:55:16", "flickr_url": "http://farm3.staticflickr.com/2531/3911658326_403b463eee_z.jpg", "id": 480797}, {"license": 5, "file_name": "000000136736.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000136736.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 09:08:32", "flickr_url": "http://farm6.staticflickr.com/5340/9048907015_62047cbb99_z.jpg", "id": 136736}, {"license": 3, "file_name": "000000538155.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000538155.jpg", "height": 640, "width": 426, "date_captured": "2013-11-19 20:29:31", "flickr_url": "http://farm3.staticflickr.com/2007/2338682702_8ded15e5a3_z.jpg", "id": 538155}, {"license": 6, "file_name": "000000071229.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000071229.jpg", "height": 480, "width": 328, "date_captured": "2013-11-23 11:32:54", "flickr_url": "http://farm2.staticflickr.com/1053/1320763641_57bf4bcf78_z.jpg", "id": 71229}, {"license": 1, "file_name": "000000095809.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000095809.jpg", "height": 640, "width": 427, "date_captured": "2013-11-20 11:51:30", "flickr_url": "http://farm4.staticflickr.com/3265/3142859074_17e4fa1190_z.jpg", "id": 95809}, {"license": 3, "file_name": "000000366148.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000366148.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 18:23:35", "flickr_url": "http://farm3.staticflickr.com/2729/4314403730_558f13b065_z.jpg", "id": 366148}, {"license": 2, "file_name": "000000538196.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000538196.jpg", "height": 640, "width": 640, "date_captured": "2013-11-24 16:21:07", "flickr_url": "http://farm8.staticflickr.com/7045/6842881856_e7f94c4869_z.jpg", "id": 538196}, {"license": 6, "file_name": "000000251493.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000251493.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 03:41:13", "flickr_url": "http://farm8.staticflickr.com/7052/6775825880_84e6754227_z.jpg", "id": 251493}, {"license": 1, "file_name": "000000243307.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000243307.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 00:01:20", "flickr_url": "http://farm4.staticflickr.com/3274/2702440581_d3c73d24a5_z.jpg", "id": 243307}, {"license": 3, "file_name": "000000218734.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000218734.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 19:36:06", "flickr_url": "http://farm5.staticflickr.com/4117/4865853370_0cfe4d123a_z.jpg", "id": 218734}, {"license": 1, "file_name": "000000505486.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000505486.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 17:03:00", "flickr_url": "http://farm6.staticflickr.com/5542/9569132569_df0124555c_z.jpg", "id": 505486}, {"license": 5, "file_name": "000000431761.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000431761.jpg", "height": 640, "width": 640, "date_captured": "2013-11-17 07:21:25", "flickr_url": "http://farm8.staticflickr.com/7391/9582430612_622087976d_z.jpg", "id": 431761}, {"license": 1, "file_name": "000000513683.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513683.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:33:55", "flickr_url": "http://farm4.staticflickr.com/3252/2609246658_c22626736f_z.jpg", "id": 513683}, {"license": 4, "file_name": "000000562835.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000562835.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 18:50:46", "flickr_url": "http://farm9.staticflickr.com/8385/8612830022_2f5a367e06_z.jpg", "id": 562835}, {"license": 4, "file_name": "000000226966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000226966.jpg", "height": 335, "width": 500, "date_captured": "2013-11-14 16:57:32", "flickr_url": "http://farm4.staticflickr.com/3048/3116617453_b6620e5e07_z.jpg", "id": 226966}, {"license": 1, "file_name": "000000038552.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000038552.jpg", "height": 479, "width": 640, "date_captured": "2013-11-16 23:25:29", "flickr_url": "http://farm3.staticflickr.com/2002/5696125346_b8febc82d3_z.jpg", "id": 38552}, {"license": 5, "file_name": "000000243354.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000243354.jpg", "height": 640, "width": 640, "date_captured": "2013-11-20 01:09:28", "flickr_url": "http://farm8.staticflickr.com/7081/7181767932_d1781d1a98_z.jpg", "id": 243354}, {"license": 5, "file_name": "000000022195.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000022195.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 06:24:47", "flickr_url": "http://farm8.staticflickr.com/7392/10101031366_d38517ca87_z.jpg", "id": 22195}, {"license": 1, "file_name": "000000169653.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000169653.jpg", "height": 504, "width": 640, "date_captured": "2013-11-22 22:45:49", "flickr_url": "http://farm4.staticflickr.com/3141/2814885390_4b9d530d6b_z.jpg", "id": 169653}, {"license": 1, "file_name": "000000267957.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000267957.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 22:19:39", "flickr_url": "http://farm6.staticflickr.com/5300/5496235507_a26989debf_z.jpg", "id": 267957}, {"license": 4, "file_name": "000000169656.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000169656.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 20:34:41", "flickr_url": "http://farm6.staticflickr.com/5482/9533764468_cec5a01f0b_z.jpg", "id": 169656}, {"license": 1, "file_name": "000000333498.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000333498.jpg", "height": 441, "width": 640, "date_captured": "2013-11-17 07:47:29", "flickr_url": "http://farm8.staticflickr.com/7288/9467673538_457e8808ae_z.jpg", "id": 333498}, {"license": 2, "file_name": "000000136894.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000136894.jpg", "height": 429, "width": 640, "date_captured": "2013-11-19 20:03:13", "flickr_url": "http://farm9.staticflickr.com/8055/8428831202_0dd8726352_z.jpg", "id": 136894}, {"license": 4, "file_name": "000000431817.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000431817.jpg", "height": 585, "width": 640, "date_captured": "2013-11-19 03:13:55", "flickr_url": "http://farm9.staticflickr.com/8512/8556006972_442f6a45f0_z.jpg", "id": 431817}, {"license": 3, "file_name": "000000505546.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000505546.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 21:28:29", "flickr_url": "http://farm5.staticflickr.com/4124/4984496355_b44d199d35_z.jpg", "id": 505546}, {"license": 1, "file_name": "000000489167.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000489167.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 08:45:45", "flickr_url": "http://farm5.staticflickr.com/4153/4984503618_7d29ffe498_z.jpg", "id": 489167}, {"license": 4, "file_name": "000000554706.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000554706.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 13:15:59", "flickr_url": "http://farm3.staticflickr.com/2338/2169075493_63cbb4031e_z.jpg", "id": 554706}, {"license": 3, "file_name": "000000513748.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513748.jpg", "height": 424, "width": 640, "date_captured": "2013-11-20 18:35:39", "flickr_url": "http://farm3.staticflickr.com/2611/3820154293_a11e2b261c_z.jpg", "id": 513748}, {"license": 5, "file_name": "000000415447.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000415447.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 19:33:54", "flickr_url": "http://farm3.staticflickr.com/2674/4021497439_1338fdf3c9_z.jpg", "id": 415447}, {"license": 4, "file_name": "000000464605.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000464605.jpg", "height": 429, "width": 640, "date_captured": "2013-11-20 04:11:59", "flickr_url": "http://farm5.staticflickr.com/4038/4381835314_b2ca1d97e6_z.jpg", "id": 464605}, {"license": 3, "file_name": "000000317149.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000317149.jpg", "height": 429, "width": 640, "date_captured": "2013-11-19 20:33:01", "flickr_url": "http://farm4.staticflickr.com/3554/3417059320_176ca4a827_z.jpg", "id": 317149}, {"license": 1, "file_name": "000000005862.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000005862.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 13:30:53", "flickr_url": "http://farm1.staticflickr.com/178/395929342_19df16eb58_z.jpg", "id": 5862}, {"license": 2, "file_name": "000000333546.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000333546.jpg", "height": 434, "width": 640, "date_captured": "2013-11-21 02:37:24", "flickr_url": "http://farm9.staticflickr.com/8101/8658970027_6eae9827e6_z.jpg", "id": 333546}, {"license": 3, "file_name": "000000497386.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000497386.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 04:33:16", "flickr_url": "http://farm9.staticflickr.com/8538/8678472399_886f8eabec_z.jpg", "id": 497386}, {"license": 1, "file_name": "000000087792.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000087792.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 15:35:43", "flickr_url": "http://farm4.staticflickr.com/3234/3125915763_1ebfab4c1d_z.jpg", "id": 87792}, {"license": 5, "file_name": "000000382707.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000382707.jpg", "height": 583, "width": 640, "date_captured": "2013-11-21 02:35:08", "flickr_url": "http://farm9.staticflickr.com/8542/8604058833_6fe0b63b3b_z.jpg", "id": 382707}, {"license": 5, "file_name": "000000079611.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000079611.jpg", "height": 425, "width": 640, "date_captured": "2013-11-24 12:23:17", "flickr_url": "http://farm8.staticflickr.com/7150/6539900111_58f48da5e2_z.jpg", "id": 79611}, {"license": 4, "file_name": "000000063238.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000063238.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 18:55:41", "flickr_url": "http://farm4.staticflickr.com/3291/2977679332_9dd2a7d7ab_z.jpg", "id": 63238}, {"license": 3, "file_name": "000000464650.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000464650.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 06:21:36", "flickr_url": "http://farm4.staticflickr.com/3039/2786431032_4dc5bb6619_z.jpg", "id": 464650}, {"license": 1, "file_name": "000000022287.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000022287.jpg", "height": 640, "width": 425, "date_captured": "2013-11-16 22:51:24", "flickr_url": "http://farm3.staticflickr.com/2459/3627778146_afaa80b091_z.jpg", "id": 22287}, {"license": 4, "file_name": "000000513811.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513811.jpg", "height": 480, "width": 640, "date_captured": "2013-11-23 04:07:01", "flickr_url": "http://farm3.staticflickr.com/2643/3941666880_606f1f95bf_z.jpg", "id": 513811}, {"license": 4, "file_name": "000000407318.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000407318.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 15:39:29", "flickr_url": "http://farm4.staticflickr.com/3108/3149563060_65978d97a4_z.jpg", "id": 407318}, {"license": 4, "file_name": "000000046885.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000046885.jpg", "height": 500, "width": 338, "date_captured": "2013-11-20 07:16:16", "flickr_url": "http://farm3.staticflickr.com/2594/3778007151_5f9e108b74_z.jpg", "id": 46885}, {"license": 3, "file_name": "000000177959.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000177959.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 13:54:48", "flickr_url": "http://farm9.staticflickr.com/8291/7624251342_179d56bdd8_z.jpg", "id": 177959}, {"license": 5, "file_name": "000000055092.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000055092.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 14:01:55", "flickr_url": "http://farm9.staticflickr.com/8089/8426778908_f7e64eb49e_z.jpg", "id": 55092}, {"license": 7, "file_name": "000000030519.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000030519.jpg", "height": 421, "width": 640, "date_captured": "2013-11-17 15:02:58", "flickr_url": "http://farm9.staticflickr.com/8388/8638556064_7a06b3400c_z.jpg", "id": 30519}, {"license": 3, "file_name": "000000030535.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000030535.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 21:50:43", "flickr_url": "http://farm3.staticflickr.com/2500/4157655408_5912a50587_z.jpg", "id": 30535}, {"license": 2, "file_name": "000000522062.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000522062.jpg", "height": 500, "width": 333, "date_captured": "2013-11-25 20:31:28", "flickr_url": "http://farm4.staticflickr.com/3501/3699306396_d8129b0a4e_z.jpg", "id": 522062}, {"license": 4, "file_name": "000000186198.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000186198.jpg", "height": 429, "width": 640, "date_captured": "2013-11-20 04:08:37", "flickr_url": "http://farm3.staticflickr.com/2800/4397601351_4b37909e24_z.jpg", "id": 186198}, {"license": 5, "file_name": "000000309084.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000309084.jpg", "height": 640, "width": 427, "date_captured": "2013-11-20 20:41:58", "flickr_url": "http://farm9.staticflickr.com/8341/8232672515_0fe978b8df_z.jpg", "id": 309084}, {"license": 5, "file_name": "000000423776.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000423776.jpg", "height": 500, "width": 333, "date_captured": "2013-11-14 22:57:55", "flickr_url": "http://farm2.staticflickr.com/1012/1395087187_5b3a3f76f5_z.jpg", "id": 423776}, {"license": 1, "file_name": "000000243574.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000243574.jpg", "height": 428, "width": 500, "date_captured": "2013-11-17 20:43:28", "flickr_url": "http://farm1.staticflickr.com/137/326046306_52aeedfbe2_z.jpg", "id": 243574}, {"license": 1, "file_name": "000000227198.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000227198.jpg", "height": 640, "width": 428, "date_captured": "2013-11-17 21:59:27", "flickr_url": "http://farm9.staticflickr.com/8421/7603921590_70684244ce_z.jpg", "id": 227198}, {"license": 1, "file_name": "000000481165.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000481165.jpg", "height": 471, "width": 640, "date_captured": "2013-11-15 01:10:21", "flickr_url": "http://farm4.staticflickr.com/3013/2375080536_5e603d78b4_z.jpg", "id": 481165}, {"license": 1, "file_name": "000000186255.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000186255.jpg", "height": 640, "width": 458, "date_captured": "2013-11-18 19:35:29", "flickr_url": "http://farm4.staticflickr.com/3207/3594690408_39ffa56043_z.jpg", "id": 186255}, {"license": 1, "file_name": "000000292751.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000292751.jpg", "height": 331, "width": 500, "date_captured": "2013-11-24 21:46:55", "flickr_url": "http://farm1.staticflickr.com/81/219845883_cb0cc299a6_z.jpg", "id": 292751}, {"license": 4, "file_name": "000000358289.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000358289.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 20:52:54", "flickr_url": "http://farm4.staticflickr.com/3789/9402283589_4d9585a5df_z.jpg", "id": 358289}, {"license": 5, "file_name": "000000104344.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000104344.jpg", "height": 612, "width": 612, "date_captured": "2013-11-18 02:27:25", "flickr_url": "http://farm9.staticflickr.com/8213/8293054254_2f3043dc83_z.jpg", "id": 104344}, {"license": 5, "file_name": "000000047001.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000047001.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 03:17:57", "flickr_url": "http://farm7.staticflickr.com/6118/6330600028_293f554a1f_z.jpg", "id": 47001}, {"license": 2, "file_name": "000000268197.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000268197.jpg", "height": 351, "width": 640, "date_captured": "2013-11-20 22:38:54", "flickr_url": "http://farm7.staticflickr.com/6113/6211974851_b10aa35bd4_z.jpg", "id": 268197}, {"license": 4, "file_name": "000000563110.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000563110.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 04:35:04", "flickr_url": "http://farm9.staticflickr.com/8234/8586154417_0a89fec400_z.jpg", "id": 563110}, {"license": 6, "file_name": "000000325545.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000325545.jpg", "height": 425, "width": 640, "date_captured": "2013-11-20 07:40:57", "flickr_url": "http://farm1.staticflickr.com/164/391697508_3d9db151c0_z.jpg", "id": 325545}, {"license": 4, "file_name": "000000399276.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000399276.jpg", "height": 640, "width": 480, "date_captured": "2013-11-17 11:35:08", "flickr_url": "http://farm3.staticflickr.com/2241/2369663451_3f86536ddb_z.jpg", "id": 399276}, {"license": 2, "file_name": "000000513966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000513966.jpg", "height": 433, "width": 640, "date_captured": "2013-11-15 10:27:03", "flickr_url": "http://farm8.staticflickr.com/7014/6553431085_39f6895536_z.jpg", "id": 513966}, {"license": 1, "file_name": "000000333748.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000333748.jpg", "height": 380, "width": 640, "date_captured": "2013-11-24 22:47:28", "flickr_url": "http://farm3.staticflickr.com/2823/9347533212_4b0218d3f1_z.jpg", "id": 333748}, {"license": 4, "file_name": "000000006068.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000006068.jpg", "height": 361, "width": 640, "date_captured": "2013-11-17 06:28:33", "flickr_url": "http://farm6.staticflickr.com/5462/9969577043_b08af7c36a_z.jpg", "id": 6068}, {"license": 2, "file_name": "000000055226.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000055226.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 01:08:38", "flickr_url": "http://farm5.staticflickr.com/4003/4195628235_2445b231be_z.jpg", "id": 55226}, {"license": 2, "file_name": "000000120782.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000120782.jpg", "height": 375, "width": 500, "date_captured": "2013-11-15 20:56:24", "flickr_url": "http://farm1.staticflickr.com/56/146502111_cabd3b396a_z.jpg", "id": 120782}, {"license": 1, "file_name": "000000456658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000456658.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 04:31:14", "flickr_url": "http://farm4.staticflickr.com/3470/3395088828_61b5fc4379_z.jpg", "id": 456658}, {"license": 3, "file_name": "000000423890.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000423890.jpg", "height": 450, "width": 600, "date_captured": "2013-11-23 02:57:21", "flickr_url": "http://farm5.staticflickr.com/4013/4518304795_bc5ccb0995_z.jpg", "id": 423890}, {"license": 1, "file_name": "000000137173.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000137173.jpg", "height": 640, "width": 480, "date_captured": "2013-11-19 00:25:08", "flickr_url": "http://farm3.staticflickr.com/2889/9657028745_9d63936bd5_z.jpg", "id": 137173}, {"license": 3, "file_name": "000000276444.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000276444.jpg", "height": 335, "width": 500, "date_captured": "2013-11-18 14:55:16", "flickr_url": "http://farm4.staticflickr.com/3082/3188004920_3f80bae175_z.jpg", "id": 276444}, {"license": 1, "file_name": "000000186336.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000186336.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 03:20:21", "flickr_url": "http://farm4.staticflickr.com/3266/3162349052_9f79532ed8_z.jpg", "id": 186336}, {"license": 2, "file_name": "000000522229.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000522229.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 04:59:22", "flickr_url": "http://farm5.staticflickr.com/4154/5086681414_ac66c9ddae_z.jpg", "id": 522229}, {"license": 3, "file_name": "000000432138.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000432138.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 21:44:04", "flickr_url": "http://farm4.staticflickr.com/3060/2651611041_58af791fee_z.jpg", "id": 432138}, {"license": 3, "file_name": "000000079883.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000079883.jpg", "height": 293, "width": 390, "date_captured": "2013-11-14 17:49:39", "flickr_url": "http://farm4.staticflickr.com/3447/3917724137_0db6a8a09d_z.jpg", "id": 79883}, {"license": 4, "file_name": "000000333842.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000333842.jpg", "height": 427, "width": 640, "date_captured": "2013-11-22 00:57:21", "flickr_url": "http://farm4.staticflickr.com/3379/3657930265_b18872915a_z.jpg", "id": 333842}, {"license": 3, "file_name": "000000505885.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000505885.jpg", "height": 640, "width": 438, "date_captured": "2013-11-18 10:38:34", "flickr_url": "http://farm7.staticflickr.com/6064/6046886669_db39468001_z.jpg", "id": 505885}, {"license": 2, "file_name": "000000079912.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000079912.jpg", "height": 375, "width": 500, "date_captured": "2013-11-14 23:50:21", "flickr_url": "http://farm4.staticflickr.com/3053/2561581967_2ac644ba3d_z.jpg", "id": 79912}, {"license": 1, "file_name": "000000268334.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000268334.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 21:02:46", "flickr_url": "http://farm9.staticflickr.com/8455/7986835616_8a767a3755_z.jpg", "id": 268334}, {"license": 3, "file_name": "000000235582.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000235582.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 18:24:30", "flickr_url": "http://farm8.staticflickr.com/7273/7495200536_eb8329375b_z.jpg", "id": 235582}, {"license": 2, "file_name": "000000505924.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000505924.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 21:08:19", "flickr_url": "http://farm9.staticflickr.com/8051/8101609385_43f72da8c0_z.jpg", "id": 505924}, {"license": 1, "file_name": "000000350280.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000350280.jpg", "height": 321, "width": 500, "date_captured": "2013-11-25 20:11:23", "flickr_url": "http://farm5.staticflickr.com/4007/4473867785_084381ee3a_z.jpg", "id": 350280}, {"license": 5, "file_name": "000000374873.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000374873.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 18:05:08", "flickr_url": "http://farm1.staticflickr.com/49/145918270_e7a6cb3420_z.jpg", "id": 374873}, {"license": 1, "file_name": "000000055385.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000055385.jpg", "height": 532, "width": 640, "date_captured": "2013-11-20 20:33:35", "flickr_url": "http://farm8.staticflickr.com/7378/8728369722_cd484028fe_z.jpg", "id": 55385}, {"license": 2, "file_name": "000000309338.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000309338.jpg", "height": 259, "width": 640, "date_captured": "2013-11-18 17:50:50", "flickr_url": "http://farm8.staticflickr.com/7198/6903791105_3b0711182a_z.jpg", "id": 309338}, {"license": 1, "file_name": "000000473182.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000473182.jpg", "height": 428, "width": 640, "date_captured": "2013-11-15 20:56:47", "flickr_url": "http://farm4.staticflickr.com/3693/9380169420_44351ab570_z.jpg", "id": 473182}, {"license": 4, "file_name": "000000145503.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000145503.jpg", "height": 375, "width": 500, "date_captured": "2013-11-24 00:53:39", "flickr_url": "http://farm2.staticflickr.com/1339/820645508_7254c972e9_z.jpg", "id": 145503}, {"license": 6, "file_name": "000000243823.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000243823.jpg", "height": 307, "width": 640, "date_captured": "2013-11-24 13:19:02", "flickr_url": "http://farm8.staticflickr.com/7359/9307449387_964b9e4df8_z.jpg", "id": 243823}, {"license": 3, "file_name": "000000555120.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000555120.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 22:30:41", "flickr_url": "http://farm8.staticflickr.com/7374/10098103653_30516530d7_z.jpg", "id": 555120}, {"license": 1, "file_name": "000000538737.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000538737.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 14:27:37", "flickr_url": "http://farm8.staticflickr.com/7062/6936329137_da858ac616_z.jpg", "id": 538737}, {"license": 3, "file_name": "000000055412.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000055412.jpg", "height": 500, "width": 335, "date_captured": "2013-11-16 19:45:04", "flickr_url": "http://farm3.staticflickr.com/2641/4166163740_09579975bc_z.jpg", "id": 55412}, {"license": 3, "file_name": "000000071796.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000071796.jpg", "height": 640, "width": 428, "date_captured": "2013-11-16 19:12:01", "flickr_url": "http://farm2.staticflickr.com/1135/1107857295_2ca78e3c38_z.jpg", "id": 71796}, {"license": 1, "file_name": "000000194685.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000194685.jpg", "height": 612, "width": 612, "date_captured": "2013-11-21 00:42:26", "flickr_url": "http://farm9.staticflickr.com/8493/8287793659_266133fee5_z.jpg", "id": 194685}, {"license": 4, "file_name": "000000268428.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000268428.jpg", "height": 430, "width": 640, "date_captured": "2013-11-15 12:44:40", "flickr_url": "http://farm6.staticflickr.com/5295/5532057711_7cdc34b788_z.jpg", "id": 268428}, {"license": 2, "file_name": "000000497807.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000497807.jpg", "height": 429, "width": 640, "date_captured": "2013-11-22 15:57:47", "flickr_url": "http://farm5.staticflickr.com/4133/4989273871_39cd72c344_z.jpg", "id": 497807}, {"license": 2, "file_name": "000000358543.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000358543.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 10:50:06", "flickr_url": "http://farm7.staticflickr.com/6166/6212577919_807ea9e8ea_z.jpg", "id": 358543}, {"license": 4, "file_name": "000000014484.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000014484.jpg", "height": 392, "width": 500, "date_captured": "2013-11-16 17:22:54", "flickr_url": "http://farm4.staticflickr.com/3459/3893365171_04fdb155a0_z.jpg", "id": 14484}, {"license": 4, "file_name": "000000153749.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000153749.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 12:37:10", "flickr_url": "http://farm5.staticflickr.com/4104/4982546734_0025bf6628_z.jpg", "id": 153749}, {"license": 4, "file_name": "000000137377.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000137377.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 06:26:22", "flickr_url": "http://farm2.staticflickr.com/1404/4720087689_91eefc3508_z.jpg", "id": 137377}, {"license": 1, "file_name": "000000301218.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000301218.jpg", "height": 640, "width": 428, "date_captured": "2013-11-16 14:06:15", "flickr_url": "http://farm4.staticflickr.com/3224/3052942000_d9618ee3bc_z.jpg", "id": 301218}, {"license": 5, "file_name": "000000252093.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000252093.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 05:56:32", "flickr_url": "http://farm4.staticflickr.com/3672/9362991929_f6f9055835_z.jpg", "id": 252093}, {"license": 2, "file_name": "000000047294.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000047294.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 17:23:48", "flickr_url": "http://farm7.staticflickr.com/6226/6270852404_f0d5a1885b_z.jpg", "id": 47294}, {"license": 6, "file_name": "000000358599.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000358599.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 05:11:24", "flickr_url": "http://farm3.staticflickr.com/2841/9709646199_def4c26d90_z.jpg", "id": 358599}, {"license": 4, "file_name": "000000530635.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000530635.jpg", "height": 640, "width": 289, "date_captured": "2013-11-18 04:10:48", "flickr_url": "http://farm5.staticflickr.com/4100/4809444993_a95a511acc_z.jpg", "id": 530635}, {"license": 1, "file_name": "000000153814.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000153814.jpg", "height": 612, "width": 612, "date_captured": "2013-11-21 02:30:37", "flickr_url": "http://farm9.staticflickr.com/8146/7457145628_08863055a3_z.jpg", "id": 153814}, {"license": 3, "file_name": "000000489695.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000489695.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 14:32:34", "flickr_url": "http://farm1.staticflickr.com/49/158589231_8a56b848bc_z.jpg", "id": 489695}, {"license": 3, "file_name": "000000424165.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000424165.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 02:33:34", "flickr_url": "http://farm3.staticflickr.com/2593/4147272243_1271fed8a6_z.jpg", "id": 424165}, {"license": 4, "file_name": "000000547055.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000547055.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 18:06:20", "flickr_url": "http://farm7.staticflickr.com/6219/6268348885_6156089ee7_z.jpg", "id": 547055}, {"license": 4, "file_name": "000000104692.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000104692.jpg", "height": 640, "width": 428, "date_captured": "2013-11-17 04:37:08", "flickr_url": "http://farm6.staticflickr.com/5492/9689420346_50e8e2c66f_z.jpg", "id": 104692}, {"license": 3, "file_name": "000000039159.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000039159.jpg", "height": 640, "width": 426, "date_captured": "2013-11-25 21:13:24", "flickr_url": "http://farm2.staticflickr.com/1324/1116195348_fc4ba05422_z.jpg", "id": 39159}, {"license": 1, "file_name": "000000030973.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000030973.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 20:42:28", "flickr_url": "http://farm4.staticflickr.com/3164/2897279128_d8f3a0d26a_z.jpg", "id": 30973}, {"license": 4, "file_name": "000000334080.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000334080.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 15:15:04", "flickr_url": "http://farm3.staticflickr.com/2036/2443118239_83acc55ee7_z.jpg", "id": 334080}, {"license": 2, "file_name": "000000473348.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000473348.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 17:23:08", "flickr_url": "http://farm8.staticflickr.com/7105/7321033416_6d782b70a6_z.jpg", "id": 473348}, {"license": 4, "file_name": "000000571658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000571658.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 21:41:04", "flickr_url": "http://farm4.staticflickr.com/3717/9122227494_08b369151b_z.jpg", "id": 571658}, {"license": 3, "file_name": "000000473373.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000473373.jpg", "height": 332, "width": 500, "date_captured": "2013-11-15 13:34:59", "flickr_url": "http://farm3.staticflickr.com/2727/4285907078_f56b65c538_z.jpg", "id": 473373}, {"license": 3, "file_name": "000000071970.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000071970.jpg", "height": 512, "width": 640, "date_captured": "2013-11-16 16:35:55", "flickr_url": "http://farm6.staticflickr.com/5180/5464363143_41f65ec6c8_z.jpg", "id": 71970}, {"license": 3, "file_name": "000000260395.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000260395.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 21:43:15", "flickr_url": "http://farm4.staticflickr.com/3703/9106153413_02bf3f3446_z.jpg", "id": 260395}, {"license": 4, "file_name": "000000334139.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000334139.jpg", "height": 428, "width": 640, "date_captured": "2013-11-20 13:25:32", "flickr_url": "http://farm2.staticflickr.com/1111/5099617090_4ef4474cf2_z.jpg", "id": 334139}, {"license": 2, "file_name": "000000178492.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000178492.jpg", "height": 426, "width": 640, "date_captured": "2013-11-17 20:16:24", "flickr_url": "http://farm6.staticflickr.com/5443/9961345094_5e28585c38_z.jpg", "id": 178492}, {"license": 5, "file_name": "000000563525.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000563525.jpg", "height": 426, "width": 640, "date_captured": "2013-11-25 19:39:30", "flickr_url": "http://farm7.staticflickr.com/6184/6079341028_bed0eacfc6_z.jpg", "id": 563525}, {"license": 1, "file_name": "000000571719.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000571719.jpg", "height": 478, "width": 640, "date_captured": "2013-11-20 23:14:36", "flickr_url": "http://farm8.staticflickr.com/7280/7654411296_a05e5981bb_z.jpg", "id": 571719}, {"license": 5, "file_name": "000000285000.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000285000.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 13:35:48", "flickr_url": "http://farm4.staticflickr.com/3594/3687263303_01c10d2964_z.jpg", "id": 285000}, {"license": 2, "file_name": "000000096586.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000096586.jpg", "height": 640, "width": 428, "date_captured": "2013-11-16 15:46:12", "flickr_url": "http://farm3.staticflickr.com/2475/3788197432_d803f6387f_z.jpg", "id": 96586}, {"license": 3, "file_name": "000000416076.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000416076.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 19:57:58", "flickr_url": "http://farm9.staticflickr.com/8244/8570361216_59db6dc1b7_z.jpg", "id": 416076}, {"license": 3, "file_name": "000000129361.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000129361.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 12:52:10", "flickr_url": "http://farm3.staticflickr.com/2761/4410435951_23981e09e5_z.jpg", "id": 129361}, {"license": 1, "file_name": "000000432467.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000432467.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 12:31:56", "flickr_url": "http://farm5.staticflickr.com/4090/5022761879_f6b812b6e1_z.jpg", "id": 432467}, {"license": 5, "file_name": "000000129371.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000129371.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 20:55:38", "flickr_url": "http://farm8.staticflickr.com/7133/6931986876_5ac41f8012_z.jpg", "id": 129371}, {"license": 5, "file_name": "000000547165.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000547165.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 22:54:40", "flickr_url": "http://farm4.staticflickr.com/3412/3418987977_1770a798c6_z.jpg", "id": 547165}, {"license": 3, "file_name": "000000555358.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000555358.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 21:22:16", "flickr_url": "http://farm1.staticflickr.com/41/104850071_f78b82fbe3_z.jpg", "id": 555358}, {"license": 3, "file_name": "000000342374.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000342374.jpg", "height": 425, "width": 640, "date_captured": "2013-11-25 00:03:33", "flickr_url": "http://farm9.staticflickr.com/8386/8478917214_aaf42c21a5_z.jpg", "id": 342374}, {"license": 3, "file_name": "000000088425.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000088425.jpg", "height": 357, "width": 500, "date_captured": "2013-11-19 22:15:00", "flickr_url": "http://farm1.staticflickr.com/71/188495342_dd6da8cd1f_z.jpg", "id": 88425}, {"license": 4, "file_name": "000000366956.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000366956.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 16:26:13", "flickr_url": "http://farm3.staticflickr.com/2236/2435964500_831ddfcc68_z.jpg", "id": 366956}, {"license": 3, "file_name": "000000440689.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000440689.jpg", "height": 450, "width": 600, "date_captured": "2013-11-15 19:32:22", "flickr_url": "http://farm6.staticflickr.com/5168/5368124767_d151f74f88_z.jpg", "id": 440689}, {"license": 3, "file_name": "000000252277.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000252277.jpg", "height": 394, "width": 640, "date_captured": "2013-11-24 00:53:10", "flickr_url": "http://farm4.staticflickr.com/3479/3186200071_c299b046d9_z.jpg", "id": 252277}, {"license": 1, "file_name": "000000039288.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000039288.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 18:32:23", "flickr_url": "http://farm1.staticflickr.com/155/331052806_1c3b0eb2d2_z.jpg", "id": 39288}, {"license": 3, "file_name": "000000276874.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000276874.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 11:38:36", "flickr_url": "http://farm4.staticflickr.com/3404/3284137474_90bf2ed9f7_z.jpg", "id": 276874}, {"license": 3, "file_name": "000000022926.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000022926.jpg", "height": 551, "width": 640, "date_captured": "2013-11-18 03:07:39", "flickr_url": "http://farm2.staticflickr.com/1390/947560980_08400d3f6e_z.jpg", "id": 22926}, {"license": 3, "file_name": "000000473500.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000473500.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 05:18:42", "flickr_url": "http://farm5.staticflickr.com/4026/4443721316_8a5eaf40f3_z.jpg", "id": 473500}, {"license": 1, "file_name": "000000129438.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000129438.jpg", "height": 418, "width": 640, "date_captured": "2013-11-18 05:08:43", "flickr_url": "http://farm1.staticflickr.com/133/386357387_2d3ff58d94_z.jpg", "id": 129438}, {"license": 4, "file_name": "000000334259.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000334259.jpg", "height": 333, "width": 500, "date_captured": "2013-11-17 02:40:54", "flickr_url": "http://farm1.staticflickr.com/182/487138093_ed8b04ca72_z.jpg", "id": 334259}, {"license": 3, "file_name": "000000555446.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000555446.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 05:14:51", "flickr_url": "http://farm9.staticflickr.com/8228/8430716115_983f133a60_z.jpg", "id": 555446}, {"license": 2, "file_name": "000000072118.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000072118.jpg", "height": 640, "width": 478, "date_captured": "2013-11-21 04:29:24", "flickr_url": "http://farm6.staticflickr.com/5138/5518360113_03d9d6f605_z.jpg", "id": 72118}, {"license": 1, "file_name": "000000047545.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000047545.jpg", "height": 640, "width": 424, "date_captured": "2013-11-24 15:45:51", "flickr_url": "http://farm9.staticflickr.com/8460/7897169872_a2f836b0c2_z.jpg", "id": 47545}, {"license": 1, "file_name": "000000326077.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000326077.jpg", "height": 375, "width": 500, "date_captured": "2013-11-16 16:22:29", "flickr_url": "http://farm1.staticflickr.com/42/87406887_4c4c40a1d5_z.jpg", "id": 326077}, {"license": 4, "file_name": "000000031187.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000031187.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 06:09:42", "flickr_url": "http://farm8.staticflickr.com/7206/6811599186_07ed1fa655_z.jpg", "id": 31187}, {"license": 5, "file_name": "000000252373.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000252373.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 19:08:46", "flickr_url": "http://farm8.staticflickr.com/7021/6420121899_9f11ded9f8_z.jpg", "id": 252373}, {"license": 3, "file_name": "000000530925.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000530925.jpg", "height": 424, "width": 640, "date_captured": "2013-11-19 18:45:57", "flickr_url": "http://farm9.staticflickr.com/8272/8747020722_c61839654e_z.jpg", "id": 530925}, {"license": 4, "file_name": "000000522741.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000522741.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 14:22:13", "flickr_url": "http://farm8.staticflickr.com/7339/9597899053_e3d1282446_z.jpg", "id": 522741}, {"license": 1, "file_name": "000000268804.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000268804.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 00:46:25", "flickr_url": "http://farm4.staticflickr.com/3721/9577674018_5257c15096_z.jpg", "id": 268804}, {"license": 2, "file_name": "000000457225.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000457225.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 07:55:11", "flickr_url": "http://farm6.staticflickr.com/5053/5491740224_e79d2096b8_z.jpg", "id": 457225}, {"license": 1, "file_name": "000000358921.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000358921.jpg", "height": 500, "width": 360, "date_captured": "2013-11-14 16:25:23", "flickr_url": "http://farm1.staticflickr.com/105/313002768_07c4deab4d_z.jpg", "id": 358921}, {"license": 4, "file_name": "000000408081.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000408081.jpg", "height": 394, "width": 640, "date_captured": "2013-11-20 05:44:01", "flickr_url": "http://farm2.staticflickr.com/1257/4724680060_77ae2c0dd6_z.jpg", "id": 408081}, {"license": 1, "file_name": "000000391703.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000391703.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 12:52:24", "flickr_url": "http://farm4.staticflickr.com/3359/3447810601_bc921b65af_z.jpg", "id": 391703}, {"license": 4, "file_name": "000000383512.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000383512.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 17:44:15", "flickr_url": "http://farm9.staticflickr.com/8392/8682024435_2cbf0fa00b_z.jpg", "id": 383512}, {"license": 3, "file_name": "000000219680.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000219680.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 01:28:52", "flickr_url": "http://farm4.staticflickr.com/3008/2679080675_2c3c1b5749_z.jpg", "id": 219680}, {"license": 1, "file_name": "000000490016.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000490016.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 01:33:11", "flickr_url": "http://farm1.staticflickr.com/98/265825214_39a332af04_z.jpg", "id": 490016}, {"license": 3, "file_name": "000000227891.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000227891.jpg", "height": 281, "width": 500, "date_captured": "2013-11-22 17:22:12", "flickr_url": "http://farm4.staticflickr.com/3240/2684209485_b1e66921d2_z.jpg", "id": 227891}, {"license": 5, "file_name": "000000424503.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000424503.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 16:34:19", "flickr_url": "http://farm5.staticflickr.com/4116/4930206162_74c511b2a8_z.jpg", "id": 424503}, {"license": 6, "file_name": "000000342585.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000342585.jpg", "height": 612, "width": 612, "date_captured": "2013-11-20 21:39:15", "flickr_url": "http://farm8.staticflickr.com/7081/7189207622_d2fac5fb92_z.jpg", "id": 342585}, {"license": 5, "file_name": "000000055873.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000055873.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 18:27:08", "flickr_url": "http://farm4.staticflickr.com/3371/3338059752_29f16b318b_z.jpg", "id": 55873}, {"license": 1, "file_name": "000000088647.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000088647.jpg", "height": 360, "width": 640, "date_captured": "2013-11-22 00:50:52", "flickr_url": "http://farm3.staticflickr.com/2731/4320890170_f56fa44ee4_z.jpg", "id": 88647}, {"license": 1, "file_name": "000000178763.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000178763.jpg", "height": 433, "width": 640, "date_captured": "2013-11-25 08:09:05", "flickr_url": "http://farm3.staticflickr.com/2863/9541668051_a93a0b6d2a_z.jpg", "id": 178763}, {"license": 3, "file_name": "000000490062.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000490062.jpg", "height": 500, "width": 367, "date_captured": "2013-11-16 12:59:55", "flickr_url": "http://farm1.staticflickr.com/31/40513262_92e820099a_z.jpg", "id": 490062}, {"license": 4, "file_name": "000000522834.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000522834.jpg", "height": 360, "width": 480, "date_captured": "2013-11-18 04:48:06", "flickr_url": "http://farm9.staticflickr.com/8186/8414768650_edd7babcc8_z.jpg", "id": 522834}, {"license": 1, "file_name": "000000080472.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000080472.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 00:59:20", "flickr_url": "http://farm4.staticflickr.com/3096/3141776397_55ea70eb56_z.jpg", "id": 80472}, {"license": 5, "file_name": "000000064092.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000064092.jpg", "height": 427, "width": 640, "date_captured": "2013-11-19 03:39:29", "flickr_url": "http://farm9.staticflickr.com/8325/8412753110_20075aec58_z.jpg", "id": 64092}, {"license": 1, "file_name": "000000162396.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000162396.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 11:06:03", "flickr_url": "http://farm6.staticflickr.com/5309/5653850686_0b543d8cd6_z.jpg", "id": 162396}, {"license": 1, "file_name": "000000088671.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000088671.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 18:42:26", "flickr_url": "http://farm4.staticflickr.com/3663/3321655722_8eb02487fd_z.jpg", "id": 88671}, {"license": 1, "file_name": "000000227946.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000227946.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 05:22:10", "flickr_url": "http://farm9.staticflickr.com/8203/8179750650_ae97181cff_z.jpg", "id": 227946}, {"license": 5, "file_name": "000000350826.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000350826.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 09:32:29", "flickr_url": "http://farm4.staticflickr.com/3811/8922753500_cee9536dde_z.jpg", "id": 350826}, {"license": 1, "file_name": "000000121453.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000121453.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 20:35:38", "flickr_url": "http://farm5.staticflickr.com/4144/5028039333_ddfde3e595_z.jpg", "id": 121453}, {"license": 3, "file_name": "000000498297.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000498297.jpg", "height": 253, "width": 640, "date_captured": "2013-11-16 21:47:27", "flickr_url": "http://farm8.staticflickr.com/7186/6813349260_58ece5fdc7_z.jpg", "id": 498297}, {"license": 4, "file_name": "000000449158.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000449158.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 18:40:15", "flickr_url": "http://farm3.staticflickr.com/2111/2129657347_e27840b065_z.jpg", "id": 449158}, {"license": 1, "file_name": "000000154257.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000154257.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 19:39:33", "flickr_url": "http://farm9.staticflickr.com/8501/8399815869_1c678cd114_z.jpg", "id": 154257}, {"license": 4, "file_name": "000000383639.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000383639.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 05:54:33", "flickr_url": "http://farm4.staticflickr.com/3154/2843439562_390c643117_z.jpg", "id": 383639}, {"license": 4, "file_name": "000000342683.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000342683.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 22:07:48", "flickr_url": "http://farm7.staticflickr.com/6011/5999461095_95a12c2af6_z.jpg", "id": 342683}, {"license": 3, "file_name": "000000039580.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000039580.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 08:06:22", "flickr_url": "http://farm4.staticflickr.com/3822/10060783776_cd0fd8f3c5_z.jpg", "id": 39580}, {"license": 3, "file_name": "000000277188.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000277188.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 17:18:56", "flickr_url": "http://farm6.staticflickr.com/5502/9635548783_608a84194d_z.jpg", "id": 277188}, {"license": 1, "file_name": "000000408266.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000408266.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 03:30:18", "flickr_url": "http://farm7.staticflickr.com/6064/6091372073_7fbdcdf8d6_z.jpg", "id": 408266}, {"license": 4, "file_name": "000000072396.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000072396.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 03:01:19", "flickr_url": "http://farm5.staticflickr.com/4098/4911039268_d543e2bcff_z.jpg", "id": 72396}, {"license": 2, "file_name": "000000080590.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000080590.jpg", "height": 375, "width": 500, "date_captured": "2013-11-25 20:07:37", "flickr_url": "http://farm5.staticflickr.com/4061/4413290094_6c53f1f97a_z.jpg", "id": 80590}, {"license": 5, "file_name": "000000277200.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000277200.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 17:03:42", "flickr_url": "http://farm4.staticflickr.com/3169/3036648592_5397d35c55_z.jpg", "id": 277200}, {"license": 1, "file_name": "000000056032.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000056032.jpg", "height": 640, "width": 428, "date_captured": "2013-11-21 02:36:02", "flickr_url": "http://farm8.staticflickr.com/7139/7075663515_1fd901b88a_z.jpg", "id": 56032}, {"license": 3, "file_name": "000000506592.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000506592.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 10:16:49", "flickr_url": "http://farm2.staticflickr.com/1043/1173193464_5bf2479cea_z.jpg", "id": 506592}, {"license": 3, "file_name": "000000105200.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000105200.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 22:43:10", "flickr_url": "http://farm8.staticflickr.com/7224/7242679652_2b75272c5d_z.jpg", "id": 105200}, {"license": 4, "file_name": "000000310006.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000310006.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 02:49:51", "flickr_url": "http://farm7.staticflickr.com/6067/6065239702_94d8c4084b_z.jpg", "id": 310006}, {"license": 6, "file_name": "000000277243.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000277243.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 14:19:43", "flickr_url": "http://farm9.staticflickr.com/8187/8119246206_17962695d5_z.jpg", "id": 277243}, {"license": 3, "file_name": "000000432897.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000432897.jpg", "height": 500, "width": 500, "date_captured": "2013-11-23 01:04:42", "flickr_url": "http://farm7.staticflickr.com/6236/6230042369_708344079c_z.jpg", "id": 432897}, {"license": 4, "file_name": "000000531201.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000531201.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 04:02:19", "flickr_url": "http://farm7.staticflickr.com/6065/6112776113_990c5d6327_z.jpg", "id": 531201}, {"license": 1, "file_name": "000000064259.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000064259.jpg", "height": 428, "width": 640, "date_captured": "2013-11-22 01:08:11", "flickr_url": "http://farm5.staticflickr.com/4027/4248914994_98e1d1dc49_z.jpg", "id": 64259}, {"license": 1, "file_name": "000000334600.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000334600.jpg", "height": 424, "width": 640, "date_captured": "2013-11-15 01:34:02", "flickr_url": "http://farm8.staticflickr.com/7439/9425027188_d97c25d56f_z.jpg", "id": 334600}, {"license": 3, "file_name": "000000555794.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000555794.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 04:21:09", "flickr_url": "http://farm4.staticflickr.com/3601/5841608201_407d9ccc88_z.jpg", "id": 555794}, {"license": 5, "file_name": "000000121619.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000121619.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 11:01:09", "flickr_url": "http://farm8.staticflickr.com/7230/7205963930_cea220ba20_z.jpg", "id": 121619}, {"license": 1, "file_name": "000000473879.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000473879.jpg", "height": 424, "width": 640, "date_captured": "2013-11-14 22:53:43", "flickr_url": "http://farm7.staticflickr.com/6078/6049589572_caaffea7af_z.jpg", "id": 473879}, {"license": 6, "file_name": "000000277284.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000277284.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 17:18:56", "flickr_url": "http://farm4.staticflickr.com/3108/2638779307_ab6f1c55d8_z.jpg", "id": 277284}, {"license": 1, "file_name": "000000228133.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000228133.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 14:41:06", "flickr_url": "http://farm9.staticflickr.com/8112/8622383005_78911ccfb1_z.jpg", "id": 228133}, {"license": 6, "file_name": "000000285478.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000285478.jpg", "height": 640, "width": 462, "date_captured": "2013-11-22 23:40:27", "flickr_url": "http://farm4.staticflickr.com/3646/3321412767_6eeebd8e70_z.jpg", "id": 285478}, {"license": 4, "file_name": "000000219943.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000219943.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 01:20:42", "flickr_url": "http://farm3.staticflickr.com/2032/2023194191_b7f15e4068_z.jpg", "id": 219943}, {"license": 4, "file_name": "000000351025.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000351025.jpg", "height": 428, "width": 640, "date_captured": "2013-11-17 16:25:10", "flickr_url": "http://farm7.staticflickr.com/6102/6299456717_b221a117d1_z.jpg", "id": 351025}, {"license": 1, "file_name": "000000547636.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000547636.jpg", "height": 360, "width": 640, "date_captured": "2013-11-14 16:48:59", "flickr_url": "http://farm7.staticflickr.com/6231/6319976018_70967f07ef_z.jpg", "id": 547636}, {"license": 3, "file_name": "000000047928.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000047928.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 14:23:39", "flickr_url": "http://farm3.staticflickr.com/2865/9582618716_13598778b5_z.jpg", "id": 47928}, {"license": 1, "file_name": "000000219963.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000219963.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 22:40:53", "flickr_url": "http://farm3.staticflickr.com/2673/3692658967_b9c85af354_z.jpg", "id": 219963}, {"license": 1, "file_name": "000000219966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000219966.jpg", "height": 640, "width": 640, "date_captured": "2013-11-20 23:19:07", "flickr_url": "http://farm9.staticflickr.com/8509/8391112461_00d389401d_z.jpg", "id": 219966}, {"license": 3, "file_name": "000000416586.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000416586.jpg", "height": 359, "width": 640, "date_captured": "2013-11-16 22:06:14", "flickr_url": "http://farm6.staticflickr.com/5451/8857271294_7324bef746_z.jpg", "id": 416586}, {"license": 1, "file_name": "000000015190.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000015190.jpg", "height": 640, "width": 480, "date_captured": "2013-11-18 09:16:30", "flickr_url": "http://farm5.staticflickr.com/4097/4763184536_0a64643b61_z.jpg", "id": 15190}, {"license": 1, "file_name": "000000236406.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000236406.jpg", "height": 325, "width": 500, "date_captured": "2013-11-18 22:15:30", "flickr_url": "http://farm1.staticflickr.com/28/55362450_55486f910e_z.jpg", "id": 236406}, {"license": 1, "file_name": "000000301943.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000301943.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 16:38:14", "flickr_url": "http://farm4.staticflickr.com/3400/3335391150_6a809f9333_z.jpg", "id": 301943}, {"license": 5, "file_name": "000000228215.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000228215.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 22:04:11", "flickr_url": "http://farm8.staticflickr.com/7094/7195426740_d40f8ea1e3_z.jpg", "id": 228215}, {"license": 2, "file_name": "000000039802.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000039802.jpg", "height": 426, "width": 640, "date_captured": "2013-11-24 09:58:42", "flickr_url": "http://farm1.staticflickr.com/175/440559386_ece961d138_z.jpg", "id": 39802}, {"license": 1, "file_name": "000000039812.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000039812.jpg", "height": 478, "width": 640, "date_captured": "2013-11-18 04:35:24", "flickr_url": "http://farm3.staticflickr.com/2669/4041470476_da77dc04a6_z.jpg", "id": 39812}, {"license": 1, "file_name": "000000220037.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000220037.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 09:00:59", "flickr_url": "http://farm4.staticflickr.com/3677/9091983943_8260b4065a_z.jpg", "id": 220037}, {"license": 1, "file_name": "000000105358.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000105358.jpg", "height": 500, "width": 375, "date_captured": "2013-11-21 20:44:56", "flickr_url": "http://farm3.staticflickr.com/2694/4220114668_ab399eb069_z.jpg", "id": 105358}, {"license": 6, "file_name": "000000547726.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000547726.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 19:57:03", "flickr_url": "http://farm4.staticflickr.com/3502/3925654939_70349828d4_z.jpg", "id": 547726}, {"license": 1, "file_name": "000000392098.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000392098.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 00:50:11", "flickr_url": "http://farm9.staticflickr.com/8081/8269609929_c21e3a126a_z.jpg", "id": 392098}, {"license": 4, "file_name": "000000383929.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000383929.jpg", "height": 640, "width": 426, "date_captured": "2013-11-18 05:33:47", "flickr_url": "http://farm6.staticflickr.com/5107/5876429740_bcb6c9d706_z.jpg", "id": 383929}, {"license": 3, "file_name": "000000162760.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000162760.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 01:35:59", "flickr_url": "http://farm5.staticflickr.com/4145/5048912307_dff938896d_z.jpg", "id": 162760}, {"license": 4, "file_name": "000000342996.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000342996.jpg", "height": 405, "width": 640, "date_captured": "2013-11-18 03:32:07", "flickr_url": "http://farm6.staticflickr.com/5101/5682066890_a30a86f08f_z.jpg", "id": 342996}, {"license": 1, "file_name": "000000293860.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000293860.jpg", "height": 425, "width": 640, "date_captured": "2013-11-16 18:04:53", "flickr_url": "http://farm8.staticflickr.com/7186/6938973595_57e39b41ed_z.jpg", "id": 293860}, {"license": 5, "file_name": "000000392167.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000392167.jpg", "height": 612, "width": 612, "date_captured": "2013-11-20 14:37:17", "flickr_url": "http://farm9.staticflickr.com/8454/7902386006_825ffcdf32_z.jpg", "id": 392167}, {"license": 1, "file_name": "000000572405.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000572405.jpg", "height": 360, "width": 640, "date_captured": "2013-11-17 21:13:38", "flickr_url": "http://farm8.staticflickr.com/7199/6963411297_6e3ecedf89_z.jpg", "id": 572405}, {"license": 1, "file_name": "000000564217.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000564217.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 09:37:38", "flickr_url": "http://farm9.staticflickr.com/8309/8049007475_dc3ab0ece3_z.jpg", "id": 564217}, {"license": 5, "file_name": "000000498690.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000498690.jpg", "height": 375, "width": 500, "date_captured": "2013-11-23 20:08:36", "flickr_url": "http://farm1.staticflickr.com/58/230895015_40719aa143_z.jpg", "id": 498690}, {"license": 3, "file_name": "000000392201.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000392201.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 07:12:31", "flickr_url": "http://farm8.staticflickr.com/7423/9612988288_dd5ab11f7a_z.jpg", "id": 392201}, {"license": 4, "file_name": "000000490507.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000490507.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 16:14:20", "flickr_url": "http://farm9.staticflickr.com/8309/8070432946_8f7bdba384_z.jpg", "id": 490507}, {"license": 6, "file_name": "000000113676.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000113676.jpg", "height": 464, "width": 640, "date_captured": "2013-11-19 03:04:52", "flickr_url": "http://farm9.staticflickr.com/8250/8583764866_7778ab682f_z.jpg", "id": 113676}, {"license": 3, "file_name": "000000457745.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000457745.jpg", "height": 612, "width": 612, "date_captured": "2013-11-16 19:17:21", "flickr_url": "http://farm9.staticflickr.com/8187/8365300532_4eea8331f9_z.jpg", "id": 457745}, {"license": 7, "file_name": "000000072731.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000072731.jpg", "height": 640, "width": 435, "date_captured": "2013-11-18 01:32:27", "flickr_url": "http://farm5.staticflickr.com/4092/4835744294_390f287c0c_z.jpg", "id": 72731}, {"license": 1, "file_name": "000000384037.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000384037.jpg", "height": 338, "width": 640, "date_captured": "2013-11-20 14:50:59", "flickr_url": "http://farm1.staticflickr.com/151/406097170_aac7e58af4_z.jpg", "id": 384037}, {"license": 5, "file_name": "000000523309.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523309.jpg", "height": 500, "width": 375, "date_captured": "2013-11-22 02:34:39", "flickr_url": "http://farm4.staticflickr.com/3478/3468989711_e01845ee0a_z.jpg", "id": 523309}, {"license": 3, "file_name": "000000564271.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000564271.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 21:12:28", "flickr_url": "http://farm2.staticflickr.com/1421/832196079_98d786de0a_z.jpg", "id": 564271}, {"license": 1, "file_name": "000000031812.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000031812.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 20:30:07", "flickr_url": "http://farm8.staticflickr.com/7449/8722752605_77ce3e1bb0_z.jpg", "id": 31812}, {"license": 4, "file_name": "000000351301.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000351301.jpg", "height": 480, "width": 320, "date_captured": "2013-11-19 23:58:35", "flickr_url": "http://farm1.staticflickr.com/51/156242009_9b978c9b8d_z.jpg", "id": 351301}, {"license": 1, "file_name": "000000293966.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000293966.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 18:01:43", "flickr_url": "http://farm8.staticflickr.com/7337/8971653658_0c72a3e10e_z.jpg", "id": 293966}, {"license": 1, "file_name": "000000580695.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000580695.jpg", "height": 640, "width": 531, "date_captured": "2013-11-20 18:50:49", "flickr_url": "http://farm6.staticflickr.com/5334/9395628398_fbc9d959e6_z.jpg", "id": 580695}, {"license": 1, "file_name": "000000375904.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000375904.jpg", "height": 375, "width": 500, "date_captured": "2013-11-20 23:42:41", "flickr_url": "http://farm4.staticflickr.com/3276/2957072883_26c0010e85_z.jpg", "id": 375904}, {"license": 1, "file_name": "000000367715.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000367715.jpg", "height": 426, "width": 640, "date_captured": "2013-11-16 17:32:48", "flickr_url": "http://farm8.staticflickr.com/7052/6804609822_9c8290de08_z.jpg", "id": 367715}, {"license": 2, "file_name": "000000244836.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000244836.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 23:51:32", "flickr_url": "http://farm1.staticflickr.com/170/384089771_fe08525174_z.jpg", "id": 244836}, {"license": 5, "file_name": "000000490610.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000490610.jpg", "height": 640, "width": 427, "date_captured": "2013-11-17 02:59:26", "flickr_url": "http://farm9.staticflickr.com/8299/7927148680_a37362ca6e_z.jpg", "id": 490610}, {"license": 2, "file_name": "000000130163.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000130163.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 01:03:27", "flickr_url": "http://farm5.staticflickr.com/4031/4259760985_78b36f1255_z.jpg", "id": 130163}, {"license": 1, "file_name": "000000343154.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000343154.jpg", "height": 478, "width": 640, "date_captured": "2013-11-24 10:26:53", "flickr_url": "http://farm6.staticflickr.com/5169/5251152065_1710fbc6fc_z.jpg", "id": 343154}, {"license": 6, "file_name": "000000343158.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000343158.jpg", "height": 427, "width": 640, "date_captured": "2013-11-15 20:02:41", "flickr_url": "http://farm5.staticflickr.com/4115/5411095008_9fa427659d_z.jpg", "id": 343158}, {"license": 4, "file_name": "000000547974.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000547974.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 07:50:15", "flickr_url": "http://farm6.staticflickr.com/5252/5503384269_24953b5cb8_z.jpg", "id": 547974}, {"license": 4, "file_name": "000000244875.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000244875.jpg", "height": 500, "width": 417, "date_captured": "2013-11-15 07:00:42", "flickr_url": "http://farm1.staticflickr.com/169/467464092_12b86f5deb_z.jpg", "id": 244875}, {"license": 4, "file_name": "000000433296.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000433296.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 17:19:47", "flickr_url": "http://farm7.staticflickr.com/6146/6204908628_8bca1f44d4_z.jpg", "id": 433296}, {"license": 2, "file_name": "000000187537.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000187537.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 11:49:41", "flickr_url": "http://farm1.staticflickr.com/214/491961657_8bb9a1d8ae_z.jpg", "id": 187537}, {"license": 1, "file_name": "000000498854.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000498854.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 20:08:52", "flickr_url": "http://farm1.staticflickr.com/52/163212255_03274c749f_z.jpg", "id": 498854}, {"license": 1, "file_name": "000000228519.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000228519.jpg", "height": 334, "width": 500, "date_captured": "2013-11-15 12:01:36", "flickr_url": "http://farm1.staticflickr.com/25/67990980_2cf53b9563_z.jpg", "id": 228519}, {"license": 1, "file_name": "000000187563.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000187563.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 15:24:08", "flickr_url": "http://farm5.staticflickr.com/4015/4311521800_723d3725c7_z.jpg", "id": 187563}, {"license": 3, "file_name": "000000466093.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000466093.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 00:31:35", "flickr_url": "http://farm3.staticflickr.com/2828/9546323357_060254bacc_z.jpg", "id": 466093}, {"license": 5, "file_name": "000000416948.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000416948.jpg", "height": 448, "width": 640, "date_captured": "2013-11-18 00:01:26", "flickr_url": "http://farm6.staticflickr.com/5181/5641163816_5569ea0d36_z.jpg", "id": 416948}, {"license": 2, "file_name": "000000187577.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000187577.jpg", "height": 427, "width": 640, "date_captured": "2013-11-20 20:50:59", "flickr_url": "http://farm9.staticflickr.com/8236/8589551725_780251119d_z.jpg", "id": 187577}, {"license": 4, "file_name": "000000572602.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000572602.jpg", "height": 475, "width": 576, "date_captured": "2013-11-19 20:31:48", "flickr_url": "http://farm6.staticflickr.com/5324/7061077193_4205ed4eb7_z.jpg", "id": 572602}, {"license": 1, "file_name": "000000310457.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000310457.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 21:16:55", "flickr_url": "http://farm4.staticflickr.com/3465/3197479926_b39da4544c_z.jpg", "id": 310457}, {"license": 1, "file_name": "000000179390.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000179390.jpg", "height": 461, "width": 640, "date_captured": "2013-11-17 23:48:54", "flickr_url": "http://farm7.staticflickr.com/6004/5918895701_17f6cc7f26_z.jpg", "id": 179390}, {"license": 4, "file_name": "000000294080.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000294080.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 01:38:06", "flickr_url": "http://farm3.staticflickr.com/2028/5729023157_7cd93a07fa_z.jpg", "id": 294080}, {"license": 3, "file_name": "000000171210.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000171210.jpg", "height": 640, "width": 256, "date_captured": "2013-11-24 06:30:12", "flickr_url": "http://farm5.staticflickr.com/4023/4485409832_290af629d0_z.jpg", "id": 171210}, {"license": 4, "file_name": "000000203994.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000203994.jpg", "height": 425, "width": 640, "date_captured": "2013-11-20 17:56:54", "flickr_url": "http://farm4.staticflickr.com/3187/2822936169_92624a4885_z.jpg", "id": 203994}, {"license": 5, "file_name": "000000523484.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523484.jpg", "height": 375, "width": 500, "date_captured": "2013-11-14 17:12:38", "flickr_url": "http://farm3.staticflickr.com/2562/4014762447_2845879cbf_z.jpg", "id": 523484}, {"license": 1, "file_name": "000000269532.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000269532.jpg", "height": 640, "width": 640, "date_captured": "2013-11-16 20:20:38", "flickr_url": "http://farm6.staticflickr.com/5349/8927106263_2d00b0020b_z.jpg", "id": 269532}, {"license": 3, "file_name": "000000523487.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523487.jpg", "height": 640, "width": 623, "date_captured": "2013-11-14 23:28:13", "flickr_url": "http://farm5.staticflickr.com/4032/4716140184_8ab1d7225e_z.jpg", "id": 523487}, {"license": 1, "file_name": "000000007393.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007393.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 12:01:02", "flickr_url": "http://farm2.staticflickr.com/1156/1252230716_67880a7ce1_z.jpg", "id": 7393}, {"license": 4, "file_name": "000000515309.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000515309.jpg", "height": 446, "width": 640, "date_captured": "2013-11-15 20:57:14", "flickr_url": "http://farm7.staticflickr.com/6107/6876034642_50bcb4edf6_z.jpg", "id": 515309}, {"license": 5, "file_name": "000000105714.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000105714.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 15:12:19", "flickr_url": "http://farm5.staticflickr.com/4145/5134389286_fe4f8e0ea0_z.jpg", "id": 105714}, {"license": 3, "file_name": "000000105718.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000105718.jpg", "height": 329, "width": 640, "date_captured": "2013-11-16 20:48:35", "flickr_url": "http://farm4.staticflickr.com/3701/9476034164_388d4507cc_z.jpg", "id": 105718}, {"license": 4, "file_name": "000000326903.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000326903.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 11:49:52", "flickr_url": "http://farm4.staticflickr.com/3321/3421735953_333c194db4_z.jpg", "id": 326903}, {"license": 5, "file_name": "000000138496.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000138496.jpg", "height": 640, "width": 426, "date_captured": "2013-11-18 14:57:14", "flickr_url": "http://farm7.staticflickr.com/6100/6337366870_1b829fb38c_z.jpg", "id": 138496}, {"license": 6, "file_name": "000000310536.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000310536.jpg", "height": 640, "width": 431, "date_captured": "2013-11-18 06:33:35", "flickr_url": "http://farm3.staticflickr.com/2425/3857638124_2bb3fda7d1_z.jpg", "id": 310536}, {"license": 2, "file_name": "000000195861.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000195861.jpg", "height": 538, "width": 640, "date_captured": "2013-11-15 04:16:41", "flickr_url": "http://farm8.staticflickr.com/7273/7025191935_530eb04eae_z.jpg", "id": 195861}, {"license": 1, "file_name": "000000097563.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000097563.jpg", "height": 640, "width": 428, "date_captured": "2013-11-18 17:14:00", "flickr_url": "http://farm3.staticflickr.com/2360/2411164563_0bc223070e_z.jpg", "id": 97563}, {"license": 5, "file_name": "000000433435.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000433435.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 08:27:56", "flickr_url": "http://farm6.staticflickr.com/5289/5329980075_68691650ea_z.jpg", "id": 433435}, {"license": 3, "file_name": "000000539941.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000539941.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 00:50:15", "flickr_url": "http://farm7.staticflickr.com/6107/6232562984_2f5a741a79_z.jpg", "id": 539941}, {"license": 4, "file_name": "000000056616.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000056616.jpg", "height": 640, "width": 609, "date_captured": "2013-11-20 06:10:33", "flickr_url": "http://farm3.staticflickr.com/2455/3904547810_7348b1d048_z.jpg", "id": 56616}, {"license": 1, "file_name": "000000015658.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000015658.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 05:41:27", "flickr_url": "http://farm3.staticflickr.com/2571/4407062712_38e412d798_z.jpg", "id": 15658}, {"license": 1, "file_name": "000000048432.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000048432.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 00:33:32", "flickr_url": "http://farm8.staticflickr.com/7269/7519859028_f4d257582f_z.jpg", "id": 48432}, {"license": 1, "file_name": "000000253238.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000253238.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 08:33:31", "flickr_url": "http://farm3.staticflickr.com/2105/2131986442_6770b96cee_z.jpg", "id": 253238}, {"license": 1, "file_name": "000000523577.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523577.jpg", "height": 333, "width": 500, "date_captured": "2013-11-18 19:48:19", "flickr_url": "http://farm4.staticflickr.com/3129/3248161270_e8abee7833_z.jpg", "id": 523577}, {"license": 1, "file_name": "000000007504.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007504.jpg", "height": 422, "width": 640, "date_captured": "2013-11-22 19:34:53", "flickr_url": "http://farm8.staticflickr.com/7119/7503914948_8392b60edc_z.jpg", "id": 7504}, {"license": 4, "file_name": "000000220504.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000220504.jpg", "height": 612, "width": 612, "date_captured": "2013-11-15 16:57:37", "flickr_url": "http://farm9.staticflickr.com/8094/8598339688_1eba4f4b12_z.jpg", "id": 220504}, {"license": 4, "file_name": "000000097632.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000097632.jpg", "height": 427, "width": 640, "date_captured": "2013-11-23 03:37:19", "flickr_url": "http://farm4.staticflickr.com/3469/3228659048_c06d092644_z.jpg", "id": 97632}, {"license": 1, "file_name": "000000286051.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000286051.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 03:47:06", "flickr_url": "http://farm5.staticflickr.com/4117/4749559205_904a32e7aa_z.jpg", "id": 286051}, {"license": 1, "file_name": "000000056677.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000056677.jpg", "height": 394, "width": 640, "date_captured": "2013-11-20 19:19:53", "flickr_url": "http://farm9.staticflickr.com/8460/8004478395_0a3c3cde3e_z.jpg", "id": 56677}, {"license": 3, "file_name": "000000032105.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032105.jpg", "height": 471, "width": 640, "date_captured": "2013-11-18 11:37:34", "flickr_url": "http://farm1.staticflickr.com/98/231309621_82f536c712_z.jpg", "id": 32105}, {"license": 2, "file_name": "000000580979.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000580979.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 08:24:24", "flickr_url": "http://farm4.staticflickr.com/3745/9294626527_de4948b1b1_z.jpg", "id": 580979}, {"license": 6, "file_name": "000000122231.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000122231.jpg", "height": 427, "width": 640, "date_captured": "2013-11-23 05:46:47", "flickr_url": "http://farm1.staticflickr.com/28/48614365_bd61519b1a_z.jpg", "id": 122231}, {"license": 5, "file_name": "000000408954.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000408954.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 02:38:50", "flickr_url": "http://farm9.staticflickr.com/8174/8026238388_510ecf200e_z.jpg", "id": 408954}, {"license": 1, "file_name": "000000056699.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000056699.jpg", "height": 491, "width": 640, "date_captured": "2013-11-15 18:07:48", "flickr_url": "http://farm9.staticflickr.com/8344/8176737103_9a1a080cb9_z.jpg", "id": 56699}, {"license": 3, "file_name": "000000449914.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000449914.jpg", "height": 480, "width": 640, "date_captured": "2013-11-23 00:40:08", "flickr_url": "http://farm9.staticflickr.com/8161/7628714314_c3141f4314_z.jpg", "id": 449914}, {"license": 3, "file_name": "000000228734.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000228734.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 21:41:23", "flickr_url": "http://farm4.staticflickr.com/3074/2654609516_0c2ca64133_z.jpg", "id": 228734}, {"license": 2, "file_name": "000000490887.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000490887.jpg", "height": 640, "width": 640, "date_captured": "2013-11-15 17:37:59", "flickr_url": "http://farm6.staticflickr.com/5350/10137162445_2fa9f46a52_z.jpg", "id": 490887}, {"license": 4, "file_name": "000000122259.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000122259.jpg", "height": 375, "width": 500, "date_captured": "2013-11-25 20:15:43", "flickr_url": "http://farm3.staticflickr.com/2703/4092290729_d60a53d99b_z.jpg", "id": 122259}, {"license": 4, "file_name": "000000253335.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000253335.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 22:24:16", "flickr_url": "http://farm9.staticflickr.com/8370/8593101886_2f0d86927a_z.jpg", "id": 253335}, {"license": 1, "file_name": "000000269723.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000269723.jpg", "height": 360, "width": 640, "date_captured": "2013-11-21 19:33:18", "flickr_url": "http://farm3.staticflickr.com/2650/3963687326_1e4c0a171d_z.jpg", "id": 269723}, {"license": 3, "file_name": "000000236961.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000236961.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 23:18:43", "flickr_url": "http://farm9.staticflickr.com/8159/7455117666_d57e8a23bc_z.jpg", "id": 236961}, {"license": 5, "file_name": "000000179618.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000179618.jpg", "height": 640, "width": 480, "date_captured": "2013-11-14 22:20:13", "flickr_url": "http://farm1.staticflickr.com/108/315850005_b7fb60e8d9_z.jpg", "id": 179618}, {"license": 3, "file_name": "000000482731.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000482731.jpg", "height": 399, "width": 640, "date_captured": "2013-11-23 00:48:14", "flickr_url": "http://farm6.staticflickr.com/5231/7185543137_a953e4efd0_z.jpg", "id": 482731}, {"license": 4, "file_name": "000000376241.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000376241.jpg", "height": 427, "width": 640, "date_captured": "2013-11-21 19:28:59", "flickr_url": "http://farm1.staticflickr.com/72/210483142_c71b6eba6f_z.jpg", "id": 376241}, {"license": 1, "file_name": "000000007601.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007601.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 23:59:11", "flickr_url": "http://farm4.staticflickr.com/3049/5850976735_5c9cea7ac2_z.jpg", "id": 7601}, {"license": 5, "file_name": "000000581042.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000581042.jpg", "height": 640, "width": 428, "date_captured": "2013-11-24 14:16:11", "flickr_url": "http://farm8.staticflickr.com/7414/9097460314_2e576449aa_z.jpg", "id": 581042}, {"license": 3, "file_name": "000000286132.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000286132.jpg", "height": 640, "width": 480, "date_captured": "2013-11-19 23:53:18", "flickr_url": "http://farm3.staticflickr.com/2262/4513219304_8410624d5c_z.jpg", "id": 286132}, {"license": 1, "file_name": "000000425398.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000425398.jpg", "height": 464, "width": 640, "date_captured": "2013-11-16 20:26:07", "flickr_url": "http://farm6.staticflickr.com/5495/9170281898_0bc2d1e7e7_z.jpg", "id": 425398}, {"license": 3, "file_name": "000000204216.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000204216.jpg", "height": 430, "width": 640, "date_captured": "2013-11-17 09:31:28", "flickr_url": "http://farm3.staticflickr.com/2891/8926202542_54230b4e7c_z.jpg", "id": 204216}, {"license": 1, "file_name": "000000523711.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523711.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 17:13:20", "flickr_url": "http://farm4.staticflickr.com/3097/2730547938_26a22980f6_z.jpg", "id": 523711}, {"license": 2, "file_name": "000000015809.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000015809.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 21:32:33", "flickr_url": "http://farm3.staticflickr.com/2024/2275648884_9b58862f65_z.jpg", "id": 15809}, {"license": 3, "file_name": "000000540110.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000540110.jpg", "height": 488, "width": 640, "date_captured": "2013-11-17 14:43:14", "flickr_url": "http://farm9.staticflickr.com/8345/8162188655_3d4385fd5e_z.jpg", "id": 540110}, {"license": 6, "file_name": "000000400850.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000400850.jpg", "height": 425, "width": 640, "date_captured": "2013-11-17 06:09:08", "flickr_url": "http://farm8.staticflickr.com/7361/9405163888_1d2eaa954b_z.jpg", "id": 400850}, {"license": 1, "file_name": "000000171478.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000171478.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 15:10:52", "flickr_url": "http://farm8.staticflickr.com/7211/7330183298_7a861d6545_z.jpg", "id": 171478}, {"license": 3, "file_name": "000000171484.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000171484.jpg", "height": 386, "width": 640, "date_captured": "2013-11-16 17:43:14", "flickr_url": "http://farm8.staticflickr.com/7022/6655669745_1a529cfe00_z.jpg", "id": 171484}, {"license": 3, "file_name": "000000081372.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000081372.jpg", "height": 427, "width": 640, "date_captured": "2013-11-24 14:58:17", "flickr_url": "http://farm8.staticflickr.com/7099/7353830546_c69b76e99b_z.jpg", "id": 81372}, {"license": 2, "file_name": "000000155107.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000155107.jpg", "height": 478, "width": 640, "date_captured": "2013-11-21 02:46:41", "flickr_url": "http://farm5.staticflickr.com/4075/4746425318_d345544354_z.jpg", "id": 155107}, {"license": 4, "file_name": "000000007653.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007653.jpg", "height": 509, "width": 640, "date_captured": "2013-11-17 03:00:03", "flickr_url": "http://farm9.staticflickr.com/8003/7304882540_595a18df44_z.jpg", "id": 7653}, {"license": 4, "file_name": "000000040433.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000040433.jpg", "height": 480, "width": 640, "date_captured": "2013-11-18 02:02:10", "flickr_url": "http://farm4.staticflickr.com/3437/3923757605_73c86043b8_z.jpg", "id": 40433}, {"license": 3, "file_name": "000000065011.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000065011.jpg", "height": 640, "width": 439, "date_captured": "2013-11-22 02:22:42", "flickr_url": "http://farm4.staticflickr.com/3309/4581290870_16335d07c8_z.jpg", "id": 65011}, {"license": 3, "file_name": "000000417276.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000417276.jpg", "height": 640, "width": 425, "date_captured": "2013-11-14 19:29:30", "flickr_url": "http://farm6.staticflickr.com/5280/7190639742_56c6e840c7_z.jpg", "id": 417276}, {"license": 1, "file_name": "000000204294.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000204294.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 04:17:11", "flickr_url": "http://farm5.staticflickr.com/4021/4456176240_1a14f3e11c_z.jpg", "id": 204294}, {"license": 1, "file_name": "000000335376.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000335376.jpg", "height": 375, "width": 500, "date_captured": "2013-11-23 04:07:24", "flickr_url": "http://farm4.staticflickr.com/3439/3834436636_b68b18ba8b_z.jpg", "id": 335376}, {"license": 4, "file_name": "000000187939.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000187939.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 02:49:39", "flickr_url": "http://farm6.staticflickr.com/5047/5356400592_4767d69b10_z.jpg", "id": 187939}, {"license": 2, "file_name": "000000327209.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000327209.jpg", "height": 424, "width": 640, "date_captured": "2013-11-24 08:27:09", "flickr_url": "http://farm3.staticflickr.com/2502/4190659862_669d30b6c4_z.jpg", "id": 327209}, {"license": 2, "file_name": "000000204339.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000204339.jpg", "height": 324, "width": 640, "date_captured": "2013-11-21 19:34:32", "flickr_url": "http://farm1.staticflickr.com/39/84043264_1045442ffa_z.jpg", "id": 204339}, {"license": 1, "file_name": "000000540211.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000540211.jpg", "height": 333, "width": 500, "date_captured": "2013-11-24 07:41:06", "flickr_url": "http://farm1.staticflickr.com/103/305248951_79bf244a1a_z.jpg", "id": 540211}, {"license": 3, "file_name": "000000433723.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000433723.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 12:20:20", "flickr_url": "http://farm4.staticflickr.com/3238/2591996168_32a822d2f7_z.jpg", "id": 433723}, {"license": 3, "file_name": "000000196156.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000196156.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 05:08:46", "flickr_url": "http://farm8.staticflickr.com/7160/6688436631_a463716843_z.jpg", "id": 196156}, {"license": 3, "file_name": "000000171581.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000171581.jpg", "height": 428, "width": 640, "date_captured": "2013-11-18 21:22:54", "flickr_url": "http://farm7.staticflickr.com/6208/6036499780_02d0329b34_z.jpg", "id": 171581}, {"license": 4, "file_name": "000000548416.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000548416.jpg", "height": 375, "width": 500, "date_captured": "2013-11-15 11:38:35", "flickr_url": "http://farm1.staticflickr.com/38/79010491_ced68258e4_z.jpg", "id": 548416}, {"license": 1, "file_name": "000000261696.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000261696.jpg", "height": 640, "width": 428, "date_captured": "2013-11-22 19:02:17", "flickr_url": "http://farm3.staticflickr.com/2775/4377309892_4bacb2eb17_z.jpg", "id": 261696}, {"license": 3, "file_name": "000000007746.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007746.jpg", "height": 375, "width": 500, "date_captured": "2013-11-16 14:15:54", "flickr_url": "http://farm4.staticflickr.com/3589/3562016463_d79230b11c_z.jpg", "id": 7746}, {"license": 5, "file_name": "000000048707.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000048707.jpg", "height": 429, "width": 640, "date_captured": "2013-11-20 13:17:44", "flickr_url": "http://farm3.staticflickr.com/2522/4085672622_ceb95de58b_z.jpg", "id": 48707}, {"license": 2, "file_name": "000000360002.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000360002.jpg", "height": 640, "width": 427, "date_captured": "2013-11-18 15:50:17", "flickr_url": "http://farm3.staticflickr.com/2801/4495450244_25ec466631_z.jpg", "id": 360002}, {"license": 2, "file_name": "000000572998.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000572998.jpg", "height": 427, "width": 640, "date_captured": "2013-11-22 21:43:08", "flickr_url": "http://farm7.staticflickr.com/6215/6287152730_40d039f7c0_z.jpg", "id": 572998}, {"license": 5, "file_name": "000000564812.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000564812.jpg", "height": 640, "width": 434, "date_captured": "2013-11-16 15:48:39", "flickr_url": "http://farm4.staticflickr.com/3423/3207138143_8705223900_z.jpg", "id": 564812}, {"license": 2, "file_name": "000000523863.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000523863.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 07:45:10", "flickr_url": "http://farm1.staticflickr.com/164/350068023_407ec2c938_z.jpg", "id": 523863}, {"license": 3, "file_name": "000000564823.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000564823.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 11:38:37", "flickr_url": "http://farm4.staticflickr.com/3043/2948738114_2e9972e0b2_z.jpg", "id": 564823}, {"license": 3, "file_name": "000000466523.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000466523.jpg", "height": 341, "width": 640, "date_captured": "2013-11-17 18:09:35", "flickr_url": "http://farm6.staticflickr.com/5466/8760479284_697d61f3b3_z.jpg", "id": 466523}, {"license": 1, "file_name": "000000196198.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000196198.jpg", "height": 401, "width": 500, "date_captured": "2013-11-15 13:46:54", "flickr_url": "http://farm3.staticflickr.com/2202/2435406511_d553097602_z.jpg", "id": 196198}, {"license": 1, "file_name": "000000327271.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000327271.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 18:49:10", "flickr_url": "http://farm9.staticflickr.com/8086/8452221810_4fcdbcb715_z.jpg", "id": 327271}, {"license": 3, "file_name": "000000441972.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000441972.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 00:35:54", "flickr_url": "http://farm8.staticflickr.com/7358/9689140902_40fb4093b0_z.jpg", "id": 441972}, {"license": 5, "file_name": "000000106100.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000106100.jpg", "height": 457, "width": 640, "date_captured": "2013-11-19 20:41:42", "flickr_url": "http://farm5.staticflickr.com/4087/5086456430_23a851ec47_z.jpg", "id": 106100}, {"license": 2, "file_name": "000000507520.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000507520.jpg", "height": 427, "width": 640, "date_captured": "2013-11-17 18:31:45", "flickr_url": "http://farm9.staticflickr.com/8532/8620321650_3083e1e446_z.jpg", "id": 507520}, {"license": 1, "file_name": "000000155268.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000155268.jpg", "height": 426, "width": 640, "date_captured": "2013-11-22 00:25:38", "flickr_url": "http://farm1.staticflickr.com/111/305483561_83766af3a1_z.jpg", "id": 155268}, {"license": 5, "file_name": "000000204420.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000204420.jpg", "height": 334, "width": 500, "date_captured": "2013-11-15 00:43:56", "flickr_url": "http://farm1.staticflickr.com/84/246515114_431dfeb854_z.jpg", "id": 204420}, {"license": 6, "file_name": "000000581256.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000581256.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 13:44:22", "flickr_url": "http://farm9.staticflickr.com/8485/8194871919_923d187eb2_z.jpg", "id": 581256}, {"license": 3, "file_name": "000000229002.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000229002.jpg", "height": 375, "width": 500, "date_captured": "2013-11-19 23:35:17", "flickr_url": "http://farm3.staticflickr.com/2122/2265618981_91e2566b87_z.jpg", "id": 229002}, {"license": 2, "file_name": "000000097936.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000097936.jpg", "height": 426, "width": 640, "date_captured": "2013-11-15 04:57:24", "flickr_url": "http://farm4.staticflickr.com/3064/3111234017_8a1a474055_z.jpg", "id": 97936}, {"license": 1, "file_name": "000000212635.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000212635.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 01:28:51", "flickr_url": "http://farm4.staticflickr.com/3486/4076582559_210590e89c_z.jpg", "id": 212635}, {"license": 2, "file_name": "000000335524.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000335524.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 04:30:22", "flickr_url": "http://farm5.staticflickr.com/4010/4354502449_3bc58d6f4e_z.jpg", "id": 335524}, {"license": 2, "file_name": "000000261800.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000261800.jpg", "height": 612, "width": 612, "date_captured": "2013-11-18 10:13:21", "flickr_url": "http://farm8.staticflickr.com/7204/6982099079_d152fb67b1_z.jpg", "id": 261800}, {"license": 5, "file_name": "000000220842.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000220842.jpg", "height": 480, "width": 640, "date_captured": "2013-11-14 18:19:26", "flickr_url": "http://farm9.staticflickr.com/8361/8266221004_8210ac7539_z.jpg", "id": 220842}, {"license": 4, "file_name": "000000073387.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000073387.jpg", "height": 427, "width": 640, "date_captured": "2013-11-18 16:10:14", "flickr_url": "http://farm5.staticflickr.com/4108/4845987782_89f01438d4_z.jpg", "id": 73387}, {"license": 4, "file_name": "000000007852.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000007852.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 20:48:24", "flickr_url": "http://farm9.staticflickr.com/8011/6977248754_74250fc0d4_z.jpg", "id": 7852}, {"license": 3, "file_name": "000000089773.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000089773.jpg", "height": 374, "width": 500, "date_captured": "2013-11-21 02:51:38", "flickr_url": "http://farm4.staticflickr.com/3612/3344575847_e051fce158_z.jpg", "id": 89773}, {"license": 2, "file_name": "000000376505.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000376505.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 23:41:00", "flickr_url": "http://farm4.staticflickr.com/3011/2722479906_1167b9ae34_z.jpg", "id": 376505}, {"license": 4, "file_name": "000000089788.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000089788.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 15:30:41", "flickr_url": "http://farm9.staticflickr.com/8185/8388766172_caf8d53a60_z.jpg", "id": 89788}, {"license": 1, "file_name": "000000016069.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000016069.jpg", "height": 424, "width": 640, "date_captured": "2013-11-18 03:04:15", "flickr_url": "http://farm6.staticflickr.com/5287/5380412371_777f742199_z.jpg", "id": 16069}, {"license": 5, "file_name": "000000212679.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000212679.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 14:16:19", "flickr_url": "http://farm4.staticflickr.com/3681/9692771432_7e9ba08cec_z.jpg", "id": 212679}, {"license": 1, "file_name": "000000532175.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000532175.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 15:31:00", "flickr_url": "http://farm8.staticflickr.com/7383/8855477266_c4a56925d0_z.jpg", "id": 532175}, {"license": 1, "file_name": "000000188120.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000188120.jpg", "height": 480, "width": 640, "date_captured": "2013-11-22 10:50:01", "flickr_url": "http://farm9.staticflickr.com/8110/8526303172_0bac8ceca2_z.jpg", "id": 188120}, {"license": 1, "file_name": "000000319192.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000319192.jpg", "height": 512, "width": 640, "date_captured": "2013-11-20 12:37:48", "flickr_url": "http://farm5.staticflickr.com/4137/4881152687_684e30d03d_z.jpg", "id": 319192}, {"license": 5, "file_name": "000000327404.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000327404.jpg", "height": 640, "width": 480, "date_captured": "2013-11-20 15:56:10", "flickr_url": "http://farm4.staticflickr.com/3266/2829200530_35cfd9526e_z.jpg", "id": 327404}, {"license": 3, "file_name": "000000204529.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000204529.jpg", "height": 480, "width": 640, "date_captured": "2013-11-25 19:34:55", "flickr_url": "http://farm7.staticflickr.com/6174/6183449159_85dc948604_z.jpg", "id": 204529}, {"license": 5, "file_name": "000000491249.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000491249.jpg", "height": 426, "width": 640, "date_captured": "2013-11-21 00:47:22", "flickr_url": "http://farm6.staticflickr.com/5149/5638690534_a42aa72f55_z.jpg", "id": 491249}, {"license": 3, "file_name": "000000098038.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000098038.jpg", "height": 480, "width": 640, "date_captured": "2013-11-17 22:43:52", "flickr_url": "http://farm8.staticflickr.com/7224/7010094975_9885caf336_z.jpg", "id": 98038}, {"license": 1, "file_name": "000000286483.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000286483.jpg", "height": 480, "width": 640, "date_captured": "2013-11-20 09:06:32", "flickr_url": "http://farm1.staticflickr.com/140/379940713_9f00f22a36_z.jpg", "id": 286483}, {"license": 4, "file_name": "000000212757.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000212757.jpg", "height": 426, "width": 640, "date_captured": "2013-11-20 16:27:40", "flickr_url": "http://farm7.staticflickr.com/6217/6259463416_2d8e72ac2e_z.jpg", "id": 212757}, {"license": 5, "file_name": "000000032533.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032533.jpg", "height": 640, "width": 634, "date_captured": "2013-11-15 05:27:46", "flickr_url": "http://farm8.staticflickr.com/7157/6796096013_3f26806314_z.jpg", "id": 32533}, {"license": 6, "file_name": "000000565018.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000565018.jpg", "height": 500, "width": 417, "date_captured": "2013-11-18 16:40:45", "flickr_url": "http://farm4.staticflickr.com/3163/3023175352_e5dd9086ae_z.jpg", "id": 565018}, {"license": 6, "file_name": "000000114459.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000114459.jpg", "height": 480, "width": 640, "date_captured": "2013-11-16 21:07:12", "flickr_url": "http://farm8.staticflickr.com/7422/9316740790_c917c07be0_z.jpg", "id": 114459}, {"license": 3, "file_name": "000000171808.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000171808.jpg", "height": 640, "width": 480, "date_captured": "2013-11-21 21:57:11", "flickr_url": "http://farm4.staticflickr.com/3085/2544365955_8cff9b6b35_z.jpg", "id": 171808}, {"license": 1, "file_name": "000000343847.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000343847.jpg", "height": 453, "width": 640, "date_captured": "2013-11-18 03:13:13", "flickr_url": "http://farm6.staticflickr.com/5210/5319475262_81cd248724_z.jpg", "id": 343847}, {"license": 4, "file_name": "000000032575.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032575.jpg", "height": 426, "width": 640, "date_captured": "2013-11-19 21:30:13", "flickr_url": "http://farm8.staticflickr.com/7171/6767499315_e242840df4_z.jpg", "id": 32575}, {"license": 3, "file_name": "000000491330.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000491330.jpg", "height": 480, "width": 640, "date_captured": "2013-11-19 20:42:53", "flickr_url": "http://farm1.staticflickr.com/170/469099265_73991ad1d6_z.jpg", "id": 491330}, {"license": 1, "file_name": "000000565070.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000565070.jpg", "height": 640, "width": 480, "date_captured": "2013-11-24 09:05:28", "flickr_url": "http://farm3.staticflickr.com/2358/2238583048_287ff2aa98_z.jpg", "id": 565070}, {"license": 3, "file_name": "000000024404.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000024404.jpg", "height": 375, "width": 500, "date_captured": "2013-11-18 22:06:51", "flickr_url": "http://farm1.staticflickr.com/76/155105224_439f0facf9_z.jpg", "id": 24404}, {"license": 3, "file_name": "000000368479.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000368479.jpg", "height": 427, "width": 640, "date_captured": "2013-11-16 14:56:18", "flickr_url": "http://farm8.staticflickr.com/7114/7486064038_c42705f7fd_z.jpg", "id": 368479}, {"license": 1, "file_name": "000000466790.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000466790.jpg", "height": 640, "width": 480, "date_captured": "2013-11-16 17:21:27", "flickr_url": "http://farm8.staticflickr.com/7261/6943829328_c1e231e85b_z.jpg", "id": 466790}, {"license": 5, "file_name": "000000147303.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000147303.jpg", "height": 360, "width": 640, "date_captured": "2013-11-16 19:37:21", "flickr_url": "http://farm8.staticflickr.com/7348/9964349114_47e89dbe48_z.jpg", "id": 147303}, {"license": 3, "file_name": "000000081768.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000081768.jpg", "height": 334, "width": 500, "date_captured": "2013-11-16 17:59:31", "flickr_url": "http://farm4.staticflickr.com/3126/2509623843_a6fb354e1d_z.jpg", "id": 81768}, {"license": 3, "file_name": "000000016243.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000016243.jpg", "height": 429, "width": 640, "date_captured": "2013-11-20 18:35:00", "flickr_url": "http://farm8.staticflickr.com/7260/7642262556_e4e14cfef0_z.jpg", "id": 16243}, {"license": 6, "file_name": "000000434039.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000434039.jpg", "height": 428, "width": 640, "date_captured": "2013-11-19 18:28:30", "flickr_url": "http://farm1.staticflickr.com/211/458917386_bccbd093ce_z.jpg", "id": 434039}, {"license": 3, "file_name": "000000384888.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000384888.jpg", "height": 640, "width": 426, "date_captured": "2013-11-25 14:27:34", "flickr_url": "http://farm4.staticflickr.com/3828/9559142051_388a3bc872_z.jpg", "id": 384888}, {"license": 1, "file_name": "000000008063.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000008063.jpg", "height": 428, "width": 640, "date_captured": "2013-11-18 12:06:47", "flickr_url": "http://farm1.staticflickr.com/146/351839106_069af2aeb2_z.jpg", "id": 8063}, {"license": 6, "file_name": "000000065407.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000065407.jpg", "height": 358, "width": 500, "date_captured": "2013-11-21 02:50:49", "flickr_url": "http://farm4.staticflickr.com/3247/2972101964_f9e6e6aaee_z.jpg", "id": 65407}, {"license": 3, "file_name": "000000466825.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000466825.jpg", "height": 640, "width": 428, "date_captured": "2013-11-15 14:44:52", "flickr_url": "http://farm6.staticflickr.com/5083/5231979556_0d0cffd321_z.jpg", "id": 466825}, {"license": 1, "file_name": "000000253834.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000253834.jpg", "height": 612, "width": 612, "date_captured": "2013-11-24 23:01:15", "flickr_url": "http://farm6.staticflickr.com/5448/9285012858_51b1cbfa7a_z.jpg", "id": 253834}, {"license": 4, "file_name": "000000106397.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000106397.jpg", "height": 512, "width": 640, "date_captured": "2013-11-17 10:53:23", "flickr_url": "http://farm6.staticflickr.com/5135/5507997428_2563936e33_z.jpg", "id": 106397}, {"license": 4, "file_name": "000000155549.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000155549.jpg", "height": 425, "width": 640, "date_captured": "2013-11-22 00:50:18", "flickr_url": "http://farm5.staticflickr.com/4066/4301247456_6f7b339c20_z.jpg", "id": 155549}, {"license": 1, "file_name": "000000319396.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000319396.jpg", "height": 640, "width": 480, "date_captured": "2013-11-15 01:38:23", "flickr_url": "http://farm1.staticflickr.com/1/179757_2e45d0c674_z.jpg", "id": 319396}, {"license": 1, "file_name": "000000270248.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000270248.jpg", "height": 424, "width": 640, "date_captured": "2013-11-23 00:25:00", "flickr_url": "http://farm9.staticflickr.com/8114/8686517149_ec281f464e_z.jpg", "id": 270248}, {"license": 3, "file_name": "000000573360.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000573360.jpg", "height": 640, "width": 427, "date_captured": "2013-11-19 21:04:36", "flickr_url": "http://farm4.staticflickr.com/3104/2559353875_e08d93e193_z.jpg", "id": 573360}, {"license": 1, "file_name": "000000163764.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000163764.jpg", "height": 640, "width": 469, "date_captured": "2013-11-20 17:12:12", "flickr_url": "http://farm2.staticflickr.com/1419/1213595442_527c2df74d_z.jpg", "id": 163764}, {"license": 4, "file_name": "000000352185.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000352185.jpg", "height": 480, "width": 640, "date_captured": "2013-11-15 04:42:23", "flickr_url": "http://farm4.staticflickr.com/3211/2708773600_5fb058bb25_z.jpg", "id": 352185}, {"license": 4, "file_name": "000000032707.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000032707.jpg", "height": 640, "width": 426, "date_captured": "2013-11-19 21:09:52", "flickr_url": "http://farm8.staticflickr.com/7210/6793115454_dba5c2b077_z.jpg", "id": 32707}, {"license": 4, "file_name": "000000524227.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000524227.jpg", "height": 480, "width": 640, "date_captured": "2013-11-21 05:46:46", "flickr_url": "http://farm5.staticflickr.com/4054/4628841371_e504764076_z.jpg", "id": 524227}, {"license": 3, "file_name": "000000253907.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000253907.jpg", "height": 380, "width": 500, "date_captured": "2013-11-14 14:13:50", "flickr_url": "http://farm4.staticflickr.com/3254/2813410670_af0e322df9_z.jpg", "id": 253907}, {"license": 5, "file_name": "000000548822.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000548822.jpg", "height": 640, "width": 427, "date_captured": "2013-11-20 19:55:24", "flickr_url": "http://farm9.staticflickr.com/8543/8632173312_0fb2a2fcdc_z.jpg", "id": 548822}, {"license": 2, "file_name": "000000131030.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000131030.jpg", "height": 640, "width": 480, "date_captured": "2013-11-23 03:25:00", "flickr_url": "http://farm3.staticflickr.com/2738/4269951363_c914d10db0_z.jpg", "id": 131030}, {"license": 4, "file_name": "000000417753.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000417753.jpg", "height": 326, "width": 500, "date_captured": "2013-11-22 21:31:13", "flickr_url": "http://farm3.staticflickr.com/2200/2247442050_efef201143_z.jpg", "id": 417753}, {"license": 4, "file_name": "000000417761.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000417761.jpg", "height": 500, "width": 375, "date_captured": "2013-11-20 14:39:58", "flickr_url": "http://farm1.staticflickr.com/233/461928114_c2bdbdfa9a_z.jpg", "id": 417761}, {"license": 1, "file_name": "000000155618.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000155618.jpg", "height": 640, "width": 478, "date_captured": "2013-11-15 01:11:37", "flickr_url": "http://farm8.staticflickr.com/7074/7326861622_beee6c24bc_z.jpg", "id": 155618}, {"license": 5, "file_name": "000000286690.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000286690.jpg", "height": 375, "width": 500, "date_captured": "2013-11-22 01:20:34", "flickr_url": "http://farm1.staticflickr.com/69/171754265_9a461452b6_z.jpg", "id": 286690}, {"license": 5, "file_name": "000000311273.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000311273.jpg", "height": 640, "width": 484, "date_captured": "2013-11-20 19:58:27", "flickr_url": "http://farm8.staticflickr.com/7377/9327092428_8fefb55278_z.jpg", "id": 311273}, {"license": 2, "file_name": "000000221169.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000221169.jpg", "height": 640, "width": 569, "date_captured": "2013-11-18 10:39:26", "flickr_url": "http://farm7.staticflickr.com/6190/6045512001_b06f5a4552_z.jpg", "id": 221169}, {"license": 3, "file_name": "000000376817.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000376817.jpg", "height": 480, "width": 640, "date_captured": "2013-11-24 09:02:21", "flickr_url": "http://farm3.staticflickr.com/2042/2415654844_3e1ac0b6b8_z.jpg", "id": 376817}, {"license": 3, "file_name": "000000442356.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000442356.jpg", "height": 640, "width": 480, "date_captured": "2013-11-22 15:02:40", "flickr_url": "http://farm6.staticflickr.com/5319/7387447756_8abce0153d_z.jpg", "id": 442356}, {"license": 3, "file_name": "000000253942.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000253942.jpg", "height": 426, "width": 640, "date_captured": "2013-11-18 15:42:31", "flickr_url": "http://farm6.staticflickr.com/5241/5343823701_9a3ffd72cd_z.jpg", "id": 253942}, {"license": 6, "file_name": "000000458751.jpg", "coco_url": "http://images.cocodataset.org/train2017/000000458751.jpg", "height": 576, "width": 592, "date_captured": "2013-11-16 21:13:51", "flickr_url": "http://farm8.staticflickr.com/7018/6821165845_48ebd9590f_z.jpg", "id": 458751}], "annotations": [{"segmentation": [[316.09, 145.29, 330.51, 133.09, 344.93, 136.42, 364.89, 144.18, 380.42, 146.4, 397.05, 133.09, 413.69, 104.25, 417.02, 89.84, 424.78, 59.89, 422.56, 43.25, 411.47, 33.27, 394.84, 28.84, 381.53, 29.95, 363.78, 31.05, 346.04, 27.73, 321.64, 23.29, 307.22, 26.62, 291.69, 41.04, 286.15, 48.8, 285.04, 57.67, 285.04, 73.2, 291.69, 92.05, 296.13, 107.58, 295.02, 125.33, 301.67, 136.42, 312.76, 144.18, 313.87, 145.29]], "area": 13657.727050000001, "iscrowd": 0, "image_id": 533220, "bbox": [285.04, 23.29, 139.74, 123.11], "category_id": 64, "id": 1954731, "split": "val", "sentences": [{"tokens": ["a", "bush", "of", "plant", "behind", "middle", "woman"], "raw": "a bush of plant behind middle woman", "sent_id": 61, "sent": "a bush of plant behind middle woman"}, {"tokens": ["green", "plant", "behind", "a", "table", "visible", "behind", "a", "lady", "'", "s", "head"], "raw": "Green plant behind a table visible behind a lady's head.", "sent_id": 62, "sent": "green plant behind a table visible behind a lady ' s head"}], "file_name": "COCO_train2014_000000533220_1954731.jpg", "ann_id": 1954731, "sent_ids": [61, 62], "ref_id": 5044}, {"segmentation": [[203.98, 146.56, 194.93, 136.68, 191.63, 117.74, 192.46, 97.98, 187.52, 86.45, 189.99, 78.22, 183.4, 74.93, 185.05, 68.34, 200.69, 79.87, 210.57, 78.22, 222.1, 73.28, 226.22, 68.34, 227.86, 79.87, 224.57, 89.75, 224.57, 94.69, 236.92, 101.28, 284.68, 114.45, 299.5, 120.21, 310.21, 135.86, 301.97, 145.74, 292.92, 151.5, 279.74, 154.8, 274.8, 152.33, 273.15, 162.21, 258.33, 166.33, 245.98, 167.15, 248.45, 158.92, 261.63, 156.45, 244.33, 152.33, 231.16, 150.68, 228.69, 144.09, 209.75, 151.5]], "area": 6075.106399999999, "iscrowd": 0, "image_id": 296760, "bbox": [183.4, 68.34, 126.81, 98.81], "category_id": 18, "id": 17811, "split": "val", "sentences": [{"tokens": ["black", "and", "white", "dog", "with", "pointy", "ears"], "raw": "Black and white dog with pointy ears.", "sent_id": 127, "sent": "black and white dog with pointy ears"}, {"tokens": ["the", "black", "and", "white", "dog", "nearest", "the", "wall"], "raw": "The black and white dog nearest the wall.", "sent_id": 128, "sent": "the black and white dog nearest the wall"}], "file_name": "COCO_train2014_000000296760_17811.jpg", "ann_id": 17811, "sent_ids": [127, 128], "ref_id": 5064}, {"segmentation": [[631.62, 359.17, 599.9, 338.02, 586.44, 328.41, 560.48, 319.75, 526.83, 322.64, 498.95, 320.71, 490.3, 318.79, 486.45, 312.06, 475.88, 310.14, 465.3, 305.33, 460.5, 299.56, 468.19, 286.1, 468.19, 279.38, 459.54, 277.45, 451.85, 283.22, 445.12, 273.61, 437.42, 269.76, 423.0, 276.49, 414.35, 279.38, 408.58, 283.22, 406.66, 293.8, 408.58, 297.64, 403.78, 310.14, 394.16, 310.14, 396.09, 328.41, 409.55, 330.33, 421.08, 344.75, 428.77, 352.44, 432.62, 359.17, 434.54, 365.9, 440.31, 368.78, 417.24, 375.51, 400.89, 377.44, 398.01, 383.2, 414.35, 387.05, 443.19, 379.36, 457.61, 383.2, 480.69, 377.44, 509.53, 386.09, 528.76, 382.24, 563.36, 375.51, 592.21, 368.78, 620.09, 365.9]], "area": 13876.142000000002, "iscrowd": 0, "image_id": 416948, "bbox": [394.16, 269.76, 237.46, 117.29], "category_id": 21, "id": 72969, "split": "val", "sentences": [{"tokens": ["small", "cow", "laying", "down"], "raw": "small cow laying down", "sent_id": 234, "sent": "small cow laying down"}, {"tokens": ["the", "front", "most", "cow", "to", "the", "right", "of", "other", "cows"], "raw": "The front most cow to the right of other cows.", "sent_id": 235, "sent": "the front most cow to the right of other cows"}], "file_name": "COCO_train2014_000000416948_72969.jpg", "ann_id": 72969, "sent_ids": [234, 235], "ref_id": 5105}, {"segmentation": [[284.68, 171.05, 287.05, 161.1, 275.68, 166.78, 261.94, 161.1, 268.1, 172.0, 283.73, 167.73], [259.57, 170.1, 256.73, 163.0, 243.0, 159.21, 253.89, 172.0, 260.52, 171.52], [226.42, 159.21, 184.73, 158.26, 143.05, 158.26, 118.89, 179.57, 112.26, 187.63, 109.42, 204.68, 109.42, 222.68, 107.05, 233.57, 103.26, 249.68, 94.74, 261.52, 96.63, 276.2, 90.95, 303.68, 90.95, 310.31, 104.21, 298.94, 105.16, 287.1, 116.52, 288.99, 118.42, 262.94, 139.26, 237.84, 138.79, 253.47, 126.0, 265.78, 126.0, 275.73, 130.73, 281.89, 127.42, 294.2, 142.58, 301.78, 148.73, 297.52, 144.94, 282.36, 152.05, 270.05, 154.89, 259.15, 149.21, 248.73, 154.89, 213.2, 155.84, 182.89, 177.15, 171.52, 203.21, 165.36, 231.63, 169.63, 225.94, 160.15]], "area": 6732.246849999996, "iscrowd": 0, "image_id": 314725, "bbox": [90.95, 158.26, 196.1, 152.05], "category_id": 24, "id": 1412089, "split": "val", "sentences": [{"tokens": ["the", "zebra", "on", "the", "left", "in", "the", "right", "hand", "picture"], "raw": "the zebra on the left in the right hand picture", "sent_id": 240, "sent": "the zebra on the left in the right hand picture"}], "file_name": "COCO_train2014_000000314725_1412089.jpg", "ann_id": 1412089, "sent_ids": [240], "ref_id": 5107}, {"segmentation": [[257.02, 146.13, 257.75, 122.98, 204.93, 112.85, 191.9, 117.91, 162.24, 120.08, 151.38, 128.77, 146.32, 117.91, 149.21, 128.04, 130.4, 134.55, 120.27, 151.2, 107.24, 166.39, 99.28, 183.76, 86.26, 213.42, 100.73, 225.0, 106.52, 235.85, 123.16, 227.89, 112.31, 207.63, 152.83, 159.16, 209.27, 134.55, 259.19, 147.58]], "area": 5696.58455, "iscrowd": 0, "image_id": 29962, "bbox": [86.26, 112.85, 172.93, 123.0], "category_id": 28, "id": 2191591, "split": "val", "sentences": [{"tokens": ["a", "black", "umbrella", ",", "being", "held", "by", "a", "person", "in", "jeans"], "raw": "a black umbrella, being held by a person in jeans.", "sent_id": 251, "sent": "a black umbrella , being held by a person in jeans"}], "file_name": "COCO_train2014_000000029962_2191591.jpg", "ann_id": 2191591, "sent_ids": [251], "ref_id": 5112}, {"segmentation": [[206.78, 364.01, 228.89, 378.46, 243.34, 397.17, 256.09, 419.27, 259.49, 432.87, 265.44, 456.68, 265.44, 473.68, 265.44, 491.53, 257.79, 561.0, 257.79, 582.25, 258.64, 595.01, 261.19, 622.05, 256.09, 634.8, 246.74, 637.35, 240.79, 606.75, 239.94, 640.0, 228.04, 633.95, 216.13, 582.94, 211.03, 576.14, 216.13, 635.65, 206.78, 628.85, 196.58, 571.89, 192.33, 559.14, 196.58, 539.59, 197.43, 536.19, 184.68, 519.19, 183.83, 528.54, 188.08, 634.8, 179.58, 628.85, 158.33, 497.93, 150.67, 459.68, 143.87, 435.87, 141.32, 419.72, 145.57, 400.17, 152.37, 378.07, 156.63, 362.76, 146.42, 323.66, 137.07, 233.55, 131.97, 222.49, 99.67, 238.65, 80.11, 241.2, 80.11, 225.04, 82.66, 215.69, 94.57, 208.04, 107.32, 199.54, 113.27, 196.14, 111.57, 183.39, 120.07, 191.04, 119.22, 179.14, 120.07, 170.64, 128.57, 172.34, 122.62, 179.99, 130.27, 180.84, 131.12, 173.19, 143.87, 194.44, 147.27, 205.49, 153.22, 225.89, 155.77, 250.55, 171.93, 301.56, 189.78, 331.31]], "area": 30882.744900000005, "iscrowd": 0, "image_id": 96586, "bbox": [80.11, 170.64, 185.33, 469.36], "category_id": 25, "id": 1823370, "split": "val", "sentences": [{"tokens": ["giraffe", "in", "the", "middle", "which", "is", "not", "eating", "leaves"], "raw": "giraffe in the middle which is not eating leaves", "sent_id": 270, "sent": "giraffe in the middle which is not eating leaves"}, {"tokens": ["the", "giraffe", "in", "the", "middle"], "raw": "the giraffe in the middle", "sent_id": 271, "sent": "the giraffe in the middle"}], "file_name": "COCO_train2014_000000096586_1823370.jpg", "ann_id": 1823370, "sent_ids": [270, 271], "ref_id": 5122}, {"segmentation": [[142.08, 186.24, 162.24, 149.76, 162.24, 117.12, 206.4, 85.44, 240.96, 104.64, 280.32, 97.92, 310.08, 111.36, 324.48, 171.84, 287.04, 209.28, 240.96, 232.32, 201.6, 221.76, 147.84, 188.16]], "area": 18058.752, "iscrowd": 0, "image_id": 158686, "bbox": [142.08, 85.44, 182.4, 146.88], "category_id": 56, "id": 1055626, "split": "val", "sentences": [{"tokens": ["green", "color", "vegetable", "in", "between", "potato", "and", "carrot"], "raw": "green color vegetable in between potato and carrot", "sent_id": 370, "sent": "green color vegetable in between potato and carrot"}, {"tokens": ["bundle", "of", "broccoli"], "raw": "Bundle of broccoli.", "sent_id": 371, "sent": "bundle of broccoli"}], "file_name": "COCO_train2014_000000158686_1055626.jpg", "ann_id": 1055626, "sent_ids": [370, 371], "ref_id": 5159}, {"segmentation": [[402.81, 167.7, 362.36, 168.54, 304.21, 166.01, 281.46, 167.7, 271.35, 91.85, 270.51, 37.92, 287.36, 21.07, 381.74, 19.38, 401.97, 34.55, 410.39, 147.47, 402.81, 160.96]], "area": 19141.29245, "iscrowd": 0, "image_id": 174892, "bbox": [270.51, 19.38, 139.88, 149.16], "category_id": 51, "id": 1533550, "split": "val", "sentences": [{"tokens": ["red", "fruit", "pur", "\u00e9", "e", "in", "a", "pink", "container"], "raw": "Red fruit pur\u00e9e in a pink container.", "sent_id": 400, "sent": "red fruit pur \u00e9 e in a pink container"}, {"tokens": ["apple", "sauce"], "raw": "Apple sauce.", "sent_id": 401, "sent": "apple sauce"}], "file_name": "COCO_train2014_000000174892_1533550.jpg", "ann_id": 1533550, "sent_ids": [400, 401], "ref_id": 5172}, {"segmentation": [[351.84, 110.39, 364.53, 117.14, 368.03, 109.04, 373.16, 90.96, 380.72, 92.85, 387.47, 95.55, 388.01, 97.44, 388.28, 113.63, 385.58, 133.34, 386.12, 137.39, 394.22, 141.97, 399.62, 146.02, 405.01, 147.37, 405.55, 142.78, 404.48, 136.04, 401.78, 127.4, 403.67, 117.95, 405.55, 104.45, 409.06, 92.31, 406.36, 84.21, 399.62, 77.46, 383.42, 69.9, 378.02, 66.66, 378.56, 58.57, 383.96, 55.06, 390.71, 55.06, 405.55, 58.3, 417.7, 59.11, 425.8, 59.11, 432.01, 55.87, 440.11, 52.36, 440.11, 52.36, 437.41, 45.07, 429.31, 44.26, 420.67, 50.2, 400.43, 47.77, 395.03, 42.91, 401.51, 39.67, 408.25, 33.46, 411.76, 25.9, 419.05, 27.25, 425.26, 28.6, 426.61, 29.95, 425.26, 21.31, 415.27, 21.31, 411.76, 21.31, 405.01, 10.52, 391.52, 13.22, 384.77, 19.43, 378.02, 16.73, 365.87, 21.85, 355.08, 32.65, 338.07, 48.31, 334.29, 59.11, 334.83, 69.9, 334.02, 77.19, 341.58, 84.75, 348.33, 87.99, 354.27, 86.91, 355.08, 94.74, 352.38, 109.58]], "area": 5831.499599999998, "iscrowd": 0, "image_id": 92760, "bbox": [334.02, 10.52, 106.09, 136.85], "category_id": 1, "id": 2164769, "split": "val", "sentences": [{"tokens": ["a", "man", "skateboarding", "with", "grey", "pants", "and", "dark", "grey", "t", "-", "shirt", "on"], "raw": "A man skateboarding with grey pants and dark grey t-shirt on.", "sent_id": 482, "sent": "a man skateboarding with grey pants and dark grey t - shirt on"}, {"tokens": ["a", "skateboarder"], "raw": "A skateboarder.", "sent_id": 483, "sent": "a skateboarder"}], "file_name": "COCO_train2014_000000092760_2164769.jpg", "ann_id": 2164769, "sent_ids": [482, 483], "ref_id": 5199}, {"segmentation": [[5.97, 80.98, 17.39, 87.4, 14.53, 98.81, 12.39, 111.65, 10.25, 125.21, 3.12, 139.48, 5.26, 166.59, 6.69, 177.29, 21.67, 178.71, 18.81, 189.41, 12.39, 202.26, 13.82, 204.4, 27.37, 203.68, 41.64, 199.4, 60.19, 200.12, 74.46, 200.12, 77.31, 185.13, 78.02, 168.73, 83.02, 179.43, 95.86, 186.56, 104.42, 179.43, 102.28, 173.01, 93.72, 155.88, 91.58, 148.75, 90.15, 135.2, 88.73, 118.79, 82.31, 105.95, 72.32, 97.39, 73.74, 77.41, 75.88, 66.0, 78.02, 55.3, 79.45, 41.74, 74.46, 33.18, 66.61, 25.33, 56.62, 19.63, 40.93, 20.34, 26.66, 25.33, 18.81, 31.75, 14.53, 38.18, 0.98, 46.02, 1.69, 83.12]], "area": 13100.7521, "iscrowd": 0, "image_id": 283624, "bbox": [0.98, 19.63, 103.44, 184.77], "category_id": 18, "id": 17054, "split": "val", "sentences": [{"tokens": ["the", "black", "dog", "with", "the", "blue", "collar", ".", "on", "the", "left"], "raw": "The black dog with the blue collar.  On the left.", "sent_id": 554, "sent": "the black dog with the blue collar . on the left"}, {"tokens": ["the", "black", "dog", "with", "the", "green", "collar"], "raw": "the black dog with the green collar", "sent_id": 555, "sent": "the black dog with the green collar"}], "file_name": "COCO_train2014_000000283624_17054.jpg", "ann_id": 17054, "sent_ids": [554, 555], "ref_id": 5226}, {"segmentation": [[278.29, 230.5, 292.31, 176.57, 319.28, 138.82, 373.21, 109.69, 427.15, 103.22, 464.9, 99.99, 511.28, 110.77, 544.72, 119.4, 590.02, 156.07, 622.38, 181.96, 640.0, 207.85, 640.0, 364.25, 605.12, 404.16, 494.02, 434.37, 392.63, 408.48, 321.44, 350.23, 291.24, 303.85]], "area": 95788.1471, "iscrowd": 0, "image_id": 1261, "bbox": [278.29, 99.99, 361.71, 334.38], "category_id": 51, "id": 713551, "split": "val", "sentences": [{"tokens": ["a", "glass", "bowl", "of", "food", "that", "is", "sitting", "on", "a", "whicker", "circle", "holder"], "raw": "A glass bowl of food that is sitting on a whicker circle holder", "sent_id": 591, "sent": "a glass bowl of food that is sitting on a whicker circle holder"}, {"tokens": ["bowl", "on", "right"], "raw": "bowl on right", "sent_id": 592, "sent": "bowl on right"}], "file_name": "COCO_train2014_000000001261_713551.jpg", "ann_id": 713551, "sent_ids": [591, 592], "ref_id": 5239}, {"segmentation": [[204.11, 236.1, 187.3, 227.92, 167.31, 187.03, 175.94, 183.4, 186.39, 184.31, 195.93, 164.77, 202.74, 149.78, 210.47, 146.6, 200.93, 139.33, 200.02, 113.89, 202.74, 106.62, 221.37, 100.26, 239.54, 101.17, 249.08, 115.71, 254.08, 134.34, 254.53, 151.14, 259.08, 170.23, 249.54, 189.31, 246.36, 187.03, 234.09, 188.85]], "area": 6602.707299999999, "iscrowd": 0, "image_id": 372198, "bbox": [167.31, 100.26, 91.77, 135.84], "category_id": 1, "id": 1720854, "split": "val", "sentences": [{"tokens": ["a", "small", "girl", "starring", "at", "something", ",", "along", "with", "her", "elder", "sister"], "raw": "A small girl starring at something, along with her elder sister", "sent_id": 680, "sent": "a small girl starring at something , along with her elder sister"}, {"tokens": ["little", "girl", "sitting", "with", "toy", "in", "her", "hand"], "raw": "Little girl sitting with toy in her hand", "sent_id": 681, "sent": "little girl sitting with toy in her hand"}], "file_name": "COCO_train2014_000000372198_1720854.jpg", "ann_id": 1720854, "sent_ids": [680, 681], "ref_id": 5278}, {"segmentation": [[0.0, 2.88, 73.35, 0.0, 58.97, 12.94, 71.91, 33.08, 96.36, 70.47, 128.0, 73.35, 117.93, 132.31, 106.43, 133.75, 96.36, 130.88, 61.84, 71.91, 58.97, 152.45, 47.46, 152.45, 33.08, 64.72, 2.88, 61.84]], "area": 9188.805800000002, "iscrowd": 0, "image_id": 404905, "bbox": [0.0, 0.0, 128.0, 152.45], "category_id": 62, "id": 1581952, "split": "val", "sentences": [{"tokens": ["a", "dark", "table", "in", "the", "far", "left", "hand", "background"], "raw": "A dark table in the far left hand background.", "sent_id": 689, "sent": "a dark table in the far left hand background"}], "file_name": "COCO_train2014_000000404905_1581952.jpg", "ann_id": 1581952, "sent_ids": [689], "ref_id": 5281}, {"segmentation": [[314.97, 375.37, 299.87, 320.36, 476.76, 345.17, 483.24, 398.02, 506.97, 402.34, 485.39, 426.07, 366.74, 407.73, 372.13, 374.29, 363.51, 361.35, 352.72, 358.11, 338.7, 358.11, 332.22, 358.11, 325.75, 358.11, 321.44, 358.11, 318.2, 358.11, 313.89, 361.35]], "area": 11348.598449999998, "iscrowd": 0, "image_id": 323728, "bbox": [299.87, 320.36, 207.1, 105.71], "category_id": 73, "id": 1627445, "split": "val", "sentences": [{"tokens": ["an", "open", "silver", "laptop", "with", "the", "logo", "of", "a", "bitten", "apple", "which", "a", "woman", "is", "using"], "raw": "An open silver laptop with the logo of a bitten apple which a woman is using.", "sent_id": 745, "sent": "an open silver laptop with the logo of a bitten apple which a woman is using"}], "file_name": "COCO_train2014_000000323728_1627445.jpg", "ann_id": 1627445, "sent_ids": [745], "ref_id": 5301}, {"segmentation": [[279.83, 314.44, 279.09, 291.52, 283.53, 283.39, 279.09, 275.99, 282.05, 235.33, 275.4, 239.03, 260.61, 244.2, 259.13, 239.77, 262.09, 227.2, 273.18, 182.1, 285.75, 168.05, 282.79, 168.05, 276.88, 154.74, 276.88, 144.39, 261.35, 144.39, 261.35, 136.26, 270.96, 130.35, 284.27, 120.0, 301.27, 120.0, 309.41, 124.43, 313.84, 139.96, 316.8, 151.05, 315.32, 157.7, 323.45, 173.23, 332.33, 197.62, 333.06, 230.89, 336.02, 254.55, 331.59, 268.6, 333.06, 280.43, 316.8, 287.08, 309.41, 308.52, 302.75, 323.31, 299.8, 348.45, 287.97, 346.97, 279.09, 361.75, 268.74, 363.23, 268.74, 349.18, 269.48, 335.88, 272.44, 323.31]], "area": 10928.65845, "iscrowd": 0, "image_id": 398083, "bbox": [259.13, 120.0, 76.89, 243.23], "category_id": 1, "id": 1726394, "split": "val", "sentences": [{"tokens": ["a", "boy", "playing", "1st", "base", "in", "a", "black", "uniform"], "raw": "a boy playing 1st base in a black uniform", "sent_id": 785, "sent": "a boy playing 1st base in a black uniform"}, {"tokens": ["the", "boy", "running"], "raw": "the boy running", "sent_id": 786, "sent": "the boy running"}], "file_name": "COCO_train2014_000000398083_1726394.jpg", "ann_id": 1726394, "sent_ids": [785, 786], "ref_id": 5318}, {"segmentation": [[179.06, 279.44, 389.39, 205.02, 453.03, 183.44, 498.34, 143.53, 501.57, 123.04, 154.25, 256.79, 146.7, 261.11, 179.06, 280.52], [213.57, 228.75, 449.8, 110.09, 470.29, 102.54, 492.94, 114.41, 484.31, 127.35]], "area": 16585.283799999997, "iscrowd": 0, "image_id": 276874, "bbox": [146.7, 102.54, 354.87, 177.98], "category_id": 35, "id": 607607, "split": "val", "sentences": [{"tokens": ["the", "rod", "/", "ski", "with", "name", "trak", "nowax"], "raw": "The rod/ski with name trak nowax.", "sent_id": 807, "sent": "the rod / ski with name trak nowax"}, {"tokens": ["the", "red", "blue", "yellow", "and", "green", "ski", "on", "the", "very", "top", "of", "the", "pile"], "raw": "The red blue yellow and green ski on the very top of the pile", "sent_id": 808, "sent": "the red blue yellow and green ski on the very top of the pile"}], "file_name": "COCO_train2014_000000276874_607607.jpg", "ann_id": 607607, "sent_ids": [807, 808], "ref_id": 5327}, {"segmentation": [[419.92, 150.4, 388.62, 161.51, 351.28, 162.52, 275.57, 164.53, 249.32, 165.54, 228.13, 165.54, 199.86, 157.47, 171.6, 150.4, 134.25, 143.34, 85.8, 145.36, 68.64, 150.4, 56.53, 156.46, 41.39, 158.48, 41.39, 142.33, 81.76, 127.19, 147.37, 124.16, 194.82, 128.2, 243.27, 140.31, 302.82, 146.36, 355.31, 146.36, 405.78, 142.33, 422.94, 140.31]], "area": 7659.6254500000005, "iscrowd": 0, "image_id": 497807, "bbox": [41.39, 124.16, 381.55, 41.38], "category_id": 38, "id": 1468176, "split": "val", "sentences": [{"tokens": ["long", "streamer", "on", "kite", "in", "the", "air"], "raw": "long streamer on kite in the air", "sent_id": 877, "sent": "long streamer on kite in the air"}, {"tokens": ["the", "tail", "of", "a", "kite"], "raw": "The tail of a kite.", "sent_id": 878, "sent": "the tail of a kite"}], "file_name": "COCO_train2014_000000497807_1468176.jpg", "ann_id": 1468176, "sent_ids": [877, 878], "ref_id": 5354}, {"segmentation": [[109.95, 141.08, 108.97, 125.51, 107.03, 108.97, 105.08, 85.62, 110.92, 61.3, 119.68, 36.97, 122.59, 26.27, 136.22, 15.57, 140.11, 1.95, 170.27, 3.89, 178.05, 13.62, 184.86, 16.54, 193.62, 28.22, 202.38, 46.7, 210.16, 56.43, 210.16, 66.16, 211.14, 76.86, 212.11, 85.62, 213.08, 93.41, 185.84, 85.62, 175.14, 89.51, 163.46, 104.11, 147.89, 122.59, 138.16, 144.0, 134.27, 155.68, 127.46, 171.24, 124.54, 172.22, 105.08, 153.73, 93.41, 106.05, 92.43, 90.49]], "area": 10377.626349999997, "iscrowd": 0, "image_id": 488073, "bbox": [92.43, 1.95, 120.65, 170.27], "category_id": 1, "id": 518630, "split": "val", "sentences": [{"tokens": ["the", "man", "sitting", "in", "the", "bleachers", "center"], "raw": "The man sitting in the bleachers center.", "sent_id": 985, "sent": "the man sitting in the bleachers center"}, {"tokens": ["a", "base", "ball", "bat"], "raw": "a base ball bat", "sent_id": 986, "sent": "a base ball bat"}], "file_name": "COCO_train2014_000000488073_518630.jpg", "ann_id": 518630, "sent_ids": [985, 986], "ref_id": 5397}, {"segmentation": [[275.52, 296.56, 276.95, 252.08, 270.05, 197.3, 270.72, 162.2, 276.95, 121.49, 284.13, 82.75, 288.43, 75.58, 291.3, 85.62, 320.0, 94.23, 363.05, 94.23, 386.01, 91.36, 390.31, 77.01, 401.79, 87.06, 393.18, 105.71, 387.44, 161.67, 374.53, 256.38, 365.92, 305.17, 360.18, 328.13, 316.43, 332.16, 279.05, 318.75, 272.82, 311.58, 276.95, 295.13]], "area": 25051.067699999996, "iscrowd": 0, "image_id": 551244, "bbox": [270.05, 75.58, 131.74, 256.58], "category_id": 47, "id": 671704, "split": "val", "sentences": [{"tokens": ["a", "glass", "with", "napkins", "and", "utensils", "inside", "of", "it", "sitting", "near", "a", "pizza"], "raw": "A glass with napkins and utensils inside of it sitting near a pizza.", "sent_id": 1019, "sent": "a glass with napkins and utensils inside of it sitting near a pizza"}, {"tokens": ["a", "glass", "of", "flatware", "sits", "next", "to", "a", "fresh", "pizza"], "raw": "A glass of flatware sits next to a fresh pizza.", "sent_id": 1020, "sent": "a glass of flatware sits next to a fresh pizza"}], "file_name": "COCO_train2014_000000551244_671704.jpg", "ann_id": 671704, "sent_ids": [1019, 1020], "ref_id": 5412}, {"segmentation": [[640.0, 384.0, 542.56, 457.35, 496.18, 446.56, 456.27, 419.6, 416.36, 340.85, 407.73, 303.1, 388.31, 262.11, 400.18, 217.89, 468.13, 198.47, 560.9, 229.75, 580.31, 264.27, 640.0, 375.37]], "area": 41935.945199999995, "iscrowd": 0, "image_id": 550308, "bbox": [388.31, 198.47, 251.69, 258.88], "category_id": 54, "id": 1555244, "split": "val", "sentences": [{"tokens": ["the", "sausage", "on", "a", "roll", "on", "the", "far", "right", "of", "the", "plate"], "raw": "The sausage on a roll on the far right of the plate", "sent_id": 1036, "sent": "the sausage on a roll on the far right of the plate"}, {"tokens": ["hot", "dog", "in", "burger"], "raw": "hot dog in burger", "sent_id": 1037, "sent": "hot dog in burger"}], "file_name": "COCO_train2014_000000550308_1555244.jpg", "ann_id": 1555244, "sent_ids": [1036, 1037], "ref_id": 5419}, {"segmentation": [[408.19, 57.03, 393.7, 60.85, 380.73, 53.98, 363.18, 51.69, 347.16, 49.4, 332.66, 62.37, 317.4, 78.4, 309.77, 88.31, 305.95, 102.81, 313.58, 111.97, 326.56, 130.28, 336.47, 139.43, 338.0, 146.3, 331.13, 156.98, 328.08, 173.01, 323.5, 179.87, 327.32, 189.03, 331.13, 192.08, 346.39, 194.37, 354.79, 195.9, 347.92, 185.21, 354.79, 180.64, 354.02, 172.24, 357.07, 168.43, 359.36, 160.03, 363.18, 153.93, 372.33, 146.3, 384.54, 166.14, 388.36, 169.19, 387.59, 185.21, 396.75, 195.9, 406.67, 203.52, 415.82, 202.0, 434.9, 198.95, 435.66, 191.32, 424.22, 183.69, 416.59, 175.29, 416.59, 148.59, 410.48, 134.86, 403.62, 127.23, 401.33, 115.02, 406.67, 89.08, 418.88, 73.82, 420.4, 65.43, 418.11, 54.74, 412.01, 54.74]], "area": 11441.403300000005, "iscrowd": 0, "image_id": 384037, "bbox": [305.95, 49.4, 129.71, 154.12], "category_id": 1, "id": 442885, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "green", "jacket", "snowboarding"], "raw": "A man in a green jacket snowboarding.", "sent_id": 1065, "sent": "a man in a green jacket snowboarding"}, {"tokens": ["guy", "in", "checkered", "pants", "snowboarding"], "raw": "Guy in checkered pants snowboarding", "sent_id": 1066, "sent": "guy in checkered pants snowboarding"}], "file_name": "COCO_train2014_000000384037_442885.jpg", "ann_id": 442885, "sent_ids": [1065, 1066], "ref_id": 5431}, {"segmentation": [[76.84, 175.2, 216.76, 108.49, 288.66, 180.06, 149.32, 275.33]], "area": 17833.903599999998, "iscrowd": 0, "image_id": 227891, "bbox": [76.84, 108.49, 211.82, 166.84], "category_id": 76, "id": 1114932, "split": "val", "sentences": [{"tokens": ["the", "laptop", "on", "the", "left"], "raw": "the laptop on the left", "sent_id": 1074, "sent": "the laptop on the left"}, {"tokens": ["the", "gray", "keyboard", "with", "the", "touch", "pad"], "raw": "the gray keyboard with the touch pad", "sent_id": 1075, "sent": "the gray keyboard with the touch pad"}], "file_name": "COCO_train2014_000000227891_1114932.jpg", "ann_id": 1114932, "sent_ids": [1074, 1075], "ref_id": 5434}, {"segmentation": [[357.03, 107.06, 456.27, 112.45, 519.91, 162.07, 531.78, 197.66, 549.03, 194.43, 549.03, 191.19, 554.43, 206.29, 554.43, 213.84, 580.31, 224.63, 544.72, 258.07, 522.07, 276.4, 503.73, 280.72, 483.24, 297.98, 409.89, 294.74, 354.88, 280.72, 328.99, 274.25, 331.15, 248.36, 328.99, 210.61, 322.52, 200.9, 332.22, 149.12, 358.11, 109.21]], "area": 34876.737499999996, "iscrowd": 0, "image_id": 69047, "bbox": [322.52, 107.06, 257.79, 190.92], "category_id": 54, "id": 309493, "split": "val", "sentences": [{"tokens": ["the", "right", "half", "of", "a", "long", "sandwich", "with", "banana", "peppers", "and", "green", "spices", "on", "the", "side"], "raw": "The right half of a long sandwich with banana peppers and green spices on the side.", "sent_id": 1088, "sent": "the right half of a long sandwich with banana peppers and green spices on the side"}], "file_name": "COCO_train2014_000000069047_309493.jpg", "ann_id": 309493, "sent_ids": [1088], "ref_id": 5439}, {"segmentation": [[69.21, 216.95, 46.77, 165.65, 81.24, 153.62, 173.43, 130.37, 168.62, 95.9, 171.82, 20.55, 168.62, 0.0, 25.93, 0.0, 31.54, 14.94, 40.35, 30.17, 46.77, 39.79, 82.04, 26.96, 98.07, 34.98, 114.91, 44.6, 116.51, 54.22, 94.87, 53.42, 79.64, 59.03, 74.02, 79.07, 0.0, 117.55, 1.88, 182.48, 21.92, 227.7, 67.61, 218.88]], "area": 22054.396100000005, "iscrowd": 0, "image_id": 209603, "bbox": [0.0, 0.0, 173.43, 227.7], "category_id": 1, "id": 184819, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "white", "shirt", "and", "blue", "jeans", "sits", "at", "a", "table", "with", "bad", "posture"], "raw": "A woman in a white shirt and blue jeans sits at a table with bad posture.", "sent_id": 1129, "sent": "a woman in a white shirt and blue jeans sits at a table with bad posture"}, {"tokens": ["a", "man", "sits", "with", "a", "napkin", "in", "his", "lap"], "raw": "A man sits with a napkin in his lap.", "sent_id": 1130, "sent": "a man sits with a napkin in his lap"}], "file_name": "COCO_train2014_000000209603_184819.jpg", "ann_id": 184819, "sent_ids": [1129, 1130], "ref_id": 5457}, {"segmentation": [[470.05, 181.55, 420.31, 217.62, 402.9, 244.97, 391.71, 256.17, 383.01, 231.3, 378.03, 197.72, 379.27, 170.36, 405.39, 161.66, 417.82, 146.74, 426.53, 131.81, 452.64, 123.11, 481.24, 121.87, 475.03, 181.55], [551.92, 74.15, 573.1, 52.38, 546.63, 40.62, 513.1, 31.21, 495.45, 30.62, 485.45, 35.91, 468.39, 37.09, 464.87, 32.38, 477.22, 26.5, 458.98, 31.21, 454.28, 38.85, 451.34, 37.09, 461.92, 25.32, 481.34, 18.85, 528.39, 21.21, 565.45, 22.97, 591.33, 19.44, 611.92, 13.56, 635.45, 4.74, 640.0, 7.09, 638.98, 72.97, 556.04, 73.56]], "area": 13195.963750000003, "iscrowd": 0, "image_id": 329502, "bbox": [378.03, 4.74, 261.97, 251.43], "category_id": 1, "id": 2156455, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "on", "a", "chair"], "raw": "a man sitting on a chair", "sent_id": 1269, "sent": "a man sitting on a chair"}, {"tokens": ["man", "sitting", "on", "the", "brown", "color", "couch"], "raw": "man sitting on the brown color couch", "sent_id": 1270, "sent": "man sitting on the brown color couch"}], "file_name": "COCO_train2014_000000329502_2156455.jpg", "ann_id": 2156455, "sent_ids": [1269, 1270], "ref_id": 5513}, {"segmentation": [[217.38, 112.15, 206.97, 137.43, 212.92, 155.27, 192.1, 162.71, 163.1, 176.09, 152.69, 198.4, 138.56, 229.62, 129.64, 256.39, 119.23, 279.44, 122.21, 301.0, 137.82, 321.82, 166.07, 333.72, 177.97, 346.36, 179.46, 388.92, 188.38, 435.14, 191.35, 452.35, 186.89, 461.28, 187.64, 480.0, 231.51, 480.0, 220.35, 458.3, 235.22, 450.87, 246.38, 443.43, 230.76, 373.54, 236.71, 340.82, 241.17, 345.29, 248.61, 331.16, 256.79, 332.65, 267.19, 333.39, 273.14, 367.59, 275.37, 400.31, 276.86, 411.46, 273.14, 424.1, 273.14, 432.28, 270.91, 442.69, 285.04, 445.66, 296.94, 447.15, 308.83, 452.35, 331.14, 459.05, 348.24, 454.59, 351.96, 447.89, 340.8, 433.77, 328.16, 431.54, 311.06, 415.18, 325.19, 413.69, 331.14, 408.49, 317.76, 312.57, 324.45, 301.42, 339.32, 308.11, 353.45, 308.85, 357.91, 296.21, 360.88, 283.57, 369.06, 276.14, 369.06, 269.44, 364.6, 263.5, 341.55, 271.56, 321.47, 274.53, 285.04, 261.15, 283.55, 242.56, 283.55, 226.95, 282.07, 204.64, 275.37, 186.05, 267.94, 177.13, 280.58, 153.28, 276.12, 145.84, 273.14, 127.25, 268.68, 113.12, 256.79, 103.46, 248.61, 102.72, 232.25, 104.2]], "area": 45850.9611, "iscrowd": 0, "image_id": 439325, "bbox": [119.23, 102.72, 249.83, 377.28], "category_id": 1, "id": 209161, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "glasses", "in", "a", "white", "shirt", "and", "black", "pants", "sitting", "on", "a", "wooden", "bench", "reading", "some", "papers"], "raw": "A man with glasses in a white shirt and black pants sitting on a wooden bench reading some papers.", "sent_id": 1622, "sent": "a man with glasses in a white shirt and black pants sitting on a wooden bench reading some papers"}, {"tokens": ["a", "man", "was", "sitting", "on", "atable"], "raw": "a man was sitting on atable", "sent_id": 1623, "sent": "a man was sitting on atable"}], "file_name": "COCO_train2014_000000439325_209161.jpg", "ann_id": 209161, "sent_ids": [1622, 1623], "ref_id": 5642}, {"segmentation": [[257.16, 445.5, 366.95, 452.72, 381.4, 600.08, 264.38, 594.3, 235.49, 588.52]], "area": 18851.135099999992, "iscrowd": 0, "image_id": 538196, "bbox": [235.49, 445.5, 145.91, 154.58], "category_id": 72, "id": 32814, "split": "val", "sentences": [{"tokens": ["a", "tv", "underneath", "the", "clocl"], "raw": "a tv underneath the clocl", "sent_id": 1644, "sent": "a tv underneath the clocl"}, {"tokens": ["a", "tv"], "raw": "a tv", "sent_id": 1645, "sent": "a tv"}], "file_name": "COCO_train2014_000000538196_32814.jpg", "ann_id": 32814, "sent_ids": [1644, 1645], "ref_id": 5649}, {"segmentation": [[41.39, 310.81, 18.58, 331.93, 18.58, 343.75, 32.09, 343.75, 59.97, 322.64, 60.81, 310.81, 41.39, 310.81], [244.09, 304.9, 225.51, 298.99, 231.42, 337.84, 244.93, 354.73, 255.07, 350.51, 248.31, 302.36, 233.11, 298.14]], "area": 1898.9688999999998, "iscrowd": 0, "image_id": 99451, "bbox": [18.58, 298.14, 236.49, 56.59], "category_id": 75, "id": 1110763, "split": "val", "sentences": [{"tokens": ["wii", "remotes", "are", "sitting", "on", "the", "laps", "of", "two", "children"], "raw": "Wii remotes are sitting on the laps of two children.", "sent_id": 1703, "sent": "wii remotes are sitting on the laps of two children"}], "file_name": "COCO_train2014_000000099451_1110763.jpg", "ann_id": 1110763, "sent_ids": [1703], "ref_id": 5669}, {"segmentation": [[134.65, 616.73, 134.65, 593.45, 174.55, 472.1, 201.14, 395.64, 201.14, 334.13, 192.83, 267.64, 186.18, 249.35, 204.47, 164.57, 199.48, 101.4, 192.83, 84.78, 181.19, 78.13, 176.21, 96.42, 182.86, 129.66, 176.21, 161.25, 154.6, 216.1, 142.96, 221.09, 121.35, 197.82, 109.71, 197.82, 89.77, 226.08, 94.75, 256.0, 86.44, 275.95, 84.78, 312.52, 108.05, 335.79, 119.69, 355.74, 94.75, 443.84, 88.1, 470.44, 61.51, 518.65, 53.19, 576.83, 43.22, 598.44, 58.18, 615.06, 63.17, 616.73, 66.49, 613.4, 69.82, 591.79, 103.06, 513.66, 141.3, 445.51, 104.73, 565.19, 104.73, 601.77, 123.01, 623.38, 134.65, 620.05]], "area": 38160.088200000006, "iscrowd": 0, "image_id": 426877, "bbox": [43.22, 78.13, 161.25, 545.25], "category_id": 1, "id": 2153576, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "white", "shirt"], "raw": "The man in the white shirt.", "sent_id": 1706, "sent": "the man in the white shirt"}, {"tokens": ["the", "man", "jumping", "who", "is", "wearing", "a", "white", "shirt", "and", "a", "light", "colored", "shorts"], "raw": "The man jumping who is wearing a white shirt and a light colored shorts.", "sent_id": 1707, "sent": "the man jumping who is wearing a white shirt and a light colored shorts"}], "file_name": "COCO_train2014_000000426877_2153576.jpg", "ann_id": 2153576, "sent_ids": [1706, 1707], "ref_id": 5671}, {"segmentation": [[442.55, 183.44, 440.9, 177.24, 443.38, 168.98, 456.6, 164.44, 465.68, 167.74, 472.7, 177.66, 473.12, 185.09, 471.88, 188.4, 473.12, 192.11, 472.7, 196.24, 470.64, 198.31, 470.64, 201.2, 483.86, 209.46, 497.49, 218.13, 506.16, 247.46, 507.81, 261.91, 504.09, 272.65, 493.77, 282.98, 490.88, 291.65, 494.18, 303.63, 497.07, 313.13, 492.94, 314.78, 496.66, 327.58, 500.38, 349.88, 502.85, 358.97, 510.7, 389.12, 511.11, 399.45, 481.38, 401.51, 449.58, 328.82, 433.88, 394.08, 429.75, 404.82, 422.32, 402.75, 411.99, 371.36, 420.66, 338.32, 418.6, 313.54, 423.97, 278.02, 424.79, 272.24, 422.32, 268.52, 414.88, 248.28, 420.25, 221.02, 424.79, 214.0, 440.9, 207.39, 445.03, 202.85, 439.66, 195.83]], "area": 15217.077900000002, "iscrowd": 0, "image_id": 529624, "bbox": [411.99, 164.44, 99.12, 240.38], "category_id": 1, "id": 568539, "split": "val", "sentences": [{"tokens": ["a", "blurry", "male", "official", "wearing", "white", "pants", "with", "arms", "behind", "his", "back"], "raw": "A blurry male official wearing white pants with arms behind his back", "sent_id": 1814, "sent": "a blurry male official wearing white pants with arms behind his back"}, {"tokens": ["a", "man", "in", "the", "bakground", "in", "a", "dress", "coat"], "raw": "A man in the bakground in a dress coat.", "sent_id": 1815, "sent": "a man in the bakground in a dress coat"}], "file_name": "COCO_train2014_000000529624_568539.jpg", "ann_id": 568539, "sent_ids": [1814, 1815], "ref_id": 5709}, {"segmentation": [[6.72, 278.27, 73.89, 218.78, 82.52, 220.7, 91.16, 193.83, 128.58, 201.51, 131.46, 225.49, 121.86, 245.64, 102.67, 238.93, 102.67, 243.73, 109.39, 261.96, 85.4, 279.23, 116.11, 284.99, 114.19, 294.58, 72.93, 294.58, 63.33, 302.26, 87.32, 328.17, 105.55, 420.28, 49.9, 418.36, 66.21, 348.32, 52.78, 350.24, 37.42, 411.65, 6.72, 408.77, 5.76, 379.02, 28.79, 331.04, 0.96, 307.06, 12.47, 276.35]], "area": 15375.392600000001, "iscrowd": 0, "image_id": 572998, "bbox": [0.96, 193.83, 130.5, 226.45], "category_id": 1, "id": 514933, "split": "val", "sentences": [{"tokens": ["referee", "dressed", "in", "a", "black", "shirt"], "raw": "referee dressed in a black shirt", "sent_id": 1885, "sent": "referee dressed in a black shirt"}, {"tokens": ["an", "umpire"], "raw": "An umpire.", "sent_id": 1886, "sent": "an umpire"}], "file_name": "COCO_train2014_000000572998_514933.jpg", "ann_id": 514933, "sent_ids": [1885, 1886], "ref_id": 5735}, {"segmentation": [[15.54, 269.13, 83.26, 227.45, 91.07, 211.82, 144.04, 186.65, 221.32, 171.01, 297.72, 134.55, 367.17, 72.04, 357.62, 56.41, 382.81, 44.26, 417.53, 55.54, 456.6, 59.01, 481.78, 69.43, 478.31, 85.93, 472.23, 88.53, 444.44, 102.43, 379.33, 133.68, 307.27, 213.56, 189.19, 282.15, 179.64, 311.67, 95.42, 353.34, 56.35, 401.96, 56.35, 425.0, 0.0, 425.0, 0.0, 279.54]], "area": 50205.91504999999, "iscrowd": 0, "image_id": 298956, "bbox": [0.0, 44.26, 481.78, 380.74], "category_id": 25, "id": 598440, "split": "val", "sentences": [{"tokens": ["the", "taller", "giraffe"], "raw": "The taller giraffe.", "sent_id": 1927, "sent": "the taller giraffe"}, {"tokens": ["a", "tall", "giraffe", "eating", "out", "of", "a", "metal", "basket"], "raw": "a tall giraffe eating out of a metal basket.", "sent_id": 1928, "sent": "a tall giraffe eating out of a metal basket"}], "file_name": "COCO_train2014_000000298956_598440.jpg", "ann_id": 598440, "sent_ids": [1927, 1928], "ref_id": 5752}, {"segmentation": [[151.62, 361.96, 167.39, 339.17, 205.96, 39.44, 201.57, 37.69, 190.18, 34.18, 177.03, 28.92, 146.36, 24.54, 114.81, 27.17, 94.65, 32.43, 91.15, 34.18, 83.26, 35.93, 80.63, 41.19, 77.12, 43.82, 73.62, 57.84, 37.69, 198.94, 35.93, 218.22, 28.04, 276.94, 27.17, 322.52, 38.56, 340.04, 56.09, 354.07, 71.87, 356.7, 89.39, 358.45, 103.42, 357.57, 123.57, 362.83, 141.98, 368.97]], "area": 45854.187, "iscrowd": 0, "image_id": 510976, "bbox": [27.17, 24.54, 178.79, 344.43], "category_id": 77, "id": 328341, "split": "val", "sentences": [{"tokens": ["the", "mobile", "phone", "with", "a", "number", "2125", "towards", "the", "top", "right", "side"], "raw": "The mobile phone with a number 2125 towards the top right side.", "sent_id": 1966, "sent": "the mobile phone with a number 2125 towards the top right side"}, {"tokens": ["a", "gray", ",", "feature", "style", "cell", "phone", "with", "a", "blue", "screen", "lit", "up", "next", "to", "a", "slider", "style", "cell", "phone"], "raw": "A gray, feature style cell phone with a blue screen lit up next to a slider style cell phone.", "sent_id": 1967, "sent": "a gray , feature style cell phone with a blue screen lit up next to a slider style cell phone"}], "file_name": "COCO_train2014_000000510976_328341.jpg", "ann_id": 328341, "sent_ids": [1966, 1967], "ref_id": 5768}, {"segmentation": [[380.52, 222.09, 386.74, 60.44, 410.36, 40.54, 534.72, 49.24, 555.85, 77.84, 554.61, 238.26, 537.2, 259.4, 415.34, 259.4, 390.47, 248.21, 381.76, 240.75]], "area": 35870.74555, "iscrowd": 0, "image_id": 510027, "bbox": [380.52, 40.54, 175.33, 218.86], "category_id": 51, "id": 2108780, "split": "val", "sentences": [{"tokens": ["a", "sweet", "foo", "in", "an", "orange", "bowl"], "raw": "a sweet foo in an orange bowl.", "sent_id": 1975, "sent": "a sweet foo in an orange bowl"}, {"tokens": ["the", "snack", "in", "the", "orange", "container"], "raw": "The snack in the orange container.", "sent_id": 1976, "sent": "the snack in the orange container"}], "file_name": "COCO_train2014_000000510027_2108780.jpg", "ann_id": 2108780, "sent_ids": [1975, 1976], "ref_id": 5771}, {"segmentation": [[185.2, 341.13, 199.14, 383.95, 193.17, 384.94, 181.22, 347.1, 177.24, 347.1, 180.22, 383.95, 167.28, 382.95, 173.25, 360.05, 168.27, 348.1, 142.39, 341.13, 126.45, 351.09, 121.48, 379.96, 105.55, 379.96, 96.58, 342.13, 109.53, 335.16, 145.37, 284.37, 172.26, 272.43, 191.18, 264.46, 247.93, 277.4, 264.86, 276.41, 263.86, 293.34, 233.0, 302.3, 220.05, 331.17, 214.08, 338.14]], "area": 9226.37105, "iscrowd": 0, "image_id": 425398, "bbox": [96.58, 264.46, 168.28, 120.48], "category_id": 20, "id": 63746, "split": "val", "sentences": [{"tokens": ["the", "larger", "of", "two", "sheep"], "raw": "The larger of two sheep.", "sent_id": 2004, "sent": "the larger of two sheep"}, {"tokens": ["a", "sheep", "grazing", "with", "a", "bunch", "of", "fur", "on", "its", "back"], "raw": "A sheep grazing with a bunch of fur on its back.", "sent_id": 2005, "sent": "a sheep grazing with a bunch of fur on its back"}], "file_name": "COCO_train2014_000000425398_63746.jpg", "ann_id": 63746, "sent_ids": [2004, 2005], "ref_id": 5784}, {"segmentation": [[399.46, 395.52, 408.27, 372.19, 413.46, 362.34, 420.19, 358.2, 424.86, 358.2, 434.19, 352.49, 439.38, 359.23, 451.82, 363.9, 465.3, 363.38, 477.74, 358.72, 487.59, 351.98, 504.18, 347.31, 521.8, 337.98, 535.28, 333.31, 553.42, 336.42, 561.2, 344.2, 568.46, 356.12, 569.5, 373.23, 571.57, 379.97, 580.38, 391.38, 588.68, 403.82, 584.53, 429.74, 587.12, 435.44, 577.79, 434.92, 576.75, 429.74, 570.01, 417.81, 563.79, 412.63, 559.65, 410.56, 553.42, 416.78, 552.39, 412.11, 553.94, 399.15, 551.35, 389.82, 537.87, 391.89, 535.8, 395.0, 535.28, 404.34, 540.98, 419.89, 537.87, 440.62, 530.1, 440.11, 524.91, 428.7, 521.8, 416.26, 520.25, 402.78, 507.29, 410.04, 500.03, 431.29, 497.44, 433.88, 490.18, 429.74, 477.22, 432.85, 484.48, 418.33, 477.74, 411.59, 471.52, 403.82, 462.19, 400.19, 447.15, 397.6, 440.93, 396.04, 423.82, 401.74, 414.49, 405.37, 407.75, 404.85]], "area": 10406.977750000007, "iscrowd": 0, "image_id": 436797, "bbox": [399.46, 333.31, 189.22, 107.31], "category_id": 20, "id": 1817638, "split": "val", "sentences": [{"tokens": ["a", "baby", "sheep", "walking", "amongst", "the", "grass"], "raw": "A baby sheep walking amongst the grass.", "sent_id": 2083, "sent": "a baby sheep walking amongst the grass"}, {"tokens": ["the", "white", "little", "lamb"], "raw": "The white little lamb.", "sent_id": 2084, "sent": "the white little lamb"}], "file_name": "COCO_train2014_000000436797_1817638.jpg", "ann_id": 1817638, "sent_ids": [2083, 2084], "ref_id": 5817}, {"segmentation": [[344.3, 56.62, 334.58, 61.02, 330.42, 66.57, 329.96, 72.35, 331.58, 79.29, 332.73, 83.23, 321.86, 86.0, 314.23, 95.95, 309.37, 108.91, 307.75, 124.64, 306.36, 131.81, 303.81, 149.39, 305.2, 153.1, 305.9, 163.04, 312.37, 177.85, 319.32, 190.81, 323.25, 201.22, 323.25, 205.85, 319.55, 216.49, 317.0, 224.12, 314.69, 235.23, 316.08, 252.35, 322.09, 253.27, 323.94, 250.27, 328.34, 236.15, 332.73, 220.19, 338.52, 209.32, 339.67, 199.83, 337.13, 191.5, 335.51, 187.11, 335.51, 184.79, 334.35, 179.7, 335.05, 178.78, 344.07, 188.96, 350.78, 198.9, 351.94, 201.91, 352.86, 210.94, 352.86, 222.73, 354.25, 229.21, 356.33, 240.55, 359.34, 253.74, 364.2, 259.29, 371.83, 263.92, 378.31, 260.68, 375.07, 255.59, 368.13, 246.56, 365.59, 240.55, 366.74, 222.5, 366.28, 210.7, 364.89, 198.21, 364.89, 191.04, 359.8, 182.25, 360.5, 179.47, 355.41, 170.45, 346.38, 155.87, 347.31, 153.33, 331.81, 153.79, 321.17, 155.64, 319.55, 152.86, 320.7, 150.78, 321.63, 148.7, 325.33, 149.16, 332.5, 149.39, 339.44, 148.7, 346.85, 145.92, 350.55, 135.51, 354.71, 128.57, 355.18, 135.28, 357.26, 139.91, 356.1, 143.15, 360.27, 149.39, 367.21, 144.3, 368.59, 141.3, 365.59, 137.83, 364.43, 137.59, 365.59, 126.95, 365.82, 109.14, 363.5, 103.12, 360.5, 101.04, 361.42, 92.02, 355.64, 90.4, 357.26, 77.7, 358.18, 69.14, 355.87, 64.05, 346.15, 59.43]], "area": 7427.1709, "iscrowd": 0, "image_id": 163985, "bbox": [303.81, 56.62, 74.5, 207.3], "category_id": 1, "id": 442726, "split": "val", "sentences": [{"tokens": ["the", "boy", "that", "is", "skiing"], "raw": "The boy that is skiing", "sent_id": 2087, "sent": "the boy that is skiing"}, {"tokens": ["young", "boy", "on", "water", "skis"], "raw": "Young boy on water skis.", "sent_id": 2088, "sent": "young boy on water skis"}], "file_name": "COCO_train2014_000000163985_442726.jpg", "ann_id": 442726, "sent_ids": [2087, 2088], "ref_id": 5819}, {"segmentation": [[445.41, 236.62, 449.81, 242.49, 449.81, 246.88, 438.82, 254.94, 428.56, 280.58, 424.17, 295.23, 416.84, 306.95, 420.5, 322.34, 402.92, 321.6, 391.93, 317.21, 379.48, 322.34, 364.83, 322.34, 366.29, 309.15, 358.97, 305.49, 356.77, 313.55, 352.37, 312.81, 345.78, 305.49, 340.65, 304.76, 334.79, 300.36, 334.06, 285.71, 355.3, 288.64, 370.69, 290.1, 383.14, 293.03, 391.93, 292.3, 398.53, 287.17, 410.25, 227.1]], "area": 4247.397650000001, "iscrowd": 0, "image_id": 321209, "bbox": [334.06, 227.1, 115.75, 95.24], "category_id": 15, "id": 576809, "split": "val", "sentences": [{"tokens": ["a", "bench", "that", "is", "close", "to", "the", "mopads"], "raw": "A bench that is close to the mopads.", "sent_id": 2115, "sent": "a bench that is close to the mopads"}, {"tokens": ["a", "bench", "with", "three", "men", "sitting", "on", "it"], "raw": "A bench with three men sitting on it.", "sent_id": 2116, "sent": "a bench with three men sitting on it"}], "file_name": "COCO_train2014_000000321209_576809.jpg", "ann_id": 576809, "sent_ids": [2115, 2116], "ref_id": 5829}, {"segmentation": [[406.59, 400.06, 411.43, 396.67, 414.82, 307.15, 415.79, 301.83, 419.66, 296.99, 422.08, 293.12, 425.95, 289.73, 438.05, 283.92, 443.85, 281.5, 450.63, 295.54, 460.79, 297.96, 475.79, 303.28, 484.5, 304.73, 493.69, 302.31, 540.15, 294.57, 541.6, 293.6, 548.86, 256.34, 546.44, 249.08, 544.02, 245.21, 541.6, 242.31, 538.69, 239.41, 536.27, 239.41, 530.95, 239.89, 519.82, 240.86, 507.73, 244.73, 500.47, 247.15, 492.72, 246.66, 486.43, 244.73, 480.63, 242.79, 473.85, 240.37, 469.5, 237.95, 463.69, 239.41, 456.92, 244.24, 450.63, 247.63, 447.24, 250.05, 445.79, 248.6, 441.92, 247.63, 438.53, 246.18, 434.66, 247.63, 433.21, 252.47, 425.46, 260.7, 413.37, 268.44, 400.3, 247.63, 402.24, 237.95, 460.79, 206.02, 475.79, 193.44, 502.4, 166.82, 534.34, 152.79, 557.08, 149.4, 587.57, 151.82, 604.5, 157.63, 613.7, 163.43, 623.86, 173.11, 632.57, 180.85, 637.41, 193.92, 639.83, 206.5, 635.96, 229.24, 633.05, 239.89, 627.73, 249.57, 621.44, 256.83, 627.25, 363.28, 627.25, 373.44, 624.83, 383.61, 620.47, 391.83, 615.15, 398.61, 578.37, 428.0, 555.15, 428.0, 564.34, 330.86, 555.15, 344.89, 546.92, 419.9, 546.44, 428.0, 540.15, 428.0, 545.95, 349.73, 504.82, 344.41, 492.72, 344.41, 451.59, 377.31, 417.24, 398.12, 412.4, 402.48]], "area": 37635.499200000006, "iscrowd": 0, "image_id": 46592, "bbox": [400.3, 149.4, 239.53, 278.6], "category_id": 62, "id": 2121963, "split": "val", "sentences": [{"tokens": ["a", "chair", "have", "black", "color", "&", "a", "white", "carrybag", "is", "here"], "raw": "a chair have black color & a white carrybag is here", "sent_id": 2131, "sent": "a chair have black color & a white carrybag is here"}, {"tokens": ["a", "black", "chair", "with", "a", "white", "bag", "on", "it", "stating", "you", "are", "in", "little", "italy"], "raw": "A black chair with a white bag on it stating you are in little Italy", "sent_id": 2132, "sent": "a black chair with a white bag on it stating you are in little italy"}], "file_name": "COCO_train2014_000000046592_2121963.jpg", "ann_id": 2121963, "sent_ids": [2131, 2132], "ref_id": 5835}, {"segmentation": [[175.6, 50.86, 223.58, 61.41, 238.93, 63.33, 249.48, 64.29, 264.84, 72.93, 273.47, 79.64, 293.62, 88.28, 308.02, 99.79, 316.65, 122.82, 323.37, 146.81, 330.09, 165.04, 329.13, 180.4, 315.69, 211.1, 305.14, 222.62, 295.54, 239.89, 290.74, 256.2, 294.58, 269.63, 293.62, 277.31, 283.07, 292.66, 257.16, 304.18, 193.83, 320.49, 163.12, 323.37, 124.74, 315.69, 71.97, 300.34, 40.3, 276.35, 23.03, 253.32, 15.35, 224.53, 10.56, 189.03, 9.6, 166.96, 22.07, 122.82, 22.07, 111.31, 26.87, 102.67, 53.73, 83.48, 85.4, 70.05, 111.31, 58.53, 132.42, 50.86, 147.77, 48.94, 162.16, 48.94, 180.4, 53.73]], "area": 69149.12244999998, "iscrowd": 0, "image_id": 223165, "bbox": [9.6, 48.94, 320.49, 274.43], "category_id": 60, "id": 1080085, "split": "val", "sentences": [{"tokens": ["a", "cinnamon", "sugar", "donut"], "raw": "A cinnamon sugar donut", "sent_id": 2150, "sent": "a cinnamon sugar donut"}, {"tokens": ["a", "light", "brown", "color", "sweet", "vada", "with", "dark", "brown", "another", "one"], "raw": "A LIGHT BROWN COLOR SWEET VADA WITH DARK BROWN ANOTHER ONE", "sent_id": 2151, "sent": "a light brown color sweet vada with dark brown another one"}], "file_name": "COCO_train2014_000000223165_1080085.jpg", "ann_id": 1080085, "sent_ids": [2150, 2151], "ref_id": 5843}, {"segmentation": [[289.08, 183.37, 230.83, 174.74, 194.16, 162.88, 169.35, 142.38, 161.8, 120.81, 160.72, 99.24, 181.21, 66.88, 206.02, 50.7, 232.99, 39.91, 248.09, 72.27, 223.28, 71.19, 213.57, 70.11, 204.94, 81.98, 189.84, 84.13, 186.61, 87.37, 197.39, 106.79, 179.06, 105.71, 187.69, 127.28, 199.55, 129.44, 195.24, 143.46, 214.65, 154.25, 235.15, 166.11, 278.29, 175.82, 296.63, 167.19, 291.24, 176.9], [439.01, 98.16, 430.38, 70.11, 410.97, 50.7, 388.31, 39.91, 371.06, 31.28, 352.72, 29.12, 328.99, 24.81, 328.99, 47.46, 343.01, 42.07, 348.4, 50.7, 354.88, 35.6, 369.98, 40.99, 371.06, 62.56, 393.71, 61.48, 400.18, 66.88, 412.04, 72.27, 415.28, 90.61, 420.67, 101.39, 440.09, 100.31]], "area": 6863.3622, "iscrowd": 0, "image_id": 1261, "bbox": [160.72, 24.81, 279.37, 158.56], "category_id": 51, "id": 1532001, "split": "val", "sentences": [{"tokens": ["a", "plate", "with", "fruit", "on", "it", "behind", "two", "other", "dishes"], "raw": "A plate with fruit on it behind two other dishes.", "sent_id": 2187, "sent": "a plate with fruit on it behind two other dishes"}, {"tokens": ["the", "plate", "holding", "the", "fruit"], "raw": "The plate holding the fruit", "sent_id": 2188, "sent": "the plate holding the fruit"}], "file_name": "COCO_train2014_000000001261_1532001.jpg", "ann_id": 1532001, "sent_ids": [2187, 2188], "ref_id": 5861}, {"segmentation": [[205.64, 237.02, 215.21, 220.93, 229.0, 195.66, 235.51, 187.62, 246.62, 185.7, 249.3, 188.0, 258.49, 171.91, 262.7, 162.72, 268.83, 156.6, 273.04, 151.62, 274.96, 147.4, 274.19, 142.43, 274.57, 137.45, 275.72, 135.53, 277.25, 123.28, 281.08, 111.41, 286.44, 106.43, 294.49, 102.6, 305.59, 102.98, 315.17, 107.19, 322.06, 111.41, 330.48, 124.81, 328.57, 138.6, 322.83, 149.7, 315.17, 161.19, 317.46, 167.7, 324.74, 180.72, 326.65, 193.36, 327.42, 199.1, 318.61, 218.25, 317.08, 229.36, 311.72, 237.4, 307.12, 240.46, 299.47, 237.4, 292.19, 232.04, 285.68, 232.04, 278.79, 233.19, 255.04, 243.14, 240.87, 245.82, 233.21, 248.12, 230.15, 247.74, 221.73, 242.76, 211.77, 238.55]], "area": 9762.992050000003, "iscrowd": 0, "image_id": 372198, "bbox": [205.64, 102.6, 124.84, 145.52], "category_id": 1, "id": 1714715, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "pajamas", "in", "a", "suitcase"], "raw": "A boy in pajamas in a suitcase", "sent_id": 2238, "sent": "a boy in pajamas in a suitcase"}, {"tokens": ["two", "young", "girls", "sitting", "in", "a", "black", "suitcase", "on", "the", "floor"], "raw": "Two young girls sitting in a black suitcase on the floor.", "sent_id": 2239, "sent": "two young girls sitting in a black suitcase on the floor"}], "file_name": "COCO_train2014_000000372198_1714715.jpg", "ann_id": 1714715, "sent_ids": [2238, 2239], "ref_id": 5881}, {"segmentation": [[201.74, 263.55, 211.05, 250.1, 215.19, 240.79, 233.81, 230.45, 244.16, 230.45, 266.92, 228.38, 270.02, 218.03, 253.47, 222.17, 215.19, 237.69, 216.22, 219.07, 228.64, 217.0, 244.16, 213.89, 262.78, 208.72, 282.43, 209.76, 290.71, 209.76, 300.02, 208.72, 313.47, 213.89, 321.75, 222.17, 332.09, 235.62, 340.37, 255.28, 342.44, 274.93, 346.58, 282.18, 356.92, 295.62, 346.58, 299.76, 340.37, 295.62, 321.75, 264.59, 320.71, 279.07, 323.82, 290.45, 306.23, 296.66, 309.33, 310.11, 309.33, 325.63, 309.33, 338.04, 311.4, 370.11, 315.54, 395.98, 318.64, 424.94, 326.92, 452.88, 328.99, 463.22, 328.99, 473.57, 310.37, 470.46, 305.19, 458.05, 300.02, 437.36, 298.99, 434.26, 292.78, 408.39, 287.61, 383.56, 274.16, 404.25, 261.74, 413.56, 258.64, 431.15, 264.85, 457.02, 261.74, 467.36, 253.47, 472.53, 244.16, 465.29, 236.91, 435.29, 228.64, 450.81, 218.29, 442.53, 211.05, 425.98, 218.29, 413.56, 242.09, 395.98, 248.29, 378.39, 247.26, 358.73, 253.47, 354.59, 280.37, 363.91, 292.78, 369.08, 297.95, 358.73, 274.16, 337.01, 257.6, 317.35, 247.26, 311.14, 225.53, 292.52]], "area": 19235.641799999987, "iscrowd": 0, "image_id": 485173, "bbox": [201.74, 208.72, 155.18, 264.85], "category_id": 20, "id": 67734, "split": "val", "sentences": [{"tokens": ["the", "head", "and", "shoulders", "and", "one", "leg", "of", "a", "goat", "closest", "to", "the", "dog"], "raw": "the head and shoulders and one leg of a goat closest to the dog", "sent_id": 2262, "sent": "the head and shoulders and one leg of a goat closest to the dog"}], "file_name": "COCO_train2014_000000485173_67734.jpg", "ann_id": 67734, "sent_ids": [2262], "ref_id": 5889}, {"segmentation": [[18.64, 85.88, 43.1, 90.64, 62.13, 83.16, 78.44, 83.84, 100.19, 93.35, 119.9, 106.95, 140.28, 123.26, 149.12, 133.45, 157.27, 132.77, 165.43, 142.96, 166.11, 154.52, 155.91, 159.95, 149.8, 159.95, 149.12, 176.26, 141.64, 187.82, 135.53, 197.33, 123.29, 201.41, 116.5, 201.41, 116.5, 208.2, 102.23, 208.88, 100.19, 200.05, 73.68, 197.33, 60.77, 191.89, 67.57, 205.48, 52.62, 198.01, 48.54, 186.46, 32.23, 175.58, 28.83, 158.59, 28.83, 148.4, 22.04, 115.1, 21.36, 112.38, 7.77, 112.38, 17.96, 105.59, 17.96, 99.47, 29.51, 96.07]], "area": 12565.565150000002, "iscrowd": 0, "image_id": 33992, "bbox": [7.77, 83.16, 158.34, 125.72], "category_id": 16, "id": 44711, "split": "val", "sentences": [{"tokens": ["left", "blacl", "chicken"], "raw": "Left blacl chicken", "sent_id": 2351, "sent": "left blacl chicken"}, {"tokens": ["left", "black", "chicken"], "raw": "Left black chicken", "sent_id": 2352, "sent": "left black chicken"}], "file_name": "COCO_train2014_000000033992_44711.jpg", "ann_id": 44711, "sent_ids": [2351, 2352], "ref_id": 5924}, {"segmentation": [[0.4, 260.04, 8.39, 256.35, 9.82, 254.51, 10.85, 252.87, 17.2, 252.66, 21.7, 286.06, 24.16, 305.31, 86.85, 306.54, 90.75, 308.18, 92.38, 311.46, 91.15, 315.56, 91.97, 324.98, 91.97, 328.26, 93.41, 368.62, 91.36, 372.72, 88.49, 372.51, 88.08, 359.4, 88.08, 339.32, 86.2, 329.73, 87.21, 328.04, 66.66, 340.71, 55.81, 341.14, 42.01, 341.14, 21.86, 340.29, 23.97, 334.65, 23.41, 333.67, 21.43, 333.67, 20.31, 332.82, 23.27, 330.29, 23.27, 328.74, 22.42, 327.05, 22.42, 324.79, 25.38, 322.4, 25.24, 320.42, 30.87, 317.32, 32.99, 314.65, 31.86, 311.83, 29.61, 310.56, 25.66, 309.29, 22.56, 310.42, 21.72, 310.7, 20.03, 309.15, 21.15, 307.46, 21.29, 306.05, 18.62, 303.8, 15.8, 302.67, 11.85, 302.81, 10.16, 302.39, 12.56, 299.57, 18.48, 298.44, 20.17, 295.06, 20.03, 292.81, 17.77, 290.97, 14.39, 290.55, 12.7, 290.55, 12.7, 287.59, 11.29, 286.75, 3.4, 292.52, 0.3, 294.64, 0.44, 270.12, 0.3, 260.54]], "area": 3117.18205, "iscrowd": 0, "image_id": 375904, "bbox": [0.3, 252.66, 93.11, 120.06], "category_id": 62, "id": 101254, "split": "val", "sentences": [{"tokens": ["the", "chair", "and", "glass", "table", "on", "the", "left"], "raw": "The chair and glass table on the left.", "sent_id": 2480, "sent": "the chair and glass table on the left"}, {"tokens": ["a", "chair", "by", "the", "wall", "in", "a", "bedroom"], "raw": "a chair by the wall in a bedroom", "sent_id": 2481, "sent": "a chair by the wall in a bedroom"}], "file_name": "COCO_train2014_000000375904_101254.jpg", "ann_id": 101254, "sent_ids": [2480, 2481], "ref_id": 5967}, {"segmentation": [[24.81, 227.6, 33.44, 227.6, 38.83, 227.6, 53.93, 217.89, 59.33, 215.73, 76.58, 213.57, 116.49, 208.18, 134.83, 282.61, 136.99, 284.76, 196.31, 319.28, 96.0, 352.72, 92.76, 354.88, 42.07, 320.36, 40.99, 292.31, 32.36, 286.92, 20.49, 223.28]], "area": 13975.745700000001, "iscrowd": 0, "image_id": 456658, "bbox": [20.49, 208.18, 175.82, 146.7], "category_id": 73, "id": 1098120, "split": "val", "sentences": [{"tokens": ["the", "bigger", "laptop", "on", "the", "left"], "raw": "the bigger laptop on the left", "sent_id": 2494, "sent": "the bigger laptop on the left"}], "file_name": "COCO_train2014_000000456658_1098120.jpg", "ann_id": 1098120, "sent_ids": [2494], "ref_id": 5973}, {"segmentation": [[265.05, 26.03, 293.98, 32.76, 322.91, 37.47, 353.18, 40.83, 380.09, 52.94, 398.93, 63.7, 404.31, 58.32, 431.22, 52.27, 454.09, 59.67, 480.33, 68.41, 500.0, 85.9, 500.0, 108.1, 495.8, 123.58, 495.8, 152.5, 468.89, 170.67, 474.27, 211.7, 474.95, 229.87, 457.45, 254.76, 454.09, 264.18, 461.49, 283.01, 446.02, 326.74, 438.62, 328.09, 433.91, 328.09, 440.64, 293.1, 428.53, 261.49, 418.44, 236.59, 412.38, 219.78, 407.67, 211.03, 402.29, 198.92, 386.82, 170.67, 376.73, 143.09, 341.75, 114.83, 308.11, 91.29, 273.13, 89.94, 250.93, 95.32, 228.73, 117.52, 198.45, 139.72, 178.95, 142.41, 168.18, 139.72, 162.8, 136.36, 158.76, 128.96, 156.07, 123.58, 154.73, 114.83, 148.0, 109.45, 137.91, 102.72, 130.51, 90.61, 119.07, 77.16, 112.35, 71.1, 111.67, 55.63, 141.27, 25.36, 171.55, 12.58, 190.38, 14.59, 218.64, 7.19, 237.47, 14.59, 263.04, 24.69]], "area": 41900.386300000006, "iscrowd": 0, "image_id": 301943, "bbox": [111.67, 7.19, 388.33, 320.9], "category_id": 18, "id": 6823, "split": "val", "sentences": [{"tokens": ["dog", "climbing", "on", "the", "window"], "raw": "dog climbing on the window", "sent_id": 2513, "sent": "dog climbing on the window"}, {"tokens": ["the", "dog", "with", "a", "paw", "on", "the", "windowsill"], "raw": "The dog with a paw on the windowsill.", "sent_id": 2514, "sent": "the dog with a paw on the windowsill"}], "file_name": "COCO_train2014_000000301943_6823.jpg", "ann_id": 6823, "sent_ids": [2513, 2514], "ref_id": 5981}, {"segmentation": [[47.48, 271.6, 48.52, 426.44, 152.77, 473.92, 321.03, 471.86, 357.16, 457.4, 376.77, 422.31, 434.58, 426.44, 451.1, 393.4, 465.55, 374.82, 459.35, 353.15, 390.19, 344.89, 385.03, 327.34, 294.19, 343.86, 289.03, 312.89, 259.1, 292.24, 163.1, 260.24, 113.55, 253.02, 86.71, 254.05, 76.39, 271.6, 51.61, 272.63]], "area": 63146.2347, "iscrowd": 0, "image_id": 445829, "bbox": [47.48, 253.02, 418.07, 220.9], "category_id": 63, "id": 113134, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "leather", "sofa", "behind", "a", "foot", "stool", "that", "has", "a", "laptop", "computer", "on", "it"], "raw": "A dark brown leather sofa behind a foot stool that has a laptop computer on it.", "sent_id": 2574, "sent": "a dark brown leather sofa behind a foot stool that has a laptop computer on it"}, {"tokens": ["the", "black", "leather", "couch", "and", "ottoman", "in", "the", "center", "of", "the", "room"], "raw": "The black leather couch and ottoman in the center of the room.", "sent_id": 2575, "sent": "the black leather couch and ottoman in the center of the room"}], "file_name": "COCO_train2014_000000445829_113134.jpg", "ann_id": 113134, "sent_ids": [2574, 2575], "ref_id": 6002}, {"segmentation": [[286.72, 133.75, 291.97, 138.99, 293.72, 152.98, 296.34, 167.84, 296.34, 183.57, 291.97, 191.44, 285.85, 212.42, 284.1, 224.66, 281.48, 232.53, 284.1, 232.53, 280.6, 239.52, 281.48, 271.86, 280.6, 278.86, 276.23, 284.1, 272.74, 288.47, 282.35, 289.35, 286.72, 283.23, 289.35, 278.86, 288.47, 257.0, 294.59, 244.76, 294.59, 233.4, 298.96, 231.65, 303.24, 221.89, 305.54, 218.43, 310.16, 210.36, 314.77, 212.09, 316.5, 213.82, 320.54, 218.43, 324.0, 224.78, 328.04, 235.16, 333.23, 238.62, 331.5, 242.08, 331.5, 248.42, 333.8, 251.31, 335.53, 261.11, 336.11, 270.92, 336.11, 281.87, 346.49, 284.18, 349.37, 283.6, 348.8, 281.87, 344.18, 277.84, 343.03, 272.07, 341.88, 263.42, 342.45, 253.61, 344.18, 239.77, 343.61, 232.85, 344.76, 230.55, 342.45, 229.97, 339.57, 209.78, 338.99, 201.71, 336.69, 195.37, 331.5, 179.22, 330.34, 173.45, 328.04, 157.88, 330.34, 138.27, 331.5, 127.89, 336.69, 122.7, 341.88, 117.51, 344.76, 114.05, 347.07, 112.89, 343.61, 108.28, 319.38, 88.67, 315.35, 84.06, 306.12, 81.17, 299.2, 84.06, 299.78, 86.94, 304.39, 90.98, 307.85, 90.98, 299.2, 92.13, 295.74, 97.9, 295.16, 105.4, 298.05, 118.08, 299.2, 119.81, 286.51, 120.97, 280.17, 122.7, 279.01, 124.43, 272.67, 125.58, 269.21, 126.16, 247.29, 127.31, 233.45, 129.62, 223.65, 128.46, 228.26, 132.5, 224.8, 135.39, 234.03, 133.08, 236.91, 134.81, 236.91, 135.96, 231.15, 140.58, 231.72, 141.73, 238.07, 137.69, 246.72, 135.96, 259.98, 135.96, 269.79, 138.27, 284.78, 133.66, 288.82, 132.5], [315.92, 95.59, 317.08, 108.28, 314.77, 120.39, 314.73, 123.2, 326.84, 117.44, 332.03, 112.82, 334.91, 112.25, 323.38, 98.98, 318.77, 93.79, 314.15, 93.79, 314.73, 96.67]], "area": 7762.387449999998, "iscrowd": 0, "image_id": 175370, "bbox": [223.65, 81.17, 125.72, 208.18], "category_id": 1, "id": 1248485, "split": "val", "sentences": [{"tokens": ["a", "man", "skating", "on", "the", "wooden", "rod"], "raw": "A MAN SKATING ON THE WOODEN ROD", "sent_id": 2586, "sent": "a man skating on the wooden rod"}, {"tokens": ["a", "man", "performing", "skateboard", "trick"], "raw": "A man performing skateboard trick", "sent_id": 2587, "sent": "a man performing skateboard trick"}], "file_name": "COCO_train2014_000000175370_1248485.jpg", "ann_id": 1248485, "sent_ids": [2586, 2587], "ref_id": 6006}, {"segmentation": [[248.81, 310.65, 247.37, 268.94, 231.55, 237.3, 230.11, 176.9, 273.26, 135.19, 335.1, 128.0, 384.0, 163.96, 389.75, 227.24, 384.0, 281.89, 388.31, 312.09, 346.61, 414.2, 310.65, 487.55, 245.93, 460.22, 231.55, 412.76, 251.69, 378.25, 251.69, 322.16], [424.0, 345.17, 422.83, 504.81, 419.96, 629.93, 228.67, 632.81, 232.99, 598.29, 245.93, 575.28, 365.3, 552.27, 411.33, 458.79]], "area": 60005.99044999998, "iscrowd": 0, "image_id": 240521, "bbox": [228.67, 128.0, 195.33, 504.81], "category_id": 1, "id": 514222, "split": "val", "sentences": [{"tokens": ["a", "man", "is", "smiling", "with", "his", "couple", "and", "both", "are", "wearing", "white", "cloth"], "raw": "A MAN IS SMILING WITH HIS COUPLE AND BOTH ARE WEARING WHITE CLOTH", "sent_id": 2630, "sent": "a man is smiling with his couple and both are wearing white cloth"}, {"tokens": ["the", "man", "wearing", "the", "white", "vest"], "raw": "The man wearing the white vest", "sent_id": 2631, "sent": "the man wearing the white vest"}], "file_name": "COCO_train2014_000000240521_514222.jpg", "ann_id": 514222, "sent_ids": [2630, 2631], "ref_id": 6022}, {"segmentation": [[636.4, 43.15, 579.24, 74.43, 486.47, 125.12, 454.11, 142.38, 434.7, 125.12, 416.36, 106.79, 399.1, 91.69, 414.2, 128.36, 433.62, 145.62, 461.66, 198.47, 542.56, 182.29, 616.99, 162.88, 640.0, 159.64, 640.0, 69.03], [594.34, 357.03, 571.69, 357.03, 514.52, 336.54, 546.88, 368.9, 570.61, 377.53, 578.16, 386.16, 522.07, 396.94, 519.91, 413.12, 530.7, 415.28, 519.91, 422.83, 604.04, 423.91, 637.48, 428.22, 636.4, 373.21]], "area": 23949.114999999998, "iscrowd": 0, "image_id": 173032, "bbox": [399.1, 43.15, 240.9, 385.07], "category_id": 1, "id": 494173, "split": "val", "sentences": [{"tokens": ["man", "holding", "the", "hand", "of", "a", "little", "girl"], "raw": "Man holding the hand of a little girl", "sent_id": 2753, "sent": "man holding the hand of a little girl"}, {"tokens": ["a", "person", "that", "is", "touching", "a", "child"], "raw": "A person that is touching a child.", "sent_id": 2754, "sent": "a person that is touching a child"}], "file_name": "COCO_train2014_000000173032_494173.jpg", "ann_id": 494173, "sent_ids": [2753, 2754], "ref_id": 6071}, {"segmentation": [[223.53, 136.78, 188.19, 141.56, 155.71, 152.07, 139.47, 170.21, 129.91, 193.14, 125.14, 266.7, 142.33, 306.82, 166.21, 325.92, 188.19, 338.34, 206.34, 334.52, 211.11, 331.65, 228.31, 345.03, 248.37, 354.58, 257.92, 352.67, 271.29, 339.3, 286.58, 334.52, 298.04, 327.83, 302.82, 310.64, 277.02, 311.59, 264.61, 313.5, 261.74, 298.22, 265.56, 270.52, 265.56, 240.9, 261.74, 217.98, 245.5, 216.07, 218.75, 230.4, 206.34, 238.99, 202.51, 244.72, 203.47, 241.86, 200.6, 222.75, 192.01, 215.11, 192.01, 202.69, 205.38, 194.1, 211.11, 180.72, 208.25, 168.3, 203.47, 163.53, 222.57, 158.75, 234.99, 153.02, 235.95, 139.65]], "area": 21304.18214999999, "iscrowd": 0, "image_id": 479734, "bbox": [125.14, 136.78, 177.68, 217.8], "category_id": 1, "id": 495552, "split": "val", "sentences": [{"tokens": ["man", "in", "seashore"], "raw": "MAN  IN SEASHORE", "sent_id": 2788, "sent": "man in seashore"}, {"tokens": ["a", "man", "falling", "off", "his", "surfboard"], "raw": "a man falling off his surfboard", "sent_id": 2789, "sent": "a man falling off his surfboard"}], "file_name": "COCO_train2014_000000479734_495552.jpg", "ann_id": 495552, "sent_ids": [2788, 2789], "ref_id": 6084}, {"segmentation": [[220.2, 197.22, 205.84, 235.52, 238.39, 247.97, 239.35, 261.37, 245.09, 250.84, 325.52, 254.67, 375.3, 256.58, 382.96, 271.9, 380.09, 282.43, 394.45, 292.96, 403.07, 283.39, 404.02, 254.67, 435.62, 246.05, 434.66, 217.33, 399.24, 214.46, 390.62, 181.91, 390.62, 217.33, 381.04, 204.88, 314.03, 209.67, 257.54, 222.12, 226.9, 191.48, 218.29, 198.18]], "area": 10219.48615, "iscrowd": 0, "image_id": 229415, "bbox": [205.84, 181.91, 229.78, 111.05], "category_id": 5, "id": 156601, "split": "val", "sentences": [{"tokens": ["a", "black", "airplane"], "raw": "A black airplane.", "sent_id": 2823, "sent": "a black airplane"}, {"tokens": ["a", "toy", "plane", "flying"], "raw": "a toy plane flying", "sent_id": 2824, "sent": "a toy plane flying"}], "file_name": "COCO_train2014_000000229415_156601.jpg", "ann_id": 156601, "sent_ids": [2823, 2824], "ref_id": 6098}, {"segmentation": [[228.09, 492.13, 220.22, 475.28, 221.35, 469.66, 235.96, 469.66, 241.57, 457.3, 220.22, 440.45, 216.85, 404.49, 219.1, 375.28, 222.47, 368.54, 237.08, 362.92, 255.06, 359.55, 275.28, 361.8, 282.02, 378.65, 285.39, 420.22, 273.03, 448.31, 256.18, 457.3, 259.55, 470.79, 273.03, 474.16, 275.28, 486.52, 269.66, 492.13]], "area": 6906.628099999997, "iscrowd": 0, "image_id": 569037, "bbox": [216.85, 359.55, 68.54, 132.58], "category_id": 46, "id": 665118, "split": "val", "sentences": [{"tokens": ["an", "empty", "wine", "glass", "near", "the", "paper", "cup"], "raw": "An empty wine glass near the paper cup", "sent_id": 2842, "sent": "an empty wine glass near the paper cup"}, {"tokens": ["the", "clear", "glass", "cup", "next", "to", "the", "short", "white", "cup"], "raw": "The clear glass cup next to the short white cup.", "sent_id": 2843, "sent": "the clear glass cup next to the short white cup"}], "file_name": "COCO_train2014_000000569037_665118.jpg", "ann_id": 665118, "sent_ids": [2842, 2843], "ref_id": 6107}, {"segmentation": [[148.52, 165.31, 142.06, 228.81, 143.14, 251.41, 137.76, 267.55, 125.92, 272.93, 119.46, 267.55, 120.54, 255.71, 119.46, 212.66, 119.46, 173.92, 116.23, 110.42, 113.0, 86.74, 99.01, 100.74, 92.56, 91.05, 92.56, 74.91, 97.94, 61.99, 105.47, 46.92, 115.16, 39.39, 117.31, 37.24, 116.23, 14.64, 118.39, 3.87, 136.68, 4.95, 149.6, 22.17, 157.13, 29.7, 186.19, 53.38, 199.1, 85.67, 187.26, 119.03, 185.11, 131.95, 189.42, 250.33, 176.5, 254.64]], "area": 16001.334499999995, "iscrowd": 0, "image_id": 401455, "bbox": [92.56, 3.87, 106.54, 269.06], "category_id": 1, "id": 209393, "split": "val", "sentences": [{"tokens": ["an", "older", "man", "dressed", "in", "blue", "and", "denim", "speaking", "into", "a", "small", "microphone"], "raw": "An older man dressed in blue and denim speaking into a small microphone", "sent_id": 2871, "sent": "an older man dressed in blue and denim speaking into a small microphone"}, {"tokens": ["a", "husky", "old", "man", "wearing", "a", "blue", "shirt", "and", "jeans"], "raw": "A husky old man wearing a blue shirt and jeans.", "sent_id": 2872, "sent": "a husky old man wearing a blue shirt and jeans"}], "file_name": "COCO_train2014_000000401455_209393.jpg", "ann_id": 209393, "sent_ids": [2871, 2872], "ref_id": 6119}, {"segmentation": [[171.63, 104.22, 198.65, 111.52, 207.42, 129.05, 212.53, 135.62, 219.83, 145.11, 234.44, 152.42, 241.74, 158.26, 222.02, 187.47, 213.26, 178.71, 203.03, 169.22, 186.97, 159.72, 170.17, 171.41, 164.33, 185.28, 150.45, 205.73, 147.53, 215.23, 154.83, 253.2, 151.91, 260.51, 142.42, 242.98, 140.22, 213.77, 140.22, 196.24, 135.84, 148.77, 140.96, 124.66, 151.18, 108.6, 157.02, 104.95]], "area": 6250.984100000001, "iscrowd": 0, "image_id": 236406, "bbox": [135.84, 104.22, 105.9, 156.29], "category_id": 24, "id": 592742, "split": "val", "sentences": [{"tokens": ["the", "left", "zebra", "with", "tail", "wag"], "raw": "the left zebra with tail wag", "sent_id": 2912, "sent": "the left zebra with tail wag"}, {"tokens": ["zebra", "'", "s", "rear", "behind", "other", "zebra", "'", "s", "head"], "raw": "Zebra's rear behind other zebra's head.", "sent_id": 2913, "sent": "zebra ' s rear behind other zebra ' s head"}], "file_name": "COCO_train2014_000000236406_592742.jpg", "ann_id": 592742, "sent_ids": [2912, 2913], "ref_id": 6133}, {"segmentation": [[303.88, 200.14, 303.33, 203.17, 306.36, 204.82, 307.19, 208.68, 308.29, 213.91, 306.36, 218.32, 303.61, 220.53, 300.02, 221.35, 295.89, 221.35, 290.38, 218.87, 288.45, 213.36, 288.73, 209.78, 289.55, 205.92, 290.66, 202.06, 290.66, 197.93, 290.38, 193.25, 290.66, 189.66, 291.76, 183.88, 292.03, 180.02, 290.38, 175.61, 291.48, 172.86, 292.58, 168.72, 293.69, 165.97, 296.44, 163.21, 296.72, 160.73, 300.02, 155.49, 303.88, 147.23, 305.26, 143.65, 314.63, 136.76, 320.42, 133.45, 324.27, 130.97, 328.96, 128.49, 333.37, 126.56, 338.33, 125.18, 342.19, 124.63, 342.19, 122.15, 339.71, 119.4, 338.88, 111.41, 340.81, 104.52, 341.08, 98.73, 343.84, 92.12, 347.15, 89.36, 350.73, 87.71, 357.07, 88.26, 358.99, 89.91, 363.4, 94.32, 365.33, 101.76, 366.16, 104.24, 368.09, 107.82, 366.71, 111.13, 367.81, 114.44, 367.54, 116.92, 372.77, 127.66, 374.7, 130.69, 381.87, 135.1, 386.55, 138.96, 391.51, 145.3, 395.09, 151.36, 398.95, 159.08, 400.88, 164.59, 402.53, 172.03, 405.56, 178.92, 405.84, 184.15, 404.19, 190.49, 404.74, 195.18, 405.29, 198.21, 405.56, 207.3, 407.22, 209.23, 412.45, 214.19, 412.73, 218.32, 412.73, 221.9, 409.15, 224.11, 405.56, 226.59, 401.98, 225.76, 395.92, 221.35, 395.37, 218.6, 396.19, 214.74, 395.37, 209.5, 394.54, 207.02, 392.06, 204.54, 388.75, 201.79, 384.9, 189.66, 382.69, 185.53, 379.66, 181.4, 378.83, 176.16, 378.01, 169.82, 376.63, 176.44, 376.91, 184.43, 376.91, 189.39, 376.91, 196.55, 377.18, 202.89, 376.35, 209.78, 376.63, 216.39, 376.35, 219.42, 376.08, 225.49, 376.91, 230.45, 374.98, 233.2, 374.43, 236.51, 374.43, 240.64, 373.05, 242.85, 372.77, 245.6, 374.43, 247.53, 376.35, 252.77, 372.5, 260.48, 370.02, 265.99, 368.64, 271.23, 368.91, 278.12, 366.71, 278.95, 367.26, 283.35, 363.4, 294.38, 363.4, 299.06, 363.68, 304.02, 360.92, 304.85, 357.89, 305.12, 354.86, 303.19, 355.14, 306.5, 352.11, 308.15, 352.38, 312.01, 354.86, 316.15, 357.07, 319.73, 355.41, 323.03, 356.24, 326.07, 355.14, 332.13, 350.73, 331.85, 341.08, 329.1, 337.78, 323.31, 331.16, 322.21, 329.79, 319.18, 331.99, 313.11, 332.82, 308.71, 335.02, 302.92, 336.95, 299.34, 333.37, 293.83, 335.02, 292.17, 336.67, 292.17, 339.15, 281.98, 341.63, 267.37, 343.29, 258.0, 345.77, 254.42, 344.94, 248.36, 345.49, 244.22, 347.15, 241.19, 346.04, 239.26, 343.84, 237.61, 342.19, 243.67, 330.89, 263.51, 323.45, 275.91, 311.87, 293.27, 301.68, 308.43, 295.89, 314.22, 292.58, 316.97, 292.58, 321.11, 288.18, 325.79, 286.8, 326.34, 285.42, 328.82, 285.97, 333.51, 285.97, 337.64, 284.04, 339.29, 279.63, 341.5, 271.09, 340.12, 261.17, 335.99, 261.45, 332.4, 265.3, 325.79, 268.34, 320.83, 267.78, 314.22, 267.78, 311.19, 272.19, 305.67, 274.12, 301.54, 276.88, 294.93, 279.63, 290.52, 284.59, 284.73, 285.97, 279.77, 288.45, 275.64, 290.1, 272.33, 293.96, 266.27, 300.85, 259.66, 302.5, 258.83, 303.61, 255.52, 303.61, 251.94, 305.81, 246.98, 306.91, 241.19, 307.19, 239.26, 306.91, 230.45, 306.64, 227.69, 310.22, 222.46, 313.53, 214.74, 314.63, 211.98, 318.76, 209.78, 316.56, 205.37, 314.91, 198.21, 317.11, 195.45, 317.94, 188.01, 319.31, 178.37, 320.69, 171.2, 314.91, 173.13, 311.05, 177.82, 308.29, 183.6, 307.46, 187.74, 307.46, 190.22, 308.02, 193.52, 305.81, 196.83]], "area": 16395.969100000002, "iscrowd": 0, "image_id": 486193, "bbox": [261.17, 87.71, 151.56, 253.79], "category_id": 1, "id": 424104, "split": "val", "sentences": [{"tokens": ["a", "male", "skier", "wearing", "a", "grey", "jacket", "and", "black", "trousers"], "raw": "A male skier wearing a grey jacket and black trousers", "sent_id": 2996, "sent": "a male skier wearing a grey jacket and black trousers"}, {"tokens": ["man", "on", "skis", "with", "poles", "in", "the", "foreground"], "raw": "Man on skis with poles in the foreground", "sent_id": 2997, "sent": "man on skis with poles in the foreground"}], "file_name": "COCO_train2014_000000486193_424104.jpg", "ann_id": 424104, "sent_ids": [2996, 2997], "ref_id": 6165}, {"segmentation": [[539.14, 384.02, 528.03, 361.8, 525.0, 339.92, 528.7, 322.75, 530.38, 312.99, 529.71, 296.83, 530.72, 287.07, 531.73, 264.18, 536.11, 234.55, 534.76, 225.8, 536.78, 220.75, 550.24, 218.06, 558.32, 200.89, 573.47, 189.44, 585.93, 190.12, 599.73, 200.55, 609.83, 215.36, 623.63, 222.77, 639.11, 240.61, 639.45, 261.15, 640.0, 295.82, 640.0, 358.1, 640.0, 394.79, 633.42, 398.15, 618.27, 405.9, 598.07, 405.9, 573.16, 400.17, 546.57, 390.08]], "area": 20553.853750000002, "iscrowd": 0, "image_id": 411238, "bbox": [525.0, 189.44, 115.0, 216.46], "category_id": 27, "id": 1168654, "split": "val", "sentences": [{"tokens": ["the", "all", "blue", "backpack", "that", "the", "man", "with", "a", "dark", "green", "textured", "hoodie", "is", "wearing"], "raw": "the all blue backpack that the man with a dark green textured hoodie is wearing", "sent_id": 3028, "sent": "the all blue backpack that the man with a dark green textured hoodie is wearing"}], "file_name": "COCO_train2014_000000411238_1168654.jpg", "ann_id": 1168654, "sent_ids": [3028], "ref_id": 6176}, {"segmentation": [[537.35, 353.78, 535.43, 74.55, 356.95, 41.93, 259.08, 17.94, 230.29, 3.54, 582.45, 1.63, 640.0, 1.63, 615.07, 40.01, 569.01, 56.32, 553.66, 71.67, 562.3, 363.38, 538.31, 358.58, 540.23, 348.02]], "area": 23873.270899999996, "iscrowd": 0, "image_id": 159957, "bbox": [230.29, 1.63, 409.71, 361.75], "category_id": 28, "id": 282565, "split": "val", "sentences": [{"tokens": ["umbrella", "stand", "with", "the", "number", "2"], "raw": "Umbrella stand with the number 2", "sent_id": 3095, "sent": "umbrella stand with the number 2"}], "file_name": "COCO_train2014_000000159957_282565.jpg", "ann_id": 282565, "sent_ids": [3095], "ref_id": 6199}, {"segmentation": [[124.45, 142.42, 129.46, 149.57, 139.47, 137.41, 148.06, 130.97, 168.08, 127.4, 195.26, 126.68, 219.58, 128.11, 246.76, 128.11, 263.93, 128.11, 274.65, 127.4, 283.95, 125.97, 286.81, 124.54, 284.67, 115.95, 283.24, 112.38, 285.38, 102.36, 287.53, 98.07, 287.53, 85.2, 274.65, 76.61, 272.51, 79.48, 270.36, 82.34, 263.93, 88.06, 263.21, 88.06, 258.2, 88.06, 251.05, 87.34, 241.75, 87.34, 232.46, 88.06, 227.45, 91.64, 232.46, 79.48, 228.88, 65.17, 221.73, 54.44, 213.86, 49.44, 201.7, 45.86, 195.98, 47.29, 190.26, 48.72, 183.1, 53.73, 175.95, 60.16, 171.66, 68.03, 168.8, 77.33, 167.37, 85.2, 164.51, 96.64, 163.79, 96.64, 159.5, 90.2, 155.92, 87.34, 153.78, 83.77, 150.92, 75.9, 143.76, 70.18, 136.61, 64.46, 131.61, 65.89, 123.74, 69.46, 123.74, 75.9, 118.73, 85.91, 121.59, 96.64, 127.31, 103.08, 126.6, 115.95, 121.59, 130.97, 120.16, 138.13]], "area": 9588.142150000003, "iscrowd": 0, "image_id": 280228, "bbox": [118.73, 45.86, 168.8, 103.71], "category_id": 1, "id": 449295, "split": "val", "sentences": [{"tokens": ["a", "red", "headed", "girl", "in", "a", "yellow", "blouse", "holding", "a", "knife", "in", "each", "hand", "posed", "as", "if", "she", "is", "about", "to", "stab", "a", "guy", "laying", "on", "the", "table"], "raw": "A red headed girl in a yellow blouse holding a knife in each hand posed as if she is about to stab a guy laying on the table.", "sent_id": 3106, "sent": "a red headed girl in a yellow blouse holding a knife in each hand posed as if she is about to stab a guy laying on the table"}, {"tokens": ["a", "girl", "with", "a", "knife", "in", "each", "hand", "standing", "over", "a", "young", "man", "on", "a", "table"], "raw": "A girl with a knife in each hand standing over a young man on a table.", "sent_id": 3107, "sent": "a girl with a knife in each hand standing over a young man on a table"}], "file_name": "COCO_train2014_000000280228_449295.jpg", "ann_id": 449295, "sent_ids": [3106, 3107], "ref_id": 6204}, {"segmentation": [[366.19, 273.29, 361.55, 273.29, 356.9, 273.29, 348.39, 272.52, 341.42, 270.19, 338.32, 267.87, 335.23, 266.32, 327.48, 261.68, 326.71, 260.9, 321.29, 257.81, 319.74, 255.48, 319.74, 250.84, 322.84, 244.65, 329.03, 236.9, 336.77, 233.81, 342.19, 229.16, 353.03, 222.97, 360.77, 218.32, 373.94, 212.9, 384.77, 209.81, 399.48, 209.03, 405.68, 208.26, 420.39, 203.61, 420.39, 195.87, 419.61, 188.13, 416.52, 181.16, 416.52, 174.19, 424.26, 171.1, 429.68, 168.0, 430.45, 168.0, 453.68, 167.23, 475.35, 168.77, 479.23, 171.1, 487.74, 175.74, 493.94, 179.61, 504.77, 186.58, 504.77, 195.87, 496.26, 198.19, 491.61, 199.74, 492.39, 205.94, 497.81, 216.77, 501.68, 229.94, 502.45, 233.03, 508.65, 250.06, 506.32, 266.32, 498.58, 269.42, 459.1, 274.84, 448.26, 274.84, 428.13, 274.84, 418.84, 274.84, 400.26, 274.84, 392.52, 274.84, 387.1, 274.84, 384.77, 274.84, 383.23, 274.84, 377.81, 274.84]], "area": 13722.29645, "iscrowd": 0, "image_id": 213005, "bbox": [319.74, 167.23, 188.91, 107.61], "category_id": 20, "id": 65473, "split": "val", "sentences": [{"tokens": ["a", "small", "lamb", "lying", "closest", "to", "the", "adult"], "raw": "A small lamb lying closest to the adult.", "sent_id": 3116, "sent": "a small lamb lying closest to the adult"}, {"tokens": ["a", "lamb", "looking", "up", "at", "a", "sheep"], "raw": "A lamb looking up at a sheep.", "sent_id": 3117, "sent": "a lamb looking up at a sheep"}], "file_name": "COCO_train2014_000000213005_65473.jpg", "ann_id": 65473, "sent_ids": [3116, 3117], "ref_id": 6208}, {"segmentation": [[0.0, 293.16, 16.49, 322.48, 27.48, 328.89, 52.22, 323.39, 54.05, 336.22, 51.3, 349.96, 59.55, 359.12, 67.79, 362.79, 95.28, 373.78, 129.17, 368.28, 152.99, 364.62, 171.32, 367.37, 184.14, 366.45, 217.12, 359.12, 231.78, 354.54, 243.69, 357.29, 283.08, 354.54, 320.65, 368.28, 329.81, 364.62, 365.54, 377.45, 382.03, 376.53, 415.01, 376.53, 436.08, 378.36, 463.56, 377.45, 479.14, 375.61, 519.45, 371.03, 546.01, 371.03, 565.25, 362.79, 595.48, 364.62, 614.72, 362.79, 626.63, 370.12, 628.46, 420.5, 619.3, 426.0, 54.05, 425.08, 0.92, 404.93]], "area": 38133.48635, "iscrowd": 0, "image_id": 111040, "bbox": [0.0, 293.16, 628.46, 132.84], "category_id": 63, "id": 115877, "split": "val", "sentences": [{"tokens": ["a", "blue", "cuchine"], "raw": "a blue cuchine", "sent_id": 3138, "sent": "a blue cuchine"}, {"tokens": ["cat", "bed"], "raw": "cat bed", "sent_id": 3139, "sent": "cat bed"}], "file_name": "COCO_train2014_000000111040_115877.jpg", "ann_id": 115877, "sent_ids": [3138, 3139], "ref_id": 6218}, {"segmentation": [[638.46, 133.33, 637.65, 235.44, 639.27, 240.3, 613.34, 195.73, 535.54, 158.45, 493.39, 151.16, 439.91, 121.98, 426.94, 96.86, 411.54, 83.89, 397.77, 100.91, 334.55, 114.69, 311.05, 95.24, 297.27, 102.53, 307.81, 139.81, 308.62, 144.67, 293.22, 133.33, 154.64, 103.34, 249.46, 68.5, 281.88, 36.08, 290.79, 12.58, 296.46, 1.23, 637.65, 2.85, 636.03, 126.03]], "area": 53893.51, "iscrowd": 0, "image_id": 111040, "bbox": [154.64, 1.23, 484.63, 239.07], "category_id": 63, "id": 111649, "split": "val", "sentences": [{"tokens": ["decorative", "pillow", "behind", "the", "cats"], "raw": "Decorative pillow behind the cats.", "sent_id": 3197, "sent": "decorative pillow behind the cats"}, {"tokens": ["patterned", "pillows", "behind", "the", "cats"], "raw": "patterned pillows behind the cats", "sent_id": 3198, "sent": "patterned pillows behind the cats"}], "file_name": "COCO_train2014_000000111040_111649.jpg", "ann_id": 111649, "sent_ids": [3197, 3198], "ref_id": 6244}, {"segmentation": [[382.0, 420.38, 392.29, 382.93, 397.91, 369.82, 372.63, 337.99, 355.78, 315.52, 348.29, 271.52, 356.72, 247.17, 368.89, 215.34, 377.31, 145.12, 387.61, 111.42, 398.85, 94.56, 409.15, 75.84, 406.34, 62.73, 411.02, 43.07, 411.96, 27.15, 427.87, 13.11, 457.83, 7.49, 480.3, 27.15, 477.49, 55.24, 480.3, 53.37, 482.18, 61.79, 479.37, 73.96, 499.03, 91.75, 491.54, 155.42, 490.6, 178.83, 515.88, 211.6, 545.84, 224.7, 557.08, 245.3, 558.95, 264.96, 542.1, 273.39, 529.93, 266.84, 517.75, 239.68, 493.41, 233.13, 473.75, 226.58, 476.56, 251.85, 490.6, 285.56, 555.2, 380.12, 559.89, 411.02, 548.65, 422.25, 500.9, 421.32, 508.39, 403.53, 453.15, 356.72, 437.24, 394.17, 426.94, 421.32, 382.93, 422.25]], "area": 49573.53575, "iscrowd": 0, "image_id": 555794, "bbox": [348.29, 7.49, 211.6, 414.76], "category_id": 1, "id": 482154, "split": "val", "sentences": [{"tokens": ["a", "lady", "in", "blue", "pant", "and", "pink", "shirt", "holding", "a", "tennis", "bat", "is", "swing", "the", "hand", "to", "hit", "the", "ball"], "raw": "A lady in blue pant and pink shirt holding a tennis bat is swing the hand to hit the ball.", "sent_id": 3211, "sent": "a lady in blue pant and pink shirt holding a tennis bat is swing the hand to hit the ball"}, {"tokens": ["an", "action", "shot", "of", "a", "woman", "in", "green", "pants", "and", "a", "red", "shirt", "about", "to", "hit", "a", "tennis", "ball"], "raw": "An action shot of a woman in green pants and a red shirt about to hit a tennis ball.", "sent_id": 3212, "sent": "an action shot of a woman in green pants and a red shirt about to hit a tennis ball"}], "file_name": "COCO_train2014_000000555794_482154.jpg", "ann_id": 482154, "sent_ids": [3211, 3212], "ref_id": 6250}, {"segmentation": [[0.94, 354.39, 108.47, 354.39, 83.22, 295.48, 156.16, 229.09, 144.0, 215.06, 126.23, 196.36, 119.69, 164.57, 109.4, 120.62, 101.92, 109.4, 108.47, 87.9, 116.88, 69.19, 0.94, 100.05]], "area": 30666.176850000003, "iscrowd": 0, "image_id": 246641, "bbox": [0.94, 69.19, 155.22, 285.2], "category_id": 67, "id": 1966744, "split": "val", "sentences": [{"tokens": ["an", "open", "part", "of", "the", "table", "between", "a", "can", "and", "two", "sandwich", "baskets"], "raw": "An open part of the table between a can and two sandwich baskets.", "sent_id": 3332, "sent": "an open part of the table between a can and two sandwich baskets"}], "file_name": "COCO_train2014_000000246641_1966744.jpg", "ann_id": 1966744, "sent_ids": [3332], "ref_id": 6296}, {"segmentation": [[164.22, 48.46, 164.22, 39.15, 164.22, 14.6, 185.38, 6.14, 202.31, 19.68, 206.55, 31.53, 221.78, 33.23, 241.25, 44.23, 257.34, 42.54, 291.2, 52.69, 290.35, 89.94, 285.27, 98.41, 298.81, 131.42, 310.67, 165.28, 314.05, 173.74, 341.14, 246.54, 349.6, 260.93, 358.07, 288.87, 354.68, 310.88, 332.67, 316.8, 321.67, 311.72, 293.74, 322.73, 270.88, 316.8, 283.58, 307.49, 293.74, 299.87, 299.66, 290.56, 299.66, 279.56, 299.66, 255.01, 290.35, 232.15, 275.11, 200.83, 254.8, 176.28, 240.41, 157.66, 231.94, 154.27, 204.85, 117.88, 202.31, 108.56, 192.16, 98.41, 173.53, 106.87, 162.53, 111.95, 147.29, 125.49, 145.6, 151.74, 143.06, 157.66, 125.28, 154.27, 111.74, 145.81, 109.2, 139.88, 120.2, 117.88, 136.29, 106.02, 161.68, 72.16, 173.53, 62.01, 167.61, 47.62]], "area": 24208.18919999999, "iscrowd": 0, "image_id": 43543, "bbox": [109.2, 6.14, 248.87, 316.59], "category_id": 1, "id": 525602, "split": "val", "sentences": [{"tokens": ["a", "person", "snowboarding"], "raw": "A person snowboarding.", "sent_id": 3377, "sent": "a person snowboarding"}, {"tokens": ["snowboarder"], "raw": "snowboarder", "sent_id": 3378, "sent": "snowboarder"}], "file_name": "COCO_train2014_000000043543_525602.jpg", "ann_id": 525602, "sent_ids": [3377, 3378], "ref_id": 6315}, {"segmentation": [[349.26, 55.0, 364.13, 46.82, 376.02, 46.07, 388.67, 50.53, 394.61, 64.66, 394.61, 75.07, 394.61, 86.22, 390.9, 92.17, 391.64, 100.35, 398.33, 104.81, 421.38, 114.48, 431.05, 125.63, 436.25, 156.86, 432.53, 163.55, 431.79, 202.96, 432.53, 216.34, 432.53, 223.04, 426.59, 222.29, 420.64, 222.29, 416.92, 228.98, 419.89, 239.39, 426.59, 243.85, 427.33, 252.03, 429.56, 264.67, 429.56, 280.29, 429.56, 286.24, 430.3, 301.85, 429.56, 315.98, 426.59, 338.46, 423.61, 343.67, 422.12, 350.36, 422.87, 358.54, 422.87, 364.48, 418.41, 412.42, 415.43, 419.12, 418.41, 432.5, 415.43, 436.22, 413.2, 439.19, 413.95, 449.6, 413.95, 461.5, 410.97, 468.19, 408.0, 472.65, 403.54, 473.39, 392.38, 473.39, 386.43, 472.65, 384.2, 468.19, 384.2, 461.5, 385.69, 455.55, 387.92, 447.37, 388.67, 436.96, 384.95, 431.01, 384.95, 427.3, 387.92, 419.86, 387.18, 410.94, 387.18, 399.78, 387.18, 389.38, 388.67, 381.2, 388.67, 368.56, 388.67, 356.66, 388.67, 347.74, 388.67, 339.56, 388.67, 329.15, 386.43, 313.53, 383.46, 300.89, 383.46, 288.25, 380.49, 288.25, 377.51, 290.48, 368.59, 303.13, 361.9, 312.05, 353.72, 318.74, 350.0, 330.64, 348.51, 338.81, 347.77, 343.28, 345.54, 352.94, 344.05, 356.66, 343.31, 364.1, 341.08, 371.53, 340.34, 380.45, 340.34, 387.14, 340.34, 391.61, 340.34, 397.55, 340.34, 403.5, 340.34, 410.94, 338.85, 422.09, 337.36, 433.24, 335.87, 443.65, 334.39, 451.83, 334.39, 460.01, 330.67, 465.96, 318.03, 476.37, 307.62, 479.34, 293.49, 480.0, 283.83, 480.0, 282.34, 480.0, 280.11, 479.34, 280.85, 471.16, 289.77, 462.99, 297.95, 455.55, 303.16, 447.37, 308.36, 442.17, 310.59, 438.45, 310.59, 426.55, 310.59, 416.14, 310.59, 406.48, 312.08, 399.04, 312.08, 389.38, 312.08, 378.97, 312.08, 369.3, 309.85, 358.89, 306.88, 349.97, 308.36, 341.05, 313.57, 327.66, 314.31, 322.46, 315.05, 315.77, 324.72, 280.82, 326.95, 267.44, 340.34, 242.16, 345.54, 223.84, 348.51, 220.12, 350.0, 208.22, 351.49, 200.04, 351.49, 193.35, 350.74, 185.92, 345.54, 182.2, 341.82, 182.2, 335.13, 179.97, 330.67, 177.74, 321.75, 188.15, 314.31, 196.33, 303.9, 200.04, 289.77, 200.04, 273.42, 200.04, 265.98, 199.3, 253.34, 196.33, 242.93, 190.38, 239.21, 183.69, 239.21, 175.51, 238.47, 167.33, 244.42, 159.89, 251.11, 165.1, 253.34, 168.07, 261.52, 170.3, 271.19, 172.53, 287.54, 173.28, 298.7, 173.28, 312.08, 159.89, 316.54, 153.2, 323.23, 140.56, 335.87, 131.64, 347.03, 121.97, 360.41, 116.02, 361.9, 106.36, 351.49, 90.74, 351.49, 82.57, 347.03, 76.62, 347.03, 70.67, 350.0, 61.75, 350.0, 61.0]], "area": 34793.62015, "iscrowd": 0, "image_id": 436025, "bbox": [238.47, 46.07, 197.78, 433.93], "category_id": 1, "id": 1250136, "split": "val", "sentences": [{"tokens": ["a", "boy", "wearing", "a", "grey", "shirt"], "raw": "A boy wearing a grey shirt.", "sent_id": 3452, "sent": "a boy wearing a grey shirt"}, {"tokens": ["a", "man", "playing", "the", "wii", "with", "a", "woman", "in", "the", "living", "room"], "raw": "A man playing the wii with a woman in the living room.", "sent_id": 3453, "sent": "a man playing the wii with a woman in the living room"}], "file_name": "COCO_train2014_000000436025_1250136.jpg", "ann_id": 1250136, "sent_ids": [3452, 3453], "ref_id": 6343}, {"segmentation": [[337.36, 265.79, 337.36, 282.18, 337.36, 306.27, 337.36, 329.41, 332.54, 342.9, 330.61, 347.72, 294.95, 358.32, 275.67, 362.18, 254.47, 375.67, 245.79, 382.42, 244.83, 351.58, 251.57, 339.05, 253.5, 334.23, 272.78, 318.8, 275.67, 288.92, 275.67, 256.15, 282.42, 219.52, 285.31, 205.07, 287.24, 194.46, 297.84, 171.33, 316.15, 163.62, 331.58, 156.87, 336.4, 156.87, 366.28, 152.05, 367.24, 152.05, 371.09, 153.98, 375.91, 165.55, 385.55, 183.86, 394.23, 197.35, 404.83, 205.07, 407.72, 221.45, 409.65, 236.87, 409.65, 243.62, 396.16, 247.48, 374.95, 251.33, 374.95, 251.33, 347.0, 266.75, 355.67, 298.56, 357.6, 311.09, 360.49, 325.55, 398.08, 339.05, 400.01, 342.9, 420.25, 348.68, 412.54, 363.14, 410.61, 367.0, 383.63, 370.85, 386.52, 366.03, 373.99, 351.58, 354.71, 340.01, 347.96, 333.26, 343.14, 319.77, 338.32, 303.38, 338.32, 288.92]], "area": 20495.375899999988, "iscrowd": 0, "image_id": 572998, "bbox": [244.83, 152.05, 175.42, 230.37], "category_id": 1, "id": 425173, "split": "val", "sentences": [{"tokens": ["a", "baseball", "bats", "man", "hitting", "the", "ball"], "raw": "A baseball bats man hitting the ball", "sent_id": 3458, "sent": "a baseball bats man hitting the ball"}, {"tokens": ["a", "baseball", "player", "with", "number", "3", "on", "his", "uniform"], "raw": "A baseball player with number 3 on his uniform.", "sent_id": 3459, "sent": "a baseball player with number 3 on his uniform"}], "file_name": "COCO_train2014_000000572998_425173.jpg", "ann_id": 425173, "sent_ids": [3458, 3459], "ref_id": 6346}, {"segmentation": [[51.07, 355.02, 48.58, 349.42, 47.65, 345.68, 47.34, 342.25, 46.71, 340.07, 47.96, 335.4, 49.51, 329.8, 49.83, 321.39, 52.32, 315.17, 58.23, 309.87, 64.77, 307.38, 74.11, 307.69, 88.74, 315.79, 89.68, 326.69, 89.06, 333.23, 89.06, 338.21, 89.68, 342.25, 86.25, 347.86, 84.07, 351.28, 82.21, 355.33, 79.72, 358.76, 84.07, 365.61, 97.15, 372.77, 113.96, 382.73, 127.66, 396.43, 130.78, 400.48, 130.78, 406.39, 129.53, 409.82, 129.84, 412.62, 127.97, 416.35, 129.84, 417.91, 128.6, 419.78, 128.29, 422.89, 133.89, 421.02, 130.78, 427.56, 128.91, 428.5, 123.62, 429.43, 119.57, 430.05, 110.85, 435.97, 106.8, 438.77, 108.67, 446.87, 105.56, 457.14, 104.0, 465.55, 106.49, 498.24, 105.56, 512.56, 106.49, 524.39, 109.92, 528.13, 113.34, 552.1, 111.16, 560.51, 108.36, 564.24, 106.18, 567.98, 102.76, 577.32, 99.95, 591.33, 102.44, 602.23, 100.58, 606.59, 99.64, 609.08, 107.43, 616.55, 111.78, 624.65, 109.29, 629.63, 103.07, 632.12, 93.1, 632.43, 84.7, 630.25, 66.95, 629.32, 64.46, 629.32, 59.17, 636.17, 57.92, 638.03, 53.87, 640.0, 28.03, 640.0, 21.49, 640.0, 21.81, 632.74, 23.98, 615.3, 22.74, 597.56, 20.87, 591.64, 19.94, 585.1, 20.87, 574.52, 21.81, 565.18, 21.81, 546.5, 21.81, 533.73, 19.63, 529.37, 21.49, 523.77, 20.87, 517.23, 16.2, 519.41, 16.2, 527.19, 14.96, 528.75, 11.22, 528.13, 11.22, 530.93, 9.66, 534.04, 4.37, 533.42, 1.88, 529.68, 0.0, 522.52, 0.0, 497.62, 0.0, 482.36, 0.0, 476.76, 0.0, 470.84, 0.0, 408.57, 3.12, 393.0, 10.6, 379.93, 18.69, 373.39, 27.41, 369.34, 37.68, 364.98, 45.47, 360.31, 49.51, 355.64]], "area": 28939.091750000018, "iscrowd": 0, "image_id": 457225, "bbox": [0.0, 307.38, 133.89, 332.62], "category_id": 1, "id": 2206115, "split": "val", "sentences": [{"tokens": ["a", "hawaiian", "native", "with", "a", "blue", "shirt", "beside", "the", "woman"], "raw": "A hawaiian native with a blue shirt beside the woman", "sent_id": 3560, "sent": "a hawaiian native with a blue shirt beside the woman"}, {"tokens": ["a", "man", "in", "grey"], "raw": "A man in grey.", "sent_id": 3561, "sent": "a man in grey"}], "file_name": "COCO_train2014_000000457225_2206115.jpg", "ann_id": 2206115, "sent_ids": [3560, 3561], "ref_id": 6383}, {"segmentation": [[638.45, 355.56, 604.57, 397.64, 583.02, 395.59, 565.57, 378.14, 533.75, 358.64, 545.04, 320.66, 577.89, 248.81, 602.52, 225.2, 612.79, 201.59, 628.18, 209.8, 635.37, 192.36, 638.45, 192.36, 640.0, 358.64]], "area": 13484.632200000007, "iscrowd": 0, "image_id": 64092, "bbox": [533.75, 192.36, 106.25, 205.28], "category_id": 19, "id": 54591, "split": "val", "sentences": [{"tokens": ["horse", "head", "to", "the", "right"], "raw": "Horse head to the right", "sent_id": 3592, "sent": "horse head to the right"}, {"tokens": ["a", "black", "horse"], "raw": "A black horse.", "sent_id": 3593, "sent": "a black horse"}], "file_name": "COCO_train2014_000000064092_54591.jpg", "ann_id": 54591, "sent_ids": [3592, 3593], "ref_id": 6394}, {"segmentation": [[526.33, 262.6, 498.54, 320.17, 485.64, 336.05, 456.85, 343.99, 414.17, 342.0, 391.34, 331.08, 350.65, 289.4, 338.74, 271.53, 353.62, 215.95, 376.45, 199.07, 425.09, 195.1, 466.78, 196.1, 496.55, 208.01, 505.49, 220.91, 521.37, 233.81]], "area": 21526.516250000004, "iscrowd": 0, "image_id": 447574, "bbox": [338.74, 195.1, 187.59, 148.89], "category_id": 47, "id": 1505274, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "soup", "next", "to", "a", "sandwich"], "raw": "A bowl of soup next to a sandwich.", "sent_id": 3668, "sent": "a bowl of soup next to a sandwich"}, {"tokens": ["a", "white", "bowl", "of", "soup", "next", "to", "a", "sandwich", "on", "a", "white", "plate"], "raw": "A white bowl of soup next to a sandwich on a white plate.", "sent_id": 3669, "sent": "a white bowl of soup next to a sandwich on a white plate"}], "file_name": "COCO_train2014_000000447574_1505274.jpg", "ann_id": 1505274, "sent_ids": [3668, 3669], "ref_id": 6417}, {"segmentation": [[416.47, 264.62, 420.28, 180.76, 459.36, 103.56, 480.32, 96.89, 475.56, 25.41, 547.03, 23.51, 560.38, 84.5, 541.32, 103.56, 596.59, 137.87, 611.84, 201.72, 613.74, 320.85, 436.48, 287.49]], "area": 40792.6866, "iscrowd": 0, "image_id": 236961, "bbox": [416.47, 23.51, 197.27, 297.34], "category_id": 1, "id": 186379, "split": "val", "sentences": [{"tokens": ["a", "boy", "wearing", "blue", "tshirt", "standing", "near", "a", "table", "with", "his", "friends", "celebrating", "birthday", "party"], "raw": "a boy wearing blue tshirt standing near a table with his friends celebrating birthday party", "sent_id": 3734, "sent": "a boy wearing blue tshirt standing near a table with his friends celebrating birthday party"}, {"tokens": ["a", "boy", "in", "a", "blue", "shirt", "about", "to", "blow", "out", "his", "candles"], "raw": "a boy in a blue shirt about to blow out his candles", "sent_id": 3735, "sent": "a boy in a blue shirt about to blow out his candles"}], "file_name": "COCO_train2014_000000236961_186379.jpg", "ann_id": 186379, "sent_ids": [3734, 3735], "ref_id": 6445}, {"segmentation": [[49.62, 87.19, 87.37, 59.15, 115.42, 47.28, 165.03, 46.2, 193.08, 80.72, 200.63, 112.0, 197.39, 146.52, 189.84, 159.46, 135.91, 179.96, 140.22, 215.55, 112.18, 215.55, 75.51, 214.47, 46.38, 209.08, 20.49, 184.27, 23.73, 161.62, 33.44, 147.6, 26.97, 117.39, 42.07, 104.45, 50.7, 83.96]], "area": 22382.360299999993, "iscrowd": 0, "image_id": 550308, "bbox": [20.49, 46.2, 180.14, 169.35], "category_id": 54, "id": 312347, "split": "val", "sentences": [{"tokens": ["burger", "in", "a", "plate", "with", "cheese"], "raw": "BURGER IN A PLATE WITH CHEESE", "sent_id": 3856, "sent": "burger in a plate with cheese"}, {"tokens": ["first", "sandwich", "on", "the", "left", "just", "beneath", "the", "fork"], "raw": "First sandwich on the left just beneath the fork", "sent_id": 3857, "sent": "first sandwich on the left just beneath the fork"}], "file_name": "COCO_train2014_000000550308_312347.jpg", "ann_id": 312347, "sent_ids": [3856, 3857], "ref_id": 6491}, {"segmentation": [[97.04, 416.79, 114.46, 406.84, 135.61, 375.74, 129.39, 379.47, 102.02, 383.2, 114.46, 348.36, 141.83, 313.53, 144.32, 312.28, 154.28, 301.09, 154.28, 293.62, 146.81, 282.42, 113.22, 281.18, 94.56, 293.62, 88.34, 289.89, 95.8, 269.98, 111.97, 271.23, 134.37, 267.49, 140.59, 263.76, 179.16, 278.69, 181.65, 286.16, 186.62, 279.94, 191.6, 256.3, 201.55, 256.3, 206.53, 282.42, 217.73, 287.4, 225.19, 292.38, 236.39, 312.28, 247.59, 311.04, 276.2, 340.9, 296.11, 362.05, 294.86, 367.03, 261.27, 358.32, 240.12, 345.88, 240.12, 345.88, 245.1, 359.56, 247.59, 379.47, 235.15, 394.4, 235.15, 395.64, 236.39, 399.37, 210.26, 416.79, 209.02, 426.75, 207.77, 444.16, 210.26, 470.29, 32.35, 471.54, 70.92, 439.19]], "area": 25545.75565, "iscrowd": 0, "image_id": 485173, "bbox": [32.35, 256.3, 263.76, 215.24], "category_id": 20, "id": 1818720, "split": "val", "sentences": [{"tokens": ["a", "goat", "which", "is", "fully", "white"], "raw": "A goat which is fully white", "sent_id": 3864, "sent": "a goat which is fully white"}, {"tokens": ["an", "all", "white", "goat", "looking", "at", "a", "dog"], "raw": "An all white goat looking at a dog.", "sent_id": 3865, "sent": "an all white goat looking at a dog"}], "file_name": "COCO_train2014_000000485173_1818720.jpg", "ann_id": 1818720, "sent_ids": [3864, 3865], "ref_id": 6493}, {"segmentation": [[154.57, 71.72, 157.9, 98.41, 180.14, 128.43, 205.72, 150.67, 244.64, 155.12, 283.55, 141.78, 308.02, 137.33, 308.02, 151.79, 309.13, 172.91, 305.79, 182.92, 310.24, 196.26, 308.02, 214.06, 308.02, 217.39, 288.0, 227.4, 272.43, 246.3, 269.1, 268.54, 231.29, 270.77, 215.72, 279.66, 215.72, 301.9, 200.16, 264.1, 173.47, 239.63, 156.79, 228.51, 136.77, 220.73, 127.88, 209.61, 130.1, 172.91, 130.1, 157.35, 112.31, 138.44, 114.53, 117.31, 113.42, 80.62, 127.88, 87.29, 142.33, 90.63, 150.12, 76.17]], "area": 21980.7005, "iscrowd": 0, "image_id": 253335, "bbox": [112.31, 71.72, 197.93, 230.18], "category_id": 19, "id": 1832348, "split": "val", "sentences": [{"tokens": ["the", "horse", "behind", "the", "woman"], "raw": "The horse behind the woman", "sent_id": 3883, "sent": "the horse behind the woman"}, {"tokens": ["a", "dark", "borwn", "horse", "behind", "the", "woman"], "raw": "a dark borwn horse behind the woman", "sent_id": 3884, "sent": "a dark borwn horse behind the woman"}], "file_name": "COCO_train2014_000000253335_1832348.jpg", "ann_id": 1832348, "sent_ids": [3883, 3884], "ref_id": 6499}, {"segmentation": [[79.39, 447.82, 75.42, 422.02, 76.41, 403.16, 64.5, 359.48, 58.55, 348.57, 41.67, 341.62, 42.66, 306.88, 20.83, 303.9, 18.84, 292.98, 42.66, 296.95, 54.58, 283.06, 70.46, 284.05, 72.44, 291.0, 86.34, 290.01, 99.24, 298.94, 134.97, 291.99, 170.71, 280.08, 185.59, 293.98, 188.57, 325.74, 198.5, 366.43, 203.46, 387.28, 196.51, 411.1, 198.5, 420.03, 183.61, 438.89, 178.65, 426.98, 172.69, 394.22, 163.76, 381.32, 162.76, 376.36, 151.85, 381.32, 130.01, 384.3, 124.06, 389.26, 118.1, 419.04, 117.11, 435.91, 120.08, 450.8, 101.23, 440.87, 102.22, 421.02, 103.21, 405.14, 103.21, 395.22, 94.28, 397.2, 92.29, 417.05, 88.32, 431.94, 87.33, 450.8, 74.43, 453.78]], "area": 16784.952899999993, "iscrowd": 0, "image_id": 160852, "bbox": [18.84, 280.08, 184.62, 173.7], "category_id": 21, "id": 76608, "split": "val", "sentences": [{"tokens": ["the", "cow", "that", "is", "the", "smallest"], "raw": "The cow that is the smallest.", "sent_id": 3929, "sent": "the cow that is the smallest"}, {"tokens": ["the", "smallest", "brown", "cow"], "raw": "the smallest brown cow", "sent_id": 3930, "sent": "the smallest brown cow"}], "file_name": "COCO_train2014_000000160852_76608.jpg", "ann_id": 76608, "sent_ids": [3929, 3930], "ref_id": 6521}, {"segmentation": [[198.66, 324.62, 198.83, 309.76, 228.48, 275.33, 226.58, 263.52, 213.28, 262.36, 209.81, 258.89, 208.08, 256.0, 206.92, 247.91, 207.5, 239.82, 211.55, 231.15, 217.91, 228.84, 214.44, 224.21, 210.39, 223.63, 209.81, 222.48, 209.24, 220.17, 215.02, 217.28, 215.02, 212.07, 242.6, 211.33, 242.76, 224.79, 245.07, 320.74], [218.48, 211.5, 218.48, 205.72, 226.0, 205.14, 230.04, 205.14, 235.82, 207.45, 239.29, 212.07], [245.07, 227.68, 258.95, 231.15, 262.41, 236.93, 242.76, 256.0], [244.5, 266.41, 262.79, 244.13, 276.87, 257.16, 281.49, 267.57, 276.87, 273.35, 268.19, 269.88, 269.93, 273.35, 270.51, 279.7, 262.99, 305.72, 261.26, 299.36, 253.74, 301.67, 253.74, 301.67, 254.32, 311.5, 254.32, 319.59, 251.43, 321.9, 245.07, 319.01], [241.61, 325.37, 242.76, 334.62, 252.01, 336.35, 247.96, 329.42, 241.61, 323.63], [255.48, 343.29, 254.32, 328.26, 269.93, 332.88, 280.33, 349.19, 284.38, 362.94, 291.5, 371.03, 279.18, 379.13, 278.02, 371.61, 273.98, 366.41, 274.55, 362.94, 265.08, 358.64], [198.84, 325.5, 193.08, 338.13, 188.76, 353.87, 174.74, 363.58, 175.82, 370.05, 204.94, 371.52, 204.94, 361.42, 198.47, 350.63, 214.65, 331.22, 215.73, 323.67]], "area": 7083.7986, "iscrowd": 0, "image_id": 292315, "bbox": [174.74, 205.14, 116.76, 173.99], "category_id": 1, "id": 466324, "split": "val", "sentences": [{"tokens": ["base", "ball", "player", "ready", "to", "swing"], "raw": "base ball player ready to swing", "sent_id": 3942, "sent": "base ball player ready to swing"}, {"tokens": ["man", "in", "white", "and", "red", "baseball", "uniform", "batting", "at", "plate"], "raw": "Man in white and red baseball uniform batting at plate.", "sent_id": 3943, "sent": "man in white and red baseball uniform batting at plate"}], "file_name": "COCO_train2014_000000292315_466324.jpg", "ann_id": 466324, "sent_ids": [3942, 3943], "ref_id": 6528}, {"segmentation": [[302.24, 493.95, 302.24, 504.88, 273.63, 525.07, 226.52, 520.02, 218.95, 534.33, 238.3, 574.71, 255.97, 583.12, 282.89, 583.96, 339.25, 563.77, 384.68, 530.96, 393.93, 521.71, 395.61, 504.04, 395.61, 495.63, 366.17, 528.44, 326.63, 517.5, 304.76, 500.68]], "area": 8127.518199999998, "iscrowd": 0, "image_id": 183392, "bbox": [218.95, 493.95, 176.66, 90.01], "category_id": 58, "id": 1070222, "split": "val", "sentences": [{"tokens": ["the", "sausage", "under", "the", "other", "sausages", "nearest", "to", "the", "camera"], "raw": "the sausage under the other sausages nearest to the camera", "sent_id": 3966, "sent": "the sausage under the other sausages nearest to the camera"}, {"tokens": ["underneath", "sausage", "closest", "to", "red", "pepper"], "raw": "Underneath sausage closest to red pepper", "sent_id": 3967, "sent": "underneath sausage closest to red pepper"}], "file_name": "COCO_train2014_000000183392_1070222.jpg", "ann_id": 1070222, "sent_ids": [3966, 3967], "ref_id": 6537}, {"segmentation": [[271.59, 429.97, 237.82, 412.5, 212.2, 396.2, 194.74, 383.39, 191.24, 375.24, 201.72, 369.42, 240.15, 381.06, 255.29, 370.58, 263.44, 362.43, 242.48, 344.96, 226.18, 347.29, 188.91, 348.45, 149.32, 336.81, 146.99, 319.34, 157.47, 303.04, 153.98, 290.23, 149.32, 255.29, 171.45, 235.5, 198.23, 233.17, 205.22, 242.48, 202.89, 279.75, 202.89, 296.05, 223.85, 292.56, 233.16, 321.67, 221.52, 326.33, 256.45, 348.45, 270.43, 358.94, 290.23, 374.07, 298.38, 417.16, 273.92, 426.48]], "area": 11201.2731, "iscrowd": 0, "image_id": 220504, "bbox": [146.99, 233.17, 151.39, 196.8], "category_id": 1, "id": 239261, "split": "val", "sentences": [{"tokens": ["female", "child", "riding", "between", "parents", "on", "motorcycle"], "raw": "female child riding between parents on motorcycle", "sent_id": 4214, "sent": "female child riding between parents on motorcycle"}, {"tokens": ["a", "baby", "between", "two", "adults", "on", "a", "motorcycle"], "raw": "A baby between two adults on a motorcycle.", "sent_id": 4215, "sent": "a baby between two adults on a motorcycle"}], "file_name": "COCO_train2014_000000220504_239261.jpg", "ann_id": 239261, "sent_ids": [4214, 4215], "ref_id": 6625}, {"segmentation": [[638.56, 267.51, 571.69, 264.27, 569.53, 242.7, 567.37, 216.81, 596.49, 158.56, 612.67, 117.57, 639.64, 76.58], [593.26, 472.45, 625.62, 357.03, 637.48, 326.83, 640.0, 312.81, 637.48, 474.61]], "area": 12341.702849999998, "iscrowd": 0, "image_id": 229825, "bbox": [567.37, 76.58, 72.63, 398.03], "category_id": 1, "id": 1727417, "split": "val", "sentences": [{"tokens": ["person", "in", "black", "standing", "off", "to", "the", "side"], "raw": "person in black standing off to the side", "sent_id": 4262, "sent": "person in black standing off to the side"}, {"tokens": ["a", "person", "'", "s", "arm", "wearing", "a", "black", "shirt"], "raw": "a person's arm wearing a black shirt", "sent_id": 4263, "sent": "a person ' s arm wearing a black shirt"}], "file_name": "COCO_train2014_000000229825_1727417.jpg", "ann_id": 1727417, "sent_ids": [4262, 4263], "ref_id": 6643}, {"segmentation": [[314.8, 101.15, 292.8, 108.31, 287.18, 134.41, 282.57, 134.41, 275.41, 126.22, 267.22, 116.5, 253.92, 117.52, 248.29, 117.01, 234.99, 131.85, 246.76, 144.13, 256.99, 146.68, 258.53, 159.47, 266.2, 177.89, 276.94, 200.4, 284.62, 202.96, 296.38, 193.24, 300.99, 201.94, 348.06, 198.87, 365.45, 196.31, 383.36, 244.91, 387.45, 269.47, 402.8, 267.42, 404.33, 246.45, 417.12, 236.21, 416.1, 211.66, 395.12, 144.13, 384.89, 120.59, 378.24, 109.85, 357.26, 97.57, 354.71, 78.13, 354.71, 59.2, 350.1, 40.78, 329.13, 20.32, 294.34, 23.39, 289.22, 35.16, 298.94, 57.67, 292.8, 64.83, 293.31, 69.94, 308.66, 98.08]], "area": 19279.032750000006, "iscrowd": 0, "image_id": 145503, "bbox": [234.99, 20.32, 182.13, 249.15], "category_id": 1, "id": 493838, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "blue", "tank", "top"], "raw": "A woman in a blue tank top.", "sent_id": 4294, "sent": "a woman in a blue tank top"}, {"tokens": ["a", "blond", "woman", "smiles", "while", "sitting", "outdoors", "at", "a", "picknic", "table"], "raw": "A blond woman smiles while sitting outdoors at a picknic table.", "sent_id": 4295, "sent": "a blond woman smiles while sitting outdoors at a picknic table"}], "file_name": "COCO_train2014_000000145503_493838.jpg", "ann_id": 493838, "sent_ids": [4294, 4295], "ref_id": 6658}, {"segmentation": [[0.0, 195.24, 69.03, 263.19, 175.82, 390.47, 199.55, 417.44, 268.58, 406.65, 313.89, 373.21, 366.74, 334.38, 387.24, 292.31, 430.38, 242.7, 443.33, 236.22, 454.11, 257.8, 440.09, 294.47, 469.21, 311.73, 492.94, 305.26, 526.38, 282.61, 535.01, 295.55, 535.01, 322.52, 532.85, 351.64, 524.22, 367.82, 515.6, 395.87, 504.81, 415.28, 497.26, 422.83, 439.01, 436.85, 412.04, 480.0, 0.0, 480.0]], "area": 76398.28319999999, "iscrowd": 0, "image_id": 577416, "bbox": [0.0, 195.24, 535.01, 284.76], "category_id": 1, "id": 1709252, "split": "val", "sentences": [{"tokens": ["a", "hand", "of", "a", "woman", "who", "is", "about", "to", "operate", "the", "mixie"], "raw": "A hand of a woman who is about to operate the mixie", "sent_id": 4319, "sent": "a hand of a woman who is about to operate the mixie"}, {"tokens": ["the", "arm", "of", "a", "plastic", "doll"], "raw": "The arm of a plastic doll.", "sent_id": 4320, "sent": "the arm of a plastic doll"}], "file_name": "COCO_train2014_000000577416_1709252.jpg", "ann_id": 1709252, "sent_ids": [4319, 4320], "ref_id": 6666}, {"segmentation": [[60.51, 301.19, 107.27, 309.44, 143.03, 281.93, 143.03, 269.56, 99.02, 81.14, 78.39, 71.51, 11.0, 72.89, 0.0, 82.52, 0.0, 160.91, 0.0, 184.29, 5.5, 196.67, 60.51, 305.31]], "area": 24692.77365, "iscrowd": 0, "image_id": 253834, "bbox": [0.0, 71.51, 143.03, 237.93], "category_id": 47, "id": 673422, "split": "val", "sentences": [{"tokens": ["the", "glass", "of", "ice", "water"], "raw": "The glass of ice water.", "sent_id": 4329, "sent": "the glass of ice water"}, {"tokens": ["a", "cup", "of", "ice", "water", "in", "a", "clear", "cup"], "raw": "A cup of ice water in a clear cup.", "sent_id": 4330, "sent": "a cup of ice water in a clear cup"}], "file_name": "COCO_train2014_000000253834_673422.jpg", "ann_id": 673422, "sent_ids": [4329, 4330], "ref_id": 6670}, {"segmentation": [[339.33, 393.12, 302.82, 397.42, 295.3, 394.2, 311.41, 383.46, 281.34, 357.69, 279.19, 345.88, 279.19, 334.06, 314.63, 338.36, 325.37, 350.17, 330.74, 346.95, 324.3, 328.69, 268.46, 330.84, 253.42, 324.4, 260.94, 304.0, 272.75, 304.0, 270.6, 314.73, 295.3, 308.29, 311.41, 298.63, 301.74, 283.59, 303.89, 268.56, 306.04, 261.04, 318.93, 256.75, 331.81, 256.75, 338.26, 264.26, 344.7, 283.59, 365.1, 288.96, 374.77, 307.22, 386.58, 321.18, 389.8, 346.95, 391.95, 368.43, 384.43, 373.8, 380.13, 373.8, 377.99, 381.31, 371.54, 393.12, 359.73, 390.98, 357.58, 381.31, 339.33, 382.39]], "area": 10623.406799999997, "iscrowd": 0, "image_id": 292315, "bbox": [253.42, 256.75, 138.53, 140.67], "category_id": 1, "id": 497738, "split": "val", "sentences": [{"tokens": ["man", "squatting", "in", "a", "protective", "head", "gear", "between", "the", "batter", "and", "umpire"], "raw": "Man squatting in a protective head gear between the batter and umpire.", "sent_id": 4385, "sent": "man squatting in a protective head gear between the batter and umpire"}, {"tokens": ["the", "catcher"], "raw": "The catcher.", "sent_id": 4386, "sent": "the catcher"}], "file_name": "COCO_train2014_000000292315_497738.jpg", "ann_id": 497738, "sent_ids": [4385, 4386], "ref_id": 6693}, {"segmentation": [[283.33, 392.84, 270.27, 360.69, 272.28, 330.55, 277.3, 314.47, 295.38, 310.45, 310.45, 319.5, 360.69, 294.38, 384.8, 290.36, 397.86, 286.34, 433.03, 322.51, 439.06, 355.67, 440.06, 383.8, 430.01, 383.8, 421.98, 373.75, 406.91, 373.75, 369.73, 387.82, 339.59, 393.84, 324.52, 397.86]], "area": 13572.566449999998, "iscrowd": 0, "image_id": 504744, "bbox": [270.27, 286.34, 169.79, 111.52], "category_id": 55, "id": 1053579, "split": "val", "sentences": [{"tokens": ["a", "orange", "fruit", "under", "the", "banana", "in", "the", "bowl", "of", "fruits"], "raw": "A orange fruit under the banana in the bowl of fruits.", "sent_id": 4419, "sent": "a orange fruit under the banana in the bowl of fruits"}, {"tokens": ["fruit", "underneath", "banana", "in", "the", "basket"], "raw": "fruit underneath banana in the basket", "sent_id": 4420, "sent": "fruit underneath banana in the basket"}], "file_name": "COCO_train2014_000000504744_1053579.jpg", "ann_id": 1053579, "sent_ids": [4419, 4420], "ref_id": 6706}, {"segmentation": [[1.92, 47.82, 36.46, 83.32, 53.73, 135.14, 63.33, 177.36, 68.13, 207.1, 68.13, 217.66, 60.45, 234.93, 54.69, 246.44, 64.29, 261.8, 95.96, 269.47, 102.67, 263.72, 106.51, 251.24, 100.75, 240.69, 97.87, 226.29, 98.83, 210.94, 106.51, 205.18, 126.66, 168.72, 149.69, 155.29, 159.29, 69.89, 174.64, 50.7, 190.95, 43.98, 190.95, 33.42, 150.65, 26.71, 104.59, 25.75, 60.45, 29.59, 34.54, 30.55, 9.6, 39.18, 1.92, 42.06]], "area": 21472.7422, "iscrowd": 0, "image_id": 330716, "bbox": [1.92, 25.75, 189.03, 243.72], "category_id": 86, "id": 1153117, "split": "val", "sentences": [{"tokens": ["a", "floral", "vase", "to", "the", "left", "of", "a", "larger", "vase"], "raw": "a floral vase to the left of a larger vase", "sent_id": 4717, "sent": "a floral vase to the left of a larger vase"}, {"tokens": ["the", "floral", "vase", "in", "the", "back", "left", "of", "the", "picture"], "raw": "the floral vase in the back left of the picture", "sent_id": 4718, "sent": "the floral vase in the back left of the picture"}], "file_name": "COCO_train2014_000000330716_1153117.jpg", "ann_id": 1153117, "sent_ids": [4717, 4718], "ref_id": 6823}, {"segmentation": [[14.36, 192.55, 29.68, 189.68, 51.7, 184.89, 63.19, 182.02, 71.8, 178.19, 78.51, 174.36, 79.46, 164.78, 66.06, 150.42, 60.32, 130.32, 57.44, 114.04, 59.36, 92.02, 72.76, 65.21, 88.08, 52.77, 104.36, 44.15, 116.8, 38.41, 134.99, 32.66, 160.84, 35.54, 171.37, 41.28, 187.65, 51.81, 202.97, 67.13, 212.54, 90.11, 221.16, 113.08, 229.78, 133.19, 224.03, 137.98, 226.9, 159.04, 228.82, 184.89, 253.71, 225.1, 281.48, 283.5, 312.11, 360.09, 315.94, 389.77, 299.67, 411.79, 295.84, 418.5, 237.43, 419.45, 232.65, 421.37, 238.39, 403.18, 238.39, 392.65, 240.31, 379.24, 215.41, 331.37, 208.71, 326.58, 164.67, 378.28, 158.93, 383.07, 156.06, 384.99, 152.23, 387.86, 152.23, 387.86, 145.52, 421.37, 1.91, 418.5, 0.0, 205.95, 0.96, 208.82, 6.7, 202.12, 14.36, 197.34]], "area": 81567.67125, "iscrowd": 0, "image_id": 439765, "bbox": [0.0, 32.66, 315.94, 388.71], "category_id": 1, "id": 212638, "split": "val", "sentences": [{"tokens": ["man", "on", "left"], "raw": "man on left", "sent_id": 4727, "sent": "man on left"}, {"tokens": ["a", "man", "leaning", "his", "head", "on", "his", "elbow"], "raw": "a man leaning his head on his elbow", "sent_id": 4728, "sent": "a man leaning his head on his elbow"}], "file_name": "COCO_train2014_000000439765_212638.jpg", "ann_id": 212638, "sent_ids": [4727, 4728], "ref_id": 6828}, {"segmentation": [[2.06, 167.64, 47.28, 230.33, 52.42, 225.2, 45.22, 209.78, 168.57, 176.89, 176.79, 187.17, 178.84, 216.97, 195.29, 214.92, 211.73, 259.11, 271.35, 334.15, 278.54, 355.73, 358.72, 467.77, 0.0, 468.79]], "area": 72336.4545, "iscrowd": 0, "image_id": 18473, "bbox": [0.0, 167.64, 358.72, 301.15], "category_id": 63, "id": 117337, "split": "val", "sentences": [{"tokens": ["a", "sofa", "with", "pink", "and", "white", "stripes", "with", "a", "white", "/", "off", "-", "white", "pillow"], "raw": "a sofa with pink and white stripes with a white/off-white pillow", "sent_id": 4747, "sent": "a sofa with pink and white stripes with a white / off - white pillow"}, {"tokens": ["a", "pink", "and", "white", "striped", "sofa", "with", "soft", "pastel", "pillow", "and", "a", "brown", "dog", "chair", "with", "red", "floral", "rug"], "raw": "a pink and white striped sofa with soft pastel pillow and a brown dog chair with red floral rug", "sent_id": 4748, "sent": "a pink and white striped sofa with soft pastel pillow and a brown dog chair with red floral rug"}], "file_name": "COCO_train2014_000000018473_117337.jpg", "ann_id": 117337, "sent_ids": [4747, 4748], "ref_id": 6835}, {"segmentation": [[418.81, 267.51, 409.12, 272.51, 399.74, 269.38, 395.99, 258.13, 395.05, 254.38, 399.12, 245.0, 402.24, 240.94, 394.74, 222.5, 400.68, 186.86, 409.43, 151.54, 423.18, 140.6, 434.75, 132.48, 429.75, 126.85, 418.18, 119.97, 418.18, 112.78, 415.99, 99.97, 415.06, 89.03, 424.43, 69.96, 436.94, 61.83, 452.25, 60.58, 460.69, 66.52, 441.0, 79.96, 441.94, 91.84, 442.56, 104.03, 451.0, 119.03, 455.69, 129.35, 460.07, 137.79, 441.0, 171.55, 431.31, 220.62, 421.0, 223.12, 417.24, 234.37, 414.74, 250.63], [500.39, 123.72, 499.45, 113.1, 537.27, 129.97, 552.9, 150.6, 561.65, 179.67, 560.09, 205.93, 558.84, 228.12, 553.21, 233.44, 546.34, 233.44, 535.71, 235.94, 528.21, 235.62, 540.4, 213.12, 544.46, 189.99, 540.71, 169.98, 530.08, 143.42, 507.58, 127.47, 500.08, 123.72], [447.25, 218.43, 444.75, 207.18, 446.63, 198.12, 451.63, 192.18, 456.32, 191.55, 472.26, 200.3, 501.01, 200.3, 515.39, 193.43, 523.83, 185.92, 526.33, 191.86, 516.02, 220.62, 509.77, 235.94, 502.89, 255.63, 492.57, 247.81, 495.07, 225.62, 477.88, 225.62]], "area": 10934.825199999996, "iscrowd": 0, "image_id": 304408, "bbox": [394.74, 60.58, 166.91, 211.93], "category_id": 1, "id": 511262, "split": "val", "sentences": [{"tokens": ["a", "man", "carrying", "a", "young", "girl"], "raw": "A man carrying a young girl.", "sent_id": 4773, "sent": "a man carrying a young girl"}, {"tokens": ["a", "old", "man", "holding", "a", "baby", "girl", "near", "jiraffe"], "raw": "A old man holding a baby girl near jiraffe", "sent_id": 4774, "sent": "a old man holding a baby girl near jiraffe"}], "file_name": "COCO_train2014_000000304408_511262.jpg", "ann_id": 511262, "sent_ids": [4773, 4774], "ref_id": 6845}, {"segmentation": [[74.26, 158.85, 74.26, 142.71, 79.64, 121.18, 86.1, 117.96, 77.49, 97.51, 80.72, 85.67, 95.78, 84.59, 101.17, 94.28, 102.24, 119.03, 115.16, 119.03, 124.84, 133.02, 130.22, 166.39, 124.84, 176.07, 128.07, 191.14, 124.84, 213.74, 130.22, 240.65, 134.53, 269.7, 142.06, 283.7, 120.54, 290.15, 115.16, 288.0, 120.54, 277.24, 117.31, 255.71, 105.47, 210.51, 99.01, 213.74, 91.48, 241.72, 93.63, 275.09, 97.94, 293.38, 79.64, 301.99, 71.03, 299.84, 81.79, 282.62, 75.34, 233.11, 80.72, 181.45, 78.57, 177.15, 66.73, 171.77, 65.65, 159.93, 67.8, 154.55]], "area": 8151.845099999998, "iscrowd": 0, "image_id": 227946, "bbox": [65.65, 84.59, 76.41, 217.4], "category_id": 1, "id": 238407, "split": "val", "sentences": [{"tokens": ["girl", "walking", "with", "food"], "raw": "Girl walking with food.", "sent_id": 4787, "sent": "girl walking with food"}, {"tokens": ["the", "girl", "in", "blue"], "raw": "the girl in blue", "sent_id": 4788, "sent": "the girl in blue"}], "file_name": "COCO_train2014_000000227946_238407.jpg", "ann_id": 238407, "sent_ids": [4787, 4788], "ref_id": 6849}, {"segmentation": [[227.8, 204.86, 215.15, 140.88, 217.38, 136.41, 218.87, 130.83, 221.1, 126.74, 222.96, 126.0, 222.96, 124.51, 212.92, 117.07, 239.7, 96.24, 253.1, 220.48, 260.16, 288.18, 260.16, 289.67, 263.51, 289.78, 264.63, 299.45, 266.49, 304.29, 269.46, 318.42, 270.95, 339.25, 269.46, 349.3, 275.41, 408.68, 269.46, 406.82, 265.0, 406.08, 257.56, 404.59, 257.93, 401.99, 255.7, 400.5, 252.35, 370.0, 250.12, 343.58, 247.14, 316.43, 244.17, 309.36, 242.31, 308.62, 240.45, 295.23, 239.7, 285.55, 241.19, 279.97, 236.36, 250.21, 234.12, 235.71, 227.8, 205.95]], "area": 6728.592399999997, "iscrowd": 0, "image_id": 243066, "bbox": [212.92, 96.24, 62.49, 312.44], "category_id": 35, "id": 2199709, "split": "val", "sentences": [{"tokens": ["blue", "ski", "standing", "in", "the", "snow"], "raw": "Blue ski standing in the snow.", "sent_id": 4817, "sent": "blue ski standing in the snow"}, {"tokens": ["blue", "ski"], "raw": "blue ski", "sent_id": 4818, "sent": "blue ski"}, {"tokens": ["a", "set", "of", "blue", "skiis"], "raw": "A set of blue skiis.", "sent_id": 4819, "sent": "a set of blue skiis"}], "file_name": "COCO_train2014_000000243066_2199709.jpg", "ann_id": 2199709, "sent_ids": [4817, 4818, 4819], "ref_id": 6864}, {"segmentation": [[328.66, 343.34, 313.98, 426.92, 284.61, 469.84, 251.86, 466.45, 231.53, 448.38, 206.68, 449.51, 195.39, 451.76, 172.8, 451.76, 152.47, 438.21, 129.88, 420.14, 155.86, 385.13, 185.22, 354.64, 167.15, 360.28, 115.2, 365.93, 81.32, 346.73, 70.02, 323.01, 180.71, 275.58, 180.71, 277.84, 179.58, 321.88, 194.26, 330.92, 237.18, 295.91, 252.99, 298.16, 267.67, 308.33, 295.91, 298.16, 329.79, 334.31]], "area": 29427.247399999997, "iscrowd": 0, "image_id": 55873, "bbox": [70.02, 275.58, 259.77, 194.26], "category_id": 53, "id": 1047353, "split": "val", "sentences": [{"tokens": ["the", "apple", "slices", "closest", "to", "the", "green", "grapes"], "raw": "The apple slices closest to the green grapes", "sent_id": 4836, "sent": "the apple slices closest to the green grapes"}], "file_name": "COCO_train2014_000000055873_1047353.jpg", "ann_id": 1047353, "sent_ids": [4836], "ref_id": 6870}, {"segmentation": [[113.33, 407.16, 135.37, 367.28, 140.62, 308.52, 135.37, 271.79, 136.42, 262.35, 151.11, 277.04, 165.8, 288.58, 182.59, 290.68, 181.54, 279.14, 166.85, 274.94, 176.3, 270.74, 179.44, 242.41, 175.25, 215.12, 163.7, 192.04, 155.31, 190.99, 152.16, 183.64, 145.86, 168.95, 137.47, 173.15, 117.53, 164.75, 82.9, 161.6, 30.43, 165.8, 4.2, 184.69, 13.64, 207.78, 27.28, 208.83, 38.83, 214.07, 57.72, 227.72, 74.51, 227.72, 86.05, 234.01, 92.35, 243.46, 81.85, 256.05, 64.01, 281.23, 51.42, 326.36, 50.37, 359.94, 54.57, 389.32, 75.56, 413.46, 104.94, 415.56]], "area": 24130.09475, "iscrowd": 0, "image_id": 70000, "bbox": [4.2, 161.6, 178.39, 253.96], "category_id": 2, "id": 1764755, "split": "val", "sentences": [{"tokens": ["a", "white", "bike", "with", "a", "green", "helmet", "resting", "on", "the", "handlebars"], "raw": "A white bike with a green helmet resting on the handlebars.", "sent_id": 4883, "sent": "a white bike with a green helmet resting on the handlebars"}, {"tokens": ["a", "white", "bike", "on", "a", "hardwood", "floor"], "raw": "A white bike on a hardwood floor.", "sent_id": 4884, "sent": "a white bike on a hardwood floor"}], "file_name": "COCO_train2014_000000070000_1764755.jpg", "ann_id": 1764755, "sent_ids": [4883, 4884], "ref_id": 6890}, {"segmentation": [[341.18, 111.36, 391.69, 106.5, 425.77, 111.36, 456.19, 148.48, 465.32, 171.61, 462.89, 177.09, 454.98, 177.09, 465.32, 180.74, 480.54, 219.68, 483.58, 304.88, 485.4, 307.92, 485.4, 317.05, 483.58, 320.09, 471.41, 324.35, 466.54, 337.13, 456.8, 344.43, 445.85, 344.43, 442.2, 337.13, 440.37, 328.0, 350.92, 324.35, 339.97, 336.52, 333.27, 340.17, 325.36, 340.17, 321.1, 324.96, 319.28, 287.23, 318.67, 228.81, 314.41, 223.94, 310.15, 213.6, 322.32, 205.69, 334.49, 177.09, 340.57, 171.61, 331.45, 124.75]], "area": 32041.480599999995, "iscrowd": 0, "image_id": 14484, "bbox": [310.15, 106.5, 175.25, 237.93], "category_id": 3, "id": 1778292, "split": "val", "sentences": [{"tokens": ["a", "green", "vw", "van"], "raw": "A green VW van.", "sent_id": 4924, "sent": "a green vw van"}, {"tokens": ["the", "front", "of", "a", "green", "and", "white", "vw", "van"], "raw": "The front of a green and white vw van", "sent_id": 4925, "sent": "the front of a green and white vw van"}], "file_name": "COCO_train2014_000000014484_1778292.jpg", "ann_id": 1778292, "sent_ids": [4924, 4925], "ref_id": 6905}, {"segmentation": [[235.19, 169.41, 349.64, 159.5, 341.53, 113.54, 310.89, 111.74, 328.91, 100.02, 345.13, 102.73, 367.66, 165.81, 385.68, 47.76, 392.89, 91.01, 464.98, 107.23, 476.69, 101.83, 479.4, 147.78, 532.56, 136.97, 531.66, 124.36, 556.89, 121.65, 562.3, 128.86, 570.41, 139.67, 574.02, 140.58, 580.32, 137.87, 596.54, 137.87, 602.85, 160.4, 608.26, 179.32, 591.14, 255.02, 553.29, 325.31, 539.77, 355.04, 492.91, 364.96, 451.46, 350.54, 396.49, 350.54, 364.96, 346.93, 341.53, 334.32, 337.02, 328.01, 323.5, 310.89, 314.49, 276.64, 314.49, 252.31, 305.48, 242.4, 295.57, 218.97, 279.35, 248.71, 273.04, 249.61, 272.14, 238.8, 261.33, 226.18, 256.82, 232.49, 247.81, 225.28, 253.22, 213.57, 225.28, 206.36, 259.52, 189.24, 247.81, 184.73, 196.44, 195.54, 186.53, 186.53, 202.75, 175.72]], "area": 66860.04305000001, "iscrowd": 0, "image_id": 372558, "bbox": [186.53, 47.76, 421.73, 317.2], "category_id": 9, "id": 179383, "split": "val", "sentences": [{"tokens": ["a", "yellow", "boat", "with", "rx60", "on", "it"], "raw": "A yellow boat with RX60 on it.", "sent_id": 4977, "sent": "a yellow boat with rx60 on it"}, {"tokens": ["a", "large", "yellow", "boat", "with", "a", "group", "of", "black", "flags", "hanging", "over", "the", "side"], "raw": "A large yellow boat with a group of black flags hanging over the side", "sent_id": 4978, "sent": "a large yellow boat with a group of black flags hanging over the side"}], "file_name": "COCO_train2014_000000372558_179383.jpg", "ann_id": 179383, "sent_ids": [4977, 4978], "ref_id": 6926}, {"segmentation": [[478.25, 190.31, 370.91, 201.52, 375.04, 208.01, 375.63, 309.44, 401.58, 317.11, 401.58, 300.6, 409.25, 294.7, 409.25, 289.98, 472.94, 271.7, 485.32, 275.24, 488.86, 268.16, 488.86, 262.85, 485.91, 195.62], [436.38, 302.95, 434.02, 328.31, 459.38, 335.98, 466.45, 330.67, 477.07, 326.54, 497.71, 318.29]], "area": 11590.018150000002, "iscrowd": 0, "image_id": 220037, "bbox": [370.91, 190.31, 126.8, 145.67], "category_id": 15, "id": 1811709, "split": "val", "sentences": [{"tokens": ["empty", "table", "space", "at", "right", "of", "woman"], "raw": "empty table space at right of woman", "sent_id": 5009, "sent": "empty table space at right of woman"}], "file_name": "COCO_train2014_000000220037_1811709.jpg", "ann_id": 1811709, "sent_ids": [5009], "ref_id": 6941}, {"segmentation": [[345.07, 420.98, 347.96, 415.19, 360.49, 409.41, 364.35, 404.59, 365.31, 394.95, 359.53, 367.0, 357.6, 360.25, 352.78, 341.94, 352.78, 313.98, 351.82, 292.78, 351.82, 260.01, 351.82, 237.84, 350.85, 217.6, 347.96, 203.14, 347.96, 189.64, 347.96, 180.01, 356.64, 160.73, 365.31, 158.8, 375.91, 153.02, 385.55, 153.02, 388.44, 149.16, 390.37, 143.38, 400.01, 130.85, 402.9, 122.17, 404.83, 116.39, 405.79, 104.82, 389.41, 104.82, 386.52, 104.82, 379.77, 96.15, 347.0, 95.18, 327.72, 90.36, 303.62, 85.54, 293.02, 85.54, 288.2, 85.54, 284.35, 93.26, 277.6, 85.54, 248.68, 87.47, 225.55, 92.29, 213.02, 95.18, 198.56, 102.89, 192.78, 114.46, 186.99, 154.94, 172.53, 192.54, 166.75, 227.24, 163.86, 247.48, 159.04, 288.92, 161.93, 309.17, 169.64, 342.9, 163.86, 323.62, 160.0, 326.52, 153.26, 336.15, 164.82, 358.32, 174.46, 369.89, 179.28, 375.67, 195.67, 386.28, 208.2, 386.28, 227.48, 390.13, 225.55, 369.89, 221.69, 341.94, 221.69, 334.23, 246.75, 356.4, 268.92, 353.5, 268.92, 319.77, 268.92, 313.98, 284.35, 342.9, 287.24, 361.22, 288.2, 376.64, 294.95, 398.81, 302.66, 416.16, 319.05, 416.16, 341.21, 420.01]], "area": 55216.15465000001, "iscrowd": 0, "image_id": 538737, "bbox": [153.26, 85.54, 252.53, 335.44], "category_id": 23, "id": 587049, "split": "val", "sentences": [{"tokens": ["the", "polar", "bear", "is", "fighting"], "raw": "The polar bear is fighting.", "sent_id": 5104, "sent": "the polar bear is fighting"}], "file_name": "COCO_train2014_000000538737_587049.jpg", "ann_id": 587049, "sent_ids": [5104], "ref_id": 6978}, {"segmentation": [[224.17, 270.31, 219.0, 135.23, 196.85, 133.75, 144.45, 138.18, 116.4, 137.45, 74.33, 135.23, 58.09, 131.54, 42.58, 127.85, 38.9, 119.73, 42.58, 107.18, 146.67, 70.28, 181.36, 59.94, 207.19, 3.85, 226.38, 0.89, 263.28, 52.56, 361.45, 71.76, 407.95, 85.04, 410.17, 97.59, 403.53, 104.23, 388.76, 110.88, 348.91, 123.42, 285.43, 129.33, 229.33, 135.97, 235.23, 274.0, 226.38, 276.95], [224.9, 336.74, 199.81, 308.69, 210.88, 296.14, 200.55, 295.4, 265.5, 290.97, 248.52, 296.14, 254.42, 310.9, 240.41, 329.36, 237.45, 343.38, 238.93, 380.29, 228.59, 382.5]], "area": 28064.505, "iscrowd": 0, "image_id": 159957, "bbox": [38.9, 0.89, 371.27, 381.61], "category_id": 28, "id": 282227, "split": "val", "sentences": [{"tokens": ["the", "umbrella", "that", "the", "two", "people", "are", "standing", "beneath"], "raw": "The umbrella that the two people are standing beneath", "sent_id": 5123, "sent": "the umbrella that the two people are standing beneath"}, {"tokens": ["a", "beach", "umbrella", "with", "a", "white", "pole", "holding", "tote", "bags"], "raw": "A beach umbrella with a white pole holding tote bags.", "sent_id": 5124, "sent": "a beach umbrella with a white pole holding tote bags"}], "file_name": "COCO_train2014_000000159957_282227.jpg", "ann_id": 282227, "sent_ids": [5123, 5124], "ref_id": 6987}, {"segmentation": [[327.21, 412.61, 323.37, 311.85, 313.77, 271.55, 291.7, 241.81, 274.43, 200.55, 270.59, 171.76, 287.87, 126.66, 299.38, 125.7, 302.26, 154.49, 310.89, 162.16, 308.98, 119.94, 339.68, 91.16, 361.75, 56.61, 387.66, 50.86, 423.16, 53.73, 437.56, 52.78, 459.62, 49.9, 490.33, 60.45, 501.84, 93.08, 500.89, 118.98, 499.93, 144.89, 492.25, 201.51, 480.73, 215.9, 480.73, 268.67, 484.57, 286.91, 490.33, 279.23, 502.8, 295.54, 498.01, 317.61, 497.05, 330.09, 485.53, 380.94, 470.18, 381.9, 475.94, 420.28, 397.25, 420.28, 401.09, 379.02, 388.62, 312.81, 379.02, 310.89, 374.22, 341.6, 364.63, 421.24, 327.21, 419.32, 326.25, 403.97]], "area": 63161.32310000001, "iscrowd": 0, "image_id": 199485, "bbox": [270.59, 49.9, 232.21, 371.34], "category_id": 22, "id": 582004, "split": "val", "sentences": [{"tokens": ["the", "elephant", "in", "the", "front", "of", "the", "line"], "raw": "The elephant in the front of the line.", "sent_id": 5309, "sent": "the elephant in the front of the line"}, {"tokens": ["an", "elephant", "used", "for", "transport"], "raw": "an elephant used for transport", "sent_id": 5310, "sent": "an elephant used for transport"}], "file_name": "COCO_train2014_000000199485_582004.jpg", "ann_id": 582004, "sent_ids": [5309, 5310], "ref_id": 7057}, {"segmentation": [[203.55, 396.1, 206.32, 406.25, 210.01, 411.61, 215.55, 413.83, 222.39, 414.75, 229.22, 414.57, 234.03, 411.98, 237.35, 409.03, 239.2, 405.89, 240.12, 403.67, 291.1, 406.25, 318.81, 406.62, 321.58, 416.41, 325.27, 423.25, 330.26, 426.2, 334.69, 426.94, 340.79, 427.13, 345.96, 424.73, 349.29, 421.77, 351.13, 417.89, 352.98, 412.53, 354.09, 407.18, 354.83, 404.04, 355.57, 402.93, 364.8, 401.27, 415.78, 383.9, 417.08, 390.92, 418.55, 395.54, 423.54, 396.65, 430.38, 397.2, 434.99, 396.65, 437.76, 394.8, 440.53, 390.37, 442.75, 383.35, 443.49, 376.52, 443.67, 372.27, 446.08, 369.87, 452.17, 367.65, 455.68, 359.15, 461.96, 357.86, 464.73, 353.24, 464.92, 351.95, 464.18, 351.21, 462.52, 350.84, 459.56, 350.1, 457.71, 349.36, 459.19, 334.03, 457.34, 329.04, 455.87, 328.49, 436.47, 324.8, 423.36, 299.31, 425.39, 299.12, 418.0, 292.29, 413.38, 289.89, 394.91, 286.75, 367.39, 284.71, 351.69, 283.61, 321.95, 283.97, 296.09, 285.08, 285.01, 286.56, 282.05, 287.85, 277.43, 290.99, 275.77, 292.47, 257.48, 320.55, 252.87, 327.2, 252.68, 329.23, 222.2, 335.69, 205.58, 341.05, 190.43, 348.62, 184.15, 354.17, 182.86, 357.68, 181.94, 363.96, 182.12, 367.83, 183.78, 371.71, 184.89, 375.78, 180.64, 377.07, 179.17, 377.25, 178.61, 379.47, 179.17, 380.95, 183.05, 381.5, 184.34, 384.46, 186.92, 386.31, 190.43, 387.23, 193.39, 387.97, 196.34, 390.18, 201.15, 395.36]], "area": 26408.589749999992, "iscrowd": 0, "image_id": 513966, "bbox": [178.61, 283.61, 286.31, 143.52], "category_id": 3, "id": 136401, "split": "val", "sentences": [{"tokens": ["a", "white", "four", "door", "car", "in", "a", "city", "intersection"], "raw": "A white four door car in a city intersection.", "sent_id": 5375, "sent": "a white four door car in a city intersection"}, {"tokens": ["small", "white", "car"], "raw": "small white car.", "sent_id": 5376, "sent": "small white car"}], "file_name": "COCO_train2014_000000513966_136401.jpg", "ann_id": 136401, "sent_ids": [5375, 5376], "ref_id": 7084}, {"segmentation": [[312.03, 146.83, 354.08, 112.53, 427.11, 90.4, 476.9, 87.08, 496.82, 98.15, 504.56, 150.15, 505.67, 185.56, 505.67, 188.88, 474.69, 180.03, 461.41, 168.96, 448.13, 154.58, 433.75, 149.04, 345.23, 166.75, 318.67, 157.9], [255.6, 140.19, 209.13, 144.62, 184.78, 166.75, 180.36, 173.39, 173.72, 175.6, 173.72, 217.65, 180.36, 261.91, 190.32, 292.89, 192.53, 319.44, 192.53, 343.79, 194.74, 391.37, 204.7, 392.47, 204.7, 352.64, 212.45, 337.15, 211.34, 317.23, 224.62, 265.23, 231.26, 286.25, 226.83, 313.91, 224.62, 330.51, 234.58, 388.05, 250.07, 388.05, 243.43, 346.0, 263.35, 310.59, 263.35, 292.89, 277.73, 296.21, 264.45, 255.27, 260.03, 253.06, 260.03, 223.18, 252.28, 182.24, 254.49, 151.26]], "area": 26886.47285, "iscrowd": 0, "image_id": 62263, "bbox": [173.72, 87.08, 331.95, 305.39], "category_id": 24, "id": 1822662, "split": "val", "sentences": [{"tokens": ["the", "zebra", "that", "is", "behind", "the", "front", "zebra", "and", "the", "elephant"], "raw": "The zebra that is behind the front zebra and the elephant.", "sent_id": 5409, "sent": "the zebra that is behind the front zebra and the elephant"}], "file_name": "COCO_train2014_000000062263_1822662.jpg", "ann_id": 1822662, "sent_ids": [5409], "ref_id": 7098}, {"segmentation": [[367.38, 474.14, 377.02, 462.89, 399.51, 457.26, 419.6, 458.87, 444.51, 466.1, 454.95, 473.33, 460.57, 478.96, 447.72, 554.48, 434.34, 618.43, 417.08, 627.06, 379.69, 614.11, 373.93, 609.8]], "area": 12347.277999999998, "iscrowd": 0, "image_id": 327404, "bbox": [367.38, 457.26, 93.19, 169.8], "category_id": 47, "id": 683416, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "juice"], "raw": "A glass of juice.", "sent_id": 5474, "sent": "a glass of juice"}, {"tokens": ["a", "glass", "of", "juice"], "raw": "A glass of juice.", "sent_id": 5475, "sent": "a glass of juice"}], "file_name": "COCO_train2014_000000327404_683416.jpg", "ann_id": 683416, "sent_ids": [5474, 5475], "ref_id": 7119}, {"segmentation": [[233.69, 450.78, 228.69, 442.03, 233.07, 410.13, 236.2, 393.87, 240.57, 383.87, 238.07, 368.86, 246.83, 343.84, 252.45, 316.33, 274.34, 291.31, 307.49, 288.18, 329.38, 286.31, 337.51, 287.56, 366.9, 278.8, 360.02, 275.68, 359.01, 272.38, 365.26, 265.55, 374.63, 261.84, 376.77, 259.11, 374.24, 256.96, 375.6, 253.45, 383.41, 252.08, 388.49, 254.81, 397.27, 253.06, 407.22, 255.99, 411.32, 258.72, 428.88, 263.01, 434.94, 269.65, 424.98, 273.36, 413.47, 272.97, 414.05, 282.53, 411.32, 292.48, 409.17, 311.02, 406.25, 321.37, 407.22, 326.44, 408.39, 349.67, 396.68, 364.69, 390.11, 367.57, 383.88, 387.4, 384.57, 405.38, 390.48, 446.49, 377.42, 444.31, 372.52, 437.51, 374.15, 413.01, 371.43, 393.41, 370.34, 371.9, 362.72, 371.63, 367.07, 394.22, 367.89, 414.37, 367.62, 422.53, 372.24, 441.59, 367.89, 451.12, 355.64, 451.12, 355.1, 438.87, 358.09, 417.36, 353.19, 399.67, 348.29, 384.15, 346.66, 376.53, 322.97, 385.24, 321.89, 390.41, 316.17, 390.96, 314.81, 386.6, 300.93, 386.06, 295.48, 383.06, 281.6, 395.86, 279.15, 404.84, 278.6, 424.44, 280.24, 437.51, 269.62, 439.96, 262.54, 434.24, 267.99, 416.27, 266.9, 398.31, 267.72, 387.42, 270.98, 381.43, 279.15, 369.45, 272.89, 366.19, 262.0, 375.44, 247.3, 401.85, 241.58, 427.98, 244.85, 439.14, 245.67, 444.58, 233.42, 450.03]], "area": 19698.61415, "iscrowd": 0, "image_id": 38552, "bbox": [228.69, 252.08, 206.25, 199.04], "category_id": 20, "id": 65800, "split": "val", "sentences": [{"tokens": ["a", "sheep", "in", "the", "middle", "of", "two", "other", "sheep"], "raw": "A sheep in the middle of two other sheep.", "sent_id": 5497, "sent": "a sheep in the middle of two other sheep"}, {"tokens": ["a", "small", "sheep", "standing", "between", "two", "other", "sheep"], "raw": "A small sheep standing between two other sheep.", "sent_id": 5498, "sent": "a small sheep standing between two other sheep"}], "file_name": "COCO_train2014_000000038552_65800.jpg", "ann_id": 65800, "sent_ids": [5497, 5498], "ref_id": 7128}, {"segmentation": [[47.02, 263.88, 27.83, 285.95, 16.31, 330.09, 19.19, 362.71, 34.54, 391.5, 43.18, 413.57, 55.65, 418.36, 268.67, 421.24, 284.03, 418.36, 300.34, 401.09, 304.18, 359.83, 303.22, 335.84, 304.18, 309.93, 286.91, 283.07, 273.47, 261.0, 255.24, 234.13, 209.18, 223.58, 180.4, 216.86, 132.42, 219.74, 101.71, 225.49, 90.2, 231.25, 66.21, 239.89, 47.98, 261.0]], "area": 50043.95695000001, "iscrowd": 0, "image_id": 128475, "bbox": [16.31, 216.86, 287.87, 204.38], "category_id": 60, "id": 1078726, "split": "val", "sentences": [{"tokens": ["the", "foremost", "donut"], "raw": "the foremost donut", "sent_id": 5508, "sent": "the foremost donut"}, {"tokens": ["the", "donut", "in", "the", "front"], "raw": "The donut in the front.", "sent_id": 5509, "sent": "the donut in the front"}], "file_name": "COCO_train2014_000000128475_1078726.jpg", "ann_id": 1078726, "sent_ids": [5508, 5509], "ref_id": 7133}, {"segmentation": [[23.38, 44.01, 48.13, 20.63, 96.27, 20.63, 118.27, 53.64, 110.02, 75.64, 110.02, 101.77, 104.52, 116.9, 141.65, 138.9, 152.66, 166.41, 149.91, 259.93, 122.4, 259.93, 127.9, 283.31, 133.4, 317.69, 132.03, 334.19, 122.4, 356.2, 129.28, 380.95, 133.4, 400.21, 122.4, 423.59, 100.4, 451.09, 68.76, 481.35, 56.39, 514.36, 55.01, 532.23, 39.88, 539.11, 19.25, 534.98, 22.0, 431.84, 23.38, 265.43]], "area": 49468.58350000001, "iscrowd": 0, "image_id": 313873, "bbox": [19.25, 20.63, 133.41, 518.48], "category_id": 1, "id": 427212, "split": "val", "sentences": [{"tokens": ["a", "boy", "with", "a", "brown", "hat", "and", "gray", "hooded", "jacket"], "raw": "A boy with a brown hat and gray hooded jacket.", "sent_id": 5569, "sent": "a boy with a brown hat and gray hooded jacket"}, {"tokens": ["skateboarding", "teen", "wearing", "a", "brown", "beanie"], "raw": "Skateboarding teen wearing a brown beanie", "sent_id": 5570, "sent": "skateboarding teen wearing a brown beanie"}], "file_name": "COCO_train2014_000000313873_427212.jpg", "ann_id": 427212, "sent_ids": [5569, 5570], "ref_id": 7156}, {"segmentation": [[392.45, 412.08, 406.81, 412.08, 422.13, 403.46, 428.83, 394.85, 439.36, 384.32, 460.42, 371.88, 477.65, 366.13, 486.26, 356.56, 490.09, 346.99, 513.06, 330.72, 518.81, 326.89, 517.85, 322.1, 509.23, 317.31, 500.62, 310.61, 497.75, 304.87, 497.75, 295.3, 499.66, 286.68, 502.53, 280.94, 502.53, 268.5, 501.58, 262.75, 506.36, 248.4, 514.98, 245.52, 523.59, 240.74, 524.55, 238.82, 524.55, 224.47, 536.04, 200.53, 541.78, 194.79, 564.75, 192.88, 583.9, 192.88, 604.95, 198.62, 618.36, 208.19, 636.54, 220.64, 640.0, 242.65, 640.0, 270.41, 639.41, 298.17, 632.71, 311.57, 619.31, 324.01, 639.41, 332.63, 640.0, 344.12, 640.0, 361.35, 640.0, 381.45, 640.0, 403.46, 639.41, 418.78, 526.46, 420.69, 511.15, 419.74, 381.93, 420.69, 381.93, 420.69]], "area": 32872.1107, "iscrowd": 0, "image_id": 443604, "bbox": [381.93, 192.88, 258.07, 227.81], "category_id": 1, "id": 224641, "split": "val", "sentences": [{"tokens": ["a", "old", "man", "who", "wearing", "glass", "looking", "a", "young", "women"], "raw": "A old man  who wearing glass looking a young women.", "sent_id": 5624, "sent": "a old man who wearing glass looking a young women"}, {"tokens": ["an", "old", "man", "is", "sitting", "near", "a", "woman", "holding", "an", "umbrella"], "raw": "AN OLD MAN IS SITTING NEAR A WOMAN HOLDING AN UMBRELLA", "sent_id": 5625, "sent": "an old man is sitting near a woman holding an umbrella"}], "file_name": "COCO_train2014_000000443604_224641.jpg", "ann_id": 224641, "sent_ids": [5624, 5625], "ref_id": 7179}, {"segmentation": [[347.33, 156.67, 368.9, 144.81, 375.37, 127.55, 392.63, 115.69, 405.57, 111.37, 410.97, 105.98, 407.73, 96.27, 400.18, 83.33, 417.44, 64.99, 446.56, 67.15, 462.74, 91.96, 455.19, 116.76, 472.45, 125.39, 515.6, 146.97, 517.75, 155.6, 497.26, 167.46, 483.24, 167.46, 471.37, 167.46, 477.84, 206.29, 501.57, 240.81, 520.99, 273.17, 531.78, 319.55, 511.28, 349.75, 510.2, 340.04, 511.28, 324.94, 505.89, 285.03, 475.69, 260.22, 467.06, 259.15, 456.27, 239.73, 456.27, 218.16, 451.96, 199.82, 451.96, 185.8, 450.88, 164.22, 420.67, 156.67, 388.31, 164.22, 369.98, 169.62, 350.56, 169.62]], "area": 13359.30360000001, "iscrowd": 0, "image_id": 489695, "bbox": [347.33, 64.99, 184.45, 284.76], "category_id": 1, "id": 206379, "split": "val", "sentences": [{"tokens": ["a", "man", "drives", "motorcycle", "with", "a", "single", "headlight"], "raw": "A man drives motorcycle with a single headlight.", "sent_id": 5646, "sent": "a man drives motorcycle with a single headlight"}, {"tokens": ["the", "biker", "behind", "the", "first", "biker"], "raw": "the biker behind the first biker", "sent_id": 5647, "sent": "the biker behind the first biker"}], "file_name": "COCO_train2014_000000489695_206379.jpg", "ann_id": 206379, "sent_ids": [5646, 5647], "ref_id": 7189}, {"segmentation": [[90.61, 201.35, 89.17, 232.99, 103.55, 258.88, 115.06, 277.57, 128.0, 286.2, 163.96, 286.2, 399.82, 296.27, 414.2, 289.08, 427.0, 151.01, 384.0, 123.69, 355.24, 113.62, 294.83, 94.92, 266.07, 94.92, 238.74, 106.43, 227.24, 116.49, 198.47, 116.49, 172.58, 120.81, 135.19, 138.07, 113.62, 155.33, 102.11, 178.34, 94.92, 194.16]], "area": 55046.62950000001, "iscrowd": 0, "image_id": 329724, "bbox": [89.17, 94.92, 337.83, 201.35], "category_id": 59, "id": 1072122, "split": "val", "sentences": [{"tokens": ["the", "pizza", "in", "the", "opened", "box", "has", "toppings", "that", "consist", "of", "tomatoes", "and", "cheese"], "raw": "The pizza in the opened box has toppings that consist of tomatoes and cheese.", "sent_id": 5669, "sent": "the pizza in the opened box has toppings that consist of tomatoes and cheese"}, {"tokens": ["a", "pizza", "with", "sliced", "tomatoes", "as", "toppings"], "raw": "A pizza with sliced tomatoes as toppings.", "sent_id": 5670, "sent": "a pizza with sliced tomatoes as toppings"}], "file_name": "COCO_train2014_000000329724_1072122.jpg", "ann_id": 1072122, "sent_ids": [5669, 5670], "ref_id": 7197}, {"segmentation": [[116.64, 278.52, 99.2, 281.79, 90.48, 286.15, 82.85, 288.33, 80.67, 271.98, 73.04, 256.72, 69.77, 244.73, 73.04, 227.28, 75.22, 212.02, 78.49, 201.12, 77.4, 194.58, 64.32, 184.77, 47.96, 176.05, 41.42, 172.78, 37.06, 165.15, 39.24, 107.37, 38.15, 99.74, 41.42, 87.75, 51.23, 59.41, 56.68, 50.69, 62.14, 47.42, 75.22, 38.7, 89.39, 38.7, 112.28, 34.34, 112.28, 29.98, 111.19, 21.26, 114.46, 14.72, 123.18, 9.27, 132.99, 0.55, 219.11, 0.55, 220.2, 10.36, 218.02, 20.17, 216.93, 22.35, 213.66, 29.98, 208.21, 35.43, 204.94, 40.88, 201.67, 48.51, 201.67, 62.68, 200.58, 72.49, 200.58, 80.12, 203.85, 88.84, 206.03, 96.47, 210.39, 115.0, 209.3, 132.45, 204.94, 143.35, 202.76, 158.61, 202.76, 169.51, 206.03, 182.59, 212.57, 189.13, 209.3, 194.58, 201.67, 196.76, 190.77, 195.67, 184.23, 195.67, 182.05, 207.66, 184.23, 217.47, 186.41, 227.28, 182.05, 229.46, 114.46, 248.0, 115.55, 261.08, 116.64, 275.25], [92.66, 336.29, 102.47, 372.27, 109.01, 365.73, 122.09, 357.0, 130.81, 345.01, 131.9, 341.74, 122.09, 346.1, 116.64, 350.46, 107.92, 346.1, 105.74, 343.92, 99.2, 334.11, 95.93, 333.02]], "area": 35814.50629999999, "iscrowd": 0, "image_id": 151893, "bbox": [37.06, 0.55, 183.14, 371.72], "category_id": 1, "id": 205187, "split": "val", "sentences": [{"tokens": ["a", "woman", "fixing", "a", "breakfast", "plate", "from", "a", "selection", "of", "fruit", ",", "yogurts", ",", "jams", ",", "and", "granola", "on", "a", "tray", "on", "which", "a", "green", "bird", "is", "perched"], "raw": "A woman fixing a breakfast plate from a selection of fruit, yogurts, jams, and granola on a tray on which a green bird is perched.", "sent_id": 5715, "sent": "a woman fixing a breakfast plate from a selection of fruit , yogurts , jams , and granola on a tray on which a green bird is perched"}, {"tokens": ["a", "lady", "in", "a", "white", "scarf", "holding", "a", "plate", "and", "fork"], "raw": "A lady in a white scarf holding a plate and fork.", "sent_id": 5716, "sent": "a lady in a white scarf holding a plate and fork"}], "file_name": "COCO_train2014_000000151893_205187.jpg", "ann_id": 205187, "sent_ids": [5715, 5716], "ref_id": 7218}, {"segmentation": [[165.03, 120.88, 221.76, 133.3, 246.61, 132.22, 263.36, 128.44, 256.34, 123.58, 249.32, 107.91, 255.26, 106.83, 270.93, 117.09, 279.03, 118.72, 293.08, 114.39, 302.8, 112.23, 316.31, 101.43, 320.09, 106.29, 316.85, 116.01, 302.8, 126.28, 306.59, 160.86, 306.59, 174.36, 310.37, 183.55, 308.75, 199.76, 301.18, 204.08, 292.0, 199.76, 276.87, 174.36, 269.85, 183.55, 270.93, 196.52, 257.96, 217.59, 250.94, 238.66, 249.86, 255.95, 252.56, 263.51, 251.48, 277.02, 250.94, 282.42, 254.18, 299.17, 259.04, 310.52, 254.72, 319.03, 246.07, 319.53, 243.91, 316.29, 244.45, 294.68, 235.81, 295.22, 233.65, 268.74, 224.46, 222.28, 225.0, 263.88, 227.71, 284.41, 230.95, 302.78, 222.3, 303.86, 219.06, 274.14, 214.2, 254.15, 210.42, 222.28, 185.02, 220.66, 168.27, 212.55, 154.23, 233.08, 146.66, 237.95, 141.8, 254.15, 141.8, 276.85, 148.28, 295.22, 159.09, 306.56, 152.07, 312.5, 143.42, 308.72, 141.8, 300.08, 139.1, 290.89, 133.7, 295.76, 125.05, 303.32, 117.49, 292.51, 122.89, 287.11, 126.67, 278.47, 122.89, 228.76, 122.89, 219.58, 107.76, 168.79, 107.76, 157.98, 113.71, 146.1, 118.57, 136.91, 125.05, 130.43, 136.4, 122.87, 148.28, 119.08, 161.79, 121.79]], "area": 22087.974300000005, "iscrowd": 0, "image_id": 459201, "bbox": [107.76, 101.43, 212.33, 218.1], "category_id": 24, "id": 590301, "split": "val", "sentences": [{"tokens": ["two", "zebras", "standing", "side", "by", "side", "with", "another", "behind", "them"], "raw": "Two zebras standing side by side with another behind them", "sent_id": 5751, "sent": "two zebras standing side by side with another behind them"}, {"tokens": ["a", "zibra", "walking", "ahead", "of", "other", "two", "zibras"], "raw": "A zibra walking ahead of other two zibras.", "sent_id": 5752, "sent": "a zibra walking ahead of other two zibras"}], "file_name": "COCO_train2014_000000459201_590301.jpg", "ann_id": 590301, "sent_ids": [5751, 5752], "ref_id": 7236}, {"segmentation": [[449.47, 316.8, 438.21, 308.76, 430.17, 300.72, 422.13, 290.26, 419.72, 278.2, 412.48, 262.93, 406.85, 253.28, 398.01, 251.67, 391.57, 254.89, 387.55, 261.32, 379.51, 283.03, 373.89, 303.93, 370.67, 316.8, 355.39, 317.6, 348.96, 318.41, 345.74, 316.8, 345.74, 309.56, 348.96, 301.52, 350.57, 290.26, 354.59, 282.22, 364.24, 252.47, 372.28, 233.98, 373.08, 225.94, 375.49, 217.9, 377.1, 209.86, 378.71, 201.82, 380.32, 196.19, 370.67, 193.78, 362.63, 180.91, 364.24, 170.46, 365.84, 164.03, 369.86, 151.97, 375.49, 143.93, 381.12, 140.71, 401.22, 130.26, 409.26, 128.65, 412.48, 120.61, 412.48, 114.18, 414.09, 102.11, 420.52, 98.09, 429.36, 96.49, 440.62, 99.7, 443.84, 105.33, 443.84, 115.78, 443.84, 120.61, 447.86, 127.84, 451.88, 135.08, 462.33, 140.71, 471.18, 147.14, 478.41, 155.18, 484.84, 162.42, 488.06, 168.05, 489.67, 176.89, 489.67, 184.93, 482.43, 190.56, 472.78, 192.97, 464.74, 192.17, 458.31, 193.78, 454.29, 205.03, 453.49, 210.66, 452.68, 217.9, 449.47, 223.53, 445.45, 224.33, 445.45, 229.96, 449.47, 240.41, 447.05, 248.45, 447.05, 258.91, 448.66, 277.4, 459.92, 282.22, 467.16, 287.85, 472.78, 294.28, 476.0, 306.34, 476.8, 311.97, 479.22, 319.21, 478.41, 323.23, 463.94, 325.64, 455.9, 323.23]], "area": 16615.462449999995, "iscrowd": 0, "image_id": 535234, "bbox": [345.74, 96.49, 143.93, 229.15], "category_id": 1, "id": 512947, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "jacket", "and", "baseball", "cap"], "raw": "A man wearing a black jacket and baseball cap.", "sent_id": 5782, "sent": "a man wearing a black jacket and baseball cap"}, {"tokens": ["a", "baseball", "umpire", "running", "to", "cover", "a", "play"], "raw": "a baseball umpire running to cover a play", "sent_id": 5783, "sent": "a baseball umpire running to cover a play"}], "file_name": "COCO_train2014_000000535234_512947.jpg", "ann_id": 512947, "sent_ids": [5782, 5783], "ref_id": 7248}, {"segmentation": [[4.13, 144.03, 47.94, 159.75, 73.77, 188.95, 81.63, 196.81, 97.35, 185.58, 115.32, 146.27, 107.46, 82.25, 106.34, 45.19, 83.88, 15.99, 58.04, 1.39, 0.0, 1.39, 1.89, 120.44]], "area": 17110.665, "iscrowd": 0, "image_id": 311273, "bbox": [0.0, 1.39, 115.32, 195.42], "category_id": 1, "id": 1225016, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "black", "shirt", "in", "the", "background"], "raw": "A person in a black shirt in the background.", "sent_id": 5809, "sent": "a person in a black shirt in the background"}, {"tokens": ["a", "woman", "in", "the", "background", "in", "a", "black", "shirt"], "raw": "A woman in the background in a black shirt", "sent_id": 5810, "sent": "a woman in the background in a black shirt"}], "file_name": "COCO_train2014_000000311273_1225016.jpg", "ann_id": 1225016, "sent_ids": [5809, 5810], "ref_id": 7257}, {"segmentation": [[278.88, 343.17, 297.25, 344.04, 301.63, 360.67, 297.25, 369.42, 305.13, 382.54, 316.5, 449.05, 309.5, 454.3, 305.13, 452.55, 303.38, 437.68, 303.38, 423.67, 293.75, 409.67, 299.88, 442.05, 297.25, 477.05, 299.0, 517.31, 302.5, 544.44, 300.75, 547.94, 287.63, 538.31, 272.75, 521.68, 278.88, 504.18, 277.13, 477.93, 267.5, 449.93, 248.25, 480.56, 240.37, 497.18, 235.12, 503.31, 228.12, 459.55, 229.0, 454.3, 240.37, 454.3, 247.37, 450.8, 247.37, 428.92, 240.37, 400.92, 247.37, 364.17, 264.0, 344.92, 285.88, 342.29]], "area": 9289.376299999998, "iscrowd": 0, "image_id": 95809, "bbox": [228.12, 342.29, 88.38, 205.65], "category_id": 1, "id": 451595, "split": "val", "sentences": [{"tokens": ["person", "using", "skis", "and", "pole", "wearing", "a", "white", "jacket", "and", "a", "back", "pack"], "raw": "person using skis and pole wearing a white jacket and a back pack", "sent_id": 5816, "sent": "person using skis and pole wearing a white jacket and a back pack"}, {"tokens": ["a", "person", "with", "white", "overcoat", "slidding", "on", "the", "snow", "and", "two", "more", "people", "following", "him"], "raw": "A person with white overcoat slidding on the snow and two more people following him", "sent_id": 5817, "sent": "a person with white overcoat slidding on the snow and two more people following him"}], "file_name": "COCO_train2014_000000095809_451595.jpg", "ann_id": 451595, "sent_ids": [5816, 5817], "ref_id": 7260}, {"segmentation": [[1.05, 283.61, 6.33, 0.0, 640.0, 34.79, 638.92, 214.03, 624.16, 184.51, 613.61, 143.39, 591.47, 111.76, 548.25, 93.83, 521.89, 112.81, 519.78, 154.99, 542.98, 196.1, 544.03, 228.79, 535.6, 244.6, 500.8, 235.11, 463.9, 223.52, 422.78, 221.41, 403.8, 199.27, 394.32, 156.04, 361.63, 146.55, 356.36, 179.23, 354.25, 223.52, 265.69, 228.79, 189.78, 254.09, 162.37, 195.05, 154.99, 172.91, 166.58, 147.6, 163.42, 66.42, 139.17, 45.34, 75.91, 65.37, 44.28, 153.93]], "area": 101001.38200000001, "iscrowd": 0, "image_id": 230436, "bbox": [1.05, 0.0, 638.95, 283.61], "category_id": 7, "id": 1795597, "split": "val", "sentences": [{"tokens": ["the", "women", "is", "wearing", "blazer"], "raw": "the women is wearing blazer", "sent_id": 5822, "sent": "the women is wearing blazer"}, {"tokens": ["window", "on", "a", "train", "with", "a", "man", "standing", "outside"], "raw": "Window on a train with a man standing outside.", "sent_id": 5823, "sent": "window on a train with a man standing outside"}], "file_name": "COCO_train2014_000000230436_1795597.jpg", "ann_id": 1795597, "sent_ids": [5822, 5823], "ref_id": 7262}, {"segmentation": [[478.48, 57.3, 468.93, 83.09, 464.16, 100.28, 442.19, 113.65, 438.37, 122.25, 439.33, 140.39, 436.46, 160.45, 434.55, 182.42, 432.64, 203.43, 429.78, 213.93, 439.33, 223.48, 467.02, 234.94, 491.85, 233.99, 508.09, 219.66, 514.78, 180.51, 524.33, 133.71, 525.28, 121.29, 510.96, 111.74, 504.27, 106.01, 504.27, 89.78, 505.22, 61.12, 504.27, 53.48, 484.21, 52.53, 474.66, 59.21]], "area": 11640.344649999997, "iscrowd": 0, "image_id": 18819, "bbox": [429.78, 52.53, 95.5, 182.41], "category_id": 44, "id": 79239, "split": "val", "sentences": [{"tokens": ["mouthwash"], "raw": "mouthwash", "sent_id": 5984, "sent": "mouthwash"}, {"tokens": ["a", "plastic", "bottle", "of", "blue", "mouth", "wash", "on", "a", "sink", "in", "the", "bathroom"], "raw": "A plastic bottle of blue mouth wash on a sink in the bathroom.", "sent_id": 5985, "sent": "a plastic bottle of blue mouth wash on a sink in the bathroom"}], "file_name": "COCO_train2014_000000018819_79239.jpg", "ann_id": 79239, "sent_ids": [5984, 5985], "ref_id": 7324}, {"segmentation": [[380.81, 392.92, 386.08, 390.01, 390.26, 385.83, 386.99, 386.38, 385.17, 386.38, 387.53, 384.92, 388.81, 384.01, 389.35, 383.65, 391.17, 382.38, 392.08, 380.38, 394.26, 378.92, 395.17, 380.38, 396.44, 378.2, 398.26, 359.83, 397.53, 350.2, 400.44, 340.2, 400.08, 336.75, 399.9, 326.38, 398.99, 322.75, 401.35, 317.29, 401.35, 306.75, 403.71, 299.11, 407.17, 288.39, 407.9, 285.66, 408.08, 280.93, 410.26, 277.11, 413.71, 273.48, 414.8, 269.3, 415.35, 265.3, 415.53, 263.12, 414.62, 253.66, 412.99, 249.66, 410.8, 243.85, 412.26, 238.39, 410.44, 233.48, 410.44, 232.57, 406.99, 227.48, 404.26, 223.12, 401.9, 219.85, 401.35, 214.39, 398.44, 210.03, 396.26, 206.58, 394.44, 205.85, 387.72, 203.49, 383.9, 203.12, 377.53, 203.3, 368.08, 197.3, 356.26, 190.4, 342.99, 185.12, 338.45, 184.21, 333.9, 182.21, 322.81, 180.58, 322.99, 179.49, 322.99, 177.31, 325.9, 176.94, 329.36, 174.4, 333.9, 174.03, 333.9, 173.31, 331.36, 173.12, 332.81, 171.12, 336.63, 169.85, 334.81, 164.94, 336.81, 162.94, 341.9, 172.4, 345.36, 174.4, 348.45, 176.58, 374.26, 188.21, 376.63, 188.76, 381.72, 188.94, 387.72, 189.3, 395.35, 189.12, 398.26, 186.03, 404.81, 184.4, 404.81, 182.03, 405.71, 180.76, 404.81, 179.67, 403.9, 176.94, 403.9, 175.85, 401.35, 174.22, 402.26, 170.94, 402.44, 167.67, 402.44, 164.03, 402.62, 160.22, 404.81, 154.04, 408.26, 148.4, 413.53, 146.22, 421.89, 146.58, 426.8, 148.22, 431.17, 149.67, 435.53, 155.67, 440.07, 166.22, 438.07, 178.03, 436.26, 183.49, 440.98, 186.94, 442.44, 190.58, 445.71, 192.94, 452.98, 199.3, 460.98, 206.94, 463.53, 215.12, 469.71, 222.03, 476.07, 225.66, 478.25, 225.48, 478.98, 229.3, 482.98, 233.48, 492.98, 244.94, 499.16, 250.75, 503.89, 257.3, 507.34, 263.3, 509.34, 265.48, 511.7, 275.84, 508.8, 282.57, 506.25, 283.66, 506.43, 277.84, 503.34, 280.75, 502.25, 279.3, 500.61, 273.48, 498.43, 269.12, 497.52, 265.84, 495.34, 261.3, 495.34, 257.12, 492.61, 257.48, 492.07, 255.12, 471.71, 238.57, 466.25, 238.75, 455.89, 227.12, 456.8, 240.03, 454.25, 242.39, 456.07, 248.75, 461.35, 252.39, 462.8, 257.12, 463.53, 261.3, 462.8, 261.3, 464.25, 264.57, 464.07, 266.57, 462.62, 269.3, 458.07, 266.93, 460.8, 276.39, 460.25, 285.3, 460.07, 288.57, 459.71, 294.39, 457.71, 295.84, 456.25, 301.66, 452.98, 312.38, 448.62, 326.56, 448.07, 330.56, 452.62, 337.11, 455.35, 339.65, 464.44, 352.56, 467.53, 367.83, 468.8, 374.38, 472.07, 378.92, 475.16, 387.1, 463.34, 389.83, 449.53, 390.92, 457.16, 384.74, 457.16, 383.47, 455.71, 381.83, 459.16, 376.2, 452.07, 361.65, 441.89, 351.11, 432.8, 340.2, 430.44, 337.29, 430.44, 326.38, 430.08, 307.29, 430.8, 299.48, 428.08, 303.66, 421.53, 320.02, 419.53, 324.75, 419.17, 330.38, 415.53, 335.29, 416.26, 340.2, 414.99, 352.74, 410.08, 368.2, 408.99, 373.65, 408.62, 375.83, 407.9, 383.47, 412.26, 391.65]], "area": 12270.989800000005, "iscrowd": 0, "image_id": 45339, "bbox": [322.81, 146.22, 188.89, 246.7], "category_id": 1, "id": 439184, "split": "val", "sentences": [{"tokens": ["a", "lady", "playing", "a", "throw", "plate", "game"], "raw": "A LADY PLAYING A THROW PLATE GAME", "sent_id": 6086, "sent": "a lady playing a throw plate game"}, {"tokens": ["a", "woman", "throwing", "a", "frisbee"], "raw": "A woman throwing a frisbee.", "sent_id": 6087, "sent": "a woman throwing a frisbee"}], "file_name": "COCO_train2014_000000045339_439184.jpg", "ann_id": 439184, "sent_ids": [6086, 6087], "ref_id": 7359}, {"segmentation": [[433.83, 356.15, 390.87, 297.09, 399.46, 262.73, 405.91, 229.44, 425.23, 212.26, 431.68, 187.56, 470.34, 171.45, 490.74, 204.74, 508.99, 257.36, 513.29, 268.1, 480.0, 260.58, 470.34, 346.49, 441.34, 359.37]], "area": 13014.250049999999, "iscrowd": 0, "image_id": 443410, "bbox": [390.87, 171.45, 122.42, 187.92], "category_id": 1, "id": 185276, "split": "val", "sentences": [{"tokens": ["middle", "-", "aged", "dark", "brown", "or", "black", "hair", "woman", "with", "read", "dress", "and", "glasses"], "raw": "middle-aged dark brown or black hair woman with read dress and glasses", "sent_id": 6147, "sent": "middle - aged dark brown or black hair woman with read dress and glasses"}, {"tokens": ["the", "woman", "in", "the", "skirt"], "raw": "The woman in the skirt.", "sent_id": 6148, "sent": "the woman in the skirt"}], "file_name": "COCO_train2014_000000443410_185276.jpg", "ann_id": 185276, "sent_ids": [6147, 6148], "ref_id": 7381}, {"segmentation": [[69.29, 282.24, 93.84, 258.22, 83.91, 267.1, 78.69, 252.74, 63.02, 246.73, 57.28, 240.99, 59.89, 236.81, 63.55, 237.07, 70.86, 239.42, 73.47, 240.46, 75.56, 238.9, 73.99, 235.24, 68.51, 232.89, 65.64, 227.67, 67.72, 223.75, 72.42, 223.75, 80.0, 225.84, 90.7, 231.85, 95.66, 234.2, 106.11, 250.91, 106.11, 246.47, 108.98, 244.12, 111.59, 243.34, 113.68, 244.64, 114.2, 248.3, 124.65, 251.69, 133.53, 253.0, 147.89, 196.6, 166.69, 237.85, 165.91, 234.72, 169.83, 223.23, 189.67, 215.92, 200.12, 272.32, 207.17, 272.06, 203.25, 283.81, 212.65, 298.43, 208.73, 326.11, 199.07, 337.6, 199.85, 341.0, 198.81, 342.3, 195.15, 338.13, 192.02, 335.78, 162.25, 347.53, 138.23, 349.62, 119.95, 350.4, 111.07, 351.7, 97.49, 347.27, 81.04, 333.43, 71.9, 301.05, 72.42, 292.69, 59.11, 296.87, 57.28, 292.17, 63.02, 287.73, 69.81, 283.29]], "area": 14882.190049999997, "iscrowd": 0, "image_id": 372558, "bbox": [57.28, 196.6, 155.37, 155.1], "category_id": 9, "id": 181598, "split": "val", "sentences": [{"tokens": ["small", "brown", "colored", "boat", "is", "on", "the", "shore", "is", "shown", "in", "the", "image"], "raw": "small brown colored boat is on the shore is shown in the image.", "sent_id": 6155, "sent": "small brown colored boat is on the shore is shown in the image"}, {"tokens": ["a", "small", "red", "boat", "with", "the", "marking", "rx55"], "raw": "a small red boat with the marking rx55", "sent_id": 6156, "sent": "a small red boat with the marking rx55"}], "file_name": "COCO_train2014_000000372558_181598.jpg", "ann_id": 181598, "sent_ids": [6155, 6156], "ref_id": 7384}, {"segmentation": [[352.36, 343.45, 348.83, 338.16, 281.17, 360.51, 272.35, 375.0, 285.29, 375.0, 295.29, 360.51, 326.47, 364.63, 323.53, 368.16, 330.0, 368.16, 325.3, 360.51, 339.41, 348.16], [399.42, 323.45, 399.42, 326.98, 412.95, 343.45, 419.42, 341.69, 420.6, 335.21, 414.71, 316.98, 398.24, 321.1], [461.77, 304.62, 467.66, 321.1, 474.72, 309.33, 476.48, 300.51, 481.78, 294.62, 461.77, 301.1]], "area": 1400.58915, "iscrowd": 0, "image_id": 311706, "bbox": [272.35, 294.62, 209.43, 80.38], "category_id": 67, "id": 1966206, "split": "val", "sentences": [{"tokens": ["the", "table", "that", "the", "laptop", "is", "sitting", "on"], "raw": "The table that the laptop is sitting on", "sent_id": 6236, "sent": "the table that the laptop is sitting on"}, {"tokens": ["the", "table", "with", "computers", "on", "it"], "raw": "the table with computers on it", "sent_id": 6237, "sent": "the table with computers on it"}], "file_name": "COCO_train2014_000000311706_1966206.jpg", "ann_id": 1966206, "sent_ids": [6236, 6237], "ref_id": 7414}, {"segmentation": [[7.11, 213.19, 6.32, 24.48, 285.05, 18.95, 285.05, 228.2]], "area": 55381.225999999995, "iscrowd": 0, "image_id": 124169, "bbox": [6.32, 18.95, 278.73, 209.25], "category_id": 72, "id": 1969209, "split": "val", "sentences": [{"tokens": ["left", "side", "monitor"], "raw": "left side monitor", "sent_id": 6239, "sent": "left side monitor"}, {"tokens": ["the", "monitor", "on", "the", "left"], "raw": "the monitor on the left", "sent_id": 6240, "sent": "the monitor on the left"}], "file_name": "COCO_train2014_000000124169_1969209.jpg", "ann_id": 1969209, "sent_ids": [6239, 6240], "ref_id": 7416}, {"segmentation": [[637.73, 418.9, 616.65, 417.79, 605.56, 417.79, 616.65, 383.41, 616.65, 368.99, 616.65, 300.22, 605.56, 301.33, 592.25, 292.46, 588.93, 218.15, 577.84, 218.15, 605.56, 130.53, 626.64, 127.21, 640.0, 123.88, 638.84, 420.01]], "area": 11117.998650000012, "iscrowd": 0, "image_id": 376241, "bbox": [577.84, 123.88, 62.16, 296.13], "category_id": 1, "id": 2156945, "split": "val", "sentences": [{"tokens": ["the", "arm", "and", "the", "brown", "shirt", "of", "the", "person", "standing", "on", "far", "right"], "raw": "the arm and the brown shirt of the person standing on far right", "sent_id": 6263, "sent": "the arm and the brown shirt of the person standing on far right"}, {"tokens": ["partial", "view", "of", "a", "man", "in", "brown", "shirt"], "raw": "partial view of a man in brown shirt", "sent_id": 6264, "sent": "partial view of a man in brown shirt"}], "file_name": "COCO_train2014_000000376241_2156945.jpg", "ann_id": 2156945, "sent_ids": [6263, 6264], "ref_id": 7425}, {"segmentation": [[72.1, 340.85, 72.1, 328.83, 71.01, 308.08, 73.2, 293.88, 77.57, 285.14, 90.68, 270.93, 102.69, 265.47, 122.36, 266.56, 133.28, 269.84, 154.04, 269.84, 163.87, 276.4, 181.35, 289.51, 184.63, 309.17, 189.0, 321.19, 189.0, 331.02, 189.0, 336.48, 184.63, 338.67, 181.35, 341.94, 175.89, 344.13, 171.52, 344.13, 166.06, 341.94, 158.41, 337.57, 143.11, 332.11, 122.36, 327.74, 107.06, 327.74, 102.69, 338.67, 99.42, 353.96, 96.14, 365.98, 96.14, 380.18, 96.14, 396.57, 101.6, 406.4, 102.69, 410.77, 90.68, 410.77, 87.4, 383.46, 75.38, 380.18, 78.66, 415.14, 68.83, 415.14, 63.36, 397.66, 62.27, 382.37, 63.36, 370.35, 75.38, 348.5, 89.58, 327.74, 88.49, 292.78, 83.03, 325.56, 71.01, 346.31], [192.28, 337.57, 193.37, 346.31, 194.46, 379.09, 194.46, 391.11, 195.55, 409.68, 205.38, 407.49, 206.48, 369.26, 207.57, 335.39, 211.94, 327.74, 223.96, 306.98, 242.53, 285.14, 254.55, 291.69, 256.73, 299.34, 267.66, 301.52, 276.4, 293.88, 270.93, 253.45, 276.4, 233.79, 262.19, 243.62, 254.55, 234.88, 249.08, 243.62, 210.85, 256.73, 199.92, 266.56, 201.02, 277.49, 201.02, 296.06, 205.38, 327.74]], "area": 13741.5209, "iscrowd": 0, "image_id": 493760, "bbox": [62.27, 233.79, 214.13, 181.35], "category_id": 19, "id": 55487, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "horse", "with", "a", "green", "leg", "wrap"], "raw": "A dark brown horse with a green leg wrap.", "sent_id": 6291, "sent": "a dark brown horse with a green leg wrap"}, {"tokens": ["a", "brown", "horse", "with", "a", "green", "saddle"], "raw": "A brown horse with a green saddle.", "sent_id": 6292, "sent": "a brown horse with a green saddle"}], "file_name": "COCO_train2014_000000493760_55487.jpg", "ann_id": 55487, "sent_ids": [6291, 6292], "ref_id": 7436}, {"segmentation": [[433.78, 422.16, 422.16, 394.08, 377.62, 383.43, 318.56, 379.56, 302.1, 342.76, 279.83, 286.6, 241.1, 200.43, 225.6, 184.94, 294.35, 139.43, 313.71, 133.62, 309.84, 110.38, 298.22, 108.44, 294.35, 80.37, 295.32, 49.38, 314.68, 9.68, 334.05, 7.75, 369.87, 5.81, 398.92, 15.49, 410.54, 46.48, 411.51, 88.11, 398.92, 98.76, 395.05, 135.56, 399.89, 146.21, 419.25, 161.7, 433.78, 185.9, 438.62, 216.89, 441.52, 240.13, 437.65, 265.3, 420.22, 274.02, 420.22, 282.73, 434.75, 277.89, 458.95, 274.98, 472.51, 300.16, 464.76, 315.65, 457.02, 325.33, 453.14, 351.48, 508.33, 358.25, 522.86, 367.94, 528.67, 396.98, 518.98, 417.32, 508.33, 418.29, 437.65, 420.22], [209.14, 319.52, 172.35, 374.71, 175.25, 394.08, 214.95, 394.08, 236.25, 393.11, 241.1, 381.49, 230.44, 358.25]], "area": 63159.44775, "iscrowd": 0, "image_id": 439765, "bbox": [172.35, 5.81, 356.32, 416.35], "category_id": 1, "id": 206583, "split": "val", "sentences": [{"tokens": ["a", "smiling", "man", "in", "a", "blue", "shirt"], "raw": "A smiling man in a blue shirt.", "sent_id": 6316, "sent": "a smiling man in a blue shirt"}, {"tokens": ["the", "man", "holding", "the", "other", "man", "'", "s", "tie"], "raw": "the man holding the other man's tie", "sent_id": 6317, "sent": "the man holding the other man ' s tie"}], "file_name": "COCO_train2014_000000439765_206583.jpg", "ann_id": 206583, "sent_ids": [6316, 6317], "ref_id": 7448}, {"segmentation": [[207.1, 464.54, 267.51, 509.12, 276.13, 496.18, 251.69, 468.85, 256.0, 448.72, 291.96, 389.75, 306.34, 365.3, 267.51, 323.6, 240.18, 300.58, 254.56, 299.15, 274.7, 281.89, 294.83, 254.56, 304.9, 230.11, 304.9, 218.61, 323.6, 225.8, 333.66, 214.29, 336.54, 188.4, 349.48, 185.53, 350.92, 179.78, 337.98, 172.58, 325.03, 153.89, 294.83, 156.76, 279.01, 169.71, 270.38, 192.72, 231.55, 192.72, 218.61, 199.91, 192.72, 211.42, 178.34, 215.73, 165.39, 221.48, 174.02, 240.18, 182.65, 240.18, 162.52, 257.44, 145.26, 293.39, 142.38, 350.92, 136.63, 401.26, 133.75, 419.96, 106.43, 467.42, 97.8, 506.25, 71.91, 532.13, 84.85, 547.96, 116.49, 562.34, 152.45, 566.65, 148.13, 552.27, 126.56, 537.89, 123.69, 517.75, 129.44, 488.99, 149.57, 463.1, 165.39, 428.58, 194.16, 412.76, 202.79, 391.19, 209.98, 369.62, 209.98, 362.43, 247.37, 378.25, 256.0, 384.0, 237.3, 421.39, 221.48, 440.09, 201.35, 453.03, 202.79, 471.73]], "area": 39430.78915, "iscrowd": 0, "image_id": 480451, "bbox": [71.91, 153.89, 279.01, 412.76], "category_id": 1, "id": 429205, "split": "val", "sentences": [{"tokens": ["a", "man", "was", "playing"], "raw": "a man was playing", "sent_id": 6346, "sent": "a man was playing"}, {"tokens": ["tennis", "player"], "raw": "tennis player", "sent_id": 6347, "sent": "tennis player"}], "file_name": "COCO_train2014_000000480451_429205.jpg", "ann_id": 429205, "sent_ids": [6346, 6347], "ref_id": 7458}, {"segmentation": [[279.19, 295.41, 271.68, 265.34, 262.01, 258.9, 264.16, 244.94, 263.09, 222.39, 270.6, 207.35, 283.49, 190.17, 284.56, 185.88, 281.34, 172.99, 281.34, 163.33, 284.56, 152.59, 293.15, 149.37, 309.26, 152.59, 311.41, 164.4, 315.7, 175.14, 315.7, 188.02, 332.89, 214.87, 338.26, 228.83, 336.11, 243.86, 318.93, 236.35, 324.3, 250.31, 345.77, 250.31, 351.14, 263.19, 351.14, 275.0, 336.11, 291.11, 322.15, 301.85, 316.78, 329.77, 316.78, 342.65, 306.04, 343.73, 298.52, 329.77, 266.31, 312.59, 271.68, 297.55]], "area": 9949.800449999999, "iscrowd": 0, "image_id": 227946, "bbox": [262.01, 149.37, 89.13, 194.36], "category_id": 1, "id": 239930, "split": "val", "sentences": [{"tokens": ["boy", "with", "banian", "and", "short", "eating", "with", "left", "hand", "before", "a", "dog"], "raw": "boy with banian and short eating with left hand before a dog", "sent_id": 6420, "sent": "boy with banian and short eating with left hand before a dog"}, {"tokens": ["a", "boy", "wearing", "a", "blue", "shirt", "who", "is", "putting", "food", "in", "his", "mouth"], "raw": "A boy wearing a blue shirt who is putting food in his mouth.", "sent_id": 6421, "sent": "a boy wearing a blue shirt who is putting food in his mouth"}], "file_name": "COCO_train2014_000000227946_239930.jpg", "ann_id": 239930, "sent_ids": [6420, 6421], "ref_id": 7490}, {"segmentation": [[289.61, 84.42, 259.74, 259.74, 262.34, 275.32, 281.82, 274.03, 302.6, 84.42, 289.61, 77.92, 289.61, 77.92]], "area": 3576.114599999999, "iscrowd": 0, "image_id": 243066, "bbox": [259.74, 77.92, 42.86, 197.4], "category_id": 35, "id": 2199785, "split": "val", "sentences": [{"tokens": ["the", "ski", "that", "is", "propped", "up", "on", "the", "right"], "raw": "The ski that is propped up on the right.", "sent_id": 6444, "sent": "the ski that is propped up on the right"}, {"tokens": ["neon", "green", "skis"], "raw": "neon green skis", "sent_id": 6445, "sent": "neon green skis"}], "file_name": "COCO_train2014_000000243066_2199785.jpg", "ann_id": 2199785, "sent_ids": [6444, 6445], "ref_id": 7502}, {"segmentation": [[225.71, 341.92, 211.89, 352.66, 204.98, 341.92, 200.37, 332.7, 178.88, 330.4, 177.34, 339.61, 145.87, 345.75, 143.56, 332.7, 110.55, 336.54, 110.55, 344.22, 108.25, 348.83, 102.87, 351.13, 96.73, 349.59, 91.36, 343.45, 91.36, 338.85, 82.91, 339.61, 70.63, 341.92, 69.09, 361.88, 65.26, 371.86, 55.28, 372.62, 48.37, 371.09, 46.06, 365.72, 42.99, 354.2, 42.22, 350.36, 36.85, 345.75, 36.85, 342.68, 36.08, 330.4, 19.96, 314.28, 16.12, 313.51, 13.05, 309.67, 9.21, 297.39, 3.84, 288.94, 3.84, 282.03, 3.07, 277.43, 6.91, 265.15, 6.98, 246.73, 5.97, 240.15, 5.46, 230.52, 6.47, 224.44, 6.47, 213.3, 6.47, 205.2, 5.97, 191.01, 5.97, 181.9, 4.95, 177.85, 4.95, 174.81, 21.16, 145.43, 39.4, 145.94, 194.39, 157.59, 195.4, 180.38, 195.4, 215.83, 199.96, 223.94, 202.49, 228.5, 203.0, 230.02, 211.1, 230.52, 217.18, 230.52, 216.17, 223.43, 223.76, 223.43, 226.8, 230.02, 225.79, 238.63, 224.27, 244.2, 218.7, 244.7, 213.63, 244.7, 209.58, 242.17, 231.36, 261.42, 232.88, 274.59, 233.39, 295.35, 229.34, 297.89, 232.88, 303.96, 234.4, 313.08, 230.55, 325.6, 225.59, 333.85, 226.69, 341.56, 226.14, 341.56]], "area": 39601.325650000006, "iscrowd": 0, "image_id": 277188, "bbox": [3.07, 145.43, 231.33, 227.19], "category_id": 8, "id": 394146, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "yellow", "ambulance", "on", "the", "far", "left"], "raw": "A white and yellow ambulance on the far left.", "sent_id": 6449, "sent": "a white and yellow ambulance on the far left"}, {"tokens": ["the", "vehicle", "on", "the", "left", "of", "the", "row"], "raw": "The vehicle on the left of the row.", "sent_id": 6450, "sent": "the vehicle on the left of the row"}], "file_name": "COCO_train2014_000000277188_394146.jpg", "ann_id": 394146, "sent_ids": [6449, 6450], "ref_id": 7504}, {"segmentation": [[118.66, 125.76, 126.57, 52.93, 333.96, 59.26, 308.65, 152.67, 112.32, 147.93]], "area": 18982.51485, "iscrowd": 0, "image_id": 404905, "bbox": [112.32, 52.93, 221.64, 99.74], "category_id": 62, "id": 1940433, "split": "val", "sentences": [{"tokens": ["a", "white", "chair", "near", "table"], "raw": "a white chair near table", "sent_id": 6451, "sent": "a white chair near table"}, {"tokens": ["white", "chair", "at", "table"], "raw": "White chair at table.", "sent_id": 6452, "sent": "white chair at table"}], "file_name": "COCO_train2014_000000404905_1940433.jpg", "ann_id": 1940433, "sent_ids": [6451, 6452], "ref_id": 7505}, {"segmentation": [[0.43, 290.54, 3.55, 287.98, 4.69, 283.44, 47.29, 287.13, 49.56, 293.94, 55.53, 299.06, 68.02, 301.61, 79.67, 297.92, 84.78, 287.7, 95.57, 287.7, 110.91, 288.83, 129.94, 286.28, 130.51, 276.62, 93.87, 274.06, 95.01, 246.51, 96.99, 217.54, 97.28, 191.98, 70.3, 191.13, 33.37, 190.85, 25.42, 191.13, 25.42, 189.14, 5.26, 191.41, 0.0, 191.41]], "area": 9957.663549999996, "iscrowd": 0, "image_id": 466949, "bbox": [0.0, 189.14, 130.51, 112.47], "category_id": 3, "id": 138061, "split": "val", "sentences": [{"tokens": ["a", "van", "standing", "behind", "the", "yellow", "vehicle"], "raw": "A van standing behind the yellow vehicle", "sent_id": 6496, "sent": "a van standing behind the yellow vehicle"}, {"tokens": ["a", "van", "parked", "behind", "a", "yellow", "school", "bus"], "raw": "A van parked behind a yellow school bus.", "sent_id": 6497, "sent": "a van parked behind a yellow school bus"}], "file_name": "COCO_train2014_000000466949_138061.jpg", "ann_id": 138061, "sent_ids": [6496, 6497], "ref_id": 7523}, {"segmentation": [[2.15, 301.99, 15.07, 292.3, 39.82, 285.85, 32.29, 235.26, 40.9, 206.21, 71.03, 195.44, 92.56, 208.36, 105.47, 227.73, 103.32, 268.63, 109.5, 288.79, 119.68, 290.82, 126.81, 296.93, 131.9, 311.69, 136.99, 319.33, 126.81, 334.6, 126.3, 339.69, 120.19, 362.09, 122.23, 366.68, 114.08, 369.73, 89.64, 378.39, 81.5, 373.8, 75.9, 379.91, 68.77, 376.35, 64.7, 378.39, 58.08, 378.39, 59.61, 382.46, 49.94, 386.53, 27.54, 390.6, 21.43, 396.71, 14.81, 399.26, 30.08, 415.18, 85.06, 454.89, 93.72, 463.04, 87.1, 477.43, 77.43, 478.96, 50.95, 479.47, 20.92, 480.0, 10.23, 465.22, 2.08, 449.94, 1.06, 369.51, 0.04, 323.18, 0.0, 305.59]], "area": 21932.288249999998, "iscrowd": 0, "image_id": 220037, "bbox": [0.0, 195.44, 136.99, 284.56], "category_id": 1, "id": 535782, "split": "val", "sentences": [{"tokens": ["a", "girl", "sitting", "the", "sofa", "front", "of", "the", "table", "is", "cooldrinks"], "raw": "A GIRL SITTING THE SOFA FRONT OF THE TABLE IS COOLDRINKS", "sent_id": 6513, "sent": "a girl sitting the sofa front of the table is cooldrinks"}, {"tokens": ["a", "young", "girl", "in", "a", "white", "shirt", "sitting", "at", "a", "brown", "table", "with", "salt", ",", "pepper", ",", "and", "silverware", "on", "top"], "raw": "A young girl in a white shirt sitting at a brown table with salt, pepper, and silverware on top.", "sent_id": 6514, "sent": "a young girl in a white shirt sitting at a brown table with salt , pepper , and silverware on top"}], "file_name": "COCO_train2014_000000220037_535782.jpg", "ann_id": 535782, "sent_ids": [6513, 6514], "ref_id": 7530}, {"segmentation": [[49.62, 59.33, 4.31, 162.88, 2.16, 102.47, 23.73, 59.33, 43.15, 59.33], [2.16, 206.02, 0.0, 364.58, 31.28, 271.82, 69.03, 247.01, 96.0, 237.3, 40.99, 230.83, 20.49, 224.36, 3.24, 211.42], [483.24, 73.35, 502.65, 71.19, 572.76, 136.99, 536.09, 128.36, 484.31, 75.51]], "area": 7696.119499999995, "iscrowd": 0, "image_id": 568840, "bbox": [0.0, 59.33, 572.76, 305.25], "category_id": 67, "id": 1623216, "split": "val", "sentences": [{"tokens": ["the", "table", "holding", "the", "trays", "of", "food", "and", "coffee"], "raw": "The table holding the trays of food and coffee", "sent_id": 6625, "sent": "the table holding the trays of food and coffee"}], "file_name": "COCO_train2014_000000568840_1623216.jpg", "ann_id": 1623216, "sent_ids": [6625], "ref_id": 7576}, {"segmentation": [[194.29, 301.45, 194.29, 265.07, 175.69, 264.26, 174.88, 258.6, 132.84, 268.31, 116.67, 324.9, 52.81, 322.47, 45.53, 341.88, 39.06, 361.28, 51.19, 365.32, 85.95, 364.51, 108.59, 362.09, 132.84, 350.77, 144.16, 341.88, 157.1, 336.22, 172.46, 332.98, 196.71, 303.88]], "area": 8026.69505, "iscrowd": 0, "image_id": 484369, "bbox": [39.06, 258.6, 157.65, 106.72], "category_id": 64, "id": 2128073, "split": "val", "sentences": [{"tokens": ["red", "flowers", "to", "the", "left", "of", "a", "blue", "teddy", "bear"], "raw": "Red flowers to the left of a blue teddy bear", "sent_id": 6642, "sent": "red flowers to the left of a blue teddy bear"}, {"tokens": ["red", "and", "purple", "wild", "flowers", "surrounded", "by", "greenery"], "raw": "RED AND PURPLE WILD FLOWERS SURROUNDED BY GREENERY", "sent_id": 6643, "sent": "red and purple wild flowers surrounded by greenery"}], "file_name": "COCO_train2014_000000484369_2128073.jpg", "ann_id": 2128073, "sent_ids": [6642, 6643], "ref_id": 7582}, {"segmentation": [[257.89, 305.15, 262.23, 308.87, 262.85, 317.54, 288.86, 340.46, 290.72, 347.27, 292.58, 354.71, 293.2, 356.57, 297.54, 362.14, 303.11, 366.48, 305.59, 372.05, 313.64, 374.53, 317.36, 372.05, 317.36, 359.66, 317.36, 354.71, 314.26, 348.51, 311.78, 345.42, 307.45, 342.32, 303.11, 337.36, 296.92, 326.83, 295.06, 323.74, 288.86, 315.06, 286.39, 309.49, 285.15, 300.2, 285.15, 288.43, 280.81, 251.88, 280.81, 248.17, 278.33, 224.63, 278.95, 209.14, 280.19, 204.19, 282.67, 192.42, 282.67, 181.89, 268.42, 171.98, 254.17, 173.83, 247.36, 185.6, 246.12, 199.85, 242.41, 207.28, 239.93, 208.52, 236.21, 208.52, 223.2, 210.38, 217.01, 210.38, 200.9, 201.09, 197.19, 201.09, 190.99, 201.09, 184.8, 204.19, 201.52, 227.1, 203.38, 228.96, 212.67, 237.02, 221.96, 245.69, 233.11, 240.73, 238.07, 237.02, 239.31, 245.07, 237.45, 251.88, 236.21, 265.51, 225.68, 298.96, 225.68, 305.15, 225.06, 318.78, 225.68, 337.98, 227.54, 345.42, 221.96, 347.27, 218.87, 347.27, 215.15, 351.61, 215.15, 359.66, 236.21, 360.9, 241.79, 360.9, 242.41, 357.8, 244.26, 337.36, 243.64, 318.78, 242.41, 315.06, 251.7, 305.15, 254.79, 300.2, 259.75, 304.53]], "area": 9670.845449999999, "iscrowd": 0, "image_id": 95018, "bbox": [184.8, 171.98, 132.56, 202.55], "category_id": 1, "id": 503465, "split": "val", "sentences": [{"tokens": ["a", "child", "with", "a", "black", "shirt", "and", "blue", "helmet", "playing", "baseball"], "raw": "a child with a black shirt and blue helmet playing baseball", "sent_id": 6654, "sent": "a child with a black shirt and blue helmet playing baseball"}, {"tokens": ["a", "child", "swinging", "a", "baseball", "bat"], "raw": "A child swinging a baseball bat.", "sent_id": 6655, "sent": "a child swinging a baseball bat"}], "file_name": "COCO_train2014_000000095018_503465.jpg", "ann_id": 503465, "sent_ids": [6654, 6655], "ref_id": 7585}, {"segmentation": [[325.02, 278.74, 340.09, 286.28, 348.7, 292.74, 350.85, 295.96, 354.08, 307.8, 344.39, 368.07, 353.0, 375.61, 361.61, 377.76, 373.45, 377.76, 378.83, 374.53, 380.99, 369.15, 382.06, 363.77, 372.38, 358.39, 387.44, 346.55, 402.51, 342.24, 407.89, 342.24, 418.65, 342.24, 428.34, 342.24, 442.33, 359.46, 445.56, 364.84, 448.79, 365.92, 452.02, 365.92, 455.25, 365.92, 467.09, 363.77, 469.24, 363.77, 476.77, 355.16, 471.39, 347.62, 468.16, 340.09, 459.55, 326.1, 462.78, 318.57, 468.16, 308.88, 471.39, 301.35, 471.39, 297.04, 469.24, 288.43, 456.32, 271.21, 432.65, 266.91, 417.58, 269.06, 399.28, 263.68, 394.98, 251.84, 394.98, 247.53, 386.37, 233.54, 372.38, 222.78, 363.77, 220.63, 343.32, 220.63, 331.48, 214.17, 313.18, 208.79, 311.03, 203.41, 307.8, 199.1, 297.04, 193.72, 291.66, 193.72, 285.2, 193.72, 275.52, 200.18, 275.52, 204.48, 280.9, 219.55, 284.13, 263.68, 283.05, 294.89, 281.97, 302.42, 288.43, 303.5, 294.89, 306.73, 306.73, 303.5, 313.18, 299.19, 314.26, 294.89, 303.5, 286.28, 306.73, 281.97]], "area": 18190.66855, "iscrowd": 0, "image_id": 32818, "bbox": [275.52, 193.72, 201.25, 184.04], "category_id": 15, "id": 573026, "split": "val", "sentences": [{"tokens": ["the", "bench", "closest", "to", "the", "palm", "tree", "and", "on", "a", "concrete", "pedestal"], "raw": "The bench closest to the palm tree and on a concrete pedestal.", "sent_id": 6685, "sent": "the bench closest to the palm tree and on a concrete pedestal"}, {"tokens": ["a", "bench", "in", "the", "shore", "near", "another", "bench"], "raw": "a bench in the shore near another bench", "sent_id": 6686, "sent": "a bench in the shore near another bench"}], "file_name": "COCO_train2014_000000032818_573026.jpg", "ann_id": 573026, "sent_ids": [6685, 6686], "ref_id": 7597}, {"segmentation": [[320.08, 179.98, 320.43, 187.71, 313.76, 191.92, 315.16, 206.66, 312.35, 215.44, 317.27, 225.62, 333.41, 257.21, 354.83, 259.32, 360.09, 259.32, 363.95, 253.35, 367.82, 240.71, 368.52, 237.9, 369.22, 232.99, 368.87, 230.88, 367.82, 227.02, 354.83, 216.14, 360.09, 214.74, 443.29, 220.0, 447.5, 211.93, 451.36, 193.67, 451.71, 191.92, 441.18, 183.84, 423.98, 170.86, 406.43, 164.19, 396.25, 161.38, 377.99, 156.82, 363.6, 168.75, 359.74, 172.61, 349.21, 173.67, 319.37, 175.42, 319.37, 176.82]], "area": 7980.121550000002, "iscrowd": 0, "image_id": 533568, "bbox": [312.35, 156.82, 139.36, 102.5], "category_id": 63, "id": 115764, "split": "val", "sentences": [{"tokens": ["a", "dark", "colored", "couch"], "raw": "A dark colored couch.", "sent_id": 6738, "sent": "a dark colored couch"}, {"tokens": ["a", "dark", "colored", "couch", "sitting", "in", "front", "of", "a", "red", "rug"], "raw": "A dark colored couch sitting in front of a red rug.", "sent_id": 6739, "sent": "a dark colored couch sitting in front of a red rug"}], "file_name": "COCO_train2014_000000533568_115764.jpg", "ann_id": 115764, "sent_ids": [6738, 6739], "ref_id": 7616}, {"segmentation": [[3.42, 115.06, 88.05, 177.46, 159.85, 238.16, 216.27, 256.96, 244.48, 275.77, 261.58, 292.87, 261.58, 296.29, 245.34, 303.13, 240.21, 310.82, 316.29, 380.92, 348.77, 417.67, 276.97, 419.38, 182.08, 419.38, 14.53, 419.38, 0.85, 397.16, 0.85, 248.42, 1.71, 159.51, 3.42, 111.64]], "area": 58807.14795, "iscrowd": 0, "image_id": 100485, "bbox": [0.85, 111.64, 347.92, 307.74], "category_id": 18, "id": 15920, "split": "val", "sentences": [{"tokens": ["a", "brown", "dog", "paw", "is", "holding", "onto", "an", "empty", "water", "bottle"], "raw": "A brown dog paw is holding onto an empty water bottle.", "sent_id": 6746, "sent": "a brown dog paw is holding onto an empty water bottle"}, {"tokens": ["brown", "dog", "paw"], "raw": "Brown dog paw", "sent_id": 6747, "sent": "brown dog paw"}], "file_name": "COCO_train2014_000000100485_15920.jpg", "ann_id": 15920, "sent_ids": [6746, 6747], "ref_id": 7621}, {"segmentation": [[174.06, 209.01, 203.02, 194.9, 269.84, 190.45, 437.64, 188.22, 490.36, 194.16, 490.36, 186.73, 482.19, 183.02, 482.19, 161.49, 508.92, 160.75, 556.44, 107.29, 583.91, 110.26, 563.12, 163.72, 580.94, 162.23, 583.91, 185.99, 566.09, 186.73, 565.35, 199.36, 584.65, 196.39, 571.29, 209.75, 556.44, 217.92, 523.02, 225.34, 505.21, 226.83, 504.46, 219.4, 473.28, 219.4, 443.58, 223.11, 433.18, 231.28, 396.06, 229.8, 325.53, 230.54, 319.59, 246.13, 288.4, 246.87, 283.2, 240.93, 234.2, 240.93, 191.88, 232.02, 167.38, 224.6]], "area": 20732.035849999997, "iscrowd": 0, "image_id": 555446, "bbox": [167.38, 107.29, 417.27, 139.58], "category_id": 5, "id": 156496, "split": "val", "sentences": [{"tokens": ["the", "klm", "plane"], "raw": "The KLM plane.", "sent_id": 6822, "sent": "the klm plane"}, {"tokens": ["an", "airplane", "with", "klm", "on", "it"], "raw": "An airplane with KLM on it.", "sent_id": 6823, "sent": "an airplane with klm on it"}], "file_name": "COCO_train2014_000000555446_156496.jpg", "ann_id": 156496, "sent_ids": [6822, 6823], "ref_id": 7651}, {"segmentation": [[158.33, 128.64, 165.04, 107.53, 183.27, 100.82, 210.14, 91.22, 230.29, 101.78, 230.29, 101.78, 268.67, 102.74, 284.03, 118.09, 282.11, 141.12, 271.55, 186.22, 286.91, 231.32, 296.5, 273.54, 296.5, 370.45, 281.15, 403.08, 248.52, 394.44, 267.71, 340.7, 254.28, 283.13, 225.49, 376.21, 220.7, 405.95, 195.75, 413.63, 171.76, 357.98, 157.37, 283.13, 152.57, 141.12]], "area": 35294.984, "iscrowd": 0, "image_id": 199485, "bbox": [152.57, 91.22, 143.93, 322.41], "category_id": 22, "id": 584071, "split": "val", "sentences": [{"tokens": ["an", "elephant", "between", "two", "other", "elephants"], "raw": "An elephant between two other elephants.", "sent_id": 6905, "sent": "an elephant between two other elephants"}, {"tokens": ["second", "elephant", "standing", "in", "the", "middle", "of", "the", "three", "standing"], "raw": "second elephant standing in the middle of the three standing", "sent_id": 6906, "sent": "second elephant standing in the middle of the three standing"}], "file_name": "COCO_train2014_000000199485_584071.jpg", "ann_id": 584071, "sent_ids": [6905, 6906], "ref_id": 7684}, {"segmentation": [[176.9, 572.4, 159.64, 559.46, 151.01, 540.76, 151.01, 486.11, 156.76, 447.28, 148.13, 404.13, 148.13, 360.99, 151.01, 330.79, 151.01, 316.4, 149.57, 300.58, 153.89, 293.39, 162.52, 291.96, 181.21, 299.15, 204.22, 322.16, 217.17, 330.79, 225.8, 336.54, 238.74, 313.53, 240.18, 306.34, 247.37, 290.52, 247.37, 277.57, 238.74, 254.56, 228.67, 241.62, 209.98, 227.24, 188.4, 202.79, 179.78, 185.53, 172.58, 174.02, 155.33, 163.96, 151.01, 139.51, 149.57, 126.56, 162.52, 92.04, 165.39, 76.22, 166.83, 63.28, 166.83, 54.65, 166.83, 48.9, 165.39, 44.58, 155.33, 35.96, 138.07, 35.96, 119.37, 37.39, 110.74, 47.46, 107.87, 53.21, 103.55, 63.28, 102.11, 70.47, 93.48, 86.29, 81.98, 93.48, 67.6, 103.55, 48.9, 130.88, 48.9, 140.94, 43.15, 179.78, 31.64, 248.81, 38.83, 260.31, 47.46, 261.75, 28.76, 281.89, 28.76, 293.39, 30.2, 319.28, 44.58, 362.43, 40.27, 412.76, 51.78, 481.8, 63.28, 533.57, 50.34, 569.53, 38.83, 581.03, 56.09, 593.98, 73.35, 595.42, 102.11, 605.48, 136.63, 602.61, 143.82, 599.73, 152.45, 586.79, 158.2, 585.35, 165.39, 585.35, 181.21, 585.35, 186.97, 569.53, 175.46, 556.58, 168.27, 552.27]], "area": 67717.40995000002, "iscrowd": 0, "image_id": 316557, "bbox": [28.76, 35.96, 218.61, 569.52], "category_id": 1, "id": 501324, "split": "val", "sentences": [{"tokens": ["the", "first", "man", "in", "line"], "raw": "The first man in line.", "sent_id": 6957, "sent": "the first man in line"}, {"tokens": ["a", "person", "in", "a", "white", "coat", "to", "the", "left", "of", "some", "other", "people"], "raw": "A person in a white coat to the left of some other people.", "sent_id": 6958, "sent": "a person in a white coat to the left of some other people"}], "file_name": "COCO_train2014_000000316557_501324.jpg", "ann_id": 501324, "sent_ids": [6957, 6958], "ref_id": 7703}, {"segmentation": [[552.07, 334.15, 540.44, 365.14, 532.7, 378.7, 536.57, 388.38, 532.7, 403.88, 523.01, 415.5, 500.73, 421.31, 468.77, 422.28, 461.99, 416.47, 450.37, 403.88, 461.02, 396.13, 446.5, 393.23, 430.03, 385.48, 431.0, 355.45, 439.72, 346.74, 457.15, 333.18, 474.58, 321.56, 500.73, 321.56, 516.23, 322.52, 525.92, 317.68, 525.92, 309.93, 523.01, 295.4, 525.92, 283.78, 551.1, 289.59, 551.1, 295.4, 551.1, 304.12, 565.63, 298.31, 569.5, 302.18, 575.31, 309.93, 571.44, 315.74, 565.63, 318.65, 551.1, 321.56, 543.35, 316.71, 543.35, 324.46]], "area": 10513.607000000007, "iscrowd": 0, "image_id": 51851, "bbox": [430.03, 283.78, 145.28, 138.5], "category_id": 70, "id": 1095092, "split": "val", "sentences": [{"tokens": ["a", "white", "toilet", "with", "a", "black", "seat"], "raw": "A white toilet with a black seat", "sent_id": 6971, "sent": "a white toilet with a black seat"}, {"tokens": ["the", "toilet"], "raw": "The toilet.", "sent_id": 6972, "sent": "the toilet"}], "file_name": "COCO_train2014_000000051851_1095092.jpg", "ann_id": 1095092, "sent_ids": [6971, 6972], "ref_id": 7710}, {"segmentation": [[498.88, 48.03, 499.72, 101.12, 32.02, 109.55, 4.21, 103.65, 2.53, 48.88, 41.29, 51.4, 164.33, 49.72, 241.85, 45.51, 258.71, 39.61, 401.12, 35.39, 430.62, 43.82, 471.91, 48.03, 484.55, 47.19]], "area": 30033.195050000002, "iscrowd": 0, "image_id": 421298, "bbox": [2.53, 35.39, 497.19, 74.16], "category_id": 67, "id": 390392, "split": "val", "sentences": [{"tokens": ["a", "plate", "of", "food", "that", "is", "furthest", "from", "the", "viewer"], "raw": "A plate of food that is furthest from the viewer.", "sent_id": 7046, "sent": "a plate of food that is furthest from the viewer"}, {"tokens": ["background", "of", "table", "top", "with", "plate", "on", "top"], "raw": "background of table top with plate on top", "sent_id": 7047, "sent": "background of table top with plate on top"}], "file_name": "COCO_train2014_000000421298_390392.jpg", "ann_id": 390392, "sent_ids": [7046, 7047], "ref_id": 7735}, {"segmentation": [[297.02, 388.4, 301.41, 419.74, 278.98, 448.58, 270.0, 452.42, 200.79, 422.94, 137.34, 378.08, 137.98, 353.08, 144.39, 340.27, 187.97, 326.17, 211.04, 340.27, 256.55, 360.13, 272.57, 371.03, 290.51, 392.18]], "area": 11867.777650000002, "iscrowd": 0, "image_id": 83641, "bbox": [137.34, 326.17, 164.07, 126.25], "category_id": 60, "id": 2118824, "split": "val", "sentences": [{"tokens": ["a", "fake", "long", "john", "donut", "in", "a", "package"], "raw": "a fake long john donut in a package", "sent_id": 7112, "sent": "a fake long john donut in a package"}, {"tokens": ["a", "plastic", "eclair", "toy"], "raw": "a plastic eclair toy", "sent_id": 7113, "sent": "a plastic eclair toy"}], "file_name": "COCO_train2014_000000083641_2118824.jpg", "ann_id": 2118824, "sent_ids": [7112, 7113], "ref_id": 7755}, {"segmentation": [[127.32, 237.41, 127.32, 222.09, 155.08, 214.44, 181.89, 203.91, 221.14, 215.39, 234.54, 208.69, 244.11, 204.86, 257.51, 189.55, 284.32, 187.63, 292.93, 183.8, 340.8, 182.84, 355.16, 160.83, 381.96, 153.17, 397.28, 146.47, 421.21, 146.47, 459.51, 157.0, 460.46, 171.36, 488.22, 203.91, 517.9, 218.27, 487.27, 307.29, 430.79, 340.8, 199.12, 367.6, 194.33, 330.27, 137.85, 246.98]], "area": 56225.90575, "iscrowd": 0, "image_id": 263176, "bbox": [127.32, 146.47, 390.58, 221.13], "category_id": 9, "id": 176340, "split": "val", "sentences": [{"tokens": ["the", "white", "and", "light", "blue", "boat", "on", "the", "right"], "raw": "The white and light blue boat on the right.", "sent_id": 7128, "sent": "the white and light blue boat on the right"}, {"tokens": ["a", "white", "and", "blue", "sail", "boat", "parked", "at", "the", "dock"], "raw": "A white and blue sail boat parked at the dock.", "sent_id": 7129, "sent": "a white and blue sail boat parked at the dock"}], "file_name": "COCO_train2014_000000263176_176340.jpg", "ann_id": 176340, "sent_ids": [7128, 7129], "ref_id": 7761}, {"segmentation": [[400.65, 175.38, 455.45, 166.84, 449.04, 156.88, 447.62, 144.78, 442.64, 135.53, 445.49, 121.3, 441.22, 95.68, 456.87, 77.18, 475.38, 68.64, 503.84, 66.5, 528.04, 76.46, 536.58, 91.41, 541.56, 115.6, 531.6, 134.82, 519.5, 153.32, 512.38, 165.42, 522.34, 176.09, 538.0, 181.79, 557.21, 191.04, 567.18, 203.85, 564.33, 203.14, 566.47, 226.62, 566.47, 242.28, 557.21, 265.76, 545.12, 275.72, 521.63, 278.57, 510.96, 246.55, 455.45, 206.7, 409.9, 179.65]], "area": 17233.7064, "iscrowd": 0, "image_id": 496732, "bbox": [400.65, 66.5, 166.53, 212.07], "category_id": 1, "id": 434184, "split": "val", "sentences": [{"tokens": ["woman", "in", "jean", "jacket", "with", "her", "back", "turned", "to", "man", "eating"], "raw": "Woman in jean jacket with her back turned to man eating.", "sent_id": 7136, "sent": "woman in jean jacket with her back turned to man eating"}, {"tokens": ["a", "woman", "wearing", "a", "blue", "-", "jean", "jacket", "sitting", "behind", "a", "man", "eating", "a", "sandwich"], "raw": "A woman wearing a blue-jean jacket sitting behind a man eating a sandwich.", "sent_id": 7137, "sent": "a woman wearing a blue - jean jacket sitting behind a man eating a sandwich"}], "file_name": "COCO_train2014_000000496732_434184.jpg", "ann_id": 434184, "sent_ids": [7136, 7137], "ref_id": 7765}, {"segmentation": [[230.31, 173.7, 250.47, 229.35, 309.0, 218.8, 335.87, 201.52, 471.18, 186.17, 556.59, 261.98, 539.32, 289.81, 441.43, 316.68, 357.95, 301.33, 292.69, 290.77, 226.48, 278.3, 241.83, 315.72, 205.36, 318.6, 187.13, 309.96, 182.33, 280.22, 107.48, 275.42, 119.0, 309.0, 68.13, 301.33, 72.93, 278.3, 2.88, 271.58, 1.92, 256.22, 227.43, 265.82, 220.72, 250.47, 140.11, 231.27, 225.52, 237.99, 216.88, 166.98]], "area": 37147.804599999996, "iscrowd": 0, "image_id": 492882, "bbox": [1.92, 166.98, 554.67, 151.62], "category_id": 5, "id": 161298, "split": "val", "sentences": [{"tokens": ["airplane", "sitting", "ground", ",", "fedex", "plane", "in", "the", "background"], "raw": "Airplane sitting ground, FedEx plane in the background.", "sent_id": 7188, "sent": "airplane sitting ground , fedex plane in the background"}, {"tokens": ["a", "large", "white", "jet", "with", "international", "on", "the", "side"], "raw": "A large white jet with international on the side.", "sent_id": 7189, "sent": "a large white jet with international on the side"}], "file_name": "COCO_train2014_000000492882_161298.jpg", "ann_id": 161298, "sent_ids": [7188, 7189], "ref_id": 7785}, {"segmentation": [[397.11, 258.14, 489.5, 259.68, 534.92, 261.22, 552.63, 282.78, 548.01, 372.86, 548.78, 448.31, 521.83, 469.87, 406.35, 476.8, 381.71, 462.94, 374.01, 440.61, 381.71, 275.08]], "area": 35859.18915, "iscrowd": 0, "image_id": 510027, "bbox": [374.01, 258.14, 178.62, 218.66], "category_id": 51, "id": 1536273, "split": "val", "sentences": [{"tokens": ["a", "green", "bowl", "of", "red", "apple", "slices"], "raw": "A green bowl of red apple slices.", "sent_id": 7216, "sent": "a green bowl of red apple slices"}, {"tokens": ["a", "container", "of", "sliced", "apples"], "raw": "A container of sliced apples.", "sent_id": 7217, "sent": "a container of sliced apples"}], "file_name": "COCO_train2014_000000510027_1536273.jpg", "ann_id": 1536273, "sent_ids": [7216, 7217], "ref_id": 7796}, {"segmentation": [[421.24, 299.44, 433.72, 277.37, 422.2, 205.41, 456.75, 150.71, 450.99, 113.29, 429.88, 133.44, 386.7, 169.9, 383.82, 172.78, 366.55, 171.82, 370.39, 152.63, 396.29, 117.13, 443.31, 81.63, 440.43, 52.84, 460.58, 25.97, 473.06, 23.09, 494.17, 41.32, 496.09, 62.43, 498.01, 64.35, 540.23, 84.5, 569.97, 114.25, 550.78, 150.71, 529.67, 182.38, 545.02, 277.37, 543.11, 335.91, 553.66, 343.58, 534.47, 347.42, 512.4, 326.31, 521.04, 267.78, 503.76, 226.52, 489.37, 211.17, 478.82, 199.65, 452.91, 218.84, 463.46, 256.26, 457.71, 309.04]], "area": 25970.204149999998, "iscrowd": 0, "image_id": 524966, "bbox": [366.55, 23.09, 203.42, 324.33], "category_id": 1, "id": 503383, "split": "val", "sentences": [{"tokens": ["it", "is", "a", "young", "black", "male", "wearing", "black", "rimmed", "glasses", "with", "his", "right", "foot", "on", "a", "soccer", "ball"], "raw": "It is a young black male wearing black rimmed glasses with his right foot on a soccer ball.", "sent_id": 7220, "sent": "it is a young black male wearing black rimmed glasses with his right foot on a soccer ball"}, {"tokens": ["a", "boy", "wearing", "glasses", "and", "white", "cleats", "with", "his", "right", "foot", "on", "a", "soccer", "ball"], "raw": "A boy wearing glasses and white cleats with his right foot on a soccer ball.", "sent_id": 7221, "sent": "a boy wearing glasses and white cleats with his right foot on a soccer ball"}], "file_name": "COCO_train2014_000000524966_503383.jpg", "ann_id": 503383, "sent_ids": [7220, 7221], "ref_id": 7797}, {"segmentation": [[177.78, 229.12, 180.08, 254.41, 174.71, 259.77, 162.45, 262.84, 74.33, 268.97, 66.67, 263.6, 57.47, 255.94, 26.05, 252.11, 5.36, 247.51, 6.9, 206.9, 9.96, 190.81, 20.69, 180.84, 51.34, 182.38, 59.0, 183.14, 67.43, 177.78, 75.1, 176.25, 101.15, 170.12, 101.15, 170.12, 111.11, 165.52, 144.83, 167.05, 163.99, 176.25, 171.65, 188.51, 180.08, 208.43, 180.08, 217.63, 178.55, 226.06]], "area": 14607.3916, "iscrowd": 0, "image_id": 466523, "bbox": [5.36, 165.52, 174.72, 103.45], "category_id": 8, "id": 1369482, "split": "val", "sentences": [{"tokens": ["vehicle", "with", "hood", "up"], "raw": "vehicle with hood up", "sent_id": 7265, "sent": "vehicle with hood up"}, {"tokens": ["a", "red", "truck", "has", "it", "'", "s", "hood", "and", "doors", "open"], "raw": "A red truck has it's hood and doors open.", "sent_id": 7266, "sent": "a red truck has it ' s hood and doors open"}], "file_name": "COCO_train2014_000000466523_1369482.jpg", "ann_id": 1369482, "sent_ids": [7265, 7266], "ref_id": 7813}, {"segmentation": [[220.16, 0.0, 327.58, 0.0, 357.32, 0.81, 352.12, 65.48, 348.16, 91.5, 343.69, 96.21, 304.29, 92.74, 211.37, 84.81, 162.55, 80.1, 161.31, 75.64, 166.52, 40.21, 172.46, 1.06, 176.43, 0.0]], "area": 16557.496199999998, "iscrowd": 0, "image_id": 183788, "bbox": [161.31, 0.0, 196.01, 96.21], "category_id": 84, "id": 1984212, "split": "val", "sentences": [{"tokens": ["the", "bottom", "end", "of", "a", "book", "with", "a", "leather", "book", "cover"], "raw": "The bottom end of a book with a leather book cover", "sent_id": 7311, "sent": "the bottom end of a book with a leather book cover"}, {"tokens": ["purple", "box", "sitting", "in", "between", "the", "book", "of", "sketches", "and", "blue", "book"], "raw": "Purple box sitting in between the book of sketches and blue book.", "sent_id": 7312, "sent": "purple box sitting in between the book of sketches and blue book"}], "file_name": "COCO_train2014_000000183788_1984212.jpg", "ann_id": 1984212, "sent_ids": [7311, 7312], "ref_id": 7827}, {"segmentation": [[188.15, 165.75, 185.91, 155.3, 189.65, 147.09, 200.85, 141.86, 209.06, 152.31, 209.8, 163.51, 220.26, 167.25, 229.96, 185.91, 234.44, 194.87, 229.96, 215.03, 226.98, 225.48, 229.22, 240.42, 228.47, 285.22, 233.7, 291.19, 215.03, 293.43, 214.28, 285.22, 214.28, 272.52, 209.8, 242.66, 207.57, 271.03, 212.04, 281.48, 209.06, 288.2, 209.06, 297.16, 200.85, 295.67, 197.11, 286.71, 190.39, 282.98, 197.11, 271.03, 191.89, 253.11, 191.14, 243.4, 186.66, 234.44, 185.91, 218.02, 180.69, 218.76, 176.95, 212.04, 173.97, 194.87, 178.45, 180.69, 182.93, 170.23, 189.65, 167.25, 191.14, 163.51]], "area": 5719.601049999999, "iscrowd": 0, "image_id": 101140, "bbox": [173.97, 141.86, 60.47, 155.3], "category_id": 1, "id": 223909, "split": "val", "sentences": [{"tokens": ["a", "men", "in", "brown", "jacket"], "raw": "A men in brown jacket", "sent_id": 7334, "sent": "a men in brown jacket"}, {"tokens": ["person", "in", "orange", "coat", "standing", "beside", "a", "truck", "with", "two", "men", "standing", "in", "front", "of", "him"], "raw": "Person in orange coat standing beside a truck with two men standing in front of him.", "sent_id": 7335, "sent": "person in orange coat standing beside a truck with two men standing in front of him"}], "file_name": "COCO_train2014_000000101140_223909.jpg", "ann_id": 223909, "sent_ids": [7334, 7335], "ref_id": 7836}, {"segmentation": [[289.08, 142.2, 293.39, 108.76, 299.87, 93.66, 332.22, 82.88, 373.21, 54.83, 427.15, 48.36, 542.56, 61.3, 547.96, 143.28, 537.17, 143.28, 522.07, 131.42, 508.04, 126.02, 483.24, 107.69, 478.92, 99.06, 462.74, 89.35, 442.25, 91.51, 418.52, 105.53, 388.31, 113.08, 389.39, 119.55, 426.07, 113.08, 444.4, 120.63, 428.22, 133.57, 318.2, 156.22, 311.73, 147.6]], "area": 16978.403949999996, "iscrowd": 0, "image_id": 11426, "bbox": [289.08, 48.36, 258.88, 107.86], "category_id": 8, "id": 395379, "split": "val", "sentences": [{"tokens": ["the", "blue", "van"], "raw": "the blue van.", "sent_id": 7368, "sent": "the blue van"}, {"tokens": ["blue", "van"], "raw": "blue van", "sent_id": 7369, "sent": "blue van"}], "file_name": "COCO_train2014_000000011426_395379.jpg", "ann_id": 395379, "sent_ids": [7368, 7369], "ref_id": 7852}, {"segmentation": [[278.58, 201.99, 255.6, 184.76, 252.73, 158.91, 226.88, 139.77, 213.48, 158.91, 201.03, 156.04, 186.67, 163.7, 172.31, 159.87, 171.36, 169.44, 178.06, 173.27, 178.06, 176.14, 160.83, 177.1, 178.06, 182.84, 187.63, 191.46, 187.63, 211.56, 199.12, 216.35, 191.46, 223.05, 185.72, 220.18, 176.14, 220.18, 169.44, 226.88, 169.44, 233.58, 165.61, 246.98, 158.91, 247.94, 166.57, 248.9, 170.4, 260.39, 172.31, 270.92, 182.84, 281.45, 187.63, 289.11, 187.63, 308.25, 193.38, 318.78, 203.91, 322.61, 216.35, 320.7, 232.62, 298.68, 238.37, 284.32, 239.33, 282.4, 249.86, 283.36, 265.17, 275.7, 259.43, 247.94, 253.69, 243.16, 246.98, 235.5, 255.6, 234.54, 259.43, 228.8, 259.43, 213.48, 265.17, 214.44]], "area": 12282.212, "iscrowd": 0, "image_id": 141603, "bbox": [158.91, 139.77, 119.67, 182.84], "category_id": 4, "id": 149926, "split": "val", "sentences": [{"tokens": ["a", "blue", "motorcycle"], "raw": "A blue motorcycle.", "sent_id": 7376, "sent": "a blue motorcycle"}, {"tokens": ["cyan", "blue", "motorcycle"], "raw": "Cyan blue motorcycle.", "sent_id": 7377, "sent": "cyan blue motorcycle"}], "file_name": "COCO_train2014_000000141603_149926.jpg", "ann_id": 149926, "sent_ids": [7376, 7377], "ref_id": 7856}, {"segmentation": [[316.93, 299.61, 313.94, 319.53, 314.94, 329.99, 313.44, 336.46, 311.45, 340.94, 310.95, 342.93, 312.95, 345.92, 324.4, 345.42, 323.9, 329.99, 324.4, 324.01, 326.89, 312.56, 329.88, 310.57, 329.38, 332.97, 328.38, 340.44, 327.89, 343.93, 327.89, 347.91, 339.84, 350.4, 340.34, 346.42, 339.84, 330.48, 340.83, 322.02, 342.33, 313.06, 341.83, 294.63, 343.82, 286.66, 359.26, 294.63, 385.16, 303.59, 400.1, 305.59, 401.09, 305.59, 423.0, 307.58, 421.51, 326.5, 414.54, 336.96, 411.55, 344.93, 411.05, 350.9, 413.54, 353.89, 423.5, 349.91, 427.98, 340.44, 432.96, 327.0, 436.45, 319.03, 439.93, 309.07, 442.92, 302.1, 448.9, 299.11, 455.87, 309.07, 457.86, 331.48, 454.38, 345.42, 452.88, 350.4, 451.89, 355.88, 453.38, 357.38, 466.33, 355.38, 467.82, 345.92, 472.3, 325.01, 470.31, 313.55, 470.81, 303.59, 480.77, 291.64, 485.25, 275.21, 488.24, 251.8, 487.24, 239.85, 482.26, 227.4, 472.3, 208.97, 456.37, 201.5, 429.97, 193.04, 391.13, 191.54, 348.8, 189.06, 334.86, 179.1, 327.89, 175.11, 318.42, 166.65, 313.94, 164.16, 310.95, 162.66, 304.98, 157.68, 300.0, 143.74, 294.52, 146.23, 291.03, 154.69, 287.05, 159.18, 278.09, 154.2, 272.61, 149.71, 270.12, 156.19, 271.12, 160.17, 267.13, 165.15, 261.16, 169.63, 250.7, 184.08, 249.7, 191.05, 250.2, 196.03, 255.18, 199.01, 273.11, 201.01, 276.59, 208.48, 280.58, 217.94, 284.56, 231.38, 288.54, 241.84, 294.02, 253.79, 299.0, 264.75, 307.97, 282.68, 317.93, 295.63, 318.42, 296.12]], "area": 25650.273349999996, "iscrowd": 0, "image_id": 313091, "bbox": [249.7, 143.74, 238.54, 213.64], "category_id": 20, "id": 61062, "split": "val", "sentences": [{"tokens": ["a", "bloody", "sheep", "on", "the", "grassy", "pasture", "who", "just", "had", "a", "baby"], "raw": "A bloody sheep on the grassy pasture who just had a baby.", "sent_id": 7396, "sent": "a bloody sheep on the grassy pasture who just had a baby"}, {"tokens": ["a", "sheep", "with", "blood", "on", "its", "hind", "leg"], "raw": "A sheep with blood on its hind leg.", "sent_id": 7397, "sent": "a sheep with blood on its hind leg"}], "file_name": "COCO_train2014_000000313091_61062.jpg", "ann_id": 61062, "sent_ids": [7396, 7397], "ref_id": 7863}, {"segmentation": [[395.72, 233.42, 426.55, 219.03, 409.08, 90.55, 469.72, 85.41, 471.78, 95.69, 465.61, 94.66, 472.81, 168.66, 513.92, 192.3, 523.17, 188.19, 524.2, 196.42, 489.25, 208.75, 492.33, 244.72, 489.25, 253.98, 482.06, 240.61, 446.08, 249.86, 446.08, 262.2, 433.75, 260.14, 430.66, 227.25, 406.0, 240.61]], "area": 10400.00685, "iscrowd": 0, "image_id": 44266, "bbox": [395.72, 85.41, 128.48, 176.79], "category_id": 62, "id": 102210, "split": "val", "sentences": [{"tokens": ["a", "brown", "wicker", "chair", "sitting", "in", "front", "of", "a", "brown", "desk"], "raw": "a brown wicker chair sitting in front of a brown desk", "sent_id": 7422, "sent": "a brown wicker chair sitting in front of a brown desk"}, {"tokens": ["a", "wood", "chair"], "raw": "A wood chair.", "sent_id": 7423, "sent": "a wood chair"}], "file_name": "COCO_train2014_000000044266_102210.jpg", "ann_id": 102210, "sent_ids": [7422, 7423], "ref_id": 7873}, {"segmentation": [[155.33, 473.2, 152.09, 393.38, 156.4, 371.81, 140.22, 308.16, 134.83, 249.92, 134.83, 233.74, 129.44, 220.79, 124.04, 186.28, 119.73, 174.41, 133.75, 134.5, 159.64, 111.85, 156.4, 78.41, 169.35, 46.05, 183.37, 34.19, 207.1, 34.19, 223.28, 59.0, 231.91, 93.51, 227.6, 115.09, 250.25, 123.72, 271.82, 159.31, 281.53, 181.96, 272.9, 185.2, 281.53, 202.46, 275.06, 218.64, 261.03, 220.79, 254.56, 213.24, 251.33, 201.38, 243.78, 195.99, 241.62, 242.37, 245.93, 272.57, 240.54, 268.25, 237.3, 322.19, 223.28, 365.33, 231.91, 376.12, 227.6, 427.9, 223.28, 472.12, 156.4, 472.12]], "area": 41344.866599999994, "iscrowd": 0, "image_id": 110704, "bbox": [119.73, 34.19, 161.8, 439.01], "category_id": 1, "id": 483149, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "blue"], "raw": "A woman in blue.", "sent_id": 7424, "sent": "a woman in blue"}, {"tokens": ["a", "nurse", "wearing", "blue", "scrubs"], "raw": "a nurse wearing blue scrubs", "sent_id": 7425, "sent": "a nurse wearing blue scrubs"}], "file_name": "COCO_train2014_000000110704_483149.jpg", "ann_id": 483149, "sent_ids": [7424, 7425], "ref_id": 7874}, {"segmentation": [[244.61, 105.35, 240.94, 106.27, 226.28, 109.94, 220.79, 111.77, 209.79, 113.6, 205.21, 115.43, 200.63, 120.93, 196.97, 124.59, 192.39, 128.26, 186.89, 136.5, 190.55, 143.83, 196.05, 146.58, 199.72, 146.58, 205.21, 148.41, 206.13, 144.75, 208.88, 153.91, 211.63, 158.49, 213.46, 162.15, 212.54, 166.74, 213.46, 174.06, 215.29, 177.73, 217.12, 179.56, 220.79, 183.23, 223.54, 186.89, 228.12, 191.47, 234.53, 196.05, 237.28, 198.8, 242.77, 203.38, 247.35, 208.88, 252.85, 216.21, 255.6, 222.62, 258.35, 230.86, 263.85, 236.36, 268.43, 240.94, 273.01, 246.44, 273.92, 248.27, 276.67, 255.6, 273.01, 262.93, 271.17, 269.34, 271.17, 274.84, 270.26, 288.58, 270.26, 294.08, 268.43, 301.41, 268.43, 304.15, 265.68, 309.65, 260.18, 320.65, 259.26, 323.39, 260.18, 328.89, 255.6, 334.39, 253.77, 338.97, 251.02, 343.55, 251.02, 346.3, 267.51, 349.96, 270.26, 348.13, 276.67, 343.55, 286.75, 337.14, 289.5, 333.47, 290.41, 328.89, 290.41, 316.98, 290.41, 308.74, 290.41, 300.49, 290.41, 293.16, 293.16, 280.34, 296.83, 272.09, 297.74, 269.34, 308.74, 264.76, 317.9, 265.68, 319.73, 265.68, 332.55, 272.09, 333.47, 275.75, 336.22, 282.17, 338.97, 289.5, 338.05, 296.83, 338.05, 302.32, 338.05, 312.4, 338.05, 318.81, 339.88, 325.23, 339.88, 329.81, 338.05, 331.64, 339.88, 332.55, 345.38, 334.39, 350.88, 333.47, 357.29, 330.72, 365.54, 327.06, 369.2, 321.56, 369.2, 314.23, 368.28, 305.99, 362.79, 295.91, 359.12, 291.33, 358.21, 288.58, 366.45, 285.83, 376.53, 290.41, 381.11, 294.08, 382.94, 295.91, 391.19, 299.57, 394.85, 300.49, 399.43, 301.41, 404.01, 303.24, 406.76, 305.99, 409.51, 307.82, 404.01, 315.15, 402.18, 316.98, 398.52, 323.39, 393.94, 328.89, 386.61, 347.21, 384.77, 349.05, 384.77, 351.79, 386.61, 354.54, 391.19, 354.54, 405.85, 354.54, 410.43, 353.63, 414.09, 349.05, 415.92, 347.21, 420.5, 361.87, 420.5, 365.54, 423.25, 373.78, 425.08, 378.36, 425.08, 383.86, 424.17, 391.19, 418.67, 397.6, 417.75, 403.1, 420.5, 405.85, 425.08, 407.68, 430.58, 407.68, 441.57, 405.85, 452.57, 400.35, 458.06, 391.19, 458.06, 387.52, 457.15, 381.11, 452.57, 369.2, 449.82, 360.95, 447.07, 351.79, 443.41, 342.63, 443.41, 338.97, 446.15, 335.3, 447.99, 333.47, 448.9, 332.55, 449.82, 332.55, 452.57, 326.14, 454.4, 323.39, 457.15, 310.57, 457.15, 307.82, 462.65, 299.57, 469.06, 294.99, 469.06, 285.83, 472.72, 272.09, 477.3, 261.1, 477.3, 256.52, 478.22, 245.52, 480.05, 239.11, 480.05, 233.61, 480.97, 217.12, 481.88, 208.88, 481.88, 206.13, 479.14, 195.14, 476.39, 183.23, 476.39, 174.98, 475.47, 170.4, 474.55, 164.9, 467.23, 156.66, 463.56, 152.99, 457.15, 149.33, 452.57, 147.5, 447.07, 144.75, 433.33, 139.25, 425.08, 136.5, 409.51, 132.84, 400.35, 131.92, 389.35, 127.34, 380.19, 124.59, 373.78, 122.76, 366.45, 122.76, 358.21, 120.01, 344.46, 118.18, 335.3, 118.18, 326.14, 118.18, 315.15, 116.35, 291.33, 112.68, 288.58, 112.68, 284.0, 112.68, 270.26, 112.68, 263.85, 111.77, 254.68, 108.1, 251.02, 108.1, 243.69, 107.19, 242.77, 107.19]], "area": 46854.65040000001, "iscrowd": 0, "image_id": 241461, "bbox": [186.89, 105.35, 294.99, 302.33], "category_id": 20, "id": 61492, "split": "val", "sentences": [{"tokens": ["a", "brown", "sheep", "with", "a", "white", "face", "and", "white", "legs", ",", "looking", "toward", "the", "camera"], "raw": "A brown sheep with a white face and white legs, looking toward the camera.", "sent_id": 7426, "sent": "a brown sheep with a white face and white legs , looking toward the camera"}, {"tokens": ["sheep", "with", "white", "face"], "raw": "sheep with white face", "sent_id": 7427, "sent": "sheep with white face"}], "file_name": "COCO_train2014_000000241461_61492.jpg", "ann_id": 61492, "sent_ids": [7426, 7427], "ref_id": 7875}, {"segmentation": [[0.96, 323.16, 14.43, 311.62, 41.36, 300.08, 66.47, 279.64, 73.47, 269.72, 88.65, 263.88, 110.26, 260.38, 155.22, 245.78, 201.35, 228.26, 235.21, 218.33, 248.06, 217.17, 253.6, 218.09, 257.56, 216.51, 258.35, 230.97, 254.78, 234.73, 245.67, 236.71, 240.33, 241.07, 234.19, 242.06, 224.88, 242.25, 214.38, 247.4, 207.65, 251.56, 201.12, 256.31, 202.7, 260.08, 193.99, 266.02, 160.73, 286.72, 135.02, 302.05, 122.66, 317.87, 129.09, 331.22, 128.1, 345.06, 120.19, 361.38, 111.78, 370.28, 61.85, 369.78, 1.03, 370.77, 1.03, 325.78], [83.84, 389.57, 113.86, 388.66, 107.04, 419.6, 106.13, 428.0, 81.56, 425.06, 82.02, 390.48], [29.46, 389.98, 18.16, 412.17, 11.88, 428.0, 1.0, 427.66, 1.41, 389.98, 27.37, 389.56], [41.6, 390.4, 45.37, 405.47, 48.72, 403.38, 46.21, 388.3, 40.77, 389.56]], "area": 17007.111599999997, "iscrowd": 0, "image_id": 166762, "bbox": [0.96, 216.51, 257.39, 211.49], "category_id": 25, "id": 596666, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "with", "its", "head", "disappearing", "behind", "a", "tree"], "raw": "A giraffe with its head disappearing behind a tree", "sent_id": 7447, "sent": "a giraffe with its head disappearing behind a tree"}, {"tokens": ["a", "large", "giraffe", "with", "its", "head", "buried", "in", "food"], "raw": "A large giraffe with its head buried in food.", "sent_id": 7448, "sent": "a large giraffe with its head buried in food"}], "file_name": "COCO_train2014_000000166762_596666.jpg", "ann_id": 596666, "sent_ids": [7447, 7448], "ref_id": 7885}, {"segmentation": [[55.01, 474.61, 55.01, 473.53, 37.75, 471.37, 20.49, 471.37, 10.79, 473.53, 1.08, 473.53, 0.0, 457.35, 2.16, 446.56, 1.08, 434.7, 1.08, 415.28, 2.16, 409.89, 2.16, 398.02, 2.16, 371.06, 1.08, 347.33, 1.08, 326.83, 1.08, 305.26, 0.0, 296.63, 3.24, 265.35, 3.24, 245.93, 2.16, 221.12, 0.0, 196.31, 2.16, 174.74, 2.16, 158.56, 2.16, 134.83, 2.16, 114.34, 3.24, 79.82, 3.24, 45.3, 4.31, 22.65, 3.24, 5.39, 24.81, 9.71, 40.99, 18.34, 50.7, 22.65, 59.33, 34.52, 63.64, 50.7, 65.8, 67.96, 62.56, 79.82, 63.64, 91.69, 63.64, 101.39, 58.25, 107.87, 53.93, 117.57, 56.09, 120.81, 56.09, 133.75, 55.01, 138.07, 57.17, 140.22, 49.62, 148.85, 46.38, 152.09, 39.91, 160.72, 39.91, 169.35, 47.46, 176.9, 53.93, 196.31, 60.4, 208.18, 72.27, 214.65, 79.82, 228.67, 84.13, 239.46, 84.13, 251.33, 87.37, 261.03, 97.08, 277.21, 103.55, 290.16, 114.34, 300.94, 120.81, 312.81, 121.89, 322.52, 132.67, 333.3, 134.83, 344.09, 135.91, 376.45, 130.52, 381.84, 120.81, 390.47, 108.94, 396.94, 105.71, 396.94, 101.39, 396.94, 88.45, 399.1, 76.58, 402.34, 71.19, 399.1, 64.72, 394.79, 53.93, 395.87, 48.54, 388.31, 45.3, 393.71, 40.99, 410.97, 46.38, 428.22, 55.01, 453.03, 57.17, 469.21, 59.33, 470.29]], "area": 34214.2496, "iscrowd": 0, "image_id": 151854, "bbox": [0.0, 5.39, 135.91, 469.22], "category_id": 1, "id": 491469, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "striped", "sweater"], "raw": "A man wearing a striped sweater.", "sent_id": 7479, "sent": "a man wearing a striped sweater"}], "file_name": "COCO_train2014_000000151854_491469.jpg", "ann_id": 491469, "sent_ids": [7479], "ref_id": 7898}, {"segmentation": [[591.97, 0.78, 600.26, 70.24, 579.52, 259.96, 578.49, 262.03, 528.73, 246.48, 472.74, 235.08, 481.04, 54.69, 500.73, 1.81]], "area": 27654.678149999992, "iscrowd": 0, "image_id": 329616, "bbox": [472.74, 0.78, 127.52, 261.25], "category_id": 44, "id": 90970, "split": "val", "sentences": [{"tokens": ["pinot", "noir", "bottle"], "raw": "pinot noir bottle", "sent_id": 7554, "sent": "pinot noir bottle"}, {"tokens": ["the", "bottle", "of", "vignette", "on", "the", "right"], "raw": "The bottle of vignette on the right", "sent_id": 7555, "sent": "the bottle of vignette on the right"}], "file_name": "COCO_train2014_000000329616_90970.jpg", "ann_id": 90970, "sent_ids": [7554, 7555], "ref_id": 7924}, {"segmentation": [[609.63, 211.02, 611.93, 218.68, 612.18, 239.62, 612.44, 254.93, 608.87, 276.3, 609.12, 284.47, 609.63, 291.62, 609.38, 299.53, 607.08, 306.42, 606.06, 312.8, 605.29, 318.93, 603.5, 321.23, 604.27, 326.33, 606.82, 329.65, 609.89, 327.87, 611.93, 330.42, 618.31, 332.72, 621.63, 332.72, 623.93, 328.89, 620.1, 316.89, 619.08, 313.06, 620.1, 308.46, 632.35, 272.98, 633.37, 263.53, 632.35, 256.9, 630.31, 248.47, 632.35, 240.81, 638.73, 223.46, 640.0, 212.48, 639.75, 96.96, 636.44, 92.88, 626.99, 89.05, 625.71, 85.73, 625.71, 79.09, 628.78, 76.82, 630.82, 73.76, 631.07, 71.72, 631.07, 69.67, 631.33, 56.94, 628.27, 51.83, 624.18, 48.0, 620.61, 45.7, 614.23, 44.43, 607.84, 44.43, 602.23, 49.79, 599.67, 54.13, 597.12, 58.72, 596.61, 67.66, 596.61, 76.08, 596.1, 82.72, 592.27, 88.08, 571.85, 105.9, 565.72, 125.05, 567.25, 128.11, 568.27, 129.39, 571.08, 154.4, 571.59, 155.68, 582.06, 157.47, 582.06, 164.33, 577.72, 166.89, 578.49, 169.44, 576.7, 170.46, 578.49, 180.93, 578.49, 186.26, 576.7, 190.09, 576.95, 193.41, 575.93, 197.24, 575.42, 199.03, 573.64, 208.93, 566.49, 218.38, 568.79, 223.74, 572.1, 227.31, 571.08, 236.5, 570.06, 244.39, 574.91, 255.37, 574.4, 267.59, 572.36, 269.13, 572.1, 287.73, 575.42, 305.58, 579.25, 316.81, 574.91, 323.96, 568.53, 323.68, 566.74, 327.51, 572.1, 325.72, 562.4, 332.61, 565.98, 336.44, 576.95, 333.63, 589.46, 332.36, 597.63, 328.53, 593.8, 312.96, 594.31, 291.26, 593.8, 270.58, 595.85, 252.22, 609.89, 213.73]], "area": 14746.469199999994, "iscrowd": 0, "image_id": 505924, "bbox": [562.4, 44.43, 77.6, 292.01], "category_id": 1, "id": 490055, "split": "val", "sentences": [{"tokens": ["a", "woman", "who", "is", "marked", "number", "14", "and", "a", "pink", "hairband", "is", "running", "away", "from", "the", "goalie"], "raw": "A woman who is marked number 14 and a pink hairband is running away from the goalie.", "sent_id": 7571, "sent": "a woman who is marked number 14 and a pink hairband is running away from the goalie"}, {"tokens": ["a", "white", "female", "soccer", "player", "that", "is", "wearing", "white", "shorts", "and", "a", "white", "shirt", "that", "reads", "14"], "raw": "A white female soccer player that is wearing white shorts and a white shirt that reads 14", "sent_id": 7572, "sent": "a white female soccer player that is wearing white shorts and a white shirt that reads 14"}], "file_name": "COCO_train2014_000000505924_490055.jpg", "ann_id": 490055, "sent_ids": [7571, 7572], "ref_id": 7932}, {"segmentation": [[390.13, 321.92, 403.59, 326.4, 426.01, 318.55, 424.89, 259.14, 443.95, 255.77, 452.91, 275.95, 460.76, 319.67, 457.4, 333.13, 474.22, 332.01, 479.82, 321.92, 465.25, 256.89, 485.43, 246.8, 464.13, 173.93, 457.4, 164.97, 458.52, 130.21, 450.67, 115.64, 429.37, 106.67, 426.01, 92.1, 424.89, 79.76, 421.52, 68.55, 396.86, 83.13, 402.47, 102.19, 402.47, 112.28, 387.89, 142.54, 390.13, 168.33, 408.07, 167.21, 413.68, 181.78, 399.1, 249.05, 411.43, 255.77, 411.43, 310.71]], "area": 12984.609899999996, "iscrowd": 0, "image_id": 432897, "bbox": [387.89, 68.55, 97.54, 264.58], "category_id": 1, "id": 494512, "split": "val", "sentences": [{"tokens": ["person", "waiting", "to", "bat"], "raw": "person waiting to bat", "sent_id": 7617, "sent": "person waiting to bat"}, {"tokens": ["woman", "resting", "the", "bat", "on", "her", "shoulder"], "raw": "Woman resting the bat on her shoulder", "sent_id": 7618, "sent": "woman resting the bat on her shoulder"}], "file_name": "COCO_train2014_000000432897_494512.jpg", "ann_id": 494512, "sent_ids": [7617, 7618], "ref_id": 7950}, {"segmentation": [[61.8, 201.48, 81.37, 153.06, 116.39, 130.4, 161.72, 105.68, 165.84, 73.75, 150.39, 53.15, 155.54, 32.55, 167.9, 16.07, 185.41, 6.8, 203.95, 1.65, 226.61, 12.98, 236.91, 24.31, 249.27, 41.82, 248.24, 71.69, 240.0, 100.53, 294.59, 124.22, 324.46, 170.58, 287.38, 212.81, 286.35, 224.14, 301.8, 254.01, 331.67, 292.12, 364.64, 389.97, 389.36, 388.94, 406.87, 448.69, 338.88, 447.66, 319.31, 431.18, 295.62, 364.22, 271.93, 381.73, 249.27, 380.7, 236.91, 375.55, 279.14, 350.83, 272.96, 296.24, 261.63, 267.4, 248.24, 252.98, 224.55, 252.98, 192.62, 238.56, 166.87, 232.38, 135.97, 238.56, 100.94, 269.46, 92.7, 273.58, 47.38, 261.22], [307.98, 200.45, 310.04, 220.02, 313.13, 235.47, 323.43, 244.74, 346.09, 247.83, 357.42, 240.62, 356.39, 226.2, 347.12, 203.54], [27.81, 320.96, 14.42, 417.79, 2.06, 421.91, 2.06, 470.32, 61.8, 464.14, 67.98, 409.55, 59.74, 378.64, 38.11, 370.4, 38.11, 357.01, 59.74, 345.68, 51.5, 318.9]], "area": 62076.75089999997, "iscrowd": 0, "image_id": 489695, "bbox": [2.06, 1.65, 404.81, 468.67], "category_id": 1, "id": 187567, "split": "val", "sentences": [{"tokens": ["a", "man", "riding", "a", "motorcycle", "ahead", "of", "another", "motorcycle"], "raw": "A man riding a motorcycle ahead of another motorcycle.", "sent_id": 7627, "sent": "a man riding a motorcycle ahead of another motorcycle"}, {"tokens": ["the", "man", "on", "the", "closest", "motorcycle"], "raw": "the man on the closest motorcycle", "sent_id": 7628, "sent": "the man on the closest motorcycle"}], "file_name": "COCO_train2014_000000489695_187567.jpg", "ann_id": 187567, "sent_ids": [7627, 7628], "ref_id": 7955}, {"segmentation": [[324.03, 300.29, 334.51, 233.58, 324.98, 203.09, 316.4, 176.4, 324.98, 134.47, 343.09, 108.74, 343.09, 86.82, 352.62, 78.24, 373.58, 77.29, 387.88, 90.63, 385.02, 118.27, 408.85, 147.81, 411.7, 207.85, 409.8, 225.96, 390.74, 223.1, 400.27, 311.73, 383.11, 331.74, 365.01, 316.49, 365.01, 250.74, 353.57, 329.84, 324.98, 324.12]], "area": 16876.363000000005, "iscrowd": 0, "image_id": 371361, "bbox": [316.4, 77.29, 95.3, 254.45], "category_id": 1, "id": 507676, "split": "val", "sentences": [{"tokens": ["the", "skier", "wearing", "black"], "raw": "the skier wearing black", "sent_id": 7669, "sent": "the skier wearing black"}, {"tokens": ["a", "person", "wearing", "black", "ski", "gear", "riding", "a", "t", "-", "bar", "lift"], "raw": "A person wearing black ski gear riding a t-bar lift.", "sent_id": 7670, "sent": "a person wearing black ski gear riding a t - bar lift"}], "file_name": "COCO_train2014_000000371361_507676.jpg", "ann_id": 507676, "sent_ids": [7669, 7670], "ref_id": 7974}, {"segmentation": [[286.24, 229.54, 432.43, 237.05, 431.75, 254.81, 475.47, 262.33, 476.15, 240.47, 625.08, 244.57, 630.54, 8.2, 285.56, 17.76]], "area": 77828.60335000002, "iscrowd": 0, "image_id": 124169, "bbox": [285.56, 8.2, 344.98, 254.13], "category_id": 72, "id": 31793, "split": "val", "sentences": [{"tokens": ["a", "dell", "monitor", "running", "a", "multimedia", "suite"], "raw": "A Dell monitor running a multimedia suite", "sent_id": 7738, "sent": "a dell monitor running a multimedia suite"}, {"tokens": ["desktop", "screen", "which", "is", "displaying", "options", "for", "viewing", "the", "pictures", "+", "videos"], "raw": "Desktop screen which is displaying options for viewing the pictures + Videos.", "sent_id": 7739, "sent": "desktop screen which is displaying options for viewing the pictures + videos"}], "file_name": "COCO_train2014_000000124169_31793.jpg", "ann_id": 31793, "sent_ids": [7738, 7739], "ref_id": 8003}, {"segmentation": [[301.21, 232.83, 491.28, 223.97, 517.85, 225.58, 517.05, 236.86, 337.45, 247.33, 338.26, 285.98, 306.85, 285.98, 297.18, 276.32, 299.6, 233.63]], "area": 4773.800200000001, "iscrowd": 0, "image_id": 147303, "bbox": [297.18, 223.97, 220.67, 62.01], "category_id": 6, "id": 168904, "split": "val", "sentences": [{"tokens": ["the", "second", "bus", "in", "from", "the", "bottom", "of", "the", "picture"], "raw": "The second bus in from the bottom of the picture.", "sent_id": 7821, "sent": "the second bus in from the bottom of the picture"}], "file_name": "COCO_train2014_000000147303_168904.jpg", "ann_id": 168904, "sent_ids": [7821], "ref_id": 8037}, {"segmentation": [[193.29, 230.98, 224.43, 210.57, 240.54, 210.57, 243.76, 233.12, 252.35, 253.53, 257.72, 268.56, 265.23, 323.33, 248.05, 343.73, 267.38, 345.88, 277.05, 334.06, 273.83, 269.63, 285.64, 258.9, 298.52, 271.78, 310.34, 321.18, 304.97, 335.14, 320.0, 336.21, 326.44, 329.77, 318.93, 281.45, 325.37, 253.53, 335.03, 254.6, 343.62, 282.52, 345.77, 308.29, 341.48, 322.25, 343.62, 326.55, 364.03, 326.55, 369.4, 314.73, 367.25, 277.15, 375.84, 258.9, 380.13, 242.79, 385.5, 219.16, 382.28, 197.69, 371.54, 181.58, 357.58, 172.99, 337.18, 163.33, 320.0, 165.47, 309.26, 175.14, 298.52, 175.14, 274.9, 162.25, 246.98, 153.66, 230.87, 152.59, 214.77, 151.51, 198.66, 149.37, 199.73, 169.77, 200.81, 183.73, 194.36, 200.91, 186.85, 213.8, 187.92, 226.68]], "area": 20099.478700000003, "iscrowd": 0, "image_id": 517095, "bbox": [186.85, 149.37, 198.65, 196.51], "category_id": 19, "id": 273831, "split": "val", "sentences": [{"tokens": ["a", "chestnut", "horse", "with", "a", "white", "stripe", "down", "its", "face"], "raw": "a chestnut horse with a white stripe down its face", "sent_id": 7822, "sent": "a chestnut horse with a white stripe down its face"}, {"tokens": ["a", "horse", "pulling", "a", "cart", "with", "another", "horse"], "raw": "A horse pulling a cart with another horse.", "sent_id": 7823, "sent": "a horse pulling a cart with another horse"}], "file_name": "COCO_train2014_000000517095_273831.jpg", "ann_id": 273831, "sent_ids": [7822, 7823], "ref_id": 8038}, {"segmentation": [[47.0, 19.49, 59.73, 26.91, 69.8, 36.98, 85.7, 42.82, 85.17, 51.3, 61.32, 38.57, 62.91, 50.24, 64.5, 57.66, 89.94, 57.66, 103.19, 58.19, 112.2, 66.14, 119.09, 92.64, 125.98, 95.82, 134.47, 101.65, 144.54, 150.95, 149.31, 179.57, 135.53, 182.76, 119.09, 112.26, 116.83, 104.29, 105.32, 107.83, 97.57, 110.71, 94.7, 151.66, 94.7, 160.73, 83.19, 160.73, 80.09, 125.1, 78.32, 125.54, 76.77, 151.88, 76.1, 181.98, 69.24, 180.65, 67.69, 166.26, 65.7, 132.18, 66.14, 109.82, 61.94, 103.41, 40.65, 60.6, 25.24, 38.25, 24.46, 22.06, 39.11, 20.52]], "area": 7517.196549999999, "iscrowd": 0, "image_id": 35945, "bbox": [24.46, 19.49, 124.85, 163.27], "category_id": 62, "id": 378457, "split": "val", "sentences": [{"tokens": ["a", "green", "chair", "with", "a", "boy", "in", "red", "sitting", "on", "it"], "raw": "A green chair with a boy in red sitting on it", "sent_id": 7846, "sent": "a green chair with a boy in red sitting on it"}, {"tokens": ["green", "chair", "the", "child", "is", "sitting", "in"], "raw": "green chair the child is sitting in", "sent_id": 7847, "sent": "green chair the child is sitting in"}], "file_name": "COCO_train2014_000000035945_378457.jpg", "ann_id": 378457, "sent_ids": [7846, 7847], "ref_id": 8046}, {"segmentation": [[18.7, 524.94, 20.13, 497.62, 37.39, 458.79, 40.27, 437.21, 40.27, 411.33, 43.15, 384.0, 50.34, 353.8, 46.02, 316.4, 46.02, 300.58, 48.9, 277.57, 50.34, 250.25, 48.9, 220.04, 56.09, 195.6, 83.42, 179.78, 122.25, 171.15, 123.69, 149.57, 128.0, 129.44, 133.75, 116.49, 135.19, 86.29, 142.38, 70.47, 155.33, 58.97, 172.58, 56.09, 185.53, 53.21, 208.54, 71.91, 231.55, 89.17, 245.93, 110.74, 263.19, 132.31, 264.63, 174.02, 263.19, 192.72, 250.25, 215.73, 232.99, 228.67, 247.37, 263.19, 283.33, 271.82, 296.27, 313.53, 287.64, 326.47, 260.31, 345.17, 220.04, 333.66, 217.17, 337.98, 231.55, 350.92, 241.62, 360.99, 241.62, 385.44, 214.29, 430.02, 234.43, 451.6, 243.06, 476.04, 231.55, 513.44, 218.61, 523.51, 181.21, 506.25, 125.12, 478.92, 112.18, 477.48, 117.93, 504.81, 120.81, 526.38, 112.18, 542.2, 92.04, 558.02, 69.03, 568.09, 44.58, 563.78]], "area": 85063.01365000001, "iscrowd": 0, "image_id": 468373, "bbox": [18.7, 53.21, 277.57, 514.88], "category_id": 88, "id": 1163364, "split": "val", "sentences": [{"tokens": ["the", "brown", "teddy", "bear", "along", "with", "a", "black", "teddy", "bear"], "raw": "the brown teddy bear along with a black teddy bear", "sent_id": 7852, "sent": "the brown teddy bear along with a black teddy bear"}, {"tokens": ["a", "light", "brown", "teddy", "bear", "sitting", "next", "to", "a", "dark", "brown", "teddy", "bear", "on", "a", "chair"], "raw": "A light brown teddy bear sitting next to a dark brown teddy bear on a chair.", "sent_id": 7853, "sent": "a light brown teddy bear sitting next to a dark brown teddy bear on a chair"}], "file_name": "COCO_train2014_000000468373_1163364.jpg", "ann_id": 1163364, "sent_ids": [7852, 7853], "ref_id": 8049}, {"segmentation": [[351.5, 578.32, 311.71, 498.74, 293.47, 435.73, 266.94, 385.99, 265.28, 384.33, 276.89, 376.04, 305.08, 331.27, 306.74, 304.75, 316.68, 293.14, 336.58, 284.85, 366.42, 283.19, 379.69, 303.09, 399.59, 316.35, 424.46, 331.27, 427.0, 342.88, 417.82, 364.44, 422.8, 385.99, 424.46, 395.94, 424.46, 404.23, 417.82, 482.16, 376.37, 624.75, 359.79, 636.35, 339.9, 626.4]], "area": 33055.928499999995, "iscrowd": 0, "image_id": 309084, "bbox": [265.28, 283.19, 161.72, 353.16], "category_id": 65, "id": 1957499, "split": "val", "sentences": [{"tokens": ["the", "white", "puffy", "mattress"], "raw": "the white puffy mattress", "sent_id": 7894, "sent": "the white puffy mattress"}, {"tokens": ["the", "right", "side", "of", "a", "bed", "next", "to", "a", "man", "and", "a", "dog"], "raw": "The right side of a bed next to a man and a dog.", "sent_id": 7895, "sent": "the right side of a bed next to a man and a dog"}], "file_name": "COCO_train2014_000000309084_1957499.jpg", "ann_id": 1957499, "sent_ids": [7894, 7895], "ref_id": 8062}, {"segmentation": [[442.52, 419.46, 321.44, 516.04, 304.14, 566.49, 341.62, 628.47, 484.32, 517.48, 485.77, 451.17, 442.52, 422.34]], "area": 19970.645900000007, "iscrowd": 0, "image_id": 85549, "bbox": [304.14, 419.46, 181.63, 209.01], "category_id": 33, "id": 1185082, "split": "val", "sentences": [{"tokens": ["a", "black", "suitcase", "next", "to", "a", "woman", "on", "her", "phone"], "raw": "A black suitcase next to a woman on her phone.", "sent_id": 7988, "sent": "a black suitcase next to a woman on her phone"}, {"tokens": ["black", "suit", "case"], "raw": "Black suit case.", "sent_id": 7989, "sent": "black suit case"}], "file_name": "COCO_train2014_000000085549_1185082.jpg", "ann_id": 1185082, "sent_ids": [7988, 7989], "ref_id": 8098}, {"segmentation": [[145.68, 172.81, 177.83, 166.78, 211.99, 165.78, 238.12, 169.8, 255.2, 177.83, 258.21, 179.84, 267.25, 166.78, 268.26, 153.72, 269.26, 140.66, 278.3, 130.61, 299.4, 128.6, 335.57, 127.6, 334.57, 119.56, 331.55, 111.52, 325.52, 93.44, 312.46, 80.38, 297.39, 73.34, 276.29, 69.32, 242.13, 74.35, 197.93, 100.47, 146.69, 117.55, 126.59, 135.64, 120.56, 143.67, 109.51, 164.77, 109.51, 176.83, 123.58, 176.83, 152.72, 172.81]], "area": 13983.31745, "iscrowd": 0, "image_id": 183435, "bbox": [109.51, 69.32, 226.06, 110.52], "category_id": 56, "id": 1056502, "split": "val", "sentences": [{"tokens": ["bag", "of", "greens", "with", "yellow", "stems"], "raw": "Bag of greens with yellow stems.", "sent_id": 8082, "sent": "bag of greens with yellow stems"}, {"tokens": ["wrapped", ",", "leafed", "lettuce", ",", "sitting", "behind", "wrapped", "carrots"], "raw": "Wrapped, leafed lettuce, sitting behind wrapped carrots.", "sent_id": 8083, "sent": "wrapped , leafed lettuce , sitting behind wrapped carrots"}], "file_name": "COCO_train2014_000000183435_1056502.jpg", "ann_id": 1056502, "sent_ids": [8082, 8083], "ref_id": 8137}, {"segmentation": [[550.31, 308.14, 563.26, 286.3, 581.05, 262.85, 568.92, 257.99, 551.12, 259.61, 543.84, 253.14, 544.65, 236.96, 543.84, 220.78, 544.65, 203.8, 547.08, 199.75, 576.2, 193.28, 582.67, 191.67, 597.23, 198.14, 612.6, 211.08, 626.35, 233.73, 637.67, 245.05, 639.29, 255.57, 640.0, 270.93, 640.0, 309.76, 638.48, 325.94, 636.05, 342.92, 636.05, 343.73, 640.0, 369.61, 638.48, 385.79, 630.39, 425.43, 572.96, 425.43, 572.96, 413.29, 569.73, 380.94, 576.2, 353.44, 568.11, 327.55, 560.02, 318.66, 548.7, 308.95]], "area": 16417.8921, "iscrowd": 0, "image_id": 535666, "bbox": [543.84, 191.67, 96.16, 233.76], "category_id": 1, "id": 1693531, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "long", "hair", "and", "a", "black", "shirt", "drinking", "from", "a", "glass"], "raw": "A man with long hair and a black shirt drinking from a glass.", "sent_id": 8178, "sent": "a man with long hair and a black shirt drinking from a glass"}, {"tokens": ["a", "man", "with", "long", "hair", "and", "a", "beard"], "raw": "a man with long hair and a beard", "sent_id": 8179, "sent": "a man with long hair and a beard"}], "file_name": "COCO_train2014_000000535666_1693531.jpg", "ann_id": 1693531, "sent_ids": [8178, 8179], "ref_id": 8172}, {"segmentation": [[120.52, 327.14, 107.12, 327.14, 86.52, 324.05, 72.1, 324.05, 61.8, 320.96, 58.71, 313.75, 60.77, 305.51, 67.98, 300.36, 70.04, 298.3, 70.04, 294.18, 70.04, 294.18, 65.92, 290.06, 63.86, 290.06, 63.86, 286.97, 63.86, 286.97, 59.74, 281.82, 58.71, 281.82, 53.56, 283.88, 52.53, 290.06, 47.38, 293.15, 40.17, 294.18, 37.08, 300.36, 29.87, 303.45, 26.78, 308.6, 35.02, 307.57, 39.14, 306.54, 47.38, 308.6, 47.38, 309.63, 50.47, 313.75, 44.29, 318.9, 42.23, 327.14, 43.26, 335.38, 50.47, 347.74, 56.65, 353.92, 69.01, 361.13, 79.31, 362.16, 86.52, 372.46, 98.88, 384.82, 107.12, 386.88, 118.45, 398.21, 125.67, 401.3, 141.12, 401.3, 143.18, 401.3, 145.24, 401.3, 145.24, 403.36, 135.97, 408.52, 127.73, 413.67, 125.67, 429.12, 127.73, 431.18, 127.73, 435.3, 133.91, 425.0, 137.0, 417.79, 139.06, 422.94, 139.06, 422.94, 142.15, 417.79, 141.12, 415.73, 142.15, 411.61, 144.21, 411.61, 146.27, 409.55, 150.39, 409.55, 152.45, 415.73, 152.45, 420.88, 147.3, 429.12, 145.24, 434.27, 144.21, 442.51, 149.36, 444.57, 154.51, 438.39, 157.6, 426.03, 159.66, 421.91, 159.66, 414.7, 159.66, 410.58, 161.72, 405.42, 170.99, 402.33, 170.99, 397.18, 179.23, 392.03, 191.59, 393.06, 203.95, 396.15, 215.28, 397.18, 217.34, 397.18, 216.31, 392.03, 222.49, 392.03, 219.4, 387.91, 222.49, 384.82, 230.73, 385.85, 234.85, 381.73, 257.51, 387.91, 265.75, 392.03, 288.41, 393.06, 299.74, 397.18, 288.41, 388.94, 278.11, 388.94, 268.84, 388.94, 294.59, 386.88, 283.26, 382.76, 260.6, 381.73, 242.06, 380.7, 235.88, 376.58, 246.18, 369.37, 278.11, 372.46, 298.71, 373.49, 311.07, 373.49, 325.49, 374.52, 337.85, 375.55, 344.03, 375.55, 352.27, 375.55, 339.91, 367.31, 313.13, 367.31, 273.99, 359.07, 253.39, 359.07, 238.97, 357.01, 216.31, 348.77, 193.65, 339.5, 167.9, 335.38, 147.3, 335.38, 133.91, 329.2, 123.61, 325.08, 118.45, 325.08]], "area": 13097.747800000006, "iscrowd": 0, "image_id": 462664, "bbox": [26.78, 281.82, 325.49, 162.75], "category_id": 16, "id": 44738, "split": "val", "sentences": [{"tokens": ["peacock", "standing", "in", "the", "grass"], "raw": "peacock standing in the grass", "sent_id": 8212, "sent": "peacock standing in the grass"}, {"tokens": ["a", "peacock", "walking", "on", "grass"], "raw": "a peacock walking on grass", "sent_id": 8213, "sent": "a peacock walking on grass"}], "file_name": "COCO_train2014_000000462664_44738.jpg", "ann_id": 44738, "sent_ids": [8212, 8213], "ref_id": 8186}, {"segmentation": [[612.0, 233.67, 605.64, 230.49, 565.9, 252.75, 535.7, 254.34, 505.5, 241.62, 503.91, 232.08, 532.52, 222.55, 268.64, 173.27, 259.11, 168.5, 189.16, 54.05, 216.19, 54.05, 302.03, 157.37, 356.07, 173.27, 608.82, 195.52]], "area": 14976.623999999994, "iscrowd": 0, "image_id": 457745, "bbox": [189.16, 54.05, 422.84, 200.29], "category_id": 5, "id": 2049011, "split": "val", "sentences": [{"tokens": ["the", "wing", "of", "an", "airplane", "over", "a", "bus"], "raw": "The wing of an airplane over a bus.", "sent_id": 8231, "sent": "the wing of an airplane over a bus"}, {"tokens": ["top", "of", "a", "plane", "'", "s", "wing"], "raw": "Top of a plane's wing.", "sent_id": 8232, "sent": "top of a plane ' s wing"}], "file_name": "COCO_train2014_000000457745_2049011.jpg", "ann_id": 2049011, "sent_ids": [8231, 8232], "ref_id": 8193}, {"segmentation": [[136.22, 57.3, 150.27, 40.0, 151.35, 34.59, 147.03, 19.46, 150.27, 7.57, 162.16, 3.24, 175.14, 4.32, 182.7, 6.49, 194.59, 5.41, 200.0, 7.57, 201.08, 11.89, 197.84, 24.86, 195.68, 40.0, 188.11, 51.89, 192.43, 60.54, 197.84, 73.51, 196.76, 112.43, 202.16, 166.49, 206.49, 193.51, 210.81, 211.89, 208.65, 236.76, 208.65, 250.81, 214.05, 267.03, 223.78, 297.3, 234.59, 308.11, 248.65, 313.51, 259.46, 322.16, 256.22, 326.49, 237.84, 330.81, 191.35, 327.57, 190.27, 304.86, 170.81, 229.19, 151.35, 258.38, 142.7, 284.32, 132.97, 310.27, 129.73, 327.57, 144.86, 342.7, 149.19, 349.19, 140.54, 351.35, 128.65, 351.35, 92.97, 348.11, 115.68, 240.0, 121.08, 189.19, 108.11, 182.7, 104.86, 120.0, 124.32, 68.11]], "area": 26463.655249999996, "iscrowd": 0, "image_id": 531201, "bbox": [92.97, 3.24, 166.49, 348.11], "category_id": 1, "id": 482309, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "dark", "clothing", "watching", "a", "tennis", "game"], "raw": "A man in dark clothing watching a tennis game.", "sent_id": 8249, "sent": "a man in dark clothing watching a tennis game"}, {"tokens": ["an", "old", "man", "in", "a", "blue", "polo", "shirt", "watching", "tennis"], "raw": "An old man in a blue polo shirt watching tennis.", "sent_id": 8250, "sent": "an old man in a blue polo shirt watching tennis"}], "file_name": "COCO_train2014_000000531201_482309.jpg", "ann_id": 482309, "sent_ids": [8249, 8250], "ref_id": 8199}, {"segmentation": [[2.47, 125.2, 15.65, 121.08, 51.89, 225.68, 113.66, 377.23, 112.84, 378.88, 0.0, 377.23]], "area": 15822.0785, "iscrowd": 0, "image_id": 43655, "bbox": [0.0, 121.08, 113.66, 257.8], "category_id": 62, "id": 104758, "split": "val", "sentences": [{"tokens": ["an", "empty", "chair", "directly", "to", "the", "left", "of", "the", "leftmost", "of", "two", "cats", "and", "behind", "a", "second", "empty", "chair", "that", "is", "closer", "to", "the", "foreground"], "raw": "An empty chair directly to the left of the leftmost of two cats and behind a second empty chair that is closer to the foreground.", "sent_id": 8254, "sent": "an empty chair directly to the left of the leftmost of two cats and behind a second empty chair that is closer to the foreground"}], "file_name": "COCO_train2014_000000043655_104758.jpg", "ann_id": 104758, "sent_ids": [8254], "ref_id": 8202}, {"segmentation": [[241.15, 3.77, 234.69, 20.99, 230.39, 32.84, 228.23, 43.6, 223.93, 64.06, 202.4, 51.14, 180.86, 11.3, 190.55, 3.77, 191.63, 1.61, 189.48, 3.77, 132.36, 0.0, 130.63, 7.23, 137.55, 18.19, 159.48, 37.81, 170.44, 51.08, 175.05, 71.84, 180.25, 86.27, 201.02, 104.73, 207.36, 109.34, 218.9, 126.08, 214.86, 135.31, 211.4, 169.34, 210.82, 182.61, 213.71, 195.31, 219.48, 208.0, 228.71, 224.73, 233.9, 233.38, 258.13, 141.65, 263.32, 116.84, 267.94, 93.77, 269.67, 66.08, 278.9, 37.81, 287.55, 30.88, 303.13, 34.34, 318.13, 33.77, 338.9, 23.38, 366.59, 4.92, 375.82, 0.0, 296.21, 0.0, 286.98, 7.23, 275.44, 11.27, 275.44, 4.34, 275.44, 1.46, 243.71, 1.46]], "area": 15625.643200000002, "iscrowd": 0, "image_id": 174700, "bbox": [130.63, 0.0, 245.19, 233.38], "category_id": 62, "id": 1578833, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "leg", "surrounded", "by", "cats"], "raw": "A wooden chair leg surrounded by cats.", "sent_id": 8331, "sent": "a wooden chair leg surrounded by cats"}, {"tokens": ["wooden", "stool", "leg", "between", "cats", "and", "suitcases"], "raw": "wooden stool leg between cats and suitcases", "sent_id": 8332, "sent": "wooden stool leg between cats and suitcases"}], "file_name": "COCO_train2014_000000174700_1578833.jpg", "ann_id": 1578833, "sent_ids": [8331, 8332], "ref_id": 8233}, {"segmentation": [[138.9, 588.62, 174.66, 588.62, 246.18, 528.11, 303.94, 440.09, 335.57, 398.83, 452.47, 376.83, 449.72, 356.2, 459.34, 338.32, 468.97, 328.69, 475.85, 314.94, 475.85, 298.44, 475.85, 286.06, 455.22, 305.31, 449.72, 310.81, 430.46, 303.94, 430.46, 276.43, 437.34, 275.06, 449.72, 240.67, 442.84, 225.55, 423.59, 192.54, 416.71, 183.77, 417.74, 180.51, 419.98, 182.22, 424.62, 186.35, 428.4, 190.82, 434.07, 197.18, 433.39, 189.79, 429.26, 181.19, 425.65, 174.66, 423.07, 169.85, 423.24, 166.75, 427.2, 165.55, 426.34, 163.66, 425.13, 159.88, 428.74, 158.67, 433.39, 162.97, 438.03, 171.74, 445.42, 182.91, 448.69, 189.1, 452.12, 171.74, 451.95, 169.85, 454.7, 168.64, 459.69, 174.32, 459.0, 197.7, 462.09, 195.63, 466.22, 200.45, 468.63, 193.23, 472.24, 187.73, 480.83, 178.1, 496.13, 171.74, 506.79, 171.05, 508.85, 169.68, 507.65, 142.0, 508.68, 131.68, 510.4, 115.35, 508.34, 106.58, 511.43, 95.41, 519.86, 83.89, 525.53, 72.03, 531.72, 62.23, 538.77, 51.57, 549.6, 44.87, 561.8, 40.06, 579.51, 39.88, 588.1, 43.84, 598.59, 48.31, 607.87, 58.62, 615.44, 71.0, 618.19, 85.61, 620.08, 93.35, 620.25, 96.27, 623.48, 99.76, 628.46, 109.01, 631.77, 122.51, 634.05, 134.84, 632.07, 141.76, 633.21, 147.23, 634.74, 151.09, 635.86, 154.23, 635.71, 158.62, 628.81, 174.97, 624.44, 184.06, 625.17, 189.87, 627.72, 223.67, 621.17, 240.75, 613.54, 259.28, 597.92, 307.26, 591.74, 324.7, 590.28, 330.88, 586.65, 340.69, 590.65, 363.59, 597.19, 383.94, 589.92, 407.56, 577.93, 448.63, 552.12, 479.52, 536.86, 492.24, 527.77, 530.76, 523.41, 551.11, 520.14, 561.65, 488.52, 560.2, 485.47, 582.25, 497.62, 601.01, 502.33, 610.35, 504.15, 611.81, 446.37, 611.81, 441.28, 603.08, 434.37, 587.46, 426.74, 574.01, 426.02, 563.47, 424.93, 547.12, 425.65, 529.31, 407.84, 520.22, 385.68, 497.69, 374.77, 480.61, 369.32, 472.98, 364.6, 463.17, 354.83, 471.85, 340.97, 508.59, 312.26, 536.58, 289.37, 553.29, 261.38, 569.29, 255.21, 579.1, 257.75, 596.91, 250.48, 607.81, 247.21, 609.63, 243.58, 611.81, 159.26, 611.44, 152.72, 610.35, 146.54, 599.09]], "area": 96663.423, "iscrowd": 0, "image_id": 541949, "bbox": [138.9, 39.88, 496.96, 571.93], "category_id": 1, "id": 426937, "split": "val", "sentences": [{"tokens": ["the", "woman", "in", "a", "black", "dress", "with", "white", "flowers", "on", "the", "skirt"], "raw": "the woman in a black dress with white flowers on the skirt", "sent_id": 8362, "sent": "the woman in a black dress with white flowers on the skirt"}], "file_name": "COCO_train2014_000000541949_426937.jpg", "ann_id": 426937, "sent_ids": [8362], "ref_id": 8240}, {"segmentation": [[487.45, 129.78, 513.36, 140.33, 559.42, 147.05, 583.41, 150.89, 578.61, 155.69, 577.65, 160.48, 553.66, 204.62, 531.59, 204.62, 541.19, 214.22, 578.61, 218.06, 579.57, 213.26, 629.47, 165.28, 640.0, 164.32, 640.0, 68.37, 630.42, 69.33, 638.1, 76.04, 637.14, 87.56, 610.27, 117.31, 593.0, 120.18, 587.24, 121.14, 545.98, 119.22, 492.25, 125.94, 485.53, 127.86]], "area": 7565.546450000006, "iscrowd": 0, "image_id": 171478, "bbox": [485.53, 68.37, 154.47, 149.69], "category_id": 5, "id": 162713, "split": "val", "sentences": [{"tokens": ["far", "right", "jet"], "raw": "Far right jet", "sent_id": 8424, "sent": "far right jet"}, {"tokens": ["the", "plane", "directly", "above", "the", "smoke", "trail"], "raw": "The plane directly above the smoke trail.", "sent_id": 8425, "sent": "the plane directly above the smoke trail"}], "file_name": "COCO_train2014_000000171478_162713.jpg", "ann_id": 162713, "sent_ids": [8424, 8425], "ref_id": 8264}, {"segmentation": [[364.58, 122.97, 321.44, 148.85, 319.28, 186.61, 319.28, 220.04, 323.6, 234.07, 335.46, 253.48, 346.25, 263.19, 360.27, 265.35, 393.71, 265.35, 417.44, 266.43, 428.22, 249.17, 443.33, 210.34, 439.01, 172.58, 421.75, 140.22, 392.63, 120.81, 364.58, 121.89]], "area": 14841.615200000004, "iscrowd": 0, "image_id": 252373, "bbox": [319.28, 120.81, 124.05, 145.62], "category_id": 27, "id": 1166084, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "blue", "bag", "on", "top", "of", "a", "black", "suitcase"], "raw": "A white and blue bag on top of a black suitcase.", "sent_id": 8469, "sent": "a white and blue bag on top of a black suitcase"}, {"tokens": ["a", "small", "blue", "and", "white", "backpack"], "raw": "A small blue and white backpack", "sent_id": 8470, "sent": "a small blue and white backpack"}], "file_name": "COCO_train2014_000000252373_1166084.jpg", "ann_id": 1166084, "sent_ids": [8469, 8470], "ref_id": 8279}, {"segmentation": [[432.51, 304.87, 432.51, 291.09, 434.35, 269.06, 433.72, 260.86, 426.93, 257.67, 430.53, 253.67, 439.32, 252.87, 438.12, 247.67, 441.32, 246.88, 441.32, 238.08, 436.92, 233.29, 426.13, 227.69, 407.74, 224.89, 378.17, 226.49, 368.97, 227.69, 366.97, 227.29, 363.38, 223.29, 351.39, 228.49, 322.21, 224.09, 297.83, 224.49, 285.83, 227.29, 275.84, 229.29, 276.64, 237.28, 263.85, 248.47, 266.25, 278.85, 270.65, 282.45, 269.05, 292.84, 274.24, 293.24, 277.04, 282.45, 290.63, 283.65, 306.22, 272.86, 327.4, 274.45, 329.0, 267.66, 326.6, 264.46, 338.2, 262.46, 347.79, 264.46, 346.59, 270.46, 346.59, 274.45, 393.35, 277.65, 390.56, 294.84, 427.33, 295.64, 426.93, 303.63, 432.13, 299.64]], "area": 9123.471699999996, "iscrowd": 0, "image_id": 76802, "bbox": [263.85, 223.29, 177.47, 81.58], "category_id": 63, "id": 117360, "split": "val", "sentences": [{"tokens": ["the", "white", "couch", "with", "the", "various", "colored", "pillows", "on", "it"], "raw": "the white couch with the various colored pillows on it", "sent_id": 8483, "sent": "the white couch with the various colored pillows on it"}, {"tokens": ["the", "large", "couch", "between", "the", "lights"], "raw": "The large couch between the lights.", "sent_id": 8484, "sent": "the large couch between the lights"}], "file_name": "COCO_train2014_000000076802_117360.jpg", "ann_id": 117360, "sent_ids": [8483, 8484], "ref_id": 8285}, {"segmentation": [[290.72, 321.5, 299.8, 326.55, 296.77, 352.8, 288.7, 374.0, 302.83, 393.17, 295.76, 414.37, 279.61, 428.0, 640.0, 428.0, 640.0, 356.83, 619.79, 335.64, 611.72, 329.58, 599.6, 302.33, 571.34, 287.18, 546.1, 287.18, 532.98, 294.25, 514.81, 329.58, 514.81, 347.75, 495.63, 355.83, 487.56, 332.61, 478.47, 311.41, 456.26, 304.34, 414.88, 306.36, 395.7, 330.59, 391.66, 298.29, 372.48, 285.17, 347.25, 286.17, 327.06, 294.25, 302.83, 315.45, 287.69, 317.47, 291.73, 324.53]], "area": 41246.12185, "iscrowd": 0, "image_id": 434039, "bbox": [279.61, 285.17, 360.39, 142.83], "category_id": 53, "id": 1048196, "split": "val", "sentences": [{"tokens": ["stack", "of", "red", "apples"], "raw": "Stack of red apples.", "sent_id": 8539, "sent": "stack of red apples"}, {"tokens": ["a", "bunch", "of", "red", "apples"], "raw": "A bunch of red apples.", "sent_id": 8540, "sent": "a bunch of red apples"}], "file_name": "COCO_train2014_000000434039_1048196.jpg", "ann_id": 1048196, "sent_ids": [8539, 8540], "ref_id": 8306}, {"segmentation": [[344.05, 180.72, 403.19, 194.67, 462.32, 213.27, 507.49, 153.47, 520.12, 158.79, 496.19, 219.92, 616.45, 219.92, 623.09, 217.92, 621.76, 220.58, 621.76, 225.9, 615.79, 224.57, 546.02, 227.23, 548.68, 234.53, 536.06, 233.2, 523.44, 233.2, 554.0, 236.53, 577.92, 242.51, 500.18, 246.49, 434.41, 253.14, 425.11, 257.79, 406.5, 255.13, 415.14, 251.81, 414.48, 247.82, 399.2, 245.16, 399.2, 248.48, 404.51, 251.14, 403.19, 254.47, 384.58, 253.14, 384.58, 251.81, 395.87, 247.82, 390.56, 244.49, 372.62, 237.85, 372.62, 245.16, 379.26, 247.82, 375.28, 253.14, 360.0, 251.81, 367.31, 247.82, 368.64, 240.51, 356.68, 233.2, 352.03, 237.85, 342.73, 225.9, 342.06, 234.53, 332.09, 223.9, 320.13, 233.2, 305.52, 228.55, 298.87, 223.24, 294.23, 221.91, 290.9, 229.88, 271.63, 226.56, 268.31, 217.26, 270.97, 209.95, 255.69, 204.63, 254.36, 202.64, 260.34, 196.0, 261.67, 203.3, 319.47, 210.62, 320.8, 211.28, 320.13, 200.65, 326.12, 186.03, 332.76, 179.39]], "area": 12879.298850000005, "iscrowd": 0, "image_id": 94608, "bbox": [254.36, 153.47, 368.73, 104.32], "category_id": 5, "id": 160282, "split": "val", "sentences": [{"tokens": ["an", "airplane", "taking", "off"], "raw": "An airplane taking off.", "sent_id": 8634, "sent": "an airplane taking off"}, {"tokens": ["an", "airplane", "with", "france", "on", "the", "side", "flying", "away"], "raw": "An airplane with France on the side flying away.", "sent_id": 8635, "sent": "an airplane with france on the side flying away"}], "file_name": "COCO_train2014_000000094608_160282.jpg", "ann_id": 160282, "sent_ids": [8634, 8635], "ref_id": 8341}, {"segmentation": [[584.93, 245.31, 570.35, 241.18, 553.58, 230.24, 547.27, 210.32, 548.48, 197.93, 552.85, 184.56, 561.12, 180.92, 570.35, 180.92, 579.83, 185.05, 587.85, 193.07, 594.65, 203.52, 600.97, 213.72, 602.67, 220.77, 602.42, 228.3, 599.51, 238.26, 598.78, 240.45, 602.42, 251.39, 617.73, 280.54, 631.1, 300.96, 640.0, 316.02, 640.0, 351.01, 631.1, 344.69, 626.48, 335.46, 611.9, 295.37, 600.24, 264.26, 593.19, 249.68]], "area": 4032.390949999999, "iscrowd": 0, "image_id": 447574, "bbox": [547.27, 180.92, 92.73, 170.09], "category_id": 50, "id": 708191, "split": "val", "sentences": [{"tokens": ["spoons"], "raw": "SPOONS", "sent_id": 8663, "sent": "spoons"}, {"tokens": ["a", "silver", "spoon", "lying", "on", "the", "table", "next", "to", "a", "knife"], "raw": "A silver spoon lying on the table next to a knife.", "sent_id": 8664, "sent": "a silver spoon lying on the table next to a knife"}], "file_name": "COCO_train2014_000000447574_708191.jpg", "ann_id": 708191, "sent_ids": [8663, 8664], "ref_id": 8351}, {"segmentation": [[39.41, 485.92, 28.15, 433.0, 12.39, 405.97, 15.77, 387.95, 15.77, 279.84, 33.78, 230.29, 59.68, 201.01, 70.95, 176.24, 61.94, 163.85, 66.44, 154.84, 65.32, 125.56, 79.95, 98.54, 112.61, 99.66, 136.26, 104.17, 153.15, 136.82, 149.77, 152.59, 139.64, 185.25, 128.38, 207.77, 127.25, 216.78, 130.63, 251.69, 158.78, 320.38, 164.41, 345.16, 176.8, 330.52, 194.82, 339.53, 202.7, 346.28, 198.2, 359.8, 192.57, 373.31, 191.44, 386.82, 184.7, 386.14, 164.82, 392.11, 178.74, 437.83, 164.82, 499.46]], "area": 47757.35705, "iscrowd": 0, "image_id": 522062, "bbox": [12.39, 98.54, 190.31, 400.92], "category_id": 1, "id": 450114, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "striped", "shirt", "and", "sport", "coat", "holding", "a", "glass", "of", "wine"], "raw": "A man with a striped shirt and sport coat holding a glass of wine.", "sent_id": 8676, "sent": "a man with a striped shirt and sport coat holding a glass of wine"}, {"tokens": ["a", "man", "wearing", "a", "black", "suit", "and", "holding", "a", "champaign", "flute"], "raw": "A man wearing a black suit and holding a champaign flute.", "sent_id": 8677, "sent": "a man wearing a black suit and holding a champaign flute"}], "file_name": "COCO_train2014_000000522062_450114.jpg", "ann_id": 450114, "sent_ids": [8676, 8677], "ref_id": 8356}, {"segmentation": [[211.42, 433.62, 213.57, 401.26, 182.29, 413.12, 156.4, 410.97, 135.91, 395.87, 115.42, 373.21, 108.94, 355.96, 115.42, 326.83, 125.12, 298.79, 134.83, 290.16, 142.38, 280.45, 143.46, 266.43, 143.46, 247.01, 167.19, 215.73, 194.16, 193.08, 217.89, 174.74, 240.54, 135.91, 256.72, 124.04, 306.34, 120.81, 351.64, 129.44, 387.24, 154.25, 410.97, 179.06, 456.27, 204.94, 482.16, 227.6, 514.52, 250.25, 522.07, 281.53, 545.8, 324.67, 550.11, 368.9, 581.39, 393.71, 578.16, 439.01, 552.27, 468.13, 500.49, 461.66, 513.44, 433.62, 471.37, 418.52, 441.17, 426.07, 436.85, 449.8, 423.91, 455.19, 385.08, 448.72, 339.78, 433.62, 316.04, 428.22, 295.55, 421.75]], "area": 106315.57669999998, "iscrowd": 0, "image_id": 496732, "bbox": [108.94, 120.81, 472.45, 347.32], "category_id": 1, "id": 422012, "split": "val", "sentences": [{"tokens": ["a", "man", "biting", "burger", "holding", "with", "two", "hands"], "raw": "A MAN BITING BURGER HOLDING WITH TWO HANDS", "sent_id": 8735, "sent": "a man biting burger holding with two hands"}, {"tokens": ["man", "eating"], "raw": "MAN EATING", "sent_id": 8736, "sent": "man eating"}], "file_name": "COCO_train2014_000000496732_422012.jpg", "ann_id": 422012, "sent_ids": [8735, 8736], "ref_id": 8378}, {"segmentation": [[346.19, 4.57, 346.19, 10.34, 346.19, 17.07, 349.07, 23.8, 349.07, 29.57, 336.57, 41.11, 334.65, 52.65, 334.65, 57.46, 334.65, 74.77, 332.72, 96.88, 332.72, 101.69, 337.53, 106.5, 345.22, 103.62, 353.88, 113.23, 361.57, 135.35, 363.49, 146.89, 363.49, 174.78, 363.49, 184.39, 363.49, 196.89, 359.65, 204.59, 380.8, 220.93, 388.5, 213.24, 393.3, 207.47, 389.46, 196.89, 389.46, 192.08, 398.11, 185.35, 398.11, 170.93, 398.11, 155.54, 398.11, 150.73, 398.11, 140.16, 400.04, 126.69, 403.88, 119.96, 407.73, 116.12, 407.73, 111.31, 407.73, 79.57, 404.84, 68.03, 404.84, 63.23, 418.31, 67.07, 427.92, 67.07, 428.88, 67.07, 435.62, 67.07, 440.42, 67.07, 446.19, 67.07, 447.16, 58.42, 433.69, 47.84, 421.19, 40.15, 411.58, 34.38, 404.84, 23.8, 394.27, 20.92, 394.27, 14.18, 397.15, 1.68, 379.84, 0.72, 368.3, 2.64, 361.57, 2.64, 360.61, 4.57, 358.69, 9.38]], "area": 11687.404400000001, "iscrowd": 0, "image_id": 478899, "bbox": [332.72, 0.72, 114.44, 220.21], "category_id": 1, "id": 513415, "split": "val", "sentences": [{"tokens": ["a", "boy", "going", "on", "stairs", "and", "one", "man", "doing", "ice", "skating"], "raw": "a boy going on stairs and one man doing ice skating", "sent_id": 8913, "sent": "a boy going on stairs and one man doing ice skating"}, {"tokens": ["a", "person", "in", "a", "blue", "and", "grey", "coat"], "raw": "A person in a blue and grey coat.", "sent_id": 8914, "sent": "a person in a blue and grey coat"}], "file_name": "COCO_train2014_000000478899_513415.jpg", "ann_id": 513415, "sent_ids": [8913, 8914], "ref_id": 8452}, {"segmentation": [[24.67, 144.68, 37.81, 184.9, 73.39, 225.89, 123.66, 236.71, 138.35, 236.71, 179.34, 222.02, 178.57, 183.35, 183.21, 155.51, 198.67, 127.67, 218.01, 111.43, 189.39, 85.91, 136.81, 70.44, 84.99, 77.4, 56.37, 92.09, 38.59, 110.65]], "area": 22341.084499999997, "iscrowd": 0, "image_id": 450914, "bbox": [24.67, 70.44, 193.34, 166.27], "category_id": 51, "id": 710771, "split": "val", "sentences": [{"tokens": ["stray", "berry", "was", "on", "a", "cup"], "raw": "stray berry was on a cup", "sent_id": 8927, "sent": "stray berry was on a cup"}, {"tokens": ["a", "small", "white", "bowl", "with", "a", "few", "small", "strawberries", "in", "it"], "raw": "A small white bowl with a few small strawberries in it.", "sent_id": 8928, "sent": "a small white bowl with a few small strawberries in it"}], "file_name": "COCO_train2014_000000450914_710771.jpg", "ann_id": 710771, "sent_ids": [8927, 8928], "ref_id": 8457}, {"segmentation": [[23.93, 435.68, 17.41, 418.27, 11.97, 406.31, 23.93, 401.96, 32.64, 400.87, 40.25, 425.89], [59.83, 404.13, 40.25, 326.9, 46.78, 320.37, 72.89, 406.31, 62.01, 409.57], [55.48, 309.49, 69.62, 300.79, 80.5, 358.44, 91.38, 389.99, 83.76, 394.34, 68.53, 354.09, 60.92, 331.25], [79.41, 297.52, 92.47, 295.35, 100.08, 339.95, 101.17, 370.41, 91.38, 348.65, 82.68, 317.1], [30.46, 269.24, 11.97, 269.24, 9.79, 252.92, 15.23, 231.17, 11.97, 220.29, 22.84, 212.67, 30.46, 202.88, 44.6, 196.35, 52.22, 182.21, 65.27, 164.81, 79.41, 156.1, 98.99, 150.67, 103.34, 138.7, 113.14, 127.82, 116.4, 100.63, 126.19, 83.22, 130.54, 78.87, 137.07, 69.08, 150.12, 69.08, 176.23, 73.43, 193.64, 89.75, 203.43, 103.89, 201.25, 119.12, 195.81, 134.35, 189.28, 147.4, 191.46, 155.02, 184.93, 165.9, 180.58, 173.51, 169.7, 181.13, 163.18, 182.21, 165.35, 195.27, 154.47, 210.5, 151.21, 218.11, 126.19, 240.96, 120.75, 252.92, 106.61, 249.66, 81.59, 255.1, 55.48, 262.71]], "area": 22617.22915, "iscrowd": 0, "image_id": 205202, "bbox": [9.79, 69.08, 193.64, 366.6], "category_id": 1, "id": 1705873, "split": "val", "sentences": [{"tokens": ["the", "kid", "on", "the", "left"], "raw": "The kid on the left.", "sent_id": 8931, "sent": "the kid on the left"}, {"tokens": ["little", "boy", "standing", "behind", "chair"], "raw": "little boy standing behind chair", "sent_id": 8932, "sent": "little boy standing behind chair"}], "file_name": "COCO_train2014_000000205202_1705873.jpg", "ann_id": 1705873, "sent_ids": [8931, 8932], "ref_id": 8459}, {"segmentation": [[30.27, 207.03, 75.68, 195.14, 134.05, 189.73, 202.16, 150.81, 262.7, 147.57, 357.84, 149.73, 370.81, 150.81, 374.05, 190.81, 472.43, 191.89, 565.41, 192.97, 600.0, 209.19, 596.76, 272.97, 605.41, 281.62, 600.0, 301.08, 542.7, 304.32, 524.32, 306.49, 508.11, 336.76, 482.16, 351.89, 442.16, 345.41, 419.46, 314.05, 128.65, 301.08, 111.35, 318.38, 83.24, 331.35, 49.73, 319.46, 37.84, 287.03, 23.78, 280.54, 16.22, 253.51, 28.11, 212.43]], "area": 78415.01124999998, "iscrowd": 0, "image_id": 232263, "bbox": [16.22, 147.57, 589.19, 204.32], "category_id": 8, "id": 394623, "split": "val", "sentences": [{"tokens": ["a", "white", "four", "door", "f", "-", "150", "truck", "parked", "in", "a", "parking", "lot"], "raw": "A white four door F-150 truck parked in a parking lot.", "sent_id": 9032, "sent": "a white four door f - 150 truck parked in a parking lot"}, {"tokens": ["a", "white", "truck", "that", "is", "parked"], "raw": "A white truck that is parked.", "sent_id": 9033, "sent": "a white truck that is parked"}], "file_name": "COCO_train2014_000000232263_394623.jpg", "ann_id": 394623, "sent_ids": [9032, 9033], "ref_id": 8497}, {"segmentation": [[223.6, 276.69, 242.42, 279.82, 258.73, 274.18, 278.81, 267.9, 296.38, 260.37, 313.94, 247.2, 319.59, 240.3, 314.57, 237.79, 332.14, 214.57, 349.08, 197.0, 381.08, 174.42, 427.0, 145.55, 425.63, 155.59, 394.88, 173.16, 369.78, 189.47, 353.47, 202.02, 332.77, 223.98, 324.61, 237.79, 303.28, 265.39, 278.18, 278.57, 256.22, 282.33, 231.12, 282.96]], "area": 1627.1872499999974, "iscrowd": 0, "image_id": 33581, "bbox": [223.6, 145.55, 203.4, 137.41], "category_id": 50, "id": 701202, "split": "val", "sentences": [{"tokens": ["the", "rightmost", "spoon"], "raw": "the rightmost spoon", "sent_id": 9038, "sent": "the rightmost spoon"}], "file_name": "COCO_train2014_000000033581_701202.jpg", "ann_id": 701202, "sent_ids": [9038], "ref_id": 8500}, {"segmentation": [[613.4, 119.69, 568.52, 142.96, 535.27, 176.21, 500.36, 242.7, 445.51, 375.69, 420.57, 478.75, 412.26, 538.6, 390.65, 563.53, 342.44, 520.31, 347.43, 450.49, 372.36, 322.49, 425.56, 214.44, 472.1, 136.31, 521.97, 96.42, 568.52, 81.45, 601.77, 81.45, 615.06, 98.08]], "area": 40222.80169999998, "iscrowd": 0, "image_id": 527345, "bbox": [342.44, 81.45, 272.62, 482.08], "category_id": 58, "id": 1922726, "split": "val", "sentences": [{"tokens": ["the", "sausage", "sitting", "on", "top", "of", "the", "beans", "and", "french", "fries"], "raw": "The sausage sitting on top of the beans and french fries.", "sent_id": 9101, "sent": "the sausage sitting on top of the beans and french fries"}, {"tokens": ["weiner", "on", "the", "right"], "raw": "weiner on the right", "sent_id": 9102, "sent": "weiner on the right"}], "file_name": "COCO_train2014_000000527345_1922726.jpg", "ann_id": 1922726, "sent_ids": [9101, 9102], "ref_id": 8520}, {"segmentation": [[237.01, 3.68, 237.01, 3.68, 377.1, 2.72, 371.35, 29.59, 355.99, 92.92, 346.4, 128.42, 347.36, 149.53, 317.61, 203.26, 288.82, 227.25, 280.19, 236.85, 265.8, 243.57, 250.44, 245.48, 241.81, 235.89, 244.69, 231.09, 253.32, 208.06, 213.02, 112.11, 211.1, 75.64, 229.33, 44.94, 233.17, 22.87, 221.66, 25.75, 237.97, 12.31, 239.89, 6.56]], "area": 27051.62035, "iscrowd": 0, "image_id": 156608, "bbox": [211.1, 2.72, 166.0, 242.76], "category_id": 1, "id": 195971, "split": "val", "sentences": [{"tokens": ["man", "in", "light", "jeans"], "raw": "Man in light jeans.", "sent_id": 9119, "sent": "man in light jeans"}, {"tokens": ["a", "man", "wearing", "stone", "wash", "jeans", "sitting", "next", "to", "a", "guy", "with", "two", "blue", "bud", "light", "beers", "and", "a", "red", "candle", "that", "is", "lit"], "raw": "a man wearing stone wash jeans sitting next to a guy with two blue Bud Light beers and a red candle that is lit", "sent_id": 9120, "sent": "a man wearing stone wash jeans sitting next to a guy with two blue bud light beers and a red candle that is lit"}], "file_name": "COCO_train2014_000000156608_195971.jpg", "ann_id": 195971, "sent_ids": [9119, 9120], "ref_id": 8528}, {"segmentation": [[218.26, 369.94, 239.33, 342.98, 251.12, 284.83, 244.38, 222.47, 238.48, 198.03, 239.33, 180.34, 235.11, 155.06, 208.99, 150.0, 203.09, 149.16, 203.09, 134.83, 165.17, 110.39, 145.79, 93.54, 132.3, 98.6, 119.66, 81.74, 132.3, 65.73, 164.33, 88.48, 186.24, 96.91, 219.94, 114.61, 262.08, 124.72, 262.08, 110.39, 252.81, 105.34, 268.82, 92.7, 289.04, 88.48, 299.16, 93.54, 304.21, 106.18, 303.37, 128.09, 303.37, 134.83, 327.81, 149.16, 337.92, 192.98, 339.61, 218.26, 331.18, 220.79, 316.85, 259.55, 317.7, 276.4, 329.49, 302.53, 341.29, 331.18, 338.76, 335.39, 310.96, 332.02, 300.0, 313.48, 273.03, 315.17, 253.65, 348.03], [258.71, 352.25, 216.57, 369.94, 257.87, 369.1, 257.87, 353.93]], "area": 22402.133049999997, "iscrowd": 0, "image_id": 513124, "bbox": [119.66, 65.73, 221.63, 304.21], "category_id": 1, "id": 462812, "split": "val", "sentences": [{"tokens": ["pitcher", "who", "just", "threw", "a", "baseball"], "raw": "Pitcher who just threw a baseball.", "sent_id": 9152, "sent": "pitcher who just threw a baseball"}, {"tokens": ["a", "baseball", "player", "pitching", "the", "ball"], "raw": "a baseball player pitching the ball", "sent_id": 9153, "sent": "a baseball player pitching the ball"}], "file_name": "COCO_train2014_000000513124_462812.jpg", "ann_id": 462812, "sent_ids": [9152, 9153], "ref_id": 8540}, {"segmentation": [[148.19, 296.53, 211.54, 301.9, 243.76, 301.9, 258.79, 296.53, 272.75, 312.64, 284.56, 309.42, 311.41, 293.31, 323.22, 289.01, 343.62, 271.83, 352.21, 272.91, 348.99, 263.24, 365.1, 244.99, 373.69, 220.29, 374.77, 197.74, 364.03, 190.22, 354.36, 193.44, 343.62, 189.15, 350.07, 175.19, 360.81, 166.6, 365.1, 156.93, 364.03, 145.12, 362.95, 141.9, 345.77, 136.53, 339.33, 138.68, 315.7, 136.53, 294.23, 129.01, 260.94, 122.57, 233.02, 131.16, 210.47, 142.97, 188.99, 150.49, 193.29, 159.08, 134.23, 179.48, 141.74, 207.4, 143.89, 209.55, 169.66, 207.4, 171.81, 210.62, 165.37, 220.29, 151.41, 231.03, 151.41, 236.4, 158.93, 246.06, 165.37, 248.21, 160.0, 254.65, 152.48, 256.8, 147.11, 286.86, 149.26, 292.23]], "area": 33025.87994999999, "iscrowd": 0, "image_id": 550308, "bbox": [134.23, 122.57, 240.54, 190.07], "category_id": 54, "id": 311410, "split": "val", "sentences": [{"tokens": ["a", "breakfast", "sandwich", "with", "egg"], "raw": "A breakfast sandwich with egg.", "sent_id": 9180, "sent": "a breakfast sandwich with egg"}, {"tokens": ["a", "sandwich", "positioned", "in", "the", "middle", "of", "a", "plate", "with", "a", "fried", "egg", "ontop"], "raw": "A sandwich positioned in the middle of a plate with a fried egg ontop.", "sent_id": 9181, "sent": "a sandwich positioned in the middle of a plate with a fried egg ontop"}], "file_name": "COCO_train2014_000000550308_311410.jpg", "ann_id": 311410, "sent_ids": [9180, 9181], "ref_id": 8551}, {"segmentation": [[352.25, 76.43, 341.29, 72.22, 332.02, 78.12, 331.18, 87.39, 325.28, 99.19, 322.75, 116.88, 326.97, 137.95, 321.07, 167.44, 323.6, 175.03, 337.92, 177.56, 351.4, 178.4, 351.4, 163.23, 355.62, 153.96, 376.69, 154.8, 394.38, 152.28, 391.85, 146.38, 380.06, 143.85, 357.3, 127.84, 353.93, 119.41, 358.99, 108.46, 358.99, 100.03, 361.52, 93.29, 357.3, 76.43], [322.75, 191.88, 327.81, 198.62, 327.81, 207.05, 342.98, 223.9, 355.62, 224.75, 353.09, 181.77, 324.44, 189.35], [331.18, 223.9, 316.85, 234.02, 337.08, 235.7, 336.24, 226.43], [294.1, 251.71, 311.8, 276.15, 316.01, 255.93, 292.42, 250.03], [340.45, 262.67, 337.92, 276.15, 368.26, 272.78, 348.88, 261.83, 339.61, 262.67]], "area": 5283.476699999997, "iscrowd": 0, "image_id": 79912, "bbox": [292.42, 72.22, 101.96, 203.93], "category_id": 1, "id": 190993, "split": "val", "sentences": [{"tokens": ["a", "woman", "on", "a", "bike", "and", "her", "dog"], "raw": "a woman on a bike and her dog", "sent_id": 9190, "sent": "a woman on a bike and her dog"}, {"tokens": ["a", "woman", "in", "blue", "dragging", "her", "bike", "in", "a", "park"], "raw": "A woman in blue dragging her bike in a park", "sent_id": 9191, "sent": "a woman in blue dragging her bike in a park"}], "file_name": "COCO_train2014_000000079912_190993.jpg", "ann_id": 190993, "sent_ids": [9190, 9191], "ref_id": 8556}, {"segmentation": [[23.73, 322.19, 19.42, 288.75, 25.89, 262.86, 45.3, 235.9, 78.74, 214.32, 133.75, 201.38, 183.37, 167.94, 254.56, 131.27, 328.99, 110.77, 423.91, 110.77, 467.06, 88.12, 494.02, 106.46, 500.49, 119.4, 535.01, 131.27, 583.55, 120.48, 625.62, 128.03, 640.0, 142.05, 640.0, 249.92, 621.3, 267.18, 598.65, 311.4, 561.98, 364.25, 508.04, 411.72, 427.15, 461.33, 328.99, 469.96, 256.72, 457.02, 202.79, 417.11, 163.96, 396.61, 77.66, 361.02, 44.22, 342.68, 32.36, 329.74]], "area": 160989.97769999996, "iscrowd": 0, "image_id": 177314, "bbox": [19.42, 88.12, 620.58, 381.84], "category_id": 51, "id": 713882, "split": "val", "sentences": [{"tokens": ["a", "white", "bowl", "of", "mushrooms", "and", "carrots"], "raw": "A white bowl of mushrooms and carrots", "sent_id": 9200, "sent": "a white bowl of mushrooms and carrots"}, {"tokens": ["a", "bowl", "of", "mushrooms"], "raw": "A bowl of mushrooms.", "sent_id": 9201, "sent": "a bowl of mushrooms"}], "file_name": "COCO_train2014_000000177314_713882.jpg", "ann_id": 713882, "sent_ids": [9200, 9201], "ref_id": 8561}, {"segmentation": [[192.98, 214.04, 191.29, 199.72, 178.65, 186.24, 145.79, 167.7, 108.71, 166.01, 63.2, 177.81, 36.24, 204.78, 19.38, 252.81, 21.91, 285.67, 35.39, 313.48, 55.62, 337.08, 93.54, 353.09, 130.62, 353.09, 167.7, 334.55, 193.82, 295.79, 205.62, 262.08]], "area": 27111.970599999993, "iscrowd": 0, "image_id": 322411, "bbox": [19.38, 166.01, 186.24, 187.08], "category_id": 51, "id": 1039433, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "pasta", "next", "to", "a", "bowl", "of", "salad"], "raw": "a bowl of pasta next to a bowl of salad", "sent_id": 9202, "sent": "a bowl of pasta next to a bowl of salad"}, {"tokens": ["the", "bowl", "with", "noodles", "in", "it"], "raw": "The bowl with noodles in it.", "sent_id": 9203, "sent": "the bowl with noodles in it"}], "file_name": "COCO_train2014_000000322411_1039433.jpg", "ann_id": 1039433, "sent_ids": [9202, 9203], "ref_id": 8562}, {"segmentation": [[0.92, 86.04, 19.33, 92.49, 29.45, 93.41, 48.77, 70.4, 51.53, 61.2, 62.58, 39.11, 78.22, 24.39, 91.11, 18.87, 93.87, 18.87, 91.11, 35.43, 98.47, 54.76, 102.15, 81.44, 102.15, 97.09, 92.03, 117.33, 83.74, 143.1, 75.46, 186.35, 94.79, 218.56, 119.63, 246.17, 150.92, 291.26, 129.76, 280.22, 156.44, 337.27, 161.05, 349.24, 171.17, 380.53, 137.12, 332.67, 137.12, 331.75, 135.28, 341.88, 140.8, 404.45, 124.23, 377.77, 114.11, 420.1, 0.0, 422.86, 0.92, 85.12]], "area": 40812.91910000001, "iscrowd": 0, "image_id": 253335, "bbox": [0.0, 18.87, 171.17, 403.99], "category_id": 19, "id": 56047, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "horse", "with", "white", "stripe", "is", "handled", "by", "a", "woman"], "raw": "A dark brown horse with white stripe is handled by a woman.", "sent_id": 9220, "sent": "a dark brown horse with white stripe is handled by a woman"}, {"tokens": ["a", "brown", "and", "white", "horse"], "raw": "A brown and white horse.", "sent_id": 9221, "sent": "a brown and white horse"}], "file_name": "COCO_train2014_000000253335_56047.jpg", "ann_id": 56047, "sent_ids": [9220, 9221], "ref_id": 8570}, {"segmentation": [[414.2, 423.83, 369.62, 418.08, 313.53, 419.52, 256.0, 428.14, 205.66, 409.45, 176.9, 406.57, 168.27, 408.01, 116.49, 367.74, 93.48, 326.03, 136.63, 249.81, 224.36, 198.03, 332.22, 177.9, 398.38, 170.71, 428.58, 170.71, 427.15, 409.45]], "area": 67817.70485, "iscrowd": 0, "image_id": 310536, "bbox": [93.48, 170.71, 335.1, 257.43], "category_id": 28, "id": 282045, "split": "val", "sentences": [{"tokens": ["a", "large", "white", "umbrella", "providing", "shade", "for", "man"], "raw": "A large white umbrella providing shade for man.", "sent_id": 9232, "sent": "a large white umbrella providing shade for man"}, {"tokens": ["closer", "white", "umbrella"], "raw": "closer white umbrella", "sent_id": 9233, "sent": "closer white umbrella"}], "file_name": "COCO_train2014_000000310536_282045.jpg", "ann_id": 282045, "sent_ids": [9232, 9233], "ref_id": 8575}, {"segmentation": [[322.06, 256.79, 322.77, 246.17, 319.22, 234.12, 331.27, 219.95, 351.81, 210.74, 376.61, 195.16, 418.41, 189.49, 445.33, 188.78, 473.67, 189.49, 487.84, 193.03, 510.51, 210.03, 538.14, 244.75, 550.89, 270.25, 558.68, 292.22, 532.47, 349.6, 338.35, 365.19, 316.39, 314.89, 316.39, 268.13]], "area": 34723.18884999999, "iscrowd": 0, "image_id": 9822, "bbox": [316.39, 188.78, 242.29, 176.41], "category_id": 60, "id": 1081535, "split": "val", "sentences": [{"tokens": ["a", "donut", "to", "the", "right", "of", "two", "other", "donuts"], "raw": "A donut to the right of two other donuts.", "sent_id": 9239, "sent": "a donut to the right of two other donuts"}], "file_name": "COCO_train2014_000000009822_1081535.jpg", "ann_id": 1081535, "sent_ids": [9239], "ref_id": 8578}, {"segmentation": [[282.74, 81.68, 290.44, 128.81, 302.94, 187.47, 301.02, 212.47, 296.21, 227.86, 294.28, 248.06, 314.48, 259.6, 317.36, 249.98, 319.29, 239.4, 322.17, 218.24, 324.1, 192.28, 324.1, 193.24, 341.41, 224.01, 348.14, 253.83, 366.41, 258.64, 374.11, 248.06, 370.26, 225.94, 360.64, 194.2, 356.8, 174.97, 351.02, 149.96, 343.33, 121.11, 348.14, 94.18, 339.48, 56.68, 324.1, 33.6, 317.36, 14.36, 296.21, 23.98, 291.4, 48.98, 277.93, 73.03, 280.82, 89.38]], "area": 12506.419750000001, "iscrowd": 0, "image_id": 524966, "bbox": [277.93, 14.36, 96.18, 245.24], "category_id": 1, "id": 548632, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "wearing", "yellow", "shoes"], "raw": "A young boy wearing yellow shoes.", "sent_id": 9300, "sent": "a young boy wearing yellow shoes"}, {"tokens": ["the", "boy", "in", "the", "middle", "with", "yellow", "shoes"], "raw": "The boy in the middle with yellow shoes.", "sent_id": 9301, "sent": "the boy in the middle with yellow shoes"}], "file_name": "COCO_train2014_000000524966_548632.jpg", "ann_id": 548632, "sent_ids": [9300, 9301], "ref_id": 8602}, {"segmentation": [[46.97, 298.82, 52.13, 327.69, 66.56, 385.44, 76.87, 442.15, 72.75, 485.46, 54.19, 492.68, 54.19, 505.05, 173.8, 514.33, 173.8, 486.49, 97.5, 481.33, 96.47, 454.52, 133.59, 446.28, 137.71, 411.22, 139.78, 377.19, 155.24, 306.04, 75.84, 310.16, 66.56, 293.66], [280.01, 314.29, 259.39, 321.51, 262.48, 357.6, 260.42, 383.37, 261.45, 418.43, 269.7, 440.09, 276.92, 438.03, 274.86, 479.27, 302.7, 492.68, 298.57, 430.81, 354.26, 416.37, 351.16, 456.59, 380.04, 461.74, 377.97, 414.31, 364.57, 367.91, 364.57, 347.28, 355.29, 343.16, 326.42, 371.0, 329.51, 393.69, 347.04, 400.9, 340.85, 411.22, 331.57, 411.22, 319.2, 400.9, 314.04, 399.87, 306.82, 378.22, 288.26, 400.9, 275.89, 374.09, 284.14, 362.75, 275.89, 357.6, 268.67, 357.6, 277.95, 327.69]], "area": 23706.33515, "iscrowd": 0, "image_id": 240500, "bbox": [46.97, 293.66, 333.07, 220.67], "category_id": 15, "id": 574215, "split": "val", "sentences": [{"tokens": ["a", "wooden", "bench", "with", "a", "giant", "white", "bird", "standing", "on", "it"], "raw": "A wooden bench with a giant white bird standing on it.", "sent_id": 9345, "sent": "a wooden bench with a giant white bird standing on it"}, {"tokens": ["bench", "with", "a", "large", "bird", "on", "it", "and", "a", "person", "in", "a", "long", "black", "coat", "in", "front", "of", "it"], "raw": "Bench with a large bird on it and a person in a long black coat in front of it", "sent_id": 9346, "sent": "bench with a large bird on it and a person in a long black coat in front of it"}], "file_name": "COCO_train2014_000000240500_574215.jpg", "ann_id": 574215, "sent_ids": [9345, 9346], "ref_id": 8618}, {"segmentation": [[97.8, 618.79, 123.69, 581.39, 133.75, 520.99, 132.31, 483.6, 128.0, 421.75, 112.18, 380.04, 122.25, 336.9, 143.82, 299.51, 176.9, 283.69, 169.71, 329.71, 176.9, 391.55, 182.65, 456.27, 151.01, 506.61, 155.33, 555.51, 146.7, 536.81, 138.07, 600.09, 123.69, 631.73, 102.11, 623.1], [224.36, 191.64, 235.87, 161.44, 247.37, 187.33, 261.75, 177.26, 274.7, 170.07, 286.2, 181.57, 270.38, 193.08, 276.13, 203.15, 327.91, 197.39, 304.9, 220.4, 289.08, 227.6, 291.96, 259.24, 271.82, 264.99, 250.25, 266.43, 227.24, 211.78, 230.11, 193.08, 237.3, 170.07], [302.02, 516.67, 325.03, 579.96, 307.78, 594.34, 291.96, 564.13, 284.76, 539.69], [243.06, 489.35, 240.18, 516.67, 248.81, 551.19, 248.81, 522.43, 247.37, 492.22], [289.08, 620.22, 293.39, 634.61, 312.09, 630.29, 304.9, 608.72, 289.08, 590.02]], "area": 20201.057399999998, "iscrowd": 0, "image_id": 186255, "bbox": [97.8, 161.44, 230.11, 473.17], "category_id": 24, "id": 591531, "split": "val", "sentences": [{"tokens": ["a", "zebra", "behind", "another", "zebra", "facing", "the", "camera"], "raw": "A zebra behind another zebra facing the camera.", "sent_id": 9418, "sent": "a zebra behind another zebra facing the camera"}], "file_name": "COCO_train2014_000000186255_591531.jpg", "ann_id": 591531, "sent_ids": [9418], "ref_id": 8649}, {"segmentation": [[128.49, 202.3, 123.16, 214.45, 114.86, 216.53, 104.48, 207.63, 111.3, 191.03, 110.41, 180.36, 106.85, 169.39, 111.0, 160.2, 113.08, 145.68, 116.04, 141.82, 120.19, 149.23, 128.2, 147.46, 137.39, 134.41, 138.57, 148.94, 146.58, 154.27, 169.11, 162.57, 188.97, 167.02, 195.79, 170.87, 194.3, 181.25, 195.79, 185.4, 197.86, 186.88, 188.37, 209.71, 187.19, 221.86, 193.12, 230.46, 202.01, 230.76, 215.35, 220.97, 223.35, 217.12, 236.99, 221.86, 241.14, 225.12, 240.25, 228.98, 236.99, 234.61, 241.44, 247.95, 247.96, 257.73, 247.37, 281.45, 247.07, 290.04, 246.48, 297.75, 244.7, 304.27, 240.84, 303.68, 239.07, 266.03, 229.28, 257.43, 208.83, 245.58, 202.01, 243.8, 197.56, 250.62, 191.34, 272.85, 196.67, 296.56, 202.01, 311.39, 201.42, 322.65, 203.79, 328.28, 203.2, 333.62, 196.97, 333.92, 187.78, 334.51, 193.41, 322.65, 194.01, 310.5, 185.71, 287.37, 178.89, 305.16, 178.3, 321.17, 179.18, 324.43, 179.48, 327.39, 176.81, 332.14, 178.3, 339.55, 162.88, 343.99, 160.51, 343.4, 167.33, 326.8, 171.48, 315.24, 173.55, 301.9, 171.77, 295.97, 171.77, 288.86, 176.52, 279.67, 176.52, 265.14, 162.29, 245.87, 155.47, 235.2, 151.32, 224.83, 151.32, 216.53, 143.02, 196.07, 139.76, 197.55, 128.79, 200.81]], "area": 9376.428300000007, "iscrowd": 0, "image_id": 517095, "bbox": [104.48, 134.41, 143.48, 209.58], "category_id": 19, "id": 59554, "split": "val", "sentences": [{"tokens": ["a", "horse", "is", "in", "right", "side", "of", "the", "driving", "person"], "raw": "a horse is in right side of the driving person", "sent_id": 9485, "sent": "a horse is in right side of the driving person"}], "file_name": "COCO_train2014_000000517095_59554.jpg", "ann_id": 59554, "sent_ids": [9485], "ref_id": 8678}, {"segmentation": [[315.68, 474.95, 239.28, 473.51, 227.75, 438.92, 247.93, 418.74, 253.69, 400.0, 233.51, 343.78, 265.23, 338.02, 294.05, 313.51, 278.2, 267.39, 256.58, 264.5, 234.95, 222.7, 266.67, 189.55, 255.14, 114.59, 232.07, 101.62, 226.31, 77.12, 265.23, 52.61, 281.08, 56.94, 328.65, 46.85, 386.31, 65.59, 423.78, 104.5, 423.78, 120.36, 400.72, 139.1, 390.63, 157.84, 383.42, 165.05, 422.34, 192.43, 471.35, 290.45, 464.14, 314.95, 459.82, 320.72, 480.0, 372.61, 474.23, 474.95, 449.73, 461.98, 438.2, 405.77, 374.77, 359.64, 341.62, 369.73, 332.97, 361.08, 345.95, 424.5, 332.97, 467.75]], "area": 70055.1109, "iscrowd": 0, "image_id": 468373, "bbox": [226.31, 46.85, 253.69, 428.1], "category_id": 88, "id": 1163134, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "teddy", "bear"], "raw": "A dark brown teddy bear.", "sent_id": 9502, "sent": "a dark brown teddy bear"}, {"tokens": ["a", "dark", "brown", "bear"], "raw": "A dark brown bear.", "sent_id": 9503, "sent": "a dark brown bear"}], "file_name": "COCO_train2014_000000468373_1163134.jpg", "ann_id": 1163134, "sent_ids": [9502, 9503], "ref_id": 8683}, {"segmentation": [[3.34, 143.37, 18.03, 142.18, 37.48, 153.3, 40.66, 156.87, 38.67, 158.46, 41.06, 162.43, 31.53, 160.84, 34.7, 170.37, 30.34, 174.34, 27.96, 178.31, 23.59, 178.7, 20.81, 179.5, 20.02, 181.09, 24.38, 189.03, 35.5, 206.89, 38.28, 226.34, 50.19, 245.8, 50.58, 253.34, 50.58, 256.91, 55.35, 270.01, 58.52, 274.38, 56.54, 281.13, 59.32, 291.05, 60.51, 298.6, 72.42, 314.48, 61.7, 314.87, 56.54, 306.93, 52.57, 303.76, 60.11, 326.39, 66.46, 355.37, 59.72, 381.17, 57.33, 399.03, 64.08, 405.78, 67.66, 407.37, 77.58, 406.58, 81.15, 408.56, 81.15, 415.31, 66.86, 421.27, 44.63, 427.62, 36.69, 426.03, 24.78, 431.19, 24.38, 431.19, 17.63, 430.4, 16.44, 424.84, 14.46, 420.47, 5.72, 414.91]], "area": 13234.739950000001, "iscrowd": 0, "image_id": 69500, "bbox": [3.34, 142.18, 77.81, 289.01], "category_id": 1, "id": 2153953, "split": "val", "sentences": [{"tokens": ["man", "standing", "bottom", "left", "side"], "raw": "man standing bottom left side.", "sent_id": 9566, "sent": "man standing bottom left side"}, {"tokens": ["a", "man", "in", "a", "dark", "suit", "and", "tam", "looking", "at", "an", "elephant"], "raw": "A man in a dark suit and tam looking at an elephant.", "sent_id": 9567, "sent": "a man in a dark suit and tam looking at an elephant"}], "file_name": "COCO_train2014_000000069500_2153953.jpg", "ann_id": 2153953, "sent_ids": [9566, 9567], "ref_id": 8709}, {"segmentation": [[312.83, 1.61, 330.31, 13.57, 350.55, 43.93, 361.59, 73.38, 362.51, 110.18, 357.91, 120.3, 350.55, 124.9, 340.43, 125.82, 333.99, 122.14, 329.39, 143.3, 320.19, 163.55, 304.55, 193.91, 299.95, 204.03, 299.03, 214.15, 299.95, 227.03, 299.95, 239.91, 285.23, 238.99, 276.03, 238.99, 274.19, 240.83, 224.5, 241.75, 221.74, 238.99, 212.54, 240.83, 145.37, 248.19, 143.53, 241.75, 129.73, 245.43, 82.81, 249.11, 77.29, 240.83, 63.49, 158.94, 63.49, 108.34, 71.77, 100.98, 100.29, 84.42, 123.29, 62.34, 129.73, 53.13, 134.33, 42.09, 127.89, 34.73, 119.61, 32.89, 120.53, 23.69, 133.41, 22.77, 134.33, 10.81, 131.57, 5.29]], "area": 58543.26659999999, "iscrowd": 0, "image_id": 155268, "bbox": [63.49, 1.61, 299.02, 247.5], "category_id": 63, "id": 112954, "split": "val", "sentences": [{"tokens": ["a", "green", "color", "sofa", "where", "opposite", "side", "of", "woman"], "raw": "A green color sofa where opposite side of woman.", "sent_id": 9570, "sent": "a green color sofa where opposite side of woman"}], "file_name": "COCO_train2014_000000155268_112954.jpg", "ann_id": 112954, "sent_ids": [9570], "ref_id": 8710}, {"segmentation": [[185.06, 370.12, 199.72, 366.45, 207.05, 368.28, 208.88, 394.85, 205.21, 421.42, 241.86, 421.42, 246.44, 410.43, 276.67, 406.76, 286.75, 398.52, 301.41, 394.85, 306.9, 394.85, 312.4, 405.85, 323.39, 421.42, 360.04, 418.67, 355.46, 382.03, 370.12, 344.46, 371.95, 301.41, 365.54, 284.0, 382.03, 261.1, 381.11, 251.02, 377.45, 246.44, 375.61, 223.54, 376.53, 206.13, 385.69, 178.65, 387.52, 162.15, 397.6, 135.59, 393.94, 124.59, 388.44, 104.44, 389.35, 82.45, 393.94, 50.39, 385.69, 33.9, 381.11, 22.9, 371.03, 42.14, 369.2, 54.97, 358.21, 53.14, 340.8, 59.55, 330.72, 64.13, 305.07, 47.64, 294.99, 31.15, 296.83, 48.55, 298.66, 62.3, 308.74, 78.79, 313.32, 82.45, 282.17, 103.52, 273.01, 125.51, 261.1, 145.66, 252.85, 168.57, 213.46, 169.48, 179.56, 177.73, 158.49, 188.72, 138.34, 207.05, 135.59, 223.54, 135.59, 244.61, 133.75, 262.01, 134.67, 300.49, 139.25, 331.64, 144.75, 344.46, 151.16, 377.45, 158.49, 391.19, 161.24, 406.76, 163.07, 420.5, 163.07, 420.5, 194.22, 420.5, 186.89, 402.18, 183.23, 388.44, 182.31, 375.61, 184.14, 370.12]], "area": 67241.49215000003, "iscrowd": 0, "image_id": 441972, "bbox": [133.75, 22.9, 263.85, 398.52], "category_id": 19, "id": 56491, "split": "val", "sentences": [{"tokens": ["the", "horse", "in", "the", "left", "side"], "raw": "the horse in the left side", "sent_id": 9571, "sent": "the horse in the left side"}], "file_name": "COCO_train2014_000000441972_56491.jpg", "ann_id": 56491, "sent_ids": [9571], "ref_id": 8711}, {"segmentation": [[44.58, 573.4, 63.28, 566.21, 87.73, 554.71, 89.17, 547.52, 81.98, 530.26, 76.22, 508.68, 87.73, 471.29, 107.87, 475.61, 163.96, 475.61, 176.9, 475.61, 192.72, 451.16, 209.98, 409.45, 232.99, 396.5, 244.49, 385.0, 217.17, 350.48, 186.97, 346.17, 182.65, 333.22, 178.34, 321.72, 178.34, 311.65, 188.4, 304.46, 195.6, 294.39, 207.1, 290.08, 212.85, 290.08, 222.92, 290.08, 231.55, 290.08, 240.18, 288.64, 240.18, 288.64, 234.43, 275.7, 230.11, 275.7, 208.54, 254.12, 195.6, 254.12, 181.21, 239.74, 184.09, 216.73, 184.09, 192.28, 169.71, 176.46, 159.64, 166.39, 136.63, 166.39, 116.49, 163.52, 107.87, 163.52, 92.04, 176.46, 87.73, 187.97, 87.73, 205.22, 87.73, 216.73, 96.36, 228.23, 100.67, 236.86, 102.11, 246.93, 107.87, 259.88, 107.87, 262.75, 109.3, 267.07, 106.43, 271.38, 103.55, 274.26, 96.36, 277.13, 81.98, 288.64, 79.1, 311.65, 73.35, 333.22, 64.72, 343.29, 54.65, 356.23, 47.46, 353.36, 44.58, 351.92, 31.64, 349.04, 14.38, 337.54, 0.0, 341.85, 8.63, 357.67, 15.82, 367.74, 4.31, 363.43, 2.88, 374.93, 14.38, 382.12, 20.13, 385.0, 21.57, 389.31, 21.57, 390.75, 34.52, 393.63, 40.27, 393.63, 50.34, 400.82, 46.02, 408.01, 38.83, 413.76, 34.52, 423.83, 30.2, 432.46, 28.76, 456.91, 25.89, 494.3, 20.13, 494.3, 18.7, 507.25, 18.7, 523.07, 15.82, 541.76, 15.82, 554.71, 15.82, 566.21]], "area": 48157.44045000002, "iscrowd": 0, "image_id": 28154, "bbox": [0.0, 163.52, 244.49, 409.88], "category_id": 1, "id": 214806, "split": "val", "sentences": [{"tokens": ["lady", "on", "left"], "raw": "lady on left", "sent_id": 9588, "sent": "lady on left"}, {"tokens": ["a", "woman", "in", "a", "black", "top", "holding", "a", "video", "game", "remote"], "raw": "A woman in a black top holding a video game remote.", "sent_id": 9589, "sent": "a woman in a black top holding a video game remote"}], "file_name": "COCO_train2014_000000028154_214806.jpg", "ann_id": 214806, "sent_ids": [9588, 9589], "ref_id": 8720}, {"segmentation": [[313.81, 269.76, 330.32, 279.4, 359.23, 269.76, 390.88, 272.52, 399.14, 278.02, 411.53, 279.4, 419.78, 279.4, 423.91, 286.28, 426.67, 287.66, 430.8, 316.56, 422.54, 322.06, 422.54, 331.7, 418.41, 384.0, 309.68, 382.62, 309.68, 368.86, 315.18, 356.47, 311.05, 353.72, 297.29, 352.34, 295.91, 345.46, 280.77, 341.33, 268.39, 341.33, 258.75, 346.84, 254.62, 352.34, 254.62, 359.23, 258.75, 366.11, 258.75, 368.86, 250.49, 368.86, 239.48, 342.71, 238.11, 339.96, 238.11, 327.57, 236.73, 322.06, 236.73, 313.81, 236.73, 306.92, 236.73, 301.42, 236.73, 293.16, 243.61, 291.78, 246.37, 333.08, 295.91, 331.7, 304.17, 331.7, 309.68, 304.17, 308.3, 295.91, 309.68, 284.9, 313.81, 279.4, 315.18, 273.89]], "area": 13887.018000000002, "iscrowd": 0, "image_id": 520696, "bbox": [236.73, 269.76, 194.07, 114.24], "category_id": 63, "id": 99434, "split": "val", "sentences": [{"tokens": ["back", "of", "a", "sofa", "with", "a", "white", "blanket", "draped", "over", "it"], "raw": "back of a sofa with a white blanket draped over it", "sent_id": 9638, "sent": "back of a sofa with a white blanket draped over it"}, {"tokens": ["a", "brown", "sofa", "with", "a", "towel", "draped", "over", "it"], "raw": "A brown sofa with a towel draped over it.", "sent_id": 9639, "sent": "a brown sofa with a towel draped over it"}], "file_name": "COCO_train2014_000000520696_99434.jpg", "ann_id": 99434, "sent_ids": [9638, 9639], "ref_id": 8738}, {"segmentation": [[234.39, 470.44, 231.06, 526.96, 221.09, 570.18, 207.79, 606.75, 201.14, 626.7, 199.48, 630.03, 182.86, 631.69, 174.55, 626.7, 161.25, 618.39, 144.62, 600.1, 134.65, 558.55, 146.29, 510.34, 156.26, 467.12, 159.58, 458.81, 191.17, 453.82, 212.78, 457.14, 226.08, 463.79, 237.71, 468.78]], "area": 13125.2631, "iscrowd": 0, "image_id": 20291, "bbox": [134.65, 453.82, 103.06, 177.87], "category_id": 46, "id": 1874306, "split": "val", "sentences": [{"tokens": ["the", "clear", "wine", "glass", "with", "the", "lower", "level", "of", "wine"], "raw": "The clear wine glass with the lower level of wine", "sent_id": 9656, "sent": "the clear wine glass with the lower level of wine"}, {"tokens": ["central", "wineglass", "on", "table"], "raw": "central wineglass on table", "sent_id": 9657, "sent": "central wineglass on table"}], "file_name": "COCO_train2014_000000020291_1874306.jpg", "ann_id": 1874306, "sent_ids": [9656, 9657], "ref_id": 8742}, {"segmentation": [[21.98, 372.95, 17.82, 376.8, 15.26, 397.94, 17.18, 425.49, 18.14, 457.21, 16.86, 470.03, 14.62, 491.49, 12.69, 502.7, 20.06, 501.42, 21.02, 479.32, 26.15, 453.05, 28.39, 437.99, 34.16, 415.88, 38.64, 430.3, 34.16, 450.8, 39.6, 463.3, 41.21, 481.88, 43.13, 492.13, 42.81, 506.87, 48.89, 506.87, 53.38, 498.86, 62.99, 491.49, 67.8, 499.18, 75.48, 494.37, 73.56, 469.38, 77.73, 455.29, 78.05, 441.51, 81.89, 425.17, 86.06, 416.2, 93.43, 395.7, 97.27, 376.16, 91.82, 360.14, 96.31, 355.65, 122.9, 343.48, 133.15, 337.39, 140.2, 325.54, 147.57, 328.42, 145.65, 321.7, 142.76, 316.57, 150.77, 315.29, 148.85, 310.48, 138.28, 312.08, 134.11, 300.87, 127.7, 297.35, 124.5, 306.96, 117.13, 302.79, 123.54, 317.21, 106.24, 323.3, 94.39, 326.18, 69.72, 328.1, 64.27, 330.99, 57.22, 344.76, 35.12, 358.54, 28.71, 359.82, 19.74, 372.95]], "area": 10976.508399999995, "iscrowd": 0, "image_id": 411778, "bbox": [12.69, 297.35, 138.08, 209.52], "category_id": 25, "id": 595246, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "on", "the", "left", "in", "the", "right", "hand", "picture"], "raw": "the giraffe on the left in the right hand picture", "sent_id": 9721, "sent": "the giraffe on the left in the right hand picture"}, {"tokens": ["giraffie", "in", "back"], "raw": "giraffie in back", "sent_id": 9722, "sent": "giraffie in back"}], "file_name": "COCO_train2014_000000411778_595246.jpg", "ann_id": 595246, "sent_ids": [9721, 9722], "ref_id": 8768}, {"segmentation": [[158.33, 345.44, 142.97, 332.0, 135.3, 298.42, 131.46, 273.47, 136.26, 123.78, 266.76, 119.94, 308.98, 126.66, 352.16, 145.85, 411.65, 168.88, 476.9, 190.95, 506.64, 203.42, 510.48, 224.53, 505.68, 237.97, 480.73, 248.52, 446.19, 256.2, 416.44, 261.0, 392.46, 268.67, 366.55, 283.07, 309.93, 310.89, 291.7, 322.41, 266.76, 334.88, 238.93, 343.52, 205.34, 341.6, 169.84, 340.64, 158.33, 342.56]], "area": 57845.44625, "iscrowd": 0, "image_id": 350826, "bbox": [131.46, 119.94, 379.02, 225.5], "category_id": 7, "id": 172812, "split": "val", "sentences": [{"tokens": ["a", "long", "train"], "raw": "A long train.", "sent_id": 9786, "sent": "a long train"}, {"tokens": ["a", "train", "is", "moving", "toward", "the", "front"], "raw": "A train is moving toward the front.", "sent_id": 9787, "sent": "a train is moving toward the front"}], "file_name": "COCO_train2014_000000350826_172812.jpg", "ann_id": 172812, "sent_ids": [9786, 9787], "ref_id": 8793}, {"segmentation": [[5.39, 277.21, 19.42, 270.74, 35.6, 268.58, 43.15, 280.45, 50.7, 293.39, 49.62, 299.87, 75.51, 297.71, 98.16, 300.94, 110.02, 309.57, 122.97, 312.81, 129.44, 303.1, 131.6, 294.47, 155.33, 294.47, 161.8, 318.2, 163.96, 332.22, 166.11, 323.6, 163.96, 296.63, 152.09, 283.69, 113.26, 266.43, 63.64, 235.15, 2.16, 226.52, 1.08, 271.82, 1.08, 276.13]], "area": 6802.0084, "iscrowd": 0, "image_id": 141581, "bbox": [1.08, 226.52, 165.03, 105.7], "category_id": 3, "id": 344793, "split": "val", "sentences": [{"tokens": ["a", "black", "car", "behind", "bags", "of", "ice"], "raw": "A black car behind bags of ice.", "sent_id": 9792, "sent": "a black car behind bags of ice"}, {"tokens": ["a", "black", "car", "parked", "next", "to", "a", "black", "trash", "can"], "raw": "A black car parked next to a black trash can", "sent_id": 9793, "sent": "a black car parked next to a black trash can"}], "file_name": "COCO_train2014_000000141581_344793.jpg", "ann_id": 344793, "sent_ids": [9792, 9793], "ref_id": 8796}, {"segmentation": [[259.69, 106.18, 266.36, 97.08, 254.83, 86.16, 257.87, 66.13, 266.97, 49.75, 284.56, 36.4, 364.04, 25.48, 374.97, 54.61, 371.33, 76.45, 365.26, 95.87]], "area": 7392.009050000001, "iscrowd": 0, "image_id": 428149, "bbox": [254.83, 25.48, 120.14, 80.7], "category_id": 1, "id": 1720856, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "black", "head", "wrap", "talking", "on", "a", "phone", "in", "a", "blue", "car"], "raw": "A man with a black head wrap talking on a phone in a blue car.", "sent_id": 9806, "sent": "a man with a black head wrap talking on a phone in a blue car"}, {"tokens": ["man", "in", "a", "car", "talking", "on", "a", "cellphone"], "raw": "Man in a car talking on a cellphone", "sent_id": 9807, "sent": "man in a car talking on a cellphone"}], "file_name": "COCO_train2014_000000428149_1720856.jpg", "ann_id": 1720856, "sent_ids": [9806, 9807], "ref_id": 8802}, {"segmentation": [[0.96, 354.49, 2.87, 314.37, 6.69, 305.77, 19.11, 299.09, 19.11, 277.12, 26.75, 256.1, 40.12, 240.82, 58.27, 239.86, 78.33, 250.37, 91.7, 270.43, 110.81, 297.18, 128.0, 320.1, 130.87, 346.85, 129.91, 371.69, 124.18, 393.66, 139.47, 421.36, 89.79, 420.41, 85.97, 406.08, 76.42, 378.37, 47.76, 394.61, 46.81, 374.55, 40.12, 345.9, 37.26, 334.43, 27.7, 336.34, 25.79, 362.13, 17.19, 394.61, 5.73, 401.3, 2.87, 401.3, 0.0, 389.84, 1.91, 366.91]], "area": 15571.426250000004, "iscrowd": 0, "image_id": 535666, "bbox": [0.0, 239.86, 139.47, 181.5], "category_id": 1, "id": 1205821, "split": "val", "sentences": [{"tokens": ["woman", "in", "the", "background", "looking", "at", "her", "phone"], "raw": "Woman in the background looking at her phone.", "sent_id": 9820, "sent": "woman in the background looking at her phone"}, {"tokens": ["a", "woman", "waring", "a", "black", "dress", "and", "sitting", "in", "front", "of", "a", "table"], "raw": "A woman waring a black dress and sitting in front of a table", "sent_id": 9821, "sent": "a woman waring a black dress and sitting in front of a table"}], "file_name": "COCO_train2014_000000535666_1205821.jpg", "ann_id": 1205821, "sent_ids": [9820, 9821], "ref_id": 8807}, {"segmentation": [[289.12, 197.24, 289.12, 162.89, 292.41, 152.54, 296.18, 148.3, 294.77, 146.89, 298.06, 143.6, 303.24, 129.95, 309.35, 119.6, 313.59, 113.95, 322.06, 109.24, 319.24, 103.6, 318.29, 101.72, 315.47, 89.01, 316.41, 78.66, 318.76, 68.78, 326.47, 62.64, 328.52, 59.97, 331.39, 60.59, 337.12, 59.97, 342.45, 59.97, 348.18, 61.41, 353.71, 63.25, 356.78, 67.35, 362.72, 72.06, 365.39, 72.88, 376.86, 76.56, 380.34, 79.23, 379.73, 80.66, 377.06, 82.09, 374.19, 85.78, 371.53, 89.47, 368.25, 91.52, 366.21, 92.95, 368.05, 96.43, 368.87, 97.25, 368.05, 99.91, 366.0, 101.14, 364.77, 101.14, 364.77, 103.4, 363.54, 105.24, 364.57, 107.49, 363.75, 110.16, 363.34, 111.38, 363.13, 111.59, 364.16, 114.05, 362.31, 117.73, 360.27, 118.55, 358.22, 119.99, 352.69, 119.78, 351.46, 122.65, 353.92, 127.77, 356.37, 136.37, 357.4, 138.63, 357.4, 140.88, 356.37, 143.95, 357.81, 148.46, 359.65, 166.69, 362.11, 182.66, 361.91, 190.45, 360.88, 199.87, 359.04, 221.17, 357.6, 230.59, 357.4, 233.46, 368.25, 251.69, 375.42, 259.06, 384.85, 270.13, 392.01, 280.16, 394.68, 281.19, 397.55, 282.21, 403.28, 288.97, 412.09, 301.26, 411.88, 303.92, 410.04, 305.56, 406.56, 305.36, 406.15, 304.33, 406.35, 302.28, 406.35, 301.87, 404.1, 299.83, 402.67, 301.46, 402.26, 304.74, 399.39, 305.77, 397.14, 305.77, 395.29, 303.72, 390.38, 304.33, 385.46, 303.31, 382.8, 299.42, 380.95, 295.93, 379.73, 295.11, 378.09, 291.02, 377.47, 287.54, 372.97, 283.03, 364.16, 275.66, 364.16, 273.61, 359.24, 269.92, 359.45, 275.66, 360.47, 281.6, 361.7, 288.97, 363.13, 297.98, 364.77, 308.63, 366.62, 313.55, 367.64, 326.66, 367.85, 338.33, 367.85, 351.24, 368.46, 358.2, 367.44, 358.82, 366.82, 359.02, 363.95, 368.03, 361.09, 378.27, 360.88, 388.11, 360.68, 395.89, 355.76, 428.25, 355.97, 435.63, 356.37, 452.22, 358.22, 460.0, 361.29, 459.59, 361.91, 461.23, 362.93, 459.79, 366.0, 458.16, 368.66, 459.18, 369.07, 461.84, 368.05, 463.48, 370.3, 466.76, 370.51, 467.99, 369.28, 469.01, 373.79, 474.54, 379.73, 477.41, 382.59, 476.8, 388.33, 478.84, 391.2, 480.0, 330.77, 480.0, 330.77, 476.18, 329.95, 472.9, 332.41, 467.37, 332.21, 464.3, 333.02, 462.46, 333.23, 460.61, 334.46, 459.59, 335.48, 456.52, 336.1, 456.31, 336.1, 452.63, 334.46, 444.43, 334.66, 439.11, 334.46, 435.63, 334.25, 432.14, 332.21, 413.91, 330.98, 396.91, 331.39, 388.52, 333.84, 373.77, 335.89, 364.14, 335.48, 361.68, 332.21, 361.07, 331.18, 361.07, 330.98, 371.72, 328.93, 373.77, 326.47, 373.56, 324.63, 382.17, 321.96, 385.65, 320.33, 387.7, 318.69, 391.18, 314.18, 425.79, 313.77, 436.85, 312.75, 446.69, 313.77, 449.55, 313.36, 464.1, 313.57, 467.78, 315.82, 473.31, 316.64, 475.77, 319.3, 476.8, 319.51, 479.66, 293.9, 480.0, 295.13, 475.57, 295.13, 473.52, 295.34, 470.24, 295.75, 466.35, 293.9, 458.16, 292.67, 451.19, 292.26, 444.23, 292.26, 436.24, 291.65, 430.09, 289.81, 420.47, 288.99, 409.0, 290.22, 394.25, 292.26, 388.72, 295.54, 371.51, 286.53, 370.29, 277.31, 370.7, 276.49, 363.32, 275.06, 359.63, 276.7, 346.94, 275.67, 318.26, 276.7, 305.77, 278.13, 284.87, 280.38, 272.99, 277.11, 269.31, 277.31, 267.05, 279.57, 262.75, 282.64, 235.51, 284.89, 225.06, 287.96, 209.09, 288.58, 207.45, 289.4, 196.59]], "area": 29214.070700000004, "iscrowd": 0, "image_id": 531201, "bbox": [275.06, 59.97, 137.03, 420.03], "category_id": 1, "id": 433632, "split": "val", "sentences": [{"tokens": ["tennis", "player", "in", "white", "shirt", "and", "tan", "shorts"], "raw": "tennis player in white shirt and tan shorts", "sent_id": 9861, "sent": "tennis player in white shirt and tan shorts"}, {"tokens": ["a", "male", "tennis", "player", "holding", "a", "racquet", "in", "a", "white", "shirt", "and", "grey", "shorts"], "raw": "a male tennis player holding a racquet in a white shirt and grey shorts", "sent_id": 9862, "sent": "a male tennis player holding a racquet in a white shirt and grey shorts"}], "file_name": "COCO_train2014_000000531201_433632.jpg", "ann_id": 433632, "sent_ids": [9861, 9862], "ref_id": 8821}, {"segmentation": [[478.92, 208.1, 448.72, 206.66, 425.71, 235.43, 447.28, 255.56, 424.27, 268.5, 425.71, 305.9, 398.38, 341.85, 376.81, 392.19, 414.2, 415.2, 424.27, 363.43, 428.58, 328.91, 463.1, 343.29, 454.47, 383.56, 428.58, 415.2, 435.78, 441.09, 471.73, 456.91, 480.0, 458.35, 477.48, 216.73]], "area": 12658.826000000001, "iscrowd": 0, "image_id": 283573, "bbox": [376.81, 206.66, 103.19, 251.69], "category_id": 1, "id": 1249025, "split": "val", "sentences": [{"tokens": ["boy", "keeping", "for", "the", "ruby", "game"], "raw": "BOY KEEPING FOR THE RUBY GAME", "sent_id": 9929, "sent": "boy keeping for the ruby game"}, {"tokens": ["the", "catcher"], "raw": "The catcher.", "sent_id": 9930, "sent": "the catcher"}], "file_name": "COCO_train2014_000000283573_1249025.jpg", "ann_id": 1249025, "sent_ids": [9929, 9930], "ref_id": 8845}, {"segmentation": [[45.73, 173.41, 181.99, 133.39, 271.55, 153.4, 284.89, 141.02, 333.48, 140.06, 353.49, 170.55, 349.68, 195.33, 320.14, 225.82, 289.65, 231.53, 270.6, 218.19, 238.2, 253.45, 184.84, 300.13, 184.84, 303.95, 202.0, 308.71, 213.43, 328.72, 183.89, 355.4, 161.02, 315.38, 158.17, 324.91, 154.36, 339.2, 157.21, 392.56, 156.26, 399.23, 157.21, 424.0, 6.67, 423.05, 9.53, 362.07, 7.62, 290.61, 1.91, 267.74, 0.0, 218.19, 18.1, 182.94, 46.69, 174.36]], "area": 61678.77035, "iscrowd": 0, "image_id": 241491, "bbox": [0.0, 133.39, 353.49, 290.61], "category_id": 1, "id": 1221121, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "an", "olive", "shirt", "blows", "out", "candles", "to", "a", "cake"], "raw": "A man in an olive shirt blows out candles to a cake.", "sent_id": 9941, "sent": "a man in an olive shirt blows out candles to a cake"}, {"tokens": ["an", "old", "man"], "raw": "an old  man", "sent_id": 9942, "sent": "an old man"}], "file_name": "COCO_train2014_000000241491_1221121.jpg", "ann_id": 1221121, "sent_ids": [9941, 9942], "ref_id": 8851}, {"segmentation": [[346.72, 260.55, 346.04, 242.77, 348.09, 231.83, 348.77, 221.57, 357.66, 215.42, 374.76, 208.58, 391.17, 202.43, 396.65, 200.37, 410.32, 192.17, 419.21, 188.75, 431.52, 186.01, 451.35, 187.38, 459.56, 188.06, 469.14, 185.33, 480.76, 180.54, 501.28, 173.7, 511.54, 173.7, 517.01, 173.7, 564.88, 178.49, 591.55, 182.59, 604.54, 186.01, 613.43, 190.12, 617.54, 201.06, 601.12, 203.11, 544.36, 201.06, 528.63, 200.37, 542.31, 207.21, 534.79, 223.63, 511.54, 229.78, 482.13, 230.46, 462.3, 231.83, 445.88, 233.2, 432.21, 229.78, 417.16, 228.41, 407.59, 239.35, 400.75, 243.46, 394.59, 257.82, 383.65, 277.65, 376.13, 281.75, 364.5, 283.12, 351.51, 273.55, 349.46, 265.34]], "area": 11634.521599999995, "iscrowd": 0, "image_id": 365231, "bbox": [346.04, 173.7, 271.5, 109.42], "category_id": 16, "id": 42108, "split": "val", "sentences": [{"tokens": ["the", "right", "last", "bird", "in", "the", "right", "hand", "picture"], "raw": "the right last bird in the right hand picture", "sent_id": 9989, "sent": "the right last bird in the right hand picture"}, {"tokens": ["the", "bird", "flying", "in", "the", "back", "of", "the", "pack"], "raw": "The bird flying in the back of the pack.", "sent_id": 9990, "sent": "the bird flying in the back of the pack"}], "file_name": "COCO_train2014_000000365231_42108.jpg", "ann_id": 42108, "sent_ids": [9989, 9990], "ref_id": 8870}, {"segmentation": [[275.16, 264.52, 271.15, 227.11, 269.82, 205.73, 252.45, 153.62, 255.79, 137.6, 226.39, 112.88, 199.68, 92.84, 170.28, 99.52, 160.93, 100.19, 164.27, 89.5, 178.97, 66.11, 186.32, 65.44, 193.66, 54.76, 197.67, 59.43, 197.0, 70.12, 208.36, 68.79, 230.41, 90.83, 260.46, 101.52, 283.17, 112.21, 296.54, 125.57, 313.24, 131.58, 339.96, 157.64, 337.96, 165.65, 335.28, 210.41, 339.96, 249.82, 340.63, 280.55, 327.93, 277.22, 321.92, 231.12, 295.87, 187.03, 295.2, 245.82, 297.2, 273.87, 291.86, 269.2, 281.18, 197.05, 281.18, 271.2, 275.83, 269.87]], "area": 11341.658749999997, "iscrowd": 0, "image_id": 17997, "bbox": [160.93, 54.76, 179.7, 225.79], "category_id": 25, "id": 598967, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "standing", "in", "the", "middle"], "raw": "The giraffe standing in the middle.", "sent_id": 10036, "sent": "the giraffe standing in the middle"}, {"tokens": ["a", "giraffe", "in", "between", "two", "other", "giraffes"], "raw": "A giraffe in between two other giraffes.", "sent_id": 10037, "sent": "a giraffe in between two other giraffes"}], "file_name": "COCO_train2014_000000017997_598967.jpg", "ann_id": 598967, "sent_ids": [10036, 10037], "ref_id": 8891}, {"segmentation": [[68.26, 201.4, 60.67, 192.98, 57.3, 151.69, 40.45, 144.1, 30.34, 133.99, 14.33, 127.25, 15.17, 112.92, 25.28, 95.22, 41.29, 86.8, 41.29, 86.8, 42.13, 75.0, 49.72, 65.73, 61.52, 67.42, 60.67, 90.17, 73.31, 95.22, 85.11, 106.18, 94.51, 121.14, 89.45, 126.19, 103.78, 130.41, 113.89, 164.96, 114.73, 172.54, 128.21, 184.34, 120.63, 189.4, 105.46, 186.03, 102.93, 172.54, 91.13, 145.58, 75.12, 146.42, 74.28, 178.44, 80.18, 196.98]], "area": 5789.745899999998, "iscrowd": 0, "image_id": 568187, "bbox": [14.33, 65.73, 113.88, 135.67], "category_id": 1, "id": 212191, "split": "val", "sentences": [{"tokens": ["a", "security", "guard", "sitting", "in", "a", "chair"], "raw": "A security guard sitting in a chair.", "sent_id": 10042, "sent": "a security guard sitting in a chair"}, {"tokens": ["the", "officer", "is", "sitting", "in", "his", "chair", "next", "to", "the", "dalmation"], "raw": "The officer is sitting in his chair next to the dalmation.", "sent_id": 10043, "sent": "the officer is sitting in his chair next to the dalmation"}], "file_name": "COCO_train2014_000000568187_212191.jpg", "ann_id": 212191, "sent_ids": [10042, 10043], "ref_id": 8894}, {"segmentation": [[44.49, 218.43, 31.01, 188.76, 36.4, 177.98, 57.98, 173.93, 110.56, 133.48, 151.01, 132.13, 168.54, 111.91, 177.98, 111.91, 195.51, 121.35, 191.46, 144.27, 206.29, 200.9, 204.94, 241.35, 183.37, 272.36, 161.8, 323.6, 171.24, 365.39, 202.25, 382.92, 233.26, 384.27, 273.71, 369.44, 288.54, 358.65, 304.72, 341.12, 335.73, 358.65, 343.82, 362.7, 319.55, 400.45, 308.76, 435.51, 246.74, 512.36, 140.22, 532.58, 128.09, 551.46, 115.96, 568.99, 10.79, 564.94, 12.13, 370.79, 24.27, 366.74, 36.4, 358.65, 43.15, 350.56, 47.19, 323.6, 41.8, 303.37, 36.4, 291.24, 25.62, 273.71, 35.06, 244.04, 48.54, 219.78]], "area": 82903.39975000001, "iscrowd": 0, "image_id": 181681, "bbox": [10.79, 111.91, 333.03, 457.08], "category_id": 23, "id": 587410, "split": "val", "sentences": [{"tokens": ["the", "smaller", "polar", "bear", "on", "the", "left"], "raw": "the smaller polar bear on the left", "sent_id": 10174, "sent": "the smaller polar bear on the left"}, {"tokens": ["a", "baby", "polar", "bear"], "raw": "A baby polar bear.", "sent_id": 10175, "sent": "a baby polar bear"}], "file_name": "COCO_train2014_000000181681_587410.jpg", "ann_id": 587410, "sent_ids": [10174, 10175], "ref_id": 8943}, {"segmentation": [[49.71, 228.36, 56.6, 248.36, 40.05, 253.88, 23.5, 271.81, 29.02, 305.6, 39.36, 338.7, 55.91, 358.01, 92.46, 358.7, 111.08, 358.01, 113.84, 342.84, 120.04, 355.94, 125.56, 362.14, 149.7, 360.76, 174.52, 362.14, 184.17, 349.04, 185.55, 344.9, 180.73, 338.7, 176.59, 338.7, 157.97, 342.15, 148.32, 341.46, 149.01, 329.73, 157.97, 311.8, 155.9, 300.77, 152.45, 296.63, 149.01, 294.56, 145.56, 271.81, 137.97, 257.33, 124.18, 254.57, 112.46, 260.77, 106.25, 258.71, 95.91, 257.33, 91.77, 251.81, 91.77, 250.43, 98.67, 247.67, 100.04, 227.67, 100.04, 218.02, 100.73, 206.99, 91.77, 197.33, 79.36, 192.51, 57.29, 201.47, 49.71, 211.81, 47.64, 224.92, 49.02, 229.05]], "area": 15252.296999999993, "iscrowd": 0, "image_id": 536146, "bbox": [23.5, 192.51, 162.05, 169.63], "category_id": 1, "id": 226879, "split": "val", "sentences": [{"tokens": ["a", "woman", "sitting", "on", "a", "sofa"], "raw": "a woman sitting on a sofa", "sent_id": 10221, "sent": "a woman sitting on a sofa"}, {"tokens": ["the", "person", "on", "the", "couch"], "raw": "The person on the couch.", "sent_id": 10222, "sent": "the person on the couch"}], "file_name": "COCO_train2014_000000536146_226879.jpg", "ann_id": 226879, "sent_ids": [10221, 10222], "ref_id": 8965}, {"segmentation": [[127.17, 366.5, 126.33, 357.26, 128.01, 345.49, 132.21, 333.73, 136.41, 325.32, 133.05, 312.71, 135.57, 305.15, 138.09, 294.22, 133.05, 286.66, 133.05, 279.1, 133.05, 274.05, 133.05, 269.85, 129.69, 262.29, 129.69, 258.09, 121.29, 267.33, 113.72, 269.01, 107.84, 273.21, 102.8, 273.21, 98.59, 269.85, 98.59, 266.49, 104.48, 265.65, 119.6, 257.25, 114.56, 253.04, 117.08, 250.52, 119.6, 242.96, 122.97, 232.03, 130.53, 219.43, 136.41, 216.06, 137.25, 211.86, 133.89, 203.46, 133.89, 194.21, 137.25, 188.33, 146.5, 184.97, 156.58, 188.33, 155.74, 195.05, 159.95, 199.25, 159.11, 205.98, 159.95, 212.7, 175.07, 218.58, 181.8, 223.63, 193.56, 230.35, 207.01, 237.91, 215.42, 243.8, 219.62, 253.04, 214.58, 253.04, 200.29, 246.32, 194.4, 242.96, 179.28, 240.44, 173.39, 235.39, 171.71, 248.84, 170.03, 254.72, 174.23, 273.21, 179.28, 290.02, 188.52, 305.15, 189.36, 309.35, 186.0, 319.44, 181.8, 332.89, 180.12, 341.29, 181.8, 351.38, 190.2, 353.9, 188.52, 358.94, 167.51, 358.94, 159.11, 352.22, 159.11, 343.81, 160.79, 334.57, 161.63, 328.68, 163.31, 322.8, 164.15, 317.76, 161.63, 312.71, 158.27, 306.83, 149.02, 336.25, 140.62, 354.74, 143.14, 364.82, 149.02, 369.87, 138.93, 373.23, 129.69, 367.34, 128.85, 363.14]], "area": 8106.447750000001, "iscrowd": 0, "image_id": 27070, "bbox": [98.59, 184.97, 121.03, 188.26], "category_id": 1, "id": 564420, "split": "val", "sentences": [{"tokens": ["the", "man", "whipping", "the", "elephant"], "raw": "The man whipping the elephant.", "sent_id": 10245, "sent": "the man whipping the elephant"}, {"tokens": ["man", "in", "camo"], "raw": "man in camo", "sent_id": 10246, "sent": "man in camo"}], "file_name": "COCO_train2014_000000027070_564420.jpg", "ann_id": 564420, "sent_ids": [10245, 10246], "ref_id": 8977}, {"segmentation": [[488.66, 317.72, 568.13, 370.34, 568.13, 378.93, 553.1, 389.67, 369.45, 389.67]], "area": 7834.87945, "iscrowd": 0, "image_id": 562474, "bbox": [369.45, 317.72, 198.68, 71.95], "category_id": 84, "id": 1984931, "split": "val", "sentences": [{"tokens": ["a", "yellow", "book", "written", "by", "a", ".", "a", ".", "milne"], "raw": "A yellow book written by A.A. Milne.", "sent_id": 10286, "sent": "a yellow book written by a . a . milne"}, {"tokens": ["a", "book", "sitting", "on", "a", "table", "in", "front", "of", "a", "group", "of", "four", "bears"], "raw": "A book sitting on a table in front of a group of four bears", "sent_id": 10287, "sent": "a book sitting on a table in front of a group of four bears"}], "file_name": "COCO_train2014_000000562474_1984931.jpg", "ann_id": 1984931, "sent_ids": [10286, 10287], "ref_id": 8997}, {"segmentation": [[451.63, 234.48, 453.26, 231.22, 451.09, 230.14, 450.54, 225.25, 446.74, 219.28, 439.15, 213.86, 433.18, 214.4, 428.29, 214.94, 423.95, 217.11, 419.07, 222.0, 418.52, 224.17, 418.52, 226.34, 415.81, 231.76, 420.15, 231.22, 422.87, 237.19, 423.41, 239.36, 420.69, 242.62, 422.87, 249.13, 421.78, 251.3, 424.49, 262.15, 425.58, 266.5, 415.81, 273.55, 414.18, 277.35, 409.3, 282.23, 402.24, 287.12, 400.07, 287.66, 399.53, 289.29, 393.02, 293.09, 384.34, 287.66, 378.37, 291.46, 376.74, 294.72, 375.11, 298.51, 375.65, 300.14, 381.62, 297.97, 376.2, 300.69, 386.51, 300.14, 393.02, 299.06, 396.82, 298.51, 400.07, 297.97, 406.04, 299.6, 421.24, 293.09, 421.24, 293.09, 425.58, 290.37, 430.46, 290.37, 437.52, 284.4, 440.77, 280.06, 459.77, 293.09, 464.65, 295.8, 445.12, 312.62, 441.32, 313.71, 428.84, 327.28, 427.75, 336.5, 429.92, 367.98, 428.29, 381.0, 434.26, 380.46, 434.26, 382.63, 423.41, 390.77, 420.69, 393.48, 420.69, 396.2, 426.12, 398.91, 461.4, 397.83, 458.68, 394.57, 460.85, 390.77, 457.05, 381.0, 458.68, 378.83, 456.51, 363.64, 453.8, 360.38, 452.71, 353.87, 452.17, 350.07, 452.17, 337.59, 458.68, 329.99, 463.57, 330.53, 481.48, 376.12, 489.07, 375.03, 490.16, 375.58, 482.56, 381.54, 481.48, 385.89, 481.48, 388.6, 504.81, 391.31, 512.95, 388.6, 511.87, 383.72, 510.78, 378.29, 509.69, 375.03, 509.15, 372.86, 510.78, 369.61, 490.7, 329.99, 500.47, 319.14, 501.01, 316.97, 499.93, 315.34, 511.87, 304.48, 511.32, 296.34, 510.24, 288.2, 504.27, 281.69, 502.1, 276.81, 501.01, 275.72, 500.47, 275.72, 500.47, 270.3, 494.5, 265.95, 476.59, 242.08, 476.59, 242.62, 471.16, 241.53, 458.68, 238.28, 452.71, 238.28, 453.26, 236.11, 453.26, 234.48]], "area": 10745.010449999996, "iscrowd": 0, "image_id": 292315, "bbox": [375.11, 213.86, 137.84, 185.05], "category_id": 1, "id": 2153026, "split": "val", "sentences": [{"tokens": ["umpire", "in", "black", "behind", "catcher"], "raw": "umpire in black behind catcher", "sent_id": 10301, "sent": "umpire in black behind catcher"}, {"tokens": ["the", "catcher", "wearing", "black"], "raw": "The catcher wearing black.", "sent_id": 10302, "sent": "the catcher wearing black"}], "file_name": "COCO_train2014_000000292315_2153026.jpg", "ann_id": 2153026, "sent_ids": [10301, 10302], "ref_id": 9003}, {"segmentation": [[397.32, 277.15, 397.32, 269.51, 393.85, 269.51, 393.16, 232.0, 393.16, 229.23, 408.44, 225.06, 409.13, 220.89, 429.97, 208.39, 433.45, 199.36, 446.64, 212.55, 470.95, 216.03, 493.18, 217.42, 525.83, 211.86, 517.49, 232.7, 523.05, 236.87, 536.25, 238.26, 530.69, 304.25, 502.21, 319.53, 465.4, 317.44, 400.1, 275.77, 399.41, 272.29]], "area": 12207.62305, "iscrowd": 0, "image_id": 83968, "bbox": [393.16, 199.36, 143.09, 120.17], "category_id": 63, "id": 114432, "split": "val", "sentences": [{"tokens": ["three", "seat", "brown", "couch", "on", "the", "right", "of", "room"], "raw": "Three seat brown couch on the right of room.", "sent_id": 10367, "sent": "three seat brown couch on the right of room"}, {"tokens": ["couch", "facing", "the", "fire", "place"], "raw": "couch facing the fire place", "sent_id": 10368, "sent": "couch facing the fire place"}], "file_name": "COCO_train2014_000000083968_114432.jpg", "ann_id": 114432, "sent_ids": [10367, 10368], "ref_id": 9030}, {"segmentation": [[355.68, 336.22, 344.86, 324.32, 335.14, 322.16, 335.14, 336.22, 335.14, 352.43, 327.57, 357.84, 323.24, 357.84, 327.57, 371.89, 327.57, 376.22, 336.22, 379.46, 354.59, 377.3, 372.97, 363.24, 376.22, 363.24, 363.24, 343.78], [357.84, 398.92, 392.43, 380.54, 396.76, 380.54, 408.65, 391.35, 408.65, 402.16, 408.65, 409.73, 409.73, 409.73, 417.3, 420.54, 433.51, 432.43, 455.14, 434.59, 468.11, 428.11, 478.92, 425.95, 499.46, 457.3, 501.62, 459.46, 454.05, 443.24, 393.51, 422.7, 367.57, 403.24], [269.19, 446.49, 292.97, 435.68, 307.03, 434.59, 325.41, 431.35, 335.14, 423.78, 344.86, 421.62, 374.05, 436.76, 384.86, 441.08, 393.51, 455.14, 428.11, 462.7, 467.03, 473.51, 259.46, 462.7, 263.78, 452.97, 265.95, 449.73], [456.94, 220.74, 466.93, 195.78, 475.49, 182.94, 476.2, 170.81, 474.77, 170.1, 464.08, 175.81, 455.52, 177.95, 458.37, 192.93, 454.8, 203.62, 454.8, 219.32, 454.8, 230.73, 457.66, 221.46], [557.51, 140.15, 528.98, 200.77, 514.72, 262.82, 516.14, 329.87, 526.84, 371.24, 541.82, 391.21, 548.24, 407.61, 567.5, 420.45, 590.32, 417.6, 601.02, 414.03, 612.43, 376.94, 635.26, 319.88, 636.68, 304.19, 637.4, 299.91, 640.0, 299.2, 639.53, 226.45, 640.0, 176.52, 640.0, 85.94, 640.0, 55.98, 640.0, 55.98, 636.68, 51.7, 633.83, 43.14, 627.41, 36.72, 623.13, 33.16, 618.14, 32.44, 616.0, 34.58, 623.13, 73.1, 624.56, 79.52, 627.41, 90.22, 628.84, 98.06, 612.43, 103.77, 595.31, 115.18, 583.9, 118.75, 573.92, 120.89, 569.64, 125.88, 563.22, 134.44]], "area": 41156.84595, "iscrowd": 0, "image_id": 215493, "bbox": [259.46, 32.44, 380.54, 441.07], "category_id": 19, "id": 368554, "split": "val", "sentences": [{"tokens": ["the", "white", "horse"], "raw": "The white horse.", "sent_id": 10376, "sent": "the white horse"}, {"tokens": ["white", "mejestic", "hors"], "raw": "white mejestic hors", "sent_id": 10377, "sent": "white mejestic hors"}], "file_name": "COCO_train2014_000000215493_368554.jpg", "ann_id": 368554, "sent_ids": [10376, 10377], "ref_id": 9033}, {"segmentation": [[311.21, 21.3, 411.89, 1.78, 498.19, 2.8, 578.31, 3.84, 640.0, 10.0, 633.78, 133.28, 594.75, 98.35, 578.31, 76.78, 554.69, 70.61, 508.45, 63.42, 480.72, 50.06, 334.85, 23.35]], "area": 16647.832499999993, "iscrowd": 0, "image_id": 404826, "bbox": [311.21, 1.78, 328.79, 131.5], "category_id": 67, "id": 413952, "split": "val", "sentences": [{"tokens": ["a", "green", "table", "cloth", "spread", "on", "the", "table"], "raw": "A green table cloth spread on the table", "sent_id": 10458, "sent": "a green table cloth spread on the table"}], "file_name": "COCO_train2014_000000404826_413952.jpg", "ann_id": 413952, "sent_ids": [10458], "ref_id": 9063}, {"segmentation": [[427.11, 415.71, 526.1, 391.24, 588.39, 390.13, 620.65, 390.13, 611.75, 352.31, 632.88, 332.29, 640.0, 338.96, 640.0, 413.49, 556.14, 416.82, 464.93, 417.94]], "area": 5468.505900000001, "iscrowd": 0, "image_id": 39802, "bbox": [427.11, 332.29, 212.89, 85.65], "category_id": 67, "id": 1959177, "split": "val", "sentences": [{"tokens": ["a", "table", "with", "a", "man", "'", "s", "arm", "rested", "on", "it"], "raw": "A table with a man's arm rested on it.", "sent_id": 10533, "sent": "a table with a man ' s arm rested on it"}], "file_name": "COCO_train2014_000000039802_1959177.jpg", "ann_id": 1959177, "sent_ids": [10533], "ref_id": 9094}, {"segmentation": [[269.43, 335.73, 273.65, 328.97, 279.56, 304.48, 279.56, 281.67, 275.34, 257.18, 271.11, 206.5, 261.82, 182.01, 256.76, 182.85, 255.07, 195.52, 253.38, 208.19, 250.0, 214.95, 239.02, 212.42, 225.51, 201.44, 219.59, 206.5, 218.75, 212.42, 210.3, 221.71, 227.2, 233.53, 223.82, 239.44, 232.26, 245.35, 241.55, 251.27, 243.24, 255.49, 252.16, 269.0, 257.68, 284.66, 265.28, 304.4, 269.43, 312.92], [233.11, 180.32, 241.55, 179.48, 244.09, 184.54, 245.78, 188.77, 244.09, 193.83, 236.49, 188.77], [173.14, 286.74, 178.21, 286.74, 188.34, 292.65, 187.5, 298.56, 195.1, 301.94, 195.1, 309.54, 201.86, 314.61, 205.24, 314.61, 202.7, 325.59, 204.39, 336.57, 193.41, 335.73, 195.1, 340.79, 191.72, 342.48, 187.5, 336.57, 180.74, 325.59, 176.52, 319.68, 173.14, 303.63]], "area": 5031.6416500000005, "iscrowd": 0, "image_id": 147710, "bbox": [173.14, 179.48, 106.42, 163.0], "category_id": 33, "id": 1187611, "split": "val", "sentences": [{"tokens": ["a", "red", "suitcase"], "raw": "A red suitcase.", "sent_id": 10565, "sent": "a red suitcase"}, {"tokens": ["the", "red", "suitcase", "that", "the", "little", "boy", "is", "holding", "on", "to"], "raw": "The red suitcase that the little boy is holding on to", "sent_id": 10566, "sent": "the red suitcase that the little boy is holding on to"}], "file_name": "COCO_train2014_000000147710_1187611.jpg", "ann_id": 1187611, "sent_ids": [10565, 10566], "ref_id": 9106}, {"segmentation": [[79.46, 220.23, 84.9, 177.78, 137.14, 172.34, 157.82, 216.96, 174.15, 211.52, 165.44, 246.35, 157.82, 281.18, 169.8, 312.74, 175.24, 356.28, 180.68, 376.96, 182.86, 384.58, 191.56, 411.79, 187.21, 441.18, 183.95, 465.12, 175.24, 472.74, 127.35, 472.74, 111.02, 455.33, 106.67, 420.5, 39.18, 425.94, 27.21, 423.76, 21.77, 371.52, 52.24, 312.74, 70.75, 271.38, 28.3, 253.97, 82.72, 240.91, 45.71, 232.2, 31.56, 221.32, 30.48, 203.9, 47.89, 203.9, 54.42, 216.96, 82.72, 228.93]], "area": 33483.0986, "iscrowd": 0, "image_id": 47294, "bbox": [21.77, 172.34, 169.79, 300.4], "category_id": 4, "id": 155048, "split": "val", "sentences": [{"tokens": ["a", "cop", "on", "a", "motorcycle", "behind", "another", "cop", "on", "a", "motorcycle"], "raw": "A cop on a motorcycle behind another cop on a motorcycle", "sent_id": 10569, "sent": "a cop on a motorcycle behind another cop on a motorcycle"}], "file_name": "COCO_train2014_000000047294_155048.jpg", "ann_id": 155048, "sent_ids": [10569], "ref_id": 9108}, {"segmentation": [[599.32, 195.08, 584.94, 145.94, 602.92, 121.96, 616.1, 96.79, 610.11, 57.24, 598.12, 32.06, 578.95, 12.89, 473.47, 32.06, 442.3, 51.24, 441.1, 75.22, 455.49, 103.98, 459.08, 144.74, 468.67, 174.7, 483.05, 209.46, 484.25, 213.06, 459.08, 227.44, 412.33, 241.83, 352.4, 307.75, 309.25, 338.92, 306.85, 355.7, 360.79, 377.27, 394.35, 408.44, 406.34, 449.19, 412.33, 504.33, 430.31, 524.71, 492.64, 524.71, 602.92, 523.51, 626.89, 518.71, 632.88, 516.32, 635.28, 510.32, 629.29, 470.77, 635.28, 319.74, 640.0, 251.42, 634.08, 235.83, 611.31, 213.06]], "area": 104047.56374999999, "iscrowd": 0, "image_id": 509746, "bbox": [306.85, 12.89, 333.15, 511.82], "category_id": 1, "id": 435539, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "tie", "hugging", "a", "girl"], "raw": "A man in a red tie hugging a girl", "sent_id": 10635, "sent": "a man in a red tie hugging a girl"}, {"tokens": ["the", "dorky", "dude", "she", "can", "do", "way", "better", "then"], "raw": "The dorky dude she can do way better then.", "sent_id": 10636, "sent": "the dorky dude she can do way better then"}], "file_name": "COCO_train2014_000000509746_435539.jpg", "ann_id": 435539, "sent_ids": [10635, 10636], "ref_id": 9135}, {"segmentation": [[311.58, 308.83, 295.26, 260.53, 306.14, 206.1, 286.41, 148.96, 251.03, 132.63, 231.99, 102.7, 233.35, 94.53, 242.19, 92.49, 258.52, 117.66, 289.13, 127.87, 295.26, 120.38, 290.49, 104.06, 295.26, 91.81, 306.82, 87.05, 318.39, 91.13, 326.55, 113.58, 344.24, 119.02, 376.89, 140.79, 388.46, 180.93, 393.9, 187.73, 378.93, 199.98, 372.13, 182.29, 374.17, 175.49, 366.69, 154.4, 347.64, 146.24, 347.64, 173.45, 344.92, 180.25, 344.92, 190.46, 355.8, 219.71, 338.79, 273.45, 333.35, 302.03, 347.64, 326.52, 297.3, 344.21, 295.94, 323.12]], "area": 13488.92815, "iscrowd": 0, "image_id": 332459, "bbox": [231.99, 87.05, 161.91, 257.16], "category_id": 1, "id": 452766, "split": "val", "sentences": [{"tokens": ["a", "man", "skiing", "with", "one", "arm", "up", "in", "the", "air"], "raw": "A man skiing with one arm up in the air.", "sent_id": 10647, "sent": "a man skiing with one arm up in the air"}, {"tokens": ["a", "man", "in", "black", "overall", "with", "white", "buttons", "skiing"], "raw": "A man in black overall with white buttons skiing", "sent_id": 10648, "sent": "a man in black overall with white buttons skiing"}], "file_name": "COCO_train2014_000000332459_452766.jpg", "ann_id": 452766, "sent_ids": [10647, 10648], "ref_id": 9140}, {"segmentation": [[0.0, 181.08, 46.49, 151.89, 76.76, 150.81, 103.78, 152.97, 147.03, 175.68, 167.57, 209.19, 167.57, 252.43, 166.49, 277.3, 175.14, 278.38, 165.41, 306.49, 161.08, 327.03, 148.11, 325.95, 140.54, 343.24, 134.05, 386.49, 138.38, 386.49, 175.14, 416.76, 191.35, 411.35, 210.81, 415.68, 234.59, 424.32, 257.3, 453.51, 206.49, 474.05, 3.24, 475.14, 0.0, 420.0, 16.22, 410.27, 16.22, 368.11, 2.16, 337.84]], "area": 52864.7087, "iscrowd": 0, "image_id": 491936, "bbox": [0.0, 150.81, 257.3, 324.33], "category_id": 1, "id": 197849, "split": "val", "sentences": [{"tokens": ["the", "man", "sitting", "with", "the", "blue", "and", "green", "jacket"], "raw": "The man sitting with the blue and green jacket.", "sent_id": 10759, "sent": "the man sitting with the blue and green jacket"}, {"tokens": ["man", "on", "a", "double", "decker", "bus", "tour"], "raw": "Man on a double decker bus tour.", "sent_id": 10760, "sent": "man on a double decker bus tour"}], "file_name": "COCO_train2014_000000491936_197849.jpg", "ann_id": 197849, "sent_ids": [10759, 10760], "ref_id": 9186}, {"segmentation": [[198.47, 218.61, 125.12, 432.9, 96.36, 569.53, 81.98, 632.81, 365.3, 631.37, 409.89, 546.52, 396.94, 529.26, 366.74, 537.89, 299.15, 533.57, 261.75, 522.07, 232.99, 512.0, 217.17, 506.25, 208.54, 460.22, 214.29, 365.3]], "area": 50020.83964999999, "iscrowd": 0, "image_id": 442356, "bbox": [81.98, 218.61, 327.91, 414.2], "category_id": 38, "id": 621033, "split": "val", "sentences": [{"tokens": ["a", "multi", "colored", "kite", "lays", "on", "the", "carpet"], "raw": "A multi colored kite lays on the carpet.", "sent_id": 10807, "sent": "a multi colored kite lays on the carpet"}, {"tokens": ["a", "multi", "-", "colored", "kite"], "raw": "A multi-colored kite.", "sent_id": 10808, "sent": "a multi - colored kite"}], "file_name": "COCO_train2014_000000442356_621033.jpg", "ann_id": 621033, "sent_ids": [10807, 10808], "ref_id": 9209}, {"segmentation": [[491.92, 170.99, 493.12, 160.57, 493.12, 158.77, 495.73, 158.37, 495.73, 153.76, 497.33, 152.76, 496.93, 146.74, 494.32, 145.34, 493.72, 143.54, 493.72, 142.13, 497.53, 140.73, 502.14, 143.54, 498.93, 146.94, 498.73, 152.35, 499.33, 152.15, 500.54, 149.75, 505.14, 149.55, 503.74, 153.36, 509.15, 153.36, 511.76, 156.56, 515.97, 155.16, 516.37, 151.15, 527.79, 143.34, 531.2, 139.93, 537.81, 132.11, 548.23, 115.68, 544.22, 115.68, 543.02, 113.88, 537.41, 113.48, 537.41, 112.28, 547.23, 105.86, 552.84, 101.85, 554.24, 99.65, 554.44, 93.44, 557.65, 93.24, 558.05, 101.45, 561.66, 102.86, 561.66, 106.86, 565.46, 107.27, 565.26, 112.88, 563.26, 112.48, 560.25, 117.08, 558.45, 124.9, 564.86, 126.3, 570.27, 125.9, 571.07, 119.29, 578.89, 89.03, 571.88, 88.23, 570.47, 87.43, 570.47, 86.02, 575.48, 84.82, 577.49, 83.62, 582.9, 84.62, 582.3, 75.6, 582.1, 72.8, 583.5, 72.8, 584.3, 59.17, 584.1, 39.13, 582.9, 38.93, 582.7, 35.93, 583.9, 33.52, 584.1, 29.31, 585.9, 29.31, 585.9, 76.0, 586.3, 85.02, 593.52, 85.42, 604.94, 33.52, 606.95, 33.52, 624.38, 97.25, 629.39, 105.66, 633.4, 133.92, 633.0, 144.14, 635.0, 169.39, 635.0, 184.82, 635.2, 197.04, 620.57, 196.24, 599.33, 193.23, 571.07, 188.83, 534.4, 186.22, 520.37, 187.22, 504.74, 183.01, 492.92, 180.61, 490.12, 181.01, 488.11, 178.61, 487.94, 175.85, 492.21, 171.85]], "area": 11538.424999999997, "iscrowd": 0, "image_id": 305624, "bbox": [487.94, 29.31, 147.26, 167.73], "category_id": 9, "id": 180315, "split": "val", "sentences": [{"tokens": ["a", "tugboat", "tied", "up", "at", "a", "dock", "in", "chilly", "weather"], "raw": "A tugboat tied up at a dock in chilly weather", "sent_id": 10835, "sent": "a tugboat tied up at a dock in chilly weather"}, {"tokens": ["a", "tall", "ship", "waiting", "in", "the", "harbor", ",", "with", "no", "sails"], "raw": "A tall ship waiting in the harbor, with no sails.", "sent_id": 10836, "sent": "a tall ship waiting in the harbor , with no sails"}], "file_name": "COCO_train2014_000000305624_180315.jpg", "ann_id": 180315, "sent_ids": [10835, 10836], "ref_id": 9218}, {"segmentation": [[383.82, 295.54, 379.98, 263.88, 383.82, 251.4, 379.98, 236.05, 454.83, 217.82, 517.2, 221.66, 534.47, 290.74, 534.47, 327.21, 522.0, 325.29, 509.52, 298.42, 500.89, 290.74, 492.25, 297.46, 480.73, 300.34, 483.61, 311.85, 494.17, 317.61, 500.89, 324.33, 499.93, 329.13, 458.67, 327.21, 437.56, 324.33, 427.96, 324.33, 412.61, 315.69, 396.29, 305.14, 387.66, 295.54]], "area": 13579.116550000004, "iscrowd": 0, "image_id": 141207, "bbox": [379.98, 217.82, 154.49, 111.31], "category_id": 6, "id": 167383, "split": "val", "sentences": [{"tokens": ["an", "orange", "bus", "in", "between", "two", "other", "buses"], "raw": "An orange bus in between two other buses.", "sent_id": 10881, "sent": "an orange bus in between two other buses"}, {"tokens": ["the", "bus", "in", "the", "middle"], "raw": "The bus in the middle", "sent_id": 10882, "sent": "the bus in the middle"}], "file_name": "COCO_train2014_000000141207_167383.jpg", "ann_id": 167383, "sent_ids": [10881, 10882], "ref_id": 9234}, {"segmentation": [[183.97, 439.68, 178.4, 439.68, 171.71, 437.45, 167.25, 435.78, 162.79, 431.32, 162.23, 422.96, 162.23, 415.71, 160.0, 406.79, 160.0, 400.65, 162.79, 393.4, 166.13, 381.7, 167.25, 375.56, 167.8, 363.85, 168.36, 351.59, 166.69, 333.19, 165.02, 324.83, 167.25, 314.79, 166.69, 310.89, 162.23, 292.49, 159.44, 247.33, 161.11, 246.21, 165.02, 242.31, 167.25, 242.31, 174.49, 245.65, 178.96, 240.08, 181.19, 235.06, 183.42, 233.95, 187.88, 231.72, 189.55, 228.37, 191.78, 224.47, 194.01, 223.35, 196.24, 222.24, 198.47, 221.68, 201.26, 220.01, 199.03, 216.66, 197.35, 216.1, 192.89, 213.32, 187.32, 214.99, 184.53, 217.22, 182.3, 220.56, 180.07, 221.68, 174.49, 218.33, 160.0, 211.09, 156.65, 207.74, 148.29, 207.18, 146.06, 207.18, 143.83, 201.05, 147.17, 201.05, 148.85, 193.8, 149.4, 190.46, 148.29, 182.09, 146.62, 177.63, 143.27, 171.5, 136.58, 167.04, 132.12, 166.48, 122.64, 166.48, 116.51, 171.5, 112.61, 175.96, 110.38, 185.44, 112.05, 188.78, 115.95, 196.59, 119.3, 201.61, 119.85, 204.95, 119.85, 208.3, 104.8, 212.2, 103.69, 215.55, 100.34, 222.24, 98.11, 226.14, 95.88, 230.6, 93.65, 238.96, 91.42, 246.21, 89.19, 251.23, 88.63, 252.34, 87.07, 255.81, 85.73, 261.17, 83.5, 265.41, 80.37, 306.5, 78.36, 319.23, 80.82, 321.24, 83.94, 323.92, 85.73, 325.7, 88.41, 325.7, 88.63, 323.92, 85.73, 321.68, 85.73, 321.01, 85.73, 319.23, 85.73, 318.11, 86.18, 316.77, 87.74, 316.1, 87.52, 316.77, 87.52, 319.67, 87.96, 321.01, 89.3, 322.58, 90.42, 323.02, 91.09, 322.35, 91.31, 321.24, 91.54, 320.12, 91.76, 316.55, 91.09, 314.31, 90.64, 312.08, 89.3, 308.51, 88.86, 307.39, 88.19, 298.91, 88.19, 296.0, 88.19, 293.1, 88.63, 289.75, 89.53, 286.62, 90.42, 282.6, 91.31, 280.15, 91.76, 277.47, 92.88, 270.1, 92.88, 268.31, 94.21, 264.74, 96.45, 262.73, 101.14, 259.16, 102.48, 258.49, 102.7, 258.26, 104.04, 276.57, 105.83, 286.18, 105.16, 296.9, 105.16, 307.84, 108.06, 314.09, 107.84, 319.45, 107.84, 323.47, 111.41, 334.91, 114.31, 344.52, 114.98, 349.43, 115.21, 356.8, 115.21, 361.27, 115.21, 366.85, 115.21, 369.98, 115.21, 373.77, 115.43, 377.35, 115.65, 380.7, 117.22, 388.06, 118.78, 394.54, 119.9, 399.23, 121.01, 404.14, 121.46, 407.05, 124.59, 418.58, 125.03, 425.05, 125.7, 427.28, 125.48, 430.86, 125.03, 433.09, 125.26, 434.65, 126.82, 436.22, 128.16, 438.23, 127.27, 433.54, 129.28, 437.11, 129.95, 439.57, 130.17, 442.02, 129.28, 444.7, 129.72, 446.49, 134.64, 447.38, 137.09, 446.94, 138.43, 447.83, 142.23, 448.72, 146.69, 448.28, 154.73, 448.28, 161.21, 448.5, 170.37, 448.28, 175.73, 447.61, 179.75, 446.71, 181.98, 445.37, 183.1, 443.14, 183.77, 440.91]], "area": 15567.380000000006, "iscrowd": 0, "image_id": 201634, "bbox": [78.36, 166.48, 122.9, 282.24], "category_id": 1, "id": 462638, "split": "val", "sentences": [{"tokens": ["person", "wearing", "black", "shirt", "and", "blue", "jeans"], "raw": "person wearing black shirt and blue jeans", "sent_id": 10938, "sent": "person wearing black shirt and blue jeans"}, {"tokens": ["a", "person", "wearing", "blue", "jeans", "and", "a", "dark", "colored", "t", "shirt", "is", "standing", "with", "a", "good", "shoe"], "raw": "A person wearing blue jeans and a dark colored t shirt is standing with a good shoe.", "sent_id": 10939, "sent": "a person wearing blue jeans and a dark colored t shirt is standing with a good shoe"}], "file_name": "COCO_train2014_000000201634_462638.jpg", "ann_id": 462638, "sent_ids": [10938, 10939], "ref_id": 9258}, {"segmentation": [[503.76, 360.79, 486.49, 402.05, 426.04, 405.89, 430.84, 381.9, 391.5, 348.32, 378.06, 348.32, 355.03, 368.47, 309.93, 368.47, 300.34, 333.92, 311.85, 314.73, 350.24, 317.61, 355.03, 300.34, 362.71, 270.59, 371.35, 264.84, 349.28, 275.39, 331.04, 277.31, 304.18, 289.78, 280.19, 284.99, 276.35, 272.51, 288.82, 262.92, 312.81, 257.16, 361.75, 225.49, 374.22, 220.7, 370.39, 185.19, 380.94, 147.77, 411.65, 128.58, 440.43, 116.11, 478.82, 114.19, 492.25, 128.58, 492.25, 151.61, 502.8, 199.59, 498.97, 214.94, 524.87, 272.51, 536.39, 318.57, 527.75, 350.24, 517.2, 360.79]], "area": 42877.30065000001, "iscrowd": 0, "image_id": 34739, "bbox": [276.35, 114.19, 260.04, 291.7], "category_id": 88, "id": 1160871, "split": "val", "sentences": [{"tokens": ["a", "smiling", "bear", "covered", "in", "green", "moss"], "raw": "A smiling bear covered in green moss.", "sent_id": 10957, "sent": "a smiling bear covered in green moss"}, {"tokens": ["rocks", "that", "look", "like", "winnie", "-", "the", "-", "poo", ",", "facing", "the", "camera"], "raw": "Rocks that look like Winnie-the-poo, facing the camera", "sent_id": 10958, "sent": "rocks that look like winnie - the - poo , facing the camera"}], "file_name": "COCO_train2014_000000034739_1160871.jpg", "ann_id": 1160871, "sent_ids": [10957, 10958], "ref_id": 9266}, {"segmentation": [[199.0, 398.0, 218.0, 419.0, 282.0, 417.0, 358.0, 405.0, 387.0, 399.0, 440.0, 399.0, 453.0, 388.0, 460.0, 368.0, 435.0, 361.0, 427.0, 358.0]], "area": 8143.5, "iscrowd": 0, "image_id": 477580, "bbox": [199.0, 358.0, 261.0, 61.0], "category_id": 57, "id": 1064215, "split": "val", "sentences": [{"tokens": ["the", "carrot", "on", "the", "very", "bottom"], "raw": "the carrot on the very bottom", "sent_id": 11005, "sent": "the carrot on the very bottom"}], "file_name": "COCO_train2014_000000477580_1064215.jpg", "ann_id": 1064215, "sent_ids": [11005], "ref_id": 9284}, {"segmentation": [[300.2, 379.77, 210.28, 401.43, 213.56, 444.75, 206.34, 444.75, 202.41, 406.68, 181.4, 404.71, 178.12, 434.9, 170.25, 432.93, 176.15, 400.77, 163.68, 355.49, 294.95, 327.92, 299.54, 346.3, 327.76, 346.96, 331.04, 348.93, 334.33, 396.84, 333.67, 404.06, 327.76, 404.06, 326.45, 378.46, 304.79, 378.46, 299.54, 398.81, 295.6, 398.15]], "area": 8821.075899999998, "iscrowd": 0, "image_id": 160380, "bbox": [163.68, 327.92, 170.65, 116.83], "category_id": 15, "id": 574054, "split": "val", "sentences": [{"tokens": ["the", "bench", "that", "is", "empty"], "raw": "The bench that is empty.", "sent_id": 11264, "sent": "the bench that is empty"}, {"tokens": ["the", "bench", "with", "no", "one", "on", "it"], "raw": "The bench with no one on it", "sent_id": 11265, "sent": "the bench with no one on it"}], "file_name": "COCO_train2014_000000160380_574054.jpg", "ann_id": 574054, "sent_ids": [11264, 11265], "ref_id": 9381}, {"segmentation": [[513.74, 220.51, 526.61, 214.72, 540.77, 219.87, 533.05, 232.09, 532.41, 236.6, 597.41, 240.46, 587.11, 244.96, 587.11, 257.19, 591.62, 265.56, 601.27, 306.1, 603.2, 315.12, 589.69, 333.78, 556.22, 339.57, 529.83, 316.4, 519.53, 299.67, 500.87, 295.81, 511.81, 304.82, 492.5, 312.54, 497.65, 276.5, 503.44, 240.46, 507.95, 226.31], [402.4, 248.18, 393.4, 261.05, 391.46, 270.71, 390.18, 285.51, 397.9, 303.53, 409.49, 311.9, 430.72, 306.75, 438.45, 293.23, 429.43, 252.69, 426.22, 262.99, 421.71, 278.43, 410.13, 283.58, 406.91, 268.14, 403.69, 250.76]], "area": 10579.95175, "iscrowd": 0, "image_id": 420823, "bbox": [390.18, 214.72, 213.02, 124.85], "category_id": 2, "id": 128392, "split": "val", "sentences": [{"tokens": ["a", "motorized", "bicycle", "behind", "a", "man", "in", "blue", "tracksuit", "bottoms"], "raw": "A motorized bicycle behind a man in blue tracksuit bottoms.", "sent_id": 11357, "sent": "a motorized bicycle behind a man in blue tracksuit bottoms"}, {"tokens": ["a", "bike", "on", "a", "street", "near", "a", "man"], "raw": "A bike on a street near a man.", "sent_id": 11358, "sent": "a bike on a street near a man"}], "file_name": "COCO_train2014_000000420823_128392.jpg", "ann_id": 128392, "sent_ids": [11357, 11358], "ref_id": 9417}, {"segmentation": [[214.06, 121.32, 232.58, 115.62, 240.41, 100.66, 261.78, 90.69, 293.12, 102.08, 300.96, 107.78, 302.38, 129.86, 300.25, 150.52, 296.69, 156.22, 293.12, 162.63, 308.08, 186.14, 313.78, 201.81, 328.03, 237.42, 333.01, 295.83, 333.01, 307.94, 320.19, 332.88, 313.07, 354.25, 309.51, 369.2, 313.07, 376.33, 314.49, 383.45, 328.74, 409.81, 338.71, 424.05, 358.66, 458.96, 366.49, 476.05, 344.41, 476.77, 327.32, 469.64, 319.48, 468.22, 317.34, 465.37, 321.62, 460.38, 324.47, 457.53, 318.06, 439.72, 298.11, 426.19, 287.43, 418.35, 274.6, 387.01, 263.92, 369.92, 250.38, 373.48, 244.69, 381.31, 232.58, 412.66, 221.18, 433.31, 213.34, 461.09, 213.34, 461.09, 215.48, 473.2, 215.48, 477.48, 159.21, 471.07, 147.1, 458.25, 145.67, 453.97, 157.78, 451.12, 172.74, 451.12, 201.95, 414.79, 204.08, 367.07, 212.63, 347.12, 236.14, 311.51, 245.4, 304.38, 246.82, 291.56, 241.12, 283.73, 238.27, 269.48, 223.32, 278.03, 204.08, 293.7, 186.99, 293.7, 175.59, 288.71, 164.91, 276.6, 164.91, 260.22, 182.71, 250.96, 201.23, 233.15, 231.15, 205.37, 242.55, 185.42, 246.82, 178.3, 241.84, 169.75, 236.14, 164.05, 235.43, 159.78, 230.44, 155.51, 231.86, 145.53, 232.58, 136.27, 221.89, 127.73]], "area": 35142.69314999999, "iscrowd": 0, "image_id": 283573, "bbox": [145.67, 90.69, 220.82, 386.79], "category_id": 1, "id": 488723, "split": "val", "sentences": [{"tokens": ["a", "batter"], "raw": "A batter.", "sent_id": 11405, "sent": "a batter"}, {"tokens": ["a", "young", "boy", "swinging", "a", "baseball", "bat"], "raw": "A young boy swinging a baseball bat.", "sent_id": 11406, "sent": "a young boy swinging a baseball bat"}], "file_name": "COCO_train2014_000000283573_488723.jpg", "ann_id": 488723, "sent_ids": [11405, 11406], "ref_id": 9436}, {"segmentation": [[221.97, 118.04, 236.01, 115.6, 240.29, 116.82, 245.17, 114.98, 253.11, 103.99, 270.82, 102.77, 285.48, 102.16, 292.81, 107.66, 292.81, 110.71, 315.4, 104.6, 322.12, 102.16, 330.06, 98.5, 344.72, 100.33, 353.88, 102.77, 356.93, 104.6, 362.43, 105.82, 355.71, 126.59, 364.87, 146.74, 363.04, 157.12, 370.98, 184.6, 353.88, 191.93, 347.77, 188.27, 342.89, 181.55, 331.28, 169.95, 325.79, 174.83, 322.73, 176.05, 318.46, 204.76, 308.69, 230.41, 305.02, 270.1, 307.47, 289.64, 316.01, 301.86, 316.63, 307.35, 300.14, 304.3, 294.03, 289.64, 292.2, 271.32, 292.81, 237.73, 292.2, 231.63, 290.98, 219.41, 287.31, 215.75, 283.04, 238.96, 280.59, 265.22, 269.6, 290.87, 262.88, 299.41, 252.5, 295.75, 253.72, 282.32, 266.55, 269.49, 271.43, 249.34, 268.38, 227.35, 265.94, 217.58, 275.71, 181.55, 273.88, 179.1, 277.54, 174.22, 294.03, 204.14, 309.91, 197.43, 305.02, 148.57, 303.19, 138.8, 301.97, 135.13, 302.58, 123.53, 293.42, 116.81, 274.49, 117.42, 254.33, 122.31, 242.73, 130.25, 231.13, 134.52, 201.81, 133.91, 204.26, 130.86, 212.2, 126.58]], "area": 9845.592200000005, "iscrowd": 0, "image_id": 459201, "bbox": [201.81, 98.5, 169.17, 208.85], "category_id": 24, "id": 594022, "split": "val", "sentences": [{"tokens": ["the", "second", "largest", "zebra", "with", "its", "head", "and", "front", "legs", "visible"], "raw": "The second largest zebra with its head and front legs visible.", "sent_id": 11438, "sent": "the second largest zebra with its head and front legs visible"}], "file_name": "COCO_train2014_000000459201_594022.jpg", "ann_id": 594022, "sent_ids": [11438], "ref_id": 9447}, {"segmentation": [[415.43, 330.53, 439.1, 293.94, 453.09, 291.78, 461.7, 276.72, 461.7, 267.03, 455.25, 245.51, 466.01, 236.9, 475.7, 221.83, 498.3, 217.52, 510.13, 239.05, 519.82, 250.89, 504.75, 277.79, 517.67, 292.86, 532.74, 301.47, 533.81, 321.92, 548.88, 340.22]], "area": 8112.880099999999, "iscrowd": 0, "image_id": 66376, "bbox": [415.43, 217.52, 133.45, 122.7], "category_id": 1, "id": 566869, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "hood", "and", "mask", "has", "his", "hands", "in", "front", "of", "his", "face", "on", "a", "laptop", "video"], "raw": "A man in a hood and mask has his hands in front of his face on a laptop video.", "sent_id": 11527, "sent": "a man in a hood and mask has his hands in front of his face on a laptop video"}, {"tokens": ["a", "person", "in", "a", "jacket", "on", "a", "screen"], "raw": "A person in a jacket on a screen.", "sent_id": 11528, "sent": "a person in a jacket on a screen"}], "file_name": "COCO_train2014_000000066376_566869.jpg", "ann_id": 566869, "sent_ids": [11527, 11528], "ref_id": 9486}, {"segmentation": [[1.18, 138.46, 53.2, 131.37, 68.57, 120.73, 83.11, 128.56, 79.76, 117.37, 86.47, 119.05, 94.86, 125.76, 96.53, 120.17, 99.89, 120.17, 103.8, 116.26, 114.99, 116.26, 117.23, 112.34, 128.97, 113.46, 130.65, 116.81, 191.61, 114.02, 207.82, 97.8, 234.11, 114.58, 244.17, 114.02, 249.21, 119.05, 254.24, 116.26, 259.83, 122.41, 320.0, 120.73, 320.0, 286.83, 320.0, 398.67, 320.0, 480.0, 37.81, 479.76, 0.0, 479.76, 1.46, 427.76]], "area": 114795.22379999996, "iscrowd": 0, "image_id": 351301, "bbox": [0.0, 97.8, 320.0, 382.2], "category_id": 67, "id": 2226771, "split": "val", "sentences": [{"tokens": ["vegetables", "skewered", "onto", "sticks", "rest", "atop", "a", "white", "cutting", "board"], "raw": "Vegetables skewered onto sticks rest atop a white cutting board.", "sent_id": 11606, "sent": "vegetables skewered onto sticks rest atop a white cutting board"}, {"tokens": ["a", "group", "of", "vegetables", "on", "skewers", "on", "a", "table"], "raw": "A group of vegetables on skewers on a table.", "sent_id": 11607, "sent": "a group of vegetables on skewers on a table"}], "file_name": "COCO_train2014_000000351301_2226771.jpg", "ann_id": 2226771, "sent_ids": [11606, 11607], "ref_id": 9515}, {"segmentation": [[54.7, 165.18, 51.35, 150.95, 51.35, 143.42, 56.37, 128.36, 74.78, 123.33, 88.17, 132.54, 86.5, 160.15, 106.58, 187.77, 109.93, 220.4, 116.62, 357.64, 117.46, 385.26, 87.34, 389.44, 91.52, 381.91, 88.17, 375.21, 79.8, 395.3, 37.13, 395.3, 38.8, 389.44, 55.54, 386.09, 61.39, 369.36, 63.07, 343.42, 53.03, 340.07, 51.35, 194.46, 55.54, 178.56]], "area": 14342.746950000004, "iscrowd": 0, "image_id": 104344, "bbox": [37.13, 123.33, 80.33, 271.97], "category_id": 1, "id": 1266025, "split": "val", "sentences": [{"tokens": ["man", "over", "person", "in", "green", "ties", "right", "shoulder"], "raw": "man over person in green ties right shoulder", "sent_id": 11610, "sent": "man over person in green ties right shoulder"}, {"tokens": ["grey", "haired", "man", "in", "black", "suit", "and", "white", "shirt", "wearing", "glasses"], "raw": "Grey haired man in black suit and white shirt wearing glasses", "sent_id": 11611, "sent": "grey haired man in black suit and white shirt wearing glasses"}], "file_name": "COCO_train2014_000000104344_1266025.jpg", "ann_id": 1266025, "sent_ids": [11610, 11611], "ref_id": 9517}, {"segmentation": [[0.0, 61.69, 0.0, 61.69, 75.84, 67.75, 75.84, 67.75, 95.06, 59.66, 138.54, 73.82, 191.12, 61.69, 191.12, 61.69, 240.67, 47.53, 280.11, 60.67, 281.12, 83.93, 193.15, 123.37, 11.12, 128.43, 44.49, 223.48, 19.21, 234.61, 15.17, 206.29, 6.07, 195.17, 2.02, 63.71, 2.02, 63.71]], "area": 17812.613250000006, "iscrowd": 0, "image_id": 423890, "bbox": [0.0, 47.53, 281.12, 187.08], "category_id": 67, "id": 1616399, "split": "val", "sentences": [{"tokens": ["brown", "wooden", "table", "behind", "the", "man"], "raw": "Brown wooden table behind the man", "sent_id": 11694, "sent": "brown wooden table behind the man"}], "file_name": "COCO_train2014_000000423890_1616399.jpg", "ann_id": 1616399, "sent_ids": [11694], "ref_id": 9550}, {"segmentation": [[12.14, 136.18, 36.43, 116.23, 48.58, 106.69, 58.12, 104.09, 61.59, 122.31, 102.36, 167.41, 161.34, 201.24, 215.12, 224.66, 196.9, 240.27, 184.76, 251.55, 168.28, 256.76, 161.34, 272.37, 157.0, 290.58, 154.4, 307.07, 152.67, 332.22, 152.67, 337.42, 143.99, 337.42, 140.52, 297.52, 125.78, 250.68, 123.17, 234.2, 105.82, 212.52, 75.47, 173.48, 53.78, 141.39, 45.97, 140.52, 23.42, 145.73, 9.54, 146.59, 9.54, 134.45]], "area": 9605.331950000002, "iscrowd": 0, "image_id": 171484, "bbox": [9.54, 104.09, 205.58, 233.33], "category_id": 25, "id": 595555, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "looking", "to", "the", "left", "behind", "another", "giraffe", "located", "to", "the", "left", "of", "two", "more", "giraffes"], "raw": "A giraffe looking to the left behind another giraffe located to the left of two more giraffes", "sent_id": 11732, "sent": "a giraffe looking to the left behind another giraffe located to the left of two more giraffes"}, {"tokens": ["a", "giraffe", "standing", "in", "a", "fenced", "area", "to", "the", "left", "of", "three", "additional", "giraffe"], "raw": "A giraffe standing in a fenced area to the left of three additional giraffe.", "sent_id": 11733, "sent": "a giraffe standing in a fenced area to the left of three additional giraffe"}], "file_name": "COCO_train2014_000000171484_595555.jpg", "ann_id": 595555, "sent_ids": [11732, 11733], "ref_id": 9567}, {"segmentation": [[413.42, 138.63, 391.95, 194.47, 313.56, 244.94, 265.23, 271.78, 194.36, 308.29, 137.45, 334.06, 30.07, 368.43, 5.37, 374.87, 0.0, 0.0, 318.93, 1.18, 335.03, 16.21, 387.65, 43.06, 408.05, 65.61, 427.38, 89.23, 429.53, 98.9, 423.09, 112.86, 405.91, 142.92]], "area": 117147.90389999996, "iscrowd": 0, "image_id": 213652, "bbox": [0.0, 0.0, 429.53, 374.87], "category_id": 54, "id": 312418, "split": "val", "sentences": [{"tokens": ["the", "left", "half", "of", "a", "club", "sandwich"], "raw": "The left half of a club sandwich.", "sent_id": 11734, "sent": "the left half of a club sandwich"}, {"tokens": ["sandwich", "on", "the", "left", "side"], "raw": "sandwich on the left side", "sent_id": 11735, "sent": "sandwich on the left side"}], "file_name": "COCO_train2014_000000213652_312418.jpg", "ann_id": 312418, "sent_ids": [11734, 11735], "ref_id": 9568}, {"segmentation": [[286.52, 190.45, 252.81, 183.71, 212.36, 183.71, 194.66, 191.29, 182.87, 194.66, 161.8, 206.46, 144.1, 217.42, 123.88, 237.64, 111.24, 269.66, 102.81, 316.01, 112.08, 349.72, 124.72, 370.79, 349.72, 369.1, 358.99, 362.36, 369.1, 321.07, 371.63, 297.47, 370.79, 267.98, 348.88, 234.27, 317.7, 212.36]], "area": 41938.017850000004, "iscrowd": 0, "image_id": 313209, "bbox": [102.81, 183.71, 268.82, 187.08], "category_id": 51, "id": 1040714, "split": "val", "sentences": [{"tokens": ["bread", "sandwich", "in", "table"], "raw": "bread sandwich in table", "sent_id": 11823, "sent": "bread sandwich in table"}, {"tokens": ["a", "bowl", "of", "fried", "snack", "and", "tomato", "sauce", "in", "a", "green", "spoon"], "raw": "A bowl of fried snack and tomato sauce in a green spoon", "sent_id": 11824, "sent": "a bowl of fried snack and tomato sauce in a green spoon"}], "file_name": "COCO_train2014_000000313209_1040714.jpg", "ann_id": 1040714, "sent_ids": [11823, 11824], "ref_id": 9601}, {"segmentation": [[637.82, 154.47, 627.45, 147.94, 613.23, 129.87, 590.94, 96.05, 571.05, 61.15, 563.61, 51.55, 571.41, 53.35, 577.17, 51.43, 579.32, 49.03, 584.84, 44.59, 582.44, 40.88, 574.89, 39.08, 568.65, 40.28, 565.77, 41.48, 561.93, 40.64, 561.09, 30.92, 563.01, 22.88, 562.89, 19.41, 558.93, 17.25, 556.42, 19.05, 555.34, 23.48, 551.26, 31.4, 548.14, 31.52, 547.18, 28.88, 547.42, 20.97, 546.94, 17.85, 541.54, 17.37, 539.62, 19.77, 538.66, 24.68, 536.74, 30.08, 538.06, 36.8, 537.22, 39.2, 532.19, 34.16, 520.55, 34.76, 518.51, 36.8, 519.59, 39.68, 524.99, 46.27, 530.15, 49.51, 530.15, 50.83, 533.27, 56.83, 533.63, 66.06, 530.63, 71.82, 532.64, 76.03, 533.73, 84.93, 540.28, 88.39, 544.28, 86.39, 548.64, 82.21, 556.46, 102.02, 561.91, 117.66, 568.46, 136.57, 572.46, 147.11, 573.37, 153.29, 580.27, 164.56, 588.82, 191.47, 591.73, 197.65, 596.09, 206.56, 591.36, 218.56, 591.91, 228.37, 591.91, 229.47, 586.64, 253.1, 584.09, 263.1, 581.18, 269.64, 572.46, 286.55, 567.55, 291.64, 567.55, 296.91, 567.18, 299.82, 557.73, 333.82, 556.64, 337.64, 550.46, 354.18, 544.1, 366.0, 543.73, 372.0, 561.55, 365.63, 559.37, 359.63, 563.37, 352.0, 562.82, 342.91, 568.09, 333.27, 578.64, 302.73, 582.27, 295.46, 592.27, 276.37, 601.0, 264.92, 611.6, 287.19, 613.88, 305.96, 613.88, 305.96, 618.19, 312.8, 618.95, 322.69, 624.53, 332.08, 628.59, 362.0, 629.09, 374.42, 632.39, 389.38, 635.94, 402.06, 635.94, 423.87, 636.1, 424.91, 640.0, 424.91, 639.92, 406.28, 639.92, 393.83, 639.92, 381.5, 639.92, 369.17, 639.92, 356.84, 639.92, 344.5, 639.92, 332.17, 639.92, 319.84, 639.92, 307.51, 639.92, 295.18, 639.92, 282.85, 639.92, 270.51, 639.92, 258.18, 639.92, 245.85, 639.92, 233.52, 639.92, 221.19, 639.92, 208.86, 639.92, 196.52, 639.92, 184.19, 639.92, 171.86, 639.86, 155.89, 637.7, 154.35]], "area": 15456.262949999978, "iscrowd": 0, "image_id": 7393, "bbox": [518.51, 17.25, 121.49, 407.66], "category_id": 25, "id": 595944, "split": "val", "sentences": [{"tokens": ["a", "large", "giraffe", "looking", "toward", "the", "camera"], "raw": "A large giraffe looking toward the camera", "sent_id": 11839, "sent": "a large giraffe looking toward the camera"}, {"tokens": ["a", "giraffe", "that", "has", "its", "face", "visible"], "raw": "A giraffe that has its face visible.", "sent_id": 11840, "sent": "a giraffe that has its face visible"}], "file_name": "COCO_train2014_000000007393_595944.jpg", "ann_id": 595944, "sent_ids": [11839, 11840], "ref_id": 9608}, {"segmentation": [[425.45, 216.4, 388.44, 206.91, 372.31, 205.01, 340.05, 211.65, 309.69, 233.48, 286.91, 259.1, 282.17, 295.15, 275.53, 301.8, 285.02, 325.52, 288.81, 353.03, 300.2, 383.4, 327.72, 403.32, 329.61, 408.07, 316.33, 415.66, 303.99, 426.1, 299.25, 429.89, 289.76, 432.74, 276.48, 439.38, 266.99, 448.87, 262.24, 449.82, 245.16, 485.87, 231.88, 507.7, 189.18, 543.35, 161.67, 577.51, 149.33, 598.38, 149.33, 628.75, 155.97, 638.23, 228.09, 639.18, 378.01, 639.18, 401.73, 589.84, 409.32, 555.68, 418.81, 521.52, 423.55, 492.11, 426.0, 419.05, 419.76, 408.61, 424.5, 406.71, 424.5, 350.73, 423.55, 249.91]], "area": 71040.02485000002, "iscrowd": 0, "image_id": 527267, "bbox": [149.33, 205.01, 276.67, 434.17], "category_id": 1, "id": 1734096, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "solid", "green", "shirt"], "raw": "A person in a solid green shirt.", "sent_id": 11851, "sent": "a person in a solid green shirt"}, {"tokens": ["a", "short", "haired", "girl", "in", "glasses", "standing", "in", "a", "green", "shirt", "with", "arms", "crossed"], "raw": "A short haired girl in glasses standing in a green shirt with arms crossed.", "sent_id": 11852, "sent": "a short haired girl in glasses standing in a green shirt with arms crossed"}], "file_name": "COCO_train2014_000000527267_1734096.jpg", "ann_id": 1734096, "sent_ids": [11851, 11852], "ref_id": 9613}, {"segmentation": [[236.8, 146.63, 214.04, 142.42, 204.78, 137.36, 190.45, 128.09, 177.81, 112.92, 170.22, 96.07, 172.75, 74.16, 190.45, 56.46, 204.78, 45.51, 222.47, 43.82, 260.39, 43.82, 304.21, 48.03, 348.03, 53.93, 369.1, 63.2, 391.85, 75.84, 408.71, 96.91, 423.88, 116.29, 435.67, 143.26, 433.15, 167.7, 424.72, 179.49, 394.38, 190.45, 375.0, 194.66, 326.12, 181.18, 273.88, 162.64, 251.97, 155.9]], "area": 27733.250149999996, "iscrowd": 0, "image_id": 149556, "bbox": [170.22, 43.82, 265.45, 150.84], "category_id": 74, "id": 1107541, "split": "val", "sentences": [{"tokens": ["the", "mouse", "nearest", "the", "large", "black", "object"], "raw": "The mouse nearest the large black object.", "sent_id": 12065, "sent": "the mouse nearest the large black object"}, {"tokens": ["the", "right", "most", "mouse"], "raw": "the right most mouse", "sent_id": 12066, "sent": "the right most mouse"}], "file_name": "COCO_train2014_000000149556_1107541.jpg", "ann_id": 1107541, "sent_ids": [12065, 12066], "ref_id": 9696}, {"segmentation": [[404.49, 405.64, 405.57, 384.07, 414.2, 370.05, 414.2, 353.87, 414.2, 324.75, 426.07, 308.57, 444.4, 297.78, 453.03, 282.68, 463.82, 262.18, 465.98, 253.56, 462.74, 247.08, 471.37, 244.93, 483.24, 243.85, 486.47, 249.24, 495.1, 255.71, 488.63, 266.5, 481.08, 271.89, 471.37, 297.78, 474.61, 319.35, 475.69, 337.69, 475.69, 344.16, 470.29, 361.42, 470.29, 386.23, 471.37, 411.04, 465.98, 419.67, 450.88, 408.88, 453.03, 377.6, 454.11, 350.63, 442.25, 346.32, 436.85, 354.95, 429.3, 380.84, 426.07, 404.57, 428.22, 416.43, 410.97, 418.59, 402.34, 412.12]], "area": 6774.672050000005, "iscrowd": 0, "image_id": 226527, "bbox": [402.34, 243.85, 92.76, 175.82], "category_id": 25, "id": 599525, "split": "val", "sentences": [{"tokens": ["a", "small", "giraffe", "looking", "looking", "at", "a", "herd", "of", "horned", "animals"], "raw": "A small giraffe looking looking at a herd of horned animals.", "sent_id": 12081, "sent": "a small giraffe looking looking at a herd of horned animals"}, {"tokens": ["giraffee", "chaild", "was", "in", "forest"], "raw": "giraffee chaild was in forest", "sent_id": 12082, "sent": "giraffee chaild was in forest"}], "file_name": "COCO_train2014_000000226527_599525.jpg", "ann_id": 599525, "sent_ids": [12081, 12082], "ref_id": 9701}, {"segmentation": [[452.79, 417.54, 452.79, 337.3, 456.61, 313.42, 448.97, 317.24, 448.97, 349.72, 430.82, 356.4, 422.22, 328.7, 428.91, 275.21, 453.75, 221.71, 491.0, 199.74, 494.82, 194.01, 491.0, 172.04, 492.91, 149.11, 512.97, 137.65, 531.12, 142.43, 538.77, 166.31, 540.68, 182.55, 534.94, 201.65, 569.33, 207.38, 594.17, 243.68, 597.99, 303.86, 586.53, 344.94, 579.84, 361.18, 582.71, 419.45, 448.97, 420.41]], "area": 34129.01914999999, "iscrowd": 0, "image_id": 390496, "bbox": [422.22, 137.65, 175.77, 282.76], "category_id": 1, "id": 224144, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "in", "front", "of", "an", "airplane"], "raw": "A man standing in front of an airplane.", "sent_id": 12127, "sent": "a man standing in front of an airplane"}, {"tokens": ["man", "wearing", "red", "shirt", "and", "white", "hat"], "raw": "man wearing red shirt and white hat", "sent_id": 12128, "sent": "man wearing red shirt and white hat"}], "file_name": "COCO_train2014_000000390496_224144.jpg", "ann_id": 224144, "sent_ids": [12127, 12128], "ref_id": 9712}, {"segmentation": [[315.15, 76.34, 319.42, 74.51, 298.66, 81.84, 263.23, 95.28, 254.68, 101.38, 234.53, 101.38, 241.86, 87.34, 246.74, 73.29, 252.24, 65.35, 255.91, 58.02, 257.13, 52.52, 257.13, 49.47, 261.4, 49.47, 264.46, 51.91, 271.78, 54.97, 288.89, 56.19, 304.15, 58.02, 329.2, 69.02, 348.74, 62.3, 348.74, 54.97, 357.29, 57.41, 362.79, 57.41, 367.67, 55.58, 374.39, 67.18, 381.11, 79.4, 406.15, 83.67, 417.14, 84.28, 456.23, 86.73, 490.43, 103.22, 515.48, 122.15, 520.97, 128.26, 539.91, 133.75, 571.66, 146.58, 563.11, 160.63, 535.02, 147.8, 502.04, 130.09, 489.82, 127.04, 487.38, 146.58, 493.49, 160.02, 505.7, 170.4, 514.86, 183.84, 524.03, 214.98, 544.79, 215.6, 538.68, 229.03, 530.74, 227.81, 516.09, 221.7, 514.25, 209.49, 499.6, 193.0, 487.99, 177.12, 486.16, 184.45, 481.88, 194.83, 483.11, 207.66, 487.99, 221.09, 486.77, 230.86, 476.39, 223.54, 466.62, 210.1, 469.67, 195.44, 470.28, 176.51, 448.9, 172.84, 423.25, 169.18, 395.77, 158.8, 366.45, 164.29, 356.07, 165.51, 347.52, 180.17, 337.14, 170.4, 337.14, 167.35, 324.92, 164.9, 327.97, 152.69, 334.08, 131.92, 340.8, 102.61, 356.07, 108.71, 373.78, 123.98, 384.77, 125.82, 390.27, 120.93, 390.27, 103.22, 383.55, 91.0, 378.67, 77.57, 373.17, 69.63, 367.67, 56.8, 357.9, 58.63, 349.35, 64.74, 315.15, 76.95], [342.63, 198.49, 342.63, 202.16, 342.63, 208.27, 342.63, 214.98, 340.8, 222.31, 336.52, 229.64, 333.47, 234.53, 324.31, 234.53, 323.09, 229.03, 325.53, 221.09, 327.36, 211.32, 332.86, 193.61, 317.59, 182.0, 310.87, 195.44, 314.54, 205.21, 316.98, 208.27, 312.09, 219.26, 311.48, 224.15, 310.87, 207.66, 310.87, 196.66, 306.6, 176.51, 315.15, 181.39, 316.98, 180.17]], "area": 17823.86355, "iscrowd": 0, "image_id": 454246, "bbox": [234.53, 49.47, 337.13, 185.06], "category_id": 19, "id": 54085, "split": "val", "sentences": [{"tokens": ["the", "horse", "in", "the", "background", "with", "a", "cover", "on", "it", "'", "s", "back"], "raw": "The horse in the background with a cover on it's back.", "sent_id": 12361, "sent": "the horse in the background with a cover on it ' s back"}, {"tokens": ["one", "of", "two", "horses", "running", "past", "each", "other", "in", "a", "dirt", "field", ".", "he", "has", "a", "black", "covering", "over", "his", "body"], "raw": "one of two horses running past each other in a dirt field. He has a black covering over his body.", "sent_id": 12362, "sent": "one of two horses running past each other in a dirt field . he has a black covering over his body"}], "file_name": "COCO_train2014_000000454246_54085.jpg", "ann_id": 54085, "sent_ids": [12361, 12362], "ref_id": 9799}, {"segmentation": [[217.81, 209.38, 421.16, 205.25, 460.39, 232.09, 528.52, 241.38, 536.77, 258.92, 528.52, 270.28, 513.03, 276.47, 507.87, 286.8, 485.16, 286.8, 467.61, 281.63, 461.42, 281.63, 459.35, 285.76, 452.13, 290.92, 436.65, 292.99, 424.26, 291.96, 409.81, 280.6, 214.71, 260.99, 205.42, 270.28, 196.13, 270.28, 187.87, 258.92, 169.29, 249.63, 178.58, 234.15, 189.94, 230.02, 204.39, 211.44]], "area": 20959.757950000003, "iscrowd": 0, "image_id": 523711, "bbox": [169.29, 205.25, 367.48, 87.74], "category_id": 3, "id": 135965, "split": "val", "sentences": [{"tokens": ["cow", "painted", "limo"], "raw": "cow painted limo.", "sent_id": 12508, "sent": "cow painted limo"}, {"tokens": ["a", "jersey", "cow", "painted", "stretch", "limousine", "with", "cow", ",", "pig", ",", "and", "rooster", "roof", "ornaments"], "raw": "A jersey cow painted stretch limousine with  cow, pig, and rooster roof ornaments", "sent_id": 12509, "sent": "a jersey cow painted stretch limousine with cow , pig , and rooster roof ornaments"}], "file_name": "COCO_train2014_000000523711_135965.jpg", "ann_id": 135965, "sent_ids": [12508, 12509], "ref_id": 9849}, {"segmentation": [[1.08, 138.92, 51.65, 173.35, 79.63, 207.78, 126.98, 359.51, 129.13, 374.57, 110.83, 381.03, 126.98, 472.5, 128.05, 481.0, 0.0, 480.03]], "area": 33259.593100000006, "iscrowd": 0, "image_id": 535418, "bbox": [0.0, 138.92, 129.13, 342.08], "category_id": 1, "id": 471301, "split": "val", "sentences": [{"tokens": ["the", "person", "'", "s", "shoulder", "and", "arm", "wearing", "blue", "and", "black", "stripes"], "raw": "The person's shoulder and arm wearing blue and black stripes", "sent_id": 12556, "sent": "the person ' s shoulder and arm wearing blue and black stripes"}, {"tokens": ["the", "right", "shoulder", "of", "a", "person", "wearing", "a", "striped", "shirt", "behind", "a", "little", "boy"], "raw": "The right shoulder of a person wearing a striped shirt behind a little boy", "sent_id": 12557, "sent": "the right shoulder of a person wearing a striped shirt behind a little boy"}], "file_name": "COCO_train2014_000000535418_471301.jpg", "ann_id": 471301, "sent_ids": [12556, 12557], "ref_id": 9866}, {"segmentation": [[160.34, 436.05, 133.37, 447.61, 97.91, 482.3, 78.65, 506.19, 71.71, 526.23, 67.86, 538.56, 57.07, 564.76, 51.67, 573.24, 48.59, 571.7, 48.59, 556.28, 54.75, 547.81, 58.61, 540.87, 62.46, 530.85, 64.77, 523.91, 64.77, 514.67, 67.09, 504.65, 76.33, 501.56, 79.42, 494.63, 91.75, 471.51, 124.89, 439.91, 131.83, 432.97, 148.01, 427.58, 161.11, 429.12]], "area": 1862.2617499999994, "iscrowd": 0, "image_id": 355345, "bbox": [48.59, 427.58, 112.52, 145.66], "category_id": 31, "id": 1430826, "split": "val", "sentences": [{"tokens": ["a", "black", "strap", "on", "a", "white", "shirt"], "raw": "A black strap on a white shirt.", "sent_id": 12564, "sent": "a black strap on a white shirt"}], "file_name": "COCO_train2014_000000355345_1430826.jpg", "ann_id": 1430826, "sent_ids": [12564], "ref_id": 9869}, {"segmentation": [[246.31, 3.46, 416.36, 2.59, 401.46, 147.22, 251.57, 122.67]], "area": 21160.3112, "iscrowd": 0, "image_id": 561479, "bbox": [246.31, 2.59, 170.05, 144.63], "category_id": 72, "id": 35009, "split": "val", "sentences": [{"tokens": ["a", "white", "computer", "screen", "between", "two", "other", "computer", "screens"], "raw": "a white computer screen between two other computer screens", "sent_id": 12604, "sent": "a white computer screen between two other computer screens"}, {"tokens": ["a", "compute", "monitor", "that", "is", "off", "and", "is", "between", "two", "other", "monitors"], "raw": "A compute monitor that is off and is between two other monitors.", "sent_id": 12605, "sent": "a compute monitor that is off and is between two other monitors"}], "file_name": "COCO_train2014_000000561479_35009.jpg", "ann_id": 35009, "sent_ids": [12604, 12605], "ref_id": 9884}, {"segmentation": [[259.14, 163.44, 367.74, 165.59, 375.0, 164.52, 373.12, 366.67, 353.76, 368.82, 327.96, 343.01, 303.23, 318.28, 277.42, 306.45, 260.22, 297.85, 254.84, 279.57, 254.84, 259.14, 266.67, 255.91, 272.04, 249.46, 276.34, 227.96, 301.08, 230.11, 286.02, 213.98, 281.72, 211.83, 276.34, 209.68, 276.34, 194.62, 276.34, 181.72, 268.82, 174.19, 261.29, 177.42, 260.22, 167.74]], "area": 18048.73585, "iscrowd": 0, "image_id": 475980, "bbox": [254.84, 163.44, 120.16, 205.38], "category_id": 63, "id": 99825, "split": "val", "sentences": [{"tokens": ["overstuffed", "leather", "tan", "sofa", "against", "the", "wall", "with", "the", "american", "flag", "on", "it"], "raw": "overstuffed leather tan sofa against the wall with the american flag on it", "sent_id": 12608, "sent": "overstuffed leather tan sofa against the wall with the american flag on it"}, {"tokens": ["the", "couch", "on", "the", "wall", "in", "front", "of", "the", "american", "flag"], "raw": "The couch on the wall in front of the American flag.", "sent_id": 12609, "sent": "the couch on the wall in front of the american flag"}], "file_name": "COCO_train2014_000000475980_99825.jpg", "ann_id": 99825, "sent_ids": [12608, 12609], "ref_id": 9886}, {"segmentation": [[556.22, 253.51, 576.55, 268.49, 582.97, 248.16, 586.18, 233.19, 601.15, 232.12, 618.27, 246.02, 640.0, 251.37, 640.0, 236.4, 626.82, 220.35, 623.61, 204.31, 633.24, 178.63, 640.0, 169.01, 639.66, 3.21, 574.41, 3.21, 587.24, 16.04, 574.41, 69.53, 573.34, 102.69, 559.43, 163.66, 551.95, 192.54, 549.81, 234.26]], "area": 17209.991050000004, "iscrowd": 0, "image_id": 290185, "bbox": [549.81, 3.21, 90.19, 265.28], "category_id": 1, "id": 1736140, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "the", "background", "wearing", "a", "gray", "sweater", "and", "a", "pair", "of", "black", "slacks", "and", "a", "pair", "of", "black", "shoes"], "raw": "The person in the background wearing a gray sweater and a pair of black slacks and a pair of black shoes.", "sent_id": 12680, "sent": "the person in the background wearing a gray sweater and a pair of black slacks and a pair of black shoes"}, {"tokens": ["man", "in", "grey", "suit", "jacket", "and", "black", "pants", "standing", "near", "bar"], "raw": "Man in grey suit jacket and black pants standing near bar.", "sent_id": 12681, "sent": "man in grey suit jacket and black pants standing near bar"}], "file_name": "COCO_train2014_000000290185_1736140.jpg", "ann_id": 1736140, "sent_ids": [12680, 12681], "ref_id": 9919}, {"segmentation": [[356.01, 219.88, 359.24, 210.21, 368.37, 203.76, 373.74, 196.24, 380.73, 187.11, 387.18, 189.79, 386.1, 198.93, 386.1, 205.37, 404.91, 202.69, 402.76, 212.9, 403.29, 220.96, 439.29, 256.42, 488.73, 278.45, 504.84, 292.42, 537.62, 299.94, 556.43, 308.0, 572.54, 317.13, 577.38, 325.19, 581.68, 345.61, 582.22, 380.0, 583.83, 391.28, 574.16, 382.15, 573.08, 353.13, 568.25, 377.85, 568.25, 388.59, 561.8, 392.36, 523.65, 390.21, 443.59, 391.28, 437.14, 357.97, 436.07, 342.39, 436.07, 325.19, 406.52, 275.76, 390.4, 246.75, 386.1, 237.61, 368.91, 239.76, 356.01, 240.3, 344.19, 241.91, 338.28, 233.31, 345.27, 226.33], [560.73, 408.76, 570.35, 414.53, 571.31, 419.34, 559.77, 420.31, 542.45, 422.23, 533.8, 410.69, 536.68, 409.73], [450.12, 411.65, 494.36, 409.73, 501.1, 420.31, 452.04, 423.19]], "area": 19692.41375, "iscrowd": 0, "image_id": 166762, "bbox": [338.28, 187.11, 245.55, 236.08], "category_id": 25, "id": 595905, "split": "val", "sentences": [{"tokens": ["animal", "on", "the", "right"], "raw": "Animal on the right", "sent_id": 12708, "sent": "animal on the right"}, {"tokens": ["the", "lighter", "giraffe", "whose", "face", "is", "visible"], "raw": "The lighter giraffe whose face is visible.", "sent_id": 12709, "sent": "the lighter giraffe whose face is visible"}], "file_name": "COCO_train2014_000000166762_595905.jpg", "ann_id": 595905, "sent_ids": [12708, 12709], "ref_id": 9930}, {"segmentation": [[457.07, 163.89, 441.8, 208.69, 433.66, 250.42, 438.75, 318.63, 433.66, 402.1, 424.5, 441.8, 460.13, 445.87, 490.67, 444.86, 516.11, 378.69, 523.24, 348.15, 520.19, 323.72, 521.2, 311.5, 569.05, 317.61, 589.41, 309.47, 590.43, 294.2, 606.71, 293.18, 636.24, 284.02, 639.29, 148.62, 633.18, 121.14, 601.62, 127.25, 560.91, 143.53, 520.19, 145.57, 472.34, 148.62]], "area": 42954.286049999995, "iscrowd": 0, "image_id": 343847, "bbox": [424.5, 121.14, 214.79, 324.73], "category_id": 22, "id": 584869, "split": "val", "sentences": [{"tokens": ["there", "is", "an", "elephant", "standing", "first", "from", "right", "side"], "raw": "There is an elephant standing first from right side", "sent_id": 12792, "sent": "there is an elephant standing first from right side"}], "file_name": "COCO_train2014_000000343847_584869.jpg", "ann_id": 584869, "sent_ids": [12792], "ref_id": 9961}, {"segmentation": [[300.08, 151.96, 269.3, 153.89, 250.07, 159.66, 244.3, 145.23, 240.45, 133.69, 234.68, 111.57, 237.56, 82.71, 251.03, 62.52, 267.38, 51.94, 286.62, 48.09, 297.2, 50.98, 326.05, 59.63, 339.51, 59.63, 358.75, 73.1, 315.47, 68.29, 315.47, 106.76, 322.2, 111.57, 349.13, 128.88, 311.62, 134.65]], "area": 8174.50495, "iscrowd": 0, "image_id": 8063, "bbox": [234.68, 48.09, 124.07, 111.57], "category_id": 27, "id": 1165114, "split": "val", "sentences": [{"tokens": ["a", "traveler", "with", "a", "black", "and", "yellow", "bag", "on", "his", "bag", "with", "others", "on", "transit"], "raw": "A traveler with a black and yellow bag on his bag with others on transit.", "sent_id": 12810, "sent": "a traveler with a black and yellow bag on his bag with others on transit"}, {"tokens": ["a", "black", "and", "yellow", "backpack"], "raw": "A black and yellow backpack", "sent_id": 12811, "sent": "a black and yellow backpack"}], "file_name": "COCO_train2014_000000008063_1165114.jpg", "ann_id": 1165114, "sent_ids": [12810, 12811], "ref_id": 9970}, {"segmentation": [[76.4, 391.01, 114.61, 366.29, 126.97, 347.19, 64.04, 300.0, 128.09, 255.06, 148.31, 180.9, 149.44, 149.44, 135.96, 133.71, 135.96, 100.0, 156.18, 80.9, 196.63, 82.02, 184.27, 101.12, 194.38, 128.09, 197.75, 140.45, 275.28, 137.08, 312.36, 128.09, 314.61, 152.81, 279.78, 169.66, 240.45, 178.65, 212.36, 183.15, 203.37, 229.21, 230.34, 269.66, 259.55, 301.12, 240.45, 313.48, 249.44, 373.03, 243.82, 398.88, 255.06, 416.85, 270.79, 430.34, 270.79, 447.19, 264.04, 448.31, 232.58, 438.2, 214.61, 377.53, 211.24, 334.83, 167.42, 350.56, 152.81, 379.78, 122.47, 392.13, 110.11, 407.87, 112.36, 425.84]], "area": 33724.402500000004, "iscrowd": 0, "image_id": 432897, "bbox": [64.04, 80.9, 250.57, 367.41], "category_id": 1, "id": 448922, "split": "val", "sentences": [{"tokens": ["a", "picture", "of", "a", "baseball", "player", "who", "is", "up", "to", "bat", ",", "and", "she", "is", "wearing", "a", "dress"], "raw": "A picture of a baseball player who is up to bat, and she is wearing a dress.", "sent_id": 12817, "sent": "a picture of a baseball player who is up to bat , and she is wearing a dress"}, {"tokens": ["a", "women", "swining", "a", "bat"], "raw": "A women swining a bat.", "sent_id": 12818, "sent": "a women swining a bat"}], "file_name": "COCO_train2014_000000432897_448922.jpg", "ann_id": 448922, "sent_ids": [12817, 12818], "ref_id": 9974}, {"segmentation": [[274.54, 266.07, 282.03, 251.09, 280.67, 214.32, 284.76, 195.93, 269.78, 166.64, 258.2, 148.94, 222.78, 137.36, 192.14, 134.63, 175.79, 135.32, 169.66, 136.0, 156.72, 127.14, 139.02, 119.65, 124.03, 122.38, 107.01, 117.61, 117.9, 127.14, 111.09, 139.4, 112.46, 155.07, 125.4, 166.64, 129.48, 173.45, 148.55, 177.54, 186.01, 180.26, 220.74, 192.52, 241.85, 197.97, 255.47, 200.01, 268.41, 196.61, 264.33, 238.15, 263.65, 260.63, 260.92, 264.03]], "area": 9056.739549999998, "iscrowd": 0, "image_id": 432467, "bbox": [107.01, 117.61, 177.75, 148.46], "category_id": 17, "id": 49960, "split": "val", "sentences": [{"tokens": ["a", "grey", "and", "white", "cat", "that", "is", "laying", "on", "the", "seat", "of", "the", "scooter"], "raw": "A grey and white cat that is laying on the seat of the scooter.", "sent_id": 12825, "sent": "a grey and white cat that is laying on the seat of the scooter"}, {"tokens": ["cat", "sitting", "on", "the", "seat", "of", "the", "moped"], "raw": "cat sitting on the seat of the moped", "sent_id": 12826, "sent": "cat sitting on the seat of the moped"}], "file_name": "COCO_train2014_000000432467_49960.jpg", "ann_id": 49960, "sent_ids": [12825, 12826], "ref_id": 9976}, {"segmentation": [[52.04, 142.87, 64.32, 127.92, 65.39, 120.98, 69.13, 114.04, 69.66, 110.3, 73.4, 104.96, 81.94, 102.29, 95.82, 104.96, 138.53, 115.64, 165.23, 121.51, 174.84, 126.85, 181.25, 135.93, 182.85, 142.34, 186.05, 148.74, 190.32, 170.63, 191.39, 185.58, 194.59, 200.53, 195.13, 203.2, 211.14, 219.22, 227.16, 246.98, 220.75, 257.12, 209.54, 269.4, 204.74, 283.28, 203.67, 289.69, 204.74, 296.1, 202.07, 298.77, 202.07, 323.33, 193.53, 330.8, 183.38, 335.07, 173.77, 330.27, 175.91, 325.99, 183.38, 308.91, 183.92, 296.1, 181.25, 292.89, 175.91, 294.5, 172.7, 297.7, 171.1, 307.31, 163.09, 326.53, 163.63, 325.99, 158.82, 342.01, 154.02, 351.09, 144.41, 364.43, 140.14, 372.44, 140.67, 379.38, 127.32, 386.86, 125.72, 401.81, 120.38, 404.48, 100.09, 402.88, 46.7, 390.6, 10.93, 382.05, 1.32, 374.58, 0.79, 299.3, 14.67, 312.65, 27.48, 317.45, 34.43, 324.39, 37.63, 326.53, 50.98, 326.53, 66.99, 327.6, 90.48, 320.12, 102.23, 316.38, 113.98, 317.45, 120.92, 314.25, 132.66, 311.05, 139.6, 312.11, 141.2, 311.58, 140.14, 306.24, 144.41, 292.89, 142.81, 289.16, 143.34, 284.89, 146.01, 282.75, 142.27, 275.81, 142.81, 274.74, 146.54, 265.66, 149.21, 253.92, 149.75, 248.58, 160.42, 233.1, 162.56, 232.03, 162.56, 226.69, 186.05, 201.6, 188.19, 200.53, 167.36, 171.17, 160.42, 166.89, 144.41, 164.76, 132.66, 161.56, 120.92, 158.35, 109.17, 156.75, 95.82, 151.95, 88.88, 150.34, 80.34, 149.81, 62.19, 144.47, 50.44, 145.01]], "area": 23881.93290000003, "iscrowd": 0, "image_id": 32105, "bbox": [0.79, 102.29, 226.37, 302.19], "category_id": 33, "id": 1842194, "split": "val", "sentences": [{"tokens": ["blue", "bag", "with", "a", "d", "logo"], "raw": "blue bag with a D logo", "sent_id": 12844, "sent": "blue bag with a d logo"}, {"tokens": ["a", "duffel", "bag", "with", "a", "green", "hat", "on", "top"], "raw": "A duffel bag with a green hat on top.", "sent_id": 12845, "sent": "a duffel bag with a green hat on top"}], "file_name": "COCO_train2014_000000032105_1842194.jpg", "ann_id": 1842194, "sent_ids": [12844, 12845], "ref_id": 9982}, {"segmentation": [[451.84, 327.48, 454.49, 296.92, 449.84, 271.67, 435.89, 253.07, 410.64, 239.12, 387.39, 229.81, 361.48, 231.81, 338.22, 241.11, 319.62, 252.4, 310.32, 271.01, 303.01, 304.23, 307.66, 329.48, 333.57, 357.38, 359.48, 373.33, 389.38, 377.98, 407.99, 375.98, 440.54, 343.43, 451.84, 324.82], [335.35, 235.65, 342.4, 207.45, 321.25, 179.26, 297.08, 168.18, 254.79, 182.28, 236.66, 214.5, 201.41, 218.53, 191.34, 224.57, 184.29, 193.36, 159.12, 172.21, 127.9, 165.16, 95.67, 186.31, 81.57, 207.45, 84.59, 228.6, 64.45, 200.4, 46.32, 197.38, 29.2, 193.36, 4.03, 200.4, 0.0, 231.62, 3.02, 320.24, 0.0, 383.69, 3.02, 393.76, 17.12, 397.79, 3.02, 397.79, 3.02, 421.96, 640.0, 418.94, 631.43, 306.15, 631.43, 289.03, 631.43, 266.87, 624.38, 246.73, 617.33, 218.53, 624.38, 197.38, 617.33, 162.14, 606.25, 136.96, 589.13, 122.86, 571.0, 119.84, 535.76, 132.93, 514.61, 151.06, 507.56, 175.23, 507.56, 193.36, 500.51, 204.43, 486.41, 231.62, 486.41, 245.72, 465.26, 235.65, 472.31, 207.45, 451.16, 162.14, 408.87, 158.11, 366.57, 193.36, 366.57, 224.57, 345.42, 242.7, 324.27, 242.7, 334.34, 232.63]], "area": 167452.02674999993, "iscrowd": 0, "image_id": 353282, "bbox": [0.0, 119.84, 640.0, 302.12], "category_id": 53, "id": 1047948, "split": "val", "sentences": [{"tokens": ["all", "of", "the", "apples", "that", "are", "in", "the", "box"], "raw": "All of the apples that are in the box.", "sent_id": 12896, "sent": "all of the apples that are in the box"}], "file_name": "COCO_train2014_000000353282_1047948.jpg", "ann_id": 1047948, "sent_ids": [12896], "ref_id": 10004}, {"segmentation": [[118.69, 181.9, 113.04, 185.5, 97.61, 194.24, 94.53, 211.21, 94.01, 216.35, 91.96, 225.6, 96.58, 242.57, 104.81, 256.45, 104.81, 262.11, 101.72, 285.76, 101.72, 296.04, 105.32, 298.62, 106.87, 304.79, 112.52, 305.81, 114.06, 306.33, 116.64, 317.64, 171.14, 295.53, 171.65, 291.42, 175.76, 285.76, 167.54, 256.45, 165.48, 249.26, 169.59, 250.8, 181.42, 233.32, 177.31, 226.63, 168.05, 196.81, 165.48, 190.64, 163.42, 184.47, 157.77, 184.47, 139.26, 178.82, 135.66, 176.76, 141.83, 171.62, 141.83, 166.48, 145.43, 156.71, 143.37, 141.28, 130.0, 133.57, 107.89, 138.71, 102.75, 149.51, 104.81, 153.11, 106.35, 158.25, 103.27, 159.28, 104.3, 164.93, 106.87, 166.99, 108.41, 173.16, 114.06, 181.9]], "area": 10548.051649999996, "iscrowd": 0, "image_id": 444033, "bbox": [91.96, 133.57, 89.46, 184.07], "category_id": 1, "id": 512347, "split": "val", "sentences": [{"tokens": ["an", "older", "woman", "in", "a", "black", "suit", "looks", "upon", "a", "spread", "-", "out", "buffet", "of", "pizza", "and", "other", "foods"], "raw": "An older woman in a black suit looks upon a spread-out buffet of pizza and other foods.", "sent_id": 13079, "sent": "an older woman in a black suit looks upon a spread - out buffet of pizza and other foods"}, {"tokens": ["a", "woman", "in", "black", "shirt", "with", "gray", "hair", "standing", "next", "to", "a", "man"], "raw": "a woman in black shirt with gray hair standing next to a man", "sent_id": 13080, "sent": "a woman in black shirt with gray hair standing next to a man"}], "file_name": "COCO_train2014_000000444033_512347.jpg", "ann_id": 512347, "sent_ids": [13079, 13080], "ref_id": 10071}, {"segmentation": [[261.0, 49.9, 258.12, 64.29, 268.67, 101.71, 274.43, 131.46, 313.77, 138.18, 311.85, 95.96, 354.07, 75.8, 425.08, 64.29, 471.14, 58.53, 478.82, 30.71, 467.3, 16.31, 432.76, 0.96, 325.29, 1.92, 300.34, 9.6, 275.39, 24.95]], "area": 16395.651749999994, "iscrowd": 0, "image_id": 128475, "bbox": [258.12, 0.96, 220.7, 137.22], "category_id": 51, "id": 1040865, "split": "val", "sentences": [{"tokens": ["a", "container", "with", "black", "stuff", "in", "it"], "raw": "A container with black stuff in it", "sent_id": 13101, "sent": "a container with black stuff in it"}, {"tokens": ["white", "glass", "bowl", "with", "a", "black", "dip"], "raw": "white glass bowl with a black dip", "sent_id": 13102, "sent": "white glass bowl with a black dip"}], "file_name": "COCO_train2014_000000128475_1040865.jpg", "ann_id": 1040865, "sent_ids": [13101, 13102], "ref_id": 10081}, {"segmentation": [[3.61, 178.73, 113.36, 157.16, 315.01, 123.4, 397.56, 114.95, 438.83, 120.58, 487.59, 150.59, 511.98, 151.53, 561.7, 159.04, 573.89, 172.16, 562.64, 189.06, 543.88, 194.68, 542.94, 194.68, 537.31, 225.63, 503.55, 264.09, 373.17, 320.36, 310.33, 331.62, 326.27, 374.77, 320.64, 378.52, 291.56, 381.34, 282.19, 373.83, 285.0, 355.07, 243.73, 356.01, 237.16, 354.13, 209.02, 344.75, 175.26, 340.07, 189.32, 354.13, 186.51, 364.44, 168.69, 373.83, 154.62, 373.83, 139.61, 369.14, 143.36, 350.38, 152.75, 338.19, 105.85, 334.44, 56.13, 335.37, 0.8, 335.37]], "area": 100068.41784999995, "iscrowd": 0, "image_id": 358599, "bbox": [0.8, 114.95, 573.09, 266.39], "category_id": 5, "id": 160766, "split": "val", "sentences": [{"tokens": ["an", "air", "force", "plane", "with", "a", "red", "nose"], "raw": "an air force plane with a red nose", "sent_id": 13133, "sent": "an air force plane with a red nose"}, {"tokens": ["us", "airforce", "plane"], "raw": "US Airforce plane", "sent_id": 13134, "sent": "us airforce plane"}], "file_name": "COCO_train2014_000000358599_160766.jpg", "ann_id": 160766, "sent_ids": [13133, 13134], "ref_id": 10096}, {"segmentation": [[568.31, 321.26, 598.65, 420.37, 594.61, 439.58, 53.6, 449.47, 52.58, 449.47, 38.43, 403.96, 7.08, 316.99, 12.13, 297.78, 18.2, 281.6, 109.21, 295.76, 153.71, 289.69, 219.44, 289.69, 244.72, 309.92, 256.85, 342.28, 288.2, 347.33, 308.43, 324.07, 357.98, 304.86, 568.31, 313.96]], "area": 77329.88730000002, "iscrowd": 0, "image_id": 423890, "bbox": [7.08, 281.6, 591.57, 167.87], "category_id": 67, "id": 320576, "split": "val", "sentences": [{"tokens": ["the", "pizza", "with", "mozerella", "cheese"], "raw": "The pizza with mozerella cheese.", "sent_id": 13196, "sent": "the pizza with mozerella cheese"}, {"tokens": ["a", "wooden", "table", "with", "two", "pizzas", "on", "top", "of", "it"], "raw": "A wooden table with two pizzas on top of it.", "sent_id": 13197, "sent": "a wooden table with two pizzas on top of it"}], "file_name": "COCO_train2014_000000423890_320576.jpg", "ann_id": 320576, "sent_ids": [13196, 13197], "ref_id": 10120}, {"segmentation": [[369.77, 146.45, 461.26, 156.93, 509.87, 173.13, 523.21, 183.62, 516.54, 199.82, 496.52, 210.3, 458.4, 220.78, 394.55, 222.69, 370.72, 226.5, 367.87, 212.21, 369.77, 204.58, 370.72, 191.24, 367.87, 180.76, 367.87, 155.98, 369.77, 145.49], [324.03, 139.78, 194.42, 137.87, 137.23, 145.49, 120.08, 159.79, 119.13, 175.99, 123.89, 188.38, 141.05, 198.86, 163.92, 208.39, 243.97, 220.78, 316.4, 225.55, 330.7, 196.0, 329.74, 180.76, 325.93, 162.65, 325.93, 147.4]], "area": 24336.643799999998, "iscrowd": 0, "image_id": 277200, "bbox": [119.13, 137.87, 404.08, 88.63], "category_id": 42, "id": 649327, "split": "val", "sentences": [{"tokens": ["yellow", "ski", "board", "on", "the", "man", "who", "is", "standing"], "raw": "yellow ski board on the man who is standing", "sent_id": 13250, "sent": "yellow ski board on the man who is standing"}, {"tokens": ["a", "beige", "surfboard", "being", "carried", "by", "a", "man", "in", "a", "wetsuit"], "raw": "A beige surfboard being carried by a man in a wetsuit", "sent_id": 13251, "sent": "a beige surfboard being carried by a man in a wetsuit"}], "file_name": "COCO_train2014_000000277200_649327.jpg", "ann_id": 649327, "sent_ids": [13250, 13251], "ref_id": 10136}, {"segmentation": [[571.69, 181.9, 483.1, 150.01, 440.58, 145.28, 407.51, 135.84, 364.98, 135.84, 328.37, 140.56, 315.37, 139.38, 304.74, 126.39, 292.93, 120.48, 285.84, 102.76, 285.84, 95.68, 356.72, 96.86, 427.59, 94.49, 491.37, 99.22, 574.05, 114.57, 591.77, 124.02, 622.48, 146.47, 624.84, 155.92, 620.12, 172.45, 602.4, 181.9]], "area": 16203.19225, "iscrowd": 0, "image_id": 426838, "bbox": [285.84, 94.49, 339.0, 87.41], "category_id": 57, "id": 1064786, "split": "val", "sentences": [{"tokens": ["the", "longer", "of", "the", "two", "carrots"], "raw": "The longer of the two carrots.", "sent_id": 13300, "sent": "the longer of the two carrots"}, {"tokens": ["a", "carrot"], "raw": "a carrot", "sent_id": 13301, "sent": "a carrot"}], "file_name": "COCO_train2014_000000426838_1064786.jpg", "ann_id": 1064786, "sent_ids": [13300, 13301], "ref_id": 10156}, {"segmentation": [[180.79, 198.82, 200.02, 236.32, 215.4, 249.78, 217.33, 254.59, 224.06, 255.55, 230.79, 259.4, 258.68, 271.9, 254.83, 298.83, 253.87, 308.44, 255.79, 313.25, 258.68, 319.98, 257.72, 332.48, 255.79, 341.14, 255.79, 352.68, 255.79, 355.56, 255.79, 368.06, 255.79, 372.87, 253.87, 372.87, 250.98, 366.14, 250.98, 344.02, 250.98, 327.67, 235.6, 309.4, 225.02, 298.83, 221.17, 294.02, 222.14, 308.44, 222.14, 323.83, 226.94, 338.25, 231.75, 348.83, 239.44, 365.18, 245.21, 370.95, 244.25, 372.87, 243.29, 374.79, 235.6, 374.79, 225.98, 362.29, 215.4, 333.44, 209.63, 317.1, 201.94, 308.44, 200.98, 324.79, 195.21, 366.14, 190.4, 369.99, 185.59, 367.1, 183.67, 360.37, 193.29, 304.59, 182.71, 269.01, 177.9, 255.55, 173.09, 238.24, 167.32, 221.9, 157.71, 214.2, 153.86, 211.32, 158.67, 196.89, 164.44, 184.39, 177.9, 184.39]], "area": 7267.643599999999, "iscrowd": 0, "image_id": 526713, "bbox": [153.86, 184.39, 104.82, 190.4], "category_id": 25, "id": 598997, "split": "val", "sentences": [{"tokens": ["a", "small", "giraffe"], "raw": "a small giraffe", "sent_id": 13311, "sent": "a small giraffe"}, {"tokens": ["a", "young", "giraffe", "walking", "with", "other", "giraffes"], "raw": "a young giraffe walking with other giraffes.", "sent_id": 13312, "sent": "a young giraffe walking with other giraffes"}], "file_name": "COCO_train2014_000000526713_598997.jpg", "ann_id": 598997, "sent_ids": [13311, 13312], "ref_id": 10160}, {"segmentation": [[199.91, 207.83, 183.66, 142.82, 208.04, 90.81, 226.73, 66.43, 234.04, 62.37, 242.17, 33.12, 252.73, 27.43, 264.92, 33.12, 281.17, 54.24, 284.42, 70.5, 284.42, 90.0, 294.99, 159.07, 303.12, 222.46, 304.74, 277.72, 287.67, 273.66, 283.61, 311.85, 288.49, 337.04, 262.48, 350.05, 264.92, 317.54, 260.86, 250.9, 255.17, 328.1, 238.92, 356.55, 220.23, 349.23, 230.79, 316.73, 238.1, 275.28, 224.29, 251.72, 219.41, 228.96, 218.6, 206.21, 223.48, 161.51, 225.91, 127.38, 206.41, 135.51, 203.16, 159.07, 214.54, 184.27, 218.6, 198.89]], "area": 22362.018700000008, "iscrowd": 0, "image_id": 259443, "bbox": [183.66, 27.43, 121.08, 329.12], "category_id": 1, "id": 541542, "split": "val", "sentences": [{"tokens": ["man", "on", "the", "left", "in", "the", "white", "cap"], "raw": "Man on the left in the white cap", "sent_id": 13425, "sent": "man on the left in the white cap"}, {"tokens": ["a", "man", "with", "a", "tattoo", "holding", "a", "tennis", "racket"], "raw": "a man with a tattoo holding a tennis racket", "sent_id": 13426, "sent": "a man with a tattoo holding a tennis racket"}], "file_name": "COCO_train2014_000000259443_541542.jpg", "ann_id": 541542, "sent_ids": [13425, 13426], "ref_id": 10207}, {"segmentation": [[568.85, 141.4, 551.51, 163.07, 537.43, 191.24, 534.18, 202.08, 532.01, 233.5, 525.51, 249.75, 519.01, 271.42, 520.09, 293.09, 520.09, 307.18, 520.09, 324.51, 517.92, 331.02, 512.51, 315.85, 512.51, 297.43, 512.51, 283.34, 512.51, 270.34, 509.26, 259.5, 503.84, 259.5, 501.67, 275.76, 502.75, 298.51, 508.17, 314.76, 509.26, 325.6, 499.5, 320.18, 496.25, 297.43, 493.0, 286.59, 493.0, 310.43, 490.84, 323.43, 485.42, 302.84, 485.42, 281.17, 480.0, 277.92, 480.0, 260.59, 477.83, 234.58, 476.75, 218.33, 494.09, 198.83, 548.26, 146.82, 553.68, 128.4, 566.68, 115.4, 569.93, 104.56, 585.1, 114.31, 589.44, 129.48, 597.02, 140.32, 593.77, 150.07, 574.27, 139.23]], "area": 7151.045550000005, "iscrowd": 0, "image_id": 50101, "bbox": [476.75, 104.56, 120.27, 226.46], "category_id": 25, "id": 598667, "split": "val", "sentences": [{"tokens": ["giraffe", "in", "front", "of", "barn", "door"], "raw": "giraffe in front of barn door", "sent_id": 13431, "sent": "giraffe in front of barn door"}, {"tokens": ["a", "giraffe", "closest", "to", "the", "door"], "raw": "A giraffe closest to the door", "sent_id": 13432, "sent": "a giraffe closest to the door"}], "file_name": "COCO_train2014_000000050101_598667.jpg", "ann_id": 598667, "sent_ids": [13431, 13432], "ref_id": 10208}, {"segmentation": [[235.61, 124.78, 244.49, 140.67, 246.35, 133.66, 253.37, 138.4, 259.97, 135.1, 268.64, 134.07, 276.9, 136.34, 285.57, 143.36, 288.25, 148.72, 298.16, 145.42, 307.86, 143.98, 316.11, 142.95, 322.31, 142.74, 325.2, 142.12, 317.97, 136.55, 304.56, 126.85, 297.54, 123.54, 276.28, 122.92, 245.32, 124.16], [302.04, 218.13, 305.84, 220.22, 308.12, 226.67, 312.67, 230.28, 320.08, 231.42, 326.16, 229.71, 326.73, 225.34, 328.25, 220.78, 328.82, 217.75, 333.38, 217.56, 334.33, 208.25, 323.5, 200.65, 313.43, 191.16, 308.69, 190.4, 305.84, 191.35, 306.6, 201.03, 306.98, 203.5, 305.27, 204.26, 302.42, 211.48], [349.47, 219.74, 350.44, 222.47, 354.46, 221.35, 354.94, 224.4, 362.18, 221.99, 362.18, 217.65, 364.11, 215.4, 365.4, 212.34, 363.63, 210.73, 360.41, 209.93, 356.71, 210.57, 352.05, 211.37, 350.76, 214.27, 348.67, 217.33], [384.37, 212.18, 384.18, 216.92, 384.94, 221.29, 393.48, 221.67, 394.62, 212.56, 393.86, 193.56, 392.72, 183.5, 390.45, 189.95, 388.74, 193.56, 388.93, 197.36, 387.03, 201.16, 387.03, 204.2, 386.65, 207.05, 387.03, 209.9, 384.56, 211.8]], "area": 2467.8676, "iscrowd": 0, "image_id": 385066, "bbox": [235.61, 122.92, 159.01, 108.5], "category_id": 3, "id": 132998, "split": "val", "sentences": [{"tokens": ["the", "vehicle", "in", "front", "of", "the", "red", "car"], "raw": "The vehicle in front of the red car.", "sent_id": 13435, "sent": "the vehicle in front of the red car"}, {"tokens": ["a", "dark", "car", "in", "front", "of", "a", "red", "car"], "raw": "A dark car in front of a red car", "sent_id": 13436, "sent": "a dark car in front of a red car"}], "file_name": "COCO_train2014_000000385066_132998.jpg", "ann_id": 132998, "sent_ids": [13435, 13436], "ref_id": 10210}, {"segmentation": [[66.87, 265.14, 73.82, 260.5, 78.45, 256.45, 84.83, 253.55, 91.78, 248.92, 96.99, 244.86, 100.47, 241.39, 106.84, 237.33, 113.21, 235.01, 116.69, 229.8, 125.38, 226.9, 133.49, 224.58, 139.86, 223.43, 142.76, 221.69, 146.24, 219.37, 152.61, 214.74, 153.77, 213.0, 160.14, 211.26, 165.35, 209.52, 171.73, 208.36, 178.1, 207.2, 182.73, 206.05, 187.95, 206.05, 193.74, 205.47, 197.8, 205.47, 205.91, 203.73, 213.44, 203.73, 227.34, 203.73, 232.56, 206.05, 240.09, 208.36, 244.14, 208.36, 252.25, 208.36, 259.21, 208.36, 267.32, 208.36, 278.32, 208.36, 288.17, 208.36, 292.23, 207.78, 292.81, 204.89, 293.97, 200.83, 296.28, 196.78, 299.18, 194.46, 303.24, 196.78, 307.87, 196.78, 308.45, 196.78, 315.98, 195.04, 320.62, 195.04, 329.89, 198.51, 334.52, 208.94, 336.84, 211.26, 340.89, 214.74, 343.79, 217.63, 344.37, 222.85, 340.89, 225.16, 340.31, 226.9, 339.15, 229.8, 335.68, 230.96, 333.94, 232.12, 331.04, 233.27, 330.46, 235.01, 328.15, 239.07, 322.93, 241.39, 318.88, 243.7, 315.98, 244.86, 314.82, 246.6, 312.51, 248.34, 311.93, 248.92, 310.19, 250.65, 308.45, 252.39, 306.13, 254.71, 304.39, 254.71, 303.24, 255.29, 300.92, 257.03, 299.18, 257.03, 294.55, 257.61, 291.65, 258.77, 287.59, 259.34, 282.96, 260.5, 280.64, 260.5, 276.59, 261.08, 276.59, 263.4, 277.17, 266.88, 276.01, 269.19, 269.63, 277.3, 267.32, 278.46, 264.42, 279.04, 263.84, 279.62, 261.52, 279.04, 259.79, 278.46, 258.63, 277.88, 258.63, 276.72, 258.63, 274.99, 258.63, 274.41, 258.05, 272.67, 258.05, 270.35, 258.05, 269.19, 258.05, 268.03, 258.05, 267.46, 257.47, 266.88, 255.73, 265.72, 253.41, 264.56, 251.67, 265.14, 249.94, 265.72, 247.04, 265.14, 245.88, 263.98, 244.72, 263.4, 242.98, 260.5, 242.41, 255.87, 242.41, 255.29, 234.29, 255.29, 231.98, 255.87, 228.5, 255.87, 226.18, 255.87, 219.23, 255.87, 215.76, 255.87, 211.7, 255.87, 207.07, 254.71, 203.59, 254.13, 194.9, 254.13, 192.0, 254.13, 187.95, 254.13, 184.47, 253.55, 181.58, 251.81, 172.88, 251.81, 169.41, 251.81, 164.77, 253.55, 159.56, 252.97, 156.08, 253.55, 153.77, 253.55, 151.45, 253.55, 149.71, 253.55, 132.33, 255.29, 128.86, 255.29, 124.22, 257.03, 118.43, 258.77, 113.79, 260.5, 112.05, 261.66, 110.32, 262.24, 105.68, 266.3, 98.73, 266.3, 96.41, 266.3, 94.1, 266.3, 90.62, 263.4, 90.62, 262.82, 88.88, 264.56, 88.88, 266.3, 83.09, 270.35, 79.61, 273.25, 78.45, 273.83, 73.24, 274.41, 71.5, 274.41, 69.18, 274.41, 65.71, 274.41, 63.97, 272.67, 63.97, 271.51, 68.6, 264.56]], "area": 11611.661549999993, "iscrowd": 0, "image_id": 357663, "bbox": [63.97, 194.46, 280.4, 85.16], "category_id": 17, "id": 48137, "split": "val", "sentences": [{"tokens": ["the", "light", "colored", "cat", "who", "is", "laying", "down"], "raw": "the light colored cat who is laying down", "sent_id": 13439, "sent": "the light colored cat who is laying down"}, {"tokens": ["a", "grey", "striped", "cat", "on", "his", "side"], "raw": "A grey striped cat on his side", "sent_id": 13440, "sent": "a grey striped cat on his side"}], "file_name": "COCO_train2014_000000357663_48137.jpg", "ann_id": 48137, "sent_ids": [13439, 13440], "ref_id": 10211}, {"segmentation": [[318.2, 251.4, 314.97, 257.87, 311.73, 278.36, 399.1, 444.48, 415.28, 441.24, 392.63, 409.96, 393.71, 390.54, 390.47, 381.91, 385.08, 387.31, 379.69, 382.99, 318.2, 267.58, 320.36, 249.24], [273.98, 286.99, 265.35, 302.09, 376.45, 434.77, 389.39, 432.61, 377.53, 416.43, 366.74, 403.49, 357.03, 384.07, 350.56, 385.15, 348.4, 389.47, 275.06, 296.7, 275.06, 286.99]], "area": 4383.273499999989, "iscrowd": 0, "image_id": 374873, "bbox": [265.35, 249.24, 149.93, 195.24], "category_id": 35, "id": 606894, "split": "val", "sentences": [{"tokens": ["red", "and", "gray", "skis", "sticking", "out", "of", "the", "snow"], "raw": "Red and gray skis sticking out of the snow.", "sent_id": 13470, "sent": "red and gray skis sticking out of the snow"}, {"tokens": ["a", "man", "'", "s", "skis", "planted", "in", "the", "snow", "next", "to", "him"], "raw": "A man's skis planted in the snow next to him", "sent_id": 13471, "sent": "a man ' s skis planted in the snow next to him"}], "file_name": "COCO_train2014_000000374873_606894.jpg", "ann_id": 606894, "sent_ids": [13470, 13471], "ref_id": 10224}, {"segmentation": [[504.0, 302.4, 459.36, 302.4, 410.4, 282.24, 421.92, 272.16, 459.36, 253.44, 470.88, 182.88, 472.32, 128.16, 450.72, 102.24, 430.56, 70.56, 434.88, 1.44, 570.24, 4.32, 571.68, 44.64, 521.28, 33.12, 496.8, 38.88, 486.72, 50.4, 482.4, 77.76, 488.16, 110.88, 501.12, 131.04, 502.56, 138.24, 488.16, 257.76, 534.24, 279.36]], "area": 16225.920000000006, "iscrowd": 0, "image_id": 153814, "bbox": [410.4, 1.44, 161.28, 300.96], "category_id": 46, "id": 1497237, "split": "val", "sentences": [{"tokens": ["wine", "glass", "nearest", "the", "woman", "'", "s", "pizza"], "raw": "Wine glass nearest the woman's pizza", "sent_id": 13541, "sent": "wine glass nearest the woman ' s pizza"}, {"tokens": ["wine", "glass", "that", "is", "closest", "to", "the", "lady", "in", "black"], "raw": "Wine glass that is closest to the lady in black.", "sent_id": 13542, "sent": "wine glass that is closest to the lady in black"}], "file_name": "COCO_train2014_000000153814_1497237.jpg", "ann_id": 1497237, "sent_ids": [13541, 13542], "ref_id": 10252}, {"segmentation": [[22.6, 355.65, 30.32, 369.72, 49.38, 369.72, 50.29, 364.27, 44.39, 358.37, 47.11, 355.65, 57.55, 352.47, 77.97, 335.68, 82.96, 326.6, 76.16, 313.44, 78.88, 310.72, 82.51, 312.53, 83.87, 322.97, 85.23, 328.42, 72.98, 345.21, 72.98, 349.75, 68.44, 352.92, 72.07, 362.91, 77.97, 368.35, 95.22, 366.54, 95.67, 361.09, 92.49, 360.19, 94.31, 342.49, 96.58, 335.68, 102.03, 312.08, 103.84, 299.82, 101.12, 290.29, 97.94, 284.39, 106.11, 274.86, 117.0, 265.33, 116.55, 252.62, 125.17, 255.35, 129.71, 253.53, 127.89, 250.35, 131.98, 244.45, 136.06, 239.01, 134.7, 223.58, 136.97, 219.49, 133.79, 215.86, 128.35, 209.05, 119.27, 206.78, 110.19, 209.05, 103.84, 215.41, 99.3, 225.39, 97.49, 233.11, 67.99, 237.19, 56.19, 244.45, 30.77, 269.42, 25.32, 285.75, 29.86, 301.64, 30.77, 309.35, 28.05, 324.79, 28.05, 338.4, 32.13, 338.4, 39.39, 337.95, 41.21, 330.23, 41.21, 323.42, 40.3, 316.16, 42.12, 312.08, 53.46, 322.52, 51.19, 330.69, 32.59, 343.39, 28.05, 342.03]], "area": 9752.703700000007, "iscrowd": 0, "image_id": 162396, "bbox": [22.6, 206.78, 114.37, 162.94], "category_id": 1, "id": 216253, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "purple", "shirt", "and", "jeans", "stooped", "down", "being", "photographed"], "raw": "A man in a purple shirt and jeans stooped down being photographed", "sent_id": 13556, "sent": "a man in a purple shirt and jeans stooped down being photographed"}, {"tokens": ["a", "man", "in", "a", "purple", "shirt", "and", "blue", "jeans", "on", "a", "skateboard"], "raw": "A man in a purple shirt and blue jeans on a skateboard.", "sent_id": 13557, "sent": "a man in a purple shirt and blue jeans on a skateboard"}], "file_name": "COCO_train2014_000000162396_216253.jpg", "ann_id": 216253, "sent_ids": [13556, 13557], "ref_id": 10258}, {"segmentation": [[319.95, 121.79, 288.47, 121.52, 281.09, 121.61, 268.23, 121.97, 263.01, 121.97, 258.61, 122.15, 255.46, 117.02, 251.5, 117.02, 249.25, 119.72, 243.86, 113.61, 242.61, 113.72, 237.0, 116.41, 223.33, 107.38, 208.69, 96.4, 198.44, 105.67, 192.59, 113.97, 165.5, 115.19, 150.13, 115.19, 129.87, 115.43, 129.14, 112.75, 118.89, 112.75, 116.69, 115.92, 103.27, 117.14, 100.1, 120.31, 96.44, 120.07, 91.07, 125.68, 83.51, 118.12, 78.14, 122.26, 79.36, 127.39, 64.96, 120.31, 55.69, 128.85, 55.69, 132.51, 57.64, 135.44, 9.57, 134.95, 0.0, 135.69, 0.05, 61.5, 0.29, 12.21, 0.0, 0.25, 148.42, 0.25, 230.17, 1.47, 278.97, 1.47, 318.02, 0.74, 319.97, 0.98]], "area": 38080.91429999999, "iscrowd": 0, "image_id": 351301, "bbox": [0.0, 0.25, 319.97, 135.44], "category_id": 67, "id": 2226423, "split": "val", "sentences": [{"tokens": ["a", "remote", "control", "set", "between", "a", "glass", "and", "a", "floral", "coffee", "mug"], "raw": "A remote control set between a glass and a floral coffee mug.", "sent_id": 13594, "sent": "a remote control set between a glass and a floral coffee mug"}, {"tokens": ["a", "tabletop", "with", "a", "remote", "and", "two", "glasses"], "raw": "A tabletop with a remote and two glasses.", "sent_id": 13595, "sent": "a tabletop with a remote and two glasses"}], "file_name": "COCO_train2014_000000351301_2226423.jpg", "ann_id": 2226423, "sent_ids": [13594, 13595], "ref_id": 10271}, {"segmentation": [[248.07, 161.02, 243.3, 151.12, 240.0, 144.52, 238.9, 136.45, 234.13, 132.78, 229.36, 133.15, 221.66, 123.97, 219.82, 117.74, 212.49, 113.7, 213.59, 108.2, 215.05, 106.0, 220.92, 106.37, 223.86, 107.47, 220.92, 92.06, 216.89, 82.16, 217.25, 74.46, 218.72, 68.95, 238.16, 68.95, 257.97, 73.36, 264.21, 75.19, 289.15, 77.39, 315.93, 82.89, 330.23, 89.86, 344.17, 91.33, 355.17, 95.0, 368.38, 100.5, 391.12, 115.54, 406.89, 124.34, 420.83, 139.01, 419.36, 144.88, 408.36, 148.55, 393.32, 154.42, 353.71, 160.66, 323.26, 169.46, 286.21, 174.96, 258.7, 173.49, 251.0, 173.49, 243.3, 163.59, 246.6, 160.29]], "area": 14162.043099999999, "iscrowd": 0, "image_id": 335376, "bbox": [212.49, 68.95, 208.34, 106.01], "category_id": 59, "id": 1076751, "split": "val", "sentences": [{"tokens": ["the", "two", "slices", "of", "pizza", "to", "the", "right"], "raw": "the two slices of pizza to the right", "sent_id": 13680, "sent": "the two slices of pizza to the right"}, {"tokens": ["topmost", "two", "slices", "of", "pizza"], "raw": "Topmost two slices of pizza.", "sent_id": 13681, "sent": "topmost two slices of pizza"}], "file_name": "COCO_train2014_000000335376_1076751.jpg", "ann_id": 1076751, "sent_ids": [13680, 13681], "ref_id": 10301}, {"segmentation": [[269.3, 283.73, 254.88, 243.33, 256.8, 228.91, 292.39, 203.9, 283.73, 190.44, 286.62, 170.24, 287.58, 145.23, 292.39, 128.88, 301.04, 108.68, 303.93, 100.99, 310.66, 91.37, 347.21, 78.87, 366.44, 53.86, 366.44, 67.33, 400.11, 79.83, 418.38, 92.33, 431.85, 115.42, 438.58, 128.88, 443.39, 160.62, 449.16, 180.82, 445.31, 191.4, 445.31, 201.02, 412.61, 219.29, 400.11, 245.26, 396.26, 281.81, 404.92, 323.16, 394.34, 368.37, 386.64, 397.22, 368.37, 399.15, 364.52, 369.33, 364.52, 353.94, 381.83, 352.98, 388.57, 338.55, 388.57, 336.63, 387.6, 329.9, 382.8, 313.55, 379.91, 295.27, 378.95, 281.81, 371.25, 270.27, 362.6, 276.04, 351.06, 268.34, 355.87, 255.84, 354.9, 251.99, 334.71, 260.65, 327.97, 272.19, 314.51, 264.49, 311.62, 282.77, 298.16, 276.04, 288.54, 286.62, 279.88, 283.73]], "area": 30452.35279999998, "iscrowd": 0, "image_id": 46592, "bbox": [254.88, 53.86, 194.28, 345.29], "category_id": 1, "id": 225515, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "blue", "shirt", "with", "two", "dogs"], "raw": "A man with a blue shirt with two dogs.", "sent_id": 13705, "sent": "a man with a blue shirt with two dogs"}, {"tokens": ["a", "man", "with", "a", "blue", "shirt", "with", "his", "two", "dogs", "in", "front", "of", "him"], "raw": "A man with a blue shirt with his two dogs in front of him.", "sent_id": 13706, "sent": "a man with a blue shirt with his two dogs in front of him"}], "file_name": "COCO_train2014_000000046592_225515.jpg", "ann_id": 225515, "sent_ids": [13705, 13706], "ref_id": 10310}, {"segmentation": [[358.11, 284.52, 382.56, 316.16, 405.57, 336.3, 428.58, 344.93, 445.84, 363.63, 445.84, 434.1, 442.97, 457.11, 440.09, 477.24, 428.58, 468.61, 435.78, 449.92, 431.46, 409.65, 430.02, 435.54, 421.39, 462.86, 415.64, 454.23, 421.39, 426.91, 412.76, 405.33, 408.45, 388.07, 388.31, 388.07, 391.19, 422.59, 395.51, 454.23, 396.94, 465.74, 388.31, 465.74, 388.31, 442.73, 384.0, 418.28, 381.12, 436.97, 381.12, 464.3, 372.49, 470.05, 375.37, 455.67, 373.93, 405.33, 365.3, 370.82, 359.55, 343.49, 343.73, 303.22, 336.54, 293.15, 330.79, 270.14, 337.98, 267.27, 346.61, 273.02, 359.55, 274.46, 360.99, 264.39, 359.55, 275.9]], "area": 9107.035349999996, "iscrowd": 0, "image_id": 348935, "bbox": [330.79, 264.39, 115.05, 212.85], "category_id": 25, "id": 598155, "split": "val", "sentences": [{"tokens": ["a", "small", "giraffe", "is", "standing", "side", "of", "the", "thorn", "tree"], "raw": "A small giraffe is standing side of the thorn tree.", "sent_id": 13737, "sent": "a small giraffe is standing side of the thorn tree"}, {"tokens": ["one", "giraffe", "standing", "alone"], "raw": "One Giraffe standing alone", "sent_id": 13738, "sent": "one giraffe standing alone"}], "file_name": "COCO_train2014_000000348935_598155.jpg", "ann_id": 598155, "sent_ids": [13737, 13738], "ref_id": 10321}, {"segmentation": [[189.84, 631.37, 171.15, 619.87, 171.15, 612.67, 176.9, 575.28, 145.26, 556.58, 130.88, 537.89, 123.69, 517.75, 123.69, 476.04, 153.89, 447.28, 191.28, 434.34, 276.13, 415.64, 286.2, 454.47, 287.64, 512.0, 287.64, 549.39, 280.45, 572.4, 277.57, 601.17, 250.25, 632.81]], "area": 27049.989749999997, "iscrowd": 0, "image_id": 319396, "bbox": [123.69, 415.64, 163.95, 217.17], "category_id": 70, "id": 1095118, "split": "val", "sentences": [{"tokens": ["a", "white", "bidet", "sits", "next", "a", "toilet", "in", "a", "dark", "bathroom"], "raw": "A white bidet sits next a toilet in a dark bathroom.", "sent_id": 13743, "sent": "a white bidet sits next a toilet in a dark bathroom"}, {"tokens": ["the", "yellow", "toilet"], "raw": "the yellow toilet", "sent_id": 13744, "sent": "the yellow toilet"}], "file_name": "COCO_train2014_000000319396_1095118.jpg", "ann_id": 1095118, "sent_ids": [13743, 13744], "ref_id": 10324}, {"segmentation": [[393.29, 171.35, 399.48, 188.9, 386.06, 210.58, 360.26, 227.1, 340.65, 239.48, 317.94, 244.65, 300.39, 247.74, 304.52, 270.45, 311.74, 273.55, 341.68, 321.03, 360.26, 305.55, 373.68, 300.39, 408.77, 286.97, 421.16, 276.65, 434.58, 274.58, 448.0, 268.39, 403.61, 176.52, 394.32, 171.35]], "area": 9688.921199999999, "iscrowd": 0, "image_id": 532711, "bbox": [300.39, 171.35, 147.61, 149.68], "category_id": 62, "id": 100482, "split": "val", "sentences": [{"tokens": ["the", "chair", "behind", "the", "guy", "wearing", "the", "stripes"], "raw": "the chair behind the guy wearing the stripes.", "sent_id": 13764, "sent": "the chair behind the guy wearing the stripes"}, {"tokens": ["a", "brown", "chair", "to", "the", "top", "left", "of", "pizza"], "raw": "A brown chair to the top left of pizza.", "sent_id": 13765, "sent": "a brown chair to the top left of pizza"}], "file_name": "COCO_train2014_000000532711_100482.jpg", "ann_id": 100482, "sent_ids": [13764, 13765], "ref_id": 10331}, {"segmentation": [[203.91, 208.69, 200.08, 135.94, 205.82, 110.09, 206.78, 109.13, 261.34, 110.09, 263.26, 141.68, 241.24, 152.21, 216.35, 185.72, 213.48, 212.52], [320.7, 116.79, 316.87, 132.11, 310.17, 138.81, 306.34, 149.34, 336.97, 164.66, 341.76, 177.1, 345.59, 206.78, 346.54, 250.81, 352.29, 290.06, 354.2, 304.42, 359.95, 304.42, 361.86, 270.92, 366.65, 205.82, 370.48, 190.5, 374.31, 188.59, 378.13, 207.73, 377.18, 230.71, 383.88, 266.13, 386.75, 224.01, 382.92, 104.35, 355.16, 101.47, 341.76, 105.3, 347.5, 117.75, 319.74, 112.0]], "area": 10954.59045, "iscrowd": 0, "image_id": 452229, "bbox": [200.08, 101.47, 186.67, 202.95], "category_id": 62, "id": 381382, "split": "val", "sentences": [{"tokens": ["the", "chair", "the", "blonde", "woman", "in", "black", "is", "on"], "raw": "The chair the blonde woman in black is on", "sent_id": 13772, "sent": "the chair the blonde woman in black is on"}, {"tokens": ["white", "fence", "used", "as", "room", "divider"], "raw": "White fence used as room divider.", "sent_id": 13773, "sent": "white fence used as room divider"}], "file_name": "COCO_train2014_000000452229_381382.jpg", "ann_id": 381382, "sent_ids": [13772, 13773], "ref_id": 10334}, {"segmentation": [[322.16, 439.46, 309.19, 444.86, 291.89, 436.22, 280.0, 410.27, 280.0, 396.22, 292.97, 278.38, 308.11, 145.41, 307.03, 133.51, 328.65, 121.62, 322.16, 78.38, 324.32, 57.84, 341.62, 44.86, 387.03, 63.24, 395.68, 107.57, 396.76, 127.03, 428.11, 137.84, 434.59, 159.46, 440.0, 199.46, 441.08, 231.89, 442.16, 251.35, 431.35, 280.54, 419.46, 334.59, 412.97, 349.73, 407.57, 399.46, 384.86, 438.38, 388.11, 458.92, 381.62, 472.97, 326.49, 472.97, 322.16, 448.11]], "area": 47835.9264, "iscrowd": 0, "image_id": 106652, "bbox": [280.0, 44.86, 162.16, 428.11], "category_id": 1, "id": 258615, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "brown", "dress", "with", "a", "floral", "scarf", "standing", "next", "to", "a", "man"], "raw": "A woman in a brown dress with a floral scarf standing next to a man", "sent_id": 13867, "sent": "a woman in a brown dress with a floral scarf standing next to a man"}, {"tokens": ["woman", "in", "black", "dress", "with", "scarf"], "raw": "Woman in black dress with scarf", "sent_id": 13868, "sent": "woman in black dress with scarf"}], "file_name": "COCO_train2014_000000106652_258615.jpg", "ann_id": 258615, "sent_ids": [13867, 13868], "ref_id": 10370}, {"segmentation": [[592.43, 64.32, 592.43, 64.32, 593.51, 154.05, 584.86, 218.92, 584.86, 220.0, 579.46, 385.95, 579.46, 385.95, 577.3, 464.86, 589.19, 480.0, 640.0, 480.0, 640.0, 477.84, 636.76, 97.3, 637.84, 0.0, 637.84, 0.0, 617.3, 0.0, 617.3, 0.0, 592.43, 61.62, 592.43, 61.62]], "area": 24310.447950000005, "iscrowd": 0, "image_id": 1994, "bbox": [577.3, 0.0, 62.7, 480.0], "category_id": 1, "id": 494681, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "plaid", "shirt"], "raw": "the back of a plaid shirt", "sent_id": 13886, "sent": "the back of a plaid shirt"}, {"tokens": ["the", "back", "side", "of", "a", "white", "and", "blue", "striped", "shirt"], "raw": "The back side of a white and blue striped shirt", "sent_id": 13887, "sent": "the back side of a white and blue striped shirt"}], "file_name": "COCO_train2014_000000001994_494681.jpg", "ann_id": 494681, "sent_ids": [13886, 13887], "ref_id": 10380}, {"segmentation": [[307.72, 267.95, 332.12, 233.51, 401.0, 244.99, 389.52, 300.95], [289.07, 156.02, 390.95, 161.76, 390.95, 197.63, 314.9, 184.72, 280.46, 181.85], [241.72, 144.54, 241.72, 141.67, 393.82, 145.97, 398.13, 90.01, 385.21, 75.66, 366.56, 69.92, 336.42, 68.48, 297.68, 71.35, 276.16, 71.35, 257.5, 77.09, 240.28, 87.14, 233.11, 100.05, 218.76, 131.62]], "area": 18677.497199999998, "iscrowd": 0, "image_id": 15190, "bbox": [218.76, 68.48, 182.24, 232.47], "category_id": 22, "id": 583880, "split": "val", "sentences": [{"tokens": ["trunk", "up", "elephant"], "raw": "trunk up elephant", "sent_id": 13913, "sent": "trunk up elephant"}, {"tokens": ["a", "pair", "of", "elephants", "interacting"], "raw": "A pair of elephants interacting.", "sent_id": 13914, "sent": "a pair of elephants interacting"}], "file_name": "COCO_train2014_000000015190_583880.jpg", "ann_id": 583880, "sent_ids": [13913, 13914], "ref_id": 10391}, {"segmentation": [[263.06, 385.25, 236.88, 331.64, 210.7, 255.58, 204.47, 165.82, 230.65, 83.53, 245.61, 44.88, 297.97, 21.19, 321.66, 22.44, 342.86, 36.16, 357.82, 48.62, 377.77, 69.82, 395.22, 96.0, 405.19, 110.96, 417.66, 128.42, 433.87, 148.36, 445.09, 153.35, 453.82, 155.84, 471.27, 155.84, 482.49, 148.36, 484.99, 160.83, 478.75, 172.05, 488.73, 187.01, 491.22, 192.0, 480.0, 198.23, 458.81, 204.47, 448.83, 218.18, 437.61, 263.06, 431.38, 290.49, 423.9, 324.16, 412.68, 365.3, 393.97, 393.97, 382.75, 405.19, 371.53, 411.43, 341.61, 421.4, 324.16, 425.14, 309.19, 423.9, 301.71, 418.91, 292.99, 413.92]], "area": 74447.86489999999, "iscrowd": 0, "image_id": 444036, "bbox": [204.47, 21.19, 286.75, 403.95], "category_id": 51, "id": 1902562, "split": "val", "sentences": [{"tokens": ["a", "brown", "dish", "of", "food"], "raw": "A brown dish of food.", "sent_id": 13941, "sent": "a brown dish of food"}, {"tokens": ["a", "brown", "plate", "on", "white", "place", "mat", "with", "two", "pieces", "of", "toast", "framing", "a", "cheese", "dish"], "raw": "A brown plate on white place mat with two pieces of toast framing a cheese dish", "sent_id": 13942, "sent": "a brown plate on white place mat with two pieces of toast framing a cheese dish"}], "file_name": "COCO_train2014_000000444036_1902562.jpg", "ann_id": 1902562, "sent_ids": [13941, 13942], "ref_id": 10401}, {"segmentation": [[326.24, 134.72, 326.24, 134.72, 293.75, 157.79, 271.63, 167.21, 271.63, 167.21, 272.57, 170.03, 271.16, 171.91, 280.1, 178.98, 292.34, 186.51, 302.23, 194.04, 305.99, 194.04, 312.11, 186.51, 318.23, 179.92, 332.83, 169.56, 342.71, 170.03, 350.72, 169.09, 350.72, 169.09, 336.59, 152.14, 336.59, 152.14], [274.02, 89.38, 274.02, 89.38, 288.53, 79.25, 301.7, 73.18, 305.75, 70.47, 310.81, 70.47, 317.9, 72.84, 320.6, 73.85, 318.57, 76.21, 276.72, 92.41, 276.72, 92.41]], "area": 2451.923749999999, "iscrowd": 0, "image_id": 263744, "bbox": [271.16, 70.47, 79.56, 123.57], "category_id": 53, "id": 1549239, "split": "val", "sentences": [{"tokens": ["an", "apple", "between", "two", "oranges"], "raw": "An apple between two oranges", "sent_id": 13996, "sent": "an apple between two oranges"}], "file_name": "COCO_train2014_000000263744_1549239.jpg", "ann_id": 1549239, "sent_ids": [13996], "ref_id": 10423}, {"segmentation": [[303.02, 570.98, 295.73, 557.61, 292.08, 551.54, 284.79, 541.82, 279.93, 527.24, 275.07, 507.8, 272.64, 490.79, 272.64, 472.56, 275.07, 459.2, 275.07, 442.18, 278.72, 436.11, 278.72, 436.11, 286.01, 410.59, 292.08, 396.01, 305.45, 382.65, 328.54, 366.85, 343.12, 361.99, 352.84, 359.56, 372.28, 363.21, 390.5, 372.93, 405.08, 391.15, 413.59, 409.38, 420.88, 428.82, 422.1, 443.4, 422.1, 460.41, 422.1, 488.36, 422.1, 505.37, 416.02, 539.39, 408.73, 553.97, 399.01, 566.12, 382.0, 572.2, 373.49, 585.56, 356.48, 590.42, 329.75, 586.78, 317.6, 580.7, 315.17, 578.27, 309.09, 572.2, 307.88, 570.98]], "area": 27618.967, "iscrowd": 0, "image_id": 47545, "bbox": [272.64, 359.56, 149.46, 230.86], "category_id": 85, "id": 339253, "split": "val", "sentences": [{"tokens": ["a", "clock", "face"], "raw": "A clock face.", "sent_id": 14089, "sent": "a clock face"}, {"tokens": ["a", "clock", "on", "the", "side", "of", "a", "building"], "raw": "A clock on the side of a building.", "sent_id": 14090, "sent": "a clock on the side of a building"}], "file_name": "COCO_train2014_000000047545_339253.jpg", "ann_id": 339253, "sent_ids": [14089, 14090], "ref_id": 10459}, {"segmentation": [[272.11, 300.45, 284.0, 314.85, 304.66, 348.65, 315.93, 387.46, 315.93, 396.23, 263.97, 421.89, 257.71, 431.91, 242.06, 439.42, 240.18, 443.8, 225.15, 446.31, 222.65, 452.57, 221.4, 466.34, 218.22, 486.92, 175.52, 493.56, 170.78, 489.77, 165.08, 430.94, 165.08, 427.14, 171.72, 432.83, 174.57, 435.68, 175.52, 428.09, 175.52, 419.55, 175.52, 412.91, 175.52, 395.83, 216.32, 329.41, 253.33, 302.84, 266.61, 296.2]], "area": 16090.071450000001, "iscrowd": 0, "image_id": 565608, "bbox": [165.08, 296.2, 150.85, 197.36], "category_id": 31, "id": 1173924, "split": "val", "sentences": [{"tokens": ["the", "tan", "colored", "leather", "bag"], "raw": "The tan colored leather bag.", "sent_id": 14120, "sent": "the tan colored leather bag"}, {"tokens": ["a", "tan", "bag"], "raw": "A tan bag.", "sent_id": 14121, "sent": "a tan bag"}], "file_name": "COCO_train2014_000000565608_1173924.jpg", "ann_id": 1173924, "sent_ids": [14120, 14121], "ref_id": 10472}, {"segmentation": [[173.27, 141.92, 187.63, 143.83, 207.73, 149.58, 196.25, 153.41, 179.97, 174.47, 165.61, 168.72, 156.04, 171.6, 171.36, 193.61, 176.14, 219.46, 175.19, 267.33, 179.02, 286.47, 154.13, 267.33, 144.55, 252.01, 123.49, 267.33, 100.52, 334.34, 97.64, 319.98, 103.39, 259.67, 117.75, 215.63, 133.07, 189.79, 156.04, 167.77, 144.55, 166.81, 162.74, 152.45], [220.18, 295.09, 216.35, 294.13, 220.18, 279.77, 224.97, 269.24, 232.62, 283.6, 232.62, 296.05]], "area": 7040.998049999999, "iscrowd": 0, "image_id": 62263, "bbox": [97.64, 141.92, 134.98, 192.42], "category_id": 24, "id": 591933, "split": "val", "sentences": [{"tokens": ["baby", "zebra", "in", "back", "of", "the", "other", "two", "baby", "zebras"], "raw": "Baby zebra in back of the other two baby zebras.", "sent_id": 14321, "sent": "baby zebra in back of the other two baby zebras"}], "file_name": "COCO_train2014_000000062263_591933.jpg", "ann_id": 591933, "sent_ids": [14321], "ref_id": 10551}, {"segmentation": [[209.9, 638.39, 204.68, 586.26, 210.94, 566.45, 241.17, 539.34, 228.66, 503.9, 238.05, 449.68, 262.02, 442.38, 292.26, 442.38, 322.49, 466.36, 314.15, 482.0, 313.11, 486.17, 320.41, 507.02, 318.32, 507.02, 315.2, 534.13, 303.73, 537.26, 322.49, 563.32, 344.39, 601.9, 371.49, 638.39]], "area": 20048.395799999995, "iscrowd": 0, "image_id": 565070, "bbox": [204.68, 442.38, 166.81, 196.01], "category_id": 1, "id": 1743810, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "white", "shirt", "talking", "on", "a", "phone"], "raw": "A woman in a white shirt talking on a phone", "sent_id": 14370, "sent": "a woman in a white shirt talking on a phone"}, {"tokens": ["woman", "talking", "on", "phone"], "raw": "woman talking on phone", "sent_id": 14371, "sent": "woman talking on phone"}], "file_name": "COCO_train2014_000000565070_1743810.jpg", "ann_id": 1743810, "sent_ids": [14370, 14371], "ref_id": 10566}, {"segmentation": [[401.74, 404.83, 409.98, 362.6, 420.28, 343.03, 409.98, 306.97, 416.16, 288.43, 442.95, 279.16, 495.48, 283.28, 535.66, 291.52, 561.41, 328.6, 602.61, 362.6, 604.67, 404.83, 591.28, 401.74, 561.41, 371.87, 548.02, 361.57, 534.63, 366.72, 550.08, 411.01, 535.66, 406.89, 521.23, 361.57, 517.11, 360.54, 510.93, 381.14, 506.81, 402.77, 509.9, 413.07, 504.75, 414.1, 498.57, 395.56, 506.81, 373.93, 503.72, 356.42, 498.57, 354.36, 463.55, 358.48, 458.4, 358.48, 449.13, 348.18, 441.92, 367.75, 440.89, 382.17, 461.49, 413.07, 448.1, 413.07, 428.52, 380.11, 426.46, 358.48, 420.28, 375.99, 409.98, 402.77, 419.25, 408.95, 415.13, 414.1, 406.89, 414.1]], "area": 14673.890050000002, "iscrowd": 0, "image_id": 38552, "bbox": [401.74, 279.16, 202.93, 134.94], "category_id": 20, "id": 66360, "split": "val", "sentences": [{"tokens": ["lamb", "in", "a", "meadow", "grazing", "next", "to", "two", "other", "lambs"], "raw": "Lamb in a meadow grazing next to two other lambs.", "sent_id": 14376, "sent": "lamb in a meadow grazing next to two other lambs"}, {"tokens": ["a", "sheep", "eating", "grass"], "raw": "A sheep eating grass", "sent_id": 14377, "sent": "a sheep eating grass"}], "file_name": "COCO_train2014_000000038552_66360.jpg", "ann_id": 66360, "sent_ids": [14376, 14377], "ref_id": 10569}, {"segmentation": [[328.55, 19.36, 335.33, 109.97, 495.36, 93.03, 497.05, 134.52, 505.52, 141.3, 507.21, 146.38, 519.07, 145.53, 515.68, 153.15, 513.14, 165.0, 513.14, 165.85, 552.09, 165.85, 566.49, 155.69, 569.03, 154.0, 570.72, 141.3, 568.18, 123.51, 576.65, 104.04, 579.19, 90.49, 579.19, 82.87, 640.0, 74.4, 640.0, 0.0, 328.55, 0.0, 330.24, 26.99]], "area": 34163.28805, "iscrowd": 0, "image_id": 333842, "bbox": [328.55, 0.0, 311.45, 165.85], "category_id": 72, "id": 124379, "split": "val", "sentences": [{"tokens": ["a", "samsung", "display", "on", "small", "table", "with", "many", "toys", "and", "next", "to", "another", "display", "of", "other", "brand", "with", "beautiful", "keyboard", "and", "mouse"], "raw": "A Samsung Display  on small table with many toys and next to another display of other brand with beautiful keyboard and mouse.", "sent_id": 14459, "sent": "a samsung display on small table with many toys and next to another display of other brand with beautiful keyboard and mouse"}], "file_name": "COCO_train2014_000000333842_124379.jpg", "ann_id": 124379, "sent_ids": [14459], "ref_id": 10596}, {"segmentation": [[261.03, 346.25, 214.65, 372.13, 159.64, 371.06, 93.84, 347.33, 34.52, 305.26, 14.02, 228.67, 36.67, 160.72, 100.31, 107.87, 170.43, 79.82, 253.48, 91.69, 299.87, 141.3, 317.12, 182.29, 318.2, 237.3, 308.49, 261.03, 296.63, 318.2]], "area": 68165.25699999998, "iscrowd": 0, "image_id": 281464, "bbox": [14.02, 79.82, 304.18, 292.31], "category_id": 51, "id": 1038931, "split": "val", "sentences": [{"tokens": ["the", "bowl", "with", "the", "white", "stuff", "in", "it"], "raw": "the bowl with the white stuff in it", "sent_id": 14498, "sent": "the bowl with the white stuff in it"}, {"tokens": ["the", "vanilla", "dessert", "with", "a", "cashew", "nose"], "raw": "the vanilla dessert with a cashew nose", "sent_id": 14499, "sent": "the vanilla dessert with a cashew nose"}], "file_name": "COCO_train2014_000000281464_1038931.jpg", "ann_id": 1038931, "sent_ids": [14498, 14499], "ref_id": 10610}, {"segmentation": [[215.31, 382.24, 217.27, 359.09, 227.87, 343.39, 246.71, 320.62, 277.71, 318.66, 265.55, 289.62, 283.99, 316.7, 350.72, 313.56, 384.86, 320.23, 420.18, 341.03, 453.55, 350.06, 461.4, 364.19, 460.22, 382.64, 453.55, 386.17, 447.27, 401.09, 426.86, 399.91, 417.05, 386.56, 333.05, 394.81, 330.7, 414.43, 308.72, 419.92, 291.84, 407.36, 262.41, 402.26, 257.3, 416.39, 249.85, 416.39, 238.86, 414.82, 226.69, 401.87]], "area": 18169.623250000004, "iscrowd": 0, "image_id": 381759, "bbox": [215.31, 289.62, 246.09, 130.3], "category_id": 3, "id": 353582, "split": "val", "sentences": [{"tokens": ["a", "grey", "volkeswagon"], "raw": "A grey VolkesWagon", "sent_id": 14523, "sent": "a grey volkeswagon"}, {"tokens": ["the", "car"], "raw": "The car.", "sent_id": 14524, "sent": "the car"}], "file_name": "COCO_train2014_000000381759_353582.jpg", "ann_id": 353582, "sent_ids": [14523, 14524], "ref_id": 10620}, {"segmentation": [[484.3, 235.26, 510.13, 251.41, 549.96, 265.4, 566.1, 289.08, 581.17, 289.08, 600.54, 276.16, 574.71, 234.19, 587.62, 191.14, 583.32, 161.0, 599.46, 142.71, 584.39, 125.49, 539.19, 121.18, 514.44, 114.73, 492.91, 126.57, 497.22, 143.78, 492.91, 151.32, 469.24, 147.01, 432.65, 138.4, 407.89, 147.01, 383.14, 154.55, 358.39, 157.78, 353.0, 163.16, 368.07, 179.3, 376.68, 180.38, 398.21, 190.06, 420.81, 190.06, 430.49, 204.05, 443.41, 208.36, 458.48, 223.43, 462.78, 229.88, 482.15, 237.42]], "area": 21063.518799999998, "iscrowd": 0, "image_id": 5862, "bbox": [353.0, 114.73, 247.54, 174.35], "category_id": 18, "id": 17126, "split": "val", "sentences": [{"tokens": ["a", "dog", "with", "brown", "fur", ",", "with", "its", "head", "up", ",", "laying", "on", "a", "gray", "sheet"], "raw": "A dog with brown fur, with its head up, laying on a gray sheet.", "sent_id": 14577, "sent": "a dog with brown fur , with its head up , laying on a gray sheet"}, {"tokens": ["brown", "dog"], "raw": "Brown dog.", "sent_id": 14578, "sent": "brown dog"}], "file_name": "COCO_train2014_000000005862_17126.jpg", "ann_id": 17126, "sent_ids": [14577, 14578], "ref_id": 10644}, {"segmentation": [[132.38, 92.5, 350.85, 93.58, 421.88, 131.25, 369.15, 183.98, 348.7, 205.51, 321.79, 292.68, 134.53, 173.22]], "area": 34593.3004, "iscrowd": 0, "image_id": 152237, "bbox": [132.38, 92.5, 289.5, 200.18], "category_id": 65, "id": 317537, "split": "val", "sentences": [{"tokens": ["the", "top", "bunk"], "raw": "the top bunk", "sent_id": 14722, "sent": "the top bunk"}, {"tokens": ["the", "bunk", "bed", "on", "top", "with", "purple", "unicorn", "not", "including", "the", "girl"], "raw": "The bunk bed on top with purple unicorn not including the girl.", "sent_id": 14723, "sent": "the bunk bed on top with purple unicorn not including the girl"}], "file_name": "COCO_train2014_000000152237_317537.jpg", "ann_id": 317537, "sent_ids": [14722, 14723], "ref_id": 10693}, {"segmentation": [[225.09, 417.18, 231.71, 400.63, 227.29, 391.8, 185.36, 391.8, 196.4, 418.28, 129.09, 419.38, 131.3, 409.45, 110.34, 367.53, 108.13, 345.46, 115.85, 328.91, 108.13, 301.32, 98.2, 279.26, 99.3, 261.6, 103.72, 252.78, 108.13, 186.57, 120.27, 158.99, 135.71, 145.75, 153.37, 140.23, 157.78, 157.89, 147.85, 175.54, 176.54, 163.4, 187.57, 167.82, 196.4, 179.95, 195.29, 190.99, 172.12, 206.43, 165.5, 228.5, 166.61, 253.88, 165.5, 285.88, 168.81, 303.53, 183.16, 301.32, 188.67, 289.19, 187.57, 275.95, 196.4, 252.78, 218.47, 252.78, 219.57, 261.6, 225.09, 257.19, 246.05, 266.02, 244.95, 258.29, 223.98, 241.74, 214.05, 224.09, 204.12, 207.54, 207.43, 188.78, 217.36, 179.95, 231.71, 172.23, 250.46, 172.23, 252.67, 165.61, 246.05, 153.47, 232.81, 152.37, 220.67, 158.99, 199.71, 165.61, 186.47, 142.44, 194.19, 124.79, 204.12, 120.37, 195.29, 101.62, 189.78, 90.58, 187.57, 81.76, 174.33, 91.69, 172.12, 90.58, 178.74, 75.14, 177.64, 59.69, 190.88, 45.34, 226.19, 42.03, 249.36, 56.38, 263.7, 75.14, 269.22, 92.79, 272.53, 113.75, 262.6, 130.3, 275.84, 145.75, 294.6, 164.51, 310.04, 198.71, 322.18, 234.02, 331.01, 257.19, 319.97, 277.05, 297.91, 289.19, 300.11, 320.08, 304.53, 341.04, 308.94, 362.01, 305.63, 399.52, 294.6, 418.28]], "area": 54031.55375000001, "iscrowd": 0, "image_id": 418500, "bbox": [98.2, 42.03, 232.81, 377.35], "category_id": 1, "id": 2154264, "split": "val", "sentences": [{"tokens": ["a", "statue", "on", "a", "bench", "is", "being", "sat", "next", "to", "by", "a", "man", "in", "shorts"], "raw": "A statue on a bench is being sat next to by a man in shorts.", "sent_id": 14725, "sent": "a statue on a bench is being sat next to by a man in shorts"}, {"tokens": ["a", "statue", "of", "a", "man", "holding", "a", "dog"], "raw": "A statue of a man holding a dog.", "sent_id": 14726, "sent": "a statue of a man holding a dog"}], "file_name": "COCO_train2014_000000418500_2154264.jpg", "ann_id": 2154264, "sent_ids": [14725, 14726], "ref_id": 10694}, {"segmentation": [[81.76, 175.24, 103.09, 168.03, 123.79, 159.87, 149.82, 153.92, 176.79, 157.37, 202.5, 168.66, 238.57, 178.69, 260.21, 186.84, 273.38, 206.29, 277.46, 226.36, 279.34, 245.18, 281.22, 252.39, 283.1, 267.44, 276.52, 281.24, 265.85, 286.57, 254.25, 288.14, 245.15, 280.3, 241.7, 271.83, 231.67, 260.86, 224.46, 254.9, 213.48, 249.88, 210.03, 269.64, 204.39, 287.83, 198.11, 302.57, 196.54, 313.54, 190.59, 328.91, 197.49, 337.69, 200.31, 342.71, 172.71, 344.59, 169.57, 329.54, 171.46, 307.9, 171.77, 293.79, 172.4, 278.73, 167.38, 269.95, 154.52, 272.15, 141.66, 272.46, 130.06, 279.99, 115.95, 265.87, 99.64, 242.04, 85.84, 202.84, 81.76, 178.06]], "area": 20924.25545, "iscrowd": 0, "image_id": 356535, "bbox": [81.76, 153.92, 201.34, 190.67], "category_id": 22, "id": 581409, "split": "val", "sentences": [{"tokens": ["a", "small", "elephant"], "raw": "A small elephant", "sent_id": 14734, "sent": "a small elephant"}, {"tokens": ["a", "young", "elephant", "in", "an", "exhibit"], "raw": "A young elephant in an exhibit.", "sent_id": 14735, "sent": "a young elephant in an exhibit"}], "file_name": "COCO_train2014_000000356535_581409.jpg", "ann_id": 581409, "sent_ids": [14734, 14735], "ref_id": 10698}, {"segmentation": [[85.81, 207.44, 94.16, 191.57, 96.67, 184.89, 98.76, 176.95, 99.18, 170.27, 100.85, 162.34, 97.5, 152.31, 97.92, 138.53, 100.01, 134.77, 101.26, 128.5, 107.53, 120.99, 114.21, 122.66, 119.22, 129.34, 125.91, 138.11, 127.99, 143.12, 133.01, 152.73, 138.85, 156.49, 146.79, 164.01, 148.88, 171.52, 149.3, 181.55, 149.3, 188.65, 155.98, 223.65, 152.64, 233.25, 148.04, 241.61, 144.7, 251.63, 145.54, 259.15, 154.31, 287.09, 153.47, 295.44, 157.23, 320.46, 156.81, 326.31, 153.89, 330.9, 149.71, 335.08, 143.03, 332.99, 128.41, 332.99, 122.56, 332.15, 117.13, 327.56, 115.05, 320.04, 117.55, 310.85, 117.13, 301.25, 117.13, 291.22, 112.96, 279.94, 109.2, 273.68, 105.86, 267.0, 100.85, 254.47, 100.43, 250.29, 102.1, 245.7, 102.93, 232.75, 101.26, 228.15, 98.34, 222.72, 93.33, 214.37, 90.82, 211.45, 89.15, 207.27]], "area": 9156.382300000001, "iscrowd": 0, "image_id": 103556, "bbox": [85.81, 120.99, 71.42, 214.09], "category_id": 1, "id": 442299, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "tee", "shirt", "and", "black", "shorts"], "raw": "A man in a white tee shirt and black shorts.", "sent_id": 14798, "sent": "a man in a white tee shirt and black shorts"}, {"tokens": ["a", "man", "in", "white", "in", "the", "background"], "raw": "a man in white in the background", "sent_id": 14799, "sent": "a man in white in the background"}], "file_name": "COCO_train2014_000000103556_442299.jpg", "ann_id": 442299, "sent_ids": [14798, 14799], "ref_id": 10721}, {"segmentation": [[604.14, 486.07, 579.66, 461.59, 555.18, 409.37, 555.18, 365.3, 543.75, 355.51, 548.65, 334.29, 538.86, 298.39, 540.49, 285.33, 551.91, 272.28, 560.07, 269.01, 578.03, 269.01, 576.39, 254.33, 566.6, 246.17, 576.39, 223.32, 556.81, 203.73, 556.81, 167.83, 582.92, 144.98, 610.67, 143.35, 610.67, 314.71, 610.67, 495.86, 604.14, 487.7]], "area": 16975.491199999993, "iscrowd": 0, "image_id": 578369, "bbox": [538.86, 143.35, 71.81, 352.51], "category_id": 1, "id": 454925, "split": "val", "sentences": [{"tokens": ["diner", "by", "himself", "on", "the", "right", "side", "of", "the", "table"], "raw": "Diner by himself on the right side of the table", "sent_id": 14809, "sent": "diner by himself on the right side of the table"}, {"tokens": ["the", "person", "partially", "visible", "on", "the", "right", "side"], "raw": "The person partially visible on the right side", "sent_id": 14810, "sent": "the person partially visible on the right side"}], "file_name": "COCO_train2014_000000578369_454925.jpg", "ann_id": 454925, "sent_ids": [14809, 14810], "ref_id": 10727}, {"segmentation": [[155.27, 311.63, 115.46, 319.59, 79.63, 351.44, 52.75, 341.49, 34.84, 327.56, 5.97, 336.51, 0.0, 341.49, 1.99, 215.08, 27.87, 227.03, 44.79, 232.0, 73.65, 224.04, 113.47, 234.99, 131.38, 240.96, 146.31, 263.85, 154.27, 290.73, 158.26, 307.65]], "area": 15116.198299999996, "iscrowd": 0, "image_id": 477580, "bbox": [0.0, 215.08, 158.26, 136.36], "category_id": 56, "id": 1056554, "split": "val", "sentences": [{"tokens": ["a", "group", "of", "broccoli"], "raw": "A group of broccoli", "sent_id": 14811, "sent": "a group of broccoli"}, {"tokens": ["a", "head", "of", "broccoli", "sits", "on", "the", "table"], "raw": "A head of broccoli sits on the table.", "sent_id": 14812, "sent": "a head of broccoli sits on the table"}], "file_name": "COCO_train2014_000000477580_1056554.jpg", "ann_id": 1056554, "sent_ids": [14811, 14812], "ref_id": 10728}, {"segmentation": [[395.26, 133.49, 481.97, 161.97, 481.97, 161.97, 583.25, 184.13, 622.49, 203.12, 618.7, 224.0, 606.04, 256.29, 585.78, 260.72, 585.15, 260.72, 584.52, 260.72, 519.95, 240.46, 418.68, 204.38, 335.12, 172.1, 313.6, 154.38, 313.6, 144.88, 337.65, 139.82, 338.29, 138.55, 354.11, 130.96]], "area": 18343.27945, "iscrowd": 0, "image_id": 426838, "bbox": [313.6, 130.96, 308.89, 129.76], "category_id": 57, "id": 1064725, "split": "val", "sentences": [{"tokens": ["carrot", "touching", "potatoes"], "raw": "carrot touching potatoes.", "sent_id": 14827, "sent": "carrot touching potatoes"}, {"tokens": ["the", "carrot", "which", "is", "very", "next", "to", "potatoe"], "raw": "The carrot which is very next to potatoe", "sent_id": 14828, "sent": "the carrot which is very next to potatoe"}], "file_name": "COCO_train2014_000000426838_1064725.jpg", "ann_id": 1064725, "sent_ids": [14827, 14828], "ref_id": 10734}, {"segmentation": [[119.55, 159.04, 83.26, 156.91, 49.1, 135.56, 25.62, 96.07, 36.29, 54.44, 75.79, 14.94, 106.74, 5.34, 141.97, 11.74, 170.79, 25.62, 192.13, 52.3, 190.0, 93.93, 176.12, 135.56, 131.29, 156.91]], "area": 19448.686599999997, "iscrowd": 0, "image_id": 572602, "bbox": [25.62, 5.34, 166.51, 153.7], "category_id": 51, "id": 1040096, "split": "val", "sentences": [{"tokens": ["a", "small", "cup", "of", "yogurt"], "raw": "A small cup of yogurt.", "sent_id": 14838, "sent": "a small cup of yogurt"}, {"tokens": ["yogurt", "in", "a", "small", "bolw", "in", "back", "left", "corner"], "raw": "yogurt in a small bolw in back left corner", "sent_id": 14839, "sent": "yogurt in a small bolw in back left corner"}], "file_name": "COCO_train2014_000000572602_1040096.jpg", "ann_id": 1040096, "sent_ids": [14838, 14839], "ref_id": 10738}, {"segmentation": [[244.69, 417.4, 181.36, 420.28, 152.57, 417.4, 123.78, 417.4, 105.55, 415.49, 99.79, 377.1, 107.47, 343.52, 116.11, 307.06, 138.18, 291.7, 162.16, 284.99, 213.02, 274.43, 241.81, 278.27, 255.24, 269.63, 255.24, 249.48, 254.28, 225.49, 251.4, 181.36, 267.71, 154.49, 302.26, 128.58, 343.52, 125.7, 355.99, 135.3, 360.79, 155.45, 362.71, 177.52, 367.51, 209.18, 380.94, 228.37, 393.42, 239.89, 394.38, 264.84, 391.5, 276.35, 362.71, 288.82, 336.8, 306.1, 320.49, 331.04, 307.06, 354.07, 283.07, 378.06, 268.67, 402.05, 260.04, 419.32, 247.56, 418.36], [521.04, 229.33, 533.51, 212.06, 553.66, 206.3, 578.61, 214.94, 603.56, 229.33, 614.11, 246.6, 617.95, 260.04, 608.36, 272.51, 587.24, 277.31, 569.01, 276.35, 547.9, 275.39, 548.86, 265.8, 543.11, 259.08, 534.47, 249.48, 526.79, 234.13]], "area": 49183.988499999985, "iscrowd": 0, "image_id": 511967, "bbox": [99.79, 125.7, 518.16, 294.58], "category_id": 1, "id": 452254, "split": "val", "sentences": [{"tokens": ["a", "man", "helping", "another", "man", "put", "on", "a", "tie", ","], "raw": "A man helping another man put on a tie,", "sent_id": 14868, "sent": "a man helping another man put on a tie ,"}, {"tokens": ["two", "men", "adjusting", "tie", "shoter", "one", "helping", "taller", "one"], "raw": "TWO MEN ADJUSTING TIE SHOTER ONE HELPING TALLER ONE.", "sent_id": 14869, "sent": "two men adjusting tie shoter one helping taller one"}], "file_name": "COCO_train2014_000000511967_452254.jpg", "ann_id": 452254, "sent_ids": [14868, 14869], "ref_id": 10752}, {"segmentation": [[76.95, 397.6, 92.53, 364.62, 118.18, 344.46, 103.52, 327.06, 95.28, 277.59, 76.04, 240.03, 76.04, 233.61, 82.45, 228.12, 120.01, 233.61, 136.5, 240.03, 158.49, 296.83, 173.15, 294.08, 204.3, 298.66, 218.04, 307.82, 225.37, 310.57, 229.03, 318.81, 215.29, 327.06, 196.97, 349.05, 207.05, 360.04, 218.04, 366.45, 219.87, 378.36, 217.12, 376.53, 206.13, 364.62, 171.32, 380.19, 139.25, 417.75, 131.92, 403.1, 95.28, 381.11, 83.37, 397.6]], "area": 14071.058149999997, "iscrowd": 0, "image_id": 200010, "bbox": [76.04, 228.12, 152.99, 189.63], "category_id": 62, "id": 102284, "split": "val", "sentences": [{"tokens": ["chair", "with", "the", "white", "cushion", "on", "the", "left"], "raw": "Chair with the white cushion on the left", "sent_id": 14889, "sent": "chair with the white cushion on the left"}, {"tokens": ["the", "chair", "with", "the", "white", "cusion", "on", "the", "back", "nearest", "the", "brick", "wall", "and", "plants"], "raw": "The chair with the white cusion on the back nearest the brick wall and plants", "sent_id": 14890, "sent": "the chair with the white cusion on the back nearest the brick wall and plants"}], "file_name": "COCO_train2014_000000200010_102284.jpg", "ann_id": 102284, "sent_ids": [14889, 14890], "ref_id": 10758}, {"segmentation": [[503.45, 100.56, 511.01, 5.31, 513.27, 0.78, 620.61, 9.85, 605.5, 141.38, 595.67, 152.72, 555.6, 117.19, 529.9, 104.34]], "area": 12574.571600000003, "iscrowd": 0, "image_id": 70380, "bbox": [503.45, 0.78, 117.16, 151.94], "category_id": 47, "id": 2215661, "split": "val", "sentences": [{"tokens": ["an", "empty", "glass", "on", "the", "table", "on", "the", "right", "side", "behind", "a", "white", "frosted", "cake"], "raw": "An empty glass on the table on the right side  behind a white frosted cake", "sent_id": 14893, "sent": "an empty glass on the table on the right side behind a white frosted cake"}, {"tokens": ["a", "empty", "glass", "neat", "the", "cake", "on", "the", "table"], "raw": "A empty glass neat the cake on the table", "sent_id": 14894, "sent": "a empty glass neat the cake on the table"}], "file_name": "COCO_train2014_000000070380_2215661.jpg", "ann_id": 2215661, "sent_ids": [14893, 14894], "ref_id": 10760}, {"segmentation": [[56.22, 162.29, 74.01, 216.38, 81.12, 237.73, 80.41, 256.94, 308.85, 229.9, 306.71, 189.34, 229.14, 132.4, 202.1, 133.12, 209.22, 145.92, 190.0, 147.35, 180.04, 135.96, 161.54, 139.52, 165.81, 150.91, 140.19, 152.33, 135.92, 139.52, 113.86, 142.37, 118.13, 153.04, 91.09, 155.89, 88.95, 143.79, 46.25, 144.5, 56.93, 160.16]], "area": 22606.717950000002, "iscrowd": 0, "image_id": 4830, "bbox": [46.25, 132.4, 262.6, 124.54], "category_id": 81, "id": 1129162, "split": "val", "sentences": [{"tokens": ["sink", "on", "the", "left"], "raw": "Sink on the left", "sent_id": 14943, "sent": "sink on the left"}, {"tokens": ["the", "sink", "farthest", "left"], "raw": "The sink farthest left.", "sent_id": 14944, "sent": "the sink farthest left"}], "file_name": "COCO_train2014_000000004830_1129162.jpg", "ann_id": 1129162, "sent_ids": [14943, 14944], "ref_id": 10780}, {"segmentation": [[249.67, 323.5, 265.97, 301.43, 270.77, 283.21, 284.2, 273.61, 286.12, 266.9, 302.43, 251.55, 307.22, 258.26, 316.82, 264.02, 317.78, 268.82, 324.49, 271.69, 334.09, 278.41, 335.04, 282.25, 356.15, 287.04, 372.46, 291.84, 388.77, 289.92, 403.16, 292.8, 410.83, 293.76, 406.03, 304.31, 392.6, 311.98, 393.56, 322.54, 397.4, 329.25, 410.83, 331.17, 418.51, 341.72, 425.22, 348.44, 431.94, 357.07, 431.94, 367.63, 437.69, 371.46, 420.42, 377.22, 406.99, 376.26, 391.64, 385.85, 374.38, 382.01, 366.7, 386.81, 341.76, 374.34, 339.84, 382.97, 330.25, 384.89, 316.82, 377.22, 312.98, 375.3, 321.61, 367.63, 320.66, 354.19, 311.06, 338.85, 298.59, 345.56, 273.65, 335.01, 269.81, 337.89, 255.42, 335.01, 253.5, 334.05, 252.54, 323.5]], "area": 13239.1125, "iscrowd": 0, "image_id": 416948, "bbox": [249.67, 251.55, 188.02, 135.26], "category_id": 21, "id": 72849, "split": "val", "sentences": [{"tokens": ["cow", "with", "bell", "around", "its", "neck", "looking", "to", "the", "left"], "raw": "Cow with bell around its neck looking to the left", "sent_id": 15013, "sent": "cow with bell around its neck looking to the left"}], "file_name": "COCO_train2014_000000416948_72849.jpg", "ann_id": 72849, "sent_ids": [15013], "ref_id": 10807}, {"segmentation": [[483.63, 61.14, 488.05, 114.94, 506.48, 135.57, 521.96, 151.05, 530.8, 170.95, 530.06, 210.01, 521.96, 276.34, 516.06, 301.4, 498.37, 303.61, 476.26, 305.08, 459.31, 313.19, 460.78, 326.46, 482.16, 325.72, 507.95, 333.83, 534.48, 341.19, 555.86, 346.35, 572.81, 347.83, 594.92, 335.3, 593.44, 331.61, 589.02, 327.93, 583.13, 324.98, 576.49, 321.3, 561.75, 315.4, 547.01, 310.24, 539.64, 306.56, 531.54, 297.71, 538.17, 245.39, 548.49, 170.95, 552.17, 162.11, 608.18, 120.1, 612.0, 101.67, 611.13, 49.35, 521.22, 33.87, 493.95, 33.87, 485.11, 50.82]], "area": 18547.520149999997, "iscrowd": 0, "image_id": 153814, "bbox": [459.31, 33.87, 152.69, 313.96], "category_id": 46, "id": 665092, "split": "val", "sentences": [{"tokens": ["glass", "of", "juice", "in", "table"], "raw": "glass of juice in table", "sent_id": 15024, "sent": "glass of juice in table"}], "file_name": "COCO_train2014_000000153814_665092.jpg", "ann_id": 665092, "sent_ids": [15024], "ref_id": 10811}, {"segmentation": [[320.53, 417.02, 312.76, 367.11, 312.76, 352.69, 324.96, 265.07, 349.36, 249.55, 343.82, 169.69, 281.71, 131.98, 277.27, 128.65, 303.89, 63.22, 267.29, 15.53, 227.36, 26.62, 211.84, 41.04, 202.96, 57.67, 198.53, 82.07, 214.05, 90.95, 217.38, 133.09, 206.29, 146.4, 176.35, 149.73, 146.4, 212.95, 147.51, 234.02, 170.8, 240.67, 137.53, 401.49, 136.42, 421.45]], "area": 57014.218149999986, "iscrowd": 0, "image_id": 376241, "bbox": [136.42, 15.53, 212.94, 405.92], "category_id": 1, "id": 2154823, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "green", "shirt", "brushing", "his", "teeth"], "raw": "A man in a green shirt brushing his teeth.", "sent_id": 15065, "sent": "a man in a green shirt brushing his teeth"}, {"tokens": ["a", "man", "in", "green", "shirt", "brushing", "his", "teeth"], "raw": "A man in green shirt brushing his teeth", "sent_id": 15066, "sent": "a man in green shirt brushing his teeth"}], "file_name": "COCO_train2014_000000376241_2154823.jpg", "ann_id": 2154823, "sent_ids": [15065, 15066], "ref_id": 10828}, {"segmentation": [[382.81, 356.1, 445.67, 361.34, 538.01, 365.92, 540.63, 361.34, 536.7, 241.5, 532.11, 184.53, 522.29, 119.05, 386.08, 134.11, 383.46, 191.08, 378.88, 265.08]], "area": 35935.09835, "iscrowd": 0, "image_id": 125658, "bbox": [378.88, 119.05, 161.75, 246.87], "category_id": 6, "id": 164609, "split": "val", "sentences": [{"tokens": ["the", "bus", "to", "the", "right"], "raw": "The bus to the right.", "sent_id": 15102, "sent": "the bus to the right"}, {"tokens": ["a", "double", "decker", "bus", "on", "the", "right", "corner"], "raw": "A double decker bus on the right corner", "sent_id": 15103, "sent": "a double decker bus on the right corner"}], "file_name": "COCO_train2014_000000125658_164609.jpg", "ann_id": 164609, "sent_ids": [15102, 15103], "ref_id": 10845}, {"segmentation": [[317.16, 141.71, 264.3, 196.82, 204.69, 290.17, 200.19, 330.65, 221.56, 362.15, 355.4, 427.38, 418.38, 424.0, 455.49, 367.77, 500.48, 218.19, 493.73, 196.82, 447.62, 178.82, 332.9, 140.58]], "area": 59457.95924999999, "iscrowd": 0, "image_id": 178763, "bbox": [200.19, 140.58, 300.29, 286.8], "category_id": 51, "id": 1898362, "split": "val", "sentences": [{"tokens": ["a", "lunch", "tray", "with", "a", "small", "yellow", "container"], "raw": "A lunch tray with a small yellow container.", "sent_id": 15188, "sent": "a lunch tray with a small yellow container"}, {"tokens": ["the", "bottom", "right", "tray", "with", "a", "salad", "in", "it"], "raw": "the bottom right tray with a salad in it", "sent_id": 15189, "sent": "the bottom right tray with a salad in it"}], "file_name": "COCO_train2014_000000178763_1898362.jpg", "ann_id": 1898362, "sent_ids": [15188, 15189], "ref_id": 10879}, {"segmentation": [[459.62, 181.42, 475.94, 151.67, 521.04, 124.81, 565.18, 100.82, 588.2, 87.38, 590.12, 69.15, 593.0, 39.41, 573.81, 0.06, 640.0, 1.98, 639.06, 418.43, 552.7, 421.31, 559.42, 364.69, 555.58, 357.02, 529.67, 352.22, 512.4, 321.51, 497.05, 325.35, 460.58, 391.56, 449.07, 352.22, 461.54, 191.01]], "area": 53402.73499999999, "iscrowd": 0, "image_id": 187577, "bbox": [449.07, 0.06, 190.93, 421.25], "category_id": 1, "id": 493470, "split": "val", "sentences": [{"tokens": ["woman", "with", "gold", "necklace", "sitting", "behind", "little", "birthday", "girl"], "raw": "Woman with gold necklace sitting behind little birthday girl.", "sent_id": 15204, "sent": "woman with gold necklace sitting behind little birthday girl"}, {"tokens": ["a", "woman", "standing", "near", "to", "a", "girl"], "raw": "A WOMAN STANDING NEAR TO A GIRL", "sent_id": 15205, "sent": "a woman standing near to a girl"}], "file_name": "COCO_train2014_000000187577_493470.jpg", "ann_id": 493470, "sent_ids": [15204, 15205], "ref_id": 10886}, {"segmentation": [[279.73, 236.61, 241.89, 259.48, 238.98, 265.71, 234.41, 289.83, 230.25, 300.64, 231.5, 311.45, 233.99, 331.41, 234.41, 360.93, 247.71, 383.38, 258.52, 383.8, 277.65, 388.37, 287.21, 391.7, 291.79, 402.1, 275.57, 409.58, 228.17, 412.07, 201.98, 408.75, 174.12, 406.25, 168.3, 403.76, 160.4, 398.35, 162.47, 392.95, 174.95, 388.37, 190.75, 384.63, 207.38, 378.81, 214.03, 372.99, 220.69, 355.11, 221.1, 311.45, 219.44, 267.79, 219.44, 262.39, 209.46, 252.82, 193.66, 247.0, 165.38, 224.97, 154.57, 210.0, 150.0, 195.03, 146.26, 160.1, 153.33, 135.15, 176.61, 72.78, 289.29, 76.94, 308.0, 134.74, 311.33, 163.43, 312.99, 190.87, 293.87, 228.29]], "area": 30002.11875, "iscrowd": 0, "image_id": 90569, "bbox": [146.26, 72.78, 166.73, 339.29], "category_id": 46, "id": 663682, "split": "val", "sentences": [{"tokens": ["wine", "glass", "on", "the", "left"], "raw": "Wine glass on the left.", "sent_id": 15206, "sent": "wine glass on the left"}, {"tokens": ["a", "glass", "of", "wine", "where", "the", "person", "holding", "it", "has", "a", "watch", "on", ",", "not", "a", "ring"], "raw": "A glass of wine where the person holding it has a watch on, not a ring.", "sent_id": 15207, "sent": "a glass of wine where the person holding it has a watch on , not a ring"}], "file_name": "COCO_train2014_000000090569_663682.jpg", "ann_id": 663682, "sent_ids": [15206, 15207], "ref_id": 10887}, {"segmentation": [[101.97, 2.68, 116.39, 89.2, 154.51, 165.42, 158.63, 197.36, 131.85, 206.63, 122.58, 339.5, 155.54, 373.49, 130.82, 384.82, 82.4, 380.7, 74.16, 377.61, 41.2, 182.94, 57.68, 28.43, 61.8, 3.71]], "area": 28259.636300000002, "iscrowd": 0, "image_id": 204529, "bbox": [41.2, 2.68, 117.43, 382.14], "category_id": 44, "id": 91365, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "chardonnay"], "raw": "A bottle of Chardonnay.", "sent_id": 15223, "sent": "a bottle of chardonnay"}, {"tokens": ["the", "bottle", "on", "the", "end", "that", "says", "chardonnay", "and", "has", "a", "green", "box", "on", "it"], "raw": "The bottle on the end that says Chardonnay and has a green box on it", "sent_id": 15224, "sent": "the bottle on the end that says chardonnay and has a green box on it"}], "file_name": "COCO_train2014_000000204529_91365.jpg", "ann_id": 91365, "sent_ids": [15223, 15224], "ref_id": 10894}, {"segmentation": [[350.67, 340.71, 353.49, 315.83, 357.72, 298.45, 365.7, 287.19, 376.97, 271.22, 391.99, 259.95, 401.85, 247.35, 404.67, 239.84, 405.14, 229.98, 405.61, 219.65, 410.3, 205.56, 419.69, 194.77, 438.94, 189.6, 450.68, 191.95, 461.01, 195.7, 464.77, 199.46, 469.46, 210.26, 470.4, 218.71, 471.34, 222.0, 472.75, 226.22, 475.09, 230.45, 475.09, 237.96, 472.28, 242.19, 468.99, 247.82, 466.17, 252.98, 463.83, 259.09, 460.07, 268.01, 460.54, 274.58, 461.48, 277.87, 464.77, 279.28, 468.05, 286.32, 476.97, 299.47, 484.02, 306.04, 491.06, 315.9, 493.88, 322.47, 507.96, 359.44, 509.37, 390.9, 515.47, 430.81, 515.94, 443.01, 512.66, 465.01, 507.02, 472.52, 504.2, 479.09, 359.13, 478.15, 360.06, 462.66, 362.41, 448.58, 362.41, 441.53, 356.78, 436.37, 352.08, 432.14, 350.67, 427.45, 353.49, 401.62, 353.49, 394.58, 349.27, 387.54, 345.98, 380.97, 347.86, 366.41, 349.74, 343.87]], "area": 35361.0383, "iscrowd": 0, "image_id": 492638, "bbox": [345.98, 189.6, 169.96, 289.49], "category_id": 1, "id": 442483, "split": "val", "sentences": [{"tokens": ["an", "overweight", "guy", "in", "a", "white", "sweater", "playing", "wii"], "raw": "An overweight guy in a white sweater playing wii", "sent_id": 15242, "sent": "an overweight guy in a white sweater playing wii"}, {"tokens": ["large", "man", "in", "white", "and", "gold", "sweater", "on", "the", "right"], "raw": "Large man in white and gold sweater on the right.", "sent_id": 15243, "sent": "large man in white and gold sweater on the right"}], "file_name": "COCO_train2014_000000492638_442483.jpg", "ann_id": 442483, "sent_ids": [15242, 15243], "ref_id": 10899}, {"segmentation": [[245.93, 302.92, 214.65, 327.73, 198.47, 344.99, 189.84, 353.62, 186.61, 314.79, 172.58, 255.46, 160.72, 204.76, 127.28, 129.26, 105.71, 94.74, 49.62, 88.27, 9.71, 94.74, 2.16, 106.61, 2.16, 377.35, 2.16, 470.11, 215.73, 474.43, 228.67, 474.43, 229.75, 434.52, 214.65, 402.16, 211.42, 376.27, 227.6, 349.3, 239.46, 337.44, 245.93, 332.04], [281.53, 354.7, 279.37, 391.37, 262.11, 434.52, 249.17, 466.88, 244.85, 471.19, 281.53, 474.43, 295.55, 435.6, 298.79, 408.63, 308.49, 367.64, 305.26, 359.01]], "area": 71773.62465, "iscrowd": 0, "image_id": 524476, "bbox": [2.16, 88.27, 306.33, 386.16], "category_id": 1, "id": 252854, "split": "val", "sentences": [{"tokens": ["a", "woman", "holding", "the", "dog", "with", "both", "hands"], "raw": "A woman holding the dog with both hands.", "sent_id": 15299, "sent": "a woman holding the dog with both hands"}, {"tokens": ["a", "woman", "with", "long", "hair", "holding", "a", "dog"], "raw": "a woman with long hair holding a dog.", "sent_id": 15300, "sent": "a woman with long hair holding a dog"}], "file_name": "COCO_train2014_000000524476_252854.jpg", "ann_id": 252854, "sent_ids": [15299, 15300], "ref_id": 10921}, {"segmentation": [[328.99, 365.66, 324.67, 330.07, 264.27, 331.15, 250.25, 313.89, 259.96, 297.71, 270.74, 294.47, 271.82, 276.13, 277.21, 269.66, 278.29, 248.09, 289.08, 235.15, 304.18, 227.6, 304.18, 206.02, 317.12, 192.0, 326.83, 188.76, 341.93, 199.55, 350.56, 236.22, 361.35, 239.46, 374.29, 291.24, 358.11, 304.18, 366.74, 304.18, 372.13, 327.91, 365.66, 328.99, 362.43, 340.85, 366.74, 364.58, 332.22, 361.35]], "area": 12315.664050000001, "iscrowd": 0, "image_id": 443410, "bbox": [250.25, 188.76, 124.04, 176.9], "category_id": 1, "id": 193900, "split": "val", "sentences": [{"tokens": ["the", "woman", "in", "the", "middle", "sitting", "on", "the", "couch"], "raw": "the woman in the middle sitting on the couch", "sent_id": 15343, "sent": "the woman in the middle sitting on the couch"}, {"tokens": ["woman", "in", "middle"], "raw": "woman in middle", "sent_id": 15344, "sent": "woman in middle"}], "file_name": "COCO_train2014_000000443410_193900.jpg", "ann_id": 193900, "sent_ids": [15343, 15344], "ref_id": 10936}, {"segmentation": [[7.87, 251.14, 3.93, 313.32, 246.33, 311.74, 379.33, 319.61, 380.12, 335.35, 387.2, 337.71, 393.5, 337.71, 391.92, 325.91, 395.86, 315.68, 415.53, 312.53, 421.04, 284.98, 412.39, 270.82, 402.94, 262.16, 393.5, 254.29, 295.12, 259.01, 289.61, 268.46, 251.05, 271.61, 232.95, 264.52, 208.55, 268.46, 201.47, 266.1, 153.46, 266.1, 126.71, 268.46, 100.74, 266.88, 68.47, 254.29]], "area": 21641.594600000004, "iscrowd": 0, "image_id": 305624, "bbox": [3.93, 251.14, 417.11, 86.57], "category_id": 15, "id": 573697, "split": "val", "sentences": [{"tokens": ["a", "bench", "on", "a", "pier", "with", "a", "couple", "sitting", "on", "it"], "raw": "A bench on a pier with a couple sitting on it.", "sent_id": 15345, "sent": "a bench on a pier with a couple sitting on it"}, {"tokens": ["a", "bench", "with", "people", "sitting", "on", "it"], "raw": "A bench with people sitting on it", "sent_id": 15346, "sent": "a bench with people sitting on it"}], "file_name": "COCO_train2014_000000305624_573697.jpg", "ann_id": 573697, "sent_ids": [15345, 15346], "ref_id": 10937}, {"segmentation": [[240.54, 300.94, 194.16, 296.63, 151.01, 283.69, 132.67, 273.98, 97.08, 253.48, 86.29, 224.36, 62.56, 212.49, 45.3, 196.31, 81.98, 174.74, 99.24, 176.9, 115.42, 171.51, 144.54, 170.43, 161.8, 189.84, 174.74, 237.3, 189.84, 266.43, 220.04, 286.92, 238.38, 293.39]], "area": 10535.367950000003, "iscrowd": 0, "image_id": 443136, "bbox": [45.3, 170.43, 195.24, 130.51], "category_id": 59, "id": 1570975, "split": "val", "sentences": [{"tokens": ["piece", "pizzza"], "raw": "piece pizzza", "sent_id": 15372, "sent": "piece pizzza"}], "file_name": "COCO_train2014_000000443136_1570975.jpg", "ann_id": 1570975, "sent_ids": [15372], "ref_id": 10947}, {"segmentation": [[180.61, 278.3, 184.15, 258.24, 175.3, 227.57, 174.71, 196.9, 160.55, 159.16, 163.5, 127.9, 163.5, 104.89, 169.4, 93.1, 179.43, 81.3, 184.15, 74.82, 182.38, 63.61, 188.86, 51.22, 204.2, 48.86, 214.82, 60.66, 213.64, 79.53, 205.38, 88.97, 203.61, 102.54, 198.89, 114.92, 214.82, 132.62, 228.97, 146.77, 238.41, 161.52, 245.49, 202.63, 249.61, 212.07, 256.1, 213.84, 259.64, 221.51, 246.08, 219.15, 238.41, 219.15, 234.28, 204.99, 225.43, 180.81, 220.12, 169.02, 215.41, 171.38, 221.3, 190.25, 219.53, 199.69, 210.69, 198.51, 207.74, 190.84, 207.74, 176.68, 198.3, 170.79, 200.07, 180.81, 193.58, 187.3, 194.76, 213.25, 192.4, 227.41, 192.4, 244.51, 193.58, 257.49, 193.58, 280.39, 186.51, 282.16, 178.84, 277.44]], "area": 8508.90555, "iscrowd": 0, "image_id": 102432, "bbox": [160.55, 48.86, 99.09, 233.3], "category_id": 1, "id": 2153643, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "no", "shirt", "or", "shoes"], "raw": "The man with no shirt or shoes.", "sent_id": 15388, "sent": "the man with no shirt or shoes"}, {"tokens": ["a", "man", "jumping", "on", "a", "beach"], "raw": "A man jumping on a beach.", "sent_id": 15389, "sent": "a man jumping on a beach"}], "file_name": "COCO_train2014_000000102432_2153643.jpg", "ann_id": 2153643, "sent_ids": [15388, 15389], "ref_id": 10954}, {"segmentation": [[615.68, 4.16, 633.41, 3.63, 640.0, 90.12, 640.0, 230.34, 488.89, 233.03, 478.15, 12.22, 488.89, 0.94, 518.98, 2.01]], "area": 35535.5768, "iscrowd": 0, "image_id": 205223, "bbox": [478.15, 0.94, 161.85, 232.09], "category_id": 1, "id": 498583, "split": "val", "sentences": [{"tokens": ["a", "white", "shirt", "with", "gray", "tie", "and", "suit", "coat", "highlighted", "with", "a", "white", "flower", "in", "the", "lapel"], "raw": "A white shirt with gray tie and suit coat highlighted with a white flower in the lapel", "sent_id": 15477, "sent": "a white shirt with gray tie and suit coat highlighted with a white flower in the lapel"}, {"tokens": ["the", "suit", "on", "the", "far", "right"], "raw": "the suit on the far right", "sent_id": 15478, "sent": "the suit on the far right"}], "file_name": "COCO_train2014_000000205223_498583.jpg", "ann_id": 498583, "sent_ids": [15477, 15478], "ref_id": 10988}, {"segmentation": [[110.69, 32.33, 116.4, 50.19, 137.11, 49.47, 164.24, 100.17, 179.95, 91.6, 196.38, 88.03, 207.09, 73.75, 199.95, 85.18, 214.23, 81.61, 215.66, 53.04, 225.66, 40.19, 234.23, 38.76, 253.51, 53.04, 262.79, 61.61, 261.36, 71.61, 256.36, 80.89, 266.36, 94.46, 258.5, 105.88, 234.23, 103.03, 227.8, 100.17, 192.09, 127.31, 182.1, 136.59, 204.95, 180.15, 213.57, 199.69, 191.73, 216.67, 177.98, 214.25, 171.51, 200.49, 157.75, 206.97, 144.0, 194.02, 132.67, 191.6, 131.06, 189.17, 136.72, 182.7, 128.63, 164.9, 95.46, 172.18, 87.37, 167.33, 80.9, 168.94, 92.22, 182.7, 88.18, 178.65, 81.71, 173.8, 74.43, 172.99, 67.15, 169.75, 74.43, 160.85, 63.91, 141.44, 76.85, 157.62, 78.47, 147.1, 103.55, 134.16, 71.19, 45.98, 86.56, 33.84, 95.46, 29.8]], "area": 17532.46125, "iscrowd": 0, "image_id": 310006, "bbox": [63.91, 29.8, 202.45, 186.87], "category_id": 5, "id": 161509, "split": "val", "sentences": [{"tokens": ["white", "plane", "in", "the", "front"], "raw": "white plane in the front.", "sent_id": 15618, "sent": "white plane in the front"}, {"tokens": ["the", "white", "bi", "-", "plane", "leading", "the", "pack"], "raw": "The white bi-plane leading the pack", "sent_id": 15619, "sent": "the white bi - plane leading the pack"}], "file_name": "COCO_train2014_000000310006_161509.jpg", "ann_id": 161509, "sent_ids": [15618, 15619], "ref_id": 11046}, {"segmentation": [[543.24, 288.81, 529.48, 316.31, 529.48, 334.19, 512.98, 354.82, 477.22, 387.83, 455.22, 408.46, 442.84, 462.09, 457.97, 548.74, 482.72, 577.62, 526.73, 584.49, 574.87, 590.0, 610.62, 590.0, 612.0, 298.44, 587.24, 283.31, 556.99, 283.31]], "area": 40153.8103, "iscrowd": 0, "image_id": 427805, "bbox": [442.84, 283.31, 169.16, 306.69], "category_id": 86, "id": 1157228, "split": "val", "sentences": [{"tokens": ["vase", "with", "small", "blue", "flowers"], "raw": "Vase with small blue flowers", "sent_id": 15622, "sent": "vase with small blue flowers"}, {"tokens": ["a", "glass", "vase", "to", "the", "right", "of", "two", "other", "vases"], "raw": "a glass vase to the right of two other vases", "sent_id": 15623, "sent": "a glass vase to the right of two other vases"}], "file_name": "COCO_train2014_000000427805_1157228.jpg", "ann_id": 1157228, "sent_ids": [15622, 15623], "ref_id": 11048}, {"segmentation": [[319.28, 271.82, 347.33, 243.78, 335.46, 222.2, 321.44, 201.71, 314.97, 181.21, 309.57, 152.09, 311.73, 131.6, 320.36, 112.18, 327.91, 103.55, 343.01, 97.08, 364.58, 96.0, 391.55, 98.16, 412.04, 113.26, 419.6, 128.36, 423.91, 146.7, 422.83, 167.19, 420.67, 182.29, 419.6, 206.02, 420.67, 222.2, 436.85, 231.91, 467.06, 244.85, 483.24, 255.64, 487.55, 261.03, 496.18, 278.29, 496.18, 284.76, 503.73, 316.04, 510.2, 333.3, 516.67, 357.03, 516.67, 381.84, 522.07, 404.49, 513.44, 417.44, 508.04, 423.91, 511.28, 437.93, 513.44, 450.88, 513.44, 462.74, 511.28, 471.37, 506.97, 476.76, 502.65, 478.92, 325.75, 476.76, 312.81, 334.38, 314.97, 306.34, 316.04, 292.31]], "area": 58450.65345, "iscrowd": 0, "image_id": 221880, "bbox": [309.57, 96.0, 212.5, 382.92], "category_id": 1, "id": 513233, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "black", "dress", "with", "a", "red", "shawl", "standing", "next", "to", "a", "man"], "raw": "A woman in a black dress with a red shawl standing next to a man.", "sent_id": 15624, "sent": "a woman in a black dress with a red shawl standing next to a man"}, {"tokens": ["lady", "in", "black", "top", "and", "red", "shawl"], "raw": "Lady in black top and red shawl.", "sent_id": 15625, "sent": "lady in black top and red shawl"}], "file_name": "COCO_train2014_000000221880_513233.jpg", "ann_id": 513233, "sent_ids": [15624, 15625], "ref_id": 11049}, {"segmentation": [[510.27, 280.54, 511.35, 260.0, 517.84, 251.35, 534.05, 239.46, 535.14, 234.05, 535.14, 224.32, 538.38, 209.19, 543.78, 198.38, 540.54, 177.84, 532.97, 176.76, 538.38, 167.03, 530.81, 157.3, 529.73, 148.65, 530.81, 147.57, 537.3, 143.24, 539.46, 134.59, 539.46, 125.95, 549.19, 109.73, 557.84, 98.92, 570.81, 91.35, 582.7, 85.95, 595.68, 81.62, 617.3, 81.62, 632.43, 81.62, 640.0, 84.86, 633.51, 472.97, 610.81, 474.05, 563.24, 474.05, 552.43, 463.24, 541.62, 439.46, 521.08, 398.38, 511.35, 389.73, 512.43, 346.49, 517.84, 329.19, 511.35, 314.05, 513.51, 296.76, 513.51, 284.86]], "area": 41578.25885, "iscrowd": 0, "image_id": 408954, "bbox": [510.27, 81.62, 129.73, 392.43], "category_id": 1, "id": 492445, "split": "val", "sentences": [{"tokens": ["woman", "in", "dark", "blue", "jacket", "with", "red", "and", "black", "scarf"], "raw": "Woman in dark blue jacket with red and black scarf.", "sent_id": 15760, "sent": "woman in dark blue jacket with red and black scarf"}, {"tokens": ["a", "person", "wearing", "a", "black", "/", "blue", "jacket", "with", "short", "hair", "and", "glasses"], "raw": "A person wearing a black/blue jacket with short hair and glasses.", "sent_id": 15761, "sent": "a person wearing a black / blue jacket with short hair and glasses"}], "file_name": "COCO_train2014_000000408954_492445.jpg", "ann_id": 492445, "sent_ids": [15760, 15761], "ref_id": 11100}, {"segmentation": [[448.84, 134.72, 447.24, 141.12, 448.04, 152.32, 448.04, 157.12, 447.24, 169.12, 444.85, 181.12, 440.05, 189.91, 416.05, 197.91, 408.05, 202.71, 405.65, 207.51, 399.25, 221.91, 376.06, 265.9, 372.06, 280.3, 372.06, 284.3, 373.66, 296.29, 374.46, 297.09, 388.86, 303.49, 394.45, 305.09, 400.85, 305.89, 406.45, 305.89, 418.45, 324.29, 416.85, 330.69, 402.45, 332.29, 399.25, 330.69, 389.66, 347.48, 384.86, 369.88, 384.86, 372.28, 400.85, 384.28, 403.25, 384.28, 406.45, 386.68, 411.25, 390.68, 413.65, 418.99, 426.45, 456.91, 432.85, 465.71, 437.65, 472.9, 440.85, 481.7, 444.05, 509.7, 440.05, 523.3, 432.05, 538.49, 431.25, 541.69, 431.25, 548.09, 429.65, 561.69, 428.05, 583.12, 416.05, 587.92, 415.25, 590.32, 419.25, 595.12, 424.05, 597.52, 447.24, 601.35, 468.04, 601.35, 471.24, 591.76, 469.64, 565.36, 465.64, 516.57, 468.84, 470.98, 471.24, 434.19, 472.04, 422.99, 479.24, 416.59, 484.84, 440.58, 486.44, 460.58, 488.04, 485.38, 488.04, 508.57, 488.04, 535.77, 488.04, 558.96, 496.84, 594.16, 520.83, 605.35, 548.83, 607.75, 556.02, 607.75, 556.82, 602.95, 554.42, 596.55, 544.03, 586.96, 534.43, 571.76, 534.43, 562.16, 538.43, 547.76, 539.23, 532.57, 537.63, 510.17, 527.23, 452.58, 532.83, 434.99, 536.83, 414.19, 536.03, 395.79, 528.03, 343.8, 528.03, 292.45, 543.23, 300.45, 567.22, 297.25, 569.0, 277.25, 563.22, 261.41, 544.83, 234.22, 534.43, 205.58, 520.83, 197.59, 502.43, 193.59, 496.84, 189.59, 504.03, 179.99, 504.03, 171.99, 506.43, 141.92, 515.23, 146.71, 517.63, 140.32, 516.83, 135.52, 498.44, 129.12, 486.44, 123.52, 479.24, 116.32, 460.04, 120.32, 449.64, 129.12]], "area": 52680.27399999999, "iscrowd": 0, "image_id": 221169, "bbox": [372.06, 116.32, 196.94, 491.43], "category_id": 1, "id": 215792, "split": "val", "sentences": [{"tokens": ["a", "fat", "man", "in", "grey", "pants"], "raw": "a fat man in grey pants", "sent_id": 15919, "sent": "a fat man in grey pants"}, {"tokens": ["man", "wearing", "camera", "around", "neck"], "raw": "Man wearing camera around neck.", "sent_id": 15920, "sent": "man wearing camera around neck"}], "file_name": "COCO_train2014_000000221169_215792.jpg", "ann_id": 215792, "sent_ids": [15919, 15920], "ref_id": 11160}, {"segmentation": [[385.56, 322.84, 408.44, 330.76, 458.6, 346.6, 502.6, 358.04, 534.28, 370.36, 531.64, 382.68, 528.12, 391.48, 531.64, 395.0, 519.32, 414.36, 494.68, 428.44, 453.32, 422.28, 419.88, 393.24, 407.56, 382.68, 384.68, 345.72, 384.68, 325.48]], "area": 8891.6608, "iscrowd": 0, "image_id": 510027, "bbox": [384.68, 322.84, 149.6, 105.6], "category_id": 53, "id": 1047371, "split": "val", "sentences": [{"tokens": ["a", "large", "apple", "slice", "in", "a", "green", "container", "between", "two", "other", "apple", "slices"], "raw": "A large apple slice in a green container between two other apple slices", "sent_id": 15923, "sent": "a large apple slice in a green container between two other apple slices"}, {"tokens": ["an", "apple", "which", "cutted", "into", "piecies"], "raw": "An apple which cutted into piecies", "sent_id": 15924, "sent": "an apple which cutted into piecies"}], "file_name": "COCO_train2014_000000510027_1047371.jpg", "ann_id": 1047371, "sent_ids": [15923, 15924], "ref_id": 11162}, {"segmentation": [[545.02, 122.82, 546.94, 100.75, 553.66, 90.2, 566.13, 16.31, 569.97, 8.64, 578.61, 2.88, 573.81, 0.96, 461.54, 1.92, 461.54, 12.47, 463.46, 23.99, 468.26, 27.83, 479.78, 39.34, 489.37, 47.98, 498.97, 53.73, 505.68, 57.57, 519.12, 66.21, 524.87, 80.6, 530.63, 93.08, 533.51, 103.63, 531.59, 115.15, 538.31, 119.94]], "area": 6705.3569, "iscrowd": 0, "image_id": 364169, "bbox": [461.54, 0.96, 117.07, 121.86], "category_id": 1, "id": 1727699, "split": "val", "sentences": [{"tokens": ["a", "person", "standing", "near", "to", "a", "girl", "only", "legs", "are", "visible"], "raw": "A person standing near to a girl only legs are visible", "sent_id": 15997, "sent": "a person standing near to a girl only legs are visible"}, {"tokens": ["a", "person", "wearing", "jeans", "and", "a", "sweater", "standing", "near", "a", "child"], "raw": "A person wearing jeans and a sweater standing near a child.", "sent_id": 15998, "sent": "a person wearing jeans and a sweater standing near a child"}], "file_name": "COCO_train2014_000000364169_1727699.jpg", "ann_id": 1727699, "sent_ids": [15997, 15998], "ref_id": 11189}, {"segmentation": [[446.15, 419.29, 440.4, 398.23, 438.49, 286.21, 427.96, 234.51, 396.36, 230.69, 382.96, 205.79, 382.96, 200.05, 408.81, 192.39, 419.34, 177.07, 418.38, 141.65, 420.3, 119.63, 408.81, 104.31, 397.32, 88.03, 397.32, 61.23, 404.02, 43.99, 416.47, 34.42, 449.02, 33.46, 452.85, 43.99, 465.3, 66.97, 473.91, 81.33, 483.49, 91.86, 513.17, 117.71, 525.61, 132.07, 539.97, 146.43, 543.8, 172.28, 549.55, 197.18, 551.46, 233.56, 552.42, 268.98, 575.4, 378.12, 568.7, 409.72, 567.74, 418.34]], "area": 44580.8641, "iscrowd": 0, "image_id": 340129, "bbox": [382.96, 33.46, 192.44, 385.83], "category_id": 1, "id": 475028, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "red"], "raw": "The man in red.", "sent_id": 16023, "sent": "the man in red"}, {"tokens": ["the", "man", "in", "the", "red", "shirt", "carrying", "baseball", "bats"], "raw": "The man in the red shirt carrying baseball bats", "sent_id": 16024, "sent": "the man in the red shirt carrying baseball bats"}], "file_name": "COCO_train2014_000000340129_475028.jpg", "ann_id": 475028, "sent_ids": [16023, 16024], "ref_id": 11200}, {"segmentation": [[500.49, 390.47, 517.75, 390.47, 520.99, 389.39, 525.3, 382.92, 525.3, 379.69, 518.83, 368.9, 513.44, 362.43, 509.12, 357.03, 501.57, 346.25, 496.18, 332.22, 490.79, 303.1, 488.63, 286.92, 491.87, 266.43, 499.42, 253.48, 501.57, 243.78, 501.57, 220.04, 505.89, 203.87, 511.28, 192.0, 517.75, 186.61, 532.85, 197.39, 533.93, 198.47, 537.17, 193.08, 550.11, 187.69, 553.35, 187.69, 554.43, 190.92, 556.58, 198.47, 559.82, 197.39, 565.21, 192.0, 573.84, 189.84, 581.39, 190.92, 587.87, 210.34, 592.18, 224.36, 588.94, 244.85, 590.02, 259.96, 593.26, 272.9, 593.26, 290.16, 590.02, 305.26, 586.79, 316.04, 582.47, 331.15, 579.24, 346.25, 574.92, 353.8, 560.9, 371.06, 556.58, 374.29, 555.51, 379.69, 558.74, 385.08, 560.9, 389.39, 564.13, 400.18, 567.37, 412.04, 574.92, 420.67, 576.0, 426.07, 574.92, 432.54, 558.74, 435.78, 529.62, 436.85, 511.28, 439.01, 505.89, 439.01, 503.73, 422.83, 501.57, 408.81, 500.49, 404.49, 503.73, 393.71]], "area": 19321.554099999998, "iscrowd": 0, "image_id": 419028, "bbox": [488.63, 186.61, 104.63, 252.4], "category_id": 86, "id": 1156945, "split": "val", "sentences": [{"tokens": ["a", "black", "ancient", "greek", "vase", "with", "figures"], "raw": "A black ancient Greek vase with figures.", "sent_id": 16044, "sent": "a black ancient greek vase with figures"}, {"tokens": ["an", "urn", "with", "pictures", "of", "people", "on", "it", "that", "is", "to", "the", "right", "of", "three", "other", "urns"], "raw": "An urn with pictures of people on it that is to the right of three other urns.", "sent_id": 16045, "sent": "an urn with pictures of people on it that is to the right of three other urns"}], "file_name": "COCO_train2014_000000419028_1156945.jpg", "ann_id": 1156945, "sent_ids": [16044, 16045], "ref_id": 11208}, {"segmentation": [[391.6, 174.32, 441.41, 174.32, 450.2, 171.39, 479.49, 146.97, 500.0, 127.44, 497.07, 370.61, 308.59, 368.65, 294.92, 302.25, 295.9, 271.0, 296.88, 249.51, 304.69, 228.03, 320.31, 206.54, 350.59, 186.04, 392.58, 169.43]], "area": 38271.3316, "iscrowd": 0, "image_id": 103430, "bbox": [294.92, 127.44, 205.08, 243.17], "category_id": 58, "id": 1921506, "split": "val", "sentences": [{"tokens": ["the", "rightmost", "hotdog"], "raw": "the rightmost hotdog", "sent_id": 16046, "sent": "the rightmost hotdog"}, {"tokens": ["a", "roll", "in", "the", "bottom", "right", "corner"], "raw": "a roll in the bottom right corner", "sent_id": 16047, "sent": "a roll in the bottom right corner"}], "file_name": "COCO_train2014_000000103430_1921506.jpg", "ann_id": 1921506, "sent_ids": [16046, 16047], "ref_id": 11209}, {"segmentation": [[405.89, 107.71, 398.21, 248.76, 402.05, 258.36, 402.05, 258.36, 408.77, 248.76, 481.69, 251.64, 487.45, 261.24, 488.41, 262.2, 494.17, 263.16, 495.13, 261.24, 502.8, 193.11, 509.52, 190.23, 503.76, 183.51, 494.17, 100.03]], "area": 14471.292750000004, "iscrowd": 0, "image_id": 169656, "bbox": [398.21, 100.03, 111.31, 163.13], "category_id": 6, "id": 166879, "split": "val", "sentences": [{"tokens": ["brown", "double", "bus"], "raw": "brown double bus", "sent_id": 16053, "sent": "brown double bus"}, {"tokens": ["a", "red", "double", "decker", "bus", "with", "the", "number", "113", "on", "it"], "raw": "a red double decker bus with the number 113 on it.", "sent_id": 16054, "sent": "a red double decker bus with the number 113 on it"}], "file_name": "COCO_train2014_000000169656_166879.jpg", "ann_id": 166879, "sent_ids": [16053, 16054], "ref_id": 11213}, {"segmentation": [[250.28, 334.82, 268.08, 285.88, 323.7, 278.09, 311.46, 268.08, 268.08, 265.85, 258.07, 268.08, 254.73, 262.52, 268.08, 211.35, 260.29, 191.33, 226.92, 190.21, 183.54, 208.01, 166.85, 231.37, 159.07, 251.39, 142.38, 281.43, 154.62, 299.22, 180.2, 343.72, 179.09, 372.64, 198.0, 379.31, 219.13, 372.64, 216.91, 347.06, 236.93, 368.19, 258.07, 365.97]], "area": 17151.142949999994, "iscrowd": 0, "image_id": 332133, "bbox": [142.38, 190.21, 181.32, 189.1], "category_id": 1, "id": 453976, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "shirt", "skateboarding"], "raw": "A man in a red shirt skateboarding.", "sent_id": 16145, "sent": "a man in a red shirt skateboarding"}, {"tokens": ["a", "man", "in", "a", "red", "shirt", "performing", "a", "kick", "flip"], "raw": "A man in a red shirt performing a kick flip.", "sent_id": 16146, "sent": "a man in a red shirt performing a kick flip"}], "file_name": "COCO_train2014_000000332133_453976.jpg", "ann_id": 453976, "sent_ids": [16145, 16146], "ref_id": 11249}, {"segmentation": [[59.61, 77.64, 59.61, 92.54, 59.61, 100.49, 50.67, 110.43, 48.69, 123.35, 49.68, 139.24, 53.65, 151.17, 51.67, 172.03, 47.69, 182.96, 46.7, 189.91, 50.67, 208.79, 56.63, 219.72, 65.58, 225.68, 68.56, 226.68, 76.51, 240.59, 76.51, 254.5, 73.52, 267.41, 82.47, 285.3, 96.38, 325.04, 100.35, 343.92, 109.29, 385.65, 107.31, 417.44, 106.31, 446.26, 115.25, 456.19, 127.18, 454.06, 133.14, 440.15, 136.12, 425.25, 135.13, 383.52, 133.14, 360.67, 140.09, 318.94, 151.02, 311.98, 164.93, 340.8, 155.99, 383.52, 153.01, 424.26, 155.0, 448.1, 181.82, 447.25, 183.81, 410.49, 187.79, 384.66, 192.75, 348.89, 192.75, 327.03, 193.75, 321.07, 196.73, 349.88, 207.66, 392.6, 208.65, 412.48, 201.7, 433.34, 218.59, 446.26, 232.5, 449.24, 241.44, 442.28, 245.41, 401.55, 247.4, 382.67, 253.36, 331.0, 253.36, 326.03, 254.36, 296.23, 246.41, 277.35, 230.51, 246.55, 226.54, 231.65, 225.54, 209.79, 225.54, 193.89, 219.58, 177.99, 210.64, 170.04, 155.0, 131.29, 147.05, 117.38, 141.09, 102.48, 131.15, 86.58, 125.19, 71.68, 116.25, 76.65, 113.27, 62.74, 101.34, 59.76, 92.4, 64.72, 79.49, 65.72, 67.56, 59.76, 61.6, 56.78, 56.63, 54.79]], "area": 49012.511549999996, "iscrowd": 0, "image_id": 113676, "bbox": [46.7, 54.79, 207.66, 401.4], "category_id": 19, "id": 54977, "split": "val", "sentences": [{"tokens": ["a", "horse", "to", "the", "left", "of", "another", "horse"], "raw": "a horse to the left of another horse", "sent_id": 16157, "sent": "a horse to the left of another horse"}, {"tokens": ["horse", "on", "the", "left", "hand", "side"], "raw": "horse on the left hand side.", "sent_id": 16158, "sent": "horse on the left hand side"}], "file_name": "COCO_train2014_000000113676_54977.jpg", "ann_id": 54977, "sent_ids": [16157, 16158], "ref_id": 11254}, {"segmentation": [[261.13, 317.39, 264.73, 264.73, 277.72, 272.67, 276.28, 243.09, 297.92, 197.65, 295.03, 155.09, 286.38, 98.1, 243.09, 78.63, 241.65, 54.1, 238.77, 34.62, 222.18, 30.3, 204.86, 38.23, 205.58, 57.71, 210.63, 83.68, 165.19, 100.99, 163.75, 145.71, 155.81, 210.63, 162.3, 253.19, 169.52, 265.46, 178.17, 261.13, 183.94, 268.34, 178.89, 316.67]], "area": 28531.7021, "iscrowd": 0, "image_id": 542442, "bbox": [155.81, 30.3, 142.11, 287.09], "category_id": 1, "id": 230265, "split": "val", "sentences": [{"tokens": ["the", "gentleman", "in", "the", "middle", "with", "a", "white", "shirt", "and", "a", "purple", "necktie"], "raw": "The gentleman in the middle with a white shirt and a purple necktie.", "sent_id": 16159, "sent": "the gentleman in the middle with a white shirt and a purple necktie"}, {"tokens": ["a", "black", "man", "with", "a", "pink", "neck", "tie", "and", "holding", "a", "bag", "in", "his", "hand"], "raw": "A black man with a pink neck tie and holding a bag in his hand.", "sent_id": 16160, "sent": "a black man with a pink neck tie and holding a bag in his hand"}], "file_name": "COCO_train2014_000000542442_230265.jpg", "ann_id": 230265, "sent_ids": [16159, 16160], "ref_id": 11255}, {"segmentation": [[109.98, 365.08, 127.07, 318.24, 124.54, 271.39, 128.34, 258.73, 116.95, 251.13, 112.51, 240.37, 97.95, 234.67, 120.74, 233.41, 136.57, 230.24, 140.37, 218.84, 157.46, 195.42, 191.01, 161.87, 208.11, 163.37, 254.32, 146.91, 268.25, 145.64, 289.77, 145.01, 304.97, 143.11, 316.99, 139.31, 335.35, 139.95, 360.04, 147.54, 380.3, 146.91, 398.66, 139.95, 425.25, 134.25, 439.18, 134.88, 460.07, 138.68, 474.0, 144.38, 496.79, 161.47, 510.71, 184.26, 512.61, 194.39, 520.21, 205.79, 527.17, 212.12, 536.67, 226.68, 557.56, 243.77, 603.77, 255.8, 593.65, 266.56, 587.95, 267.83, 571.49, 267.19, 553.76, 263.39, 541.73, 257.06, 534.14, 246.94, 524.64, 232.37, 515.78, 222.88, 510.08, 239.34, 494.25, 258.33, 484.76, 276.06, 477.16, 295.05, 473.36, 308.34, 469.56, 336.16, 464.5, 374.78, 451.21, 390.61, 456.9, 412.73, 441.08, 416.52, 440.44, 395.63, 432.85, 348.15, 427.15, 327.9, 409.42, 315.23, 399.93, 315.23, 347.38, 315.87, 354.98, 395.0, 355.61, 415.89, 341.05, 418.42, 342.95, 397.53, 330.29, 358.28, 323.33, 317.77, 319.53, 308.27, 300.54, 283.58, 289.14, 291.18, 278.38, 372.21, 275.21, 410.83, 266.35, 405.13, 263.18, 380.44, 258.12, 308.27, 262.55, 296.88, 253.69, 272.19, 253.69, 256.36, 243.56, 255.09, 229.0, 258.89, 204.31, 263.32, 190.38, 274.08, 184.05, 285.48, 184.05, 300.67, 182.15, 317.13, 177.72, 326.63, 170.12, 334.86, 159.36, 350.05, 150.5, 365.25, 148.6, 372.21, 135.3, 376.01, 116.31, 377.91, 109.98, 369.04, 108.08, 356.38]], "area": 66534.56845, "iscrowd": 0, "image_id": 73387, "bbox": [97.95, 134.25, 505.82, 284.17], "category_id": 24, "id": 588241, "split": "val", "sentences": [{"tokens": ["zebra", "with", "birds", "on", "its", "back"], "raw": "Zebra with birds on its back", "sent_id": 16211, "sent": "zebra with birds on its back"}, {"tokens": ["a", "zebra", "where", "more", "birds", "sit", "on", "its", "back"], "raw": "A zebra where more birds sit on its back", "sent_id": 16212, "sent": "a zebra where more birds sit on its back"}], "file_name": "COCO_train2014_000000073387_588241.jpg", "ann_id": 588241, "sent_ids": [16211, 16212], "ref_id": 11277}, {"segmentation": [[183.02, 180.84, 282.16, 240.76, 340.99, 289.78, 340.99, 308.3, 279.98, 279.98, 211.35, 244.03, 152.52, 204.81, 161.23, 177.57]], "area": 7054.825200000004, "iscrowd": 0, "image_id": 364803, "bbox": [152.52, 177.57, 188.47, 130.73], "category_id": 57, "id": 1065509, "split": "val", "sentences": [{"tokens": ["a", "small", "carrot", "that", "has", "a", "larger", "carrot", "to", "its", "left", "and", "onions", "to", "its", "right"], "raw": "A small carrot that has a larger carrot to its left and onions to its right.", "sent_id": 16268, "sent": "a small carrot that has a larger carrot to its left and onions to its right"}, {"tokens": ["two", "orange", "carrots", "in", "the", "center", "of", "some", "other", "vegetables"], "raw": "Two orange carrots in the center of some other vegetables.", "sent_id": 16269, "sent": "two orange carrots in the center of some other vegetables"}], "file_name": "COCO_train2014_000000364803_1065509.jpg", "ann_id": 1065509, "sent_ids": [16268, 16269], "ref_id": 11298}, {"segmentation": [[215.78, 537.62, 320.77, 526.11, 325.08, 518.92, 320.77, 514.6, 307.83, 514.6, 208.59, 521.8], [94.97, 566.38, 0.05, 580.76, 0.0, 575.01, 5.8, 560.63, 67.65, 549.12, 96.41, 553.44], [46.07, 527.55, 7.24, 540.49, 1.49, 537.62, 4.37, 524.67, 34.57, 504.54]], "area": 4230.351549999999, "iscrowd": 0, "image_id": 62759, "bbox": [0.0, 504.54, 325.08, 76.22], "category_id": 35, "id": 610240, "split": "val", "sentences": [{"tokens": ["the", "skis", "of", "the", "woman", "in", "white", "pants"], "raw": "The skis of the woman in white pants.", "sent_id": 16329, "sent": "the skis of the woman in white pants"}, {"tokens": ["womans", "skiis"], "raw": "womans skiis", "sent_id": 16330, "sent": "womans skiis"}], "file_name": "COCO_train2014_000000062759_610240.jpg", "ann_id": 610240, "sent_ids": [16329, 16330], "ref_id": 11323}, {"segmentation": [[195.03, 276.04, 201.64, 250.85, 210.73, 233.5, 219.81, 222.35, 235.1, 214.09, 252.86, 209.96, 275.98, 207.89, 293.33, 212.85, 309.03, 221.11, 306.13, 214.92, 316.46, 212.85, 328.44, 212.44, 337.11, 210.79, 343.31, 214.92, 363.54, 226.89, 375.52, 245.89, 388.74, 277.28, 387.91, 329.71, 380.48, 347.88, 378.41, 354.9, 389.56, 405.29, 379.65, 409.0, 358.59, 408.59, 339.18, 412.31, 336.7, 407.77, 331.74, 399.51, 323.48, 402.81, 324.31, 412.72, 315.63, 405.7, 308.2, 385.88, 300.76, 373.49, 293.33, 361.92, 286.31, 353.66, 261.53, 327.67, 245.83, 298.76, 234.68, 285.95, 222.29, 274.39, 205.77, 271.5, 197.92, 275.22], [362.72, 431.84, 385.02, 483.05, 412.69, 477.68, 397.41, 428.54, 361.89, 431.84], [387.5, 505.36, 387.91, 518.99, 385.02, 526.42, 387.5, 529.31, 408.15, 541.29, 425.08, 542.11, 441.19, 534.68, 442.43, 527.66, 436.23, 518.16, 429.63, 511.14, 423.02, 503.29], [340.83, 432.67, 338.76, 448.36, 336.7, 460.34, 335.87, 471.08, 335.46, 476.86, 336.28, 481.4, 345.78, 484.29, 364.37, 484.29, 365.2, 478.1, 362.72, 471.08, 360.24, 462.4, 359.0, 454.56, 357.76, 433.49], [329.26, 435.14, 331.33, 448.36, 335.87, 457.45, 336.7, 461.58, 336.7, 466.12, 334.63, 466.95, 328.44, 468.18, 317.29, 470.66, 322.24, 450.84, 322.24, 445.06, 322.24, 436.38]], "area": 29804.97530000001, "iscrowd": 0, "image_id": 457225, "bbox": [195.03, 207.89, 247.4, 334.22], "category_id": 22, "id": 585644, "split": "val", "sentences": [{"tokens": ["elephant", "in", "a", "fenced", "area", "behind", "a", "woman"], "raw": "Elephant in a fenced area behind a woman.", "sent_id": 16373, "sent": "elephant in a fenced area behind a woman"}, {"tokens": ["an", "elephant", "behind", "a", "woman", "wearing", "a", "lei"], "raw": "an elephant behind a woman wearing a lei", "sent_id": 16374, "sent": "an elephant behind a woman wearing a lei"}], "file_name": "COCO_train2014_000000457225_585644.jpg", "ann_id": 585644, "sent_ids": [16373, 16374], "ref_id": 11343}, {"segmentation": [[328.99, 70.38, 323.6, 83.33, 323.6, 88.72, 317.12, 87.64, 310.65, 86.56, 304.18, 91.96, 300.94, 97.35, 295.55, 87.64, 289.08, 87.64, 285.84, 97.35, 258.88, 89.8, 248.09, 91.96, 254.56, 105.98, 266.43, 108.13, 279.37, 114.61, 293.39, 116.76, 310.65, 111.37, 325.75, 112.45, 344.09, 120.0, 367.82, 124.31, 381.84, 124.31, 395.87, 125.39, 399.1, 127.55, 407.73, 124.31, 410.97, 124.31, 413.12, 126.47, 418.52, 129.71, 430.38, 129.71, 446.56, 117.84, 454.11, 102.74, 447.64, 91.96, 428.22, 69.3, 407.73, 69.3, 402.34, 66.07, 393.71, 59.6, 379.69, 56.36, 364.58, 57.44, 350.56, 59.6, 343.01, 57.44, 336.54, 52.04, 323.6, 43.42, 321.44, 43.42, 326.83, 60.67, 330.07, 69.3]], "area": 8980.922149999999, "iscrowd": 0, "image_id": 69231, "bbox": [248.09, 43.42, 206.02, 86.29], "category_id": 17, "id": 1402379, "split": "val", "sentences": [{"tokens": ["luxurious", "black", "cat", "snuggled", "on", "the", "white", "blanket"], "raw": "luxurious black cat snuggled on the white blanket", "sent_id": 16428, "sent": "luxurious black cat snuggled on the white blanket"}, {"tokens": ["the", "black", "cat", "only"], "raw": "The black cat only.", "sent_id": 16429, "sent": "the black cat only"}], "file_name": "COCO_train2014_000000069231_1402379.jpg", "ann_id": 1402379, "sent_ids": [16428, 16429], "ref_id": 11361}, {"segmentation": [[350.85, 179.3, 345.47, 214.82, 357.31, 266.48, 389.6, 301.99, 425.11, 324.59, 469.24, 345.04, 528.43, 350.42, 587.62, 324.59, 620.99, 284.77, 631.75, 229.88, 624.22, 186.83, 600.54, 149.17, 565.02, 119.03, 531.66, 100.74, 497.22, 89.97, 424.04, 93.2, 376.68, 124.41, 350.85, 165.31]], "area": 57505.3196, "iscrowd": 0, "image_id": 281464, "bbox": [345.47, 89.97, 286.28, 260.45], "category_id": 51, "id": 714852, "split": "val", "sentences": [{"tokens": ["a", "bowl", "right", "of", "another"], "raw": "A bowl right of another.", "sent_id": 16487, "sent": "a bowl right of another"}, {"tokens": ["a", "small", "white", "cup", "with", "black", "food", "with", "a", "face", "on", "it"], "raw": "A small white cup with black food with a face on it", "sent_id": 16488, "sent": "a small white cup with black food with a face on it"}], "file_name": "COCO_train2014_000000281464_714852.jpg", "ann_id": 714852, "sent_ids": [16487, 16488], "ref_id": 11382}, {"segmentation": [[216.8, 425.0, 240.67, 386.8, 271.24, 339.04, 284.61, 303.71, 287.47, 274.1, 284.61, 255.96, 255.96, 233.99, 231.12, 210.11, 229.21, 190.06, 136.57, 425.0, 215.84, 423.09], [120.34, 422.13, 215.84, 153.76, 209.16, 150.9, 189.1, 148.99, 162.36, 158.54, 151.85, 188.15, 150.9, 212.02, 157.58, 229.21, 157.58, 232.08, 135.62, 255.0, 121.29, 281.74, 104.1, 306.57, 99.33, 340.0, 84.04, 347.64, 43.93, 352.42, 35.34, 340.96, 24.83, 332.36, 9.55, 332.36, 0.0, 333.31, 0.0, 374.38, 23.88, 373.43, 33.43, 393.48, 51.57, 396.35, 76.4, 402.08, 92.64, 410.67, 105.06, 405.9, 129.89, 383.93, 146.12, 339.04, 210.11, 152.81]], "area": 33665.037000000004, "iscrowd": 0, "image_id": 54282, "bbox": [0.0, 148.99, 287.47, 276.01], "category_id": 1, "id": 443214, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "shirt"], "raw": "A man in a red shirt", "sent_id": 16524, "sent": "a man in a red shirt"}, {"tokens": ["man", "in", "red", "t", "-", "shirt"], "raw": "man in red t-shirt", "sent_id": 16525, "sent": "man in red t - shirt"}], "file_name": "COCO_train2014_000000054282_443214.jpg", "ann_id": 443214, "sent_ids": [16524, 16525], "ref_id": 11397}, {"segmentation": [[309.26, 370.74, 328.5, 364.13, 336.31, 346.09, 350.14, 341.28, 393.43, 334.67, 455.96, 339.48, 475.2, 371.94, 487.82, 399.0, 492.63, 463.93, 469.19, 463.93, 463.17, 468.14, 464.38, 475.95, 437.92, 478.36, 425.9, 471.14, 407.26, 473.55, 397.64, 478.36, 332.71, 479.56, 326.09, 464.53, 312.26, 460.32, 303.25, 465.13, 300.84, 461.53, 285.21, 430.26, 280.4, 417.03, 287.95, 406.66, 292.29, 404.74, 288.43, 402.81, 284.82, 401.61, 286.75, 392.22, 295.66, 392.22, 298.31, 395.59, 298.31, 396.31]], "area": 24284.19765, "iscrowd": 0, "image_id": 532744, "bbox": [280.4, 334.67, 212.23, 144.89], "category_id": 8, "id": 1371453, "split": "val", "sentences": [{"tokens": ["the", "red", "nissan", "pickup", "truck"], "raw": "The red Nissan pickup truck", "sent_id": 16532, "sent": "the red nissan pickup truck"}, {"tokens": ["a", "small", "orange", "nissan", "pick", "up", "truck", "in", "the", "traffic"], "raw": "A small orange Nissan pick up truck in the traffic.", "sent_id": 16533, "sent": "a small orange nissan pick up truck in the traffic"}], "file_name": "COCO_train2014_000000532744_1371453.jpg", "ann_id": 1371453, "sent_ids": [16532, 16533], "ref_id": 11401}, {"segmentation": [[0.97, 370.28, 17.38, 369.31, 20.28, 366.41, 31.86, 366.41, 32.83, 371.24, 97.52, 366.41, 104.28, 358.69, 132.28, 357.72, 144.83, 355.79, 172.83, 352.9, 178.62, 351.93, 173.79, 308.48, 173.79, 308.48, 166.07, 298.83, 158.34, 289.17, 163.17, 270.83, 163.17, 266.97, 170.9, 266.97, 174.76, 271.79, 173.79, 276.62, 186.34, 269.86, 190.21, 262.14, 181.52, 254.41, 173.79, 254.41, 162.21, 260.21, 159.31, 253.45, 168.0, 242.83, 151.59, 239.93, 141.93, 235.1, 129.38, 238.0, 119.72, 243.79, 109.1, 242.83, 116.83, 251.52, 114.9, 257.31, 100.41, 249.59, 89.79, 254.41, 85.93, 264.07, 89.79, 267.93, 100.41, 274.69, 112.97, 268.9, 116.83, 271.79, 116.83, 278.55, 88.83, 286.28, 55.03, 296.9, 39.59, 299.79, 28.97, 295.93, 14.48, 301.72, 4.83, 315.24, 0.97, 330.69, 0.97, 330.69, 1.93, 369.31]], "area": 15367.761950000002, "iscrowd": 0, "image_id": 416948, "bbox": [0.97, 235.1, 189.24, 136.14], "category_id": 21, "id": 71175, "split": "val", "sentences": [{"tokens": ["the", "cow", "sitting", "by", "itself"], "raw": "The cow sitting by itself.", "sent_id": 16536, "sent": "the cow sitting by itself"}, {"tokens": ["a", "cow", "that", "is", "resting", "seperately"], "raw": "A cow that is resting seperately", "sent_id": 16537, "sent": "a cow that is resting seperately"}], "file_name": "COCO_train2014_000000416948_71175.jpg", "ann_id": 71175, "sent_ids": [16536, 16537], "ref_id": 11403}, {"segmentation": [[199.73, 336.21, 209.4, 147.22, 312.48, 145.07, 382.28, 208.43, 377.99, 320.1, 316.78, 345.88, 194.36, 340.51, 194.36, 340.51]], "area": 31973.792799999996, "iscrowd": 0, "image_id": 125658, "bbox": [194.36, 145.07, 187.92, 200.81], "category_id": 6, "id": 164169, "split": "val", "sentences": [{"tokens": ["a", "two", "decker", "red", "bus", "is", "parked", "between", "two", "other", "buses"], "raw": "A two decker red bus is parked between two other buses", "sent_id": 16645, "sent": "a two decker red bus is parked between two other buses"}, {"tokens": ["a", "red", "bus", "in", "between", "2", "other", "red", "buses"], "raw": "A red bus in between 2 other red buses", "sent_id": 16646, "sent": "a red bus in between 2 other red buses"}], "file_name": "COCO_train2014_000000125658_164169.jpg", "ann_id": 164169, "sent_ids": [16645, 16646], "ref_id": 11447}, {"segmentation": [[127.9, 87.98, 79.85, 87.98, 68.76, 86.5, 56.93, 104.98, 51.01, 119.03, 67.28, 145.65, 70.98, 160.43, 54.71, 173.74, 59.15, 221.06, 53.97, 251.37, 79.85, 270.59, 128.64, 277.25, 147.13, 279.47, 165.61, 263.2, 199.62, 273.55, 226.97, 252.85, 217.36, 232.15, 233.63, 228.45, 229.19, 200.36, 213.67, 204.05, 140.47, 167.09, 144.17, 136.78, 156.74, 108.68, 142.69, 88.72]], "area": 22423.121199999994, "iscrowd": 0, "image_id": 102144, "bbox": [51.01, 86.5, 182.62, 192.97], "category_id": 88, "id": 1163421, "split": "val", "sentences": [{"tokens": ["the", "teddy", "bear", "on", "the", "end", "with", "a", "blue", "tie"], "raw": "The teddy bear on the end with a blue tie.", "sent_id": 16667, "sent": "the teddy bear on the end with a blue tie"}, {"tokens": ["a", "brown", "teddy", "bear", "with", "a", "blue", "bow"], "raw": "A brown teddy bear with a blue bow.", "sent_id": 16668, "sent": "a brown teddy bear with a blue bow"}], "file_name": "COCO_train2014_000000102144_1163421.jpg", "ann_id": 1163421, "sent_ids": [16667, 16668], "ref_id": 11455}, {"segmentation": [[53.81, 351.87, 258.3, 279.77, 312.11, 331.43, 256.14, 463.8, 242.15, 479.09, 90.4, 478.01, 58.12, 439.26, 37.67, 403.75], [460.63, 424.2, 433.72, 479.09, 568.25, 472.63, 464.93, 410.21], [312.11, 399.44, 322.87, 374.69, 345.47, 373.61, 345.47, 355.32, 363.77, 359.62, 362.69, 379.0, 360.54, 412.36, 341.17, 428.5], [297.04, 429.58, 273.36, 474.78, 315.34, 476.93, 329.33, 458.64]], "area": 45966.19084999999, "iscrowd": 0, "image_id": 152237, "bbox": [37.67, 279.77, 530.58, 199.32], "category_id": 65, "id": 317777, "split": "val", "sentences": [{"tokens": ["an", "orange", "sheet", "covered", "mattress", "sitting", "on", "the", "lower", "bunk", "of", "the", "bed"], "raw": "An orange sheet covered mattress sitting on the lower bunk of the bed.", "sent_id": 16713, "sent": "an orange sheet covered mattress sitting on the lower bunk of the bed"}, {"tokens": ["bed", "with", "orange", "sheets"], "raw": "bed with orange sheets", "sent_id": 16714, "sent": "bed with orange sheets"}], "file_name": "COCO_train2014_000000152237_317777.jpg", "ann_id": 317777, "sent_ids": [16713, 16714], "ref_id": 11474}, {"segmentation": [[96.21, 214.25, 156.44, 213.73, 160.6, 222.03, 159.56, 333.15, 160.6, 356.51, 123.73, 368.46, 120.1, 364.3, 126.85, 348.21, 125.81, 335.23, 135.16, 321.73, 136.19, 317.05, 123.73, 300.96, 110.75, 290.57, 108.68, 277.07, 106.6, 265.65, 110.75, 226.19, 107.12, 219.44, 98.81, 215.8], [0.0, 222.36, 33.59, 220.34, 27.11, 229.24, 24.69, 236.92, 23.47, 246.23, 22.26, 259.98, 25.5, 276.57, 25.5, 283.85, 16.19, 291.13, 4.86, 298.42, 0.0, 307.32]], "area": 8182.761649999997, "iscrowd": 0, "image_id": 220037, "bbox": [0.0, 213.73, 160.6, 154.73], "category_id": 15, "id": 2063568, "split": "val", "sentences": [{"tokens": ["the", "backing", "behind", "the", "girl", "in", "the", "white", "top"], "raw": "The backing behind the girl in the white top.", "sent_id": 16741, "sent": "the backing behind the girl in the white top"}, {"tokens": ["the", "back", "of", "the", "seat", "behind", "the", "long", "haired", "woman"], "raw": "The back of the seat behind the long haired woman", "sent_id": 16742, "sent": "the back of the seat behind the long haired woman"}], "file_name": "COCO_train2014_000000220037_2063568.jpg", "ann_id": 2063568, "sent_ids": [16741, 16742], "ref_id": 11484}, {"segmentation": [[32.95, 163.44, 49.42, 153.75, 62.98, 162.47, 55.23, 167.31, 60.08, 178.94, 67.83, 191.54, 75.58, 211.89, 83.33, 219.64, 98.84, 221.58, 97.87, 237.08, 87.21, 255.49, 83.33, 262.27, 75.58, 260.34, 69.77, 260.34, 63.95, 262.27, 52.33, 267.12, 37.79, 248.71, 25.19, 240.96, 9.69, 219.64, 0.0, 208.01, 0.0, 180.88, 15.5, 189.6, 31.01, 182.82, 36.82, 173.13, 31.01, 165.37]], "area": 5923.655950000002, "iscrowd": 0, "image_id": 63238, "bbox": [0.0, 153.75, 98.84, 113.37], "category_id": 54, "id": 1910718, "split": "val", "sentences": [{"tokens": ["a", "triangular", "finger", "sandwich", ",", "with", "only", "dark", "bread", ",", "pate", "and", "tomato"], "raw": "A triangular finger sandwich, with only dark bread, pate and tomato", "sent_id": 16823, "sent": "a triangular finger sandwich , with only dark bread , pate and tomato"}], "file_name": "COCO_train2014_000000063238_1910718.jpg", "ann_id": 1910718, "sent_ids": [16823], "ref_id": 11515}, {"segmentation": [[472.42, 156.82, 464.22, 149.53, 458.74, 143.14, 456.92, 122.16, 468.78, 103.01, 484.28, 100.28, 504.35, 102.1, 527.15, 99.36, 564.54, 99.36, 610.14, 96.63, 603.76, 104.84, 595.55, 114.87, 589.16, 123.08, 582.78, 133.11, 580.04, 137.67, 574.57, 148.61, 578.22, 175.06, 580.04, 196.95, 582.78, 215.19, 585.52, 232.52, 587.34, 254.41, 584.6, 263.53, 573.66, 260.79, 562.71, 253.5, 551.77, 246.2, 540.83, 243.46, 538.09, 256.23, 532.62, 262.62, 525.32, 280.86, 519.85, 311.86, 515.29, 313.69, 508.91, 306.39, 507.99, 291.8, 507.08, 276.3, 494.31, 277.21, 488.84, 281.77, 483.37, 285.42, 479.72, 288.15, 472.42, 284.5, 468.78, 258.06, 471.51, 245.29, 479.72, 237.99, 476.98, 221.57, 467.86, 201.51, 466.95, 177.8, 501.61, 174.15, 508.91, 165.94, 499.79, 155.0, 477.9, 156.82]], "area": 19248.920999999995, "iscrowd": 0, "image_id": 7601, "bbox": [456.92, 96.63, 153.22, 217.06], "category_id": 21, "id": 71589, "split": "val", "sentences": [{"tokens": ["a", "black", "cow", "that", "is", "only", "half", "visible", "standing", "close", "to", "a", "fully", "visible", "cow"], "raw": "A black cow that is only half visible standing close to a fully visible cow.", "sent_id": 16852, "sent": "a black cow that is only half visible standing close to a fully visible cow"}], "file_name": "COCO_train2014_000000007601_71589.jpg", "ann_id": 71589, "sent_ids": [16852], "ref_id": 11526}, {"segmentation": [[147.93, 96.21, 158.28, 75.52, 170.69, 28.97, 188.28, 12.41, 193.45, 12.41, 204.83, 31.03, 250.34, 55.86, 263.79, 51.72, 282.41, 47.59, 289.66, 47.59, 259.66, 83.79, 259.66, 94.14, 255.52, 125.17, 253.45, 132.41, 296.9, 141.72, 356.9, 161.38, 372.41, 162.41, 432.41, 193.45, 461.38, 215.17, 506.9, 253.45, 549.31, 347.59, 523.45, 445.86, 520.34, 466.55, 463.45, 456.21, 464.48, 423.1, 452.07, 364.14, 376.55, 312.41, 328.97, 291.72, 215.17, 317.59, 101.38, 316.55, 82.76, 315.52, 97.24, 296.9, 195.52, 297.93, 225.52, 300.0, 128.28, 272.07, 39.31, 256.55, 20.69, 270.0, 14.48, 264.83, 0.0, 258.62, 9.31, 229.66, 54.83, 224.48, 77.59, 223.45, 105.52, 197.59, 112.76, 174.83, 125.17, 145.86, 127.24, 134.48, 151.03, 82.76, 157.24, 57.93]], "area": 87385.65370000004, "iscrowd": 0, "image_id": 274853, "bbox": [0.0, 12.41, 549.31, 454.14], "category_id": 17, "id": 49538, "split": "val", "sentences": [{"tokens": ["a", "black", "cat", "lying", "on", "the", "white", "bed", "in", "front", "of", "another", "white", "cat", "sleeping", "beside"], "raw": "A black cat lying on the white bed in front of another white cat sleeping beside.", "sent_id": 16870, "sent": "a black cat lying on the white bed in front of another white cat sleeping beside"}, {"tokens": ["the", "black", "cat"], "raw": "the black cat", "sent_id": 16871, "sent": "the black cat"}], "file_name": "COCO_train2014_000000274853_49538.jpg", "ann_id": 49538, "sent_ids": [16870, 16871], "ref_id": 11535}, {"segmentation": [[367.82, 416.36, 402.34, 406.65, 391.55, 366.74, 349.48, 366.74, 337.62, 358.11, 337.62, 353.8, 355.96, 346.25, 355.96, 340.85, 339.78, 298.79, 312.81, 273.98, 324.67, 253.48, 334.38, 251.33, 345.17, 231.91, 339.78, 201.71, 317.12, 158.56, 316.04, 167.19, 317.12, 176.9, 307.42, 181.21, 303.1, 168.27, 285.84, 158.56, 273.98, 142.38, 270.74, 121.89, 291.24, 104.63, 307.42, 107.87, 328.99, 130.52, 354.88, 131.6, 388.31, 156.4, 423.91, 192.0, 436.85, 214.65, 437.93, 234.07, 414.2, 288.0, 400.18, 320.36, 414.2, 360.27, 422.83, 396.94, 430.38, 432.54, 399.1, 437.93, 375.37, 432.54, 363.51, 422.83]], "area": 23354.525200000007, "iscrowd": 0, "image_id": 124569, "bbox": [270.74, 104.63, 167.19, 333.3], "category_id": 1, "id": 421516, "split": "val", "sentences": [{"tokens": ["man", "in", "black", "clothes", "on", "a", "skateboard"], "raw": "Man in black clothes on a skateboard.", "sent_id": 16991, "sent": "man in black clothes on a skateboard"}, {"tokens": ["the", "man", "on", "the", "skateboard", "is", "wearing", "knee", "and", "elbow", "pads"], "raw": "The man on the skateboard is wearing knee and elbow pads.", "sent_id": 16992, "sent": "the man on the skateboard is wearing knee and elbow pads"}], "file_name": "COCO_train2014_000000124569_421516.jpg", "ann_id": 421516, "sent_ids": [16991, 16992], "ref_id": 11581}, {"segmentation": [[255.48, 470.4, 276.12, 470.4, 273.27, 456.88, 272.56, 432.68, 270.42, 414.89, 272.56, 392.83, 273.98, 372.19, 273.27, 347.29, 284.65, 370.06, 289.64, 397.81, 288.21, 426.99, 285.37, 446.2, 284.65, 459.73, 294.62, 465.42, 310.99, 462.57, 310.99, 446.92, 304.58, 423.43, 304.58, 399.24, 310.27, 428.41, 312.41, 413.47, 306.72, 368.63, 303.87, 342.3, 308.14, 362.94, 314.54, 424.14, 314.54, 438.38, 322.37, 456.88, 332.34, 443.36, 324.51, 419.87, 318.81, 380.02, 325.22, 339.46, 328.07, 313.13, 320.24, 282.53, 308.85, 256.91, 298.18, 243.39, 282.52, 220.61, 271.85, 209.94, 260.46, 200.69, 244.09, 233.42, 250.5, 247.66, 243.38, 278.97, 243.38, 302.45, 247.65, 328.78, 253.34, 342.3, 255.48, 350.84, 257.61, 383.58, 256.19, 399.24, 260.46, 405.64, 259.04, 425.57, 257.61, 435.53, 256.19, 444.78, 254.05, 464.0, 254.05, 470.4], [231.99, 197.29, 226.3, 170.96, 222.74, 170.25, 209.93, 173.09, 209.22, 160.29, 214.2, 151.03, 207.09, 147.48, 197.83, 138.22, 206.37, 136.09, 214.91, 138.22, 219.18, 119.72, 224.88, 119.72, 225.59, 126.84, 227.01, 128.97, 231.28, 124.7, 235.55, 117.59, 238.4, 121.14, 238.4, 135.38, 239.11, 139.65, 242.67, 136.09, 252.63, 130.4, 256.19, 132.53, 254.05, 141.07, 247.65, 140.36, 236.97, 141.07, 231.28, 144.63, 237.69, 149.61, 240.53, 152.46, 241.96, 161.71, 244.09, 175.23, 246.94, 176.65, 231.99, 199.43]], "area": 16589.51105, "iscrowd": 0, "image_id": 321766, "bbox": [197.83, 117.59, 134.51, 352.81], "category_id": 25, "id": 596331, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "to", "the", "right", "with", "its", "neck", "behind", "the", "giraffe", "on", "the", "left"], "raw": "A giraffe to the right with its neck behind the giraffe on the left.", "sent_id": 17088, "sent": "a giraffe to the right with its neck behind the giraffe on the left"}], "file_name": "COCO_train2014_000000321766_596331.jpg", "ann_id": 596331, "sent_ids": [17088], "ref_id": 11618}, {"segmentation": [[80.78, 472.5, 49.34, 472.06, 44.91, 470.73, 66.17, 444.61, 61.3, 431.77, 39.16, 399.45, 33.85, 386.17, 31.19, 399.01, 21.45, 394.14, 24.99, 375.1, 34.73, 375.1, 40.49, 370.23, 51.11, 371.55, 57.76, 378.2, 71.04, 370.67, 75.47, 364.91, 82.55, 356.5, 89.19, 356.94, 94.5, 364.03, 104.69, 372.0, 109.56, 387.05, 119.3, 383.51, 129.04, 383.51, 135.24, 386.61, 140.55, 392.36, 146.75, 397.68, 154.72, 403.43, 166.68, 407.86, 171.99, 410.07, 154.72, 414.95, 131.7, 421.59, 139.67, 427.79, 162.69, 430.88, 174.64, 438.85, 177.3, 445.5, 187.93, 458.78, 203.87, 461.44, 204.75, 471.62, 196.34, 472.95, 191.91, 463.21, 174.64, 446.38, 171.55, 445.05, 157.38, 445.05, 168.89, 453.47, 177.74, 471.62, 168.89, 472.5, 154.72, 449.92, 152.06, 456.57, 148.08, 460.99, 133.91, 456.12, 120.18, 464.98, 117.53, 472.95, 48.46, 472.5]], "area": 10364.835899999998, "iscrowd": 0, "image_id": 484369, "bbox": [21.45, 356.5, 183.3, 116.45], "category_id": 64, "id": 19096, "split": "val", "sentences": [{"tokens": ["grass", "and", "other", "vegetation", "below", "the", "blue", "doll", ",", "parts", "of", "the", "feet", "of", "the", "doll"], "raw": "Grass and other vegetation below the blue doll, parts of the feet of the doll.", "sent_id": 17093, "sent": "grass and other vegetation below the blue doll , parts of the feet of the doll"}], "file_name": "COCO_train2014_000000484369_19096.jpg", "ann_id": 19096, "sent_ids": [17093], "ref_id": 11620}, {"segmentation": [[234.41, 277.64, 249.68, 327.45, 253.7, 335.49, 253.7, 345.13, 247.27, 354.77, 235.22, 365.21, 232.0, 374.86, 219.15, 386.91, 219.15, 391.73, 236.02, 394.14, 245.66, 395.75, 258.52, 396.55, 261.73, 398.96, 248.88, 402.98, 233.61, 406.99, 223.97, 409.4, 218.34, 414.22, 216.74, 421.46, 209.51, 429.49, 204.69, 424.67, 202.28, 419.85, 195.04, 419.85, 191.83, 426.28, 191.83, 432.7, 187.81, 429.49, 182.99, 424.67, 174.96, 427.88, 138.0, 435.11, 106.67, 438.33, 99.44, 458.41, 102.65, 482.52, 109.88, 492.96, 121.93, 507.42, 170.14, 531.53, 190.22, 541.97, 197.46, 545.19, 198.26, 546.79, 176.57, 558.84, 166.12, 562.86, 151.66, 560.45, 133.18, 557.24, 107.47, 564.47, 97.02, 576.52, 96.22, 592.59, 105.06, 612.67, 119.52, 617.5, 129.16, 622.32, 143.62, 623.12, 160.5, 621.51, 183.8, 613.48, 182.19, 603.84, 186.21, 574.11, 191.03, 562.86, 195.04, 562.86, 195.85, 557.24, 197.46, 549.2, 204.69, 547.6, 209.51, 552.42, 222.36, 554.02, 225.58, 531.53, 227.18, 512.24, 238.43, 517.07, 251.29, 537.15, 289.05, 574.91, 293.06, 581.34, 298.69, 583.75, 315.56, 548.4, 336.45, 513.05, 345.29, 502.6, 351.72, 502.6, 354.13, 513.85, 355.73, 531.53, 427.0, 480.11, 427.0, 347.54, 424.83, 321.83, 426.44, 209.35, 399.12, 182.03, 392.69, 176.41, 401.53, 150.69, 399.92, 120.16, 393.49, 95.25, 369.39, 67.94, 341.27, 49.46, 323.6, 46.24, 304.31, 40.62, 281.82, 34.19, 264.94, 34.19, 244.86, 35.0, 230.4, 43.03, 208.7, 59.9, 203.88, 64.72, 187.01, 71.15, 173.35, 84.01, 170.14, 92.84, 166.12, 102.48, 163.71, 109.72, 158.89, 122.57, 156.48, 133.82, 154.87, 140.25, 152.46, 152.3, 161.3, 152.3, 165.32, 150.69, 165.32, 154.71, 154.07, 167.56, 151.66, 176.4, 150.05, 186.04, 154.87, 199.7, 172.55, 211.75, 180.58, 211.75, 191.03, 216.57, 207.1, 214.97, 215.93, 210.95, 216.74, 209.34, 217.54, 213.36, 212.72, 223.0, 207.9, 239.87, 206.29, 241.48, 203.88, 253.53, 208.7, 262.37, 222.36, 272.01, 230.4, 278.44], [354.93, 548.73, 359.75, 581.67, 403.94, 587.29, 418.4, 585.69, 411.97, 551.94, 403.94, 542.3, 395.1, 551.14, 384.66, 551.14, 374.21, 554.35, 361.36, 553.55, 358.14, 549.53, 350.91, 544.71]], "area": 119489.39369999999, "iscrowd": 0, "image_id": 101573, "bbox": [96.22, 34.19, 330.78, 588.93], "category_id": 1, "id": 507144, "split": "val", "sentences": [{"tokens": ["the", "woman", "sitting", "up", "holding", "the", "book"], "raw": "The woman sitting up holding the book.", "sent_id": 17115, "sent": "the woman sitting up holding the book"}, {"tokens": ["a", "woman", "with", "black", "curly", "hair", "and", "sandals", "sitting", "on", "the", "grass"], "raw": "A woman with black curly hair and sandals sitting on the grass", "sent_id": 17116, "sent": "a woman with black curly hair and sandals sitting on the grass"}], "file_name": "COCO_train2014_000000101573_507144.jpg", "ann_id": 507144, "sent_ids": [17115, 17116], "ref_id": 11631}, {"segmentation": [[337.88, 442.65, 335.67, 434.55, 298.87, 430.14, 270.91, 430.87, 264.28, 446.33, 247.35, 446.33, 238.52, 439.71, 237.05, 436.03, 235.58, 419.83, 223.8, 413.95, 228.95, 363.9, 250.3, 355.07, 288.57, 325.63, 305.5, 321.21, 324.63, 324.15, 322.43, 343.29, 327.58, 346.23, 331.99, 326.36, 345.98, 326.36, 345.24, 343.29]], "area": 11174.693850000001, "iscrowd": 0, "image_id": 301218, "bbox": [223.8, 321.21, 122.18, 125.12], "category_id": 3, "id": 346236, "split": "val", "sentences": [{"tokens": ["a", "silver", "audi", "car"], "raw": "a silver audi car", "sent_id": 17156, "sent": "a silver audi car"}, {"tokens": ["white", "car", "next", "to", "truck", "with", "mendon", "truck", "leasing", "mud", "flap"], "raw": "White car next to truck with Mendon Truck Leasing mud flap", "sent_id": 17157, "sent": "white car next to truck with mendon truck leasing mud flap"}], "file_name": "COCO_train2014_000000301218_346236.jpg", "ann_id": 346236, "sent_ids": [17156, 17157], "ref_id": 11646}, {"segmentation": [[518.19, 377.81, 453.16, 347.87, 459.35, 327.23, 449.03, 322.06, 433.55, 341.68, 384.0, 292.13, 387.1, 268.39, 379.87, 253.94, 384.0, 214.71, 391.23, 206.45, 414.97, 184.77, 458.32, 180.65, 488.26, 188.9, 527.48, 201.29, 546.06, 215.74, 598.71, 241.55, 621.42, 275.61, 640.0, 307.61, 640.0, 313.81, 614.19, 296.26, 616.26, 330.32, 603.87, 346.84, 596.65, 347.87, 585.29, 368.52, 561.55, 362.32, 550.19, 358.19]], "area": 33814.671050000004, "iscrowd": 0, "image_id": 397760, "bbox": [379.87, 180.65, 260.13, 197.16], "category_id": 20, "id": 65715, "split": "val", "sentences": [{"tokens": ["a", "black", "sheep", "lying", "down", "looking", "at", "the", "camera"], "raw": "A black sheep lying down looking at the camera.", "sent_id": 17177, "sent": "a black sheep lying down looking at the camera"}, {"tokens": ["an", "animal", "laying", "on", "the", "ground", "directly", "facing", "forward"], "raw": "An animal laying on the ground directly facing forward.", "sent_id": 17178, "sent": "an animal laying on the ground directly facing forward"}], "file_name": "COCO_train2014_000000397760_65715.jpg", "ann_id": 65715, "sent_ids": [17177, 17178], "ref_id": 11655}, {"segmentation": [[50.37, 349.39, 38.58, 332.24, 47.16, 314.02, 34.3, 301.16, 23.58, 271.15, 33.22, 273.3, 33.22, 263.65, 41.8, 261.51, 126.47, 161.83, 162.91, 132.9, 175.77, 135.04, 175.77, 175.77, 184.34, 224.0, 170.41, 367.61, 152.19, 375.11, 133.97, 369.75, 112.53, 370.83, 90.03, 363.32, 64.3, 360.11, 53.59, 354.75]], "area": 24803.099099999996, "iscrowd": 0, "image_id": 2411, "bbox": [23.58, 132.9, 160.76, 242.21], "category_id": 61, "id": 1089258, "split": "val", "sentences": [{"tokens": ["the", "white", "piece", "of", "cake"], "raw": "The white piece of cake", "sent_id": 17200, "sent": "the white piece of cake"}, {"tokens": ["the", "slice", "of", "cake", "on", "the", "left"], "raw": "The slice of cake on the left.", "sent_id": 17201, "sent": "the slice of cake on the left"}], "file_name": "COCO_train2014_000000002411_1089258.jpg", "ann_id": 1089258, "sent_ids": [17200, 17201], "ref_id": 11663}, {"segmentation": [[239.33, 330.11, 247.94, 312.88, 278.58, 312.88, 281.45, 283.2, 293.89, 231.51, 302.51, 225.76, 303.47, 209.49, 319.74, 199.92, 336.01, 210.45, 323.57, 228.64, 321.65, 264.06, 333.14, 257.36, 330.27, 271.71, 315.91, 279.37, 326.44, 321.49, 328.36, 346.38, 344.63, 350.21, 330.27, 356.91, 313.04, 355.96, 313.04, 313.84, 304.42, 302.35, 294.85, 322.45, 274.75, 323.41, 256.56, 326.28, 246.98, 336.81]], "area": 5183.788050000001, "iscrowd": 0, "image_id": 105200, "bbox": [239.33, 199.92, 105.3, 156.99], "category_id": 1, "id": 424796, "split": "val", "sentences": [{"tokens": ["blond", "soccer", "player", "in", "red", "uniform"], "raw": "blond soccer player in red uniform", "sent_id": 17207, "sent": "blond soccer player in red uniform"}], "file_name": "COCO_train2014_000000105200_424796.jpg", "ann_id": 424796, "sent_ids": [17207], "ref_id": 11667}, {"segmentation": [[372.59, 217.38, 301.52, 262.48, 295.64, 273.76, 290.25, 272.77, 288.28, 281.11, 293.19, 290.42, 290.25, 293.85, 289.26, 293.36, 289.26, 290.91, 282.89, 277.19, 266.23, 265.91, 248.09, 270.32, 246.13, 278.66, 241.72, 278.17, 208.88, 229.64, 205.44, 221.8, 211.33, 209.54, 263.78, 233.07, 277.99, 218.86, 285.83, 224.25, 339.26, 234.05, 352.01, 227.19, 353.48, 220.33, 360.83, 214.44, 373.08, 212.48, 373.08, 217.38], [356.42, 184.05, 361.81, 187.48, 355.44, 189.94, 350.54, 188.95, 344.16, 192.39, 344.16, 192.39, 342.69, 197.78, 339.26, 203.66, 333.87, 197.78, 353.48, 182.09, 353.48, 182.09]], "area": 5166.011699999999, "iscrowd": 0, "image_id": 141952, "bbox": [205.44, 182.09, 167.64, 111.76], "category_id": 62, "id": 379256, "split": "val", "sentences": [{"tokens": ["there", "is", "chair", "on", "which", "a", "man", "is", "resting"], "raw": "There is chair on which a man is resting", "sent_id": 17326, "sent": "there is chair on which a man is resting"}, {"tokens": ["a", "green", "chair", "seats", "a", "homeless", "man", "in", "a", "white", "hat"], "raw": "A green chair seats a homeless man in a white hat.", "sent_id": 17327, "sent": "a green chair seats a homeless man in a white hat"}], "file_name": "COCO_train2014_000000141952_379256.jpg", "ann_id": 379256, "sent_ids": [17326, 17327], "ref_id": 11714}, {"segmentation": [[155.19, 331.9, 155.19, 331.9, 151.24, 319.07, 128.54, 338.81, 116.7, 341.77, 100.91, 358.54, 88.08, 348.67, 77.22, 337.82, 84.13, 324.99, 94.0, 313.14, 106.83, 306.24, 112.75, 288.47, 119.66, 260.84, 130.52, 235.18, 134.47, 221.36, 133.48, 198.66, 130.52, 176.95, 130.52, 155.24, 133.48, 140.43, 146.31, 123.65, 200.59, 130.56, 212.43, 159.18, 210.46, 187.8, 204.54, 208.53, 251.91, 223.33, 243.03, 234.19, 226.25, 268.73, 189.73, 289.46, 189.73, 304.26, 166.05, 315.12, 157.17, 321.04, 162.1, 333.87, 190.72, 332.88, 220.33, 337.82, 230.2, 330.91, 237.11, 320.05, 244.02, 303.28, 244.02, 302.29, 247.96, 294.39, 260.79, 295.38, 265.73, 331.9, 276.58, 365.45, 276.58, 366.44, 272.64, 381.24, 255.86, 385.19, 257.83, 354.6, 235.13, 334.86, 215.39, 341.77, 175.92, 345.71, 159.14, 339.79, 149.27, 322.03, 149.27, 322.03]], "area": 21062.646200000003, "iscrowd": 0, "image_id": 340535, "bbox": [77.22, 123.65, 199.36, 261.54], "category_id": 1, "id": 563939, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "striped", "shirt", "and", "glasses", "sitting", "at", "a", "table", "next", "to", "a", "female"], "raw": "A man wearing a striped shirt and glasses sitting at a table next to a female.", "sent_id": 17348, "sent": "a man wearing a striped shirt and glasses sitting at a table next to a female"}, {"tokens": ["a", "man", "wearing", "a", "blue", "and", "white", "shirt"], "raw": "a man wearing a blue and white shirt", "sent_id": 17349, "sent": "a man wearing a blue and white shirt"}], "file_name": "COCO_train2014_000000340535_563939.jpg", "ann_id": 563939, "sent_ids": [17348, 17349], "ref_id": 11724}, {"segmentation": [[485.79, 233.41, 277.31, 131.34, 231.08, 124.37, 184.85, 94.71, 183.1, 65.92, 204.91, 54.58, 245.9, 66.79, 299.12, 117.39, 412.52, 186.3, 504.98, 229.92, 494.51, 243.01]], "area": 8526.207799999995, "iscrowd": 0, "image_id": 79111, "bbox": [183.1, 54.58, 321.88, 188.43], "category_id": 50, "id": 706687, "split": "val", "sentences": [{"tokens": ["a", "small", "spatula", "which", "is", "above", "all", "spatula"], "raw": "A small spatula which is above all spatula", "sent_id": 17402, "sent": "a small spatula which is above all spatula"}, {"tokens": ["smallest", "wooden", "spoon", "of", "the", "group"], "raw": "Smallest wooden spoon of the group.", "sent_id": 17403, "sent": "smallest wooden spoon of the group"}], "file_name": "COCO_train2014_000000079111_706687.jpg", "ann_id": 706687, "sent_ids": [17402, 17403], "ref_id": 11742}, {"segmentation": [[218.61, 319.38, 207.1, 309.31, 208.54, 286.3, 207.1, 185.62, 178.34, 182.75, 168.27, 164.05, 186.97, 145.35, 208.54, 141.04, 209.98, 119.47, 245.93, 109.4, 247.37, 89.26, 271.82, 84.95, 271.82, 99.33, 302.02, 107.96, 296.27, 128.1, 319.28, 133.85, 329.35, 149.67, 337.98, 178.43, 325.03, 185.62, 287.64, 195.69, 286.2, 292.05, 287.64, 328.01]], "area": 21443.2824, "iscrowd": 0, "image_id": 505546, "bbox": [168.27, 84.95, 169.71, 243.06], "category_id": 11, "id": 417847, "split": "val", "sentences": [{"tokens": ["a", "green", "fire", "hydrant", "with", "water", "coming", "out", "of", "it"], "raw": "A green fire hydrant with water coming out of it.", "sent_id": 17418, "sent": "a green fire hydrant with water coming out of it"}, {"tokens": ["green", "and", "white", "fire", "hydrant", "with", "water", "flowing", "out"], "raw": "Green and white fire hydrant with water flowing out.", "sent_id": 17419, "sent": "green and white fire hydrant with water flowing out"}], "file_name": "COCO_train2014_000000505546_417847.jpg", "ann_id": 417847, "sent_ids": [17418, 17419], "ref_id": 11749}, {"segmentation": [[279.82, 293.48, 279.0, 279.48, 281.05, 263.43, 275.7, 241.61, 254.71, 239.55, 245.65, 229.67, 255.12, 260.96, 256.76, 272.49, 261.29, 282.78, 262.53, 286.48, 262.53, 289.36, 255.53, 283.19, 252.24, 271.25, 248.12, 265.9, 248.94, 281.95, 251.41, 286.89, 250.59, 292.25, 244.41, 293.07, 242.77, 280.31, 244.83, 266.72, 246.06, 257.66, 242.77, 244.9, 240.71, 237.49, 237.0, 223.91, 235.77, 223.49, 223.42, 230.08, 193.78, 235.02, 195.84, 228.85, 195.84, 222.26, 178.96, 216.5, 173.19, 210.73, 188.84, 210.73, 230.0, 203.32, 231.65, 201.68, 243.59, 191.38, 268.29, 186.86, 279.0, 189.33, 292.99, 192.21, 301.23, 196.32, 304.93, 206.62, 315.22, 231.73, 316.87, 241.2, 324.28, 259.31, 323.87, 265.08, 323.46, 272.07, 320.16, 284.01, 320.99, 295.95, 321.81, 302.95, 315.64, 306.66, 305.75, 303.36, 298.76, 295.13, 298.76, 282.78, 298.34, 274.54, 297.93, 260.96, 292.99, 252.72, 285.99, 243.26, 288.05, 266.31, 288.46, 274.13, 287.23, 289.78, 285.58, 298.01, 283.11, 299.24, 281.05, 295.54, 280.64, 293.07]], "area": 7241.742550000001, "iscrowd": 0, "image_id": 330516, "bbox": [173.19, 186.86, 151.09, 119.8], "category_id": 19, "id": 59938, "split": "val", "sentences": [{"tokens": ["a", "brown", "horse", "bent", "over", "eating", "grass"], "raw": "A brown horse bent over eating grass.", "sent_id": 17478, "sent": "a brown horse bent over eating grass"}, {"tokens": ["the", "lighter", "colored", "pony", "eating", "grass"], "raw": "The lighter colored pony eating grass.", "sent_id": 17479, "sent": "the lighter colored pony eating grass"}], "file_name": "COCO_train2014_000000330516_59938.jpg", "ann_id": 59938, "sent_ids": [17478, 17479], "ref_id": 11774}, {"segmentation": [[285.77, 303.94, 272.62, 328.22, 264.52, 353.52, 261.49, 358.58, 252.38, 361.61, 233.16, 363.64, 213.93, 364.65, 203.81, 378.81, 194.71, 415.24, 194.71, 460.77, 213.93, 476.96, 245.3, 481.01, 290.83, 489.1, 336.36, 494.16, 372.79, 500.23, 391.0, 502.26, 393.03, 477.97, 395.05, 439.52, 395.05, 415.24, 386.96, 397.03, 362.67, 385.9, 343.45, 374.77, 331.31, 347.45, 318.15, 323.16, 306.01, 310.01, 297.92, 321.14, 309.05, 340.36, 311.07, 364.65, 294.88, 360.6, 289.82, 323.16, 287.8, 305.96]], "area": 25284.952350000007, "iscrowd": 0, "image_id": 48432, "bbox": [194.71, 303.94, 200.34, 198.32], "category_id": 31, "id": 1834458, "split": "val", "sentences": [{"tokens": ["the", "bag", "with", "the", "nike", "swoosh", "on", "it"], "raw": "The bag with the nike swoosh on it.", "sent_id": 17519, "sent": "the bag with the nike swoosh on it"}, {"tokens": ["bule", "bag", "in", "man", "hand"], "raw": "bule bag in man hand", "sent_id": 17520, "sent": "bule bag in man hand"}], "file_name": "COCO_train2014_000000048432_1834458.jpg", "ann_id": 1834458, "sent_ids": [17519, 17520], "ref_id": 11792}, {"segmentation": [[1.66, 41.56, 73.14, 34.91, 73.14, 84.78, 79.79, 154.6, 0.0, 161.25], [3.32, 310.86, 53.19, 320.83, 58.18, 458.81, 109.71, 473.77, 142.96, 470.44, 166.23, 450.49, 157.92, 322.49, 201.14, 309.19, 177.87, 403.95, 201.14, 452.16, 216.1, 470.44, 159.58, 482.08, 74.81, 492.05, 3.32, 518.65], [172.88, 142.96, 219.43, 121.35, 256.0, 128.0, 259.32, 177.87, 176.21, 146.29], [167.9, 124.68, 157.92, 86.44, 164.57, 54.86, 166.23, 41.56, 179.53, 4.99, 234.39, 4.99, 249.35, 19.95, 265.97, 28.26, 256.0, 39.9, 216.1, 28.26, 206.13, 28.26, 196.16, 43.22, 199.48, 58.18, 209.45, 71.48, 192.83, 103.06, 192.83, 128.0]], "area": 34286.86205000001, "iscrowd": 0, "image_id": 56032, "bbox": [0.0, 4.99, 265.97, 513.66], "category_id": 67, "id": 2194724, "split": "val", "sentences": [{"tokens": ["a", "table", "on", "which", "bottles", "and", "plates", "are", "placed"], "raw": "A table on which bottles and plates are placed", "sent_id": 17568, "sent": "a table on which bottles and plates are placed"}, {"tokens": ["a", "brown", "color", "dinning", "table"], "raw": "A brown color dinning table.", "sent_id": 17569, "sent": "a brown color dinning table"}], "file_name": "COCO_train2014_000000056032_2194724.jpg", "ann_id": 2194724, "sent_ids": [17568, 17569], "ref_id": 11812}, {"segmentation": [[19.56, 337.11, 26.46, 286.49, 10.36, 240.47, 4.6, 224.36, 1.15, 214.0, 1.15, 86.29, 12.66, 80.54, 5.75, 63.28, 1.15, 46.02, 5.75, 29.91, 13.81, 24.16, 27.61, 25.31, 35.67, 34.52, 39.12, 47.17, 39.12, 65.58, 39.12, 73.64, 42.57, 82.84, 58.68, 90.89, 71.33, 100.1, 79.39, 118.51, 110.45, 195.6, 109.3, 210.55, 104.7, 212.85, 94.35, 211.7, 89.74, 194.44, 89.74, 178.34, 62.13, 126.56, 66.73, 166.83, 69.03, 194.44, 64.43, 216.31, 57.53, 248.52, 54.08, 271.53, 72.49, 323.31, 75.94, 331.36, 59.83, 335.96, 48.32, 335.96, 46.02, 331.36, 50.62, 316.4, 48.32, 301.45, 29.91, 337.11, 24.16, 338.27]], "area": 17124.700099999995, "iscrowd": 0, "image_id": 68786, "bbox": [1.15, 24.16, 109.3, 314.11], "category_id": 1, "id": 225162, "split": "val", "sentences": [{"tokens": ["a", "woman", "walking", "by"], "raw": "A woman walking by.", "sent_id": 17608, "sent": "a woman walking by"}, {"tokens": ["the", "woman", "walking", "on", "the", "left"], "raw": "The woman walking on the left.", "sent_id": 17609, "sent": "the woman walking on the left"}], "file_name": "COCO_train2014_000000068786_225162.jpg", "ann_id": 225162, "sent_ids": [17608, 17609], "ref_id": 11829}, {"segmentation": [[304.12, 360.0, 302.77, 338.81, 217.31, 272.26, 217.31, 271.25, 213.59, 278.68, 211.9, 280.03, 213.93, 285.44, 214.27, 289.15, 212.24, 291.52, 214.27, 297.6, 215.95, 304.35, 212.91, 332.73, 213.25, 334.41, 217.64, 337.79, 215.95, 343.53, 214.27, 345.9, 216.29, 348.94, 214.6, 352.66, 211.23, 355.36, 206.5, 355.36, 204.13, 352.66, 205.15, 347.93, 203.46, 344.89, 200.42, 341.85, 200.42, 338.47, 202.11, 335.43, 200.75, 324.62, 196.36, 310.77, 196.7, 295.91, 199.4, 292.87, 195.35, 289.49, 196.36, 284.08, 197.71, 281.04, 193.66, 276.32, 190.62, 242.2, 181.16, 233.75, 181.84, 228.35, 289.59, 207.41, 291.96, 206.73, 297.02, 202.34, 306.14, 199.64, 307.16, 173.63, 312.56, 170.25, 324.72, 169.57, 332.15, 170.93, 336.88, 197.95, 349.04, 202.0, 352.76, 206.39, 356.47, 214.16, 357.83, 215.51, 357.83, 223.28, 355.46, 224.3, 355.8, 234.09, 457.47, 271.92, 456.8, 279.69, 441.94, 286.11, 440.92, 320.9, 433.49, 331.04, 435.52, 337.45, 432.14, 343.53, 434.84, 350.97, 434.84, 359.41, 413.9, 360.0, 412.89, 353.33, 414.57, 344.55, 415.93, 341.17, 413.22, 335.09, 416.26, 330.7, 410.86, 320.23, 411.2, 311.78, 341.61, 343.87, 342.29, 360.0]], "area": 26870.033800000005, "iscrowd": 0, "image_id": 547636, "bbox": [181.16, 169.57, 276.31, 190.43], "category_id": 67, "id": 1614309, "split": "val", "sentences": [{"tokens": ["the", "keg", "on", "the", "corner", "of", "the", "table"], "raw": "The keg on the corner of the table.", "sent_id": 17650, "sent": "the keg on the corner of the table"}, {"tokens": ["a", "table", "with", "a", "large", "jug", "of", "water", "on", "top"], "raw": "A table with a large jug of water on top.", "sent_id": 17651, "sent": "a table with a large jug of water on top"}], "file_name": "COCO_train2014_000000547636_1614309.jpg", "ann_id": 1614309, "sent_ids": [17650, 17651], "ref_id": 11845}, {"segmentation": [[435.78, 333.3, 392.63, 325.75, 348.4, 291.24, 295.55, 256.72, 284.76, 245.93, 288.0, 227.6, 310.65, 220.04, 354.88, 231.91, 400.18, 278.29, 440.09, 312.81]], "area": 7264.798050000004, "iscrowd": 0, "image_id": 421086, "bbox": [284.76, 220.04, 155.33, 113.26], "category_id": 59, "id": 1076790, "split": "val", "sentences": [{"tokens": ["the", "slice", "of", "pizza", "that", "is", "being", "lifted", "off", "of", "the", "sheet", "on", "the", "right"], "raw": "The slice of pizza that is being lifted off of the sheet on the right.", "sent_id": 17696, "sent": "the slice of pizza that is being lifted off of the sheet on the right"}, {"tokens": ["the", "pizza", "slice", "being", "held"], "raw": "The pizza slice being held", "sent_id": 17697, "sent": "the pizza slice being held"}], "file_name": "COCO_train2014_000000421086_1076790.jpg", "ann_id": 1076790, "sent_ids": [17696, 17697], "ref_id": 11864}, {"segmentation": [[555.33, 395.06, 557.48, 411.14, 560.69, 426.15, 559.62, 439.01, 558.55, 450.81, 552.12, 463.67, 547.83, 469.03, 534.96, 470.1, 521.03, 471.18, 499.59, 467.96, 481.36, 464.74, 474.93, 464.74, 468.5, 463.67, 464.21, 455.09, 464.21, 449.73, 459.92, 432.58, 457.77, 414.36, 462.06, 399.35, 464.21, 393.99, 459.92, 383.27, 455.63, 372.55, 445.98, 365.04, 438.48, 359.68, 450.27, 346.82, 457.77, 342.53, 436.33, 328.59, 429.9, 315.73, 427.76, 305.0, 465.28, 317.87, 473.86, 327.52, 501.73, 328.59, 521.03, 331.81, 537.11, 332.88, 553.19, 326.45, 563.91, 325.37, 567.13, 323.23, 567.13, 340.38, 552.12, 345.74, 547.83, 359.68, 549.97, 383.27, 557.48, 393.99, 562.84, 400.42]], "area": 14385.657950000006, "iscrowd": 0, "image_id": 61951, "bbox": [427.76, 305.0, 139.37, 166.18], "category_id": 4, "id": 150911, "split": "val", "sentences": [{"tokens": ["a", "red", "moterscooter"], "raw": "A red moterscooter", "sent_id": 17732, "sent": "a red moterscooter"}, {"tokens": ["red", "scooter"], "raw": "Red scooter.", "sent_id": 17733, "sent": "red scooter"}], "file_name": "COCO_train2014_000000061951_150911.jpg", "ann_id": 150911, "sent_ids": [17732, 17733], "ref_id": 11879}, {"segmentation": [[249.46, 258.44, 239.48, 251.46, 238.49, 246.47, 234.49, 236.49, 231.5, 224.52, 231.5, 208.55, 231.5, 188.59, 230.5, 171.63, 223.52, 152.67, 223.52, 129.72, 216.53, 97.79, 214.54, 70.85, 224.52, 63.86, 226.51, 74.84, 233.5, 83.82, 236.49, 94.8, 240.48, 96.79, 255.45, 89.81, 259.44, 87.81, 265.43, 72.84, 274.41, 72.84, 282.39, 84.82, 283.39, 104.77, 287.38, 120.74, 289.38, 127.72, 289.38, 149.68, 289.38, 153.67, 370.2, 149.68, 390.16, 146.68, 401.14, 145.69, 446.04, 179.61, 446.04, 201.57, 452.03, 214.54, 449.03, 240.48, 445.04, 255.45, 445.04, 264.43, 445.04, 277.4, 445.04, 295.36, 443.05, 307.34, 439.05, 323.3, 437.06, 342.26, 438.06, 358.23, 450.03, 442.05, 448.03, 454.02, 448.03, 456.02, 437.06, 457.02, 431.07, 455.02, 421.09, 449.03, 416.1, 433.07, 416.1, 408.12, 422.09, 382.18, 423.09, 367.21, 421.09, 351.24, 421.09, 326.3, 418.1, 314.32, 413.11, 309.33, 392.15, 302.35, 391.16, 305.34, 390.16, 322.31, 396.15, 342.26, 396.15, 356.23, 397.14, 366.21, 399.14, 380.18, 402.13, 399.14, 401.14, 416.1, 399.14, 434.06, 398.14, 439.05, 391.16, 450.03, 382.18, 450.03, 379.18, 440.05, 375.19, 429.08, 380.18, 397.14, 382.18, 368.21, 379.18, 342.26, 376.19, 331.29, 372.2, 321.31, 368.21, 346.25, 368.21, 368.21, 365.21, 387.17, 364.22, 404.13, 364.22, 423.09, 370.2, 435.06, 372.2, 447.04, 372.2, 455.02, 372.2, 458.01, 369.2, 458.01, 352.24, 450.03, 348.25, 446.04, 348.25, 432.07, 348.25, 402.13, 348.25, 388.16, 343.26, 365.21, 338.27, 342.26, 334.28, 324.3, 321.31, 320.31, 304.34, 326.3, 304.34, 346.25, 308.34, 375.19, 308.34, 390.16, 308.34, 417.1, 309.33, 434.06, 314.32, 455.02, 281.39, 453.02, 281.39, 445.04, 286.38, 414.11, 288.38, 398.14, 288.38, 383.17, 278.4, 353.24, 270.42, 326.3, 264.43, 303.35]], "area": 50439.511749999976, "iscrowd": 0, "image_id": 113676, "bbox": [214.54, 63.86, 237.49, 394.15], "category_id": 19, "id": 56468, "split": "val", "sentences": [{"tokens": ["horse", "closer", "to", "the", "camera"], "raw": "Horse closer to the camera", "sent_id": 17756, "sent": "horse closer to the camera"}, {"tokens": ["horse", "in", "left", "pulling", "position"], "raw": "horse in left pulling position", "sent_id": 17757, "sent": "horse in left pulling position"}], "file_name": "COCO_train2014_000000113676_56468.jpg", "ann_id": 56468, "sent_ids": [17756, 17757], "ref_id": 11886}, {"segmentation": [[336.15, 267.62, 330.38, 264.73, 322.44, 254.64, 318.11, 233.72, 316.67, 217.13, 327.49, 133.45, 340.48, 103.15, 381.59, 86.56, 377.27, 56.99, 377.99, 46.17, 378.71, 43.28, 383.76, 37.51, 388.81, 35.35, 405.4, 36.07, 417.66, 42.56, 419.82, 54.1, 419.82, 66.36, 420.55, 71.41, 421.27, 77.18, 420.55, 80.79, 415.5, 85.12, 449.4, 106.76, 465.27, 129.12, 484.75, 199.81, 491.24, 243.09, 474.65, 244.54, 470.32, 230.83, 465.99, 215.68, 462.38, 225.78, 471.76, 258.24, 473.93, 271.95, 446.51, 268.34, 446.51, 268.34, 438.58, 317.39, 359.95, 316.67, 351.3, 310.18, 354.18, 295.03, 355.62, 284.93, 354.9, 278.44, 354.18, 276.28, 352.02, 271.95, 342.64, 266.9, 338.31, 265.46]], "area": 32249.98215, "iscrowd": 0, "image_id": 542442, "bbox": [316.67, 35.35, 174.57, 282.04], "category_id": 1, "id": 232026, "split": "val", "sentences": [{"tokens": ["man", "with", "a", "suit", "walking", "with", "his", "friends", "smoking", "a", "cigar"], "raw": "Man with a suit walking with his friends smoking a cigar.", "sent_id": 17779, "sent": "man with a suit walking with his friends smoking a cigar"}, {"tokens": ["a", "man", "in", "a", "light", "blue", "shirt", "and", "sunglasses"], "raw": "A man in a light blue shirt and sunglasses.", "sent_id": 17780, "sent": "a man in a light blue shirt and sunglasses"}], "file_name": "COCO_train2014_000000542442_232026.jpg", "ann_id": 232026, "sent_ids": [17779, 17780], "ref_id": 11895}, {"segmentation": [[174.64, 137.88, 224.53, 109.1, 287.87, 115.81, 355.99, 108.14, 409.73, 109.1, 455.79, 132.12, 453.87, 135.0, 425.08, 135.96, 396.29, 138.84, 383.82, 122.53, 379.02, 132.12, 366.55, 136.92, 357.91, 128.29, 342.56, 146.52, 332.96, 139.8, 322.41, 121.57, 309.93, 137.88, 288.82, 145.56, 260.04, 146.52, 223.58, 158.03, 189.03, 163.79, 166.0, 186.82, 136.26, 215.61, 128.58, 233.84, 95.96, 233.84, 125.7, 193.54], [109.39, 242.47, 101.71, 260.7, 108.43, 311.56, 110.35, 324.03, 126.66, 324.03, 126.66, 301.01, 122.82, 272.22, 127.62, 259.74], [220.7, 262.62, 221.66, 281.81, 224.53, 312.52, 224.53, 331.71, 237.01, 338.43, 242.77, 315.4, 245.64, 360.5, 262.92, 355.7, 256.2, 303.88, 254.28, 269.34, 252.36, 254.95, 223.58, 256.87], [394.38, 313.48, 369.43, 353.78, 365.59, 372.01, 384.78, 370.09, 409.73, 322.12, 397.25, 317.32]], "area": 16150.909450000005, "iscrowd": 0, "image_id": 73387, "bbox": [95.96, 108.14, 359.83, 263.87], "category_id": 24, "id": 589374, "split": "val", "sentences": [{"tokens": ["the", "zebra", "behind", "another", "zebra"], "raw": "The zebra behind another zebra", "sent_id": 17824, "sent": "the zebra behind another zebra"}, {"tokens": ["two", "zeebras", "having", "their", "food", "on", "the", "field"], "raw": "Two Zeebras having their food on the field", "sent_id": 17825, "sent": "two zeebras having their food on the field"}], "file_name": "COCO_train2014_000000073387_589374.jpg", "ann_id": 589374, "sent_ids": [17824, 17825], "ref_id": 11911}, {"segmentation": [[440.29, 340.08, 438.36, 343.39, 434.22, 343.11, 438.36, 359.68, 446.37, 374.6, 449.96, 373.49, 451.89, 379.29, 438.64, 382.06, 432.56, 382.06, 433.11, 379.29, 428.69, 378.19, 432.56, 372.67, 421.24, 354.71, 416.27, 351.12, 415.71, 344.77, 405.77, 341.73, 408.81, 330.96, 413.5, 313.84, 417.65, 303.62, 420.69, 290.36, 422.07, 283.18, 408.26, 283.74, 391.96, 277.11, 385.89, 275.73, 384.78, 268.55, 382.57, 266.61, 377.6, 267.72, 377.05, 265.78, 377.6, 264.4, 382.02, 262.47, 385.06, 261.64, 394.72, 267.99, 405.77, 270.2, 404.67, 258.33, 402.73, 253.36, 404.11, 243.41, 405.77, 240.38, 406.6, 238.99, 405.86, 238.55, 395.2, 238.25, 392.98, 235.0, 391.95, 230.26, 391.36, 228.63, 391.65, 223.9, 390.91, 221.97, 390.32, 221.09, 390.32, 219.31, 381.88, 218.13, 378.63, 216.2, 379.66, 214.28, 385.14, 215.17, 390.62, 215.46, 393.58, 207.62, 395.5, 205.4, 398.61, 203.18, 404.68, 201.4, 408.08, 200.66, 409.71, 201.85, 414.44, 203.62, 418.59, 208.06, 420.07, 215.91, 420.96, 217.39, 420.22, 218.42, 420.36, 221.53, 422.58, 222.42, 422.29, 223.31, 423.18, 225.08, 421.25, 227.6, 421.4, 228.63, 426.88, 229.37, 431.61, 230.26, 446.56, 236.33, 452.92, 238.55, 460.03, 242.99, 463.43, 263.86, 463.88, 270.22, 465.5, 274.07, 465.36, 277.18, 468.02, 280.29, 470.68, 283.84, 471.72, 285.61, 466.1, 294.35, 461.8, 295.38, 460.92, 294.35, 460.18, 298.64, 458.7, 312.7, 454.7, 313.14, 452.04, 318.91, 451.74, 320.39, 455.29, 318.03, 460.77, 314.18, 473.35, 309.74, 474.24, 309.89, 477.64, 313.88, 477.2, 315.21, 477.79, 315.66, 479.27, 324.39, 480.3, 328.68, 480.16, 340.97, 478.68, 349.4, 474.38, 353.7, 473.35, 354.44, 472.76, 354.44, 470.24, 351.92, 468.91, 350.29, 467.58, 342.74, 466.39, 341.56, 458.84, 332.09, 457.51, 335.49, 456.92, 335.49, 456.33, 335.34, 455.44, 331.94, 446.41, 334.9, 440.79, 338.45]], "area": 8034.685250000004, "iscrowd": 0, "image_id": 369961, "bbox": [377.05, 200.66, 103.25, 181.4], "category_id": 1, "id": 497508, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "a", "yellow", "t", "-", "shirt", "runs", "with", "a", "frisbee", "in", "a", "farm", "'", "s", "empty", "field"], "raw": "A boy in a yellow t-shirt runs with a frisbee in a farm's empty field.", "sent_id": 17878, "sent": "a boy in a yellow t - shirt runs with a frisbee in a farm ' s empty field"}, {"tokens": ["a", "boy", "wearing", "a", "yellow", "shirt"], "raw": "A boy wearing a yellow shirt.", "sent_id": 17879, "sent": "a boy wearing a yellow shirt"}], "file_name": "COCO_train2014_000000369961_497508.jpg", "ann_id": 497508, "sent_ids": [17878, 17879], "ref_id": 11928}, {"segmentation": [[6.85, 339.93, 26.24, 307.13, 57.55, 304.14, 81.4, 275.82, 138.06, 257.92, 144.02, 251.96, 141.04, 201.27, 144.02, 171.45, 167.87, 150.58, 193.22, 150.58, 211.11, 161.01, 227.51, 208.72, 227.51, 234.07, 212.6, 250.47, 223.04, 265.38, 237.95, 272.83, 234.97, 310.11, 234.97, 332.47, 230.49, 366.76, 203.66, 390.62, 206.64, 421.93, 203.66, 442.8, 163.4, 444.29, 138.06, 454.73, 112.71, 469.64, 102.27, 502.44, 91.84, 548.66, 21.76, 550.15, 85.87, 442.8, 0.0, 468.15]], "area": 51361.695649999994, "iscrowd": 0, "image_id": 427301, "bbox": [0.0, 150.58, 237.95, 399.57], "category_id": 1, "id": 213085, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "blue", "jeans"], "raw": "a man wearing blue jeans", "sent_id": 17959, "sent": "a man wearing blue jeans"}, {"tokens": ["the", "guy", "on", "the", "left", "making", "sarcastic", "and", "funny", "faces", "for", "the", "photo"], "raw": "The guy on the left making sarcastic and funny faces for the photo.", "sent_id": 17960, "sent": "the guy on the left making sarcastic and funny faces for the photo"}], "file_name": "COCO_train2014_000000427301_213085.jpg", "ann_id": 213085, "sent_ids": [17959, 17960], "ref_id": 11957}, {"segmentation": [[117.67, 324.25, 119.94, 287.03, 114.95, 281.13, 101.33, 279.77, 93.62, 288.39, 75.01, 292.48, 68.65, 298.38, 56.85, 288.84, 49.14, 268.87, 51.86, 261.16, 64.57, 267.96, 69.11, 275.68, 70.92, 278.86, 67.75, 287.48, 83.63, 286.57, 90.89, 282.94, 83.18, 271.6, 80.45, 267.06, 84.09, 257.53, 91.8, 254.35, 98.16, 254.35, 108.14, 259.34, 106.78, 270.23, 113.59, 277.04, 128.57, 273.87, 133.11, 280.67, 148.54, 297.47, 143.55, 305.18, 138.1, 305.64, 147.18, 316.08, 154.44, 324.25, 181.67, 338.32, 188.48, 352.84, 190.75, 361.47, 211.63, 386.89, 205.73, 392.33, 180.77, 378.72, 180.77, 372.81, 169.87, 351.94, 145.82, 343.77, 131.75, 347.4, 130.38, 348.76, 134.01, 364.19, 130.84, 367.37, 122.21, 374.18, 118.13, 369.64, 113.59, 364.64, 117.67, 359.65, 102.24, 343.77, 117.22, 329.69]], "area": 5107.596399999998, "iscrowd": 0, "image_id": 25455, "bbox": [49.14, 254.35, 162.49, 137.98], "category_id": 1, "id": 501158, "split": "val", "sentences": [{"tokens": ["the", "man", "catching", "the", "ball", "on", "home", "base"], "raw": "the man catching the ball on home base", "sent_id": 17977, "sent": "the man catching the ball on home base"}, {"tokens": ["catcher", "and", "umpire"], "raw": "catcher and umpire", "sent_id": 17978, "sent": "catcher and umpire"}], "file_name": "COCO_train2014_000000025455_501158.jpg", "ann_id": 501158, "sent_ids": [17977, 17978], "ref_id": 11963}, {"segmentation": [[377.77, 303.09, 376.63, 359.11, 393.78, 387.69, 401.78, 402.56, 388.06, 416.28, 386.92, 430.0, 406.35, 457.44, 426.93, 476.87, 426.93, 476.87, 473.81, 472.3, 480.67, 462.01, 481.0, 431.14, 471.52, 410.56, 479.53, 401.41, 481.0, 281.37, 479.53, 275.65, 439.51, 267.65, 428.08, 272.22, 439.51, 298.52, 442.94, 329.39, 442.94, 339.68, 433.79, 340.82, 423.5, 335.1, 415.5, 298.52, 424.65, 276.79, 405.21, 273.36, 381.2, 296.23]], "area": 16953.879100000002, "iscrowd": 0, "image_id": 183392, "bbox": [376.63, 267.65, 104.37, 209.22], "category_id": 47, "id": 1878106, "split": "val", "sentences": [{"tokens": ["the", "whie", "egg", "holder", "on", "the", "white", "plate", "with", "water", "in", "it"], "raw": "The whie egg holder on the white plate with water in it.", "sent_id": 18005, "sent": "the whie egg holder on the white plate with water in it"}, {"tokens": ["white", "cup", "with", "red", "pepper"], "raw": "White cup with red pepper.", "sent_id": 18006, "sent": "white cup with red pepper"}], "file_name": "COCO_train2014_000000183392_1878106.jpg", "ann_id": 1878106, "sent_ids": [18005, 18006], "ref_id": 11972}, {"segmentation": [[307.26, 254.26, 340.7, 235.78, 389.98, 196.18, 416.38, 186.5, 443.66, 183.86, 474.46, 193.54, 492.94, 206.74, 485.02, 222.58, 474.46, 234.9, 409.34, 263.06, 338.06, 307.06, 325.74, 282.42, 304.62, 275.38, 307.26, 256.02]], "area": 11017.776, "iscrowd": 0, "image_id": 294080, "bbox": [304.62, 183.86, 188.32, 123.2], "category_id": 57, "id": 1064896, "split": "val", "sentences": [{"tokens": ["a", "glazed", "carrot", "with", "a", "green", "leaf", "on", "top", "of", "it"], "raw": "A glazed carrot with a green leaf on top of it.", "sent_id": 18031, "sent": "a glazed carrot with a green leaf on top of it"}, {"tokens": ["a", "piece", "of", "carrot", "served", "in", "a", "bowl", "of", "beef", "stew"], "raw": "a piece of carrot served in a bowl of beef stew", "sent_id": 18032, "sent": "a piece of carrot served in a bowl of beef stew"}], "file_name": "COCO_train2014_000000294080_1064896.jpg", "ann_id": 1064896, "sent_ids": [18031, 18032], "ref_id": 11982}, {"segmentation": [[301.27, 195.25, 302.23, 156.87, 297.43, 112.74, 302.23, 82.03, 312.78, 67.64, 302.23, 58.05, 305.11, 45.57, 297.43, 43.66, 300.31, 33.1, 296.47, 20.63, 323.34, 10.07, 331.01, 35.02, 341.57, 46.53, 355.96, 80.11, 358.84, 136.72, 355.96, 156.87, 346.36, 165.51, 339.65, 181.82, 325.26, 193.33], [331.01, 234.59, 368.43, 272.97, 381.86, 267.21, 378.03, 262.41, 353.08, 235.55, 344.45, 214.44, 329.09, 225.95]], "area": 9342.199299999995, "iscrowd": 0, "image_id": 176229, "bbox": [296.47, 10.07, 85.39, 262.9], "category_id": 1, "id": 259030, "split": "val", "sentences": [{"tokens": ["a", "man", "wear", "gray", "jacket", "walking", "in", "the", "park"], "raw": "A man wear gray jacket walking in the park", "sent_id": 18128, "sent": "a man wear gray jacket walking in the park"}, {"tokens": ["a", "man", "and", "a", "woman", "are", "walking", "on", "the", "walkway"], "raw": "A MAN AND A WOMAN ARE WALKING ON THE WALKWAY", "sent_id": 18129, "sent": "a man and a woman are walking on the walkway"}], "file_name": "COCO_train2014_000000176229_259030.jpg", "ann_id": 259030, "sent_ids": [18128, 18129], "ref_id": 12022}, {"segmentation": [[48.62, 227.36, 84.56, 210.45, 130.01, 204.11, 205.06, 230.53, 239.94, 265.41, 255.79, 302.41, 240.99, 338.34, 189.2, 370.05, 108.87, 373.22, 69.76, 356.31, 60.25, 328.83, 42.28, 330.95, 9.51, 305.58, 31.71, 259.07]], "area": 29692.480349999994, "iscrowd": 0, "image_id": 158686, "bbox": [9.51, 204.11, 246.28, 169.11], "category_id": 56, "id": 1914929, "split": "val", "sentences": [{"tokens": ["fresh", "kale", "on", "wooden", "tray", "with", "other", "veggies"], "raw": "fresh kale  on wooden tray with other veggies", "sent_id": 18170, "sent": "fresh kale on wooden tray with other veggies"}, {"tokens": ["leafy", "green", "vegetable", "to", "the", "left", "of", "the", "yams", "and", "just", "below", "the", "broccolli"], "raw": "leafy green vegetable to the left of the yams and just below the broccolli.", "sent_id": 18171, "sent": "leafy green vegetable to the left of the yams and just below the broccolli"}], "file_name": "COCO_train2014_000000158686_1914929.jpg", "ann_id": 1914929, "sent_ids": [18170, 18171], "ref_id": 12037}, {"segmentation": [[183.78, 203.78, 178.38, 188.65, 175.14, 180.0, 163.24, 175.68, 148.11, 175.68, 141.62, 176.76, 137.3, 170.27, 136.22, 162.7, 140.54, 159.46, 140.54, 151.89, 143.78, 145.41, 152.43, 138.92, 161.08, 132.43, 162.16, 122.7, 155.68, 120.54, 148.11, 119.46, 145.95, 110.81, 138.38, 107.57, 130.81, 105.41, 115.68, 91.35, 110.27, 81.62, 114.59, 68.65, 121.08, 58.92, 123.24, 50.27, 135.14, 48.11, 153.51, 53.51, 163.24, 53.51, 178.38, 45.95, 182.7, 41.62, 178.38, 26.49, 180.54, 18.92, 185.95, 10.27, 200.0, 0.54, 289.73, 3.78, 276.76, 26.49, 267.03, 39.46, 268.11, 49.19, 271.35, 54.59, 271.35, 62.16, 265.95, 67.57, 262.7, 71.89, 254.05, 76.22, 248.65, 82.7, 241.08, 87.03, 241.08, 90.27, 241.08, 109.73, 240.0, 119.46, 240.0, 125.95, 241.08, 131.35, 241.08, 141.08, 243.24, 147.57, 243.24, 149.73, 236.76, 155.14, 225.95, 158.38, 223.78, 161.62, 219.46, 167.03, 219.46, 183.24, 219.46, 185.41, 190.27, 195.14]], "area": 19082.550449999995, "iscrowd": 0, "image_id": 513683, "bbox": [110.27, 0.54, 179.46, 203.24], "category_id": 64, "id": 292543, "split": "val", "sentences": [{"tokens": ["plant", "inside", "the", "home"], "raw": "plant inside the home", "sent_id": 18184, "sent": "plant inside the home"}, {"tokens": ["a", "large", "leafy", "plant", "behind", "the", "man", "in", "the", "blue", "shirt"], "raw": "A large leafy plant behind the man in the blue shirt.", "sent_id": 18185, "sent": "a large leafy plant behind the man in the blue shirt"}], "file_name": "COCO_train2014_000000513683_292543.jpg", "ann_id": 292543, "sent_ids": [18184, 18185], "ref_id": 12043}, {"segmentation": [[355.4, 2.98, 368.4, 48.49, 437.74, 45.24, 469.16, 61.49, 481.08, 76.66, 499.5, 70.16, 580.77, 142.75, 640.0, 178.51, 637.87, 5.07]], "area": 24269.746900000006, "iscrowd": 0, "image_id": 568840, "bbox": [355.4, 2.98, 284.6, 175.53], "category_id": 67, "id": 414081, "split": "val", "sentences": [{"tokens": ["the", "part", "of", "the", "table", "in", "the", "top", "right", "corner"], "raw": "The part of the table in the top right corner.", "sent_id": 18232, "sent": "the part of the table in the top right corner"}], "file_name": "COCO_train2014_000000568840_414081.jpg", "ann_id": 414081, "sent_ids": [18232], "ref_id": 12062}, {"segmentation": [[44.99, 320.7, 36.38, 311.12, 55.52, 242.2, 68.93, 224.01, 69.88, 211.56, 95.73, 154.13, 115.83, 132.11, 94.77, 102.43, 90.94, 76.58, 98.6, 57.44, 108.18, 37.33, 130.19, 30.63, 153.17, 31.59, 183.8, 39.25, 204.86, 60.31, 207.73, 84.24, 203.91, 95.73, 213.48, 117.75, 208.69, 134.98, 211.56, 143.6, 238.37, 125.41, 241.24, 112.96, 236.45, 99.56, 241.24, 77.54, 243.16, 71.8, 250.81, 90.94, 261.34, 89.03, 268.04, 98.6, 268.04, 107.22, 269.96, 117.75, 269.96, 126.36, 264.22, 134.98, 257.51, 143.6, 246.98, 156.04, 240.28, 164.66, 231.67, 176.14, 225.92, 188.59, 223.05, 202.95, 219.22, 205.82, 202.95, 201.99, 181.89, 251.77, 157.0, 284.32, 161.78, 297.72, 126.36, 302.51, 188.59, 335.06, 206.78, 321.65, 229.75, 329.31, 228.8, 337.93, 248.9, 348.46, 248.9, 358.03, 242.2, 363.78, 222.09, 363.78, 193.38, 364.73, 117.75, 335.06, 96.69, 321.65, 65.1, 326.44, 55.52, 328.36, 43.08, 321.65]], "area": 40343.72435000001, "iscrowd": 0, "image_id": 236961, "bbox": [36.38, 30.63, 233.58, 334.1], "category_id": 1, "id": 195669, "split": "val", "sentences": [{"tokens": ["the", "young", "boy", "with", "the", "white", "shirt"], "raw": "the young boy with the white shirt", "sent_id": 18318, "sent": "the young boy with the white shirt"}, {"tokens": ["boy", "in", "white", "shirt"], "raw": "Boy in white shirt.", "sent_id": 18319, "sent": "boy in white shirt"}], "file_name": "COCO_train2014_000000236961_195669.jpg", "ann_id": 195669, "sent_ids": [18318, 18319], "ref_id": 12096}, {"segmentation": [[201.35, 526.38, 195.6, 483.24, 194.16, 437.21, 194.16, 379.69, 181.21, 319.28, 182.65, 172.58, 169.71, 125.12, 148.13, 106.43, 132.31, 90.61, 113.62, 37.39, 97.8, 28.76, 66.16, 40.27, 51.78, 53.21, 58.97, 69.03, 79.1, 109.3, 84.85, 120.81, 74.79, 158.2, 60.4, 198.47, 25.89, 207.1, 14.38, 241.62, 46.02, 266.07, 54.65, 274.7, 102.11, 408.45, 132.31, 473.17, 135.19, 507.69, 96.36, 535.01, 77.66, 553.71, 99.24, 579.6, 181.21, 585.35, 207.1, 573.84]], "area": 54836.0188, "iscrowd": 0, "image_id": 463101, "bbox": [14.38, 28.76, 192.72, 556.59], "category_id": 1, "id": 447019, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "hat", "skating"], "raw": "a man wearing a hat skating", "sent_id": 18322, "sent": "a man wearing a hat skating"}, {"tokens": ["an", "older", "man", "in", "a", "reindeer", "sweater"], "raw": "An older man in a reindeer sweater", "sent_id": 18323, "sent": "an older man in a reindeer sweater"}], "file_name": "COCO_train2014_000000463101_447019.jpg", "ann_id": 447019, "sent_ids": [18322, 18323], "ref_id": 12098}, {"segmentation": [[4.02, 300.16, 9.66, 312.23, 65.18, 300.97, 106.22, 296.94, 124.73, 321.08, 139.22, 336.37, 140.83, 370.17, 3.22, 369.37, 4.02, 300.97]], "area": 8545.663649999999, "iscrowd": 0, "image_id": 377019, "bbox": [3.22, 296.94, 137.61, 73.23], "category_id": 63, "id": 116964, "split": "val", "sentences": [{"tokens": ["a", "patterned", "-", "upholstery", "couch", "to", "the", "left", "of", "two", "young", "people", "playing", "a", "nintendo", "wii", "game"], "raw": "A patterned-upholstery couch to the left of two young people playing a Nintendo Wii game.", "sent_id": 18354, "sent": "a patterned - upholstery couch to the left of two young people playing a nintendo wii game"}, {"tokens": ["a", "white", "flower", "sofa"], "raw": "A white flower sofa", "sent_id": 18355, "sent": "a white flower sofa"}], "file_name": "COCO_train2014_000000377019_116964.jpg", "ann_id": 116964, "sent_ids": [18354, 18355], "ref_id": 12109}, {"segmentation": [[360.75, 113.14, 346.96, 130.0, 318.87, 128.98, 275.97, 141.23, 269.84, 157.58, 257.58, 183.62, 252.47, 200.48, 235.11, 207.63, 215.19, 207.63, 200.38, 190.26, 184.55, 180.56, 163.1, 178.52, 148.8, 166.26, 154.93, 141.74, 190.68, 116.72, 206.0, 99.87, 221.32, 88.12, 236.13, 86.08, 262.18, 95.27, 269.33, 91.69, 275.97, 74.33, 292.31, 70.24, 302.01, 70.75, 315.8, 85.05, 333.68, 94.25, 353.6, 105.99]], "area": 14120.143199999999, "iscrowd": 0, "image_id": 538155, "bbox": [148.8, 70.24, 211.95, 137.39], "category_id": 56, "id": 1055509, "split": "val", "sentences": [{"tokens": ["there", "is", "broccoli", "on", "a", "plate", "of", "food"], "raw": "There is broccoli on a plate of food.", "sent_id": 18397, "sent": "there is broccoli on a plate of food"}, {"tokens": ["a", "broccoli", "side", "dish"], "raw": "a broccoli side dish", "sent_id": 18398, "sent": "a broccoli side dish"}], "file_name": "COCO_train2014_000000538155_1055509.jpg", "ann_id": 1055509, "sent_ids": [18397, 18398], "ref_id": 12128}, {"segmentation": [[348.72, 106.61, 376.54, 104.78, 392.5, 111.62, 392.5, 122.11, 398.42, 131.69, 398.42, 138.07, 402.53, 142.63, 405.27, 146.74, 408.46, 148.56, 420.31, 150.84, 421.23, 161.79, 413.47, 178.2, 404.35, 188.69, 396.6, 198.27, 394.78, 220.16, 403.9, 248.89, 406.18, 268.04, 402.53, 280.35, 437.19, 284.0, 455.88, 283.54, 470.02, 281.26, 482.79, 292.66, 483.24, 299.05, 477.32, 296.77, 473.67, 296.77, 479.6, 305.89, 466.37, 311.36, 453.6, 305.89, 453.6, 305.89, 428.98, 303.15, 414.84, 302.24, 412.11, 302.7, 420.77, 318.66, 423.05, 341.0, 413.47, 376.12, 404.81, 389.34, 408.46, 412.6, 402.53, 428.1, 326.83, 428.56, 324.09, 404.39, 328.2, 358.33, 330.48, 346.48, 304.48, 332.34, 297.64, 320.94, 288.52, 309.08, 288.52, 297.23, 297.64, 275.79, 301.29, 233.38, 301.29, 202.37, 305.4, 185.04, 317.71, 168.63, 330.93, 162.24, 322.73, 145.83, 324.55, 124.39, 335.49, 108.89, 341.88, 106.61], [478.68, 151.75, 508.78, 173.64, 528.85, 195.08, 535.23, 201.46, 527.02, 247.97, 520.64, 251.62, 508.33, 252.99, 512.43, 246.61, 518.81, 242.5, 513.34, 238.85, 501.03, 236.57, 503.77, 227.0, 509.69, 216.97, 517.9, 206.02, 519.73, 199.18, 510.61, 189.15, 479.14, 166.8, 476.4, 156.77]], "area": 34008.51120000001, "iscrowd": 0, "image_id": 280191, "bbox": [288.52, 104.78, 246.71, 323.78], "category_id": 1, "id": 427637, "split": "val", "sentences": [{"tokens": ["a", "guy", "holding", "a", "girl", "in", "the", "chari"], "raw": "A guy holding a girl in the chari", "sent_id": 18399, "sent": "a guy holding a girl in the chari"}, {"tokens": ["a", "young", "man", "sits", "on", "a", "bench", "with", "his", "arm", "around", "a", "smiling", "girl"], "raw": "A young man sits on a bench with his arm around a smiling girl.", "sent_id": 18400, "sent": "a young man sits on a bench with his arm around a smiling girl"}], "file_name": "COCO_train2014_000000280191_427637.jpg", "ann_id": 427637, "sent_ids": [18399, 18400], "ref_id": 12129}, {"segmentation": [[16.19, 503.89, 45.87, 509.28, 63.41, 507.94, 80.95, 501.19, 91.74, 506.59, 106.58, 520.08, 117.37, 529.52, 132.21, 530.87, 153.8, 529.52, 176.73, 525.47, 194.27, 522.78, 215.86, 521.43, 225.3, 520.08, 240.14, 520.08, 249.58, 518.73, 263.07, 516.03, 269.82, 518.73, 261.73, 533.57, 250.93, 541.66, 246.89, 556.5, 246.89, 567.3, 242.84, 580.79, 238.79, 590.23, 223.95, 592.93, 165.94, 592.93, 137.61, 592.93, 58.01, 588.88, 37.77, 587.53, 20.24, 587.53, 8.09, 498.49, 8.09, 498.49]], "area": 17319.81919999999, "iscrowd": 0, "image_id": 100777, "bbox": [8.09, 498.49, 261.73, 94.44], "category_id": 62, "id": 372856, "split": "val", "sentences": [{"tokens": ["the", "chair", "of", "the", "man", "with", "the", "bald", "spot"], "raw": "The chair of the man with the bald spot", "sent_id": 18443, "sent": "the chair of the man with the bald spot"}, {"tokens": ["a", "wooden", "chair", "being", "sat", "on", "by", "a", "man", "in", "the", "foreground"], "raw": "a wooden chair being sat on by a man in the foreground", "sent_id": 18444, "sent": "a wooden chair being sat on by a man in the foreground"}], "file_name": "COCO_train2014_000000100777_372856.jpg", "ann_id": 372856, "sent_ids": [18443, 18444], "ref_id": 12145}, {"segmentation": [[610.65, 99.28, 640.0, 96.55, 640.0, 301.32, 635.22, 317.7, 612.47, 284.94, 609.74, 316.79, 611.56, 339.54, 594.27, 337.72, 589.72, 260.37, 586.08, 227.6, 575.16, 147.52]], "area": 11457.14575, "iscrowd": 0, "image_id": 7601, "bbox": [575.16, 96.55, 64.84, 242.99], "category_id": 21, "id": 75041, "split": "val", "sentences": [{"tokens": ["the", "far", "right", "black", "cow"], "raw": "The far right black cow.", "sent_id": 18481, "sent": "the far right black cow"}, {"tokens": ["cow", "on", "the", "far", "right", "who", "is", "barely", "visible"], "raw": "cow on the far right who is barely visible", "sent_id": 18482, "sent": "cow on the far right who is barely visible"}], "file_name": "COCO_train2014_000000007601_75041.jpg", "ann_id": 75041, "sent_ids": [18481, 18482], "ref_id": 12158}, {"segmentation": [[252.01, 274.53, 287.39, 274.53, 319.81, 268.64, 340.45, 284.11, 349.29, 304.01, 350.76, 371.81, 358.87, 397.6, 355.19, 439.61, 361.08, 452.13, 333.81, 455.08, 338.97, 423.39, 324.23, 374.76, 308.76, 383.6, 315.39, 404.97, 296.23, 451.4, 276.33, 453.61, 290.33, 418.23, 286.65, 393.92, 267.49, 396.13, 257.17, 423.39, 260.12, 463.19, 228.43, 464.66, 224.01, 413.08, 196.74, 358.54, 184.95, 323.17, 188.64, 292.22, 161.37, 277.48, 157.69, 273.06, 186.43, 266.43, 205.59, 252.42, 238.01, 265.69]], "area": 24727.2614, "iscrowd": 0, "image_id": 160852, "bbox": [157.69, 252.42, 203.39, 212.24], "category_id": 21, "id": 76127, "split": "val", "sentences": [{"tokens": ["the", "middle", "cow", "in", "a", "group", "of", "three", "looks", "at", "the", "camera"], "raw": "The middle cow in a group of three looks at the camera.", "sent_id": 18522, "sent": "the middle cow in a group of three looks at the camera"}, {"tokens": ["a", "brown", "cow", "standing", "in", "the", "snow", "between", "two", "other", "brown", "cows"], "raw": "A brown cow standing in the snow between two other brown cows.", "sent_id": 18523, "sent": "a brown cow standing in the snow between two other brown cows"}], "file_name": "COCO_train2014_000000160852_76127.jpg", "ann_id": 76127, "sent_ids": [18522, 18523], "ref_id": 12175}, {"segmentation": [[183.23, 208.31, 288.07, 234.77, 441.9, 224.97, 584.95, 208.31, 490.89, 307.27, 452.68, 330.79, 420.34, 332.75, 222.42, 279.84, 158.73, 251.42, 159.71, 245.54, 167.55, 239.66, 176.37, 205.37], [104.84, 183.81, 132.28, 197.53, 139.13, 207.33, 137.17, 220.07, 134.24, 235.74, 114.64, 225.95, 96.02, 216.15]], "area": 30947.352549999996, "iscrowd": 0, "image_id": 561551, "bbox": [96.02, 183.81, 488.93, 148.94], "category_id": 9, "id": 179104, "split": "val", "sentences": [{"tokens": ["a", "white", "boat", "with", "yellow", "and", "black", "bottom"], "raw": "a white boat with yellow and black bottom", "sent_id": 18545, "sent": "a white boat with yellow and black bottom"}, {"tokens": ["a", "long", "boat", "with", "a", "black", "base", "and", "white", "top"], "raw": "A long boat with a black base and white top.", "sent_id": 18546, "sent": "a long boat with a black base and white top"}], "file_name": "COCO_train2014_000000561551_179104.jpg", "ann_id": 179104, "sent_ids": [18545, 18546], "ref_id": 12184}, {"segmentation": [[442.32, 210.24, 453.81, 265.77, 459.55, 310.77, 472.96, 301.2, 484.44, 325.13, 579.23, 299.28, 609.86, 292.58, 606.03, 257.16, 595.5, 249.5, 602.2, 230.35, 582.1, 222.69, 587.84, 215.99, 576.35, 204.5, 543.8, 204.5, 539.02, 193.01, 501.68, 189.18, 507.42, 223.65, 505.51, 214.07, 492.1, 192.05, 461.47, 193.97, 452.85, 196.84, 440.4, 208.33]], "area": 16508.52345, "iscrowd": 0, "image_id": 66518, "bbox": [440.4, 189.18, 169.46, 135.95], "category_id": 54, "id": 312376, "split": "val", "sentences": [{"tokens": ["a", "skewered", "half", "sandwich", "with", "its", "other", "half", "between", "it", "and", "a", "glass", "of", "red", "wine"], "raw": "A skewered half sandwich with its other half between it and a glass of red wine.", "sent_id": 18565, "sent": "a skewered half sandwich with its other half between it and a glass of red wine"}, {"tokens": ["half", "of", "a", "sandwich", "to", "the", "right", "of", "another", "half"], "raw": "Half of a sandwich to the right of another half.", "sent_id": 18566, "sent": "half of a sandwich to the right of another half"}], "file_name": "COCO_train2014_000000066518_312376.jpg", "ann_id": 312376, "sent_ids": [18565, 18566], "ref_id": 12193}, {"segmentation": [[355.96, 315.04, 364.58, 298.86, 366.74, 279.44, 389.39, 254.63, 441.17, 194.23, 435.78, 185.6, 426.07, 183.44, 415.28, 184.52, 402.34, 201.78, 372.13, 250.32, 358.11, 254.63, 371.06, 226.59, 393.71, 188.84, 400.18, 166.18, 412.04, 153.24, 436.85, 132.75, 451.96, 129.51, 477.84, 142.45, 483.24, 147.85, 503.73, 127.35, 524.22, 105.78, 535.01, 92.84, 578.16, 112.25, 586.79, 134.9, 545.8, 178.05, 535.01, 188.84, 559.82, 202.86, 572.76, 227.67, 576.0, 249.24, 570.61, 315.04, 542.56, 352.79, 508.04, 366.81, 495.1, 356.03, 495.1, 342.0, 509.12, 277.29, 509.12, 264.34, 491.87, 265.42, 486.47, 257.87, 486.47, 255.71, 432.54, 297.78, 404.49, 321.51, 380.76, 330.14, 367.82, 333.38, 357.03, 318.27]], "area": 33353.44874999999, "iscrowd": 0, "image_id": 100667, "bbox": [355.96, 92.84, 230.83, 273.97], "category_id": 52, "id": 1042185, "split": "val", "sentences": [{"tokens": ["a", "banana", "on", "the", "right"], "raw": "A banana on the right.", "sent_id": 18567, "sent": "a banana on the right"}, {"tokens": ["the", "banana", "to", "the", "far", "right"], "raw": "The banana to the far right.", "sent_id": 18568, "sent": "the banana to the far right"}], "file_name": "COCO_train2014_000000100667_1042185.jpg", "ann_id": 1042185, "sent_ids": [18567, 18568], "ref_id": 12194}, {"segmentation": [[35.73, 273.13, 119.7, 278.49, 147.39, 247.22, 151.86, 220.42, 152.75, 194.52, 172.41, 170.4, 179.55, 154.32, 179.55, 130.2, 178.66, 123.95, 136.67, 131.09, 109.88, 134.67, 92.01, 130.2, 58.06, 125.73, 31.27, 137.34, 11.61, 127.52, 0.89, 208.81, 2.68, 232.93, 18.76, 257.05, 38.41, 277.59]], "area": 21595.46085, "iscrowd": 0, "image_id": 291897, "bbox": [0.89, 123.95, 178.66, 154.54], "category_id": 54, "id": 2218821, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "bread", "with", "garnish"], "raw": "a piece of bread with garnish", "sent_id": 18632, "sent": "a piece of bread with garnish"}, {"tokens": ["a", "piece", "of", "bread", "with", "greens", "on", "it", "to", "the", "left", "of", "a", "sandwich"], "raw": "A piece of bread with greens on it to the left of a sandwich.", "sent_id": 18633, "sent": "a piece of bread with greens on it to the left of a sandwich"}], "file_name": "COCO_train2014_000000291897_2218821.jpg", "ann_id": 2218821, "sent_ids": [18632, 18633], "ref_id": 12215}, {"segmentation": [[270.97, 287.26, 302.16, 258.87, 298.16, 244.47, 260.17, 237.67, 242.17, 230.87, 234.58, 224.08, 234.58, 212.48, 223.78, 204.08, 208.98, 203.28, 196.58, 210.48, 179.79, 239.27, 179.79, 262.87, 187.39, 291.26, 190.59, 303.26, 222.98, 342.85, 235.38, 341.25, 243.77, 339.65, 248.97, 329.25, 248.97, 318.86, 252.57, 332.85, 271.37, 330.85, 275.37, 315.26, 277.37, 303.66, 275.77, 294.86]], "area": 10608.428500000002, "iscrowd": 0, "image_id": 346876, "bbox": [179.79, 203.28, 122.37, 139.57], "category_id": 56, "id": 1059728, "split": "val", "sentences": [{"tokens": ["the", "broccoli", "closest", "to", "the", "camera", "furthest", "from", "the", "fork"], "raw": "The broccoli  closest to the camera furthest from the fork", "sent_id": 18693, "sent": "the broccoli closest to the camera furthest from the fork"}], "file_name": "COCO_train2014_000000346876_1059728.jpg", "ann_id": 1059728, "sent_ids": [18693], "ref_id": 12238}, {"segmentation": [[444.22, 132.03, 352.07, 210.42, 295.69, 226.92, 248.93, 244.8, 177.41, 254.43, 140.28, 284.68, 86.64, 360.32, 71.51, 431.84, 89.39, 478.6, 141.65, 497.85, 198.04, 492.35, 224.17, 473.1, 266.8, 441.47, 308.06, 365.82, 325.94, 302.56, 364.45, 248.93, 398.83, 206.29, 477.22, 126.53, 462.09, 112.77]], "area": 53513.04965000001, "iscrowd": 0, "image_id": 560180, "bbox": [71.51, 112.77, 405.71, 385.08], "category_id": 43, "id": 660413, "split": "val", "sentences": [{"tokens": ["several", "tennis", "racquets", "held", "in", "a", "chain", "link", "fence"], "raw": "Several tennis racquets held in a chain link fence", "sent_id": 18761, "sent": "several tennis racquets held in a chain link fence"}, {"tokens": ["a", "yellow", "tennis", "racket", "behind", "a", "pink", "tennis", "racket"], "raw": "a yellow tennis racket behind a pink tennis racket", "sent_id": 18762, "sent": "a yellow tennis racket behind a pink tennis racket"}], "file_name": "COCO_train2014_000000560180_660413.jpg", "ann_id": 660413, "sent_ids": [18761, 18762], "ref_id": 12257}, {"segmentation": [[4.87, 267.86, 17.53, 287.34, 37.01, 304.87, 61.36, 320.45, 140.26, 342.86, 197.73, 355.52, 256.17, 360.39, 287.34, 361.36, 374.03, 359.42, 406.17, 350.65, 439.29, 319.48, 457.79, 292.21, 472.4, 270.78, 488.96, 243.51, 495.78, 217.21, 499.68, 218.18, 500.0, 352.6, 487.01, 364.29, 446.1, 369.16, 2.92, 368.18, 0.97, 266.88], [497.73, 113.96, 498.7, 24.35, 469.48, 11.69, 446.1, 13.64, 432.47, 28.25, 439.29, 50.65, 449.03, 48.7, 447.08, 26.3, 462.66, 28.25, 478.25, 51.62, 487.99, 65.26, 477.27, 72.08, 471.43, 76.95, 474.35, 100.32, 487.01, 119.81, 495.78, 126.62]], "area": 20084.484600000014, "iscrowd": 0, "image_id": 548416, "bbox": [0.97, 11.69, 499.03, 357.47], "category_id": 51, "id": 1900836, "split": "val", "sentences": [{"tokens": ["white", "bowl", "full", "of", "soup"], "raw": "white bowl full of soup", "sent_id": 18853, "sent": "white bowl full of soup"}, {"tokens": ["the", "white", "bowl"], "raw": "The white bowl.", "sent_id": 18854, "sent": "the white bowl"}], "file_name": "COCO_train2014_000000548416_1900836.jpg", "ann_id": 1900836, "sent_ids": [18853, 18854], "ref_id": 12296}, {"segmentation": [[225.84, 301.66, 224.88, 337.65, 233.57, 337.89, 232.36, 357.94, 226.08, 359.15, 225.84, 374.61, 224.15, 375.33, 210.14, 376.06, 210.14, 359.63, 93.71, 360.6, 43.71, 362.05, 36.22, 363.5, 36.46, 377.51, 35.98, 378.96, 21.73, 378.96, 20.28, 362.05, 1.44, 363.26, 0.0, 364.71, 0.0, 304.32, 224.63, 301.66]], "area": 13702.09905, "iscrowd": 0, "image_id": 109654, "bbox": [0.0, 301.66, 233.57, 77.3], "category_id": 15, "id": 575496, "split": "val", "sentences": [{"tokens": ["a", "stone", "bench", "that", "doesnt", "have", "an", "animal", "in", "front", "of", "it"], "raw": "A stone bench that doesnt have an animal in front of it", "sent_id": 18921, "sent": "a stone bench that doesnt have an animal in front of it"}, {"tokens": ["a", "low", "bench", "on", "the", "left", "side", "of", "an", "entrance", "gate"], "raw": "A low bench on the left side of an entrance gate.", "sent_id": 18922, "sent": "a low bench on the left side of an entrance gate"}], "file_name": "COCO_train2014_000000109654_575496.jpg", "ann_id": 575496, "sent_ids": [18921, 18922], "ref_id": 12318}, {"segmentation": [[381.63, 175.41, 356.74, 155.26, 359.11, 124.44, 379.26, 117.33, 437.33, 109.04, 477.63, 109.04, 510.81, 98.37, 529.78, 105.48, 632.89, 129.19, 640.0, 138.67, 640.0, 424.3, 602.07, 452.74, 497.78, 391.11, 463.41, 382.81, 453.93, 361.48, 391.11, 343.7, 344.89, 292.74, 357.93, 252.44, 370.96, 254.81, 354.37, 224.0, 375.7, 220.44, 384.0, 209.78, 378.07, 194.37, 386.37, 187.26, 388.74, 176.59]], "area": 77298.84050000002, "iscrowd": 0, "image_id": 66034, "bbox": [344.89, 98.37, 295.11, 354.37], "category_id": 54, "id": 2218732, "split": "val", "sentences": [{"tokens": ["half", "a", "sandwich", "sitting", "on", "the", "right", "side", "of", "a", "plate"], "raw": "Half a sandwich sitting on the right side of a plate.", "sent_id": 18937, "sent": "half a sandwich sitting on the right side of a plate"}, {"tokens": ["sandwich", "half", "to", "right"], "raw": "sandwich half to right", "sent_id": 18938, "sent": "sandwich half to right"}], "file_name": "COCO_train2014_000000066034_2218732.jpg", "ann_id": 2218732, "sent_ids": [18937, 18938], "ref_id": 12324}, {"segmentation": [[352.72, 311.73, 306.34, 289.08, 325.75, 234.07, 344.09, 141.3, 358.11, 134.83, 300.94, 125.12, 235.15, 122.97, 185.53, 125.12, 132.67, 144.54, 99.24, 169.35, 59.33, 198.47, 31.28, 225.44, 12.94, 262.11, 15.1, 316.04, 15.1, 341.93, 50.7, 349.48, 118.65, 346.25, 132.67, 361.35, 162.88, 358.11, 195.24, 348.4, 278.29, 330.07, 325.75, 325.75]], "area": 60806.16335, "iscrowd": 0, "image_id": 136736, "bbox": [12.94, 122.97, 345.17, 238.38], "category_id": 7, "id": 173498, "split": "val", "sentences": [{"tokens": ["train", "with", "green", "t", "on", "it"], "raw": "train with green t on it", "sent_id": 18961, "sent": "train with green t on it"}], "file_name": "COCO_train2014_000000136736_173498.jpg", "ann_id": 173498, "sent_ids": [18961], "ref_id": 12335}, {"segmentation": [[58.12, 174.35, 77.49, 166.82, 90.4, 161.43, 105.47, 154.98, 113.0, 157.13, 132.38, 168.97, 167.89, 182.96, 194.8, 206.64, 233.54, 208.79, 257.22, 209.87, 265.83, 204.48, 265.83, 204.48, 257.22, 191.57, 238.92, 170.04, 234.62, 166.82, 229.24, 165.74, 229.24, 163.59, 236.77, 157.13, 259.37, 146.37, 266.91, 152.83, 288.43, 166.82, 302.42, 191.57, 314.26, 174.35, 340.09, 177.58, 344.39, 160.36, 360.54, 154.98, 386.37, 157.13, 387.44, 157.13, 408.97, 170.04, 416.5, 180.81, 441.26, 195.87, 460.63, 200.18, 486.46, 191.57, 502.6, 201.26, 519.82, 221.7, 520.9, 240.0, 510.13, 257.22, 499.37, 258.3, 472.47, 259.37, 418.65, 253.99, 408.97, 271.21, 401.43, 289.51, 380.99, 298.12, 327.17, 303.5, 277.67, 292.74, 242.15, 283.05, 232.47, 277.67, 228.16, 269.06, 221.7, 264.75, 194.8, 259.37, 154.98, 234.62, 125.92, 214.17, 93.63, 189.42]], "area": 36913.66445000001, "iscrowd": 0, "image_id": 19501, "bbox": [58.12, 146.37, 462.78, 157.13], "category_id": 1, "id": 498442, "split": "val", "sentences": [{"tokens": ["woman", "body", "surfing"], "raw": "Woman body surfing.", "sent_id": 18990, "sent": "woman body surfing"}, {"tokens": ["a", "woman", "in", "a", "blue", "bikini"], "raw": "a woman in a blue bikini.", "sent_id": 18991, "sent": "a woman in a blue bikini"}], "file_name": "COCO_train2014_000000019501_498442.jpg", "ann_id": 498442, "sent_ids": [18990, 18991], "ref_id": 12348}, {"segmentation": [[169.29, 256.61, 185.92, 251.18, 214.05, 224.96, 213.73, 222.4, 219.16, 206.74, 221.08, 184.04, 222.36, 176.37, 223.64, 170.93, 222.68, 168.06, 215.33, 161.66, 214.37, 157.83, 215.65, 153.67, 217.89, 153.35, 219.16, 153.35, 222.68, 154.95, 227.48, 161.02, 227.16, 153.67, 223.64, 149.51, 223.0, 146.0, 225.24, 144.08, 227.8, 146.64, 230.35, 150.15, 232.59, 155.59, 234.19, 154.63, 236.11, 153.03, 234.19, 148.87, 236.11, 147.28, 238.03, 146.64, 238.99, 157.83, 245.38, 153.67, 249.54, 152.71, 245.7, 163.9, 245.7, 167.1, 245.7, 171.25, 246.98, 177.33, 246.02, 182.44, 240.58, 185.96, 238.03, 179.88, 232.59, 181.16, 232.59, 209.3, 229.39, 223.36, 229.39, 234.87, 244.91, 260.28, 251.76, 273.97, 282.85, 286.4, 282.85, 296.98, 262.95, 287.03, 246.16, 275.21, 237.45, 253.44, 229.99, 333.05, 229.37, 346.11, 221.28, 345.49, 215.68, 312.53, 212.57, 336.78, 185.21, 334.91, 184.59, 314.39, 178.37, 302.57, 172.77, 310.66, 173.39, 319.99, 174.64, 329.94, 170.91, 336.78, 156.6, 338.02, 153.49, 319.37, 161.58, 266.5]], "area": 8639.549699999998, "iscrowd": 0, "image_id": 171484, "bbox": [153.49, 144.08, 129.36, 202.03], "category_id": 25, "id": 595620, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "looking", "at", "the", "wall"], "raw": "The giraffe looking at the wall.", "sent_id": 19004, "sent": "the giraffe looking at the wall"}, {"tokens": ["a", "young", "giraffe", "in", "a", "zoo", ",", "facing", "away", "from", "the", "camera", "toward", "an", "adult", "giraffe"], "raw": "A young giraffe in a zoo, facing away from the camera toward an adult giraffe", "sent_id": 19005, "sent": "a young giraffe in a zoo , facing away from the camera toward an adult giraffe"}], "file_name": "COCO_train2014_000000171484_595620.jpg", "ann_id": 595620, "sent_ids": [19004, 19005], "ref_id": 12353}, {"segmentation": [[142.42, 571.16, 222.75, 573.81, 273.95, 562.33, 274.84, 501.42, 251.88, 482.88, 261.59, 293.08, 263.36, 275.43, 272.19, 126.23, 278.37, 99.75, 283.66, 71.5, 285.43, 52.96, 315.45, 76.8, 327.8, 77.68, 346.34, 63.55, 341.05, 45.02, 317.21, 56.49, 279.25, 24.71, 260.71, 108.58, 252.77, 228.64, 248.35, 263.95, 230.7, 377.83, 223.63, 444.04, 187.44, 444.92, 138.89, 449.34, 135.35, 535.85]], "area": 24867.704049999986, "iscrowd": 0, "image_id": 11673, "bbox": [135.35, 24.71, 210.99, 549.1], "category_id": 8, "id": 1796612, "split": "val", "sentences": [{"tokens": ["the", "black", "and", "yellow", "mercedes", "lift"], "raw": "The black and yellow mercedes lift.", "sent_id": 19114, "sent": "the black and yellow mercedes lift"}, {"tokens": ["yellow", "crane"], "raw": "Yellow crane.", "sent_id": 19115, "sent": "yellow crane"}], "file_name": "COCO_train2014_000000011673_1796612.jpg", "ann_id": 1796612, "sent_ids": [19114, 19115], "ref_id": 12394}, {"segmentation": [[195.01, 292.02, 177.69, 316.12, 185.97, 334.19, 198.02, 345.49, 231.15, 355.27, 277.84, 356.78, 313.23, 350.0, 344.86, 336.45, 365.94, 322.9, 370.46, 299.55, 363.68, 278.47, 321.51, 264.16, 290.64, 261.15, 300.43, 256.63, 294.41, 252.87, 264.29, 256.63, 262.03, 262.66, 262.78, 266.42, 230.4, 270.19, 214.59, 277.72, 201.79, 289.01]], "area": 14285.490549999999, "iscrowd": 0, "image_id": 68305, "bbox": [177.69, 252.87, 192.77, 103.91], "category_id": 81, "id": 2140856, "split": "val", "sentences": [{"tokens": ["the", "white", "sink"], "raw": "the white sink", "sent_id": 19134, "sent": "the white sink"}, {"tokens": ["a", "white", "sink"], "raw": "A white sink", "sent_id": 19135, "sent": "a white sink"}], "file_name": "COCO_train2014_000000068305_2140856.jpg", "ann_id": 2140856, "sent_ids": [19134, 19135], "ref_id": 12403}, {"segmentation": [[299.77, 141.69, 296.88, 150.37, 293.02, 163.86, 298.8, 179.28, 293.98, 185.07, 290.13, 197.6, 290.13, 226.51, 307.48, 265.07, 364.35, 264.1, 371.09, 261.21, 378.81, 242.9, 361.46, 213.98, 352.78, 185.07, 337.36, 172.53, 332.54, 165.79, 326.76, 151.33, 320.97, 143.62, 317.12, 143.62, 307.48, 141.69], [313.26, 278.56, 298.8, 310.37, 297.84, 363.38, 280.49, 380.73, 287.24, 386.52, 317.12, 385.55, 313.26, 366.28, 322.9, 315.19, 330.61, 317.12, 345.07, 286.27, 351.82, 286.27, 365.31, 314.23, 375.91, 343.14, 378.81, 360.49, 378.81, 370.85, 374.95, 380.49, 376.88, 387.24, 390.37, 388.2, 391.34, 381.46, 394.23, 367.96, 391.34, 344.83, 382.32, 308.78, 374.06, 269.73]], "area": 12468.051399999998, "iscrowd": 0, "image_id": 122231, "bbox": [280.49, 141.69, 113.74, 246.51], "category_id": 1, "id": 478122, "split": "val", "sentences": [{"tokens": ["person", "on", "right", "with", "hat"], "raw": "Person on right with hat.", "sent_id": 19159, "sent": "person on right with hat"}], "file_name": "COCO_train2014_000000122231_478122.jpg", "ann_id": 478122, "sent_ids": [19159], "ref_id": 12414}, {"segmentation": [[471.58, 45.25, 482.48, 21.74, 496.59, 10.41, 509.62, 6.14, 520.1, 4.64, 532.49, 4.64, 549.38, 9.35, 558.57, 16.4, 575.24, 11.06, 589.56, 11.06, 602.17, 13.83, 610.93, 21.1, 615.21, 26.87, 621.19, 30.08, 640.0, 25.16, 640.0, 44.18, 638.93, 46.96, 620.98, 54.01, 613.92, 71.97, 611.36, 78.17, 610.9, 84.46, 610.04, 87.02, 602.56, 92.37, 594.65, 99.85, 591.45, 109.46, 596.36, 120.58, 604.7, 123.36, 604.49, 119.51, 604.49, 113.1, 606.62, 108.82, 612.39, 107.54, 614.53, 107.33, 623.51, 110.53, 625.0, 121.22, 625.22, 129.77, 604.7, 171.02, 588.88, 190.04, 579.48, 205.43, 562.81, 202.44, 523.66, 195.98, 520.42, 191.12, 522.69, 179.46, 524.63, 176.87, 534.67, 168.45, 537.91, 166.18, 560.91, 132.49, 557.35, 125.68, 540.51, 117.91, 529.82, 111.75, 517.18, 99.44, 492.88, 87.46, 485.43, 60.57, 469.88, 45.67]], "area": 18897.636200000004, "iscrowd": 0, "image_id": 402448, "bbox": [469.88, 4.64, 170.12, 200.79], "category_id": 62, "id": 1930596, "split": "val", "sentences": [{"tokens": ["brown", "chair", "with", "a", "cat", "looking", "at", "it"], "raw": "brown chair with a cat looking at it", "sent_id": 19188, "sent": "brown chair with a cat looking at it"}, {"tokens": ["the", "chair", "-", "the", "cat", "is", "looking"], "raw": "The chair - the cat is looking", "sent_id": 19189, "sent": "the chair - the cat is looking"}], "file_name": "COCO_train2014_000000402448_1930596.jpg", "ann_id": 1930596, "sent_ids": [19188, 19189], "ref_id": 12424}, {"segmentation": [[5.73, 205.4, 39.16, 200.63, 87.87, 196.81, 117.47, 198.72, 147.08, 213.04, 162.36, 253.15, 181.46, 290.4, 199.61, 353.43, 191.01, 358.21, 185.28, 376.36, 176.69, 385.91, 156.63, 384.0, 28.65, 374.45, 7.64, 389.73, 4.78, 212.09]], "area": 30372.21845, "iscrowd": 0, "image_id": 257867, "bbox": [4.78, 196.81, 194.83, 192.92], "category_id": 3, "id": 350313, "split": "val", "sentences": [{"tokens": ["car", "with", "a", "yellow", "license", "plate", "in", "traffic"], "raw": "car with a yellow license plate in traffic", "sent_id": 19300, "sent": "car with a yellow license plate in traffic"}, {"tokens": ["the", "small", "grey", "car", "to", "the", "left", "of", "the", "tow", "truck"], "raw": "the small grey car to the left of the tow truck", "sent_id": 19301, "sent": "the small grey car to the left of the tow truck"}], "file_name": "COCO_train2014_000000257867_350313.jpg", "ann_id": 350313, "sent_ids": [19300, 19301], "ref_id": 12463}, {"segmentation": [[129.17, 395.83, 131.01, 397.66, 131.01, 400.41, 132.84, 404.99, 133.75, 411.4, 132.84, 413.24, 129.17, 411.4, 127.34, 411.4, 127.34, 411.4, 123.68, 413.24, 123.68, 410.49, 121.85, 405.91, 119.1, 405.91, 116.35, 401.33, 115.43, 396.74, 115.43, 395.83, 88.86, 369.26, 86.12, 369.26, 84.28, 368.34, 79.7, 357.35, 78.79, 355.52, 77.87, 350.94, 74.21, 339.03, 70.54, 332.62, 62.3, 318.87, 62.3, 317.96, 58.63, 313.38, 56.8, 312.46, 58.63, 306.96, 63.21, 304.22, 61.38, 295.97, 53.14, 284.98, 57.72, 277.65, 57.72, 276.73, 218.95, 213.52, 224.45, 213.52, 225.37, 219.02, 228.12, 219.93, 234.53, 227.26, 237.28, 227.26, 240.94, 227.26, 248.27, 234.59, 251.02, 244.67, 251.94, 245.58, 262.01, 250.16, 267.51, 251.08, 276.67, 254.74, 292.25, 261.16, 296.83, 263.91, 296.83, 268.49, 294.08, 274.9, 290.41, 274.9, 290.41, 284.98, 291.33, 287.73, 292.25, 295.05, 292.25, 305.13, 292.25, 307.88, 284.92, 314.29, 284.92, 309.71, 283.08, 306.05, 128.26, 394.91]], "area": 26011.20915, "iscrowd": 0, "image_id": 523863, "bbox": [53.14, 213.52, 243.69, 199.72], "category_id": 63, "id": 99551, "split": "val", "sentences": [{"tokens": ["a", "tan", "modern", "looking", "couch", "being", "view", "from", "a", "higher", "angle"], "raw": "a tan modern looking couch being view from a higher angle", "sent_id": 19346, "sent": "a tan modern looking couch being view from a higher angle"}, {"tokens": ["couch", "and", "pillows", "on", "top", "which", "is", "behind", "ottoman"], "raw": "Couch and pillows on top which is behind ottoman.", "sent_id": 19347, "sent": "couch and pillows on top which is behind ottoman"}], "file_name": "COCO_train2014_000000523863_99551.jpg", "ann_id": 99551, "sent_ids": [19346, 19347], "ref_id": 12481}, {"segmentation": [[78.74, 305.26, 119.73, 265.35, 142.38, 244.85, 174.74, 227.6, 186.61, 224.36, 190.92, 201.71, 216.81, 163.96, 235.15, 146.7, 296.63, 122.97, 320.36, 119.73, 321.44, 129.44, 321.44, 130.52, 328.99, 124.04, 344.09, 132.67, 378.61, 139.15, 381.84, 146.7, 403.42, 143.46, 480.0, 176.9, 504.81, 175.82, 542.56, 227.6, 533.93, 242.7, 503.73, 235.15, 503.73, 235.15, 468.13, 229.75, 461.66, 242.7, 445.48, 244.85, 379.69, 288.0, 340.85, 327.91, 307.42, 288.0, 282.61, 277.21, 240.54, 277.21, 228.67, 286.92, 220.04, 309.57, 231.91, 337.62, 234.07, 343.01, 180.13, 345.17, 121.89, 332.22, 83.06, 318.2, 87.37, 302.02]], "area": 51950.280549999996, "iscrowd": 0, "image_id": 331520, "bbox": [78.74, 119.73, 463.82, 225.44], "category_id": 32, "id": 296161, "split": "val", "sentences": [{"tokens": ["the", "thing", "being", "held"], "raw": "The thing being held", "sent_id": 19370, "sent": "the thing being held"}, {"tokens": ["the", "object", "being", "wrapped", "with", "string"], "raw": "The object being wrapped with string.", "sent_id": 19371, "sent": "the object being wrapped with string"}], "file_name": "COCO_train2014_000000331520_296161.jpg", "ann_id": 296161, "sent_ids": [19370, 19371], "ref_id": 12490}, {"segmentation": [[134.04, 243.94, 118.99, 244.59, 115.72, 234.12, 111.8, 232.16, 110.49, 247.86, 100.02, 247.86, 92.17, 236.74, 84.32, 221.04, 83.67, 211.88, 73.86, 202.73, 69.28, 187.03, 64.04, 177.87, 57.5, 170.67, 47.69, 168.06, 45.07, 173.29, 38.53, 176.56, 34.61, 183.76, 24.14, 187.68, 15.64, 187.68, 8.44, 175.25, 9.75, 164.79, 16.95, 147.12, 22.18, 130.77, 26.76, 120.96, 32.64, 110.49, 36.57, 105.26, 48.34, 96.76, 52.27, 104.61, 57.5, 100.68, 58.16, 110.49, 66.66, 117.69, 87.59, 124.88, 88.9, 126.19, 90.21, 126.85, 94.79, 147.12, 89.55, 160.21, 89.55, 190.3, 90.86, 205.34, 102.64, 212.54, 109.83, 212.54, 115.72, 202.07, 120.95, 190.95, 130.11, 175.91, 134.04, 171.98, 147.12, 183.1, 152.35, 194.22, 160.2, 211.88, 165.43, 223.0, 158.24, 225.62, 137.31, 227.58, 134.04, 228.89, 134.04, 235.43, 130.77, 243.94], [99.37, 257.67, 105.25, 274.68, 107.87, 291.03, 98.06, 310.0, 94.79, 317.2, 109.18, 316.55, 111.8, 308.7, 118.34, 293.65, 118.34, 285.8, 115.07, 272.72, 112.45, 257.02, 116.37, 255.06, 119.65, 269.45, 122.92, 280.57, 119.65, 300.19, 113.1, 317.85, 126.19, 317.85, 128.15, 315.24, 130.77, 300.19, 128.15, 286.46, 128.15, 277.95, 130.77, 269.45, 130.77, 253.75, 115.72, 252.44, 103.95, 259.64], [218.42, 232.16, 214.5, 240.67, 221.04, 255.06, 224.96, 288.42, 221.69, 298.88, 234.77, 301.5, 236.08, 295.61, 233.47, 283.19, 234.12, 267.49, 230.19, 254.4, 229.54, 240.01, 232.16, 232.82, 219.07, 233.47]], "area": 10693.5028, "iscrowd": 0, "image_id": 275658, "bbox": [8.44, 96.76, 227.64, 221.09], "category_id": 19, "id": 57031, "split": "val", "sentences": [{"tokens": ["the", "black", "horse", "pulling", "the", "carriage"], "raw": "The black horse pulling the carriage", "sent_id": 19452, "sent": "the black horse pulling the carriage"}, {"tokens": ["black", "horse", "next", "to", "white", "horse", "pulling", "a", "carriage"], "raw": "Black horse next to white horse pulling a carriage", "sent_id": 19453, "sent": "black horse next to white horse pulling a carriage"}], "file_name": "COCO_train2014_000000275658_57031.jpg", "ann_id": 57031, "sent_ids": [19452, 19453], "ref_id": 12520}, {"segmentation": [[331.04, 37.42, 347.36, 75.8, 356.95, 88.28, 387.66, 108.43, 411.65, 140.09, 431.8, 169.84, 442.35, 155.45, 456.75, 169.84, 453.87, 188.07, 461.54, 188.07, 474.02, 165.04, 481.69, 165.04, 479.78, 194.79, 475.94, 201.51, 466.34, 236.05, 470.18, 256.2, 466.34, 248.52, 458.67, 270.59, 453.87, 299.38, 449.07, 341.6, 448.11, 350.24, 448.11, 373.27, 437.56, 403.97, 428.92, 405.89, 419.32, 402.05, 411.65, 394.38, 399.17, 385.74, 397.25, 371.35, 399.17, 354.07, 393.42, 326.25, 375.18, 304.18, 370.39, 284.99, 365.59, 270.59, 355.99, 255.24, 355.99, 228.37, 359.83, 212.06, 334.88, 183.27, 307.06, 148.73, 283.07, 130.5, 241.81, 98.83, 181.36, 74.84, 142.01, 63.33, 97.87, 67.17, 79.64, 71.01, 3.84, 18.23, 0.0, 0.96, 283.07, 4.8, 309.93, 23.03, 331.04, 36.46]], "area": 52066.19710000002, "iscrowd": 0, "image_id": 427461, "bbox": [0.0, 0.96, 481.69, 404.93], "category_id": 25, "id": 597696, "split": "val", "sentences": [{"tokens": ["girrafe", "in", "the", "back"], "raw": "girrafe in the back.", "sent_id": 19483, "sent": "girrafe in the back"}], "file_name": "COCO_train2014_000000427461_597696.jpg", "ann_id": 597696, "sent_ids": [19483], "ref_id": 12531}, {"segmentation": [[49.6, 438.28, 65.25, 393.38, 80.22, 362.77, 101.31, 349.16, 121.72, 353.92, 130.56, 389.98, 135.32, 433.52, 129.88, 488.63, 121.04, 524.0, 110.83, 554.62, 86.34, 572.98, 72.05, 574.34, 60.49, 556.66, 48.92, 534.21, 47.56, 510.4, 47.56, 494.07, 46.88, 478.42, 47.56, 463.45, 50.28, 451.21, 50.96, 442.36]], "area": 15017.459949999999, "iscrowd": 0, "image_id": 369509, "bbox": [46.88, 349.16, 88.44, 225.18], "category_id": 85, "id": 335712, "split": "val", "sentences": [{"tokens": ["a", "big", "clock", "face", "is", "shown", "from", "the", "side", "angle"], "raw": "A big clock face is shown from the side angle.", "sent_id": 19508, "sent": "a big clock face is shown from the side angle"}, {"tokens": ["clock", "face", "not", "facing", "camera"], "raw": "clock face not facing camera", "sent_id": 19509, "sent": "clock face not facing camera"}], "file_name": "COCO_train2014_000000369509_335712.jpg", "ann_id": 335712, "sent_ids": [19508, 19509], "ref_id": 12542}, {"segmentation": [[210.0, 440.94, 207.16, 428.63, 206.21, 413.48, 204.32, 398.33, 214.73, 385.08, 233.67, 367.09, 238.4, 283.78, 238.4, 266.74, 251.65, 258.22, 268.69, 248.75, 281.0, 240.23, 280.06, 226.03, 271.53, 232.66, 259.23, 201.41, 257.33, 183.43, 256.39, 167.33, 264.91, 120.94, 300.88, 106.74, 340.65, 128.52, 355.79, 166.38, 350.11, 216.56, 379.46, 239.28, 416.38, 248.75, 440.05, 265.79, 458.04, 336.8, 459.93, 344.37, 469.4, 379.4, 465.61, 393.6, 469.4, 412.53, 461.83, 421.06, 441.0, 427.68, 417.33, 449.46, 416.38, 486.38, 391.77, 538.45, 396.5, 570.64, 401.24, 636.91, 314.14, 638.8, 308.46, 635.02, 321.71, 563.07, 310.35, 538.45, 311.3, 511.94, 293.31, 511.94, 233.67, 526.14, 200.53, 526.14, 169.29, 525.2, 159.82, 581.05, 142.78, 619.87, 130.47, 640.0, 85.98, 636.91, 98.28, 527.09, 111.54, 487.33, 113.43, 467.45, 124.79, 457.03, 143.73, 444.72]], "area": 96413.19604999997, "iscrowd": 0, "image_id": 427301, "bbox": [85.98, 106.74, 383.42, 533.26], "category_id": 1, "id": 223368, "split": "val", "sentences": [{"tokens": ["man", "in", "striped", "shirt"], "raw": "Man in striped shirt.", "sent_id": 19589, "sent": "man in striped shirt"}, {"tokens": ["a", "man", "on", "a", "couch", "with", "striped", "clothes", "and", "another", "man"], "raw": "A man on a couch with striped clothes and another man.", "sent_id": 19590, "sent": "a man on a couch with striped clothes and another man"}], "file_name": "COCO_train2014_000000427301_223368.jpg", "ann_id": 223368, "sent_ids": [19589, 19590], "ref_id": 12574}, {"segmentation": [[41.71, 287.64, 87.73, 287.64, 138.07, 306.34, 194.16, 350.92, 220.04, 379.69, 231.55, 409.89, 238.74, 428.58, 258.88, 419.96, 266.07, 409.89, 300.58, 547.96, 261.75, 625.62, 76.22, 576.72, 69.03, 477.48, 61.84, 477.48, 53.21, 477.48, 37.39, 464.54, 28.76, 454.47, 15.82, 442.97, 24.45, 427.15, 34.52, 421.39, 37.39, 411.33, 37.39, 405.57, 24.45, 384.0, 10.07, 353.8, 10.07, 319.28, 20.13, 299.15, 34.52, 293.39]], "area": 62926.83815000001, "iscrowd": 0, "image_id": 280051, "bbox": [10.07, 287.64, 290.51, 337.98], "category_id": 62, "id": 382030, "split": "val", "sentences": [{"tokens": ["a", "chair", "with", "a", "white", "&", "black", "color", "cover"], "raw": "A chair with a white & black color cover", "sent_id": 19632, "sent": "a chair with a white & black color cover"}, {"tokens": ["a", "white", "chair", "wrapped", "in", "a", "black", "sash"], "raw": "a white chair wrapped in a black sash.", "sent_id": 19633, "sent": "a white chair wrapped in a black sash"}], "file_name": "COCO_train2014_000000280051_382030.jpg", "ann_id": 382030, "sent_ids": [19632, 19633], "ref_id": 12588}, {"segmentation": [[308.52, 133.34, 317.1, 121.02, 327.28, 115.65, 341.22, 122.62, 346.04, 134.95, 354.62, 150.5, 365.88, 155.32, 377.14, 165.51, 377.14, 176.23, 375.53, 187.48, 366.95, 193.92, 350.33, 197.67, 342.83, 200.89, 338.54, 208.93, 345.51, 225.54, 349.26, 242.7, 340.15, 244.31, 324.6, 241.63, 312.27, 237.87, 311.2, 243.23, 307.99, 252.88, 303.16, 265.21, 302.62, 279.15, 299.41, 283.44, 287.08, 280.76, 277.97, 273.25, 280.11, 264.68, 285.47, 264.14, 292.44, 238.95, 292.44, 223.94, 283.86, 235.73, 270.46, 243.77, 265.1, 233.58, 269.93, 224.47, 280.11, 213.22, 283.86, 202.49, 283.86, 189.63, 287.08, 178.37, 294.58, 176.76, 302.09, 175.69, 306.91, 176.76, 315.49, 168.19, 318.71, 166.58, 317.1, 159.61, 312.27, 152.11, 310.13, 140.85]], "area": 8181.979549999997, "iscrowd": 0, "image_id": 321539, "bbox": [265.1, 115.65, 112.04, 167.79], "category_id": 1, "id": 455379, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "green", "shirt", "sitting", "in", "the", "library"], "raw": "a man in a green shirt sitting in the library", "sent_id": 19643, "sent": "a man in a green shirt sitting in the library"}, {"tokens": ["person", "wearing", "hoodie", "on", "the", "computer"], "raw": "Person wearing hoodie on the computer.", "sent_id": 19644, "sent": "person wearing hoodie on the computer"}], "file_name": "COCO_train2014_000000321539_455379.jpg", "ann_id": 455379, "sent_ids": [19643, 19644], "ref_id": 12593}, {"segmentation": [[351.4, 293.26, 351.4, 274.72, 355.62, 259.55, 355.62, 236.8, 349.72, 232.58, 351.4, 218.26, 350.56, 207.3, 347.19, 135.67, 327.81, 140.73, 298.31, 127.25, 300.84, 117.98, 304.21, 112.92, 310.11, 112.92, 327.81, 64.89, 344.66, 45.51, 352.25, 41.29, 346.35, 37.92, 356.46, 29.49, 374.16, 15.17, 381.74, 4.21, 428.09, 0.0, 433.15, 6.74, 428.09, 16.01, 440.73, 28.65, 436.52, 31.18, 465.17, 57.3, 466.85, 69.94, 483.71, 81.74, 484.55, 87.64, 475.28, 104.49, 466.01, 106.18, 444.1, 97.75, 450.0, 140.73, 459.27, 195.51, 459.27, 203.09, 450.0, 214.89, 433.99, 300.84, 432.3, 346.35, 424.72, 345.51, 407.02, 326.97, 388.48, 318.54, 375.0, 316.01, 372.47, 307.58]], "area": 33959.059149999994, "iscrowd": 0, "image_id": 376941, "bbox": [298.31, 0.0, 186.24, 346.35], "category_id": 1, "id": 435964, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "black", "leather", "coat", "surrounded", "by", "luggage"], "raw": "A person in a black leather coat surrounded by luggage.", "sent_id": 19692, "sent": "a person in a black leather coat surrounded by luggage"}, {"tokens": ["the", "man", "wearing", "a", "black", "leather", "jacket"], "raw": "The man wearing a black leather jacket.", "sent_id": 19693, "sent": "the man wearing a black leather jacket"}], "file_name": "COCO_train2014_000000376941_435964.jpg", "ann_id": 435964, "sent_ids": [19692, 19693], "ref_id": 12611}, {"segmentation": [[332.39, 319.02, 323.8, 303.74, 320.93, 289.41, 317.11, 280.82, 322.84, 279.86, 327.62, 278.91, 359.14, 273.17, 365.83, 273.17, 383.02, 273.17, 383.02, 273.17, 393.52, 272.22, 393.52, 270.31, 365.83, 253.12, 359.14, 247.39, 350.54, 237.83, 342.9, 223.51, 341.95, 211.09, 343.86, 203.45, 347.68, 192.94, 354.36, 177.66, 362.0, 167.15, 375.38, 153.78, 385.88, 145.18, 404.03, 138.5, 412.63, 134.68, 446.06, 121.3, 469.94, 120.35, 469.94, 112.71, 468.98, 101.25, 469.94, 91.7, 473.76, 78.32, 482.35, 68.77, 489.04, 66.86, 515.78, 74.5, 523.43, 93.61, 523.43, 106.02, 525.34, 112.71, 527.25, 120.35, 524.38, 124.17, 519.61, 137.54, 519.61, 140.41, 509.1, 147.09, 508.14, 147.09, 496.68, 150.91, 489.04, 153.78, 489.04, 154.74, 485.22, 159.51, 477.58, 170.97, 473.76, 176.7, 468.03, 191.03, 462.3, 201.54, 458.48, 206.31, 476.62, 215.87, 480.44, 223.51, 481.4, 232.1, 467.07, 257.89, 461.34, 267.44, 457.52, 277.95, 453.7, 286.55, 453.7, 287.5, 451.79, 292.28, 450.83, 296.1, 453.7, 312.34, 454.65, 319.98, 462.3, 326.66, 463.25, 327.62, 450.83, 330.48, 447.01, 330.48, 422.18, 330.48, 404.99, 330.48, 405.94, 319.98, 406.9, 312.34, 406.9, 306.61, 401.17, 303.74, 376.33, 306.61, 355.32, 303.74, 366.78, 316.16, 368.69, 320.93, 367.74, 326.66, 344.81, 322.84, 342.9, 322.84]], "area": 25917.354099999997, "iscrowd": 0, "image_id": 176229, "bbox": [317.11, 66.86, 210.14, 263.62], "category_id": 1, "id": 185726, "split": "val", "sentences": [{"tokens": ["man", "on", "skateboard"], "raw": "man on skateboard", "sent_id": 19755, "sent": "man on skateboard"}, {"tokens": ["the", "man", "on", "the", "skatboard"], "raw": "The man on the skatboard.", "sent_id": 19756, "sent": "the man on the skatboard"}], "file_name": "COCO_train2014_000000176229_185726.jpg", "ann_id": 185726, "sent_ids": [19755, 19756], "ref_id": 12638}, {"segmentation": [[204.22, 43.15, 191.28, 74.79, 185.53, 100.67, 186.97, 136.63, 176.9, 162.52, 182.65, 214.29, 184.09, 227.24, 197.03, 253.12, 205.66, 283.33, 212.85, 306.34, 227.24, 346.61, 232.99, 365.3, 253.12, 381.12, 273.26, 395.51, 279.01, 414.2, 264.63, 435.78, 251.69, 448.72, 222.92, 445.84, 214.29, 434.34, 212.85, 409.89, 211.42, 395.51, 195.6, 349.48, 189.84, 316.4, 184.09, 293.39, 184.09, 286.2, 169.71, 291.96, 152.45, 300.58, 133.75, 303.46, 129.44, 306.34, 125.12, 317.84, 122.25, 343.73, 116.49, 368.18, 113.62, 381.12, 113.62, 391.19, 112.18, 415.64, 125.12, 425.71, 132.31, 438.65, 130.88, 444.4, 100.67, 444.4, 83.42, 444.4, 77.66, 435.78, 79.1, 415.64, 79.1, 379.69, 79.1, 365.3, 79.1, 326.47, 92.04, 299.15, 94.92, 273.26, 81.98, 232.99, 70.47, 201.35, 70.47, 179.78, 70.47, 161.08, 66.16, 148.13, 66.16, 125.12, 70.47, 104.99, 80.54, 79.1, 87.73, 67.6, 109.3, 60.4, 122.25, 51.78, 138.07, 37.39, 149.57, 34.52, 158.2, 23.01, 174.02, 2.88, 201.35, 11.51, 209.98, 24.45, 209.98, 41.71, 204.22, 51.78]], "area": 41688.90054999999, "iscrowd": 0, "image_id": 548822, "bbox": [66.16, 2.88, 212.85, 445.84], "category_id": 1, "id": 442246, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "red"], "raw": "A man wearing red.", "sent_id": 19842, "sent": "a man wearing red"}, {"tokens": ["a", "man", "in", "all", "red", "with", "a", "foot", "on", "the", "football"], "raw": "a man in all red with a foot on the football", "sent_id": 19843, "sent": "a man in all red with a foot on the football"}], "file_name": "COCO_train2014_000000548822_442246.jpg", "ann_id": 442246, "sent_ids": [19842, 19843], "ref_id": 12670}, {"segmentation": [[44.83, 107.53, 49.81, 100.06, 57.29, 97.07, 65.25, 101.06, 77.21, 112.51, 77.21, 120.48, 88.66, 130.45, 99.12, 137.92, 118.55, 181.75, 125.03, 194.2, 125.03, 215.12, 128.01, 237.04, 129.51, 243.01, 146.94, 254.47, 153.42, 269.91, 163.88, 281.37, 169.36, 286.35, 169.36, 288.84, 163.38, 293.82, 152.42, 304.78, 145.95, 305.77, 127.02, 305.77, 126.02, 303.28, 140.47, 297.8, 146.44, 291.83, 143.95, 291.33, 148.44, 285.85, 144.45, 275.89, 124.53, 256.46, 115.56, 250.48, 112.07, 246.5, 115.06, 227.57, 117.55, 221.1, 109.58, 220.6, 101.62, 227.07, 97.63, 219.11, 92.65, 212.63, 88.66, 213.63, 88.66, 220.6, 89.66, 227.57, 79.7, 227.57, 80.7, 226.08, 84.18, 224.58, 81.19, 222.09, 82.19, 215.62, 78.7, 216.61, 76.21, 208.65, 78.2, 203.17, 71.73, 188.22, 65.25, 173.78, 48.82, 171.29, 44.33, 174.28, 34.87, 176.77, 28.4, 173.28, 28.89, 167.8, 37.86, 163.82, 65.75, 160.33, 65.25, 142.4, 66.75, 136.42, 54.79, 130.94, 49.81, 124.97, 46.33, 125.46, 46.33, 120.98, 38.86, 117.99, 34.37, 114.01, 35.37, 110.52, 40.85, 110.02, 44.83, 108.53], [80.32, 233.89, 79.3, 240.8, 83.39, 252.32, 90.05, 253.09, 96.71, 253.09, 95.94, 248.48, 102.08, 247.2, 107.46, 246.18, 99.01, 245.41, 93.89, 234.4], [82.88, 268.96, 82.62, 277.67, 88.77, 271.52, 86.46, 267.68], [91.07, 266.92, 94.66, 275.37, 96.45, 266.4, 93.89, 267.17], [79.3, 285.09, 89.54, 274.34, 94.66, 282.28, 92.35, 294.82, 91.33, 298.92], [86.98, 298.92, 83.39, 302.76, 89.03, 301.23, 89.03, 304.04, 66.75, 304.04, 61.88, 306.86, 62.4, 304.04, 70.59, 294.57, 78.78, 288.94]], "area": 7773.027349999999, "iscrowd": 0, "image_id": 275917, "bbox": [28.4, 97.07, 140.96, 209.79], "category_id": 1, "id": 1718768, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "plaid", "shorts"], "raw": "A man wearing plaid shorts.", "sent_id": 19912, "sent": "a man wearing plaid shorts"}, {"tokens": ["a", "man", "in", "plaid", "shorts", "and", "a", "white", "tshirt", "to", "the", "left", "of", "the", "photo", "walking", "away"], "raw": "A man in plaid shorts and a white tshirt to the left of the photo walking away.", "sent_id": 19913, "sent": "a man in plaid shorts and a white tshirt to the left of the photo walking away"}], "file_name": "COCO_train2014_000000275917_1718768.jpg", "ann_id": 1718768, "sent_ids": [19912, 19913], "ref_id": 12698}, {"segmentation": [[170.6, 111.8, 175.24, 128.37, 183.85, 136.33, 190.48, 140.31, 197.11, 156.88, 207.06, 176.77, 206.39, 205.94, 178.55, 222.51, 182.53, 245.71, 177.23, 264.27, 150.05, 259.63, 125.52, 261.62, 107.62, 265.6, 106.95, 264.94, 103.64, 247.7, 89.06, 236.43, 79.77, 224.5, 83.75, 190.03, 97.67, 176.77, 108.94, 170.14, 116.24, 161.52, 120.21, 141.63, 130.82, 129.04, 136.12, 121.74, 136.12, 109.15, 147.39, 102.52, 168.61, 103.18]], "area": 13346.460649999999, "iscrowd": 0, "image_id": 421618, "bbox": [79.77, 102.52, 127.29, 163.08], "category_id": 1, "id": 432311, "split": "val", "sentences": [{"tokens": ["the", "person", "sitting", "to", "the", "left", "of", "the", "scale"], "raw": "The person sitting to the left of the scale.", "sent_id": 19946, "sent": "the person sitting to the left of the scale"}, {"tokens": ["woman", "selling", "produce", "in", "an", "outdoor", "marketplace"], "raw": "Woman selling produce in an outdoor marketplace", "sent_id": 19947, "sent": "woman selling produce in an outdoor marketplace"}], "file_name": "COCO_train2014_000000421618_432311.jpg", "ann_id": 432311, "sent_ids": [19946, 19947], "ref_id": 12712}, {"segmentation": [[314.95, 208.69, 271.87, 351.33, 333.14, 358.03, 357.07, 354.2, 395.37, 349.42, 435.57, 336.97, 499.71, 312.08, 538.0, 291.98, 572.47, 269.96, 582.04, 259.43, 583.0, 246.98]], "area": 29230.841050000003, "iscrowd": 0, "image_id": 47001, "bbox": [271.87, 208.69, 311.13, 149.34], "category_id": 59, "id": 1077664, "split": "val", "sentences": [{"tokens": ["a", "piece", "o", "pizza", "from", "the", "whole", "pizza", "in", "a", "plate"], "raw": "A piece o pizza from the whole pizza in a plate", "sent_id": 20030, "sent": "a piece o pizza from the whole pizza in a plate"}], "file_name": "COCO_train2014_000000047001_1077664.jpg", "ann_id": 1077664, "sent_ids": [20030], "ref_id": 12742}, {"segmentation": [[372.31, 318.37, 375.03, 292.04, 438.6, 192.15, 537.58, 19.61, 536.67, 18.71, 546.66, 0.54, 636.56, 1.45, 640.0, 1.45, 640.0, 375.58, 631.11, 401.0, 543.93, 401.0, 381.39, 342.89]], "area": 74995.843, "iscrowd": 0, "image_id": 524866, "bbox": [372.31, 0.54, 267.69, 400.46], "category_id": 77, "id": 328038, "split": "val", "sentences": [{"tokens": ["windows", "laptop"], "raw": "windows laptop", "sent_id": 20054, "sent": "windows laptop"}, {"tokens": ["a", "laptop"], "raw": "A laptop", "sent_id": 20055, "sent": "a laptop"}], "file_name": "COCO_train2014_000000524866_328038.jpg", "ann_id": 328038, "sent_ids": [20054, 20055], "ref_id": 12754}, {"segmentation": [[304.12, 417.63, 275.11, 493.44, 260.13, 497.89, 288.21, 421.15], [258.26, 412.73, 194.62, 480.11, 180.58, 485.73, 173.1, 483.86, 223.64, 435.19, 245.16, 410.86], [308.8, 392.85, 313.48, 376.94, 309.74, 376.01, 306.93, 378.82], [277.92, 391.92, 290.08, 379.75, 287.28, 375.07, 276.04, 383.49]], "area": 2313.592950000003, "iscrowd": 0, "image_id": 577246, "bbox": [173.1, 375.07, 140.38, 122.82], "category_id": 35, "id": 608478, "split": "val", "sentences": [{"tokens": ["the", "skis", "on", "the", "feet", "of", "the", "woman", "with", "the", "brown", "cap"], "raw": "The skis on the feet of the woman with the brown cap.", "sent_id": 20069, "sent": "the skis on the feet of the woman with the brown cap"}, {"tokens": ["skis", "of", "woman", "wearing", "blue", ",", "white", ",", "and", "red"], "raw": "skis of woman wearing blue, white, and red", "sent_id": 20070, "sent": "skis of woman wearing blue , white , and red"}], "file_name": "COCO_train2014_000000577246_608478.jpg", "ann_id": 608478, "sent_ids": [20069, 20070], "ref_id": 12761}, {"segmentation": [[222.02, 469.66, 95.0, 469.66, 59.78, 456.85, 28.82, 420.56, 3.2, 359.72, 0.0, 290.34, 22.42, 224.16, 59.78, 186.8, 104.61, 165.45, 175.06, 152.64, 204.94, 157.98, 268.99, 195.34, 304.21, 235.9, 322.36, 274.33, 322.36, 345.84, 308.48, 393.88, 274.33, 436.57, 232.7, 466.46]], "area": 82973.99345, "iscrowd": 0, "image_id": 572602, "bbox": [0.0, 152.64, 322.36, 317.02], "category_id": 51, "id": 1040573, "split": "val", "sentences": [{"tokens": ["strawberry", "pieces", "in", "a", "green", "bowl"], "raw": "STRAWBERRY PIECES IN A GREEN BOWL", "sent_id": 20127, "sent": "strawberry pieces in a green bowl"}, {"tokens": ["strawberries", "in", "bowl"], "raw": "strawberries in bowl", "sent_id": 20128, "sent": "strawberries in bowl"}], "file_name": "COCO_train2014_000000572602_1040573.jpg", "ann_id": 1040573, "sent_ids": [20127, 20128], "ref_id": 12784}, {"segmentation": [[0.0, 5.64, 1.06, 30.58, 16.47, 56.62, 17.93, 63.22, 20.02, 68.18, 30.79, 64.2, 28.39, 65.39, 38.36, 81.34, 51.51, 81.34, 45.93, 63.8, 38.36, 57.02, 28.79, 50.25, 25.6, 28.32, 25.6, 13.17, 27.6, 2.41, 57.49, 2.01, 55.9, 5.2, 59.49, 11.58, 66.66, 40.28, 66.66, 51.04, 59.09, 59.02, 55.1, 63.4, 59.49, 83.33, 149.18, 78.95, 145.59, 69.38, 149.97, 64.6, 149.57, 43.47, 145.99, 23.14, 140.41, 18.36, 127.25, 15.96, 124.46, 13.97, 122.87, 10.38, 124.06, 6.8, 133.23, 2.41, 135.62, 0.82, 0.89, 0.02]], "area": 8484.905100000002, "iscrowd": 0, "image_id": 320834, "bbox": [0.0, 0.02, 149.97, 83.31], "category_id": 1, "id": 1709022, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "plaid", "shirt", "with", "blue", "pants"], "raw": "A person in a plaid shirt with blue pants", "sent_id": 20143, "sent": "a person in a plaid shirt with blue pants"}, {"tokens": ["white", "color", "shirt"], "raw": "white color shirt", "sent_id": 20144, "sent": "white color shirt"}], "file_name": "COCO_train2014_000000320834_1709022.jpg", "ann_id": 1709022, "sent_ids": [20143, 20144], "ref_id": 12792}, {"segmentation": [[240.54, 293.79, 254.31, 393.87, 270.84, 402.13, 257.07, 425.08, 276.35, 403.05, 385.6, 426.0, 388.36, 400.29, 395.7, 325.01, 385.6, 320.42, 384.69, 298.38, 376.42, 305.73, 238.71, 286.45, 240.54, 297.47]], "area": 16411.061450000005, "iscrowd": 0, "image_id": 200010, "bbox": [238.71, 286.45, 156.99, 139.55], "category_id": 62, "id": 109396, "split": "val", "sentences": [{"tokens": ["a", "lawn", "chair", ",", "its", "back", "is", "directly", "facing", "the", "camera"], "raw": "A lawn chair, its back is directly facing the camera.", "sent_id": 20153, "sent": "a lawn chair , its back is directly facing the camera"}, {"tokens": ["the", "back", "of", "a", "chair", "without", "cushions"], "raw": "The back of a chair without cushions.", "sent_id": 20154, "sent": "the back of a chair without cushions"}], "file_name": "COCO_train2014_000000200010_109396.jpg", "ann_id": 109396, "sent_ids": [20153, 20154], "ref_id": 12794}, {"segmentation": [[444.62, 273.77, 459.03, 304.65, 480.64, 354.05, 435.36, 367.43, 419.92, 366.4, 443.59, 343.76, 417.86, 269.65, 429.18, 248.04, 458.0, 209.96, 441.53, 198.64, 420.95, 224.37, 396.25, 216.13, 434.33, 193.49, 436.39, 139.97, 441.53, 119.39, 424.04, 110.13, 423.01, 65.87, 448.74, 64.84, 474.47, 65.87, 486.82, 120.42, 474.47, 122.48, 491.96, 166.73, 499.17, 200.7, 527.99, 258.33, 508.43, 273.77, 542.4, 303.62, 575.33, 332.44, 588.71, 336.55, 581.51, 360.22, 567.1, 368.46, 560.92, 350.96, 491.96, 294.36, 476.53, 277.89, 448.74, 273.77]], "area": 19525.01040000001, "iscrowd": 0, "image_id": 90573, "bbox": [396.25, 64.84, 192.46, 303.62], "category_id": 1, "id": 555328, "split": "val", "sentences": [{"tokens": ["the", "girl", "wearing", "a", "yellow", "shirt"], "raw": "The girl wearing a yellow shirt.", "sent_id": 20223, "sent": "the girl wearing a yellow shirt"}, {"tokens": ["the", "player", "in", "a", "yellow", "shirt"], "raw": "The player in a yellow shirt.", "sent_id": 20224, "sent": "the player in a yellow shirt"}], "file_name": "COCO_train2014_000000090573_555328.jpg", "ann_id": 555328, "sent_ids": [20223, 20224], "ref_id": 12818}, {"segmentation": [[172.2, 86.64, 181.88, 76.41, 194.26, 68.88, 199.1, 66.73, 213.09, 65.65, 236.77, 72.11, 247.0, 82.87, 254.35, 98.05, 244.41, 120.42, 237.66, 128.94, 233.76, 132.84, 227.01, 142.07, 217.42, 153.08, 217.42, 153.08, 222.75, 165.86, 223.81, 172.96, 222.04, 179.0, 221.68, 196.56, 220.26, 203.66, 219.2, 207.92, 143.22, 208.98, 131.15, 191.72, 125.92, 184.57, 119.46, 182.96, 114.08, 180.27, 111.93, 177.58, 118.39, 171.12, 116.23, 167.89, 109.78, 160.36, 108.7, 157.13, 111.93, 153.9, 114.08, 152.29, 114.08, 149.06, 116.77, 145.83, 118.39, 145.29, 118.39, 141.52, 122.69, 139.91, 127.53, 142.06, 127.0, 138.83, 131.3, 136.68, 137.76, 138.83, 143.68, 146.37, 145.29, 157.13, 146.37, 159.82, 146.91, 160.36, 151.21, 168.43, 159.28, 171.66, 163.59, 161.43, 163.05, 153.9, 159.28, 140.45, 160.9, 130.76, 160.9, 125.92, 165.74, 121.61, 165.74, 116.23, 163.59, 112.47, 165.74, 106.55, 167.35, 98.48, 169.51, 93.09, 171.12, 86.64], [90.94, 136.68, 94.71, 130.22, 97.4, 129.15, 99.01, 125.38, 103.86, 123.77, 107.09, 125.92, 109.24, 132.38, 105.47, 137.22, 103.32, 136.68, 103.32, 139.91, 100.63, 142.06, 100.63, 145.83, 99.01, 147.44, 96.86, 147.98, 90.94, 147.44, 86.1, 144.75, 87.71, 139.37, 91.48, 137.76], [24.18, 187.05, 11.6, 195.44, 1.12, 197.12, 1.12, 210.11, 66.11, 210.11, 65.27, 205.5, 68.63, 203.41, 69.88, 201.31, 69.88, 199.63, 65.69, 196.28, 61.92, 192.92, 63.17, 187.05, 71.56, 185.8, 73.24, 184.12, 69.88, 180.34, 68.63, 174.47, 71.14, 171.96, 79.11, 173.64, 81.62, 174.06, 81.62, 172.8, 78.69, 169.44, 77.01, 168.6, 75.75, 169.44, 73.24, 170.28, 70.72, 169.86, 66.95, 170.7, 64.85, 168.19, 62.76, 171.54, 62.34, 168.19, 63.17, 163.99, 63.17, 161.06, 65.27, 158.96, 62.76, 158.96, 52.69, 158.96, 48.08, 162.32, 43.89, 165.67, 39.7, 169.02, 35.08, 174.06, 31.31, 178.25, 23.34, 188.31]], "area": 14308.553349999993, "iscrowd": 0, "image_id": 551869, "bbox": [1.12, 65.65, 253.23, 144.46], "category_id": 1, "id": 192216, "split": "val", "sentences": [{"tokens": ["small", "baby", "eating", "banana", "with", "her", "mom"], "raw": "Small Baby Eating banana with her mom", "sent_id": 20225, "sent": "small baby eating banana with her mom"}, {"tokens": ["a", "baby", "eating", "a", "banana"], "raw": "A baby eating a banana.", "sent_id": 20226, "sent": "a baby eating a banana"}], "file_name": "COCO_train2014_000000551869_192216.jpg", "ann_id": 192216, "sent_ids": [20225, 20226], "ref_id": 12819}, {"segmentation": [[385.12, 384.23, 385.61, 369.59, 381.71, 351.55, 374.39, 322.77, 366.59, 297.4, 358.29, 273.02, 360.25, 269.6, 366.59, 264.24, 387.56, 255.94, 407.07, 249.11, 426.58, 241.8, 435.36, 238.87, 442.68, 238.87, 449.02, 244.24, 449.51, 250.09, 441.21, 260.33, 436.83, 272.04, 438.29, 276.92, 449.02, 274.97, 458.77, 276.92, 462.68, 293.5, 466.58, 313.01, 467.55, 323.26, 467.55, 329.11, 386.1, 383.25]], "area": 9583.006099999999, "iscrowd": 0, "image_id": 160866, "bbox": [358.29, 238.87, 109.26, 145.36], "category_id": 62, "id": 378280, "split": "val", "sentences": [{"tokens": ["a", "chair"], "raw": "a chair", "sent_id": 20282, "sent": "a chair"}, {"tokens": ["an", "empty", "chair", "at", "a", "desk"], "raw": "An empty chair at a desk.", "sent_id": 20283, "sent": "an empty chair at a desk"}], "file_name": "COCO_train2014_000000160866_378280.jpg", "ann_id": 378280, "sent_ids": [20282, 20283], "ref_id": 12841}, {"segmentation": [[184.4, 419.67, 196.29, 404.82, 189.36, 330.54, 174.5, 305.78, 167.57, 259.24, 150.73, 293.9, 142.81, 299.84, 125.97, 286.97, 132.91, 258.25, 125.97, 212.69, 125.97, 203.78, 111.12, 201.8, 105.18, 187.93, 139.84, 182.98, 154.69, 156.24, 184.4, 150.3, 196.29, 175.06, 230.95, 188.92, 244.82, 192.88, 276.51, 177.04, 317.11, 187.93, 336.92, 214.67, 336.92, 258.25, 322.06, 313.7, 312.16, 380.06, 312.16, 405.81, 297.3, 413.73, 281.46, 401.84, 289.38, 336.48, 282.45, 327.57, 262.64, 303.8, 235.9, 303.8, 233.92, 419.67, 231.94, 429.57, 226.0, 434.53, 216.1, 429.57, 218.08, 395.9, 218.08, 318.66, 204.21, 311.72, 209.16, 408.78, 205.2, 427.59, 198.27, 433.54, 185.4, 427.59]], "area": 33308.202150000005, "iscrowd": 0, "image_id": 332385, "bbox": [105.18, 150.3, 231.74, 284.23], "category_id": 24, "id": 590393, "split": "val", "sentences": [{"tokens": ["a", "zebra", "in", "front", "of", "two", "others"], "raw": "A zebra in front of two others.", "sent_id": 20347, "sent": "a zebra in front of two others"}, {"tokens": ["the", "zebra", "whose", "face", "is", "visible"], "raw": "The zebra whose face is visible", "sent_id": 20348, "sent": "the zebra whose face is visible"}], "file_name": "COCO_train2014_000000332385_590393.jpg", "ann_id": 590393, "sent_ids": [20347, 20348], "ref_id": 12864}, {"segmentation": [[214.17, 371.25, 219.55, 352.95, 227.09, 340.04, 256.14, 330.35, 299.19, 315.28, 372.38, 312.05, 415.43, 308.83, 468.16, 312.05, 471.39, 319.59, 446.64, 362.64, 444.48, 420.75, 418.65, 442.28, 394.98, 463.8, 347.62, 463.8, 292.74, 433.67, 231.39, 404.61]], "area": 28238.23115, "iscrowd": 0, "image_id": 215569, "bbox": [214.17, 308.83, 257.22, 154.97], "category_id": 67, "id": 392057, "split": "val", "sentences": [{"tokens": ["a", "row", "of", "glasses", "with", "a", "womens", "hand"], "raw": "a row of glasses with a womens hand", "sent_id": 20357, "sent": "a row of glasses with a womens hand"}, {"tokens": ["a", "row", "of", "four", "wine", "glasses"], "raw": "A row of four wine glasses.", "sent_id": 20358, "sent": "a row of four wine glasses"}], "file_name": "COCO_train2014_000000215569_392057.jpg", "ann_id": 392057, "sent_ids": [20357, 20358], "ref_id": 12869}, {"segmentation": [[81.62, 1.02, 77.54, 30.61, 118.35, 88.76, 157.11, 126.51, 178.54, 142.83, 187.72, 162.22, 176.5, 162.22, 170.38, 159.16, 184.66, 179.56, 179.56, 194.86, 166.3, 187.72, 131.61, 145.89, 76.52, 97.94, 51.01, 66.31, 27.55, 53.05, 0.0, 58.15, 2.04, 1.02]], "area": 10435.156299999999, "iscrowd": 0, "image_id": 295613, "bbox": [0.0, 1.02, 187.72, 193.84], "category_id": 1, "id": 1246318, "split": "val", "sentences": [{"tokens": ["adult", "arm", "reaching", "down", "towards", "a", "baby"], "raw": "adult arm reaching down towards a baby", "sent_id": 20416, "sent": "adult arm reaching down towards a baby"}, {"tokens": ["a", "hand", "reaching", "down", "to", "receive", "something", "from", "the", "baby"], "raw": "A hand reaching down to receive something from the baby.", "sent_id": 20417, "sent": "a hand reaching down to receive something from the baby"}], "file_name": "COCO_train2014_000000295613_1246318.jpg", "ann_id": 1246318, "sent_ids": [20416, 20417], "ref_id": 12894}, {"segmentation": [[497.47, 322.19, 497.47, 364.67, 513.92, 389.34, 530.36, 403.04, 538.59, 434.56, 542.7, 494.86, 541.33, 527.76, 520.77, 564.76, 504.33, 570.24, 493.36, 552.42, 483.77, 520.9, 478.29, 485.27, 464.58, 483.9, 457.73, 522.27, 448.14, 540.09, 431.69, 538.72, 415.25, 511.31, 407.02, 488.01, 405.65, 440.05, 413.88, 418.12, 416.62, 397.56, 422.1, 366.04, 438.54, 397.56, 433.06, 426.34, 449.51, 438.68, 467.32, 424.97, 478.29, 397.56, 479.66, 381.12, 481.03, 372.89, 481.03, 356.45, 446.77, 318.08, 454.99, 316.71, 479.66, 341.37, 485.14, 311.22]], "area": 18694.72055, "iscrowd": 0, "image_id": 523487, "bbox": [405.65, 311.22, 137.05, 259.02], "category_id": 2, "id": 127154, "split": "val", "sentences": [{"tokens": ["a", "blue", "bicycle"], "raw": "A blue bicycle.", "sent_id": 20431, "sent": "a blue bicycle"}, {"tokens": ["a", "blue", "bicycle", "ridden", "by", "a", "man", "in", "black", "shorts"], "raw": "A blue bicycle ridden by a man in black shorts", "sent_id": 20432, "sent": "a blue bicycle ridden by a man in black shorts"}], "file_name": "COCO_train2014_000000523487_127154.jpg", "ann_id": 127154, "sent_ids": [20431, 20432], "ref_id": 12900}, {"segmentation": [[148.65, 364.02, 156.25, 350.51, 158.78, 337.84, 157.09, 323.48, 157.94, 314.19, 160.47, 303.21, 135.14, 262.67, 140.2, 245.78, 142.74, 243.24, 138.51, 234.8, 144.43, 223.82, 156.25, 222.13, 149.49, 209.46, 156.25, 205.24, 174.83, 201.86, 186.66, 192.57, 192.57, 184.12, 195.95, 187.5, 211.15, 177.36, 234.8, 171.45, 241.55, 146.96, 246.62, 123.31, 255.91, 110.64, 250.84, 96.28, 277.03, 68.41, 293.92, 51.52, 304.05, 51.52, 308.28, 53.21, 311.66, 43.92, 320.1, 41.39, 333.61, 46.45, 365.71, 56.59, 391.89, 92.06, 411.32, 131.76, 418.07, 178.21, 402.03, 210.3, 411.32, 233.11, 421.45, 257.6, 401.18, 242.4, 380.07, 243.24, 383.45, 246.62, 423.14, 282.09, 460.3, 320.95, 468.75, 340.37, 482.26, 369.93]], "area": 70403.061, "iscrowd": 0, "image_id": 574563, "bbox": [135.14, 41.39, 347.12, 328.54], "category_id": 1, "id": 440446, "split": "val", "sentences": [{"tokens": ["a", "young", "dark", "haired", "asian", "girl", "about", "to", "take", "a", "bite", "out", "of", "a", "donut"], "raw": "a young dark haired asian girl about to take a bite out of a donut", "sent_id": 20486, "sent": "a young dark haired asian girl about to take a bite out of a donut"}, {"tokens": ["a", "girl", "pretending", "to", "eat", "a", "fake", "donut"], "raw": "a girl pretending to eat a fake donut", "sent_id": 20487, "sent": "a girl pretending to eat a fake donut"}], "file_name": "COCO_train2014_000000574563_440446.jpg", "ann_id": 440446, "sent_ids": [20486, 20487], "ref_id": 12919}, {"segmentation": [[4.14, 88.91, 34.46, 146.8, 81.32, 139.91, 82.7, 155.07, 48.24, 155.07, 49.62, 206.07, 45.49, 237.77, 44.11, 254.31, 38.59, 277.74, 33.08, 287.39, 16.54, 292.91, 67.54, 343.91, 84.08, 276.36, 93.73, 251.55, 113.03, 239.15, 117.16, 255.69, 119.92, 263.96, 164.03, 247.42, 165.41, 272.23, 165.41, 280.5, 164.03, 313.58, 155.76, 328.74, 136.46, 353.55, 130.95, 374.23, 169.54, 321.85, 195.73, 276.36, 226.05, 261.2, 249.49, 269.47, 271.54, 266.72, 288.08, 261.2, 292.22, 288.77, 281.19, 303.93, 271.54, 312.2, 257.76, 337.01, 221.92, 352.18, 216.41, 353.55, 183.32, 412.82, 146.11, 467.96, 97.86, 474.85, 93.73, 528.61, 64.78, 583.74, 48.24, 600.28, 2.76, 604.42, 0.0, 91.66]], "area": 59027.437450000005, "iscrowd": 0, "image_id": 578369, "bbox": [0.0, 88.91, 292.22, 515.51], "category_id": 1, "id": 423485, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "hat"], "raw": "a man wearing a hat", "sent_id": 20523, "sent": "a man wearing a hat"}, {"tokens": ["the", "man", "wearing", "a", "purple", "sweatshirt", "next", "to", "a", "woman"], "raw": "The man wearing a purple sweatshirt next to a woman.", "sent_id": 20524, "sent": "the man wearing a purple sweatshirt next to a woman"}], "file_name": "COCO_train2014_000000578369_423485.jpg", "ann_id": 423485, "sent_ids": [20523, 20524], "ref_id": 12929}, {"segmentation": [[365.66, 5.39, 495.1, 100.31, 634.25, 135.91, 636.4, 373.21, 579.24, 366.74, 590.02, 266.43, 378.61, 99.24, 306.34, 4.31]], "area": 36018.99479999999, "iscrowd": 0, "image_id": 19501, "bbox": [306.34, 4.31, 330.06, 368.9], "category_id": 1, "id": 514411, "split": "val", "sentences": [{"tokens": ["the", "person", "cheering", "in", "the", "white", "t", "-", "shirt"], "raw": "The person cheering in the white t-shirt.", "sent_id": 20542, "sent": "the person cheering in the white t - shirt"}, {"tokens": ["the", "arm", "of", "someone", "in", "a", "white", "shirt"], "raw": "The arm of someone in a white shirt.", "sent_id": 20543, "sent": "the arm of someone in a white shirt"}], "file_name": "COCO_train2014_000000019501_514411.jpg", "ann_id": 514411, "sent_ids": [20542, 20543], "ref_id": 12936}, {"segmentation": [[338.06, 584.02, 313.5, 598.47, 297.61, 598.47, 287.49, 585.46, 291.83, 568.13, 309.16, 550.79, 320.72, 513.23, 323.61, 485.78, 319.28, 475.67, 304.83, 503.12, 306.28, 517.56, 265.82, 556.57, 267.27, 490.11, 267.27, 477.11, 271.6, 455.44, 251.38, 443.88, 251.38, 423.66, 242.71, 388.98, 238.37, 374.54, 238.37, 357.2, 215.26, 347.09, 210.93, 326.86, 221.04, 305.19, 275.94, 163.61, 313.5, 126.05, 333.72, 56.7, 364.06, 59.59, 377.07, 9.03, 416.07, 17.7, 433.41, 42.26, 449.3, 88.49, 453.63, 140.5, 443.52, 199.73, 418.96, 222.84, 434.85, 280.63, 439.19, 318.19, 452.19, 371.65, 463.75, 399.1, 430.52, 436.66, 391.51, 432.33, 385.73, 456.88, 382.84, 471.33, 381.4, 504.56, 372.73, 547.9, 356.84, 571.02, 338.06, 585.46]], "area": 85757.66515, "iscrowd": 0, "image_id": 358543, "bbox": [210.93, 9.03, 252.82, 589.44], "category_id": 1, "id": 513689, "split": "val", "sentences": [{"tokens": ["a", "woman", "on", "a", "subway"], "raw": "A woman on a subway.", "sent_id": 20555, "sent": "a woman on a subway"}, {"tokens": ["women", "was", "smileing", "in", "train"], "raw": "women was smileing in train", "sent_id": 20556, "sent": "women was smileing in train"}], "file_name": "COCO_train2014_000000358543_513689.jpg", "ann_id": 513689, "sent_ids": [20555, 20556], "ref_id": 12942}, {"segmentation": [[184.55, 326.15, 171.74, 220.02, 336.43, 228.55, 332.16, 331.03, 183.94, 326.15]], "area": 16260.083799999997, "iscrowd": 0, "image_id": 437224, "bbox": [171.74, 220.02, 164.69, 111.01], "category_id": 72, "id": 32807, "split": "val", "sentences": [{"tokens": ["the", "screen", "on", "the", "back", "of", "the", "seat", "that", "says", "spoil", "yourself"], "raw": "the screen on the back of the seat that says SPOIL YOURSELF", "sent_id": 20640, "sent": "the screen on the back of the seat that says spoil yourself"}, {"tokens": ["the", "screen", "with", "text", "clearly", "on", "it"], "raw": "The screen with text clearly on it", "sent_id": 20641, "sent": "the screen with text clearly on it"}], "file_name": "COCO_train2014_000000437224_32807.jpg", "ann_id": 32807, "sent_ids": [20640, 20641], "ref_id": 12979}, {"segmentation": [[301.41, 421.42, 338.05, 391.19, 326.14, 299.57, 316.06, 286.75, 309.65, 285.83, 296.83, 284.0, 263.85, 303.24, 207.96, 290.41, 207.96, 281.25, 202.46, 268.43, 191.47, 261.1, 116.35, 276.67, 94.36, 285.83, 79.7, 292.25, 85.2, 392.1, 92.53, 419.59, 142.92, 421.42, 203.38, 421.42, 241.86, 421.42, 297.74, 421.42]], "area": 33852.48720000001, "iscrowd": 0, "image_id": 259120, "bbox": [79.7, 261.1, 258.35, 160.32], "category_id": 62, "id": 110725, "split": "val", "sentences": [{"tokens": ["light", "big", "brown", "chair"], "raw": "light big brown chair", "sent_id": 20700, "sent": "light big brown chair"}, {"tokens": ["a", "beige", "sofa", "sitting", "on", "a", "green", "carpet"], "raw": "A beige sofa sitting on a green carpet.", "sent_id": 20701, "sent": "a beige sofa sitting on a green carpet"}], "file_name": "COCO_train2014_000000259120_110725.jpg", "ann_id": 110725, "sent_ids": [20700, 20701], "ref_id": 12997}, {"segmentation": [[51.11, 200.83, 71.22, 178.9, 78.99, 168.84, 140.69, 145.53, 169.49, 140.96, 196.91, 141.87, 201.94, 139.59, 203.77, 143.24, 223.42, 150.1, 229.36, 147.82, 229.36, 151.47, 249.47, 162.44, 270.04, 180.27, 279.64, 183.92, 284.21, 193.52, 283.3, 196.72, 287.87, 201.75, 286.5, 215.92, 284.67, 215.92, 284.21, 234.66, 278.73, 265.74, 267.76, 291.79, 252.67, 306.24, 241.25, 317.67, 216.11, 332.29, 190.51, 339.15, 182.28, 340.98, 99.56, 169.12]], "area": 25282.901700000002, "iscrowd": 0, "image_id": 228133, "bbox": [51.11, 139.59, 236.76, 201.39], "category_id": 60, "id": 1079989, "split": "val", "sentences": [{"tokens": ["a", "donut", "with", "blue", "frosting", "and", "pink", "sprinkles"], "raw": "A donut with blue frosting and pink sprinkles.", "sent_id": 20722, "sent": "a donut with blue frosting and pink sprinkles"}, {"tokens": ["a", "donut", "with", "blue", "frosting"], "raw": "A donut with blue frosting.", "sent_id": 20723, "sent": "a donut with blue frosting"}], "file_name": "COCO_train2014_000000228133_1079989.jpg", "ann_id": 1079989, "sent_ids": [20722, 20723], "ref_id": 13005}, {"segmentation": [[327.87, 333.33, 313.82, 270.1, 274.0, 278.3, 261.12, 260.73, 230.68, 239.66, 241.22, 157.69, 265.81, 72.21, 281.03, 56.99, 290.4, 54.64, 292.74, 37.08, 314.99, 33.57, 333.0, 45.28, 333.0, 329.82]], "area": 19915.817049999998, "iscrowd": 0, "image_id": 323664, "bbox": [230.68, 33.57, 102.32, 299.76], "category_id": 1, "id": 524784, "split": "val", "sentences": [{"tokens": ["a", "man", "playing", "the", "wii", "with", "his", "hands", "up"], "raw": "A man playing the Wii with his hands up.", "sent_id": 20739, "sent": "a man playing the wii with his hands up"}, {"tokens": ["a", "man", "holding", "a", "wii", "remote", "above", "his", "head"], "raw": "A man holding a wii remote above his head.", "sent_id": 20740, "sent": "a man holding a wii remote above his head"}], "file_name": "COCO_train2014_000000323664_524784.jpg", "ann_id": 524784, "sent_ids": [20739, 20740], "ref_id": 13013}, {"segmentation": [[123.73, 470.91, 112.64, 412.69, 111.53, 396.61, 96.01, 360.56, 95.45, 338.38, 104.88, 313.43, 117.08, 302.9, 133.16, 297.35, 165.87, 301.79, 195.82, 318.98, 214.11, 342.27, 225.76, 366.66, 237.96, 415.46, 276.22, 398.82, 292.3, 398.27, 296.18, 419.89, 299.51, 468.13, 296.73, 478.12, 290.08, 478.12, 286.75, 455.38, 273.44, 455.94, 255.15, 478.12, 246.83, 479.22, 232.97, 479.78, 221.88, 479.22, 159.22, 478.12, 120.96, 478.12]], "area": 24240.91165, "iscrowd": 0, "image_id": 149921, "bbox": [95.45, 297.35, 204.06, 182.43], "category_id": 62, "id": 382856, "split": "val", "sentences": [{"tokens": ["chair", "under", "girl", "with", "green", "shorts"], "raw": "Chair under girl with green shorts.", "sent_id": 20833, "sent": "chair under girl with green shorts"}, {"tokens": ["an", "old", "chair"], "raw": "An old chair", "sent_id": 20834, "sent": "an old chair"}], "file_name": "COCO_train2014_000000149921_382856.jpg", "ann_id": 382856, "sent_ids": [20833, 20834], "ref_id": 13046}, {"segmentation": [[202.67, 470.52, 202.67, 470.52, 219.26, 442.07, 251.26, 431.41, 267.85, 400.59, 291.56, 385.19, 304.59, 363.85, 315.26, 357.93, 349.63, 328.3, 349.63, 328.3, 357.93, 305.78, 357.93, 305.78, 348.44, 290.37, 363.85, 250.07, 363.85, 250.07, 357.93, 224.0, 367.41, 220.44, 376.89, 220.44, 381.63, 209.78, 378.07, 194.37, 384.0, 189.63, 387.56, 177.78, 355.56, 154.07, 350.81, 143.41, 350.81, 143.41, 208.59, 112.59, 155.26, 110.22, 117.33, 109.04, 1.19, 118.52, 0.0, 385.19, 90.07, 429.04, 180.15, 470.52, 200.3, 470.52]], "area": 107086.0293, "iscrowd": 0, "image_id": 66034, "bbox": [0.0, 109.04, 387.56, 361.48], "category_id": 54, "id": 2219583, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "half", "on", "the", "left"], "raw": "The sandwich half on the left.", "sent_id": 20859, "sent": "the sandwich half on the left"}, {"tokens": ["half", "of", "a", "sliced", "sandwich", "that", "is", "closest", "to", "the", "white", "mug", "handle"], "raw": "Half of a sliced sandwich that is closest to the white mug handle.", "sent_id": 20860, "sent": "half of a sliced sandwich that is closest to the white mug handle"}], "file_name": "COCO_train2014_000000066034_2219583.jpg", "ann_id": 2219583, "sent_ids": [20859, 20860], "ref_id": 13056}, {"segmentation": [[80.33, 539.44, 95.47, 574.33, 100.74, 594.41, 104.03, 625.69, 95.47, 640.0, 54.32, 639.51, 0.0, 639.51, 0.0, 547.67, 0.0, 543.06, 0.0, 477.22, 0.33, 440.03, 5.6, 444.96, 8.56, 452.21, 8.89, 455.83, 11.53, 463.73]], "area": 13279.521049999996, "iscrowd": 0, "image_id": 125774, "bbox": [0.0, 440.03, 104.03, 199.97], "category_id": 1, "id": 2025487, "split": "val", "sentences": [{"tokens": ["the", "arm", "of", "a", "dark", "skinned", "person", "sitting", "next", "to", "a", "man", "holding", "a", "teddy", "bear"], "raw": "the arm of a dark skinned person sitting next to a man holding a teddy bear", "sent_id": 20868, "sent": "the arm of a dark skinned person sitting next to a man holding a teddy bear"}, {"tokens": ["the", "arm", "of", "the", "photo", "not", "being", "pictured"], "raw": "The arm of the photo not being pictured.", "sent_id": 20869, "sent": "the arm of the photo not being pictured"}], "file_name": "COCO_train2014_000000125774_2025487.jpg", "ann_id": 2025487, "sent_ids": [20868, 20869], "ref_id": 13059}, {"segmentation": [[419.46, 111.4, 396.08, 132.03, 363.07, 155.41, 303.94, 192.54, 265.43, 199.42, 221.42, 203.54, 160.91, 209.04, 125.15, 218.67, 101.77, 231.05, 68.76, 257.18, 57.76, 268.18, 46.76, 287.43, 30.26, 308.06, 19.25, 339.69, 27.51, 374.08, 44.01, 404.33, 71.51, 413.96, 92.14, 349.32, 152.66, 272.31, 221.42, 257.18, 269.56, 236.55, 314.94, 221.42, 336.94, 200.79, 422.21, 143.03, 433.21, 130.65, 423.59, 119.65]], "area": 24750.661000000007, "iscrowd": 0, "image_id": 560180, "bbox": [19.25, 111.4, 413.96, 302.56], "category_id": 43, "id": 656076, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "white", "zebra", "design", "tennis", "bat"], "raw": "A BLACK AND WHITE ZEBRA DESIGN TENNIS BAT", "sent_id": 20886, "sent": "a black and white zebra design tennis bat"}, {"tokens": ["a", "black", "and", "white", "racquet", "next", "to", "a", "yellow", "racquet", "in", "a", "fence"], "raw": "A black and white racquet next to a yellow racquet in a fence.", "sent_id": 20887, "sent": "a black and white racquet next to a yellow racquet in a fence"}], "file_name": "COCO_train2014_000000560180_656076.jpg", "ann_id": 656076, "sent_ids": [20886, 20887], "ref_id": 13067}, {"segmentation": [[207.04, 134.88, 189.27, 125.61, 172.27, 125.61, 152.96, 121.75, 134.42, 121.75, 122.83, 116.34, 118.97, 115.57, 115.88, 120.98, 107.38, 124.07, 103.52, 125.61, 96.57, 127.16, 91.16, 121.75, 89.61, 119.43, 93.48, 134.11, 91.93, 146.47, 90.39, 154.97, 91.16, 164.24, 88.07, 185.87, 91.16, 209.05, 92.7, 209.05, 102.75, 211.36, 108.15, 211.36, 110.47, 208.27, 115.88, 199.78, 125.15, 185.1, 134.42, 171.97, 139.83, 175.06, 150.64, 184.33, 152.96, 199.78, 163.0, 218.32, 166.87, 224.5, 176.14, 242.27, 178.45, 253.08, 186.18, 275.48, 190.04, 286.3, 191.59, 294.8, 186.95, 306.39, 183.09, 311.79, 180.0, 323.38, 179.23, 329.56, 186.95, 330.33, 196.22, 331.11, 206.27, 327.24, 206.27, 323.38, 203.18, 319.52, 207.81, 312.57, 210.13, 311.02, 209.36, 301.75, 205.49, 295.57, 204.72, 289.39, 208.58, 275.48, 207.81, 266.99, 203.18, 256.17, 210.9, 238.4, 207.04, 225.27, 214.76, 224.5, 224.03, 225.27, 247.21, 225.27, 263.43, 216.77, 266.52, 212.91, 265.75, 230.68, 272.7, 241.49, 274.25, 245.36, 279.66, 262.35, 281.2, 266.99, 279.66, 285.53, 279.66, 295.57, 272.7, 306.39, 267.3, 310.25, 277.34, 314.11, 285.06, 314.11, 287.38, 310.25, 288.93, 300.21, 295.11, 294.03, 295.11, 288.62, 294.33, 273.17, 292.79, 261.58, 292.02, 248.45, 292.79, 243.04, 283.52, 223.73, 288.93, 208.27, 298.2, 209.05, 302.83, 223.73, 306.7, 238.4, 311.33, 256.94, 315.19, 263.12, 316.74, 279.35, 316.74, 280.89, 313.65, 295.57, 309.01, 311.02, 307.47, 317.2, 319.06, 317.97, 322.92, 317.97, 329.1, 315.66, 326.78, 307.93, 326.78, 306.39, 324.46, 296.34, 326.01, 277.8, 322.92, 262.35, 326.01, 241.49, 320.6, 230.68, 322.15, 216.0, 322.15, 193.6, 322.92, 177.37, 314.42, 162.7, 306.7, 151.11, 298.97, 143.38, 292.79, 138.75, 285.06, 134.88, 278.88, 134.11, 260.34, 131.79, 252.62, 135.66, 238.71, 143.38, 229.44, 141.84, 221.72, 139.52, 213.99, 135.66, 208.58, 134.88]], "area": 24199.055050000003, "iscrowd": 0, "image_id": 275658, "bbox": [88.07, 115.57, 241.03, 215.54], "category_id": 19, "id": 53544, "split": "val", "sentences": [{"tokens": ["a", "dappled", "gray", "horse", "pulling", "a", "red", "cart"], "raw": "A dappled gray horse pulling a red cart", "sent_id": 20948, "sent": "a dappled gray horse pulling a red cart"}, {"tokens": ["the", "grey", "horse", "with", "its", "whole", "body", "visible"], "raw": "The grey horse with its whole body visible.", "sent_id": 20949, "sent": "the grey horse with its whole body visible"}], "file_name": "COCO_train2014_000000275658_53544.jpg", "ann_id": 53544, "sent_ids": [20948, 20949], "ref_id": 13094}, {"segmentation": [[2.16, 30.95, 25.89, 55.76, 26.97, 70.86, 46.38, 112.93, 49.62, 162.55, 58.25, 224.03, 48.54, 238.05, 56.09, 282.28, 67.96, 326.5, 65.8, 363.18, 79.82, 382.59, 69.03, 402.01, 73.35, 417.11, 58.25, 419.27, 45.3, 421.42, 36.67, 416.03, 36.67, 400.93, 30.2, 392.3, 29.12, 371.81, 21.57, 340.52, 12.94, 309.24, 1.08, 256.39]], "area": 16693.661050000006, "iscrowd": 0, "image_id": 389743, "bbox": [1.08, 30.95, 78.74, 390.47], "category_id": 1, "id": 469512, "split": "val", "sentences": [{"tokens": ["the", "man", "watching", "the", "tennis", "match"], "raw": "The man watching the tennis match", "sent_id": 21030, "sent": "the man watching the tennis match"}, {"tokens": ["body", "of", "person", "standing", "in", "the", "corner", "of", "the", "pic"], "raw": "body of person standing in the corner of the pic", "sent_id": 21031, "sent": "body of person standing in the corner of the pic"}], "file_name": "COCO_train2014_000000389743_469512.jpg", "ann_id": 469512, "sent_ids": [21030, 21031], "ref_id": 13121}, {"segmentation": [[241.76, 302.56, 237.1, 325.15, 236.81, 335.45, 237.39, 341.05, 237.1, 347.23, 236.51, 353.71, 240.04, 361.36, 245.05, 366.96, 240.93, 365.19, 237.39, 363.43, 232.68, 362.54, 230.92, 361.95, 227.68, 361.66, 217.96, 361.66, 209.72, 365.19, 209.13, 366.66, 211.78, 367.55, 218.84, 367.55, 226.21, 367.55, 233.57, 369.9, 242.69, 371.08, 245.64, 371.08, 246.82, 372.26, 258.08, 366.21, 258.08, 365.21, 259.09, 363.42, 259.64, 362.75, 260.09, 361.75, 261.43, 360.41, 263.1, 359.18, 265.45, 357.06, 268.12, 360.74, 272.14, 364.65, 274.59, 368.67, 278.39, 371.9, 282.07, 369.22, 283.63, 367.77, 286.64, 366.66, 289.43, 363.53, 290.1, 363.42, 291.22, 367.33, 291.33, 368.55, 293.0, 370.23, 296.8, 373.13, 299.36, 372.91, 302.82, 370.67, 303.6, 368.78, 305.05, 365.54, 306.39, 363.09, 311.97, 358.85, 321.01, 348.02, 327.26, 337.2, 339.42, 320.02, 343.32, 314.44, 349.35, 305.96, 360.39, 291.79, 371.44, 278.52, 376.68, 270.6, 382.93, 261.78, 382.82, 246.83, 382.82, 244.38, 379.25, 243.04, 369.43, 242.14, 365.86, 246.61, 365.97, 248.95, 363.74, 248.62, 362.73, 250.18, 355.15, 257.65, 352.47, 258.66, 352.02, 257.54, 349.01, 257.88, 348.12, 258.99, 348.23, 255.09, 344.21, 253.64, 342.65, 253.64, 341.54, 254.64, 341.31, 255.31, 340.31, 254.08, 335.07, 251.29, 331.38, 249.51, 329.93, 249.17, 327.59, 247.95, 324.91, 247.95, 323.13, 247.83, 319.67, 249.62, 316.77, 252.41, 314.42, 253.75, 312.64, 255.09, 311.19, 256.65, 309.85, 256.43, 305.95, 260.22, 299.81, 263.45, 292.78, 267.69, 282.07, 273.38, 273.25, 278.96, 258.08, 287.89, 253.62, 294.14, 252.84, 299.94, 250.83, 299.16, 248.71, 298.71, 246.59, 298.82, 243.8, 300.05, 242.68, 301.39, 241.79, 302.84]], "area": 10887.973800000003, "iscrowd": 0, "image_id": 339579, "bbox": [209.13, 242.14, 173.8, 130.99], "category_id": 54, "id": 313437, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "standing", "next", "to", "the", "man", "'", "s", "thumb"], "raw": "The sandwich standing next to the man's thumb.", "sent_id": 21033, "sent": "the sandwich standing next to the man ' s thumb"}], "file_name": "COCO_train2014_000000339579_313437.jpg", "ann_id": 313437, "sent_ids": [21033], "ref_id": 13122}, {"segmentation": [[566.72, 169.44, 544.71, 154.13, 531.3, 151.25, 445.15, 152.21, 427.91, 152.21, 403.98, 176.14, 399.2, 269.96, 400.15, 280.49, 406.85, 289.11, 430.79, 286.23, 437.49, 292.93, 539.92, 292.93, 553.32, 288.15, 560.02, 279.53, 557.15, 234.54, 558.11, 198.16, 557.15, 177.1]], "area": 21445.500699999997, "iscrowd": 0, "image_id": 131449, "bbox": [399.2, 151.25, 167.52, 141.68], "category_id": 6, "id": 163875, "split": "val", "sentences": [{"tokens": ["the", "bus", "on", "the", "right"], "raw": "The bus on the right", "sent_id": 21037, "sent": "the bus on the right"}, {"tokens": ["the", "bus", "no", "is", "1232", "and", "it", "is", "on", "the", "left", "side"], "raw": "The bus no is 1232 and it is on the left side.", "sent_id": 21038, "sent": "the bus no is 1232 and it is on the left side"}], "file_name": "COCO_train2014_000000131449_163875.jpg", "ann_id": 163875, "sent_ids": [21037, 21038], "ref_id": 13125}, {"segmentation": [[295.88, 8.54, 305.15, 16.45, 310.33, 24.08, 306.97, 26.23, 305.95, 28.13, 307.7, 31.49, 303.17, 33.53, 301.71, 35.14, 298.35, 36.31, 291.78, 27.98, 285.35, 22.29, 279.07, 19.51, 268.99, 17.9, 262.86, 18.34, 254.97, 21.85, 249.71, 27.11, 246.21, 35.14, 245.04, 40.25, 240.51, 50.92, 242.7, 54.28, 244.16, 57.49, 244.45, 62.75, 236.23, 68.65, 244.65, 84.05, 235.26, 95.6, 223.23, 113.4, 212.65, 137.95, 197.01, 134.58, 189.79, 133.86, 170.54, 137.71, 165.97, 135.78, 151.29, 134.1, 138.54, 137.22, 139.02, 149.25, 138.54, 149.98, 117.61, 148.53, 114.96, 78.27, 114.72, 71.78, 113.28, 57.82, 114.48, 32.8, 117.85, 23.66, 119.53, 13.55, 122.9, 5.37, 129.88, 0.08, 185.94, 0.8, 190.51, 2.24, 199.65, 0.0, 235.02, 0.08, 240.08, 4.41, 245.13, 5.13, 250.9, 3.68, 264.62, 2.72, 282.91, 2.24, 296.38, 8.74]], "area": 17814.18355, "iscrowd": 0, "image_id": 402448, "bbox": [113.28, 0.0, 197.05, 149.98], "category_id": 62, "id": 1936752, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "to", "the", "left", "of", "a", "cat", "on", "a", "table"], "raw": "A wooden chair to the left of a cat on a table.", "sent_id": 21095, "sent": "a wooden chair to the left of a cat on a table"}, {"tokens": ["a", "wooden", "chair", "that", "is", "on", "the", "left", "and", "is", "behind", "the", "cat", "on", "the", "table"], "raw": "A wooden chair that is on the left and is behind the cat on the table.", "sent_id": 21096, "sent": "a wooden chair that is on the left and is behind the cat on the table"}], "file_name": "COCO_train2014_000000402448_1936752.jpg", "ann_id": 1936752, "sent_ids": [21095, 21096], "ref_id": 13147}, {"segmentation": [[145.01, 286.38, 152.3, 261.6, 153.76, 241.2, 151.57, 229.54, 148.65, 225.17, 146.47, 214.24, 157.4, 198.93, 163.23, 190.92, 165.41, 170.52, 178.53, 156.67, 201.12, 167.6, 222.98, 205.49, 239.74, 227.35, 277.63, 231.0, 317.71, 227.35, 356.33, 222.98, 396.41, 225.9, 419.73, 241.93, 451.79, 244.84, 472.2, 258.69, 472.93, 279.82, 453.25, 297.31, 440.86, 305.33, 428.48, 297.31, 440.13, 319.9, 354.88, 320.63, 239.74, 314.8, 221.52, 312.61, 200.39, 314.07, 186.55, 309.7, 175.62, 304.6, 153.03, 306.05, 145.01, 297.31, 142.1, 287.11]], "area": 30612.923800000004, "iscrowd": 0, "image_id": 236406, "bbox": [142.1, 156.67, 330.83, 163.96], "category_id": 24, "id": 591341, "split": "val", "sentences": [{"tokens": ["a", "zebra", "laying", "down", "in", "an", "enclosure"], "raw": "A zebra laying down in an enclosure.", "sent_id": 21117, "sent": "a zebra laying down in an enclosure"}, {"tokens": ["a", "zebra", "in", "the", "zoo", "setting"], "raw": "A zebra in the zoo setting.", "sent_id": 21118, "sent": "a zebra in the zoo setting"}], "file_name": "COCO_train2014_000000236406_591341.jpg", "ann_id": 591341, "sent_ids": [21117, 21118], "ref_id": 13155}, {"segmentation": [[549.14, 406.8, 547.21, 387.57, 549.14, 376.03, 549.14, 362.57, 548.18, 347.18, 539.52, 328.91, 539.52, 310.63, 539.52, 297.17, 537.6, 278.9, 541.44, 258.7, 545.29, 251.97, 545.29, 210.61, 539.52, 190.42, 531.83, 142.33, 528.94, 124.06, 525.09, 108.67, 522.21, 102.9, 512.59, 95.21, 509.71, 86.55, 511.63, 79.82, 505.86, 77.9, 498.17, 73.09, 499.13, 67.32, 504.9, 63.47, 513.55, 61.55, 512.59, 49.05, 513.55, 32.7, 519.32, 31.74, 526.06, 31.74, 526.06, 39.43, 526.06, 51.93, 529.9, 51.93, 532.79, 46.16, 532.79, 35.58, 535.67, 33.66, 541.44, 33.66, 541.44, 43.28, 542.41, 50.01, 543.37, 58.66, 545.29, 60.59, 553.95, 59.63, 560.68, 60.59, 560.68, 65.4, 553.95, 72.13, 549.14, 74.05, 543.37, 77.9, 539.52, 81.75, 544.33, 96.17, 562.6, 155.8, 572.22, 185.61, 584.72, 201.96, 592.41, 217.35, 602.99, 236.58, 608.76, 246.2, 627.04, 261.59, 636.65, 269.28, 639.54, 276.01, 640.0, 285.63, 639.54, 367.37, 634.73, 368.34, 623.19, 370.26, 614.53, 374.11, 616.46, 394.3, 611.65, 397.19, 598.18, 376.03, 592.41, 367.37, 587.61, 363.53, 581.84, 355.83, 577.99, 349.1, 569.33, 355.83, 567.41, 374.11, 567.41, 402.0, 567.41, 410.65, 556.83, 411.61]], "area": 19961.9797, "iscrowd": 0, "image_id": 453475, "bbox": [498.17, 31.74, 141.83, 379.87], "category_id": 25, "id": 600341, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "which", "is", "standing", "on", "the", "right", "side", "of", "the", "other", "two", "giraffes"], "raw": "A giraffe which is standing on the right side of the other two giraffes.", "sent_id": 21182, "sent": "a giraffe which is standing on the right side of the other two giraffes"}, {"tokens": ["the", "tallest", ",", "closest", "giraffe"], "raw": "The tallest, closest giraffe.", "sent_id": 21183, "sent": "the tallest , closest giraffe"}], "file_name": "COCO_train2014_000000453475_600341.jpg", "ann_id": 600341, "sent_ids": [21182, 21183], "ref_id": 13180}, {"segmentation": [[280.02, 309.58, 281.11, 289.12, 280.56, 283.67, 279.47, 280.12, 283.56, 267.98, 284.11, 262.8, 284.11, 260.89, 288.47, 249.98, 289.02, 246.43, 290.11, 242.75, 290.11, 240.16, 290.25, 234.71, 285.47, 239.07, 277.56, 240.98, 271.02, 241.8, 267.06, 241.39, 264.33, 238.39, 263.38, 235.11, 263.24, 230.34, 264.88, 223.39, 265.83, 222.16, 274.29, 211.79, 279.34, 205.66, 277.97, 195.15, 277.56, 190.93, 272.38, 173.33, 268.7, 167.88, 267.61, 162.56, 267.06, 158.88, 272.38, 153.56, 273.47, 147.69, 274.84, 145.92, 294.34, 136.1, 300.75, 133.37, 308.93, 130.78, 328.43, 127.24, 328.84, 117.69, 326.25, 116.32, 324.89, 113.87, 320.93, 99.69, 320.93, 96.69, 320.93, 94.09, 324.89, 86.32, 325.03, 83.87, 334.44, 69.55, 340.03, 64.09, 346.16, 60.27, 368.67, 60.95, 375.49, 64.23, 387.08, 75.41, 396.35, 88.5, 398.67, 96.14, 393.76, 101.6, 390.35, 104.87, 382.85, 119.05, 381.22, 123.42, 401.4, 140.87, 399.08, 144.83, 391.72, 153.56, 409.86, 168.56, 416.4, 176.88, 422.4, 185.47, 427.99, 196.65, 440.54, 218.2, 450.5, 235.93, 448.45, 239.89, 446.95, 242.89, 461.27, 259.39, 476.14, 280.67, 487.05, 302.62, 499.73, 319.94, 509.96, 330.99, 506.14, 342.58, 503.28, 345.72, 504.64, 352.68, 501.64, 355.95, 495.5, 357.86, 492.78, 358.27, 488.82, 357.86, 488.14, 355.68, 488.41, 353.9, 483.64, 349.81, 482.14, 346.68, 481.59, 344.36, 482.82, 342.86, 482.41, 340.68, 477.09, 326.9, 476.68, 320.9, 476.68, 318.04, 471.91, 309.17, 452.27, 286.8, 436.31, 270.17, 431.4, 262.8, 423.63, 252.57, 418.45, 246.71, 410.26, 234.3, 406.99, 229.8, 402.76, 225.02, 399.63, 220.79, 395.13, 218.88, 392.26, 219.7, 389.67, 222.29, 387.9, 224.34, 387.63, 231.3, 387.49, 243.3, 390.22, 245.34, 397.99, 249.43, 401.95, 255.16, 404.95, 270.44, 409.17, 285.71, 409.17, 301.81, 406.72, 307.81, 403.99, 323.35, 403.45, 326.49, 397.99, 330.31, 397.44, 341.77, 397.44, 355.68, 394.99, 359.91, 391.44, 364.13, 388.99, 378.59, 385.17, 397.96, 386.53, 411.32, 388.17, 427.82, 391.31, 429.05, 396.76, 444.6, 396.76, 454.15, 405.76, 470.92, 416.13, 485.11, 416.13, 500.65, 412.31, 510.47, 407.13, 511.97, 402.76, 512.65, 399.76, 525.88, 398.94, 529.98, 398.94, 537.07, 403.58, 531.2, 406.86, 526.7, 412.04, 526.02, 415.86, 528.61, 415.86, 531.07, 414.63, 534.34, 406.45, 543.48, 400.99, 547.71, 399.08, 550.57, 398.67, 551.11, 411.08, 556.84, 413.67, 562.84, 412.86, 569.25, 409.31, 580.85, 404.67, 583.44, 395.4, 587.12, 381.49, 588.89, 374.4, 579.76, 370.99, 573.62, 367.58, 554.12, 368.26, 547.57, 367.99, 533.38, 367.99, 532.16, 367.85, 529.16, 366.49, 519.06, 362.8, 507.47, 361.85, 502.29, 357.89, 488.11, 359.94, 480.33, 360.21, 479.1, 358.03, 473.24, 346.71, 472.01, 337.44, 467.78, 329.53, 461.65, 326.93, 456.33, 319.3, 438.6, 312.34, 420.19, 307.16, 407.78, 301.57, 390.46, 300.48, 384.86, 294.75, 388.41, 294.75, 383.23, 294.07, 372.18, 295.29, 369.18, 286.43, 353.63, 284.93, 346.81, 282.88, 334.27, 280.43, 332.9, 277.84, 329.08, 279.47, 325.26, 280.29, 323.35, 279.88, 312.58]], "area": 51304.46600000001, "iscrowd": 0, "image_id": 580695, "bbox": [263.24, 60.27, 246.72, 528.62], "category_id": 1, "id": 2205911, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "a", "white", "shirt"], "raw": "A girl in a white shirt.", "sent_id": 21239, "sent": "a girl in a white shirt"}, {"tokens": ["a", "girl", "in", "a", "white", "shirt", ",", "playing", "a", "soccer", "game"], "raw": "A girl in a white shirt, playing a soccer game.", "sent_id": 21240, "sent": "a girl in a white shirt , playing a soccer game"}], "file_name": "COCO_train2014_000000580695_2205911.jpg", "ann_id": 2205911, "sent_ids": [21239, 21240], "ref_id": 13203}, {"segmentation": [[606.34, 26.0, 579.1, 22.37, 557.92, 38.1, 551.87, 54.44, 556.1, 72.6, 564.58, 81.68, 557.92, 90.76, 531.89, 102.86, 518.58, 107.7, 503.45, 133.12, 493.76, 167.02, 492.55, 175.49, 497.39, 195.46, 505.26, 197.88, 507.68, 197.28, 509.5, 206.36, 500.42, 211.8, 499.21, 222.7, 497.39, 234.8, 490.74, 251.75, 493.76, 257.2, 496.79, 282.01, 499.82, 289.88, 494.37, 336.48, 485.29, 368.56, 485.29, 372.19, 494.37, 377.03, 503.45, 384.3, 508.89, 404.88, 509.5, 415.16, 504.05, 415.77, 502.84, 429.08, 512.53, 446.64, 529.47, 459.95, 544.0, 458.74, 543.39, 444.22, 537.34, 433.32, 561.55, 445.43, 564.58, 436.95, 561.55, 424.24, 538.55, 412.14, 535.52, 400.03, 542.79, 390.35, 567.0, 397.01, 571.84, 395.8, 576.68, 383.09, 579.1, 310.46, 582.73, 250.54, 593.02, 155.52, 591.21, 129.49, 591.81, 65.94, 600.29, 42.94, 606.34, 28.42]], "area": 30602.767850000004, "iscrowd": 0, "image_id": 1994, "bbox": [485.29, 22.37, 121.05, 437.58], "category_id": 1, "id": 489055, "split": "val", "sentences": [{"tokens": ["the", "guy", "with", "a", "camera"], "raw": "The guy with a camera.", "sent_id": 21269, "sent": "the guy with a camera"}, {"tokens": ["man", "with", "vertical", "striped", "shirt"], "raw": "man with vertical striped shirt", "sent_id": 21270, "sent": "man with vertical striped shirt"}], "file_name": "COCO_train2014_000000001994_489055.jpg", "ann_id": 489055, "sent_ids": [21269, 21270], "ref_id": 13209}, {"segmentation": [[99.29, 428.0, 183.15, 387.51, 225.57, 372.09, 332.57, 328.71, 440.53, 316.18, 518.61, 331.6, 631.4, 373.05, 634.29, 427.04, 492.59, 423.18, 246.77, 428.0, 122.42, 424.14]], "area": 38899.8139, "iscrowd": 0, "image_id": 334139, "bbox": [99.29, 316.18, 535.0, 111.82], "category_id": 67, "id": 1091176, "split": "val", "sentences": [{"tokens": ["the", "table", "with", "the", "paper", "bag", "on", "it"], "raw": "the table with the paper bag on it", "sent_id": 21365, "sent": "the table with the paper bag on it"}, {"tokens": ["a", "brown", "paper", "bag", "in", "front", "of", "girl"], "raw": "A brown paper bag in front of girl", "sent_id": 21366, "sent": "a brown paper bag in front of girl"}], "file_name": "COCO_train2014_000000334139_1091176.jpg", "ann_id": 1091176, "sent_ids": [21365, 21366], "ref_id": 13247}, {"segmentation": [[386.24, 162.54, 369.09, 149.68, 383.17, 117.85, 382.56, 103.77, 370.32, 94.58, 359.91, 100.7, 360.52, 80.5, 349.5, 84.17, 343.99, 111.73, 315.83, 106.21, 315.21, 72.54, 320.72, 60.91, 350.72, 54.79, 312.15, 47.44, 283.38, 37.03, 291.95, 22.95, 320.11, 11.32, 347.66, 2.74, 379.5, 2.74, 435.22, 2.74, 457.26, 13.15, 486.03, 22.34, 513.58, 46.83, 512.97, 54.17, 489.71, 59.07, 501.34, 71.32, 485.42, 78.05, 460.32, 63.97, 446.24, 81.11, 436.44, 109.89, 424.81, 126.42, 424.81, 140.5, 404.6, 142.95]], "area": 18440.429300000003, "iscrowd": 0, "image_id": 333748, "bbox": [283.38, 2.74, 230.2, 159.8], "category_id": 64, "id": 27560, "split": "val", "sentences": [{"tokens": ["the", "blant", "behind", "the", "empty", "chair"], "raw": "The blant behind the empty chair.", "sent_id": 21411, "sent": "the blant behind the empty chair"}, {"tokens": ["a", "tree", "behind", "a", "green", "bottle", "of", "wine"], "raw": "a tree behind a green bottle of wine", "sent_id": 21412, "sent": "a tree behind a green bottle of wine"}], "file_name": "COCO_train2014_000000333748_27560.jpg", "ann_id": 27560, "sent_ids": [21411, 21412], "ref_id": 13266}, {"segmentation": [[184.8, 275.85, 139.79, 282.55, 129.26, 281.6, 134.05, 272.98, 176.18, 266.28, 147.45, 251.91, 105.32, 246.17, 49.79, 244.25, 19.15, 246.17, 8.62, 250.0, 0.0, 266.28, 3.83, 292.13, 11.49, 307.45, 19.15, 323.73, 27.77, 337.13, 38.3, 347.66, 51.7, 355.32, 65.11, 364.9, 72.77, 369.69, 101.49, 375.43, 116.81, 373.52, 140.75, 366.81, 150.33, 357.24, 157.99, 351.49, 166.6, 340.0, 180.97, 323.73, 183.84, 314.15, 191.5, 300.75, 191.5, 288.3, 187.67, 272.02]], "area": 18475.2486, "iscrowd": 0, "image_id": 541338, "bbox": [0.0, 244.25, 191.5, 131.18], "category_id": 51, "id": 716457, "split": "val", "sentences": [{"tokens": ["the", "white", "bowl", "on", "the", "left"], "raw": "The white bowl on the left.", "sent_id": 21443, "sent": "the white bowl on the left"}, {"tokens": ["an", "orange", "soup", "next", "to", "a", "glass", "of", "beer"], "raw": "An orange soup next to a glass of beer.", "sent_id": 21444, "sent": "an orange soup next to a glass of beer"}], "file_name": "COCO_train2014_000000541338_716457.jpg", "ann_id": 716457, "sent_ids": [21443, 21444], "ref_id": 13279}, {"segmentation": [[99.75, 214.51, 113.6, 215.43, 127.46, 200.65, 138.54, 194.19, 171.79, 190.49, 194.88, 204.35, 207.81, 240.37, 187.49, 272.69, 181.95, 278.23, 182.87, 298.55, 183.8, 329.03, 182.87, 347.5, 168.09, 350.27, 127.46, 338.27, 108.98, 317.95, 98.82, 306.86, 93.28, 293.01]], "area": 13020.681550000001, "iscrowd": 0, "image_id": 363593, "bbox": [93.28, 190.49, 114.53, 159.78], "category_id": 1, "id": 213466, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "a", "black", "tie", "looking", "down"], "raw": "A man in a white shirt and a black tie looking down.", "sent_id": 21445, "sent": "a man in a white shirt and a black tie looking down"}, {"tokens": ["a", "nab", "wearing", "a", "white", "shirt", "and", "tie"], "raw": "A nab wearing a white shirt and tie.", "sent_id": 21446, "sent": "a nab wearing a white shirt and tie"}], "file_name": "COCO_train2014_000000363593_213466.jpg", "ann_id": 213466, "sent_ids": [21445, 21446], "ref_id": 13280}, {"segmentation": [[638.11, 2.05, 32.48, 3.0, 223.53, 104.26, 290.4, 123.36, 380.19, 148.2, 384.01, 160.62, 122.27, 207.43, 5.73, 215.07, 7.64, 297.22, 431.78, 348.81, 467.12, 207.43, 491.96, 199.79, 491.96, 172.08, 498.64, 152.98, 525.39, 147.25, 542.59, 193.1, 573.15, 214.11, 598.95, 245.64, 608.5, 268.56, 618.05, 371.73, 632.38, 376.51, 635.25, 375.55]], "area": 141376.51049999997, "iscrowd": 0, "image_id": 390496, "bbox": [5.73, 2.05, 632.38, 374.46], "category_id": 5, "id": 157155, "split": "val", "sentences": [{"tokens": ["an", "airplane", "with", "one", "man", "standing", "under", "the", "wing"], "raw": "An airplane with one man standing under the wing.", "sent_id": 21457, "sent": "an airplane with one man standing under the wing"}, {"tokens": ["an", "aeroplane", "on", "which", "a", "number", "written", "on", "it"], "raw": "An aeroplane on which a number written on it", "sent_id": 21458, "sent": "an aeroplane on which a number written on it"}], "file_name": "COCO_train2014_000000390496_157155.jpg", "ann_id": 157155, "sent_ids": [21457, 21458], "ref_id": 13286}, {"segmentation": [[188.69, 429.16, 324.46, 457.92, 398.09, 400.4, 402.7, 310.65, 411.9, 240.47, 388.89, 170.28, 337.11, 112.76, 292.24, 92.04, 240.47, 87.44, 181.79, 128.86, 166.83, 167.98, 158.78, 224.36, 154.18, 232.41, 146.12, 250.82, 189.84, 428.01]], "area": 75901.07615, "iscrowd": 0, "image_id": 106397, "bbox": [146.12, 87.44, 265.78, 370.48], "category_id": 14, "id": 418237, "split": "val", "sentences": [{"tokens": ["parking", "meter", "closest", "to", "the", "orange", "ticket"], "raw": "Parking meter closest to the orange ticket.", "sent_id": 21486, "sent": "parking meter closest to the orange ticket"}, {"tokens": ["the", "closer", "parking", "meter"], "raw": "the closer parking meter", "sent_id": 21487, "sent": "the closer parking meter"}], "file_name": "COCO_train2014_000000106397_418237.jpg", "ann_id": 418237, "sent_ids": [21486, 21487], "ref_id": 13299}, {"segmentation": [[640.0, 363.6, 525.14, 305.0, 481.5, 266.35, 495.22, 258.87, 516.41, 256.38, 599.94, 205.26, 640.0, 171.6]], "area": 14973.571650000002, "iscrowd": 0, "image_id": 181009, "bbox": [481.5, 171.6, 158.5, 192.0], "category_id": 27, "id": 1827348, "split": "val", "sentences": [{"tokens": ["a", "light", "blue", "backpack", "on", "the", "lap", "of", "the", "passenger", "next", "to", "the", "one", "using", "his", "cell", "phone"], "raw": "a light blue backpack on the lap of the passenger next to the one using his cell phone", "sent_id": 21513, "sent": "a light blue backpack on the lap of the passenger next to the one using his cell phone"}], "file_name": "COCO_train2014_000000181009_1827348.jpg", "ann_id": 1827348, "sent_ids": [21513], "ref_id": 13310}, {"segmentation": [[328.39, 425.0, 325.24, 403.8, 304.45, 381.11, 315.79, 352.76, 314.53, 323.77, 325.87, 306.76, 326.5, 284.08, 342.25, 274.0, 358.63, 276.52, 361.15, 301.72, 376.91, 319.36, 384.47, 348.98, 409.04, 384.89, 432.99, 423.96, 376.28, 423.33, 331.54, 423.33]], "area": 10515.034150000001, "iscrowd": 0, "image_id": 306967, "bbox": [304.45, 274.0, 128.54, 151.0], "category_id": 1, "id": 1233029, "split": "val", "sentences": [{"tokens": ["a", "woman", "standing", "in", "a", "dugout", "wearing", "a", "black", "jacket"], "raw": "A woman standing in a dugout wearing a black jacket.", "sent_id": 21556, "sent": "a woman standing in a dugout wearing a black jacket"}, {"tokens": ["a", "blurried", "person", "standing", "in", "the", "dugout", "with", "beige", "shirt", "and", "a", "white", "top", "on"], "raw": "A blurried person standing in the dugout with beige shirt and a white top on", "sent_id": 21557, "sent": "a blurried person standing in the dugout with beige shirt and a white top on"}], "file_name": "COCO_train2014_000000306967_1233029.jpg", "ann_id": 1233029, "sent_ids": [21556, 21557], "ref_id": 13329}, {"segmentation": [[258.64, 365.33, 374.88, 344.02, 438.81, 332.4, 463.03, 316.9, 473.68, 325.61, 482.4, 336.27, 485.31, 333.36, 489.18, 328.52, 482.4, 320.77, 477.56, 318.83, 468.84, 314.96, 490.15, 312.05, 495.96, 309.15, 503.71, 290.74, 496.93, 284.93, 501.78, 260.71, 507.59, 259.74, 514.37, 286.87, 527.93, 310.12, 542.46, 320.77, 556.99, 324.65, 578.3, 319.8, 593.8, 302.37, 602.52, 267.49, 594.77, 221.0, 581.21, 198.72, 551.18, 185.16, 550.21, 177.41, 531.81, 181.28, 512.43, 151.25, 504.68, 130.91, 509.53, 120.25, 523.09, 117.35, 523.09, 108.63, 517.28, 102.82, 532.77, 96.04, 530.84, 90.23, 506.62, 97.01, 494.03, 97.98, 509.53, 76.66, 525.02, 65.04, 521.15, 58.26, 503.71, 59.23, 504.68, 68.91, 489.18, 89.26, 484.34, 81.51, 479.5, 83.44, 451.4, 70.85, 427.19, 77.63, 420.41, 85.38, 410.72, 108.63, 408.78, 116.38, 407.81, 121.22, 392.32, 127.04, 386.5, 124.13, 371.0, 130.91, 371.0, 134.78, 346.79, 140.6, 351.63, 150.28, 373.91, 144.47, 384.57, 151.25, 356.47, 169.66, 327.41, 196.78, 314.82, 195.81, 309.01, 201.62, 271.23, 210.34, 256.7, 210.34, 223.77, 189.03, 193.74, 193.87, 158.86, 201.62, 144.33, 185.16, 138.52, 185.16, 138.52, 192.91, 143.36, 213.25, 124.96, 221.0, 100.74, 227.78, 97.84, 241.34, 86.21, 260.71, 89.12, 270.4, 81.37, 280.09, 81.37, 286.87, 87.18, 289.77, 92.02, 297.52, 91.06, 313.02, 100.74, 340.15, 117.21, 359.52, 149.18, 376.95, 173.39, 377.92, 247.98, 352.74, 255.73, 346.93]], "area": 88821.43964999997, "iscrowd": 0, "image_id": 208243, "bbox": [81.37, 58.26, 521.15, 319.66], "category_id": 4, "id": 150740, "split": "val", "sentences": [{"tokens": ["two", "sporty", "-", "looking", "motorcycles", "next", "to", "each", "other", "on", "a", "road"], "raw": "Two sporty-looking motorcycles next to each other on a road.", "sent_id": 21558, "sent": "two sporty - looking motorcycles next to each other on a road"}, {"tokens": ["the", "front", "motorcycle"], "raw": "The front motorcycle.", "sent_id": 21559, "sent": "the front motorcycle"}], "file_name": "COCO_train2014_000000208243_150740.jpg", "ann_id": 150740, "sent_ids": [21558, 21559], "ref_id": 13330}, {"segmentation": [[189.61, 214.04, 200.56, 214.04, 208.99, 312.64, 198.03, 327.81, 168.54, 321.07], [133.99, 203.93, 92.7, 219.1, 86.8, 306.74, 95.22, 306.74]], "area": 5073.729950000001, "iscrowd": 0, "image_id": 326077, "bbox": [86.8, 203.93, 122.19, 123.88], "category_id": 6, "id": 366411, "split": "val", "sentences": [{"tokens": ["a", "red", "bus", "obscured", "by", "a", "tree"], "raw": "A red bus obscured by a tree", "sent_id": 21597, "sent": "a red bus obscured by a tree"}], "file_name": "COCO_train2014_000000326077_366411.jpg", "ann_id": 366411, "sent_ids": [21597], "ref_id": 13347}, {"segmentation": [[343.89, 420.41, 341.98, 406.08, 370.64, 350.67, 410.76, 303.86, 427.0, 277.12, 477.63, 288.58, 512.97, 302.91, 539.72, 314.37, 547.36, 289.54, 551.18, 274.25, 527.3, 234.13, 503.42, 213.11, 562.65, 205.47, 598.95, 188.28, 630.47, 191.14, 640.0, 216.94, 640.0, 301.0, 640.0, 347.81, 638.11, 365.96, 634.29, 375.51, 628.56, 386.02, 621.87, 410.85, 619.96, 421.36, 592.26, 414.67, 590.35, 385.06, 540.68, 420.41, 471.9, 422.32, 422.22, 416.58, 403.12, 410.85, 394.52, 416.58, 355.36, 422.32], [127.05, 237.0, 125.14, 219.8, 136.6, 196.88, 166.21, 169.17, 190.1, 144.34, 213.02, 126.19, 221.62, 125.23, 215.89, 115.68, 208.25, 87.02, 202.51, 76.51, 215.89, 85.11, 216.84, 87.02, 217.8, 75.56, 229.26, 84.15, 234.99, 86.07, 271.29, 85.11, 297.09, 97.53, 333.38, 135.74, 345.8, 146.25, 353.45, 155.8, 357.27, 158.67, 334.34, 174.9, 300.91, 204.52, 270.34, 237.95, 261.74, 242.73, 252.19, 242.73, 244.55, 233.18, 237.86, 228.4, 190.1, 243.68, 168.13, 245.59, 131.83, 237.95]], "area": 64272.36094999998, "iscrowd": 0, "image_id": 233022, "bbox": [125.14, 75.56, 514.86, 346.76], "category_id": 24, "id": 592351, "split": "val", "sentences": [{"tokens": ["a", "zebra", "standing", "behind", "the", "side", "of", "a", "smaller", "zebra"], "raw": "A zebra standing behind the side of a smaller zebra.", "sent_id": 21608, "sent": "a zebra standing behind the side of a smaller zebra"}, {"tokens": ["a", "zebra", "looking", "to", "the", "left"], "raw": "A zebra looking to the left.", "sent_id": 21609, "sent": "a zebra looking to the left"}], "file_name": "COCO_train2014_000000233022_592351.jpg", "ann_id": 592351, "sent_ids": [21608, 21609], "ref_id": 13352}, {"segmentation": [[349.43, 141.26, 341.07, 182.44, 339.14, 209.46, 333.35, 320.14, 323.05, 336.22, 304.39, 336.87, 297.96, 349.73, 290.88, 369.68, 323.7, 371.61, 390.61, 403.78, 427.93, 417.94, 450.45, 431.45, 394.47, 425.02, 343.0, 406.36, 338.5, 424.37, 458.18, 434.0, 465.9, 424.37, 487.13, 418.58, 493.57, 358.1, 485.2, 277.02, 467.83, 236.49, 446.59, 171.5, 433.73, 115.52, 415.71, 102.01, 398.98, 93.64, 373.24, 101.36, 356.51, 126.46]], "area": 41957.7485, "iscrowd": 0, "image_id": 323960, "bbox": [290.88, 93.64, 202.69, 340.36], "category_id": 1, "id": 535809, "split": "val", "sentences": [{"tokens": ["blonde", "haired", "woman", "in", "a", "lace", "blouse"], "raw": "Blonde haired woman in a lace blouse.", "sent_id": 21612, "sent": "blonde haired woman in a lace blouse"}, {"tokens": ["thin", "blonde", "haired", "woman", "who", "has", "a", "big", "smile"], "raw": "Thin blonde haired woman who has a big smile.", "sent_id": 21613, "sent": "thin blonde haired woman who has a big smile"}], "file_name": "COCO_train2014_000000323960_535809.jpg", "ann_id": 535809, "sent_ids": [21612, 21613], "ref_id": 13353}, {"segmentation": [[360.99, 478.92, 375.37, 419.96, 393.22, 354.74, 401.13, 335.95, 413.99, 315.17, 428.83, 292.42, 438.72, 280.55, 450.59, 271.65, 450.0, 254.36, 447.28, 240.08, 448.64, 228.51, 447.28, 225.79, 443.88, 213.54, 441.16, 205.38, 441.16, 201.3, 439.8, 189.05, 441.84, 177.49, 441.84, 159.12, 457.48, 138.71, 466.33, 123.06, 489.46, 113.54, 503.75, 110.14, 515.31, 110.14, 518.03, 110.14, 540.48, 108.1, 548.65, 110.82, 571.78, 117.62, 582.66, 142.11, 588.78, 156.4, 589.46, 166.6, 587.42, 174.77, 587.42, 178.85, 585.38, 188.37, 584.02, 197.22, 581.3, 211.5, 580.62, 214.9, 579.94, 226.47, 573.14, 244.16, 567.01, 250.96, 560.21, 253.68, 557.49, 255.04, 555.45, 270.69, 555.45, 275.45, 556.13, 282.94, 557.49, 284.3, 569.74, 276.81, 571.1, 276.81, 575.86, 278.85, 581.3, 284.98, 594.91, 298.58, 604.43, 307.81, 607.83, 313.93, 608.51, 336.57, 609.19, 345.42, 613.96, 368.93, 613.96, 406.35, 613.28, 419.27, 607.83, 460.28, 610.55, 469.13, 612.6, 477.29, 613.28, 484.77, 532.32, 471.85, 515.99, 474.57, 486.06, 485.45, 475.85, 487.49, 472.45, 488.17, 467.01, 488.86, 460.21, 477.29, 454.76, 467.77, 443.2, 472.53, 432.31, 475.25, 424.83, 478.65, 413.26, 483.41, 408.5, 483.41, 403.74, 493.62, 393.54, 494.3, 388.09, 492.26, 381.29, 488.86]], "area": 65194.34035000002, "iscrowd": 0, "image_id": 69344, "bbox": [360.99, 108.1, 252.97, 386.2], "category_id": 1, "id": 1728287, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "wearing", "a", "blue", "shirt", "with", "ninja", "on", "it", "eating", "cake"], "raw": "A young boy wearing a blue shirt with  ninja on it eating cake", "sent_id": 21614, "sent": "a young boy wearing a blue shirt with ninja on it eating cake"}, {"tokens": ["a", "small", "boy", "in", "a", "blue", "shirt", "with", "a", "figure", "on", "the", "front", "that", "has", "a", "black", "and", "red", "hat"], "raw": "A small boy in a blue shirt with a figure on the front that has a black and red hat.", "sent_id": 21615, "sent": "a small boy in a blue shirt with a figure on the front that has a black and red hat"}], "file_name": "COCO_train2014_000000069344_1728287.jpg", "ann_id": 1728287, "sent_ids": [21614, 21615], "ref_id": 13354}, {"segmentation": [[239.89, 210.14, 235.09, 189.99, 245.64, 169.84, 247.56, 185.19, 253.32, 196.71, 261.96, 192.87, 274.43, 204.38, 306.1, 219.74, 338.72, 252.36, 356.95, 277.31, 392.46, 297.46, 518.16, 302.26, 615.07, 319.53, 640.0, 338.72, 640.0, 355.99, 640.0, 422.2, 366.55, 420.28, 323.37, 421.24, 311.85, 402.05, 268.67, 337.76, 243.73, 280.19, 241.81, 276.35, 199.59, 291.7, 189.03, 283.07, 173.68, 258.12, 195.75, 241.81]], "area": 53986.4196, "iscrowd": 0, "image_id": 436941, "bbox": [173.68, 169.84, 466.32, 252.36], "category_id": 24, "id": 592167, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "white", "zebra", "standing", "sideways", "facing", "another", "zebra"], "raw": "A black and white zebra standing sideways facing another zebra", "sent_id": 21722, "sent": "a black and white zebra standing sideways facing another zebra"}, {"tokens": ["a", "zebra", "with", "it", "'", "s", "nose", "on", "the", "other", "zebra"], "raw": "A zebra with it's nose on the other zebra.", "sent_id": 21723, "sent": "a zebra with it ' s nose on the other zebra"}], "file_name": "COCO_train2014_000000436941_592167.jpg", "ann_id": 592167, "sent_ids": [21722, 21723], "ref_id": 13392}, {"segmentation": [[450.82, 309.59, 424.06, 308.65, 423.12, 313.34, 441.9, 315.69, 435.85, 326.49, 426.35, 336.86, 431.12, 343.22, 445.43, 318.18, 482.4, 325.33, 480.57, 320.21], [550.22, 160.06, 559.4, 163.73, 566.53, 171.29, 568.18, 179.26, 555.58, 164.78]], "area": 607.6213000000005, "iscrowd": 0, "image_id": 443916, "bbox": [423.12, 160.06, 145.06, 183.16], "category_id": 62, "id": 1593511, "split": "val", "sentences": [{"tokens": ["a", "metal", "chair", "to", "the", "right"], "raw": "A metal chair to the right.", "sent_id": 21824, "sent": "a metal chair to the right"}, {"tokens": ["the", "chair", "the", "bear", "on", "the", "right", "is", "sitting", "in"], "raw": "the chair the bear on the right is sitting in", "sent_id": 21825, "sent": "the chair the bear on the right is sitting in"}], "file_name": "COCO_train2014_000000443916_1593511.jpg", "ann_id": 1593511, "sent_ids": [21824, 21825], "ref_id": 13433}, {"segmentation": [[34.52, 446.84, 30.2, 412.32, 40.27, 374.93, 51.78, 357.67, 69.03, 357.67, 87.73, 364.86, 123.69, 370.62, 132.31, 374.93, 104.99, 333.22, 92.04, 292.95, 86.29, 249.81, 90.61, 221.04, 107.87, 203.79, 130.88, 192.28, 159.64, 183.65, 205.66, 179.34, 241.62, 180.77, 266.07, 169.27, 281.89, 163.52, 299.15, 170.71, 306.34, 195.16, 294.83, 222.48, 281.89, 241.18, 250.25, 245.49, 247.37, 267.07, 245.93, 294.39, 260.31, 350.48, 276.13, 408.01, 284.76, 436.77, 279.01, 449.72, 260.31, 456.91, 248.81, 429.58, 254.56, 400.82, 232.99, 356.23, 215.73, 393.63, 197.03, 419.52, 168.27, 455.47, 163.96, 458.35, 168.27, 472.73, 195.6, 500.05, 189.84, 508.68, 161.08, 508.68, 120.81, 487.11, 135.19, 455.47, 161.08, 420.95, 179.78, 392.19, 197.03, 357.67, 174.02, 326.03, 166.83, 351.92, 178.34, 390.75, 162.52, 409.45, 140.94, 409.45, 117.93, 403.7, 92.04, 396.5, 77.66, 395.07, 74.79, 418.08, 66.16, 446.84, 54.65, 455.47, 34.52, 442.53]], "area": 45329.255200000014, "iscrowd": 0, "image_id": 381923, "bbox": [30.2, 163.52, 276.14, 345.16], "category_id": 1, "id": 475521, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "white", "shirt", "and", "black", "shorts", "holding", "a", "tennis", "racket", "on", "the", "ground"], "raw": "A man with a white shirt and black shorts holding a tennis racket on the ground", "sent_id": 21830, "sent": "a man with a white shirt and black shorts holding a tennis racket on the ground"}, {"tokens": ["a", "male", "tennis", "player", "holding", "a", "racket"], "raw": "A male tennis player holding a racket.", "sent_id": 21831, "sent": "a male tennis player holding a racket"}], "file_name": "COCO_train2014_000000381923_475521.jpg", "ann_id": 475521, "sent_ids": [21830, 21831], "ref_id": 13435}, {"segmentation": [[180.4, 208.22, 199.59, 177.52, 203.42, 139.13, 218.78, 126.66, 246.6, 110.35, 284.99, 110.35, 328.17, 128.58, 340.64, 156.41, 371.35, 201.51, 373.27, 232.21, 375.18, 237.97, 375.18, 265.8, 374.22, 269.63, 355.99, 283.07, 316.65, 297.46, 309.93, 309.93, 306.1, 332.96, 302.26, 332.96, 273.47, 337.76, 237.97, 237.97, 215.9, 223.58, 193.83, 213.02]], "area": 26699.718000000004, "iscrowd": 0, "image_id": 246753, "bbox": [180.4, 110.35, 194.78, 227.41], "category_id": 1, "id": 184322, "split": "val", "sentences": [{"tokens": ["the", "woman", "holding", "the", "puppy"], "raw": "the woman holding the puppy", "sent_id": 21863, "sent": "the woman holding the puppy"}, {"tokens": ["hispanic", "female", "holding", "puppy"], "raw": "HISPANIC FEMALE HOLDING PUPPY", "sent_id": 21864, "sent": "hispanic female holding puppy"}], "file_name": "COCO_train2014_000000246753_184322.jpg", "ann_id": 184322, "sent_ids": [21863, 21864], "ref_id": 13445}, {"segmentation": [[511.48, 61.09, 524.65, 65.97, 533.28, 73.26, 559.28, 75.72, 576.35, 72.8, 585.13, 92.8, 583.67, 101.58, 575.38, 109.87, 571.96, 111.82, 563.67, 115.72, 559.77, 124.5, 559.28, 132.31, 566.6, 134.26, 575.38, 141.09, 578.31, 151.33, 578.79, 159.62, 577.82, 171.82, 583.18, 177.67, 588.55, 178.64, 592.94, 184.99, 594.89, 189.38, 597.33, 205.96, 598.79, 221.08, 603.18, 224.01, 606.6, 227.42, 609.52, 236.2, 609.52, 242.05, 590.27, 246.28, 578.13, 240.06, 568.35, 233.25, 560.65, 220.22, 557.1, 207.19, 556.21, 200.09, 554.73, 192.09, 542.89, 188.24, 536.96, 211.14, 525.69, 214.9, 517.55, 210.52, 514.88, 177.34, 494.49, 149.12, 501.57, 124.66, 507.77, 116.93, 509.94, 112.44, 512.19, 106.32, 495.44, 84.29, 497.05, 65.71, 509.21, 59.05]], "area": 11424.371050000005, "iscrowd": 0, "image_id": 102144, "bbox": [494.49, 59.05, 115.03, 187.23], "category_id": 88, "id": 1163390, "split": "val", "sentences": [{"tokens": ["the", "bear", "furthest", "to", "the", "right"], "raw": "The bear furthest to the right", "sent_id": 21873, "sent": "the bear furthest to the right"}], "file_name": "COCO_train2014_000000102144_1163390.jpg", "ann_id": 1163390, "sent_ids": [21873], "ref_id": 13450}, {"segmentation": [[153.67, 515.16, 365.88, 450.77, 362.96, 421.5, 326.37, 380.52, 289.78, 332.22, 273.68, 300.02, 259.04, 300.02, 232.7, 308.8, 197.58, 291.24, 177.09, 261.97, 171.23, 231.24, 182.94, 209.28, 150.74, 182.94, 98.06, 182.94, 71.71, 188.8, 60.0, 242.95, 33.66, 311.73, 55.61, 408.32, 74.64, 453.69, 87.81, 491.75, 95.13, 501.99]], "area": 65990.40814999997, "iscrowd": 0, "image_id": 112122, "bbox": [33.66, 182.94, 332.22, 332.22], "category_id": 3, "id": 1771065, "split": "val", "sentences": [{"tokens": ["the", "side", "of", "the", "car", "visible", "in", "the", "mirror"], "raw": "the side of the car visible in the mirror", "sent_id": 21900, "sent": "the side of the car visible in the mirror"}, {"tokens": ["the", "reflection", "of", "a", "car", "with", "a", "dog", "hanging", "out", "of", "a", "window"], "raw": "The reflection of a car with a dog hanging out of a window.", "sent_id": 21901, "sent": "the reflection of a car with a dog hanging out of a window"}], "file_name": "COCO_train2014_000000112122_1771065.jpg", "ann_id": 1771065, "sent_ids": [21900, 21901], "ref_id": 13459}, {"segmentation": [[292.35, 74.74, 399.53, 74.07, 412.34, 115.19, 411.67, 196.08, 415.04, 236.53, 397.51, 239.23, 394.14, 244.62, 369.87, 246.64, 346.95, 238.55, 324.03, 243.27, 303.81, 258.78, 285.61, 250.69, 278.19, 239.9, 277.52, 110.47, 284.93, 76.77]], "area": 22610.6268, "iscrowd": 0, "image_id": 346562, "bbox": [277.52, 74.07, 137.52, 184.71], "category_id": 6, "id": 166296, "split": "val", "sentences": [{"tokens": ["the", "bak", "of", "a", "red", "and", "yellow", "bus"], "raw": "The bak of a red and yellow bus.", "sent_id": 21910, "sent": "the bak of a red and yellow bus"}, {"tokens": ["travel", "bus"], "raw": "travel bus", "sent_id": 21911, "sent": "travel bus"}], "file_name": "COCO_train2014_000000346562_166296.jpg", "ann_id": 166296, "sent_ids": [21910, 21911], "ref_id": 13462}, {"segmentation": [[369.04, 201.97, 270.55, 206.96, 280.52, 215.69, 280.52, 230.65, 279.27, 241.87, 291.74, 249.35, 297.97, 261.82, 309.19, 285.51, 326.65, 300.47, 327.9, 311.69, 354.08, 304.21, 375.27, 310.44, 375.27, 209.45, 371.53, 204.47], [211.95, 210.7, 153.35, 213.19, 167.06, 224.42, 160.83, 278.03, 160.83, 355.32, 170.81, 335.38, 187.01, 327.9, 205.71, 335.38, 210.7, 331.64, 203.22, 304.21, 199.48, 278.03, 205.71, 256.83, 214.44, 249.35, 209.45, 235.64, 209.45, 226.91, 211.95, 211.95]], "area": 13638.878349999995, "iscrowd": 0, "image_id": 220037, "bbox": [153.35, 201.97, 221.92, 153.35], "category_id": 15, "id": 1811890, "split": "val", "sentences": [{"tokens": ["the", "section", "of", "black", "bench", "back", "behind", "the", "woman", "in", "glasses"], "raw": "The section of black bench back behind the woman in glasses.", "sent_id": 21999, "sent": "the section of black bench back behind the woman in glasses"}, {"tokens": ["the", "black", "bench", "behind", "the", "woman", "with", "glasses"], "raw": "The black bench behind the woman with glasses.", "sent_id": 22000, "sent": "the black bench behind the woman with glasses"}], "file_name": "COCO_train2014_000000220037_1811890.jpg", "ann_id": 1811890, "sent_ids": [21999, 22000], "ref_id": 13497}, {"segmentation": [[176.48, 43.34, 343.57, 56.91, 433.37, 55.87, 457.39, 60.05, 468.88, 177.0, 435.46, 202.07, 413.53, 212.51, 401.0, 224.0, 359.23, 214.6, 272.55, 193.71, 223.47, 195.8, 206.77, 195.8, 189.01, 208.33, 185.88, 209.38, 181.7, 196.85, 153.51, 187.45, 153.51, 175.96, 161.86, 175.96, 143.07, 145.68, 145.15, 95.55, 167.08, 59.0]], "area": 46740.50025, "iscrowd": 0, "image_id": 196198, "bbox": [143.07, 43.34, 325.81, 180.66], "category_id": 70, "id": 1967620, "split": "val", "sentences": [{"tokens": ["a", "ceramic", "top", "to", "a", "toilet", "tank"], "raw": "A ceramic top to a toilet tank", "sent_id": 22009, "sent": "a ceramic top to a toilet tank"}, {"tokens": ["the", "top", "of", "a", "toilet", ",", "which", "says", "poop"], "raw": "The top of a toilet, which says POOP.", "sent_id": 22010, "sent": "the top of a toilet , which says poop"}], "file_name": "COCO_train2014_000000196198_1967620.jpg", "ann_id": 1967620, "sent_ids": [22009, 22010], "ref_id": 13502}, {"segmentation": [[65.01, 349.26, 72.23, 389.71, 80.9, 425.82, 92.46, 479.28, 93.91, 490.84, 93.91, 512.51, 85.24, 550.07, 91.02, 574.63, 91.02, 606.41, 88.13, 617.97, 88.13, 617.97, 108.35, 632.42, 143.02, 632.42, 179.14, 625.19, 239.82, 615.08, 223.93, 606.41, 199.37, 555.85, 195.03, 544.29, 192.14, 487.95, 202.26, 444.6, 206.59, 428.71, 218.15, 401.26, 222.48, 385.37, 228.26, 346.37, 228.26, 329.03, 239.82, 255.35, 208.04, 177.34, 215.26, 45.87, 208.04, 3.97, 141.58, 2.53, 122.8, 31.42, 105.46, 57.43, 83.79, 96.43, 41.9, 138.33, 30.34, 167.22, 34.67, 196.12, 41.9, 203.34, 44.79, 233.68, 47.67, 297.25, 63.57, 349.26, 63.57, 357.92]], "area": 88039.0673, "iscrowd": 0, "image_id": 358543, "bbox": [30.34, 2.53, 209.48, 629.89], "category_id": 1, "id": 536085, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "coat", "with", "a", "purple", "umbrella"], "raw": "A man in a coat with a purple umbrella.", "sent_id": 22039, "sent": "a man in a coat with a purple umbrella"}, {"tokens": ["the", "bearded", "man", "with", "the", "purple", "umbrella"], "raw": "The bearded man with the purple umbrella.", "sent_id": 22040, "sent": "the bearded man with the purple umbrella"}], "file_name": "COCO_train2014_000000358543_536085.jpg", "ann_id": 536085, "sent_ids": [22039, 22040], "ref_id": 13514}, {"segmentation": [[40.18, 15.95, 25.83, 47.52, 24.39, 74.79, 25.83, 97.75, 12.91, 122.14, 11.48, 127.88, 4.3, 145.1, 4.3, 624.38, 67.44, 631.56, 78.92, 628.69, 80.36, 599.99, 87.53, 584.2, 73.18, 546.89, 68.88, 516.76, 54.53, 472.28, 54.53, 424.92, 57.4, 379.0, 54.53, 323.04, 55.96, 288.6, 73.18, 271.38, 90.4, 249.85, 94.71, 202.5, 100.45, 179.54, 90.4, 146.54, 96.14, 116.4, 101.88, 97.75, 117.67, 74.79, 136.32, 64.74, 147.8, 48.96, 154.98, 30.3]], "area": 44157.02354999999, "iscrowd": 0, "image_id": 520590, "bbox": [4.3, 15.95, 150.68, 615.61], "category_id": 1, "id": 472323, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "girl", "wearing", "a", "pink", "and", "white", "sweater"], "raw": "The back of a girl wearing a pink and white sweater", "sent_id": 22085, "sent": "the back of a girl wearing a pink and white sweater"}, {"tokens": ["a", "man", "walking", "in", "opposite", "direction", "of", "a", "boy", "taking", "a", "picture", "with", "his", "phone"], "raw": "A man walking in opposite direction of a boy taking a picture with his phone", "sent_id": 22086, "sent": "a man walking in opposite direction of a boy taking a picture with his phone"}], "file_name": "COCO_train2014_000000520590_472323.jpg", "ann_id": 472323, "sent_ids": [22085, 22086], "ref_id": 13533}, {"segmentation": [[384.22, 109.78, 380.99, 88.25, 387.44, 73.18, 386.37, 58.12, 408.97, 37.67, 455.25, 45.2, 477.85, 60.27, 488.61, 86.1, 478.92, 106.55, 487.53, 116.23, 485.38, 137.76, 467.09, 152.83, 464.93, 170.04, 513.36, 204.48, 528.43, 236.77, 541.35, 281.97, 545.65, 304.57, 528.43, 311.03, 528.43, 428.34, 511.21, 441.26, 531.66, 480.0, 350.85, 480.0, 362.69, 448.79, 353.0, 411.12, 356.23, 336.86, 355.16, 322.87, 339.01, 368.07, 348.7, 413.27, 333.63, 428.34, 313.18, 420.81, 309.96, 406.82, 318.57, 390.67, 315.34, 358.39, 315.34, 323.95, 322.87, 302.42, 311.03, 286.28, 302.42, 269.06, 347.62, 195.87, 391.75, 174.35, 393.9, 161.43, 390.67, 143.14, 373.45, 124.84]], "area": 71049.87264999999, "iscrowd": 0, "image_id": 121453, "bbox": [302.42, 37.67, 243.23, 442.33], "category_id": 1, "id": 192531, "split": "val", "sentences": [{"tokens": ["a", "boy", "with", "plaid", "shorts", "on"], "raw": "A boy with plaid shorts on.", "sent_id": 22134, "sent": "a boy with plaid shorts on"}, {"tokens": ["a", "child", "in", "a", "grey", "shirt", "and", "plaid", "pants", "standing", "in", "from", "of", "a", "tv"], "raw": "A child in a grey shirt and plaid pants standing in from of a TV.", "sent_id": 22135, "sent": "a child in a grey shirt and plaid pants standing in from of a tv"}], "file_name": "COCO_train2014_000000121453_192531.jpg", "ann_id": 192531, "sent_ids": [22134, 22135], "ref_id": 13554}, {"segmentation": [[404.93, 214.94, 438.51, 188.07, 449.07, 163.12, 450.99, 141.05, 452.91, 119.94, 462.5, 105.55, 472.1, 94.04, 476.9, 99.79, 498.97, 107.47, 491.29, 129.54, 491.29, 158.33, 495.13, 178.48, 497.05, 182.31, 490.33, 205.34, 491.29, 207.26, 492.25, 255.24, 491.29, 263.88, 482.65, 280.19, 467.3, 293.62, 461.54, 298.42, 440.43, 326.25, 410.69, 356.95, 394.38, 379.02, 376.14, 403.01, 370.39, 392.46, 392.46, 354.07, 406.85, 333.92, 427.96, 304.18, 406.85, 302.26, 391.5, 328.17, 359.83, 382.86, 353.11, 386.7, 346.4, 377.1, 367.51, 352.16, 383.82, 307.06, 379.98, 287.87, 384.78, 249.48, 393.42, 218.78]], "area": 17710.89985, "iscrowd": 0, "image_id": 83005, "bbox": [346.4, 94.04, 152.57, 308.97], "category_id": 19, "id": 54682, "split": "val", "sentences": [{"tokens": ["a", "horse", "with", "red", "wrapped", "around", "its", "legs", "carrying", "a", "rider", "holding", "a", "rope"], "raw": "A horse with red wrapped around its legs carrying a rider holding a rope.", "sent_id": 22198, "sent": "a horse with red wrapped around its legs carrying a rider holding a rope"}, {"tokens": ["a", "horse", "that", "a", "man", "in", "a", "yellow", "hat", "is", "riding"], "raw": "A horse that a man in a yellow hat is riding.", "sent_id": 22199, "sent": "a horse that a man in a yellow hat is riding"}], "file_name": "COCO_train2014_000000083005_54682.jpg", "ann_id": 54682, "sent_ids": [22198, 22199], "ref_id": 13579}, {"segmentation": [[398.52, 225.92, 400.78, 209.63, 407.12, 196.96, 411.64, 182.49, 417.97, 168.01, 421.59, 153.98, 428.38, 131.81, 432.45, 116.89, 438.78, 97.88, 441.05, 83.86, 441.95, 79.33, 446.48, 76.17, 464.12, 80.69, 468.19, 81.6, 472.72, 85.22, 484.48, 90.19, 486.74, 90.19, 491.72, 90.19, 503.93, 94.26, 507.1, 96.53, 513.89, 110.55, 521.12, 117.34, 525.2, 124.58, 527.01, 127.29, 512.89, 149.17, 497.24, 161.84, 491.28, 167.8, 483.83, 176.0, 474.89, 182.7, 468.18, 192.39, 459.98, 199.1, 452.53, 209.53, 445.82, 216.24, 439.86, 221.46, 431.66, 231.89, 418.33, 247.02, 407.5, 245.94, 403.17, 242.69, 402.08, 240.52, 397.75, 235.1, 397.75, 229.69, 402.08, 223.18, 402.08, 221.02]], "area": 10684.841750000003, "iscrowd": 0, "image_id": 510027, "bbox": [397.75, 76.17, 129.26, 170.85], "category_id": 54, "id": 311169, "split": "val", "sentences": [{"tokens": ["cake", "cut", "into", "a", "triange", "in", "the", "orange", "colored", "container", "block"], "raw": "Cake cut into a triange in the orange colored container block.", "sent_id": 22279, "sent": "cake cut into a triange in the orange colored container block"}, {"tokens": ["the", "triangle", "shaped", "treat", "in", "the", "orange", "box"], "raw": "the triangle shaped treat in the orange box", "sent_id": 22280, "sent": "the triangle shaped treat in the orange box"}], "file_name": "COCO_train2014_000000510027_311169.jpg", "ann_id": 311169, "sent_ids": [22279, 22280], "ref_id": 13609}, {"segmentation": [[98.16, 392.63, 104.63, 382.92, 107.87, 379.69, 119.73, 328.99, 127.28, 280.45, 131.6, 261.03, 133.75, 249.17, 124.04, 248.09, 120.81, 232.99, 121.89, 206.02, 128.36, 186.61, 141.3, 182.29, 152.09, 177.98, 152.09, 170.43, 155.33, 157.48, 163.96, 143.46, 176.9, 143.46, 183.37, 148.85, 184.45, 157.48, 187.69, 180.13, 197.39, 185.53, 211.42, 199.55, 213.57, 217.89, 217.89, 228.67, 215.73, 240.54, 212.49, 244.85, 200.63, 244.85, 196.31, 245.93, 210.34, 290.16, 197.39, 339.78, 196.31, 348.4, 204.94, 361.35, 207.1, 365.66, 194.16, 376.45, 192.0, 316.04, 192.0, 293.39, 184.45, 282.61, 163.96, 280.45, 154.25, 302.02, 131.6, 367.82, 124.04, 388.31, 124.04, 398.02, 102.47, 396.94, 96.0, 394.79]], "area": 13303.6771, "iscrowd": 0, "image_id": 352185, "bbox": [96.0, 143.46, 121.89, 254.56], "category_id": 1, "id": 221507, "split": "val", "sentences": [{"tokens": ["a", "man", "on", "a", "bicycle"], "raw": "A man on a bicycle", "sent_id": 22285, "sent": "a man on a bicycle"}, {"tokens": ["a", "man", "on", "a", "bike"], "raw": "a man on a bike", "sent_id": 22286, "sent": "a man on a bike"}], "file_name": "COCO_train2014_000000352185_221507.jpg", "ann_id": 221507, "sent_ids": [22285, 22286], "ref_id": 13611}, {"segmentation": [[130.76, 63.3, 193.77, 144.14, 202.09, 208.33, 169.99, 298.68, 121.25, 361.68, 111.74, 324.83, 118.88, 188.12, 122.44, 81.13]], "area": 16581.841050000006, "iscrowd": 0, "image_id": 382469, "bbox": [111.74, 63.3, 90.35, 298.38], "category_id": 28, "id": 282775, "split": "val", "sentences": [{"tokens": ["left", "most", "white", "umbrella"], "raw": "left most white umbrella", "sent_id": 22289, "sent": "left most white umbrella"}, {"tokens": ["the", "white", "umbrella", "on", "the", "left"], "raw": "The white umbrella on the left", "sent_id": 22290, "sent": "the white umbrella on the left"}], "file_name": "COCO_train2014_000000382469_282775.jpg", "ann_id": 282775, "sent_ids": [22289, 22290], "ref_id": 13613}, {"segmentation": [[180.9, 423.6, 176.79, 435.94, 175.42, 452.38, 179.53, 475.68, 185.01, 497.61, 187.75, 518.16, 191.86, 525.01, 185.01, 526.39, 178.16, 519.53, 182.27, 538.72, 167.19, 538.72, 152.12, 525.01, 149.38, 497.61, 148.01, 474.31, 154.86, 453.75, 149.38, 430.45, 143.9, 412.64, 149.38, 400.3], [169.94, 370.15, 185.01, 363.3, 212.42, 356.45, 202.83, 368.78, 219.27, 385.23, 232.98, 374.27, 249.42, 389.34, 253.53, 383.86, 272.72, 387.97, 293.28, 389.34, 301.5, 405.79, 309.72, 412.64, 313.83, 426.34, 309.72, 437.31, 298.76, 434.56, 285.05, 429.08, 264.5, 419.49, 253.53, 409.9, 237.09, 408.53, 234.35, 424.97, 242.57, 452.38, 245.31, 475.68, 252.16, 520.9, 232.98, 514.05, 232.98, 493.49, 232.98, 471.57, 231.61, 456.49, 227.49, 444.16, 223.38, 429.08, 222.01, 442.79, 223.38, 460.6, 222.01, 478.42, 216.53, 488.01, 216.53, 518.16, 217.9, 537.35, 202.83, 529.13, 202.83, 493.49, 202.83, 464.71, 202.83, 441.42, 204.2, 424.97, 201.46, 411.27, 215.16, 404.42, 213.79, 394.82, 191.86, 390.71, 178.16, 385.23]], "area": 11544.93615, "iscrowd": 0, "image_id": 313437, "bbox": [143.9, 356.45, 169.93, 182.27], "category_id": 20, "id": 66657, "split": "val", "sentences": [{"tokens": ["small", "lamb", "in", "man", "'", "s", "right", "hand"], "raw": "Small lamb in man's right hand", "sent_id": 22338, "sent": "small lamb in man ' s right hand"}], "file_name": "COCO_train2014_000000313437_66657.jpg", "ann_id": 66657, "sent_ids": [22338], "ref_id": 13630}, {"segmentation": [[77.71, 368.95, 121.14, 288.95, 158.86, 268.38, 171.43, 266.1, 178.29, 255.81, 172.57, 244.38, 168.0, 229.52, 169.14, 188.38, 178.29, 175.81, 189.71, 170.1, 200.0, 164.38, 208.0, 162.1, 228.57, 165.52, 245.71, 175.81, 248.0, 186.1, 251.43, 198.67, 249.14, 205.52, 240.0, 234.1, 235.43, 247.81, 234.29, 255.81, 250.29, 276.38, 282.29, 283.24, 288.0, 291.24, 313.14, 326.67, 275.43, 348.38, 258.29, 407.81, 249.14, 434.1, 86.86, 430.67, 86.86, 419.24, 94.86, 386.1, 78.86, 371.24]], "area": 36023.27020000001, "iscrowd": 0, "image_id": 242090, "bbox": [77.71, 162.1, 235.43, 272.0], "category_id": 1, "id": 2161507, "split": "val", "sentences": [{"tokens": ["a", "black", "haired", "indian", "man", "facing", "a", "vendor", "in", "front", "of", "bananas"], "raw": "A black haired Indian man facing a vendor in front of bananas.", "sent_id": 22351, "sent": "a black haired indian man facing a vendor in front of bananas"}, {"tokens": ["a", "man", "in", "a", "white", "shirt", "standing", "by", "some", "bananas"], "raw": "A man in a white shirt standing by some bananas.", "sent_id": 22352, "sent": "a man in a white shirt standing by some bananas"}], "file_name": "COCO_train2014_000000242090_2161507.jpg", "ann_id": 2161507, "sent_ids": [22351, 22352], "ref_id": 13637}, {"segmentation": [[368.79, 233.21, 373.37, 245.78, 371.08, 260.65, 371.08, 266.36, 383.66, 270.94, 404.23, 277.8, 431.67, 305.24, 441.96, 312.1, 439.68, 321.24, 428.24, 340.68, 422.53, 358.97, 409.95, 371.55, 405.38, 373.83, 405.38, 395.56, 401.95, 425.28, 397.37, 447.01, 397.37, 464.16, 397.37, 484.73, 400.8, 522.46, 401.95, 539.61, 398.52, 544.19, 385.94, 543.04, 377.94, 530.47, 377.94, 513.32, 380.23, 491.59, 375.65, 455.01, 365.36, 420.71, 345.93, 476.73, 348.21, 538.47, 339.07, 543.04, 326.49, 544.19, 313.91, 541.9, 309.34, 533.9, 316.2, 519.03, 324.2, 512.17, 319.63, 489.31, 327.63, 434.43, 326.49, 379.55, 329.92, 349.82, 324.2, 315.53, 297.91, 346.39, 279.61, 368.12, 275.04, 380.69, 264.75, 377.26, 256.75, 377.26, 265.89, 366.97, 283.04, 349.82, 303.62, 302.95, 337.92, 269.79, 337.92, 252.64, 347.07, 242.35, 364.22, 222.92]], "area": 22758.37020000001, "iscrowd": 0, "image_id": 116832, "bbox": [256.75, 222.92, 185.21, 321.27], "category_id": 1, "id": 2152590, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "blue", "color", "shirt", "standing", "along", "with", "him", "friend"], "raw": "a man with blue color shirt standing along with him friend", "sent_id": 22443, "sent": "a man with blue color shirt standing along with him friend"}, {"tokens": ["a", "white", "man", "with", "a", "blue", "shirt", "and", "grey", "pants", "touching", "a", "yellow", "hydrant", "next", "to", "another", "man"], "raw": "A white man with a blue shirt and grey pants touching a yellow hydrant next to another man", "sent_id": 22444, "sent": "a white man with a blue shirt and grey pants touching a yellow hydrant next to another man"}], "file_name": "COCO_train2014_000000116832_2152590.jpg", "ann_id": 2152590, "sent_ids": [22443, 22444], "ref_id": 13669}, {"segmentation": [[242.98, 302.12, 221.69, 280.83, 222.81, 219.2, 240.74, 177.74, 266.51, 164.29, 283.32, 166.53, 294.53, 176.62, 315.82, 178.86, 320.3, 188.94, 334.87, 195.67, 340.47, 218.08, 312.46, 253.94, 282.2, 269.63, 253.06, 287.56, 248.58, 298.76]], "area": 10333.957300000002, "iscrowd": 0, "image_id": 339579, "bbox": [221.69, 164.29, 118.78, 137.83], "category_id": 54, "id": 313877, "split": "val", "sentences": [{"tokens": ["half", "a", "sandwich", "with", "lettuce", "and", "bacon", "on", "very", "white", "colored", "bread"], "raw": "Half a sandwich with lettuce and bacon on very white colored bread.", "sent_id": 22468, "sent": "half a sandwich with lettuce and bacon on very white colored bread"}, {"tokens": ["a", "hero", "sandwich", "on", "a", "white", "plate", "with", "lettuce", "and", "cold", "cuts", "on", "it"], "raw": "A hero sandwich on a white plate with lettuce and cold cuts on it", "sent_id": 22469, "sent": "a hero sandwich on a white plate with lettuce and cold cuts on it"}], "file_name": "COCO_train2014_000000339579_313877.jpg", "ann_id": 313877, "sent_ids": [22468, 22469], "ref_id": 13677}, {"segmentation": [[469.21, 470.29, 483.24, 418.52, 492.94, 388.31, 485.39, 335.46, 471.37, 299.87, 450.88, 264.27, 439.01, 231.91, 435.78, 193.08, 435.78, 174.74, 419.6, 157.48, 395.87, 138.07, 380.76, 127.28, 376.45, 115.42, 391.55, 70.11, 393.71, 59.33, 363.51, 40.99, 331.15, 39.91, 305.26, 76.58, 314.97, 110.02, 316.68, 141.21, 304.95, 154.47, 300.35, 161.11, 298.82, 168.76, 303.42, 186.11, 307.5, 194.78, 311.58, 212.64, 313.11, 236.62, 310.05, 253.46, 309.54, 282.54, 308.52, 302.95, 308.52, 315.2, 308.52, 320.3, 282.5, 347.34, 268.21, 355.0, 272.8, 370.81, 280.97, 382.55, 303.93, 388.16, 313.11, 386.63, 313.62, 390.71, 301.37, 412.14, 295.25, 422.35, 279.43, 476.43, 279.94, 480.0, 335.05, 480.0, 393.73, 400.92, 409.54, 401.43, 415.16, 467.25, 417.2, 478.98, 470.77, 480.0]], "area": 58327.0191, "iscrowd": 0, "image_id": 389743, "bbox": [268.21, 39.91, 224.73, 440.09], "category_id": 1, "id": 463265, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "tennis", "gear", "playing", "the", "game", "of", "tennis"], "raw": "A woman in tennis gear playing the game of tennis", "sent_id": 22478, "sent": "a woman in tennis gear playing the game of tennis"}, {"tokens": ["a", "woman", "playing", "tennis"], "raw": "A woman playing tennis", "sent_id": 22479, "sent": "a woman playing tennis"}], "file_name": "COCO_train2014_000000389743_463265.jpg", "ann_id": 463265, "sent_ids": [22478, 22479], "ref_id": 13681}, {"segmentation": [[590.12, 111.31, 596.84, 116.11, 601.64, 128.58, 624.67, 148.73, 640.0, 163.12, 640.0, 304.18, 598.76, 285.95, 567.09, 247.56, 587.24, 122.82]], "area": 9612.943649999996, "iscrowd": 0, "image_id": 541938, "bbox": [567.09, 111.31, 72.91, 192.87], "category_id": 47, "id": 673893, "split": "val", "sentences": [{"tokens": ["a", "bottle"], "raw": "a bottle", "sent_id": 22581, "sent": "a bottle"}, {"tokens": ["a", "blue", "and", "whit", "spotted", "jar", "holding", "butter", "on", "the", "right"], "raw": "A blue and whit spotted jar holding butter on the right.", "sent_id": 22582, "sent": "a blue and whit spotted jar holding butter on the right"}], "file_name": "COCO_train2014_000000541938_673893.jpg", "ann_id": 673893, "sent_ids": [22581, 22582], "ref_id": 13722}, {"segmentation": [[214.98, 212.49, 242.14, 216.91, 257.8, 217.25, 259.88, 222.66, 269.88, 221.41, 288.22, 217.66, 294.05, 229.75, 302.39, 243.08, 304.47, 250.58, 299.05, 259.33, 289.88, 263.08, 287.38, 278.92, 283.63, 293.09, 268.22, 289.75, 272.38, 263.08, 256.97, 267.67, 239.88, 267.25, 216.13, 253.08, 207.8, 265.17, 202.38, 283.5, 180.71, 284.75, 186.96, 267.67, 189.88, 256.83, 186.96, 237.67, 184.88, 253.08, 181.55, 273.5, 169.04, 288.5, 177.8, 255.58, 176.55, 237.67, 183.21, 223.91, 194.05, 213.91, 206.96, 212.25], [313.22, 188.91, 318.64, 187.25, 319.89, 178.08, 322.8, 180.58, 326.55, 184.75, 330.72, 184.75, 336.14, 181.0, 336.55, 187.66, 334.89, 192.25, 340.72, 196.83, 344.47, 203.91, 353.64, 209.75, 355.72, 216.83, 352.39, 221.0, 344.05, 221.0, 334.89, 217.66, 326.97, 211.41, 320.3, 203.08, 316.14, 194.33, 313.22, 189.33]], "area": 7326.071000000002, "iscrowd": 0, "image_id": 467760, "bbox": [169.04, 178.08, 186.68, 115.01], "category_id": 24, "id": 590663, "split": "val", "sentences": [{"tokens": ["zebra", "with", "its", "head", "behind", "the", "other", "zebra"], "raw": "Zebra with its head behind the other zebra", "sent_id": 22609, "sent": "zebra with its head behind the other zebra"}, {"tokens": ["a", "zebra", "that", "is", "on", "the", "left", "and", "is", "not", "completely", "visible"], "raw": "A zebra that is on the left and is not completely visible.", "sent_id": 22610, "sent": "a zebra that is on the left and is not completely visible"}], "file_name": "COCO_train2014_000000467760_590663.jpg", "ann_id": 590663, "sent_ids": [22609, 22610], "ref_id": 13735}, {"segmentation": [[235.11, 133.01, 229.21, 133.01, 223.31, 130.48, 219.1, 117.84, 214.89, 114.47, 216.57, 106.04, 220.79, 99.3, 221.63, 94.24, 227.53, 85.81, 234.27, 83.29, 241.01, 79.07, 248.6, 79.07, 251.12, 79.07, 262.08, 81.6, 265.45, 83.29, 267.13, 84.97, 269.66, 88.34, 275.56, 113.62, 278.09, 130.48, 283.15, 143.96, 284.83, 155.76, 284.83, 161.66, 287.36, 173.46, 287.36, 183.57, 290.73, 196.21, 292.42, 203.79, 289.89, 218.12, 286.52, 226.54, 282.3, 232.44, 282.3, 241.71, 284.83, 253.51, 286.52, 262.78, 279.78, 275.42, 277.25, 282.16, 272.19, 304.92, 272.19, 318.4, 269.66, 335.25, 268.82, 362.22, 268.82, 370.65, 230.06, 369.8, 230.06, 359.69, 225.84, 352.11, 222.47, 341.99, 221.63, 300.7, 221.63, 270.37, 223.31, 242.56, 225.0, 234.13, 224.16, 226.54, 216.57, 228.23, 212.36, 234.97, 206.46, 241.71, 203.09, 245.08, 199.72, 245.08, 197.19, 243.4, 195.51, 240.03, 195.51, 225.7, 203.09, 216.43, 209.83, 209.69, 205.62, 208.85, 200.56, 207.16, 189.61, 207.16, 182.87, 207.16, 177.81, 201.26, 172.75, 193.68, 177.81, 189.47, 181.18, 183.57, 187.08, 183.57, 197.19, 186.94, 204.78, 191.99, 214.89, 196.21, 216.57, 196.21, 220.79, 196.21, 223.31, 181.04, 227.53, 170.08, 233.43, 151.54, 235.96, 143.96, 236.8, 139.75]], "area": 17375.871550000007, "iscrowd": 0, "image_id": 479396, "bbox": [172.75, 79.07, 119.67, 291.58], "category_id": 1, "id": 214015, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "black", "dress", "playing", "wii"], "raw": "A woman in black dress playing Wii", "sent_id": 22664, "sent": "a woman in black dress playing wii"}, {"tokens": ["woman", "in", "black", "dress"], "raw": "Woman in black dress.", "sent_id": 22665, "sent": "woman in black dress"}], "file_name": "COCO_train2014_000000479396_214015.jpg", "ann_id": 214015, "sent_ids": [22664, 22665], "ref_id": 13754}, {"segmentation": [[6.23, 308.35, 136.0, 283.43, 173.38, 262.67, 215.95, 266.82, 270.97, 289.66, 354.03, 320.8, 425.66, 339.49, 473.42, 360.26, 473.42, 366.49, 426.7, 376.87, 328.07, 378.94, 205.56, 369.6, 209.72, 452.66, 182.72, 453.69, 185.84, 373.75, 7.27, 365.45, 0.0, 363.37, 0.0, 310.42, 5.19, 304.19]], "area": 35565.46029999999, "iscrowd": 0, "image_id": 380284, "bbox": [0.0, 262.67, 473.42, 191.02], "category_id": 28, "id": 1424698, "split": "val", "sentences": [{"tokens": ["straw", "-", "based", "umbrellas", "sit", "near", "a", "waterway"], "raw": "Straw-based umbrellas sit near a waterway.", "sent_id": 22755, "sent": "straw - based umbrellas sit near a waterway"}, {"tokens": ["umbrella", "in", "front"], "raw": "umbrella in front", "sent_id": 22756, "sent": "umbrella in front"}], "file_name": "COCO_train2014_000000380284_1424698.jpg", "ann_id": 1424698, "sent_ids": [22755, 22756], "ref_id": 13786}, {"segmentation": [[396.29, 131.7, 412.61, 122.1, 429.88, 127.86, 441.39, 162.4, 431.8, 181.59, 431.8, 195.03, 432.76, 205.58, 448.11, 231.49, 439.47, 260.28, 431.8, 351.44, 434.68, 362.95, 414.53, 372.55, 403.01, 400.37, 403.01, 409.97, 389.58, 403.25, 388.62, 384.06, 389.58, 378.3, 377.1, 391.74, 362.71, 390.78, 367.51, 364.87, 367.51, 351.44, 357.91, 344.72, 367.51, 320.73, 355.03, 303.46, 361.75, 275.63, 342.56, 274.67, 341.6, 258.36, 341.6, 246.84, 348.32, 237.25, 362.71, 237.25, 361.75, 229.57, 353.11, 223.82, 350.24, 221.9, 358.87, 205.58, 362.71, 198.87, 371.35, 194.07, 376.14, 192.15, 376.14, 183.51, 375.18, 149.93, 386.7, 136.5]], "area": 18996.018399999997, "iscrowd": 0, "image_id": 345882, "bbox": [341.6, 122.1, 106.51, 287.87], "category_id": 1, "id": 492809, "split": "val", "sentences": [{"tokens": ["a", "small", "girl", "wearing", "a", "brown", "dress", "with", "embroidered", "flowers"], "raw": "A small girl wearing a brown dress with embroidered flowers", "sent_id": 22771, "sent": "a small girl wearing a brown dress with embroidered flowers"}, {"tokens": ["a", "little", "girl", "wearing", "a", "brown", "dress", "with", "flowers"], "raw": "A little girl wearing a brown dress with flowers.", "sent_id": 22772, "sent": "a little girl wearing a brown dress with flowers"}], "file_name": "COCO_train2014_000000345882_492809.jpg", "ann_id": 492809, "sent_ids": [22771, 22772], "ref_id": 13792}, {"segmentation": [[391.55, 297.71, 426.07, 292.31, 467.06, 300.94, 473.53, 309.57, 495.1, 313.89, 515.6, 322.52, 538.25, 295.55, 531.78, 245.93, 519.91, 213.57, 472.45, 189.84, 478.92, 142.38, 457.35, 122.97, 429.3, 121.89, 409.89, 142.38, 417.44, 165.03, 413.12, 197.39, 388.31, 204.94, 374.29, 216.81, 340.85, 264.27, 343.01, 300.94, 379.69, 297.71]], "area": 22233.680849999997, "iscrowd": 0, "image_id": 209537, "bbox": [340.85, 121.89, 197.4, 200.63], "category_id": 1, "id": 1713338, "split": "val", "sentences": [{"tokens": ["a", "fat", "white", "man", "in", "a", "black", "shirt"], "raw": "A fat white man in a black shirt", "sent_id": 22780, "sent": "a fat white man in a black shirt"}, {"tokens": ["man", "in", "black", "shirt", "eating", "at", "an", "outside", "table"], "raw": "Man in black shirt eating at an outside table.", "sent_id": 22781, "sent": "man in black shirt eating at an outside table"}], "file_name": "COCO_train2014_000000209537_1713338.jpg", "ann_id": 1713338, "sent_ids": [22780, 22781], "ref_id": 13795}, {"segmentation": [[302.68, 116.33, 350.12, 129.88, 390.78, 152.47, 425.79, 167.15, 451.76, 193.13, 469.84, 211.2, 492.42, 233.79, 503.72, 254.12, 504.85, 268.8, 503.72, 290.26, 473.22, 298.16, 430.31, 277.84, 406.59, 257.51, 369.32, 221.36, 345.6, 201.04, 311.72, 182.96, 291.39, 168.28, 271.06, 147.95, 271.06, 133.27, 290.26, 121.98]], "area": 17704.816600000002, "iscrowd": 0, "image_id": 450914, "bbox": [271.06, 116.33, 233.79, 181.83], "category_id": 52, "id": 1043892, "split": "val", "sentences": [{"tokens": ["one", "of", "two", "bananas", "is", "placed", "immediately", "to", "the", "right", "of", "some", "oranges"], "raw": "One of two bananas is placed immediately to the right of some oranges.", "sent_id": 22795, "sent": "one of two bananas is placed immediately to the right of some oranges"}, {"tokens": ["the", "banana", "that", "is", "to", "the", "outmost", "left", "hand", "side", ".", "it", "is", "more", "towards", "the", "oranges", "rather", "than", "the", "apples"], "raw": "The banana that is to the outmost left hand side. It is more towards the oranges rather than the apples.", "sent_id": 22796, "sent": "the banana that is to the outmost left hand side . it is more towards the oranges rather than the apples"}], "file_name": "COCO_train2014_000000450914_1043892.jpg", "ann_id": 1043892, "sent_ids": [22795, 22796], "ref_id": 13801}, {"segmentation": [[115.18, 272.52, 110.66, 216.81, 315.43, 180.67, 322.96, 165.62, 329.73, 155.83, 331.99, 140.02, 371.89, 148.3, 456.96, 143.79, 500.0, 132.49, 499.11, 290.58, 461.47, 331.24, 182.18, 330.48, 114.43, 285.31]], "area": 58509.6256, "iscrowd": 0, "image_id": 53232, "bbox": [110.66, 132.49, 389.34, 198.75], "category_id": 65, "id": 317976, "split": "val", "sentences": [{"tokens": ["the", "bed", "closest", "to", "the", "camera"], "raw": "The bed closest to the camera.", "sent_id": 22820, "sent": "the bed closest to the camera"}, {"tokens": ["the", "hotel", "room", "bed", ",", "of", "two", ",", "furthest", "away", "from", "the", "window"], "raw": "The hotel room bed, of two, furthest away from the window.", "sent_id": 22821, "sent": "the hotel room bed , of two , furthest away from the window"}], "file_name": "COCO_train2014_000000053232_317976.jpg", "ann_id": 317976, "sent_ids": [22820, 22821], "ref_id": 13812}, {"segmentation": [[421.56, 491.16, 473.5, 482.15, 479.87, 477.38, 480.0, 573.32, 466.08, 586.04, 437.46, 526.67, 403.53, 504.41, 396.11, 498.05, 412.55, 483.21], [38.31, 500.17, 46.79, 562.72, 81.25, 533.56, 95.03, 518.19, 55.28, 508.12, 39.9, 500.7], [8.63, 482.15, 28.77, 493.28, 31.95, 570.67, 1.74, 591.87, 0.15, 508.12, 15.52, 501.76, 10.22, 489.57], [2.55, 602.06, 37.93, 578.93, 59.01, 632.0, 61.06, 640.0, 0.51, 637.44]], "area": 11047.860950000004, "iscrowd": 0, "image_id": 131030, "bbox": [0.15, 477.38, 479.85, 162.62], "category_id": 67, "id": 1621887, "split": "val", "sentences": [{"tokens": ["table", "underneath", "the", "platters", "of", "pizza", "in", "front", "of", "the", "smiling", "guy", "with", "glasses"], "raw": "Table underneath the platters of pizza in front of the smiling guy with glasses", "sent_id": 22839, "sent": "table underneath the platters of pizza in front of the smiling guy with glasses"}], "file_name": "COCO_train2014_000000131030_1621887.jpg", "ann_id": 1621887, "sent_ids": [22839], "ref_id": 13819}, {"segmentation": [[0.0, 349.15, 54.71, 350.14, 63.16, 348.73, 86.63, 352.02, 88.98, 353.9, 179.59, 358.59, 255.66, 362.82, 362.23, 364.69, 411.06, 365.63, 430.31, 372.68, 453.79, 389.11, 470.69, 408.36, 481.49, 417.75, 468.34, 440.76, 448.62, 439.35, 440.64, 429.49, 440.64, 429.49, 440.64, 448.27, 443.46, 478.79, 1.18, 478.32]], "area": 53927.4708, "iscrowd": 0, "image_id": 205794, "bbox": [0.0, 348.73, 481.49, 130.06], "category_id": 65, "id": 318517, "split": "val", "sentences": [{"tokens": ["a", "well", "made", "bed", ",", "with", "a", "turquoise", "towel", "on", "it"], "raw": "A well made bed, with a turquoise towel on it", "sent_id": 22840, "sent": "a well made bed , with a turquoise towel on it"}, {"tokens": ["a", "bed", "with", "a", "green", "towel", "rolled", "up", "on", "it"], "raw": "A bed with a green towel rolled up on it.", "sent_id": 22841, "sent": "a bed with a green towel rolled up on it"}], "file_name": "COCO_train2014_000000205794_318517.jpg", "ann_id": 318517, "sent_ids": [22840, 22841], "ref_id": 13820}, {"segmentation": [[239.52, 352.29, 221.81, 363.47, 208.76, 357.88, 206.9, 342.97, 209.69, 315.94, 216.22, 292.64, 251.63, 259.09, 275.86, 246.04, 372.79, 247.9, 426.84, 248.84, 439.89, 219.01, 448.28, 212.49, 443.62, 203.17, 478.1, 171.48, 480.9, 154.71, 488.35, 128.61, 508.86, 111.84, 577.82, 100.65, 637.47, 122.09, 638.4, 404.48, 287.05, 404.48, 357.88, 320.6, 398.88, 290.78, 280.52, 285.18, 268.41, 298.23, 264.68, 308.48, 258.16, 312.21, 251.63, 334.58, 247.9, 350.42]], "area": 78001.83320000001, "iscrowd": 0, "image_id": 363593, "bbox": [206.9, 100.65, 431.5, 303.83], "category_id": 1, "id": 192573, "split": "val", "sentences": [{"tokens": ["a", "white", "-", "haired", "man", "talking", "on", "a", "phone"], "raw": "A white-haired man talking on a phone.", "sent_id": 22842, "sent": "a white - haired man talking on a phone"}, {"tokens": ["a", "white", "haired", "man", "talking", "on", "a", "cellphone"], "raw": "A white haired man talking on a cellphone.", "sent_id": 22843, "sent": "a white haired man talking on a cellphone"}], "file_name": "COCO_train2014_000000363593_192573.jpg", "ann_id": 192573, "sent_ids": [22842, 22843], "ref_id": 13821}, {"segmentation": [[7.64, 159.21, 166.21, 187.87, 255.05, 140.1, 300.91, 145.84, 288.49, 174.49, 2.87, 216.52, 3.82, 166.85]], "area": 8381.242650000002, "iscrowd": 0, "image_id": 390496, "bbox": [2.87, 140.1, 298.04, 76.42], "category_id": 5, "id": 158601, "split": "val", "sentences": [{"tokens": ["an", "airplane", "with", "three", "windows", "and", "white", "and", "black", "rudder"], "raw": "An airplane with three windows and white and black rudder", "sent_id": 22857, "sent": "an airplane with three windows and white and black rudder"}, {"tokens": ["part", "of", "a", "small", "white", "airplane", "with", "three", "windows"], "raw": "Part of a small white airplane with three windows.", "sent_id": 22858, "sent": "part of a small white airplane with three windows"}], "file_name": "COCO_train2014_000000390496_158601.jpg", "ann_id": 158601, "sent_ids": [22857, 22858], "ref_id": 13828}, {"segmentation": [[302.34, 324.09, 316.78, 335.43, 331.72, 361.2, 348.22, 383.37, 372.96, 395.74, 424.5, 402.44, 455.42, 387.49, 498.2, 348.32, 521.4, 328.22, 525.0, 307.6, 518.3, 290.59, 506.96, 288.53, 489.96, 289.04, 485.32, 292.14, 483.26, 292.14, 476.04, 286.98, 481.19, 281.31, 502.84, 278.74, 499.75, 273.07, 470.37, 259.67, 457.48, 254.51, 447.69, 252.45, 443.57, 249.36, 438.93, 244.72, 435.32, 246.27, 430.68, 243.69, 428.11, 245.23, 421.92, 241.63, 418.31, 242.14, 396.15, 242.14, 375.02, 242.14, 357.49, 244.72, 333.27, 247.81, 309.56, 257.6, 296.16, 271.52, 289.46, 288.01, 292.04, 298.32, 297.71, 307.08, 332.24, 292.14, 339.97, 297.81, 330.18, 303.48, 312.14, 315.85, 305.95, 317.39, 302.34, 318.94]], "area": 26196.587750000006, "iscrowd": 0, "image_id": 541338, "bbox": [289.46, 241.63, 235.54, 160.81], "category_id": 51, "id": 714379, "split": "val", "sentences": [{"tokens": ["this", "is", "a", "bowl", "of", "vegetables", "and", "seasoning", "with", "two", "utensils", "placed", "in", "the", "food"], "raw": "This is a bowl of vegetables and seasoning with two utensils placed in the food", "sent_id": 22859, "sent": "this is a bowl of vegetables and seasoning with two utensils placed in the food"}, {"tokens": ["a", "bowl", "of", "food", "with", "two", "utensils", "in", "the", "bowl"], "raw": "A bowl of food with two utensils in the bowl.", "sent_id": 22860, "sent": "a bowl of food with two utensils in the bowl"}], "file_name": "COCO_train2014_000000541338_714379.jpg", "ann_id": 714379, "sent_ids": [22859, 22860], "ref_id": 13829}, {"segmentation": [[456.54, 383.82, 468.82, 385.18, 470.87, 382.45, 478.38, 382.45, 476.33, 373.24, 477.69, 364.03, 477.01, 364.03, 479.74, 359.93, 478.72, 354.13, 475.65, 349.69, 481.11, 301.92, 481.11, 299.53, 497.83, 337.75, 498.85, 346.96, 501.92, 367.1, 499.88, 372.22, 500.22, 373.92, 503.63, 379.38, 503.63, 382.11, 504.31, 387.91, 506.02, 389.28, 507.38, 390.3, 519.33, 391.33, 519.33, 385.53, 517.62, 371.19, 515.57, 367.78, 517.96, 361.64, 515.57, 357.54, 512.5, 349.35, 514.21, 339.45, 511.14, 328.19, 512.84, 316.59, 509.43, 287.58, 507.04, 279.05, 511.14, 292.7, 513.19, 295.09, 522.4, 289.97, 520.01, 284.85, 519.67, 281.44, 519.67, 275.3, 516.94, 272.23, 518.3, 250.38, 516.94, 245.27, 524.79, 236.73, 512.84, 215.23, 501.58, 209.77, 488.61, 207.39, 487.93, 203.97, 488.27, 197.15, 490.32, 194.76, 494.07, 188.62, 492.71, 183.16, 489.3, 179.06, 488.61, 173.6, 481.79, 172.58, 470.19, 178.04, 464.73, 187.93, 463.36, 191.69, 466.09, 194.08, 472.23, 203.29, 472.57, 210.8, 459.61, 216.26, 450.73, 222.74, 452.78, 237.08, 452.1, 257.21, 462.68, 264.38, 458.58, 266.42, 457.9, 284.17, 459.27, 307.38, 458.58, 328.88, 460.63, 365.05, 460.97, 368.12, 460.97, 373.24, 456.19, 376.99, 455.17, 382.8]], "area": 9554.066800000006, "iscrowd": 0, "image_id": 405777, "bbox": [450.73, 172.58, 74.06, 218.75], "category_id": 1, "id": 2151726, "split": "val", "sentences": [{"tokens": ["man", "with", "green", "shirt", "standing", "beside", "horse"], "raw": "man with green shirt standing beside horse", "sent_id": 22863, "sent": "man with green shirt standing beside horse"}, {"tokens": ["an", "older", "man", "in", "brown", "shirt", "and", "tan", "slacks", "carries", "a", "brown", "paper", "shopping", "bag"], "raw": "An older man in brown shirt and tan slacks carries a brown paper shopping bag.", "sent_id": 22864, "sent": "an older man in brown shirt and tan slacks carries a brown paper shopping bag"}], "file_name": "COCO_train2014_000000405777_2151726.jpg", "ann_id": 2151726, "sent_ids": [22863, 22864], "ref_id": 13831}, {"segmentation": [[274.77, 284.46, 284.35, 273.93, 314.98, 276.8, 321.69, 271.06, 324.56, 257.65, 295.84, 262.44, 312.11, 131.28, 312.11, 126.49, 313.07, 124.57, 318.81, 120.74, 306.37, 103.51, 291.05, 101.6, 278.6, 101.6, 264.24, 75.75, 264.24, 70.96, 264.24, 62.34, 264.24, 35.54, 261.37, 21.17, 257.54, 13.52, 265.2, 6.81, 346.58, 3.94, 352.32, 21.17, 355.2, 40.32, 359.02, 61.39, 373.39, 86.28, 422.21, 115.96, 471.04, 150.42, 484.44, 170.53, 488.27, 182.02, 414.55, 240.42, 421.26, 363.92, 389.66, 372.54, 382.0, 422.32, 346.58, 421.37, 334.13, 401.26, 327.43, 399.35, 337.0, 374.45, 338.92, 362.01, 324.56, 348.6, 310.2, 340.95, 293.92, 334.24, 289.13, 328.5, 275.73, 319.88, 269.03, 312.22, 264.24, 309.35, 254.67, 305.52]], "area": 47848.85605000002, "iscrowd": 0, "image_id": 545145, "bbox": [254.67, 3.94, 233.6, 418.38], "category_id": 1, "id": 457359, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "hat"], "raw": "A man wearing a hat.", "sent_id": 22939, "sent": "a man wearing a hat"}, {"tokens": ["a", "man", "cooking", "with", "a", "maroon", "shirt", "on", "and", "a", "black", "hat"], "raw": "a man cooking with a maroon shirt on and a black hat.", "sent_id": 22940, "sent": "a man cooking with a maroon shirt on and a black hat"}], "file_name": "COCO_train2014_000000545145_457359.jpg", "ann_id": 457359, "sent_ids": [22939, 22940], "ref_id": 13860}, {"segmentation": [[124.45, 418.49, 123.35, 381.05, 116.74, 356.82, 98.02, 341.4, 89.21, 244.49, 96.91, 232.37, 95.81, 177.31, 122.24, 135.46, 139.86, 120.04, 143.17, 96.91, 150.88, 104.62, 154.18, 98.02, 144.27, 67.18, 148.68, 40.75, 159.69, 27.53, 192.73, 26.43, 216.96, 44.05, 227.97, 66.08, 221.36, 88.1, 221.36, 106.83, 213.65, 110.13, 209.25, 128.85, 210.35, 135.46, 201.54, 158.59, 214.75, 231.27, 246.69, 235.68, 264.31, 258.81, 248.89, 277.53, 237.88, 277.53, 233.48, 267.62, 226.87, 268.72, 231.27, 312.77, 222.46, 332.59, 212.55, 342.5, 212.55, 392.06, 178.41, 409.68, 166.3, 416.29]], "area": 40241.63050000001, "iscrowd": 0, "image_id": 327209, "bbox": [89.21, 26.43, 175.1, 392.06], "category_id": 1, "id": 2150594, "split": "val", "sentences": [{"tokens": ["a", "blonde", "young", "man"], "raw": "a blonde young man", "sent_id": 23041, "sent": "a blonde young man"}, {"tokens": ["boy", "in", "a", "purple", "and", "black", "jacket", "and", "khaki", "pants"], "raw": "boy in a purple and black jacket and khaki pants", "sent_id": 23042, "sent": "boy in a purple and black jacket and khaki pants"}], "file_name": "COCO_train2014_000000327209_2150594.jpg", "ann_id": 2150594, "sent_ids": [23041, 23042], "ref_id": 13895}, {"segmentation": [[307.92, 376.1, 294.49, 354.38, 284.22, 337.4, 283.43, 326.34, 286.2, 317.65, 291.33, 312.12, 285.41, 305.41, 276.72, 297.11, 267.63, 289.21, 260.13, 293.95, 259.34, 291.58, 264.47, 280.92, 264.08, 266.7, 265.26, 256.83, 277.9, 248.54, 288.17, 243.8, 298.83, 243.01, 308.71, 245.38, 314.63, 250.12, 319.37, 259.59, 323.32, 274.21, 321.74, 287.24, 327.67, 287.64, 343.86, 286.06, 358.08, 286.06, 365.58, 288.03, 380.98, 304.22, 401.52, 322.79, 418.5, 342.14, 420.08, 352.8, 418.9, 356.75, 409.42, 357.94, 404.28, 359.91, 430.75, 377.26, 437.85, 384.76, 441.8, 389.9, 465.5, 416.36, 498.68, 451.91, 484.46, 468.21, 505.0, 489.54, 534.62, 520.85, 555.94, 562.72, 580.83, 593.64, 571.35, 599.17, 566.21, 603.51, 563.05, 606.67, 559.5, 605.88, 557.13, 604.3, 554.76, 599.96, 549.62, 588.9, 527.11, 559.67, 514.08, 545.06, 503.81, 526.89, 491.17, 515.83, 477.74, 504.38, 468.27, 493.72, 462.34, 485.03, 455.63, 482.26, 461.95, 491.35, 469.06, 502.41, 478.14, 514.25, 489.2, 530.84, 501.84, 547.03, 514.47, 568.36, 526.72, 586.92, 538.57, 605.09, 541.33, 611.92, 520.79, 611.52, 515.66, 608.76, 493.54, 585.85, 474.58, 560.58, 453.26, 534.51, 437.46, 512.81, 427.98, 516.76, 417.32, 504.52, 396.78, 480.43, 386.12, 463.05, 374.27, 442.01, 354.92, 413.74, 347.02, 395.96, 338.33, 380.17, 330.03, 369.9, 333.98, 382.54, 338.33, 395.96, 335.17, 403.86, 327.67, 406.63, 320.16, 401.49, 313.05, 392.01, 308.71, 383.33, 306.34, 377.4]], "area": 33267.35060000004, "iscrowd": 0, "image_id": 241170, "bbox": [259.34, 243.01, 321.49, 368.91], "category_id": 1, "id": 426123, "split": "val", "sentences": [{"tokens": ["boy", "looking", "away", "from", "camera"], "raw": "BOY LOOKING AWAY FROM CAMERA", "sent_id": 23053, "sent": "boy looking away from camera"}, {"tokens": ["torso", "of", "the", "boy", "holding", "kite"], "raw": "Torso of the boy holding kite.", "sent_id": 23054, "sent": "torso of the boy holding kite"}], "file_name": "COCO_train2014_000000241170_426123.jpg", "ann_id": 426123, "sent_ids": [23053, 23054], "ref_id": 13900}, {"segmentation": [[158.2, 282.39, 146.7, 290.3, 120.09, 292.45, 94.2, 293.17, 76.22, 286.7, 68.31, 277.35, 68.31, 270.16, 79.1, 261.53, 91.33, 257.22, 102.11, 250.03, 97.8, 241.4, 93.48, 227.02, 99.24, 211.92, 69.03, 216.95, 51.78, 207.6, 40.27, 190.34, 40.27, 175.24, 37.39, 168.77, 30.2, 155.83, 33.8, 146.48, 33.08, 137.85, 23.01, 124.18, 30.92, 117.71, 38.83, 125.62, 47.46, 142.16, 53.21, 147.2, 60.4, 139.29, 57.53, 127.78, 57.53, 113.4, 55.37, 94.7, 55.37, 81.76, 53.93, 65.94, 48.9, 58.03, 48.18, 45.8, 63.28, 46.52, 81.98, 47.24, 127.28, 45.8, 171.15, 45.8, 191.28, 54.43, 166.83, 78.16, 162.52, 98.3, 163.24, 125.62, 168.99, 142.88, 174.74, 135.69, 192.72, 137.13, 190.56, 157.26, 194.16, 168.05, 181.93, 177.4, 165.39, 201.85, 133.03, 216.23, 133.03, 231.33, 123.69, 247.15, 151.01, 261.53, 156.76, 273.76]], "area": 25488.366800000007, "iscrowd": 0, "image_id": 419396, "bbox": [23.01, 45.8, 171.15, 247.37], "category_id": 86, "id": 1154759, "split": "val", "sentences": [{"tokens": ["blue", "and", "gold", "vase"], "raw": "blue and gold vase", "sent_id": 23061, "sent": "blue and gold vase"}, {"tokens": ["full", "view", "of", "a", "blue", "color", "mug", "with", "flower", "designs"], "raw": "Full view of a blue color mug with flower designs.", "sent_id": 23062, "sent": "full view of a blue color mug with flower designs"}], "file_name": "COCO_train2014_000000419396_1154759.jpg", "ann_id": 1154759, "sent_ids": [23061, 23062], "ref_id": 13904}, {"segmentation": [[199.33, 294.26, 106.79, 336.18, 90.97, 336.18, 77.52, 330.64, 64.86, 280.81, 71.19, 279.23, 71.98, 278.44, 75.15, 261.03, 203.29, 230.18, 213.57, 231.77]], "area": 9894.889100000002, "iscrowd": 0, "image_id": 272155, "bbox": [64.86, 230.18, 148.71, 106.0], "category_id": 73, "id": 1099412, "split": "val", "sentences": [{"tokens": ["a", "laptop", "on", "tabule"], "raw": "a laptop on tabule", "sent_id": 23097, "sent": "a laptop on tabule"}, {"tokens": ["a", "laptop", "sitting", "on", "a", "table", "being", "used", "by", "a", "man"], "raw": "A laptop sitting on a table being used by a man", "sent_id": 23098, "sent": "a laptop sitting on a table being used by a man"}], "file_name": "COCO_train2014_000000272155_1099412.jpg", "ann_id": 1099412, "sent_ids": [23097, 23098], "ref_id": 13919}, {"segmentation": [[110.51, 425.26, 94.86, 415.68, 92.84, 399.53, 98.39, 394.48, 107.48, 392.46, 118.07, 391.45, 127.16, 390.95, 139.77, 386.41, 133.21, 380.35, 121.1, 377.33, 105.96, 379.85, 95.87, 381.87, 82.25, 383.89, 87.29, 374.3, 97.89, 364.71, 111.01, 357.14, 123.12, 353.1, 132.71, 362.19, 150.37, 364.21, 155.42, 391.96, 168.54, 389.94, 181.15, 388.93, 189.23, 390.95, 197.3, 388.93, 207.9, 385.4, 228.59, 381.87, 252.3, 374.3, 270.97, 367.74, 272.49, 368.24, 270.47, 387.42, 259.37, 422.74, 197.3, 446.46, 163.49, 455.04, 149.36, 448.98, 130.69, 433.84, 118.07, 426.78]], "area": 10216.146750000002, "iscrowd": 0, "image_id": 194685, "bbox": [82.25, 353.1, 190.24, 101.94], "category_id": 1, "id": 1718092, "split": "val", "sentences": [{"tokens": ["the", "blue", "letters", "on", "a", "colorful", "child", "'", "s", "blanket", "on", "the", "bottom", "bunk"], "raw": "The blue letters on a colorful child's blanket on the bottom bunk.", "sent_id": 23109, "sent": "the blue letters on a colorful child ' s blanket on the bottom bunk"}, {"tokens": ["the", "person", "and", "their", "blanket", "on", "the", "bottom", "bunk"], "raw": "the person and their blanket on the bottom bunk", "sent_id": 23110, "sent": "the person and their blanket on the bottom bunk"}], "file_name": "COCO_train2014_000000194685_1718092.jpg", "ann_id": 1718092, "sent_ids": [23109, 23110], "ref_id": 13923}, {"segmentation": [[170.54, 210.58, 127.49, 231.47, 88.24, 252.36, 80.01, 270.72, 83.17, 277.68, 90.77, 279.58, 82.54, 292.25, 92.03, 290.35, 94.57, 279.58, 125.59, 277.05, 185.73, 261.86, 183.2, 249.83, 173.07, 227.67], [187.63, 204.88, 188.89, 228.31, 192.69, 249.2, 202.82, 256.79, 239.54, 240.33, 263.6, 228.31, 288.29, 191.59, 262.96, 184.62, 233.84, 187.16]], "area": 8630.252150000002, "iscrowd": 0, "image_id": 347596, "bbox": [80.01, 184.62, 208.28, 107.63], "category_id": 42, "id": 647347, "split": "val", "sentences": [{"tokens": ["a", "surfboard", "being", "carried", "by", "a", "man", "walking", "right"], "raw": "A surfboard being carried by a man walking right.", "sent_id": 23140, "sent": "a surfboard being carried by a man walking right"}, {"tokens": ["a", "white", "surfboard"], "raw": "A White surfboard", "sent_id": 23141, "sent": "a white surfboard"}], "file_name": "COCO_train2014_000000347596_647347.jpg", "ann_id": 647347, "sent_ids": [23140, 23141], "ref_id": 13934}, {"segmentation": [[193.29, 197.87, 371.39, 178.69, 440.8, 172.3, 474.6, 174.13, 476.42, 186.91, 439.89, 190.57, 358.6, 198.79, 261.79, 211.57, 186.89, 218.88], [37.11, 208.83, 164.06, 196.96, 159.49, 222.53, 15.19, 234.41, 0.57, 237.15, 0.0, 209.75]], "area": 9450.401949999998, "iscrowd": 0, "image_id": 92685, "bbox": [0.0, 172.3, 476.42, 64.85], "category_id": 7, "id": 248785, "split": "val", "sentences": [{"tokens": ["3rd", "train", "from", "front"], "raw": "3rd train from front", "sent_id": 23148, "sent": "3rd train from front"}, {"tokens": ["orange", "train", "on", "furthest", "track"], "raw": "Orange train on furthest track.", "sent_id": 23149, "sent": "orange train on furthest track"}], "file_name": "COCO_train2014_000000092685_248785.jpg", "ann_id": 248785, "sent_ids": [23148, 23149], "ref_id": 13936}, {"segmentation": [[15.13, 335.34, 28.88, 305.08, 141.65, 295.46, 167.78, 302.33, 151.28, 354.59, 147.16, 380.72, 156.78, 402.73, 162.28, 415.11, 158.16, 426.11, 144.4, 420.61, 133.4, 409.6, 125.15, 404.1, 116.9, 410.98, 112.77, 415.11, 104.52, 416.48, 88.02, 409.6, 55.01, 408.23, 50.89, 424.73, 41.26, 424.73, 27.51, 426.11, 24.76, 416.48, 16.5, 401.35, 13.75, 344.97]], "area": 15883.808150000006, "iscrowd": 0, "image_id": 198277, "bbox": [13.75, 295.46, 154.03, 130.65], "category_id": 3, "id": 144210, "split": "val", "sentences": [{"tokens": ["a", "yellow", "taxi", ",", "which", "is", "to", "the", "left", "of", "another", "taxi"], "raw": "A yellow taxi, which is to the left of another taxi", "sent_id": 23168, "sent": "a yellow taxi , which is to the left of another taxi"}, {"tokens": ["the", "yellow", "cab", "closest", "to", "the", "buildings", "on", "the", "left"], "raw": "the yellow cab closest to the buildings on the left.", "sent_id": 23169, "sent": "the yellow cab closest to the buildings on the left"}], "file_name": "COCO_train2014_000000198277_144210.jpg", "ann_id": 144210, "sent_ids": [23168, 23169], "ref_id": 13945}, {"segmentation": [[342.77, 454.5, 332.62, 455.63, 321.34, 446.61, 324.72, 436.46, 320.21, 429.69, 323.6, 418.42, 334.87, 385.72, 341.64, 360.91, 363.06, 323.71, 372.08, 307.92, 366.44, 304.54, 366.44, 294.39, 369.83, 275.22, 376.59, 266.2, 383.36, 259.44, 379.97, 223.36, 373.21, 194.04, 366.44, 183.89, 345.02, 177.13, 326.98, 163.6, 313.45, 160.22, 299.92, 148.94, 295.41, 148.94, 288.64, 141.05, 276.24, 141.05, 279.62, 129.77, 294.28, 130.9, 329.23, 148.94, 345.02, 152.32, 360.81, 151.2, 363.06, 142.18, 369.83, 134.28, 383.36, 124.14, 391.25, 124.14, 392.38, 115.12, 403.65, 108.35, 409.29, 103.84, 437.48, 115.12, 439.73, 125.26, 439.73, 137.67, 447.62, 148.94, 460.03, 146.69, 469.05, 147.81, 466.79, 143.3, 465.66, 141.05, 474.68, 138.79, 483.7, 141.05, 496.11, 153.45, 510.77, 170.36, 523.17, 186.15, 525.42, 203.06, 515.28, 206.44, 498.36, 201.93, 487.09, 196.3, 474.68, 200.81, 471.3, 217.72, 472.43, 241.4, 472.43, 252.67, 481.45, 269.59, 489.34, 291.01, 485.96, 301.16, 474.68, 301.16, 474.68, 320.32, 483.7, 348.51, 493.85, 364.3, 513.02, 416.16, 517.53, 429.69, 526.55, 448.86, 526.55, 457.88, 513.02, 463.52, 494.98, 453.37, 485.96, 434.2, 480.32, 410.53, 469.05, 389.1, 448.75, 369.93, 440.86, 349.64, 435.22, 339.49, 425.07, 319.2, 410.42, 334.98, 396.89, 359.79, 375.46, 382.34, 364.19, 406.01, 347.28, 446.61, 347.28, 446.61, 347.28, 453.37]], "area": 35122.72864999998, "iscrowd": 0, "image_id": 169653, "bbox": [276.24, 103.84, 250.31, 359.68], "category_id": 1, "id": 449278, "split": "val", "sentences": [{"tokens": ["a", "baseball", "umpire", "calling", "a", "strikeout"], "raw": "A baseball umpire calling a strikeout.", "sent_id": 23245, "sent": "a baseball umpire calling a strikeout"}, {"tokens": ["an", "umpire", "in", "a", "baseball", "game"], "raw": "An umpire in a baseball game.", "sent_id": 23246, "sent": "an umpire in a baseball game"}], "file_name": "COCO_train2014_000000169653_449278.jpg", "ann_id": 449278, "sent_ids": [23245, 23246], "ref_id": 13974}, {"segmentation": [[308.49, 373.21, 321.44, 353.8, 350.56, 346.25, 474.61, 283.69, 454.11, 348.4, 347.33, 412.04, 320.36, 442.25, 310.65, 445.48, 286.92, 431.46, 285.84, 405.57, 304.18, 371.06]], "area": 11067.988, "iscrowd": 0, "image_id": 286483, "bbox": [285.84, 283.69, 188.77, 161.79], "category_id": 36, "id": 617242, "split": "val", "sentences": [{"tokens": ["a", "black", "snowboard", "with", "a", "woman", "'", "s", "feet", "attached", "to", "it"], "raw": "A black snowboard with a woman's feet attached to it.", "sent_id": 23291, "sent": "a black snowboard with a woman ' s feet attached to it"}, {"tokens": ["black", "snowboard", "in", "the", "snow"], "raw": "Black snowboard in the snow.", "sent_id": 23292, "sent": "black snowboard in the snow"}], "file_name": "COCO_train2014_000000286483_617242.jpg", "ann_id": 617242, "sent_ids": [23291, 23292], "ref_id": 13993}, {"segmentation": [[176.61, 242.02, 187.45, 225.77, 205.87, 212.77, 222.12, 208.43, 234.04, 208.43, 249.21, 218.19, 258.96, 234.44, 263.3, 265.86, 252.46, 295.12, 243.79, 310.28, 252.46, 326.54, 243.79, 360.13, 236.21, 372.05, 232.96, 415.39, 222.12, 446.81, 221.04, 469.56, 71.51, 471.73, 75.85, 419.72, 109.44, 338.46]], "area": 32306.337050000002, "iscrowd": 0, "image_id": 416076, "bbox": [71.51, 208.43, 191.79, 263.3], "category_id": 1, "id": 465041, "split": "val", "sentences": [{"tokens": ["the", "girl", "with", "long", "light", "hair"], "raw": "The girl with long light hair.", "sent_id": 23312, "sent": "the girl with long light hair"}, {"tokens": ["a", "young", "girl", "with", "a", "green", "plaid", "jacket", "wearing", "snow", "googles"], "raw": "A young girl with a green plaid jacket wearing snow googles.", "sent_id": 23313, "sent": "a young girl with a green plaid jacket wearing snow googles"}], "file_name": "COCO_train2014_000000416076_465041.jpg", "ann_id": 465041, "sent_ids": [23312, 23313], "ref_id": 14002}, {"segmentation": [[196.92, 139.35, 168.34, 185.41, 165.16, 242.58, 212.8, 368.04, 335.09, 514.14, 370.02, 545.91, 377.97, 552.26, 260.45, 550.67, 195.33, 493.5, 134.99, 407.74, 115.93, 329.93, 100.05, 291.81, 93.7, 228.29, 112.75, 144.12, 160.4, 115.53, 198.51, 120.3, 204.86, 128.24]], "area": 39617.25264999999, "iscrowd": 0, "image_id": 527345, "bbox": [93.7, 115.53, 284.27, 436.73], "category_id": 58, "id": 2219930, "split": "val", "sentences": [{"tokens": ["the", "hotdog", "on", "the", "left"], "raw": "The hotdog on the left", "sent_id": 23335, "sent": "the hotdog on the left"}, {"tokens": ["sausage", "that", "is", "on", "top", "of", "the", "beans"], "raw": "sausage that is on top of the beans", "sent_id": 23336, "sent": "sausage that is on top of the beans"}], "file_name": "COCO_train2014_000000527345_2219930.jpg", "ann_id": 2219930, "sent_ids": [23335, 23336], "ref_id": 14011}, {"segmentation": [[232.58, 198.57, 199.49, 209.93, 176.76, 225.24, 170.84, 235.61, 169.85, 242.03, 173.8, 253.89, 177.26, 264.26, 181.21, 272.17, 227.15, 286.0, 221.22, 297.36, 199.49, 321.56, 180.22, 358.61, 175.78, 388.74, 174.79, 395.17, 175.28, 401.0, 389.17, 401.0, 388.68, 365.03, 380.28, 334.41, 363.48, 313.66, 358.05, 306.74, 394.6, 303.78, 419.3, 287.48, 421.28, 261.79, 405.97, 236.11, 363.98, 214.87, 299.27, 201.04]], "area": 40049.7802, "iscrowd": 0, "image_id": 196198, "bbox": [169.85, 198.57, 251.43, 202.43], "category_id": 70, "id": 1967568, "split": "val", "sentences": [{"tokens": ["a", "toilet", "with", "a", "wooden", "seat"], "raw": "A toilet with a wooden seat.", "sent_id": 23381, "sent": "a toilet with a wooden seat"}, {"tokens": ["white", "and", "brown", "uropian", "closet"], "raw": "white and brown uropian closet", "sent_id": 23382, "sent": "white and brown uropian closet"}], "file_name": "COCO_train2014_000000196198_1967568.jpg", "ann_id": 1967568, "sent_ids": [23381, 23382], "ref_id": 14029}, {"segmentation": [[39.91, 460.58, 169.35, 419.6, 227.6, 409.89, 266.43, 417.44, 308.49, 462.74, 20.49, 470.29]], "area": 9620.629100000004, "iscrowd": 0, "image_id": 412190, "bbox": [20.49, 409.89, 288.0, 60.4], "category_id": 81, "id": 1136394, "split": "val", "sentences": [{"tokens": ["an", "empty", "sink"], "raw": "An empty sink.", "sent_id": 23458, "sent": "an empty sink"}, {"tokens": ["white", "sink"], "raw": "White sink.", "sent_id": 23459, "sent": "white sink"}], "file_name": "COCO_train2014_000000412190_1136394.jpg", "ann_id": 1136394, "sent_ids": [23458, 23459], "ref_id": 14059}, {"segmentation": [[531.34, 181.19, 535.69, 170.81, 538.82, 160.19, 541.72, 154.16, 547.27, 149.57, 551.86, 148.12, 556.68, 149.33, 558.13, 149.57, 559.82, 147.88, 557.65, 142.33, 557.65, 130.74, 557.65, 119.88, 559.82, 109.75, 563.44, 100.82, 571.41, 94.3, 579.85, 91.16, 584.44, 90.68, 587.58, 89.23, 592.65, 92.85, 600.13, 100.09, 604.23, 106.85, 607.13, 113.37, 609.78, 123.99, 611.23, 132.19, 611.23, 136.78, 608.58, 139.43, 606.4, 141.12, 603.99, 143.54, 602.06, 143.78, 600.85, 146.67, 603.27, 146.67, 610.75, 146.92, 615.58, 145.47, 621.13, 142.81, 624.75, 144.26, 626.92, 146.19, 633.44, 145.47, 635.13, 147.88, 640.0, 152.23, 639.95, 185.77, 639.95, 234.04, 639.95, 282.32, 639.95, 330.59, 639.95, 378.86, 638.02, 382.96, 634.16, 385.62, 631.26, 385.86, 623.78, 386.1, 626.44, 389.48, 631.5, 391.41, 635.37, 392.37, 639.47, 393.82, 640.0, 394.79, 639.47, 417.47, 630.54, 421.34, 619.68, 423.03, 603.02, 416.75, 596.27, 405.89, 593.13, 400.34, 586.85, 396.48, 582.03, 392.62, 578.65, 383.44, 577.92, 376.2, 580.34, 370.89, 585.89, 352.31, 587.34, 341.21, 587.82, 332.76, 589.03, 325.28, 598.2, 300.42, 599.4, 292.45, 594.09, 289.56, 586.13, 290.28, 582.03, 288.11, 578.89, 284.25, 574.06, 283.04, 562.96, 280.63, 554.03, 276.52, 546.31, 270.73, 538.1, 265.18, 536.17, 260.11, 534.48, 254.08, 541.48, 236.22, 542.44, 227.77, 542.93, 226.8, 538.34, 224.39, 535.93, 219.56, 534.24, 207.5, 532.55, 200.98, 529.65, 196.63, 529.65, 191.33, 529.17, 186.26]], "area": 23229.450050000003, "iscrowd": 0, "image_id": 550760, "bbox": [529.17, 89.23, 110.83, 333.8], "category_id": 1, "id": 570390, "split": "val", "sentences": [{"tokens": ["a", "woman", "sitting", "with", "arms", "folded"], "raw": "a woman sitting with arms folded", "sent_id": 23491, "sent": "a woman sitting with arms folded"}, {"tokens": ["a", "women"], "raw": "a women", "sent_id": 23492, "sent": "a women"}], "file_name": "COCO_train2014_000000550760_570390.jpg", "ann_id": 570390, "sent_ids": [23491, 23492], "ref_id": 14072}, {"segmentation": [[209.53, 344.63, 211.96, 332.49, 210.34, 300.94, 207.91, 271.01, 210.34, 261.3, 207.91, 232.18, 203.06, 207.1, 209.53, 192.54, 205.48, 162.61, 210.34, 152.9, 208.72, 124.58, 208.72, 117.3, 208.72, 114.07, 184.45, 101.93, 168.27, 92.22, 166.65, 84.94, 171.51, 75.24, 192.54, 67.96, 245.93, 57.44, 242.7, 53.39, 248.36, 42.07, 257.26, 29.93, 273.44, 29.93, 285.57, 42.88, 285.57, 62.29, 285.57, 69.57, 303.37, 95.46, 308.22, 110.02, 309.84, 120.54, 316.31, 135.1, 313.08, 148.85, 318.74, 156.13, 303.37, 160.99, 300.13, 146.43, 292.85, 127.82, 291.24, 140.76, 298.52, 173.12, 296.9, 181.21, 295.28, 186.88, 295.28, 204.67, 295.28, 224.09, 295.28, 237.84, 288.81, 261.3, 283.96, 289.62, 279.1, 323.6, 277.48, 326.83, 271.01, 328.45, 266.16, 320.36, 260.49, 300.94, 260.49, 287.19, 260.49, 272.63, 260.49, 258.88, 251.6, 225.71, 236.22, 259.69, 236.22, 275.87, 239.46, 295.28, 232.99, 314.7, 231.37, 343.01, 237.03, 350.29]], "area": 23732.9001, "iscrowd": 0, "image_id": 268334, "bbox": [166.65, 29.93, 152.09, 320.36], "category_id": 1, "id": 203918, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "near", "the", "sheep", "touching", "a", "lying", "sheep", "with", "a", "rod"], "raw": "A man standing near the sheep touching a lying sheep with a rod.", "sent_id": 23497, "sent": "a man standing near the sheep touching a lying sheep with a rod"}, {"tokens": ["a", "older", "man", "wearing", "a", "gray", "t", "-", "shirt", "and", "gray", "sweat", "pants"], "raw": "A older man wearing a gray T-Shirt and gray sweat pants.", "sent_id": 23498, "sent": "a older man wearing a gray t - shirt and gray sweat pants"}], "file_name": "COCO_train2014_000000268334_203918.jpg", "ann_id": 203918, "sent_ids": [23497, 23498], "ref_id": 14074}, {"segmentation": [[251.81, 231.72, 212.84, 248.95, 182.11, 248.95, 140.15, 248.95, 146.14, 329.89, 185.86, 334.39, 245.07, 334.39, 320.01, 331.39, 323.01, 307.41, 313.27, 296.92, 313.27, 283.43, 314.02, 272.94, 314.02, 266.94, 335.0, 268.44, 359.73, 269.19, 371.72, 272.94, 377.72, 281.93, 383.71, 272.19, 393.46, 245.21, 395.7, 206.99, 397.2, 195.0, 385.96, 181.51, 356.73, 164.27, 302.77, 167.27, 287.79, 178.51, 278.04, 189.0, 260.06, 215.98], [427.93, 302.17, 431.68, 281.93, 453.41, 276.68, 469.9, 255.7, 496.13, 255.7, 500.0, 256.45, 500.0, 331.39, 460.16, 335.0, 428.68, 333.64]], "area": 31404.22309999999, "iscrowd": 0, "image_id": 254176, "bbox": [140.15, 164.27, 359.85, 170.73], "category_id": 4, "id": 152963, "split": "val", "sentences": [{"tokens": ["a", "motorcycle", "covered", "in", "no", "signs"], "raw": "A motorcycle covered in NO signs.", "sent_id": 23503, "sent": "a motorcycle covered in no signs"}, {"tokens": ["a", "side", "car", "with", "signs", "on", "it"], "raw": "A side car with signs on it.", "sent_id": 23504, "sent": "a side car with signs on it"}], "file_name": "COCO_train2014_000000254176_152963.jpg", "ann_id": 152963, "sent_ids": [23503, 23504], "ref_id": 14076}, {"segmentation": [[164.8, 312.41, 141.26, 184.6, 131.17, 103.89, 137.89, 61.29, 165.92, 27.65, 210.76, 44.47, 242.15, 97.16, 278.03, 198.06, 294.84, 313.53, 291.48, 316.89, 246.64, 325.86, 215.25, 326.98, 196.19, 323.62, 171.52, 318.01]], "area": 34016.586500000005, "iscrowd": 0, "image_id": 238187, "bbox": [131.17, 27.65, 163.67, 299.33], "category_id": 52, "id": 1041433, "split": "val", "sentences": [{"tokens": ["the", "top", "of", "the", "banana", "on", "the", "apple"], "raw": "the top of the banana on the apple", "sent_id": 23574, "sent": "the top of the banana on the apple"}, {"tokens": ["half", "cut", "banana", "on", "top", "of", "the", "apple"], "raw": "half cut banana on top of the apple.", "sent_id": 23575, "sent": "half cut banana on top of the apple"}], "file_name": "COCO_train2014_000000238187_1041433.jpg", "ann_id": 1041433, "sent_ids": [23574, 23575], "ref_id": 14105}, {"segmentation": [[170.14, 81.59, 198.36, 71.22, 220.83, 68.92, 237.53, 58.55, 282.47, 52.21, 319.91, 48.18, 350.44, 52.21, 389.61, 80.44, 424.17, 109.82, 426.0, 275.14, 426.0, 324.68, 402.28, 293.58, 385.0, 274.57, 363.69, 267.08, 338.34, 265.35, 311.27, 265.35, 290.53, 263.62, 266.91, 259.59, 232.92, 254.4, 220.83, 250.95, 217.37, 220.99, 202.97, 219.84, 186.84, 231.36, 180.5, 265.35, 166.1, 288.97, 152.85, 310.86, 148.82, 333.9, 145.37, 282.63, 122.32, 301.64, 110.23, 312.01, 91.22, 316.62, 96.98, 307.4, 115.41, 295.3, 134.42, 268.23, 136.72, 219.84, 141.91, 154.17, 155.73, 116.15, 162.07, 89.08]], "area": 56969.03310000002, "iscrowd": 0, "image_id": 559700, "bbox": [91.22, 48.18, 334.78, 285.72], "category_id": 22, "id": 583851, "split": "val", "sentences": [{"tokens": ["a", "large", "standing", "elephant"], "raw": "A large standing elephant.", "sent_id": 23637, "sent": "a large standing elephant"}, {"tokens": ["a", "large", "adult", "elephant", "with", "tusks", "standing", "beside", "a", "younger", "elephant"], "raw": "A large adult elephant with tusks standing beside a younger elephant", "sent_id": 23638, "sent": "a large adult elephant with tusks standing beside a younger elephant"}], "file_name": "COCO_train2014_000000559700_583851.jpg", "ann_id": 583851, "sent_ids": [23637, 23638], "ref_id": 14127}, {"segmentation": [[270.76, 69.97, 292.65, 69.97, 298.9, 81.23, 302.03, 86.23, 317.66, 85.6, 322.03, 88.1, 330.79, 85.6, 351.42, 96.23, 357.67, 111.86, 335.16, 142.5, 343.92, 158.13, 345.17, 173.76, 356.42, 170.01, 365.8, 169.39, 386.43, 195.65, 372.05, 210.65, 342.04, 207.53, 317.66, 211.28, 302.65, 214.4, 290.15, 222.53, 284.52, 235.04, 252.01, 247.54, 227.0, 236.91, 228.87, 227.53, 233.87, 217.53, 226.37, 208.15, 243.25, 186.89, 243.88, 148.75, 261.39, 129.37, 261.39, 106.86, 259.51, 80.6]], "area": 15693.7008, "iscrowd": 0, "image_id": 102144, "bbox": [226.37, 69.97, 160.06, 177.57], "category_id": 88, "id": 1159680, "split": "val", "sentences": [{"tokens": ["teddy", "bear", "doll", ",", "second", "from", "left"], "raw": "Teddy bear doll, second from left", "sent_id": 23686, "sent": "teddy bear doll , second from left"}], "file_name": "COCO_train2014_000000102144_1159680.jpg", "ann_id": 1159680, "sent_ids": [23686], "ref_id": 14152}, {"segmentation": [[273.04, 304.51, 315.46, 298.7, 322.99, 304.17, 328.46, 272.35, 330.17, 259.69, 333.25, 253.88, 337.35, 263.8, 341.8, 267.22, 347.96, 268.25, 353.78, 272.01, 358.91, 279.88, 362.33, 283.3, 368.49, 288.77, 372.59, 288.77, 381.49, 289.12, 386.96, 290.83, 383.88, 301.43, 383.54, 309.64, 385.93, 317.51, 386.28, 322.64, 388.67, 329.83, 392.09, 331.2, 386.62, 342.83, 378.41, 353.78, 374.3, 363.35, 367.12, 374.64, 358.57, 375.0, 276.12, 375.0, 273.04, 365.41, 272.01, 360.28, 276.8, 354.8, 275.09, 328.12, 275.09, 320.93]], "area": 9387.376400000003, "iscrowd": 0, "image_id": 479396, "bbox": [272.01, 253.88, 120.08, 121.12], "category_id": 63, "id": 2224557, "split": "val", "sentences": [{"tokens": ["sofa"], "raw": "SOFA", "sent_id": 23697, "sent": "sofa"}, {"tokens": ["an", "empty", "couch", "seat", "behind", "the", "woman", "holding", "the", "wii", "controller"], "raw": "An empty couch seat behind the woman holding the Wii controller.", "sent_id": 23698, "sent": "an empty couch seat behind the woman holding the wii controller"}], "file_name": "COCO_train2014_000000479396_2224557.jpg", "ann_id": 2224557, "sent_ids": [23697, 23698], "ref_id": 14158}, {"segmentation": [[429.97, 150.64, 405.03, 263.53, 405.03, 267.46, 552.7, 269.43, 558.61, 145.39]], "area": 16661.716750000007, "iscrowd": 0, "image_id": 94300, "bbox": [405.03, 145.39, 153.58, 124.04], "category_id": 84, "id": 1656431, "split": "val", "sentences": [{"tokens": ["a", "childs", "book", "on", "a", "bench"], "raw": "a childs book on a bench", "sent_id": 23705, "sent": "a childs book on a bench"}, {"tokens": ["a", "tangerine", "bear", "hard", "back", "book"], "raw": "A Tangerine Bear hard back book.", "sent_id": 23706, "sent": "a tangerine bear hard back book"}], "file_name": "COCO_train2014_000000094300_1656431.jpg", "ann_id": 1656431, "sent_ids": [23705, 23706], "ref_id": 14161}, {"segmentation": [[1.38, 168.13, 63.26, 107.62, 147.16, 75.98, 199.42, 69.11, 211.79, 40.23, 226.92, 73.23, 349.32, 111.74, 416.71, 183.26, 426.34, 195.63, 292.93, 192.88, 220.04, 192.88, 96.27, 194.26, 39.88, 184.63]], "area": 36762.11134999999, "iscrowd": 0, "image_id": 261800, "bbox": [1.38, 40.23, 424.96, 155.4], "category_id": 28, "id": 286413, "split": "val", "sentences": [{"tokens": ["a", "red", "umbrella", "opened", "for", "protection", "during", "a", "rain", "storm"], "raw": "a red umbrella opened for protection during a rain storm", "sent_id": 23746, "sent": "a red umbrella opened for protection during a rain storm"}, {"tokens": ["a", "red", "umbrella"], "raw": "a red umbrella", "sent_id": 23747, "sent": "a red umbrella"}], "file_name": "COCO_train2014_000000261800_286413.jpg", "ann_id": 286413, "sent_ids": [23746, 23747], "ref_id": 14175}, {"segmentation": [[314.22, 480.0, 638.19, 480.0, 617.61, 334.81, 566.68, 243.79, 556.93, 227.54, 509.26, 214.54, 487.58, 206.95, 455.08, 176.61, 461.58, 154.94, 455.08, 135.44, 461.58, 97.52, 450.74, 84.51, 396.57, 82.35, 345.64, 70.43, 314.22, 95.35, 315.3, 111.6, 334.81, 128.94, 344.56, 161.44, 349.98, 174.45, 331.56, 179.86, 322.89, 188.53, 323.97, 221.04, 308.8, 236.21, 288.22, 260.05, 275.21, 277.38, 247.04, 303.39, 234.04, 328.31, 226.46, 347.81, 228.62, 380.32, 249.21, 400.9, 271.96, 405.24, 293.63, 405.24, 312.05, 380.32, 312.05, 480.0]], "area": 105923.31354999999, "iscrowd": 0, "image_id": 376817, "bbox": [226.46, 70.43, 411.73, 409.57], "category_id": 1, "id": 447372, "split": "val", "sentences": [{"tokens": ["man", "in", "white", "shirt", "and", "blue", "and", "blue", "checked", "vest"], "raw": "Man in white shirt and blue and blue checked vest.", "sent_id": 23758, "sent": "man in white shirt and blue and blue checked vest"}, {"tokens": ["an", "officer", "in", "a", "blue", "vest"], "raw": "an officer in a blue vest", "sent_id": 23759, "sent": "an officer in a blue vest"}], "file_name": "COCO_train2014_000000376817_447372.jpg", "ann_id": 447372, "sent_ids": [23758, 23759], "ref_id": 14180}, {"segmentation": [[359.8, 214.25, 354.16, 170.72, 347.71, 152.19, 326.75, 145.74, 339.65, 141.71, 352.55, 139.29, 360.61, 132.84, 378.34, 136.87, 383.98, 144.13, 385.59, 156.22, 392.85, 168.31, 422.67, 180.4, 445.24, 190.07, 450.88, 208.61, 467.81, 209.41, 481.51, 212.64, 491.18, 212.64, 483.93, 219.89, 515.36, 219.89, 458.94, 235.21, 462.97, 239.24, 453.3, 243.27, 443.63, 246.49, 422.67, 252.13, 421.86, 254.55, 410.58, 250.52, 393.65, 247.3, 394.46, 252.13, 391.23, 250.52, 391.23, 244.88, 364.64, 223.12]], "area": 8516.235449999996, "iscrowd": 0, "image_id": 418847, "bbox": [326.75, 132.84, 188.61, 121.71], "category_id": 16, "id": 42931, "split": "val", "sentences": [{"tokens": ["a", "white", "bird", "stands", "behind", "two", "brown", "birds"], "raw": "A white bird stands behind two brown birds", "sent_id": 23790, "sent": "a white bird stands behind two brown birds"}, {"tokens": ["white", "bird", "standing", "in", "water"], "raw": "white bird standing in water", "sent_id": 23791, "sent": "white bird standing in water"}], "file_name": "COCO_train2014_000000418847_42931.jpg", "ann_id": 42931, "sent_ids": [23790, 23791], "ref_id": 14192}, {"segmentation": [[323.14, 135.12, 350.06, 130.31, 369.3, 151.47, 367.37, 179.36, 365.45, 199.56, 395.26, 203.4, 411.61, 227.44, 420.02, 291.03, 400.79, 323.73, 406.56, 266.02, 374.82, 265.06, 377.7, 342.0, 366.16, 349.69, 333.47, 352.58, 275.76, 387.2, 274.8, 346.81, 278.65, 260.25, 282.5, 217.94, 304.61, 206.4, 307.5, 151.58, 325.77, 130.42]], "area": 22098.742650000004, "iscrowd": 0, "image_id": 533220, "bbox": [274.8, 130.31, 145.22, 256.89], "category_id": 1, "id": 470648, "split": "val", "sentences": [{"tokens": ["woman", "in", "the", "middle"], "raw": "Woman in the middle.", "sent_id": 23889, "sent": "woman in the middle"}, {"tokens": ["a", "woman", "with", "a", "black", "shirt", "and", "jeans", "drinking", "a", "beer"], "raw": "A woman with a black shirt and jeans drinking a beer.", "sent_id": 23890, "sent": "a woman with a black shirt and jeans drinking a beer"}], "file_name": "COCO_train2014_000000533220_470648.jpg", "ann_id": 470648, "sent_ids": [23889, 23890], "ref_id": 14224}, {"segmentation": [[335.55, 563.01, 254.4, 580.56, 175.43, 570.69, 158.98, 553.14, 161.17, 529.01, 164.46, 480.76, 188.59, 454.43, 219.3, 450.05, 254.4, 447.85, 341.04, 454.43, 372.84, 493.92, 376.13, 526.82, 348.72, 570.69, 334.46, 565.2]], "area": 24006.175999999996, "iscrowd": 0, "image_id": 230570, "bbox": [158.98, 447.85, 217.15, 132.71], "category_id": 54, "id": 2191807, "split": "val", "sentences": [{"tokens": ["a", "perfectly", "sliced", "piece", "of", "sandwich", "sits", "in", "a", "wrapper"], "raw": "A perfectly sliced piece of sandwich sits in a wrapper.", "sent_id": 23965, "sent": "a perfectly sliced piece of sandwich sits in a wrapper"}, {"tokens": ["a", "part", "of", "a", "sandwich", "that", "is", "next", "to", "the", "other", "half", "thats", "been", "eaten", "on"], "raw": "A part of a sandwich that is next to the other half thats been eaten on", "sent_id": 23966, "sent": "a part of a sandwich that is next to the other half thats been eaten on"}], "file_name": "COCO_train2014_000000230570_2191807.jpg", "ann_id": 2191807, "sent_ids": [23965, 23966], "ref_id": 14253}, {"segmentation": [[174.09, 243.31, 178.93, 232.43, 136.62, 250.56, 118.48, 274.74, 125.73, 291.67, 118.48, 317.06, 91.88, 317.06, 77.38, 335.19, 77.38, 336.4, 87.05, 370.25, 79.79, 417.4, 77.38, 419.82, 78.58, 479.06, 81.0, 506.87, 94.3, 520.17, 106.39, 533.47, 272.02, 531.05, 275.65, 514.12, 263.56, 486.32, 256.31, 463.34, 249.05, 463.34, 217.62, 392.01, 199.48, 392.01, 197.07, 392.01, 174.09, 371.46, 175.3, 350.91, 175.3, 335.19, 142.66, 320.68, 148.71, 315.85, 130.57, 302.55, 152.33, 273.53, 160.8, 259.03]], "area": 32175.476699999996, "iscrowd": 0, "image_id": 195861, "bbox": [77.38, 232.43, 198.27, 301.04], "category_id": 4, "id": 151964, "split": "val", "sentences": [{"tokens": ["motorcycle", "next", "to", "man", "standing", "in", "far", "left", "of", "picture"], "raw": "Motorcycle next to man standing in far left of picture.", "sent_id": 24064, "sent": "motorcycle next to man standing in far left of picture"}, {"tokens": ["the", "motorcycle", "that", "the", "women", "is", "approaching"], "raw": "the motorcycle that the women is approaching", "sent_id": 24065, "sent": "the motorcycle that the women is approaching"}], "file_name": "COCO_train2014_000000195861_151964.jpg", "ann_id": 151964, "sent_ids": [24064, 24065], "ref_id": 14283}, {"segmentation": [[261.34, 208.69, 279.53, 187.63, 282.4, 177.1, 297.72, 177.1, 314.95, 192.42, 327.4, 211.56, 347.5, 222.09, 359.95, 219.22, 393.45, 212.52, 417.38, 212.52, 442.27, 248.9, 434.62, 275.7, 425.04, 261.34, 425.04, 237.41, 416.43, 260.39, 428.87, 281.45, 407.81, 291.98, 397.28, 273.79, 391.54, 260.39, 367.6, 270.92, 336.97, 265.17, 338.89, 294.85, 312.08, 288.15, 313.04, 260.39, 300.59, 244.11, 290.06, 221.14, 266.13, 227.84, 256.56, 220.18]], "area": 9862.727850000005, "iscrowd": 0, "image_id": 467760, "bbox": [256.56, 177.1, 185.71, 117.75], "category_id": 24, "id": 589039, "split": "val", "sentences": [{"tokens": ["a", "full", "grown", "zebra", "facing", "the", "left"], "raw": "a full grown zebra facing the left", "sent_id": 24102, "sent": "a full grown zebra facing the left"}, {"tokens": ["zebra", "with", "the", "shorter", "of", "tails"], "raw": "Zebra with the shorter of tails.", "sent_id": 24103, "sent": "zebra with the shorter of tails"}], "file_name": "COCO_train2014_000000467760_589039.jpg", "ann_id": 589039, "sent_ids": [24102, 24103], "ref_id": 14299}, {"segmentation": [[436.25, 318.58, 439.01, 264.59, 435.21, 251.43, 457.7, 242.43, 482.63, 242.09, 522.43, 249.01, 532.47, 258.36, 526.58, 275.66, 549.08, 295.04, 555.66, 310.62, 551.16, 327.24, 539.39, 337.62, 520.7, 342.81, 516.55, 353.89, 498.55, 361.5, 463.59, 361.15, 463.59, 357.69, 435.9, 323.43]], "area": 10962.8146, "iscrowd": 0, "image_id": 357470, "bbox": [435.21, 242.09, 120.45, 119.41], "category_id": 47, "id": 671258, "split": "val", "sentences": [{"tokens": ["a", "cream", "color", "cup", "near", "a", "laptop"], "raw": "A cream color cup near a laptop", "sent_id": 24111, "sent": "a cream color cup near a laptop"}, {"tokens": ["the", "coffee", "mug", "next", "to", "the", "macbook"], "raw": "The coffee mug next to the macbook.", "sent_id": 24112, "sent": "the coffee mug next to the macbook"}], "file_name": "COCO_train2014_000000357470_671258.jpg", "ann_id": 671258, "sent_ids": [24111, 24112], "ref_id": 14304}, {"segmentation": [[223.49, 461.98, 272.83, 454.72, 290.25, 414.09, 319.27, 473.59, 332.34, 473.59, 336.69, 444.57, 362.81, 472.14, 407.8, 461.98, 367.17, 502.62, 371.52, 553.41, 343.95, 530.19, 362.81, 573.73, 342.49, 576.63, 293.15, 508.42, 210.43, 461.98]], "area": 10149.92825, "iscrowd": 0, "image_id": 116040, "bbox": [210.43, 414.09, 197.37, 162.54], "category_id": 5, "id": 159041, "split": "val", "sentences": [{"tokens": ["bottom", "airplane"], "raw": "bottom airplane", "sent_id": 24165, "sent": "bottom airplane"}, {"tokens": ["the", "lowest", "plane", "in", "the", "sky"], "raw": "The lowest plane in the sky.", "sent_id": 24166, "sent": "the lowest plane in the sky"}], "file_name": "COCO_train2014_000000116040_159041.jpg", "ann_id": 159041, "sent_ids": [24165, 24166], "ref_id": 14329}, {"segmentation": [[198.16, 140.43, 157.0, 146.17, 119.66, 150.96, 96.69, 169.15, 72.76, 179.68, 63.18, 184.47, 69.88, 199.78, 62.22, 230.42, 68.93, 242.86, 108.18, 212.23, 112.0, 203.61, 115.83, 201.7, 118.71, 215.1, 118.71, 234.25, 115.83, 250.52, 115.83, 259.14, 129.24, 257.22, 130.19, 235.2, 134.98, 208.4, 138.81, 214.14, 144.55, 235.2, 147.42, 254.35, 165.61, 259.14, 163.7, 243.82, 163.7, 224.67, 163.7, 218.93, 186.67, 212.23, 201.03, 217.02, 181.89, 261.05, 185.72, 259.14, 197.2, 246.69, 204.86, 236.16, 207.73, 230.42, 210.61, 228.5, 218.27, 263.92, 220.18, 266.8, 230.71, 254.35, 224.97, 240.95, 222.09, 224.67, 224.01, 206.49, 227.84, 194.04, 229.75, 189.25, 249.86, 206.49, 251.77, 213.19, 251.77, 201.7, 246.03, 187.34, 239.33, 176.81, 229.75, 151.92]], "area": 13321.573549999996, "iscrowd": 0, "image_id": 253942, "bbox": [62.22, 140.43, 189.55, 126.37], "category_id": 24, "id": 593885, "split": "val", "sentences": [{"tokens": ["zebra", "who", "is", "first", "in", "the", "group"], "raw": "Zebra who is first in the group.", "sent_id": 24236, "sent": "zebra who is first in the group"}, {"tokens": ["a", "zebra", "walking", "in", "leading", "pack", ",", "leaning", "down", "to", "graze"], "raw": "A zebra walking in leading pack, leaning down to graze", "sent_id": 24237, "sent": "a zebra walking in leading pack , leaning down to graze"}], "file_name": "COCO_train2014_000000253942_593885.jpg", "ann_id": 593885, "sent_ids": [24236, 24237], "ref_id": 14357}, {"segmentation": [[640.0, 47.35, 604.84, 74.26, 604.84, 159.28, 602.69, 294.89, 602.69, 377.76, 596.23, 473.54, 640.0, 473.54, 640.0, 48.43]], "area": 15351.010249999985, "iscrowd": 0, "image_id": 571658, "bbox": [596.23, 47.35, 43.77, 426.19], "category_id": 6, "id": 366021, "split": "val", "sentences": [{"tokens": ["the", "bus", "on", "the", "far", "right"], "raw": "The bus on the far right.", "sent_id": 24253, "sent": "the bus on the far right"}], "file_name": "COCO_train2014_000000571658_366021.jpg", "ann_id": 366021, "sent_ids": [24253], "ref_id": 14363}, {"segmentation": [[476.66, 138.33, 475.38, 103.18, 471.54, 74.41, 469.62, 60.99, 451.09, 55.88, 447.25, 43.73, 452.37, 29.67, 481.13, 39.9, 509.25, 36.06, 522.04, 37.34, 546.97, 27.75, 558.47, 39.26, 548.25, 55.24, 529.07, 65.47, 525.87, 109.57, 529.71, 115.32, 538.02, 128.74, 543.13, 138.33, 483.05, 140.25]], "area": 7028.161650000002, "iscrowd": 0, "image_id": 222199, "bbox": [447.25, 27.75, 111.22, 112.5], "category_id": 20, "id": 1817711, "split": "val", "sentences": [{"tokens": ["the", "head", "of", "the", "white", "animal", "looking", "at", "the", "dog"], "raw": "The head of the white animal looking at the dog.", "sent_id": 24261, "sent": "the head of the white animal looking at the dog"}, {"tokens": ["the", "head", "of", "an", "out", "of", "focus", "white", "lamb"], "raw": "the head of an out of focus white lamb", "sent_id": 24262, "sent": "the head of an out of focus white lamb"}], "file_name": "COCO_train2014_000000222199_1817711.jpg", "ann_id": 1817711, "sent_ids": [24261, 24262], "ref_id": 14366}, {"segmentation": [[390.52, 276.36, 363.32, 275.64, 344.71, 276.36, 341.13, 295.69, 348.28, 308.57, 364.03, 313.58, 409.14, 307.14, 434.19, 310.72, 437.06, 325.75, 443.5, 331.48, 453.52, 330.05, 454.24, 322.89, 444.93, 318.59, 442.78, 315.73, 444.93, 310.72, 484.31, 305.71, 489.32, 264.9, 486.45, 262.75, 436.34, 269.91, 404.84, 272.78], [610.19, 236.06, 547.31, 248.44, 543.01, 252.73, 546.59, 277.79, 558.04, 299.27, 558.76, 307.86, 570.93, 315.01, 577.37, 317.16, 584.53, 311.44, 581.67, 298.55, 590.98, 287.09, 610.31, 282.8, 621.04, 310.0, 640.0, 307.86, 640.0, 241.99, 640.0, 235.55, 640.0, 234.12]], "area": 11329.574450000002, "iscrowd": 0, "image_id": 132746, "bbox": [341.13, 234.12, 298.87, 97.36], "category_id": 5, "id": 2171388, "split": "val", "sentences": [{"tokens": ["an", "aeroplane", "is", "standing", "behind", "another", "one"], "raw": "an aeroplane is standing behind another one", "sent_id": 24282, "sent": "an aeroplane is standing behind another one"}], "file_name": "COCO_train2014_000000132746_2171388.jpg", "ann_id": 2171388, "sent_ids": [24282], "ref_id": 14374}, {"segmentation": [[366.74, 64.41, 411.76, 68.68, 438.78, 86.69, 453.0, 114.18, 450.63, 145.93, 443.04, 166.79, 428.83, 177.69, 407.5, 182.9, 380.48, 183.38, 351.57, 170.11, 333.09, 148.3, 328.82, 137.88, 347.3, 119.87, 371.95, 86.69, 374.32, 72.95]], "area": 10280.337650000001, "iscrowd": 0, "image_id": 263744, "bbox": [328.82, 64.41, 124.18, 118.97], "category_id": 55, "id": 1053502, "split": "val", "sentences": [{"tokens": ["an", "orange", "with", "a", "sticker", "in", "a", "black", "and", "white", "photo", ",", "under", "a", "banana"], "raw": "An orange with a sticker in a black and white photo, under a banana.", "sent_id": 24315, "sent": "an orange with a sticker in a black and white photo , under a banana"}, {"tokens": ["orange", "with", "a", "sticker", "on", "it"], "raw": "Orange with a sticker on it", "sent_id": 24316, "sent": "orange with a sticker on it"}], "file_name": "COCO_train2014_000000263744_1053502.jpg", "ann_id": 1053502, "sent_ids": [24315, 24316], "ref_id": 14386}, {"segmentation": [[159.75, 118.83, 159.75, 114.67, 167.37, 100.11, 168.76, 93.87, 170.15, 86.24, 160.44, 91.78, 158.36, 95.25, 149.34, 98.03, 147.96, 90.4, 138.94, 86.24, 132.7, 98.03, 128.54, 93.17, 114.67, 84.85, 113.98, 95.25, 120.91, 107.73, 123.69, 111.2, 123.69, 122.99, 123.69, 125.07, 100.81, 113.97, 75.84, 115.36, 68.91, 119.52, 59.89, 126.46, 52.27, 143.1, 44.64, 165.98, 48.8, 178.46, 55.73, 188.86, 61.97, 197.18, 66.13, 208.97, 71.68, 223.53, 73.76, 230.47, 72.38, 247.11, 70.3, 257.51, 70.3, 272.07, 68.91, 285.25, 71.68, 287.33, 84.16, 274.15, 80.7, 266.52, 80.7, 261.67, 82.78, 250.58, 87.63, 261.67, 91.1, 279.01, 93.18, 289.41, 98.03, 290.79, 102.89, 280.39, 91.1, 249.88, 90.4, 237.4, 92.48, 222.15, 98.03, 212.44, 104.97, 214.52, 111.9, 235.32, 115.37, 250.58, 113.98, 267.91, 113.98, 276.93, 121.61, 283.86, 124.38, 281.09, 124.38, 250.58, 123.69, 239.48, 122.3, 219.37, 118.14, 207.58, 113.29, 183.31, 107.74, 152.11, 114.67, 128.54, 151.42, 122.99]], "area": 9340.819099999999, "iscrowd": 0, "image_id": 459201, "bbox": [44.64, 84.85, 125.51, 205.94], "category_id": 24, "id": 593142, "split": "val", "sentences": [{"tokens": ["zebra", "behind", "other", "two", "zebras"], "raw": "zebra behind other two zebras", "sent_id": 24365, "sent": "zebra behind other two zebras"}, {"tokens": ["a", "zebra", "with", "its", "head", "obscured", "between", "two", "other", "zebras"], "raw": "A zebra with its head obscured between two other zebras.", "sent_id": 24366, "sent": "a zebra with its head obscured between two other zebras"}], "file_name": "COCO_train2014_000000459201_593142.jpg", "ann_id": 593142, "sent_ids": [24365, 24366], "ref_id": 14408}, {"segmentation": [[79.1, 398.48, 76.22, 428.68, 81.98, 454.57, 142.38, 480.46, 248.81, 280.55, 296.27, 235.96, 296.27, 215.83, 271.82, 204.32, 276.13, 181.31, 327.91, 107.96, 323.6, 50.43, 201.35, 27.42, 103.55, 86.39, 38.83, 148.23, 23.01, 237.4, 25.89, 287.74, 41.71, 335.2, 54.65, 363.96]], "area": 83748.57825, "iscrowd": 0, "image_id": 74549, "bbox": [23.01, 27.42, 304.9, 453.04], "category_id": 54, "id": 309805, "split": "val", "sentences": [{"tokens": ["the", "rye", "sandwich", "half", "that", "doesn", "'", "t", "have", "a", "bite", "taken", "out", "of", "it"], "raw": "The rye sandwich half that doesn't have a bite taken out of it.", "sent_id": 24410, "sent": "the rye sandwich half that doesn ' t have a bite taken out of it"}, {"tokens": ["left", "portion", "of", "sandwich", "closest", "to", "pickle"], "raw": "left portion of sandwich closest to pickle", "sent_id": 24411, "sent": "left portion of sandwich closest to pickle"}], "file_name": "COCO_train2014_000000074549_309805.jpg", "ann_id": 309805, "sent_ids": [24410, 24411], "ref_id": 14421}, {"segmentation": [[360.32, 478.98, 246.4, 456.69, 190.68, 433.16, 128.77, 373.73, 97.82, 334.11, 97.82, 301.91, 163.44, 292.01, 162.2, 279.63, 146.11, 279.63, 154.78, 252.39, 164.68, 247.43, 180.78, 244.96, 194.4, 253.63, 199.35, 269.72, 195.64, 274.67, 175.82, 287.06, 174.59, 290.77, 232.78, 284.58, 248.88, 283.34, 328.12, 314.3, 344.22, 318.01, 357.84, 313.06, 375.18, 315.54, 372.7, 331.63, 387.56, 342.78, 398.7, 350.2, 435.85, 366.3, 454.42, 396.02, 453.18, 434.4, 448.23, 452.98, 419.75, 483.93]], "area": 49264.832200000004, "iscrowd": 0, "image_id": 22926, "bbox": [97.82, 244.96, 356.6, 238.97], "category_id": 9, "id": 177412, "split": "val", "sentences": [{"tokens": ["a", "small", "boat", "with", "an", "umbrella"], "raw": "A small boat with an umbrella.", "sent_id": 24449, "sent": "a small boat with an umbrella"}, {"tokens": ["an", "outboard", "motor", "boat"], "raw": "an outboard motor boat", "sent_id": 24450, "sent": "an outboard motor boat"}], "file_name": "COCO_train2014_000000022926_177412.jpg", "ann_id": 177412, "sent_ids": [24449, 24450], "ref_id": 14435}, {"segmentation": [[161.44, 334.41, 167.21, 350.27, 170.09, 357.48, 191.71, 357.48, 201.8, 358.92, 211.89, 348.83, 224.86, 341.62, 236.4, 325.77, 249.37, 318.56, 260.9, 307.03, 276.76, 302.7, 291.17, 295.5, 309.91, 294.05, 285.41, 281.08, 266.67, 279.64, 263.78, 270.99, 256.58, 253.69, 262.34, 237.84, 203.24, 250.81, 180.18, 256.58, 181.62, 266.67, 183.06, 270.99, 177.3, 282.52, 177.3, 286.85, 177.3, 302.7, 177.3, 308.47, 171.53, 320.0, 160.0, 327.21], [165.77, 422.34, 203.24, 415.14, 237.84, 405.05, 256.58, 387.75, 260.9, 373.33, 276.76, 351.71, 291.17, 343.06, 304.14, 330.09, 321.44, 325.77, 324.32, 327.21, 325.77, 338.74, 335.86, 350.27, 337.3, 367.57, 347.39, 418.02, 344.5, 435.32, 332.97, 452.61, 330.09, 458.38, 332.97, 488.65, 343.06, 516.04, 351.71, 543.42, 351.71, 576.58, 360.36, 622.7, 322.88, 624.14, 298.38, 624.14, 289.73, 612.61, 285.41, 603.96, 281.08, 618.38, 283.96, 622.7, 224.86, 625.59, 211.89, 618.38, 204.68, 593.87, 200.36, 573.69, 198.92, 547.75, 197.48, 526.13, 193.15, 517.48, 178.74, 507.39, 184.5, 490.09, 187.39, 474.23, 184.5, 480.0, 168.65, 475.68, 162.88, 461.26, 160.0, 429.55, 160.0, 416.58]], "area": 48087.28539999999, "iscrowd": 0, "image_id": 505885, "bbox": [160.0, 237.84, 200.36, 387.75], "category_id": 1, "id": 466908, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "girl"], "raw": "the back of a girl", "sent_id": 24463, "sent": "the back of a girl"}, {"tokens": ["the", "back", "of", "a", "woman", "with", "dark", "hair", "wearing", "a", "jacket", "and", "standing", "under", "and", "umbrella", "with", "a", "hand", "around", "her", "shoulder"], "raw": "The back of a woman with dark hair wearing a jacket and standing under and umbrella with a hand around her shoulder", "sent_id": 24464, "sent": "the back of a woman with dark hair wearing a jacket and standing under and umbrella with a hand around her shoulder"}], "file_name": "COCO_train2014_000000505885_466908.jpg", "ann_id": 466908, "sent_ids": [24463, 24464], "ref_id": 14442}, {"segmentation": [[45.47, 254.55, 58.21, 252.96, 60.99, 248.98, 47.06, 236.24, 48.65, 234.25, 78.51, 231.86, 84.08, 235.44, 84.48, 240.22, 70.94, 245.79, 66.96, 261.72, 120.31, 260.52, 127.48, 261.32, 123.49, 269.68, 125.09, 274.86, 144.2, 291.58, 150.57, 309.09, 152.56, 317.45, 149.37, 344.52, 134.24, 362.84, 126.28, 367.22, 100.4, 367.61, 83.29, 360.85, 70.94, 350.5, 60.99, 325.42, 59.4, 311.88, 60.2, 302.72, 47.06, 292.37, 47.85, 290.38, 59.0, 259.33, 44.27, 258.53, 44.27, 256.54], [12.02, 293.17, 0.0, 281.62, 1.28, 241.81, 1.28, 224.7, 2.07, 217.13, 17.2, 220.71, 17.6, 223.5, 5.66, 222.7, 5.66, 224.7, 18.79, 235.44, 12.82, 233.45, 2.47, 228.68, 2.07, 248.18, 12.42, 251.37, 18.39, 254.55, 7.25, 255.35, 6.05, 268.49, 3.27, 277.24, 16.8, 292.37]], "area": 9521.755450000004, "iscrowd": 0, "image_id": 216150, "bbox": [0.0, 217.13, 152.56, 150.48], "category_id": 2, "id": 240879, "split": "val", "sentences": [{"tokens": ["a", "bike", "with", "a", "laid", "shirt", "on", "its", "seat", "resting", "on", "a", "pole"], "raw": "A bike with a laid shirt on its seat resting on a pole.", "sent_id": 24598, "sent": "a bike with a laid shirt on its seat resting on a pole"}], "file_name": "COCO_train2014_000000216150_240879.jpg", "ann_id": 240879, "sent_ids": [24598], "ref_id": 14497}, {"segmentation": [[322.31, 340.46, 322.65, 325.84, 318.91, 319.71, 317.89, 315.97, 316.19, 313.59, 304.62, 311.55, 321.97, 305.09, 327.07, 300.66, 334.22, 294.2, 344.08, 262.91, 349.18, 251.68, 352.93, 247.26, 362.11, 246.58, 370.61, 243.18, 392.72, 242.16, 401.91, 243.52, 413.13, 248.28, 423.34, 258.49, 431.16, 263.93, 447.49, 293.18, 446.81, 311.89, 437.28, 319.71, 419.94, 320.73, 413.13, 317.33, 416.19, 311.89, 434.56, 311.21, 442.39, 304.75, 442.05, 292.84, 436.26, 281.28, 430.14, 271.75, 426.06, 266.31, 421.64, 263.59, 423.0, 271.75, 412.11, 292.84, 410.41, 302.71, 405.31, 313.25, 400.21, 325.5, 400.55, 334.0, 397.83, 344.2, 399.19, 357.47, 400.89, 366.31, 395.1, 379.24, 383.2, 381.28, 384.22, 373.46, 387.96, 362.23, 389.32, 348.97, 386.94, 334.68, 385.92, 324.82, 382.86, 317.67, 379.46, 315.63, 375.72, 315.29, 374.7, 316.65, 374.02, 334.34, 377.08, 343.52, 378.78, 354.41, 369.25, 351.69, 369.25, 338.08, 366.87, 331.96, 365.51, 323.11, 366.53, 315.29, 357.69, 312.91, 355.99, 315.63, 355.65, 334.34, 354.29, 343.86, 354.29, 352.37, 349.18, 357.13, 344.76, 354.75, 348.5, 341.82, 347.82, 333.32, 347.82, 324.82, 347.82, 316.31, 343.74, 314.27, 344.08, 321.07, 341.36, 329.24, 334.9, 337.4, 332.18, 342.5, 331.16, 344.88, 322.99, 345.22, 320.95, 343.18, 322.31, 338.08]], "area": 8141.8339999999935, "iscrowd": 0, "image_id": 413556, "bbox": [304.62, 242.16, 142.87, 139.12], "category_id": 21, "id": 73878, "split": "val", "sentences": [{"tokens": ["black", "and", "white", "cow", "on", "the", "right", "from", "the", "man"], "raw": "Black and white cow on the right from the man.", "sent_id": 24611, "sent": "black and white cow on the right from the man"}, {"tokens": ["a", "black", "and", "white", "cow"], "raw": "A black and white cow.", "sent_id": 24612, "sent": "a black and white cow"}], "file_name": "COCO_train2014_000000413556_73878.jpg", "ann_id": 73878, "sent_ids": [24611, 24612], "ref_id": 14500}, {"segmentation": [[328.22, 248.0, 329.97, 258.49, 321.81, 270.14, 317.15, 295.2, 317.15, 313.26, 315.99, 337.15, 308.41, 359.88, 285.69, 361.04, 284.52, 359.29, 286.27, 352.88, 282.19, 308.02, 275.2, 301.03, 266.46, 275.97, 261.8, 268.98, 259.47, 231.69, 267.04, 176.87, 283.36, 161.14, 286.27, 158.22, 281.61, 154.15, 281.61, 145.99, 282.19, 135.5, 284.52, 130.26, 287.44, 129.09, 296.18, 128.51, 303.17, 129.09, 307.25, 133.17, 309.58, 141.91, 307.25, 150.07, 306.08, 151.82, 311.32, 159.97, 322.98, 164.63, 332.3, 177.45, 338.71, 207.17, 337.55, 230.48]], "area": 11662.9175, "iscrowd": 0, "image_id": 376838, "bbox": [259.47, 128.51, 79.24, 232.53], "category_id": 1, "id": 225828, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "no", "hat", ",", "with", "his", "back", "toward", "the", "camera"], "raw": "A man with no hat, with his back toward the camera.", "sent_id": 24660, "sent": "a man with no hat , with his back toward the camera"}, {"tokens": ["a", "short", "person", "with", "a", "jacket", "on"], "raw": "A short person with a jacket on.", "sent_id": 24661, "sent": "a short person with a jacket on"}], "file_name": "COCO_train2014_000000376838_225828.jpg", "ann_id": 225828, "sent_ids": [24660, 24661], "ref_id": 14520}, {"segmentation": [[291.62, 293.19, 243.7, 293.19, 213.58, 291.82, 182.09, 295.93, 167.03, 308.25, 161.56, 328.79, 151.97, 363.01, 149.23, 382.18, 164.3, 410.93, 180.72, 427.36, 183.46, 431.47, 208.11, 417.78, 236.86, 410.93, 249.18, 413.67, 264.24, 419.15, 282.04, 427.36, 310.79, 425.99, 320.38, 416.41, 324.48, 382.18, 324.48, 367.12, 314.9, 332.89, 309.42, 327.42]], "area": 19813.051149999996, "iscrowd": 0, "image_id": 198277, "bbox": [149.23, 291.82, 175.25, 139.65], "category_id": 3, "id": 140720, "split": "val", "sentences": [{"tokens": ["a", "yellow", "taxi", "cab", "follows", "behind", "a", "bus"], "raw": "A yellow taxi cab follows behind a bus.", "sent_id": 24717, "sent": "a yellow taxi cab follows behind a bus"}, {"tokens": ["a", "yellow", "taxi", "with", "a", "bike", "rack", "attached", "to", "the", "bumper"], "raw": "A yellow taxi with a bike rack attached to the bumper.", "sent_id": 24718, "sent": "a yellow taxi with a bike rack attached to the bumper"}], "file_name": "COCO_train2014_000000198277_140720.jpg", "ann_id": 140720, "sent_ids": [24717, 24718], "ref_id": 14544}, {"segmentation": [[363.67, 326.7, 313.81, 263.94, 303.49, 229.55, 285.43, 202.9, 294.89, 177.97, 282.85, 171.95, 304.35, 161.63, 304.35, 142.72, 320.68, 143.58, 323.26, 124.66, 334.44, 130.68, 339.6, 114.35, 348.19, 119.5, 353.35, 106.61, 362.81, 110.91, 364.53, 93.71, 381.72, 105.75, 386.88, 91.13, 404.94, 104.03, 415.25, 91.99, 432.45, 107.47, 446.21, 92.85, 472.0, 93.71, 484.03, 104.03, 489.19, 116.06, 484.89, 134.98, 484.89, 137.56, 500.0, 156.47, 499.51, 323.26, 367.97, 326.7]], "area": 40696.29425, "iscrowd": 0, "image_id": 292751, "bbox": [282.85, 91.13, 217.15, 235.57], "category_id": 88, "id": 1995927, "split": "val", "sentences": [{"tokens": ["a", "green", "stuffed", "animal", "on", "top", "of", "a", "baby"], "raw": "A green stuffed animal on top of a baby.", "sent_id": 24803, "sent": "a green stuffed animal on top of a baby"}, {"tokens": ["green", "stuffed", "animal"], "raw": "green stuffed animal", "sent_id": 24804, "sent": "green stuffed animal"}], "file_name": "COCO_train2014_000000292751_1995927.jpg", "ann_id": 1995927, "sent_ids": [24803, 24804], "ref_id": 14579}, {"segmentation": [[190.5, 218.53, 206.26, 221.05, 222.01, 222.31, 240.92, 222.31, 247.22, 216.01, 254.78, 241.85, 258.56, 255.72, 251.0, 270.84, 247.85, 281.56, 240.92, 287.23, 250.37, 288.49, 254.78, 284.71, 261.09, 285.34, 263.61, 267.69, 274.95, 246.89, 273.69, 239.33, 271.8, 222.31, 272.43, 216.01, 283.14, 245.63, 284.4, 270.84, 282.51, 290.38, 282.51, 291.64, 293.86, 291.64, 292.6, 290.38, 299.53, 285.97, 295.12, 262.02, 297.64, 241.85, 292.6, 229.25, 305.2, 186.39, 304.57, 169.38, 293.23, 149.84, 267.39, 141.01, 228.94, 148.58, 202.47, 149.21, 182.94, 146.06, 159.62, 157.4, 156.47, 155.51, 135.04, 166.85, 118.65, 184.5, 107.94, 204.67, 101.01, 210.97, 95.96, 216.64, 99.75, 231.14, 96.59, 253.83, 92.81, 277.15, 96.59, 281.56, 99.12, 284.08, 117.39, 285.34, 118.02, 279.67, 130.0, 261.39, 135.67, 251.94, 133.78, 241.22, 140.71, 224.84, 155.21, 216.01, 164.03, 219.79, 165.92, 230.51, 158.99, 250.68, 160.25, 256.98, 152.69, 276.52, 148.9, 280.3, 146.38, 282.82, 144.49, 288.49, 155.84, 287.86, 159.62, 282.19, 166.55, 278.41, 167.18, 258.87, 177.89, 242.48, 179.16, 258.24, 181.05, 272.1, 176.63, 285.34, 179.79, 288.49, 185.46, 281.56, 192.39, 282.19, 192.39, 272.73, 189.87, 239.96]], "area": 18853.93404999999, "iscrowd": 0, "image_id": 250387, "bbox": [92.81, 141.01, 212.39, 150.63], "category_id": 24, "id": 588941, "split": "val", "sentences": [{"tokens": ["zebra", "eating", "some", "grass", "next", "to", "an", "antelope"], "raw": "zebra eating some grass next to an antelope", "sent_id": 24899, "sent": "zebra eating some grass next to an antelope"}, {"tokens": ["a", "zebra", "grazing", "in", "a", "field"], "raw": "A zebra grazing in a field.", "sent_id": 24900, "sent": "a zebra grazing in a field"}], "file_name": "COCO_train2014_000000250387_588941.jpg", "ann_id": 588941, "sent_ids": [24899, 24900], "ref_id": 14617}, {"segmentation": [[90.4, 149.55, 102.9, 169.74, 122.14, 160.13, 123.1, 138.97, 135.6, 124.54, 146.18, 109.15, 179.84, 109.15, 202.92, 82.23, 211.58, 77.42, 245.24, 98.58, 254.85, 97.61, 251.97, 86.07, 239.47, 84.15, 223.12, 63.95, 219.27, 43.76, 195.23, 29.33, 176.95, 20.68, 164.45, 38.95, 170.22, 45.68, 183.69, 38.95, 187.53, 46.64, 172.15, 61.07, 154.84, 71.65, 113.48, 95.69, 108.67, 129.35, 89.44, 133.2, 88.48, 150.51]], "area": 6846.593049999999, "iscrowd": 0, "image_id": 125193, "bbox": [88.48, 20.68, 166.37, 149.06], "category_id": 1, "id": 426040, "split": "val", "sentences": [{"tokens": ["a", "person", "skateboarding", "on", "a", "half", "-", "pipe"], "raw": "A person skateboarding on a half-pipe.", "sent_id": 24995, "sent": "a person skateboarding on a half - pipe"}, {"tokens": ["a", "skateboarder", "riding", "a", "pipe"], "raw": "A skateboarder riding a pipe", "sent_id": 24996, "sent": "a skateboarder riding a pipe"}], "file_name": "COCO_train2014_000000125193_426040.jpg", "ann_id": 426040, "sent_ids": [24995, 24996], "ref_id": 14649}, {"segmentation": [[28.35, 326.25, 48.3, 305.27, 91.79, 280.2, 123.0, 266.9, 171.6, 240.3, 209.97, 221.88, 213.04, 219.32, 180.3, 257.18, 128.62, 297.6, 119.42, 297.08, 107.14, 293.5, 97.42, 296.06, 61.09, 326.76, 32.96, 340.06, 27.84, 336.99]], "area": 4182.163450000002, "iscrowd": 0, "image_id": 7746, "bbox": [27.84, 219.32, 185.2, 120.74], "category_id": 49, "id": 693894, "split": "val", "sentences": [{"tokens": ["knife", "on", "a", "white", "plate"], "raw": "Knife on a white plate.", "sent_id": 25032, "sent": "knife on a white plate"}, {"tokens": ["a", "knife", "in", "the", "plate"], "raw": "A knife in the plate", "sent_id": 25033, "sent": "a knife in the plate"}], "file_name": "COCO_train2014_000000007746_693894.jpg", "ann_id": 693894, "sent_ids": [25032, 25033], "ref_id": 14662}, {"segmentation": [[211.12, 310.03, 206.96, 265.14, 209.45, 216.94, 212.78, 22.44, 212.78, 11.64, 226.91, 8.31, 256.83, 12.47, 305.04, 11.64, 366.55, 4.16, 421.4, 13.3, 428.88, 314.18, 426.39, 311.69]], "area": 64673.104849999996, "iscrowd": 0, "image_id": 419396, "bbox": [206.96, 4.16, 221.92, 310.02], "category_id": 86, "id": 1992346, "split": "val", "sentences": [{"tokens": ["the", "floral", "pattern", "detail", "close", "-", "up"], "raw": "the floral pattern detail close-up", "sent_id": 25072, "sent": "the floral pattern detail close - up"}, {"tokens": ["zoomed", "in", "section", "of", "vase"], "raw": "Zoomed in section of vase.", "sent_id": 25073, "sent": "zoomed in section of vase"}], "file_name": "COCO_train2014_000000419396_1992346.jpg", "ann_id": 1992346, "sent_ids": [25072, 25073], "ref_id": 14674}, {"segmentation": [[139.33, 438.86, 155.2, 434.68, 164.4, 434.68, 177.77, 440.53, 193.64, 451.39, 194.48, 459.75, 194.48, 480.64, 194.48, 500.69, 191.97, 508.21, 191.13, 555.84, 179.44, 555.84, 165.23, 561.69, 163.56, 534.95, 156.88, 524.09, 141.0, 524.09, 137.66, 539.97, 136.82, 544.98, 135.99, 560.85, 130.14, 563.36, 125.12, 563.36, 124.29, 549.16, 121.78, 539.13, 125.96, 524.93, 122.62, 517.41, 111.75, 517.41, 112.59, 557.51, 101.73, 561.69, 100.06, 555.84, 99.22, 534.95, 95.04, 518.24, 90.87, 505.71, 86.69, 487.32, 100.89, 440.53, 99.22, 432.18, 91.7, 423.82, 84.18, 416.3, 81.67, 413.79, 86.69, 407.11, 98.39, 417.14, 110.08, 411.29, 119.27, 411.29, 132.64, 413.79, 142.67, 406.27, 143.51, 413.79, 141.0, 422.99, 137.66, 428.83, 135.99, 433.01, 137.66, 438.86]], "area": 11704.655850000001, "iscrowd": 0, "image_id": 156823, "bbox": [81.67, 406.27, 112.81, 157.09], "category_id": 20, "id": 64405, "split": "val", "sentences": [{"tokens": ["baby", "sheep", "with", "other", "sheep"], "raw": "Baby sheep with other sheep", "sent_id": 25130, "sent": "baby sheep with other sheep"}, {"tokens": ["the", "goat", "on", "the", "left"], "raw": "The goat on the left.", "sent_id": 25131, "sent": "the goat on the left"}], "file_name": "COCO_train2014_000000156823_64405.jpg", "ann_id": 64405, "sent_ids": [25130, 25131], "ref_id": 14698}, {"segmentation": [[180.15, 391.24, 178.97, 378.3, 140.15, 365.95, 139.56, 367.71, 131.33, 362.42, 125.45, 354.19, 120.74, 311.24, 123.68, 284.87, 110.15, 274.28, 108.39, 262.52, 133.09, 255.46, 133.09, 243.69, 203.09, 221.93, 208.97, 233.69, 221.33, 273.69, 274.27, 290.75, 283.68, 295.46, 286.03, 309.57, 286.03, 346.87, 281.91, 350.99, 281.91, 356.28, 269.56, 359.81, 262.5, 355.69, 260.74, 350.99, 206.62, 373.93, 206.62, 380.4, 201.33, 384.51, 202.5, 391.57, 190.74, 396.28]], "area": 18589.90205, "iscrowd": 0, "image_id": 535874, "bbox": [108.39, 221.93, 177.64, 174.35], "category_id": 63, "id": 1949415, "split": "val", "sentences": [{"tokens": ["an", "arm", "chair", "with", "spotted", "cushions"], "raw": "An arm chair with spotted cushions.", "sent_id": 25331, "sent": "an arm chair with spotted cushions"}, {"tokens": ["a", "tacky", "animal", "print", "arm", "chair", "in", "a", "room", "with", "other", "tacky", "animal", "print", "items"], "raw": "A tacky animal print arm chair in a room with other tacky animal print items", "sent_id": 25332, "sent": "a tacky animal print arm chair in a room with other tacky animal print items"}], "file_name": "COCO_train2014_000000535874_1949415.jpg", "ann_id": 1949415, "sent_ids": [25331, 25332], "ref_id": 14766}, {"segmentation": [[562.46, 135.08, 584.36, 127.12, 592.33, 110.2, 617.21, 105.22, 633.14, 105.22, 640.0, 112.19, 640.0, 164.95, 627.17, 183.86, 629.16, 191.83, 639.11, 207.76, 640.0, 251.56, 628.16, 274.46, 632.15, 292.37, 640.0, 299.34, 640.0, 323.24, 638.12, 331.2, 637.12, 340.16, 639.11, 344.14, 640.0, 346.13, 640.0, 351.11, 640.0, 422.79, 621.2, 406.86, 614.23, 398.89, 609.25, 378.98, 604.27, 365.05, 572.42, 389.93, 565.45, 399.89, 558.48, 406.86, 558.48, 412.83, 554.5, 421.79, 543.55, 433.74, 542.55, 434.73, 508.7, 436.72, 501.73, 435.73, 523.64, 402.88, 523.64, 391.93, 528.61, 380.97, 532.6, 376.0, 533.59, 366.04, 539.56, 360.07, 545.54, 355.09, 570.42, 320.25, 570.42, 311.29, 574.41, 303.33, 575.4, 301.33, 564.45, 267.49, 563.46, 251.56, 569.43, 236.63, 560.47, 225.68, 560.47, 203.77, 572.42, 184.86, 574.41, 172.91, 573.41, 163.95, 575.4, 160.97, 558.48, 152.01, 553.5, 142.05, 559.47, 134.09]], "area": 23016.793850000005, "iscrowd": 0, "image_id": 305219, "bbox": [501.73, 105.22, 138.27, 331.5], "category_id": 1, "id": 524511, "split": "val", "sentences": [{"tokens": ["the", "little", "boy", "wearing", "red", "and", "white", "swinging", "a", "bat"], "raw": "The little boy wearing red and white swinging a bat.", "sent_id": 25362, "sent": "the little boy wearing red and white swinging a bat"}, {"tokens": ["a", "little", "leaguer", "wearing", "his", "uniform", ",", "swinging", "a", "baseball", "bat"], "raw": "A little leaguer wearing his uniform, swinging a baseball bat.", "sent_id": 25363, "sent": "a little leaguer wearing his uniform , swinging a baseball bat"}], "file_name": "COCO_train2014_000000305219_524511.jpg", "ann_id": 524511, "sent_ids": [25362, 25363], "ref_id": 14774}, {"segmentation": [[84.96, 3.31, 82.75, 222.88, 82.75, 258.19, 2.21, 303.43, 3.31, 1.1]], "area": 22518.8476, "iscrowd": 0, "image_id": 56699, "bbox": [2.21, 1.1, 82.75, 302.33], "category_id": 6, "id": 1366030, "split": "val", "sentences": [{"tokens": ["the", "red", "bus", "with", "only", "the", "back", "end", "visible", ",", "in", "front", "of", "the", "bus", "labeled", "j322bsh"], "raw": "The red bus with only the back end visible, in front of the bus labeled J322BSH", "sent_id": 25391, "sent": "the red bus with only the back end visible , in front of the bus labeled j322bsh"}], "file_name": "COCO_train2014_000000056699_1366030.jpg", "ann_id": 1366030, "sent_ids": [25391], "ref_id": 14783}, {"segmentation": [[2.2, 158.43, 0.43, 147.09, 2.55, 138.23, 1.49, 119.09, 17.44, 113.06, 33.74, 119.44, 38.71, 136.45, 39.06, 143.19, 38.0, 150.98, 58.91, 161.62, 73.44, 177.92, 78.75, 204.15, 75.21, 219.74, 62.81, 237.11, 58.91, 241.36, 58.91, 248.1, 69.19, 292.05, 68.12, 299.13, 39.77, 301.61, 32.68, 303.03, 26.3, 297.72, 25.24, 280.0, 28.07, 274.32, 57.49, 264.4, 58.91, 257.67, 45.08, 254.12, 22.76, 253.06, 2.55, 257.31, 1.49, 241.72, 5.03, 241.36, 27.36, 240.65, 26.3, 234.63, 18.5, 235.34, 14.6, 231.79, 1.49, 234.63, 0.07, 174.02, 3.62, 152.4]], "area": 9306.096099999995, "iscrowd": 0, "image_id": 444033, "bbox": [0.07, 113.06, 78.68, 189.97], "category_id": 1, "id": 518084, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "shirt", "holding", "a", "plate", "in", "a", "food", "line", "at", "a", "potluck"], "raw": "A man in a blue shirt holding a plate in a food line at a potluck", "sent_id": 25458, "sent": "a man in a blue shirt holding a plate in a food line at a potluck"}, {"tokens": ["man", "in", "blue", "shirt"], "raw": "MAN IN BLUE SHIRT", "sent_id": 25459, "sent": "man in blue shirt"}], "file_name": "COCO_train2014_000000444033_518084.jpg", "ann_id": 518084, "sent_ids": [25458, 25459], "ref_id": 14804}, {"segmentation": [[465.5, 106.5, 500.0, 91.0, 500.0, 327.5, 499.5, 332.0, 426.5, 328.5, 436.0, 294.0, 448.5, 286.0, 453.0, 231.5, 437.5, 229.5, 444.0, 195.0, 460.5, 187.5, 466.0, 141.0, 458.0, 135.0, 464.5, 105.5]], "area": 11470.5, "iscrowd": 0, "image_id": 473373, "bbox": [426.5, 91.0, 73.5, 241.0], "category_id": 62, "id": 1582431, "split": "val", "sentences": [{"tokens": ["the", "wooden", "back", "to", "a", "chair"], "raw": "The wooden back to a chair.", "sent_id": 25568, "sent": "the wooden back to a chair"}, {"tokens": ["a", "wooden", "back", "of", "a", "chair"], "raw": "A wooden back of a chair.", "sent_id": 25569, "sent": "a wooden back of a chair"}], "file_name": "COCO_train2014_000000473373_1582431.jpg", "ann_id": 1582431, "sent_ids": [25568, 25569], "ref_id": 14839}, {"segmentation": [[281.89, 261.75, 256.0, 289.08, 241.62, 313.53, 217.17, 358.11, 195.6, 418.52, 195.6, 432.9, 211.42, 444.4, 592.54, 566.65, 606.92, 556.58, 609.8, 543.64, 629.93, 488.99, 627.06, 339.42, 283.33, 261.75]], "area": 86723.10824999998, "iscrowd": 0, "image_id": 445540, "bbox": [195.6, 261.75, 434.33, 304.9], "category_id": 77, "id": 328411, "split": "val", "sentences": [{"tokens": ["a", "blackberry", "cellphone", "sitting", "on", "a", "table", "alongside", "another", "brand", "of", "cellphone"], "raw": "A blackberry cellphone sitting on a table alongside another brand of cellphone.", "sent_id": 25620, "sent": "a blackberry cellphone sitting on a table alongside another brand of cellphone"}, {"tokens": ["a", "grey", "blackberry", "phone", "sitting", "on", "a", "talble"], "raw": "A grey blackberry phone sitting on a talble.", "sent_id": 25621, "sent": "a grey blackberry phone sitting on a talble"}], "file_name": "COCO_train2014_000000445540_328411.jpg", "ann_id": 328411, "sent_ids": [25620, 25621], "ref_id": 14856}, {"segmentation": [[561.35, 300.79, 557.16, 293.44, 576.04, 275.61, 598.08, 243.08, 605.42, 180.12, 635.85, 197.96, 640.0, 71.0, 622.21, 66.8, 620.11, 50.01, 606.47, 33.23, 585.49, 26.93, 564.5, 27.98, 551.91, 54.21, 554.01, 69.95, 550.86, 78.34, 559.26, 87.79, 561.35, 99.33, 561.35, 101.43, 567.65, 108.77, 569.75, 108.77, 588.64, 101.43, 569.75, 124.51, 562.4, 144.45, 567.65, 167.53, 569.75, 189.57, 576.04, 218.95, 562.4, 245.18, 549.81, 278.75, 545.62, 295.54, 554.01, 308.13, 561.35, 307.08], [639.0, 244.13, 611.72, 316.53, 616.97, 330.17, 622.21, 342.76, 629.56, 389.98, 639.0, 418.31, 640.0, 251.47]], "area": 16619.907050000005, "iscrowd": 0, "image_id": 277284, "bbox": [545.62, 26.93, 94.38, 391.38], "category_id": 1, "id": 1742952, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "white", "holding", "a", "red", "frisbee"], "raw": "The man in white holding a red frisbee.", "sent_id": 25709, "sent": "the man in white holding a red frisbee"}, {"tokens": ["a", "man", "in", "a", "white", "tee", "shirt", "holding", "a", "red", "frisbee"], "raw": "A man in a white tee shirt holding a red frisbee.", "sent_id": 25710, "sent": "a man in a white tee shirt holding a red frisbee"}], "file_name": "COCO_train2014_000000277284_1742952.jpg", "ann_id": 1742952, "sent_ids": [25709, 25710], "ref_id": 14892}, {"segmentation": [[189.84, 159.64, 173.66, 389.39, 381.84, 448.72, 473.53, 423.91, 475.69, 445.48, 510.2, 432.54, 528.54, 401.26, 547.96, 391.55, 586.79, 374.29, 585.71, 348.4, 597.57, 341.93, 593.26, 294.47, 585.71, 288.0, 592.18, 208.18, 403.42, 116.49, 353.8, 110.02, 256.72, 126.2, 210.34, 136.99]], "area": 113971.29079999999, "iscrowd": 0, "image_id": 571658, "bbox": [173.66, 110.02, 423.91, 338.7], "category_id": 6, "id": 365725, "split": "val", "sentences": [{"tokens": ["the", "chool", "bus", "next", "to", "the", "van"], "raw": "The chool bus next to the van", "sent_id": 25798, "sent": "the chool bus next to the van"}, {"tokens": ["a", "school", "bus", "that", "is", "travelling", "in", "the", "middle", "of", "a", "grey", "car", "and", "another", "bus"], "raw": "A school bus that is travelling in the middle of a grey car and another bus", "sent_id": 25799, "sent": "a school bus that is travelling in the middle of a grey car and another bus"}], "file_name": "COCO_train2014_000000571658_365725.jpg", "ann_id": 365725, "sent_ids": [25798, 25799], "ref_id": 14924}, {"segmentation": [[640.0, 142.16, 600.32, 146.16, 585.91, 138.95, 472.25, 141.36, 397.01, 183.78, 395.41, 215.0, 403.42, 217.4, 413.82, 254.22, 370.6, 295.84, 370.6, 337.46, 392.21, 337.46, 393.01, 318.25, 475.45, 268.62, 474.65, 334.26, 487.46, 334.26, 489.86, 279.03, 552.3, 288.63, 569.11, 329.46, 567.5, 338.26, 586.71, 334.26, 583.51, 311.85, 573.11, 291.04, 629.14, 279.83, 640.0, 318.25, 637.94, 255.02]], "area": 36294.089949999994, "iscrowd": 0, "image_id": 222199, "bbox": [370.6, 138.95, 269.4, 199.31], "category_id": 20, "id": 62028, "split": "val", "sentences": [{"tokens": ["the", "back", "end", "of", "a", "sheep"], "raw": "The back end of a sheep.", "sent_id": 25826, "sent": "the back end of a sheep"}, {"tokens": ["the", "rear", "end", "of", "an", "out", "of", "focus", "white", "lamb"], "raw": "the rear end of an out of focus white lamb", "sent_id": 25827, "sent": "the rear end of an out of focus white lamb"}], "file_name": "COCO_train2014_000000222199_62028.jpg", "ann_id": 62028, "sent_ids": [25826, 25827], "ref_id": 14935}, {"segmentation": [[191.7, 230.19, 140.38, 209.06, 116.23, 172.83, 95.09, 127.55, 90.57, 89.81, 105.66, 59.62, 125.28, 36.98, 175.09, 26.42, 214.34, 35.47, 255.09, 64.15, 271.7, 104.91, 268.68, 136.6, 267.17, 156.23, 244.53, 195.47, 235.47, 216.6, 200.75, 230.19, 190.19, 228.68]], "area": 27512.61155, "iscrowd": 0, "image_id": 427654, "bbox": [90.57, 26.42, 181.13, 203.77], "category_id": 55, "id": 1052755, "split": "val", "sentences": [{"tokens": ["a", "lemon", "placed", "behind", "a", "spoon"], "raw": "A lemon placed behind a spoon.", "sent_id": 25874, "sent": "a lemon placed behind a spoon"}, {"tokens": ["a", "lemon", "to", "the", "left", "of", "another", "one"], "raw": "A lemon to the left of another one.", "sent_id": 25875, "sent": "a lemon to the left of another one"}], "file_name": "COCO_train2014_000000427654_1052755.jpg", "ann_id": 1052755, "sent_ids": [25874, 25875], "ref_id": 14951}, {"segmentation": [[376.98, 453.99, 352.21, 453.99, 342.08, 430.35, 357.84, 390.95, 365.72, 367.31, 370.22, 352.68, 371.35, 313.28, 382.6, 309.91, 391.61, 307.65, 409.62, 321.16, 416.37, 332.42, 427.63, 356.06, 449.02, 379.7, 465.9, 395.46, 495.17, 416.84, 491.79, 433.73, 455.77, 484.38, 442.26, 495.64, 444.51, 521.53, 441.14, 566.56, 438.89, 600.32, 407.37, 638.6, 396.11, 548.54, 369.1, 602.58, 382.6, 640.0, 340.95, 630.72, 330.82, 577.81, 337.58, 546.29, 362.34, 521.53, 370.22, 508.02, 379.23, 487.76]], "area": 27981.491100000007, "iscrowd": 0, "image_id": 452565, "bbox": [330.82, 307.65, 164.35, 332.35], "category_id": 1, "id": 497359, "split": "val", "sentences": [{"tokens": ["indian", "man", "in", "button", "up", "colored", "shirt", "and", "blue", "pants", "walking"], "raw": "Indian man in button up colored shirt and blue pants walking.", "sent_id": 25987, "sent": "indian man in button up colored shirt and blue pants walking"}, {"tokens": ["man", "wearing", "a", "white", "shirt"], "raw": "Man wearing a white shirt", "sent_id": 25988, "sent": "man wearing a white shirt"}], "file_name": "COCO_train2014_000000452565_497359.jpg", "ann_id": 497359, "sent_ids": [25987, 25988], "ref_id": 15001}, {"segmentation": [[280.94, 529.56, 361.98, 548.38, 396.71, 531.73, 411.18, 496.28, 445.19, 411.62, 437.95, 386.29, 429.27, 377.61, 319.28, 344.33, 249.82, 328.41, 239.69, 332.75, 227.39, 337.09, 170.95, 446.35, 176.74, 460.82, 186.87, 499.17]], "area": 42337.57395, "iscrowd": 0, "image_id": 503022, "bbox": [170.95, 328.41, 274.24, 219.97], "category_id": 51, "id": 1903387, "split": "val", "sentences": [{"tokens": ["the", "small", "red", "container", "with", "slices", "of", "seasoned", "sausage"], "raw": "The small red container with slices of seasoned sausage.", "sent_id": 26070, "sent": "the small red container with slices of seasoned sausage"}, {"tokens": ["sliced", "bananas", "in", "a", "red", "bowl"], "raw": "Sliced bananas in a red bowl.", "sent_id": 26071, "sent": "sliced bananas in a red bowl"}], "file_name": "COCO_train2014_000000503022_1903387.jpg", "ann_id": 1903387, "sent_ids": [26070, 26071], "ref_id": 15036}, {"segmentation": [[637.98, 106.97, 598.82, 87.87, 550.11, 94.55, 525.28, 121.29, 516.69, 128.93, 485.17, 138.48, 492.81, 150.9, 503.31, 154.72, 526.24, 154.72, 523.37, 164.27, 510.96, 176.69, 505.22, 183.37, 521.46, 187.19, 526.24, 197.7, 527.19, 198.65, 519.55, 206.29, 527.19, 235.9, 564.44, 239.72, 565.39, 248.31, 546.29, 258.82, 528.15, 302.75, 514.78, 355.28, 525.28, 395.39, 513.82, 417.36, 640.0, 417.36]], "area": 36855.39200000001, "iscrowd": 0, "image_id": 471136, "bbox": [485.17, 87.87, 154.83, 329.49], "category_id": 1, "id": 1727245, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "blue", "hat"], "raw": "A man wearing a blue hat.", "sent_id": 26080, "sent": "a man wearing a blue hat"}, {"tokens": ["zoo", "employee", "in", "blue", "shirt", "and", "blue", "hat"], "raw": "zoo employee in blue shirt and blue hat", "sent_id": 26081, "sent": "zoo employee in blue shirt and blue hat"}], "file_name": "COCO_train2014_000000471136_1727245.jpg", "ann_id": 1727245, "sent_ids": [26080, 26081], "ref_id": 15038}, {"segmentation": [[340.44, 63.11, 365.33, 62.22, 386.67, 72.0, 396.44, 85.33, 397.33, 91.56, 400.89, 92.44, 408.89, 103.11, 406.22, 114.67, 406.22, 126.22, 408.0, 133.33, 422.22, 140.44, 430.22, 152.0, 469.33, 161.78, 500.44, 177.78, 518.22, 224.0, 536.89, 288.89, 545.78, 337.78, 516.44, 341.33, 488.0, 353.78, 410.67, 352.0, 407.11, 313.78, 394.67, 268.44, 385.78, 263.11, 367.11, 261.33, 371.56, 223.11, 354.67, 216.89, 336.89, 224.0, 337.78, 261.33, 343.11, 288.0, 335.11, 289.78, 325.33, 282.67, 316.44, 265.78, 306.67, 262.22, 292.44, 260.44, 281.78, 262.22, 270.22, 264.89, 264.0, 270.22, 246.22, 283.56, 267.56, 234.67, 287.11, 192.89, 304.89, 171.56, 341.33, 161.78, 342.22, 150.22, 334.22, 120.89, 322.67, 111.11, 323.56, 86.22, 336.0, 70.22]], "area": 41682.2148, "iscrowd": 0, "image_id": 520112, "bbox": [246.22, 62.22, 299.56, 291.56], "category_id": 1, "id": 2207666, "split": "val", "sentences": [{"tokens": ["a", "balding", "man", "with", "white", "hair", "wearing", "a", "gray", "checked", "shirt", "and", "holding", "a", "wine", "glass"], "raw": "A balding man with white hair wearing a gray checked shirt and holding a wine glass.", "sent_id": 26197, "sent": "a balding man with white hair wearing a gray checked shirt and holding a wine glass"}, {"tokens": ["a", "balding", "older", "man", "wearing", "a", "gray", "shirt", "and", "holding", "a", "wine", "glass", "in", "right", "hand"], "raw": "A balding older man wearing a gray shirt and holding a wine glass in right hand.", "sent_id": 26198, "sent": "a balding older man wearing a gray shirt and holding a wine glass in right hand"}], "file_name": "COCO_train2014_000000520112_2207666.jpg", "ann_id": 2207666, "sent_ids": [26197, 26198], "ref_id": 15076}, {"segmentation": [[108.9, 383.15, 99.35, 378.37, 69.73, 362.13, 52.54, 358.31, 40.12, 357.36, 18.15, 351.63, 15.28, 333.48, 4.78, 322.01, 3.82, 306.73, 10.51, 201.65, 88.84, 167.26, 109.85, 171.08, 147.11, 176.81, 198.69, 196.88, 223.53, 203.56, 283.71, 227.44, 284.67, 242.73, 279.89, 251.32, 274.16, 256.1, 265.56, 270.43, 260.79, 290.49, 257.92, 304.82, 256.01, 314.37, 249.32, 325.84, 244.55, 335.39, 235.95, 347.81, 150.93, 365.0, 139.47, 374.55, 124.18, 383.15, 112.72, 379.33]], "area": 44259.75765000001, "iscrowd": 0, "image_id": 213419, "bbox": [3.82, 167.26, 280.85, 215.89], "category_id": 9, "id": 181697, "split": "val", "sentences": [{"tokens": ["the", "boat", "with", "says", "marleni", "-", "n", "on", "it"], "raw": "The boat with says marleni-n on it.", "sent_id": 26203, "sent": "the boat with says marleni - n on it"}, {"tokens": ["an", "old", "row", "boat", "with", "'", "marleni", "-", "iv", "'", "written", "on", "it"], "raw": "An old row boat with 'Marleni-IV' written on it.", "sent_id": 26204, "sent": "an old row boat with ' marleni - iv ' written on it"}], "file_name": "COCO_train2014_000000213419_181697.jpg", "ann_id": 181697, "sent_ids": [26203, 26204], "ref_id": 15079}, {"segmentation": [[139.82, 459.1, 233.51, 495.14, 196.04, 512.43, 194.59, 526.85, 201.8, 531.17, 198.92, 565.77, 198.92, 604.68, 193.15, 616.22, 180.18, 621.98, 164.32, 632.07, 119.64, 603.24, 109.55, 593.15, 103.78, 510.99, 93.69, 499.46, 99.46, 477.84]], "area": 14379.818050000002, "iscrowd": 0, "image_id": 155618, "bbox": [93.69, 459.1, 139.82, 172.97], "category_id": 70, "id": 1096024, "split": "val", "sentences": [{"tokens": ["the", "tank", "of", "the", "toilet"], "raw": "The tank of the toilet", "sent_id": 26343, "sent": "the tank of the toilet"}, {"tokens": ["the", "top", "of", "the", "toilet"], "raw": "The top of the toilet.", "sent_id": 26344, "sent": "the top of the toilet"}], "file_name": "COCO_train2014_000000155618_1096024.jpg", "ann_id": 1096024, "sent_ids": [26343, 26344], "ref_id": 15131}, {"segmentation": [[323.1, 339.61, 314.84, 329.29, 334.45, 320.0, 347.87, 315.87, 355.1, 315.87, 350.97, 333.42, 348.9, 337.55, 324.13, 337.55], [349.94, 222.97, 346.84, 231.23, 365.42, 234.32, 374.71, 236.39, 375.74, 241.55, 385.03, 241.55, 400.52, 251.87, 406.71, 261.16, 401.55, 281.81, 393.29, 300.39, 393.29, 308.65, 387.1, 316.9, 386.06, 329.29, 392.26, 333.42, 393.29, 338.58, 421.16, 340.65, 418.06, 327.23, 429.78, 319.64, 441.13, 318.25, 454.19, 325.16, 456.34, 330.28, 456.26, 342.71, 468.65, 342.71, 470.47, 342.71, 479.05, 382.29, 482.06, 392.26, 480.0, 398.45, 475.87, 399.48, 474.84, 407.74, 551.23, 409.81, 551.23, 425.29, 589.42, 422.19, 585.29, 313.81, 595.61, 297.29, 612.13, 282.84, 613.16, 269.42, 604.9, 256.0, 593.55, 249.81, 581.16, 239.48, 565.68, 236.39, 544.0, 238.45, 528.52, 239.48, 508.51, 226.18, 479.64, 218.92, 458.32, 216.77, 408.77, 214.71, 346.84, 216.77], [316.74, 233.03, 316.15, 223.84, 312.29, 220.29, 311.11, 218.51, 251.82, 221.18, 242.93, 222.36, 222.77, 226.51, 211.21, 229.48, 204.69, 230.66, 195.79, 234.22, 187.79, 239.56, 180.97, 238.96, 148.36, 239.85, 137.99, 239.26, 129.69, 239.56, 124.05, 240.74, 107.75, 244.59, 97.67, 247.26, 93.52, 249.04, 89.96, 253.49, 84.63, 258.53, 84.92, 262.47, 84.04, 266.62, 83.74, 268.99, 83.44, 273.73, 83.74, 277.29, 85.81, 283.22, 88.48, 288.55, 92.34, 293.89, 95.3, 296.85, 98.26, 299.82, 100.64, 306.83, 100.64, 346.53, 105.97, 346.53, 136.5, 320.74, 137.99, 317.18, 140.65, 313.33, 150.44, 309.18, 151.62, 308.29, 151.33, 304.44, 152.51, 298.51, 156.07, 292.87, 156.37, 286.35, 158.14, 280.72, 159.33, 275.98, 162.0, 272.72, 166.15, 271.23, 170.0, 267.38, 182.16, 266.79, 187.79, 267.97, 190.46, 268.57, 192.24, 269.16, 195.79, 270.05, 201.42, 273.01, 202.31, 274.79, 206.76, 273.61, 209.72, 273.61, 213.58, 274.49, 216.25, 275.38, 219.51, 275.98, 225.44, 276.87, 226.92, 277.76, 238.48, 262.93, 239.37, 259.97, 243.52, 257.3, 255.08, 254.93, 263.08, 254.63, 269.31, 252.56, 274.64, 249.3, 277.31, 246.04, 279.39, 244.55, 285.32, 243.07, 288.87, 241.0, 294.21, 240.4, 299.25, 238.92, 302.81, 238.03, 303.7, 236.25, 312.89, 233.59, 315.55, 233.29]], "area": 42648.31225, "iscrowd": 0, "image_id": 499966, "bbox": [83.44, 214.71, 529.72, 210.58], "category_id": 63, "id": 116020, "split": "val", "sentences": [{"tokens": ["a", "blue", "and", "white", "striped", "couch"], "raw": "A blue and white striped couch.", "sent_id": 26702, "sent": "a blue and white striped couch"}, {"tokens": ["a", "white", "and", "blue", "lined", "three", "seater", "sofa"], "raw": "A white and blue lined three seater sofa", "sent_id": 26703, "sent": "a white and blue lined three seater sofa"}], "file_name": "COCO_train2014_000000499966_116020.jpg", "ann_id": 116020, "sent_ids": [26702, 26703], "ref_id": 15252}, {"segmentation": [[250.28, 133.05, 261.57, 110.46, 275.95, 91.98, 289.81, 83.25, 305.72, 77.09, 320.61, 75.55, 338.57, 70.93, 348.33, 74.53, 351.41, 75.55, 365.27, 70.93, 378.1, 82.23, 381.18, 96.09, 369.89, 105.84, 365.78, 107.9, 359.62, 111.49, 355.52, 110.98, 351.41, 110.98, 343.71, 109.44, 336.52, 114.57, 334.47, 123.81, 332.41, 127.4, 332.41, 127.92, 354.49, 136.64, 357.06, 142.8, 357.06, 148.45, 354.49, 154.61, 347.82, 171.04, 340.63, 186.95, 339.6, 193.62, 344.22, 195.68, 342.68, 197.73, 352.95, 200.3, 356.54, 200.81, 357.57, 201.84, 359.62, 206.97, 344.74, 211.08, 319.58, 209.02, 314.96, 204.92, 316.5, 198.24, 313.93, 194.14, 301.1, 190.54, 292.37, 185.92, 290.83, 179.25, 293.4, 172.58, 293.91, 165.39, 293.91, 163.85, 296.99, 159.74, 300.59, 155.64, 302.13, 151.53, 278.0, 149.48, 270.81, 147.94, 263.63, 141.26, 259.52, 136.13, 254.39, 133.05]], "area": 9673.96, "iscrowd": 0, "image_id": 543678, "bbox": [250.28, 70.93, 130.9, 140.15], "category_id": 1, "id": 1740394, "split": "val", "sentences": [{"tokens": ["a", "young", "man", "is", "doing", "a", "trick", "in", "the", "air", "while", "skateboarding"], "raw": "a young man is doing a trick in the air while skateboarding", "sent_id": 26742, "sent": "a young man is doing a trick in the air while skateboarding"}, {"tokens": ["a", "boy", "jumping", "in", "mid", "air"], "raw": "a boy jumping in mid air", "sent_id": 26743, "sent": "a boy jumping in mid air"}], "file_name": "COCO_train2014_000000543678_1740394.jpg", "ann_id": 1740394, "sent_ids": [26742, 26743], "ref_id": 15267}, {"segmentation": [[145.61, 116.12, 248.19, 106.63, 248.79, 42.0, 245.82, 7.61, 245.23, 4.05, 126.04, 13.54, 145.61, 118.49]], "area": 11635.96345, "iscrowd": 0, "image_id": 561479, "bbox": [126.04, 4.05, 122.75, 114.44], "category_id": 72, "id": 2194899, "split": "val", "sentences": [{"tokens": ["small", "monitor", "on", "table", "next", "to", "package", "of", "cd", "disks", "and", "headphones"], "raw": "Small monitor on table next to package of cd disks and headphones.", "sent_id": 26746, "sent": "small monitor on table next to package of cd disks and headphones"}, {"tokens": ["first", "from", "the", "left", "computer", "monitor"], "raw": "first from the left computer monitor", "sent_id": 26747, "sent": "first from the left computer monitor"}], "file_name": "COCO_train2014_000000561479_2194899.jpg", "ann_id": 2194899, "sent_ids": [26746, 26747], "ref_id": 15269}, {"segmentation": [[323.99, 229.76, 334.47, 216.42, 340.19, 209.75, 355.44, 209.75, 367.83, 211.66, 378.31, 217.38, 381.17, 228.81, 371.64, 232.62, 323.99, 264.07, 311.6, 273.6, 305.89, 285.03, 311.6, 293.61, 323.04, 295.51, 342.1, 299.33, 348.77, 299.33, 353.53, 295.51, 359.25, 291.7, 369.73, 275.5, 381.17, 267.88, 383.07, 285.03, 392.6, 292.66, 400.22, 288.84, 412.61, 282.17, 430.72, 271.69, 437.39, 265.97, 443.11, 263.12, 460.26, 263.12, 466.93, 263.12, 477.41, 264.07, 485.99, 264.07, 494.56, 264.07, 494.56, 257.4, 488.85, 242.15, 485.03, 234.53, 493.61, 235.48, 500.28, 229.76, 501.23, 217.38, 501.23, 204.03, 499.33, 164.97, 494.56, 132.57, 488.85, 105.88, 483.13, 82.06, 477.41, 46.8, 477.41, 38.23, 451.68, 20.12, 421.19, 22.98, 394.51, 43.95, 381.17, 69.67, 384.02, 104.93, 380.21, 132.57, 357.34, 146.86, 338.28, 200.22, 332.57, 209.75]], "area": 32043.6336, "iscrowd": 0, "image_id": 342374, "bbox": [305.89, 20.12, 195.34, 279.21], "category_id": 1, "id": 454349, "split": "val", "sentences": [{"tokens": ["a", "little", "girl", "with", "brown", "hair", "wearing", "a", "striped", "shirt", "and", "a", "purple", "jacket"], "raw": "A little girl with brown hair wearing a striped shirt and a purple jacket.", "sent_id": 26780, "sent": "a little girl with brown hair wearing a striped shirt and a purple jacket"}, {"tokens": ["a", "girl", "baby", "preparing", "sandwich", "with", "bread", "and", "jam", "with", "her", "friends"], "raw": "A GIRL BABY PREPARING SANDWICH WITH BREAD AND JAM WITH HER FRIENDS", "sent_id": 26781, "sent": "a girl baby preparing sandwich with bread and jam with her friends"}], "file_name": "COCO_train2014_000000342374_454349.jpg", "ann_id": 454349, "sent_ids": [26780, 26781], "ref_id": 15282}, {"segmentation": [[145.62, 398.02, 144.54, 379.69, 149.93, 378.61, 148.85, 339.78, 140.22, 295.55, 125.12, 254.56, 130.52, 243.78, 113.26, 240.54, 115.42, 213.57, 135.91, 180.13, 140.22, 160.72, 140.22, 153.17, 134.83, 135.91, 136.99, 121.89, 151.01, 106.79, 174.74, 136.99, 176.9, 145.62, 187.69, 156.4, 196.31, 167.19, 208.18, 185.53, 212.49, 199.55, 217.89, 235.15, 217.89, 238.38, 212.49, 240.54, 217.89, 294.47, 204.94, 334.38, 202.79, 372.13, 202.79, 428.22, 182.29, 432.54, 181.21, 417.44, 182.29, 410.97, 182.29, 371.06, 181.21, 328.99, 175.82, 323.6, 170.43, 348.4, 170.43, 409.89, 152.09, 407.73]], "area": 19379.9919, "iscrowd": 0, "image_id": 562835, "bbox": [113.26, 106.79, 104.63, 325.75], "category_id": 1, "id": 184644, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "white", "tshirt", ",", "black", "gym", "shorts", ",", "and", "brown", "shoes", "walking", "in", "his", "kitchen"], "raw": "A man with a white tshirt, black gym shorts, and brown shoes walking in his kitchen.", "sent_id": 27021, "sent": "a man with a white tshirt , black gym shorts , and brown shoes walking in his kitchen"}, {"tokens": ["a", "man", "in", "a", "white", "shirt", "walking", "away"], "raw": "a man in a white shirt walking away", "sent_id": 27022, "sent": "a man in a white shirt walking away"}], "file_name": "COCO_train2014_000000562835_184644.jpg", "ann_id": 184644, "sent_ids": [27021, 27022], "ref_id": 15376}, {"segmentation": [[523.42, 185.49, 564.74, 191.0, 588.62, 175.39, 624.43, 22.04, 620.76, 1.84, 547.29, 1.84, 531.68, 20.2, 517.91, 69.79, 541.78, 86.32, 544.54, 91.83, 519.75, 183.66]], "area": 14089.067750000002, "iscrowd": 0, "image_id": 69839, "bbox": [517.91, 1.84, 106.52, 189.16], "category_id": 44, "id": 82101, "split": "val", "sentences": [{"tokens": ["a", "plain", "glass", "bottle", "with", "a", "white", "liquid"], "raw": "A plain glass bottle with a white liquid.", "sent_id": 27137, "sent": "a plain glass bottle with a white liquid"}, {"tokens": ["a", "half", "empty", "bottle", "of", "clear", "liquid"], "raw": "A half empty bottle of clear liquid.", "sent_id": 27138, "sent": "a half empty bottle of clear liquid"}], "file_name": "COCO_train2014_000000069839_82101.jpg", "ann_id": 82101, "sent_ids": [27137, 27138], "ref_id": 15426}, {"segmentation": [[44.58, 300.34, 74.79, 268.7, 90.61, 252.88, 93.48, 205.42, 120.81, 225.56, 122.25, 215.49, 93.48, 163.72, 103.55, 91.81, 140.94, 63.04, 198.47, 65.92, 234.43, 91.81, 253.12, 156.52, 231.55, 203.98, 218.61, 237.06, 218.61, 245.69, 258.88, 262.95, 271.82, 268.7, 313.53, 238.5, 339.42, 238.5, 339.42, 238.5, 348.04, 203.98, 339.42, 146.46, 339.42, 136.39, 379.69, 170.91, 381.12, 205.42, 384.0, 258.64, 391.19, 346.37, 384.0, 370.82, 320.72, 372.25, 299.15, 363.63, 312.09, 455.67, 312.09, 501.69, 312.09, 611.0, 312.09, 628.25, 84.85, 631.13, 92.04, 585.11, 54.65, 484.43]], "area": 130822.36760000001, "iscrowd": 0, "image_id": 520590, "bbox": [44.58, 63.04, 346.61, 568.09], "category_id": 1, "id": 459587, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "blue", "and", "white", "outfit"], "raw": "A person in a blue and white outfit.", "sent_id": 27139, "sent": "a person in a blue and white outfit"}, {"tokens": ["a", "boy", "looking", "at", "his", "cellphone"], "raw": "A boy looking at his cellphone.", "sent_id": 27140, "sent": "a boy looking at his cellphone"}], "file_name": "COCO_train2014_000000520590_459587.jpg", "ann_id": 459587, "sent_ids": [27139, 27140], "ref_id": 15427}, {"segmentation": [[78.11, 157.92, 81.51, 150.0, 93.96, 147.74, 105.28, 162.45, 117.74, 176.04, 118.87, 178.3, 120.0, 185.09, 130.19, 186.23, 138.11, 183.96, 153.96, 193.02, 163.02, 205.47, 168.68, 220.19, 159.62, 232.64, 141.51, 243.96, 126.79, 265.47, 90.57, 314.15, 96.23, 358.3, 31.7, 356.04, 3.4, 352.64, 2.26, 351.51, 1.13, 311.89, 0.0, 264.34, 11.32, 255.28, 14.72, 253.02, 19.25, 242.83, 19.25, 223.58, 19.25, 220.19, 19.25, 211.13, 26.04, 206.6, 32.83, 198.68, 37.36, 188.49, 44.15, 177.17, 55.47, 164.72, 74.72, 154.53]], "area": 21507.712550000007, "iscrowd": 0, "image_id": 517985, "bbox": [0.0, 147.74, 168.68, 210.56], "category_id": 56, "id": 1056900, "split": "val", "sentences": [{"tokens": ["the", "green", "vegetable", "in", "the", "left"], "raw": "the green vegetable in the left", "sent_id": 27141, "sent": "the green vegetable in the left"}, {"tokens": ["green", "vegetable", "by", "brown", "food"], "raw": "green vegetable by brown food", "sent_id": 27142, "sent": "green vegetable by brown food"}], "file_name": "COCO_train2014_000000517985_1056900.jpg", "ann_id": 1056900, "sent_ids": [27141, 27142], "ref_id": 15428}, {"segmentation": [[60.04, 375.0, 57.89, 356.51, 52.89, 350.08, 70.05, 345.79, 79.35, 345.07, 82.92, 339.35, 77.92, 328.62, 73.63, 317.89, 72.91, 312.17, 85.07, 287.14, 90.79, 269.98, 93.65, 250.67, 103.66, 222.06, 112.96, 209.19, 124.4, 199.89, 140.85, 192.74, 160.16, 189.17, 161.59, 181.3, 156.58, 169.86, 150.86, 158.41, 144.43, 144.11, 150.15, 104.71, 154.44, 98.27, 171.6, 88.26, 188.77, 79.68, 202.35, 78.96, 210.94, 79.68, 217.37, 86.83, 228.81, 86.83, 231.67, 90.4, 238.11, 96.12, 241.69, 103.99, 242.4, 114.72, 242.4, 145.47, 240.97, 162.63, 236.68, 161.2, 234.54, 166.21, 234.54, 186.23, 233.82, 199.11, 260.28, 211.27, 268.86, 217.7, 286.03, 247.02, 296.04, 266.33, 303.91, 284.93, 308.2, 296.37, 301.76, 330.7, 262.43, 367.96, 254.56, 375.0]], "area": 45368.05070000001, "iscrowd": 0, "image_id": 495776, "bbox": [52.89, 78.96, 255.31, 296.04], "category_id": 1, "id": 460547, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "blue", "blouse", "looks", "at", "her", "phone"], "raw": "A woman in a blue blouse looks at her phone.", "sent_id": 27150, "sent": "a woman in a blue blouse looks at her phone"}, {"tokens": ["a", "woman", "in", "a", "light", "blue", "sleeveless", "shirt", "looking", "at", "her", "phone"], "raw": "A woman in a light blue sleeveless shirt looking at her phone.", "sent_id": 27151, "sent": "a woman in a light blue sleeveless shirt looking at her phone"}], "file_name": "COCO_train2014_000000495776_460547.jpg", "ann_id": 460547, "sent_ids": [27150, 27151], "ref_id": 15433}, {"segmentation": [[561.16, 306.1, 545.08, 309.05, 539.67, 305.77, 535.9, 288.22, 533.27, 276.74, 534.26, 271.98, 535.9, 266.73, 542.3, 255.41, 552.96, 249.51, 553.45, 243.6, 548.36, 240.48, 546.23, 231.46, 551.81, 227.52, 555.09, 237.7, 557.55, 240.98, 570.18, 208.5, 571.0, 203.9, 576.58, 201.28, 577.73, 145.99, 584.62, 140.09, 640.0, 119.42, 638.92, 309.38, 640.0, 327.76, 605.12, 321.69, 595.28, 309.38, 580.03, 311.68]], "area": 14751.599249999996, "iscrowd": 0, "image_id": 438663, "bbox": [533.27, 119.42, 106.73, 208.34], "category_id": 8, "id": 400693, "split": "val", "sentences": [{"tokens": ["a", "yellow", "color", "truk", "parked", "near", "white", "car"], "raw": "a yellow color truk parked near white car", "sent_id": 27233, "sent": "a yellow color truk parked near white car"}, {"tokens": ["the", "truck", "with", "no", "markings"], "raw": "The truck with no markings.", "sent_id": 27234, "sent": "the truck with no markings"}], "file_name": "COCO_train2014_000000438663_400693.jpg", "ann_id": 400693, "sent_ids": [27233, 27234], "ref_id": 15467}, {"segmentation": [[231.3, 172.85, 392.95, 172.85, 395.44, 223.83, 397.93, 251.19, 402.9, 271.09, 397.93, 274.82, 392.95, 281.04, 359.38, 284.77, 353.16, 287.25, 345.7, 303.42, 345.7, 305.91, 358.13, 320.83, 355.65, 325.8, 332.02, 344.46, 322.07, 339.48, 310.88, 335.75, 313.37, 346.94, 314.61, 353.16, 300.93, 360.62, 307.15, 368.08, 287.25, 363.11, 294.72, 385.49, 233.78, 390.47, 220.1, 360.62, 193.99, 344.46, 193.99, 341.97, 207.67, 287.25, 207.67, 171.61]], "area": 33325.335600000006, "iscrowd": 0, "image_id": 422255, "bbox": [193.99, 171.61, 208.91, 218.86], "category_id": 73, "id": 1970392, "split": "val", "sentences": [{"tokens": ["the", "laptop", "is", "being", "used", "by", "the", "boy", "while", "the", "girl", "watches"], "raw": "The laptop is being used by the boy while the girl watches.", "sent_id": 27245, "sent": "the laptop is being used by the boy while the girl watches"}, {"tokens": ["a", "white", "labtop"], "raw": "A white labtop.", "sent_id": 27246, "sent": "a white labtop"}], "file_name": "COCO_train2014_000000422255_1970392.jpg", "ann_id": 1970392, "sent_ids": [27245, 27246], "ref_id": 15470}, {"segmentation": [[420.67, 371.06, 393.71, 387.24, 363.51, 373.21, 355.96, 350.56, 366.74, 331.15, 360.27, 277.21, 374.29, 258.88, 382.92, 242.7, 404.49, 196.31, 421.75, 167.19, 440.09, 157.48, 440.09, 136.99, 440.09, 125.12, 439.01, 116.49, 429.3, 108.94, 436.85, 96.0, 464.9, 89.53, 480.0, 84.13, 487.55, 87.37, 495.1, 79.82, 511.28, 76.58, 517.75, 87.37, 529.62, 87.37, 551.19, 101.39, 539.33, 128.36, 537.17, 138.07, 558.74, 158.56, 599.73, 223.28, 602.97, 266.43, 588.94, 299.87, 569.53, 319.28, 566.29, 327.91, 555.51, 401.26, 553.35, 430.38, 532.85, 446.56, 477.84, 414.2, 469.21, 378.61, 485.39, 335.46, 480.0, 326.83, 430.38, 304.18, 426.07, 326.83, 428.22, 349.48]], "area": 53141.5089, "iscrowd": 0, "image_id": 443916, "bbox": [355.96, 76.58, 247.01, 369.98], "category_id": 88, "id": 1674457, "split": "val", "sentences": [{"tokens": ["a", "giant", "teddybear", "with", "a", "happy", "halloween", "sign"], "raw": "a giant teddybear with a happy Halloween sign", "sent_id": 27298, "sent": "a giant teddybear with a happy halloween sign"}, {"tokens": ["bear", "on", "right", "wearing", "happy", "halloween", "sign"], "raw": "bear on right wearing Happy Halloween sign", "sent_id": 27299, "sent": "bear on right wearing happy halloween sign"}], "file_name": "COCO_train2014_000000443916_1674457.jpg", "ann_id": 1674457, "sent_ids": [27298, 27299], "ref_id": 15487}, {"segmentation": [[199.8, 209.22, 201.82, 203.16, 203.16, 197.78, 203.16, 191.05, 205.18, 180.96, 205.18, 176.25, 209.89, 171.55, 209.89, 164.82, 215.27, 150.69, 215.27, 147.33, 214.6, 139.93, 219.31, 132.53, 222.0, 125.13, 248.91, 99.56, 265.05, 96.2, 278.51, 93.51, 283.89, 91.49, 290.62, 91.49, 298.69, 92.84, 308.11, 93.51, 312.82, 95.53, 315.51, 95.53, 331.65, 102.93, 339.73, 113.69, 349.82, 123.11, 359.24, 129.16, 365.29, 132.53, 367.98, 133.87, 369.33, 136.56, 373.36, 141.95, 380.09, 151.36, 388.16, 166.16, 388.16, 173.56, 392.2, 188.36, 399.6, 193.75, 400.27, 205.18, 406.33, 213.25, 408.35, 215.27, 410.36, 222.0, 412.38, 229.4, 415.75, 240.16, 415.75, 240.84, 419.11, 242.18, 419.11, 245.55, 419.78, 248.91, 425.16, 259.67, 425.16, 260.35, 427.85, 273.13, 427.85, 284.56, 427.85, 285.91, 427.85, 293.98, 427.85, 304.07, 428.53, 320.89, 428.53, 322.91, 428.53, 326.27, 415.07, 329.64, 399.6, 329.64, 395.56, 328.29, 395.56, 328.29, 385.47, 327.62, 372.69, 327.62, 363.27, 326.95, 356.55, 326.95, 345.11, 326.95, 329.64, 327.62, 318.2, 328.29, 311.47, 328.29, 308.11, 328.29, 298.02, 327.62, 288.6, 327.62, 282.55, 326.27, 273.13, 326.95, 269.09, 326.95, 263.71, 327.62, 261.69, 324.25, 259.67, 319.55, 258.33, 315.51, 256.98, 310.13, 252.95, 298.69, 251.6, 294.65, 248.91, 284.56, 247.56, 279.85, 247.56, 276.49, 246.89, 266.4, 245.55, 262.36, 236.13, 242.85, 237.47, 238.15, 237.47, 238.15, 222.67, 231.42, 205.85, 228.05, 203.16, 228.05, 197.78, 219.31, 197.11, 205.85]], "area": 39395.605999999985, "iscrowd": 0, "image_id": 301943, "bbox": [197.11, 91.49, 231.42, 238.15], "category_id": 18, "id": 15742, "split": "val", "sentences": [{"tokens": ["a", "puppy", "that", "is", "sitting", "in", "front", "of", "another", "puppy"], "raw": "A puppy that is sitting in front of another puppy.", "sent_id": 27360, "sent": "a puppy that is sitting in front of another puppy"}, {"tokens": ["the", "dog", "closest", "to", "the", "camera"], "raw": "the dog closest to the camera", "sent_id": 27361, "sent": "the dog closest to the camera"}], "file_name": "COCO_train2014_000000301943_15742.jpg", "ann_id": 15742, "sent_ids": [27360, 27361], "ref_id": 15504}, {"segmentation": [[78.21, 357.68, 104.88, 271.2, 129.13, 181.49, 122.66, 176.64, 112.16, 171.79, 91.14, 174.22, 74.17, 185.53, 61.24, 185.53, 63.67, 176.64, 61.24, 166.95, 47.5, 169.37, 42.65, 173.41, 45.88, 183.11, 9.52, 183.11, 4.67, 176.64, 0.0, 178.26, 2.24, 251.0, 50.73, 356.06]], "area": 15902.584499999999, "iscrowd": 0, "image_id": 223023, "bbox": [0.0, 166.95, 129.13, 190.73], "category_id": 81, "id": 2139862, "split": "val", "sentences": [{"tokens": ["a", "bathtub"], "raw": "A bathtub.", "sent_id": 27368, "sent": "a bathtub"}, {"tokens": ["the", "bathtub", "on", "the", "left", "side", "of", "the", "toilet"], "raw": "the bathtub on the left side of the toilet", "sent_id": 27369, "sent": "the bathtub on the left side of the toilet"}], "file_name": "COCO_train2014_000000223023_2139862.jpg", "ann_id": 2139862, "sent_ids": [27368, 27369], "ref_id": 15508}, {"segmentation": [[240.95, 211.07, 243.29, 260.35, 259.72, 290.85, 282.01, 311.97, 310.17, 323.71, 367.67, 333.09, 400.52, 309.63, 422.81, 273.25, 425.16, 193.47, 402.87, 159.44, 391.13, 150.05, 366.49, 139.49, 345.37, 135.97, 317.21, 134.8, 290.23, 140.67, 271.45, 150.05, 257.37, 170.0, 245.64, 193.47]], "area": 29414.921099999996, "iscrowd": 0, "image_id": 427654, "bbox": [240.95, 134.8, 184.21, 198.29], "category_id": 55, "id": 1051722, "split": "val", "sentences": [{"tokens": ["the", "first", "lemon", "from", "the", "right"], "raw": "The first lemon from the right.", "sent_id": 27431, "sent": "the first lemon from the right"}], "file_name": "COCO_train2014_000000427654_1051722.jpg", "ann_id": 1051722, "sent_ids": [27431], "ref_id": 15533}, {"segmentation": [[1.63, 145.12, 45.85, 127.97, 117.12, 152.38, 150.12, 141.82, 167.94, 135.89, 278.14, 142.48, 307.18, 182.08, 315.76, 221.02, 295.3, 271.17, 286.72, 285.69, 314.44, 317.37, 313.24, 428.0, 1.11, 427.34]], "area": 87715.55554999999, "iscrowd": 0, "image_id": 243574, "bbox": [1.11, 127.97, 314.65, 300.03], "category_id": 17, "id": 47487, "split": "val", "sentences": [{"tokens": ["a", "cat", "with", "its", "ears", "down", ",", "facing", "another", "cat"], "raw": "A cat with its ears down, facing another cat.", "sent_id": 27437, "sent": "a cat with its ears down , facing another cat"}], "file_name": "COCO_train2014_000000243574_47487.jpg", "ann_id": 47487, "sent_ids": [27437], "ref_id": 15536}, {"segmentation": [[180.6, 119.62, 162.89, 139.11, 154.03, 139.99, 144.29, 135.56, 131.9, 141.76, 123.04, 156.82, 107.38, 124.96, 122.15, 107.51, 150.34, 84.69, 126.17, 44.42, 114.09, 26.98, 118.12, 17.58, 130.2, 25.63, 143.62, 45.77, 155.7, 68.59, 162.42, 79.32, 170.47, 87.38, 197.32, 77.98, 208.05, 87.38, 209.4, 98.12, 193.29, 102.14, 187.92, 120.94, 194.63, 134.36, 213.42, 155.83, 214.77, 167.91, 198.66, 173.28, 196.19, 152.46, 196.19, 174.7, 176.43, 164.81, 171.49, 137.64]], "area": 6252.101449999997, "iscrowd": 0, "image_id": 83605, "bbox": [107.38, 17.58, 107.39, 157.12], "category_id": 1, "id": 438579, "split": "val", "sentences": [{"tokens": ["a", "man", "wearinf", "a", "light", "blue", "t", "-", "shirt", "and", "jeans", "with", "his", "arms", "extended"], "raw": "A man wearinf a light blue t-shirt and jeans with his arms extended.", "sent_id": 27482, "sent": "a man wearinf a light blue t - shirt and jeans with his arms extended"}, {"tokens": ["a", "man", "on", "a", "skateboard"], "raw": "A man on a skateboard", "sent_id": 27483, "sent": "a man on a skateboard"}], "file_name": "COCO_train2014_000000083605_438579.jpg", "ann_id": 438579, "sent_ids": [27482, 27483], "ref_id": 15552}, {"segmentation": [[205.66, 586.79, 195.6, 546.52, 205.66, 490.43, 211.42, 460.22, 217.17, 431.46, 207.1, 422.83, 199.91, 419.96, 205.66, 408.45, 204.22, 392.63, 209.98, 381.12, 215.73, 366.74, 218.61, 356.67, 221.48, 343.73, 227.24, 335.1, 227.24, 317.84, 228.67, 302.02, 244.49, 287.64, 261.75, 287.64, 271.82, 291.96, 277.57, 297.71, 270.38, 319.28, 267.51, 333.66, 279.01, 343.73, 290.52, 356.67, 303.46, 376.81, 307.78, 394.07, 307.78, 412.76, 310.65, 430.02, 291.96, 442.97, 293.39, 454.47, 293.39, 481.8, 290.52, 513.44, 306.34, 537.89, 323.6, 565.21, 333.66, 585.35, 290.52, 591.1, 277.57, 591.1, 303.46, 608.36, 325.03, 625.62, 313.53, 632.81, 280.45, 628.49, 253.12, 609.8, 248.81, 606.92, 247.37, 629.93, 232.99, 631.37, 220.04, 619.87, 218.61, 605.48, 209.98, 579.6]], "area": 28980.82269999999, "iscrowd": 0, "image_id": 452565, "bbox": [195.6, 287.64, 138.06, 345.17], "category_id": 1, "id": 487379, "split": "val", "sentences": [{"tokens": ["man", "in", "cultural", "clothing"], "raw": "man in cultural clothing", "sent_id": 27544, "sent": "man in cultural clothing"}, {"tokens": ["a", "man", ",", "wearing", "traditional", "dress", ",", "including", "a", "scarf"], "raw": "A man, wearing traditional dress, including a scarf.", "sent_id": 27545, "sent": "a man , wearing traditional dress , including a scarf"}], "file_name": "COCO_train2014_000000452565_487379.jpg", "ann_id": 487379, "sent_ids": [27544, 27545], "ref_id": 15575}, {"segmentation": [[50.0, 124.37, 12.5, 149.38, 3.75, 174.38, 17.5, 216.88, 23.75, 229.38, 1.25, 470.63, 53.75, 473.13, 76.25, 463.13, 68.75, 459.38, 41.25, 434.38, 160.0, 405.63, 172.5, 420.63, 185.0, 421.88, 193.75, 389.38, 170.0, 299.38, 137.5, 235.63, 117.5, 223.13, 101.25, 168.13, 101.25, 145.63, 55.0, 134.38]], "area": 41311.15, "iscrowd": 0, "image_id": 323728, "bbox": [1.25, 124.37, 192.5, 348.76], "category_id": 1, "id": 2151720, "split": "val", "sentences": [{"tokens": ["a", "girl", "with", "full", "sleeve", "and", "specs", "on", "eyes", ",", "reading", "a", "newspaper"], "raw": "A girl with full sleeve and specs on eyes, reading a newspaper", "sent_id": 27625, "sent": "a girl with full sleeve and specs on eyes , reading a newspaper"}, {"tokens": ["the", "woman", "on", "the", "left", "in", "the", "black", "sweater"], "raw": "The woman on the left in the black sweater.", "sent_id": 27626, "sent": "the woman on the left in the black sweater"}], "file_name": "COCO_train2014_000000323728_2151720.jpg", "ann_id": 2151720, "sent_ids": [27625, 27626], "ref_id": 15605}, {"segmentation": [[544.05, 125.06, 570.73, 108.86, 592.65, 125.06, 627.9, 140.3, 631.71, 171.74, 612.66, 209.86, 601.22, 239.39, 555.49, 252.73, 469.73, 245.11, 425.91, 229.87, 391.6, 188.89, 355.4, 177.46, 325.86, 150.78, 307.76, 105.05, 314.43, 87.9, 286.8, 57.41, 307.76, 48.83, 315.38, 84.09, 347.78, 84.09, 363.02, 74.56, 375.41, 85.99, 365.88, 98.38, 374.45, 109.81, 385.89, 115.53, 417.33, 106.95, 464.02, 107.91, 445.91, 126.01, 484.98, 132.68, 511.66, 139.35, 538.34, 129.82]], "area": 33351.0823, "iscrowd": 0, "image_id": 100485, "bbox": [286.8, 48.83, 344.91, 203.9], "category_id": 18, "id": 1403027, "split": "val", "sentences": [{"tokens": ["a", "dogs", "nose"], "raw": "A dogs nose.", "sent_id": 27639, "sent": "a dogs nose"}, {"tokens": ["pink", "and", "black", "snout", "of", "an", "animal", "with", "whiskers", "coming", "off", "it"], "raw": "Pink and black snout of an animal with whiskers coming off it.", "sent_id": 27640, "sent": "pink and black snout of an animal with whiskers coming off it"}], "file_name": "COCO_train2014_000000100485_1403027.jpg", "ann_id": 1403027, "sent_ids": [27639, 27640], "ref_id": 15611}, {"segmentation": [[270.27, 371.35, 335.14, 365.95, 336.22, 157.3, 297.3, 169.19, 278.92, 168.11, 233.51, 168.11, 235.68, 213.51, 248.65, 256.76, 272.43, 331.35, 287.57, 350.81], [362.16, 367.03, 391.35, 354.05, 394.59, 281.62, 419.46, 264.32, 393.51, 223.24, 379.46, 172.43, 344.86, 158.38]], "area": 24542.199399999998, "iscrowd": 0, "image_id": 75621, "bbox": [233.51, 157.3, 185.95, 214.05], "category_id": 6, "id": 365883, "split": "val", "sentences": [{"tokens": ["a", "double", "decker", "bus", "designated", "2246", "headed", "to", "arica"], "raw": "A double decker bus designated 2246 headed to Arica", "sent_id": 27644, "sent": "a double decker bus designated 2246 headed to arica"}, {"tokens": ["a", "yellow", "bus", "displaying", "arica"], "raw": "A yellow bus displaying ARICA", "sent_id": 27645, "sent": "a yellow bus displaying arica"}], "file_name": "COCO_train2014_000000075621_365883.jpg", "ann_id": 365883, "sent_ids": [27644, 27645], "ref_id": 15614}, {"segmentation": [[425.2, 232.96, 440.37, 232.54, 482.94, 238.01, 495.58, 238.44, 494.74, 201.77, 508.23, 159.2, 533.1, 133.49, 560.49, 115.78, 527.2, 116.63, 496.43, 126.32, 471.14, 145.71, 451.75, 167.63, 431.94, 195.87, 424.78, 221.58]], "area": 6777.459550000003, "iscrowd": 0, "image_id": 9185, "bbox": [424.78, 115.78, 135.71, 122.66], "category_id": 53, "id": 1047808, "split": "val", "sentences": [{"tokens": ["the", "reddish", "orange", "in", "the", "back", "from", "the", "right"], "raw": "The reddish orange in the back from the right.", "sent_id": 27646, "sent": "the reddish orange in the back from the right"}, {"tokens": ["apple", "furthest", "to", "the", "right"], "raw": "apple furthest to the right", "sent_id": 27647, "sent": "apple furthest to the right"}], "file_name": "COCO_train2014_000000009185_1047808.jpg", "ann_id": 1047808, "sent_ids": [27646, 27647], "ref_id": 15615}, {"segmentation": [[147.95, 226.27, 197.97, 137.43, 187.44, 117.03, 244.03, 159.81, 243.38, 163.75, 240.08, 169.68, 233.5, 178.23, 247.32, 190.08, 240.74, 197.32, 245.35, 203.24, 249.3, 207.85, 243.38, 209.82, 246.67, 223.64, 200.6, 201.92, 169.67, 234.17]], "area": 5275.224199999999, "iscrowd": 0, "image_id": 136092, "bbox": [147.95, 117.03, 101.35, 117.14], "category_id": 84, "id": 1655904, "split": "val", "sentences": [{"tokens": ["book", "on", "brown", "pant", "leg"], "raw": "Book on brown pant leg.", "sent_id": 27756, "sent": "book on brown pant leg"}, {"tokens": ["second", "persons", "pamphlet"], "raw": "second persons pamphlet", "sent_id": 27757, "sent": "second persons pamphlet"}], "file_name": "COCO_train2014_000000136092_1655904.jpg", "ann_id": 1655904, "sent_ids": [27756, 27757], "ref_id": 15656}, {"segmentation": [[300.42, 205.85, 348.72, 228.07, 361.28, 304.38, 399.92, 381.66, 417.31, 422.23, 22.22, 422.23, 28.01, 392.29, 26.08, 372.0, 18.35, 353.65, 18.35, 341.09, 21.25, 320.8, 34.78, 291.82, 55.06, 272.5, 56.99, 270.57, 70.52, 263.81, 80.18, 262.84, 85.97, 257.05, 89.84, 247.39, 89.84, 246.42, 89.84, 246.42, 89.84, 238.7, 89.84, 237.73, 74.38, 238.7, 69.55, 222.27, 67.62, 209.72, 56.99, 186.53, 53.13, 177.84, 53.13, 173.01, 53.13, 132.44, 62.79, 97.66, 72.45, 72.55, 86.94, 50.33, 104.33, 35.84, 117.85, 26.18, 137.17, 18.45, 159.39, 7.82, 187.4, 6.86, 204.79, 6.86, 221.21, 10.72, 232.8, 17.48, 235.7, 18.45, 240.53, 31.01, 253.09, 36.8, 264.68, 52.26, 275.31, 67.72, 282.07, 74.48, 287.86, 84.14, 293.66, 100.56, 302.35, 116.98, 303.32, 128.57, 304.29, 139.2, 304.29, 161.42, 304.29, 173.01, 307.18, 189.43]], "area": 113011.38565, "iscrowd": 0, "image_id": 102208, "bbox": [18.35, 6.86, 398.96, 415.37], "category_id": 1, "id": 466169, "split": "val", "sentences": [{"tokens": ["the", "blond", "boy"], "raw": "the blond boy", "sent_id": 27876, "sent": "the blond boy"}, {"tokens": ["a", "boy", "with", "blonde", "hair"], "raw": "A boy with blonde hair.", "sent_id": 27877, "sent": "a boy with blonde hair"}], "file_name": "COCO_train2014_000000102208_466169.jpg", "ann_id": 466169, "sent_ids": [27876, 27877], "ref_id": 15705}, {"segmentation": [[392.49, 383.94, 403.98, 374.37, 387.71, 360.97, 400.15, 349.48, 429.83, 345.65, 432.7, 337.99, 423.13, 337.99, 435.57, 311.19, 441.32, 299.7, 454.72, 290.13, 455.68, 279.6, 453.76, 270.98, 465.25, 264.28, 478.65, 267.15, 485.35, 283.43, 484.4, 293.0, 493.01, 294.91, 502.58, 299.7, 502.58, 317.89, 496.84, 325.55, 496.84, 339.91, 492.05, 360.97, 488.22, 363.84, 477.69, 359.05, 464.29, 359.05, 453.76, 360.97, 447.06, 369.58, 446.1, 377.24, 440.36, 383.94, 432.7, 390.64, 423.13, 381.07, 421.21, 379.16, 421.21, 383.94, 417.38, 389.69, 404.94, 389.69, 396.32, 387.77]], "area": 6929.782100000001, "iscrowd": 0, "image_id": 162396, "bbox": [387.71, 264.28, 114.87, 126.36], "category_id": 1, "id": 218835, "split": "val", "sentences": [{"tokens": ["the", "sitting", "man", "with", "the", "camera"], "raw": "The sitting man with the camera", "sent_id": 27888, "sent": "the sitting man with the camera"}, {"tokens": ["a", "man", "with", "a", "camera"], "raw": "A man with a camera.", "sent_id": 27889, "sent": "a man with a camera"}], "file_name": "COCO_train2014_000000162396_218835.jpg", "ann_id": 218835, "sent_ids": [27888, 27889], "ref_id": 15709}, {"segmentation": [[468.4, 220.25, 469.36, 258.72, 503.98, 276.04, 521.29, 277.96, 569.38, 266.42, 604.01, 252.95, 590.54, 224.1, 574.19, 214.48, 553.03, 230.83, 546.3, 225.06, 567.46, 208.71, 544.38, 200.05, 518.41, 199.09, 489.56, 207.75, 465.51, 219.29], [519.37, 287.58, 528.03, 306.81, 554.96, 305.85, 581.89, 290.46, 588.62, 279.88, 549.19, 284.69, 517.45, 285.65]], "area": 8781.07385, "iscrowd": 0, "image_id": 541338, "bbox": [465.51, 199.09, 138.5, 107.72], "category_id": 51, "id": 1039307, "split": "val", "sentences": [{"tokens": ["small", "bowl", "of", "soup"], "raw": "small bowl of soup", "sent_id": 28015, "sent": "small bowl of soup"}, {"tokens": ["a", "bowl", "of", "soup", "behind", "a", "bowl", "of", "pasta"], "raw": "A bowl of soup behind a bowl of pasta.", "sent_id": 28016, "sent": "a bowl of soup behind a bowl of pasta"}], "file_name": "COCO_train2014_000000541338_1039307.jpg", "ann_id": 1039307, "sent_ids": [28015, 28016], "ref_id": 15761}, {"segmentation": [[268.34, 122.83, 255.43, 91.26, 255.43, 58.26, 271.21, 45.35, 294.17, 46.78, 304.22, 58.26, 312.83, 78.35, 307.09, 108.48, 331.48, 128.57, 360.18, 151.53, 387.44, 223.28, 380.27, 249.11, 357.31, 254.85, 354.44, 379.7, 353.0, 418.44, 347.26, 533.24, 342.96, 594.94, 341.52, 604.99, 295.61, 615.03, 288.43, 603.55, 295.61, 587.77, 289.87, 576.29, 226.73, 576.29, 215.25, 564.81, 242.51, 557.63, 242.51, 540.41, 255.43, 527.5, 238.21, 475.84, 226.73, 300.77, 220.99, 257.72, 192.29, 234.76, 192.29, 206.06, 226.73, 171.62, 243.95, 138.62, 262.6, 127.14]], "area": 63472.837550000004, "iscrowd": 0, "image_id": 421887, "bbox": [192.29, 45.35, 195.15, 569.68], "category_id": 1, "id": 195366, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "coveralls", "standing", "next", "to", "a", "the", "wing", "of", "a", "plane"], "raw": "A man in coveralls standing next to a the wing of a plane.", "sent_id": 28037, "sent": "a man in coveralls standing next to a the wing of a plane"}, {"tokens": ["a", "man", "in", "a", "pilot", "suit", "standing", "next", "to", "an", "airplane"], "raw": "A man in a pilot suit standing next to an airplane.", "sent_id": 28038, "sent": "a man in a pilot suit standing next to an airplane"}], "file_name": "COCO_train2014_000000421887_195366.jpg", "ann_id": 195366, "sent_ids": [28037, 28038], "ref_id": 15767}, {"segmentation": [[47.46, 469.21, 59.33, 430.38, 85.21, 395.87, 98.16, 358.11, 100.31, 318.2, 121.89, 288.0, 166.11, 247.01, 225.44, 224.36, 244.85, 127.28, 257.8, 113.26, 239.46, 122.97, 240.54, 111.1, 242.7, 94.92, 266.43, 85.21, 268.58, 79.82, 314.97, 81.98, 338.7, 81.98, 363.51, 83.06, 384.0, 103.55, 405.57, 113.26, 413.12, 138.07, 414.2, 158.56, 407.73, 173.66, 396.94, 183.37, 396.94, 202.79, 390.47, 222.2, 387.24, 231.91, 387.24, 262.11, 372.13, 272.9, 364.58, 286.92, 357.03, 289.08, 350.56, 306.34, 344.09, 310.65, 335.46, 310.65, 309.57, 355.96, 288.0, 405.57, 288.0, 442.25, 290.16, 463.82, 201.71, 480.0]], "area": 78288.82629999999, "iscrowd": 0, "image_id": 544701, "bbox": [47.46, 79.82, 366.74, 400.18], "category_id": 1, "id": 481846, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "spiky", "hair", "looking", "at", "a", "box", "of", "desserts"], "raw": "A man with spiky hair looking at a box of desserts.", "sent_id": 28061, "sent": "a man with spiky hair looking at a box of desserts"}, {"tokens": ["man", "with", "blue", "shirt"], "raw": "man with blue shirt", "sent_id": 28062, "sent": "man with blue shirt"}], "file_name": "COCO_train2014_000000544701_481846.jpg", "ann_id": 481846, "sent_ids": [28061, 28062], "ref_id": 15774}, {"segmentation": [[105.13, 208.18, 225.96, 202.68, 208.7, 164.24, 167.9, 159.53, 233.02, 161.89, 220.47, 165.81, 243.22, 200.33, 392.29, 171.3, 484.09, 162.67, 520.96, 174.44, 528.81, 190.91, 477.81, 212.88, 474.67, 230.93, 466.04, 231.71, 466.04, 215.24, 317.76, 215.24, 323.25, 225.44, 318.54, 231.71, 302.06, 231.71, 298.93, 218.37, 279.31, 220.73, 283.23, 228.57, 277.74, 233.28, 263.62, 234.07, 261.27, 227.01, 91.01, 211.31]], "area": 13882.020449999996, "iscrowd": 0, "image_id": 192137, "bbox": [91.01, 159.53, 437.8, 74.54], "category_id": 5, "id": 158475, "split": "val", "sentences": [{"tokens": ["a", "plane", "with", "a", "red", "and", "white", "stripes", "on", "the", "tail"], "raw": "A plane with a red and white stripes on the tail", "sent_id": 28153, "sent": "a plane with a red and white stripes on the tail"}, {"tokens": ["long", "airplane", "with", "a", "blue", "strip", "down", "the", "side", "parked", "first", "in", "a", "sequence", "of", "planes"], "raw": "Long airplane with a blue strip down the side parked first in a sequence of planes.", "sent_id": 28154, "sent": "long airplane with a blue strip down the side parked first in a sequence of planes"}], "file_name": "COCO_train2014_000000192137_158475.jpg", "ann_id": 158475, "sent_ids": [28153, 28154], "ref_id": 15799}, {"segmentation": [[266.48, 133.98, 357.07, 135.14, 366.36, 147.33, 373.32, 168.24, 373.9, 169.98, 408.74, 163.59, 415.71, 173.46, 414.55, 177.53, 551.59, 166.49, 553.91, 195.53, 554.49, 201.91, 515.59, 207.72, 515.0, 214.11, 515.0, 217.01, 526.62, 218.75, 535.33, 221.08, 544.62, 225.14, 553.33, 227.46, 549.26, 236.75, 513.84, 247.21, 480.17, 252.43, 424.42, 243.72, 424.42, 246.04, 408.16, 249.53, 422.68, 257.08, 422.68, 261.14, 416.29, 267.53, 409.91, 271.59, 401.2, 278.56, 394.23, 275.08, 387.26, 265.79, 376.23, 269.85, 370.42, 274.5, 366.94, 291.92, 359.97, 297.72, 340.23, 297.72, 339.07, 297.72, 320.48, 291.33, 316.42, 282.63, 314.1, 271.59, 314.1, 262.3, 313.52, 254.75, 296.1, 254.75, 282.16, 257.08, 266.48, 264.04, 242.68, 262.88, 212.48, 262.3, 182.29, 265.21, 199.33, 253.01, 188.3, 240.82, 188.3, 222.24, 191.79, 203.08, 221.98, 161.85, 224.3, 149.07, 236.5, 138.62, 246.95, 135.72]], "area": 37101.043, "iscrowd": 0, "image_id": 43609, "bbox": [182.29, 133.98, 372.2, 163.74], "category_id": 8, "id": 400915, "split": "val", "sentences": [{"tokens": ["brown", "truck"], "raw": "Brown truck.", "sent_id": 28284, "sent": "brown truck"}, {"tokens": ["an", "old", "rusty", "flatbed", "pick", "up", "truck"], "raw": "An old rusty flatbed pick up truck", "sent_id": 28285, "sent": "an old rusty flatbed pick up truck"}], "file_name": "COCO_train2014_000000043609_400915.jpg", "ann_id": 400915, "sent_ids": [28284, 28285], "ref_id": 15847}, {"segmentation": [[316.24, 198.91, 319.05, 163.36, 326.53, 103.48, 326.53, 92.25, 296.59, 66.99, 258.23, 66.05, 208.64, 69.8, 106.66, 84.77, 117.89, 90.38, 110.4, 94.12, 110.4, 101.61, 129.12, 103.48, 136.6, 103.48, 136.6, 107.22, 126.31, 107.22, 120.7, 107.22, 129.12, 117.51, 147.83, 120.32, 159.99, 119.39, 130.99, 129.68, 144.09, 137.16, 177.77, 127.81, 156.25, 139.97, 143.15, 143.71, 145.96, 148.39, 172.15, 148.39, 159.99, 158.68, 166.54, 167.1, 189.0, 167.1, 203.03, 173.65, 245.13, 168.97, 257.3, 167.1, 262.91, 176.46, 263.85, 197.98, 269.46, 212.95, 267.59, 241.95, 258.23, 282.18, 233.91, 310.25, 225.48, 313.06, 203.97, 323.35, 193.67, 332.71, 189.0, 335.51, 199.29, 336.45, 203.03, 336.45, 198.35, 344.87, 203.97, 350.48, 211.45, 354.23, 226.42, 357.03, 241.39, 365.45, 268.52, 371.07, 279.75, 375.75, 278.82, 390.72, 274.14, 399.14, 270.39, 412.24, 278.82, 406.62, 288.17, 403.81, 304.08, 407.56, 308.76, 401.94, 320.92, 401.01, 292.85, 389.78, 290.98, 389.78, 299.4, 374.81, 324.66, 372.94, 338.7, 369.2, 352.73, 393.52, 351.79, 402.88, 349.92, 414.11, 346.18, 421.59, 346.18, 424.4, 344.31, 429.08, 343.37, 432.82, 363.96, 436.0, 376.12, 436.0, 379.86, 436.0, 384.54, 426.27, 393.9, 428.14, 387.35, 419.72, 362.09, 397.27, 343.37, 361.71, 348.99, 355.16, 374.25, 340.19, 364.89, 328.03, 364.89, 314.93, 363.96, 307.45, 364.89, 290.6, 372.38, 277.51, 368.64, 248.5, 367.7, 244.76, 370.51, 231.66, 371.44, 223.24, 371.44, 200.78, 379.86, 182.07, 395.77, 170.84, 400.45, 169.91, 419.16, 184.88, 429.45, 207.33, 431.32, 220.43, 467.81, 226.98, 494.01, 241.95, 511.79, 251.31, 498.69, 234.47, 517.4, 239.15, 529.56, 259.73, 536.11, 266.28, 520.21, 234.47, 496.82, 214.82, 494.01, 206.4, 514.59, 219.5, 536.11, 241.95, 548.27, 260.66, 552.95, 260.66, 534.24, 223.24, 514.59, 200.78, 473.42, 153.07, 445.36, 119.39, 429.45, 107.22, 443.48, 99.74, 458.45, 99.74, 466.88, 99.74, 488.39, 112.84, 505.24, 133.42, 528.63, 145.58, 540.79, 154.0, 530.5, 116.58, 503.36, 89.45, 480.91, 77.28, 445.36, 73.54, 415.42, 78.22, 387.35, 89.45, 352.73, 152.13, 351.79, 152.13, 342.44, 184.88, 336.82, 223.24, 334.95, 233.53, 324.66, 225.11, 313.43, 212.01, 316.24, 200.78]], "area": 59795.65955000002, "iscrowd": 0, "image_id": 533050, "bbox": [106.66, 66.05, 446.29, 369.95], "category_id": 16, "id": 43597, "split": "val", "sentences": [{"tokens": ["the", "nearest", "seagull"], "raw": "The nearest seagull.", "sent_id": 28315, "sent": "the nearest seagull"}, {"tokens": ["the", "painted", "seagull", "in", "nearer", "than", "the", "other", "seagull"], "raw": "the painted seagull in nearer than the other seagull", "sent_id": 28316, "sent": "the painted seagull in nearer than the other seagull"}], "file_name": "COCO_train2014_000000533050_43597.jpg", "ann_id": 43597, "sent_ids": [28315, 28316], "ref_id": 15858}, {"segmentation": [[570.95, 413.83, 565.42, 395.02, 559.89, 375.1, 546.61, 329.74, 555.46, 262.24, 558.78, 201.38, 570.95, 167.08, 576.48, 139.42, 566.52, 113.97, 588.65, 79.67, 615.21, 79.67, 636.23, 80.77, 640.0, 113.97, 640.0, 388.38, 640.0, 410.51, 638.45, 420.47, 600.83, 419.36, 583.12, 419.36]], "area": 26455.267, "iscrowd": 0, "image_id": 454144, "bbox": [546.61, 79.67, 93.39, 340.8], "category_id": 1, "id": 2154921, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "blue", "full", "sleeves", "and", "hand", "inside", "pocket"], "raw": "A man with blue full sleeves and hand inside pocket", "sent_id": 28364, "sent": "a man with blue full sleeves and hand inside pocket"}, {"tokens": ["man", "in", "blue", "coat"], "raw": "man in blue coat", "sent_id": 28365, "sent": "man in blue coat"}], "file_name": "COCO_train2014_000000454144_2154921.jpg", "ann_id": 2154921, "sent_ids": [28364, 28365], "ref_id": 15878}, {"segmentation": [[126.07, 503.03, 112.47, 470.9, 118.65, 435.06, 98.88, 416.52, 96.4, 302.81, 101.35, 232.36, 67.98, 217.53, 87.75, 156.97, 79.1, 135.96, 103.82, 100.11, 139.66, 80.34, 163.15, 34.61, 195.28, 30.9, 221.24, 35.84, 234.83, 75.39, 237.3, 161.91, 208.88, 280.56, 203.93, 373.26, 190.34, 427.64, 198.99, 477.08, 205.17, 495.62, 176.74, 501.8, 156.97, 454.83, 163.15, 391.8, 160.67, 343.6, 139.66, 422.7, 137.19, 473.37]], "area": 49355.945900000006, "iscrowd": 0, "image_id": 487992, "bbox": [67.98, 30.9, 169.32, 472.13], "category_id": 1, "id": 461644, "split": "val", "sentences": [{"tokens": ["the", "man", "wearing", "the", "long", "black", "wig", "with", "sunglasses", "on"], "raw": "the man wearing the long black wig with sunglasses on", "sent_id": 28394, "sent": "the man wearing the long black wig with sunglasses on"}, {"tokens": ["a", "man", "with", "a", "lady", "holding", "glass"], "raw": "A MAN WITH A LADY HOLDING GLASS", "sent_id": 28395, "sent": "a man with a lady holding glass"}], "file_name": "COCO_train2014_000000487992_461644.jpg", "ann_id": 461644, "sent_ids": [28394, 28395], "ref_id": 15891}, {"segmentation": [[152.48, 298.63, 187.92, 252.45, 236.24, 236.35, 291.01, 225.61, 335.03, 233.12, 372.62, 257.82, 394.09, 295.41, 408.05, 338.36, 417.72, 389.9, 377.99, 437.15, 320.0, 474.73, 226.58, 468.29, 173.96, 431.78, 155.7, 392.05, 151.41, 334.06]], "area": 51906.2389, "iscrowd": 0, "image_id": 87792, "bbox": [151.41, 225.61, 266.31, 249.12], "category_id": 60, "id": 1081823, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "donut"], "raw": "A dark brown donut", "sent_id": 28396, "sent": "a dark brown donut"}, {"tokens": ["dark", "brown", "glazed", "donut"], "raw": "Dark brown glazed donut", "sent_id": 28397, "sent": "dark brown glazed donut"}], "file_name": "COCO_train2014_000000087792_1081823.jpg", "ann_id": 1081823, "sent_ids": [28396, 28397], "ref_id": 15892}, {"segmentation": [[306.51, 257.22, 341.42, 234.78, 367.17, 228.14, 465.22, 211.52, 507.59, 205.7, 523.38, 215.67, 545.81, 242.26, 526.7, 248.08, 523.38, 255.56, 481.83, 258.88, 377.14, 277.16, 330.61, 281.31, 314.0, 287.13, 305.68, 257.22]], "area": 10628.95475, "iscrowd": 0, "image_id": 477580, "bbox": [305.68, 205.7, 240.13, 81.43], "category_id": 44, "id": 94161, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "wine", "laying", "down", "amongst", "the", "veggies"], "raw": "a bottle of wine laying down amongst the veggies", "sent_id": 28526, "sent": "a bottle of wine laying down amongst the veggies"}, {"tokens": ["a", "bottle", "of", "wine", "between", "the", "vegetables"], "raw": "A bottle of wine between the vegetables", "sent_id": 28527, "sent": "a bottle of wine between the vegetables"}], "file_name": "COCO_train2014_000000477580_94161.jpg", "ann_id": 94161, "sent_ids": [28526, 28527], "ref_id": 15940}, {"segmentation": [[348.9, 231.96, 352.7, 222.46, 354.6, 210.1, 357.45, 193.94, 354.6, 184.43, 347.0, 179.68, 338.44, 176.83, 340.34, 166.37, 342.24, 157.81, 349.85, 152.11, 356.5, 148.3, 367.91, 135.0, 377.42, 123.59, 395.48, 125.49, 406.89, 126.44, 413.54, 136.9, 416.39, 142.6, 425.9, 142.6, 446.82, 137.85, 471.53, 128.34, 492.45, 121.69, 507.66, 117.88, 512.41, 112.18, 517.17, 100.77, 532.38, 93.17, 547.59, 98.87, 550.44, 102.67, 556.14, 108.38, 559.0, 115.98, 559.0, 123.59, 555.19, 131.19, 542.83, 135.95, 532.38, 138.8, 530.48, 138.8, 522.87, 126.44, 518.12, 122.64, 496.25, 129.29, 481.04, 136.9, 470.58, 146.4, 464.88, 157.81, 455.37, 168.27, 442.06, 174.92, 442.06, 183.48, 444.91, 189.18, 441.11, 195.84, 431.61, 206.3, 415.44, 233.87, 409.74, 242.42, 397.38, 264.29, 392.63, 271.89, 389.78, 290.91, 391.68, 301.36, 397.38, 319.43, 394.53, 340.34, 396.43, 355.55, 399.28, 357.45, 395.48, 359.35, 378.37, 361.26, 345.09, 361.26, 343.19, 355.55, 351.75, 351.75, 359.35, 347.0, 369.81, 340.34, 372.66, 324.18, 368.86, 307.07, 364.11, 276.65, 364.11, 270.94, 367.91, 258.58, 369.81, 250.03, 373.61, 241.47, 380.27, 236.72, 359.35, 248.13, 353.65, 248.13, 351.75, 231.96]], "area": 15509.589250000005, "iscrowd": 0, "image_id": 530925, "bbox": [338.44, 93.17, 220.56, 268.09], "category_id": 1, "id": 427217, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "red", "jersey", "and", "white", "pants", "holding", "a", "mitt", "behind", "him", "and", "balancing", "on", "one", "foot"], "raw": "A man wearing a red jersey and white pants holding a mitt behind him and balancing on one foot", "sent_id": 28540, "sent": "a man wearing a red jersey and white pants holding a mitt behind him and balancing on one foot"}, {"tokens": ["a", "pitcher"], "raw": "A pitcher.", "sent_id": 28541, "sent": "a pitcher"}], "file_name": "COCO_train2014_000000530925_427217.jpg", "ann_id": 427217, "sent_ids": [28540, 28541], "ref_id": 15944}, {"segmentation": [[284.76, 359.01, 284.76, 341.75, 281.53, 320.18, 281.53, 314.79, 281.53, 306.16, 281.53, 267.33, 269.66, 252.22, 267.51, 238.2, 243.78, 197.21, 237.3, 177.8, 234.07, 156.22, 226.52, 154.07, 221.12, 142.2, 217.89, 137.89, 208.18, 130.34, 209.26, 123.87, 201.71, 121.71, 182.29, 118.47, 176.9, 122.79, 171.51, 134.65, 170.43, 142.2, 170.43, 156.22, 171.51, 159.46, 175.82, 167.01, 189.84, 172.4, 192.0, 177.8, 190.92, 189.66, 190.92, 201.53, 195.24, 212.31, 200.63, 228.49, 202.79, 248.99, 200.63, 253.3, 211.42, 270.56, 218.97, 284.58, 223.28, 292.13, 234.07, 301.84, 244.85, 308.31, 253.48, 318.02, 266.43, 339.6, 280.45, 349.3, 282.61, 355.78]], "area": 11524.088149999998, "iscrowd": 0, "image_id": 136331, "bbox": [170.43, 118.47, 114.33, 240.54], "category_id": 1, "id": 525253, "split": "val", "sentences": [{"tokens": ["the", "woman", "in", "the", "background", "leaning", "on", "the", "counter"], "raw": "The woman in the background leaning on the counter.", "sent_id": 28544, "sent": "the woman in the background leaning on the counter"}, {"tokens": ["a", "lady", "in", "the", "kitchen", "is", "watching", "something", "else", "instead", "of", "cooking"], "raw": "A lady in the kitchen is watching something else instead of cooking", "sent_id": 28545, "sent": "a lady in the kitchen is watching something else instead of cooking"}], "file_name": "COCO_train2014_000000136331_525253.jpg", "ann_id": 525253, "sent_ids": [28544, 28545], "ref_id": 15946}, {"segmentation": [[45.3, 253.48, 107.87, 244.85, 114.34, 279.37, 106.79, 283.69, 119.73, 308.49, 183.37, 268.58, 217.89, 241.62, 256.72, 228.67, 262.11, 217.89, 251.33, 185.53, 281.53, 165.03, 303.1, 177.98, 324.67, 165.03, 351.64, 168.27, 355.96, 187.69, 351.64, 207.1, 337.62, 217.89, 336.54, 225.44, 341.93, 232.99, 357.03, 225.44, 355.96, 214.65, 366.74, 218.97, 376.45, 203.87, 408.81, 209.26, 437.93, 230.83, 436.85, 248.09, 494.02, 277.21, 499.42, 285.84, 512.36, 257.8, 490.79, 245.93, 503.73, 208.18, 573.84, 220.04, 556.58, 269.66, 519.91, 262.11, 508.04, 305.26, 423.91, 273.98, 407.73, 277.21, 410.97, 291.24, 405.57, 298.79, 389.39, 290.16, 375.37, 289.08, 375.37, 312.81, 419.6, 372.13, 418.52, 431.46, 422.83, 474.61, 305.26, 473.53, 217.89, 473.53, 209.26, 444.4, 210.34, 358.11, 262.11, 322.52, 256.72, 294.47, 247.01, 284.76, 241.62, 277.21, 234.07, 304.18, 222.2, 310.65, 212.49, 296.63, 214.65, 289.08, 201.71, 286.92, 166.11, 307.42, 121.89, 332.22, 100.31, 290.16, 42.07, 302.02, 34.52, 251.33]], "area": 65483.67590000001, "iscrowd": 0, "image_id": 182642, "bbox": [34.52, 165.03, 539.32, 309.58], "category_id": 4, "id": 152420, "split": "val", "sentences": [{"tokens": ["the", "motorcycle", "closest", "to", "the", "camera"], "raw": "The motorcycle closest to the camera.", "sent_id": 28612, "sent": "the motorcycle closest to the camera"}, {"tokens": ["the", "motorcycle", "handlebars", "and", "gas", "tank", "in", "the", "front"], "raw": "the motorcycle handlebars and gas tank in the front", "sent_id": 28613, "sent": "the motorcycle handlebars and gas tank in the front"}], "file_name": "COCO_train2014_000000182642_152420.jpg", "ann_id": 152420, "sent_ids": [28612, 28613], "ref_id": 15974}, {"segmentation": [[164.42, 324.48, 205.99, 227.81, 206.96, 205.57, 204.06, 196.87, 197.29, 171.74, 191.49, 146.6, 204.06, 106.0, 237.89, 38.33, 251.43, 26.73, 273.66, 1.6, 373.48, 6.74, 382.92, 35.06, 381.57, 381.57, 382.92, 556.85, 377.53, 567.64, 369.44, 570.34, 113.26, 571.69, 141.57, 536.63, 152.36, 528.54, 164.49, 525.84, 233.26, 513.71, 250.79, 502.92, 287.19, 458.43, 307.42, 428.76, 322.25, 396.4, 341.12, 362.7, 338.43, 355.96, 319.55, 342.47, 304.72, 341.12, 292.58, 347.87, 271.01, 372.13, 227.87, 384.27, 180.67, 372.13, 163.15, 333.03]], "area": 91496.85840000003, "iscrowd": 0, "image_id": 181681, "bbox": [113.26, 1.6, 269.66, 570.09], "category_id": 23, "id": 586234, "split": "val", "sentences": [{"tokens": ["a", "mother", "white", "polar", "bear", "with", "her", "baby", "nuzzling", "her"], "raw": "A mother white polar bear with her baby nuzzling her.", "sent_id": 28620, "sent": "a mother white polar bear with her baby nuzzling her"}, {"tokens": ["the", "big", "mama", "bear"], "raw": "The big mama bear", "sent_id": 28621, "sent": "the big mama bear"}], "file_name": "COCO_train2014_000000181681_586234.jpg", "ann_id": 586234, "sent_ids": [28620, 28621], "ref_id": 15978}, {"segmentation": [[249.69, 283.55, 222.42, 240.5, 220.99, 145.79, 236.77, 111.35, 251.12, 97.0, 284.13, 79.78, 324.3, 89.83, 337.22, 105.61, 355.87, 127.14, 367.35, 142.92, 384.57, 241.94, 373.09, 283.55, 400.36, 454.31, 398.92, 474.4, 387.44, 485.88, 363.05, 477.27, 368.79, 454.31, 358.74, 438.53, 334.35, 320.86, 318.57, 320.86, 298.48, 316.56, 295.61, 309.38, 301.35, 302.21, 314.26, 302.21, 324.3, 302.21, 324.3, 290.73, 299.91, 270.64, 284.13, 264.9, 272.65, 266.33]], "area": 35338.80509999999, "iscrowd": 0, "image_id": 102030, "bbox": [220.99, 79.78, 179.37, 406.1], "category_id": 1, "id": 228282, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "blue", "jeans", ",", "a", "brown", "vest", ",", "a", "tan", "shirt", "and", "hat", ",", "holding", "the", "face", "of", "a", "sheep", "that", "has", "just", "been", "shorn"], "raw": "A man wearing blue jeans, a brown vest, a tan shirt and hat, holding the face of a sheep that has just been shorn.", "sent_id": 28670, "sent": "a man wearing blue jeans , a brown vest , a tan shirt and hat , holding the face of a sheep that has just been shorn"}, {"tokens": ["a", "man", "wearing", "a", "hat", "petting", "a", "goat"], "raw": "A man wearing a hat petting a goat", "sent_id": 28671, "sent": "a man wearing a hat petting a goat"}], "file_name": "COCO_train2014_000000102030_228282.jpg", "ann_id": 228282, "sent_ids": [28670, 28671], "ref_id": 16000}, {"segmentation": [[135.47, 102.93, 126.61, 122.41, 129.27, 149.85, 184.16, 152.51, 229.32, 163.13, 249.68, 192.35, 268.27, 241.93, 347.07, 262.3, 356.81, 293.29, 341.76, 303.03, 336.45, 303.03, 325.82, 287.09, 301.03, 283.55, 292.18, 280.01, 270.93, 287.97, 245.25, 287.97, 221.35, 267.61, 216.92, 278.23, 206.3, 284.43, 251.45, 295.94, 278.01, 297.71, 278.01, 314.54, 270.04, 326.05, 254.99, 334.9, 235.51, 316.31, 208.07, 325.16, 193.9, 325.16, 165.57, 313.65, 159.37, 290.63, 169.11, 257.87, 163.8, 241.05, 162.91, 226.88, 129.27, 228.65, 97.39, 202.09, 84.11, 218.91, 36.3, 216.26, 24.79, 190.58, 32.76, 164.9, 54.89, 159.59, 77.91, 165.79, 82.34, 132.14, 90.31, 121.52, 83.23, 98.5, 105.36, 77.25, 121.3, 77.25, 130.15, 90.53]], "area": 30114.679849999997, "iscrowd": 0, "image_id": 408081, "bbox": [24.79, 77.25, 332.02, 257.65], "category_id": 1, "id": 492747, "split": "val", "sentences": [{"tokens": ["a", "skateboarder", "headed", "down", "a", "ramp", "with", "the", "sky", "in", "the", "background"], "raw": "A skateboarder headed down a ramp with the sky in the background.", "sent_id": 28738, "sent": "a skateboarder headed down a ramp with the sky in the background"}, {"tokens": ["person", "on", "the", "skateboard"], "raw": "person on the skateboard", "sent_id": 28739, "sent": "person on the skateboard"}], "file_name": "COCO_train2014_000000408081_492747.jpg", "ann_id": 492747, "sent_ids": [28738, 28739], "ref_id": 16027}, {"segmentation": [[239.82, 304.24, 229.91, 327.03, 205.14, 330.01, 183.34, 335.95, 190.27, 344.87, 227.93, 367.67, 347.84, 335.95, 370.64, 267.57, 348.84, 270.55, 239.82, 298.29]], "area": 9444.51095, "iscrowd": 0, "image_id": 281840, "bbox": [183.34, 267.57, 187.3, 100.1], "category_id": 73, "id": 1101892, "split": "val", "sentences": [{"tokens": ["the", "black", "laptop", "that", "the", "woman", "is", "holding"], "raw": "The black laptop that the woman is holding.", "sent_id": 28789, "sent": "the black laptop that the woman is holding"}, {"tokens": ["the", "black", "laptop"], "raw": "the black laptop", "sent_id": 28790, "sent": "the black laptop"}], "file_name": "COCO_train2014_000000281840_1101892.jpg", "ann_id": 1101892, "sent_ids": [28789, 28790], "ref_id": 16047}, {"segmentation": [[202.79, 379.69, 181.21, 433.62, 155.33, 428.22, 136.99, 410.97, 131.6, 395.87, 114.34, 367.82, 104.63, 345.17, 89.53, 337.62, 76.58, 331.15, 58.25, 328.99, 46.38, 312.81, 30.2, 289.08, 35.6, 251.33, 44.22, 221.12, 59.33, 201.71, 67.96, 188.76, 65.8, 175.82, 52.85, 165.03, 35.6, 148.85, 32.36, 129.44, 50.7, 114.34, 57.17, 117.57, 72.27, 99.24, 99.24, 93.84, 121.89, 77.66, 140.22, 83.06, 145.62, 112.18, 169.35, 140.22, 183.37, 157.48, 209.26, 169.35, 234.07, 184.45, 245.93, 215.73, 262.11, 226.52, 262.11, 249.17, 280.45, 285.84, 280.45, 319.28, 283.69, 348.4, 271.82, 358.11, 240.54, 341.93, 230.83, 337.62, 225.44, 335.46, 228.67, 294.47, 181.21, 283.69, 167.19, 298.79, 173.66, 323.6, 210.34, 371.06]], "area": 49760.3815, "iscrowd": 0, "image_id": 443916, "bbox": [30.2, 77.66, 253.49, 355.96], "category_id": 88, "id": 1674436, "split": "val", "sentences": [{"tokens": ["stuffed", "black", "bear", "wearing", "yellow", "t", "shirt", "with", "orange", "pumkin", "on", "shirt"], "raw": "stuffed black bear wearing yellow t shirt with orange pumkin on shirt", "sent_id": 28850, "sent": "stuffed black bear wearing yellow t shirt with orange pumkin on shirt"}, {"tokens": ["the", "huge", "toy", "bear", "seated", "with", "a", "jack", "-", "o", "-", "lantern", "on", "one", "side", "of", "its", "body"], "raw": "The huge toy bear seated with a jack-o-lantern on one side of its body.", "sent_id": 28851, "sent": "the huge toy bear seated with a jack - o - lantern on one side of its body"}], "file_name": "COCO_train2014_000000443916_1674436.jpg", "ann_id": 1674436, "sent_ids": [28850, 28851], "ref_id": 16072}, {"segmentation": [[264.65, 45.04, 281.46, 30.48, 307.24, 18.15, 356.54, 31.6, 368.87, 61.85, 375.59, 88.75, 389.04, 114.52, 398.0, 162.71, 395.76, 169.43, 385.68, 163.83, 374.47, 143.66, 363.27, 123.49, 358.78, 103.32, 347.58, 111.16, 362.15, 131.33, 364.39, 160.47, 353.18, 147.02, 343.1, 122.37, 334.13, 90.99, 318.44, 70.82, 300.51, 54.01, 274.74, 52.89, 255.69, 54.01, 254.57, 42.8]], "area": 7142.785299999997, "iscrowd": 0, "image_id": 137173, "bbox": [254.57, 18.15, 143.43, 151.28], "category_id": 19, "id": 1404238, "split": "val", "sentences": [{"tokens": ["a", "light", "brown", "horse", "directly", "behind", "the", "dark", "brown", "horse", "and", "girl"], "raw": "A light brown horse directly behind the dark brown horse and girl.", "sent_id": 28873, "sent": "a light brown horse directly behind the dark brown horse and girl"}, {"tokens": ["a", "horse", "that", "is", "behind", "the", "other", "horse"], "raw": "A horse that is behind the other horse.", "sent_id": 28874, "sent": "a horse that is behind the other horse"}], "file_name": "COCO_train2014_000000137173_1404238.jpg", "ann_id": 1404238, "sent_ids": [28873, 28874], "ref_id": 16083}, {"segmentation": [[107.61, 120.22, 125.55, 112.74, 136.77, 103.77, 151.72, 111.99, 156.96, 125.45, 155.46, 137.41, 178.64, 139.66, 186.87, 162.84, 197.33, 181.53, 206.31, 218.17, 225.75, 291.44, 245.94, 365.47, 229.49, 368.46, 208.55, 321.35, 174.9, 235.37, 165.18, 214.43, 149.48, 187.51, 121.81, 189.75, 95.64, 187.51, 91.16, 163.58, 119.57, 160.59, 108.36, 138.16, 103.12, 118.72]], "area": 11136.8223, "iscrowd": 0, "image_id": 509914, "bbox": [91.16, 103.77, 154.78, 264.69], "category_id": 1, "id": 207700, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "on", "bike"], "raw": "A man sitting on bike", "sent_id": 28912, "sent": "a man sitting on bike"}, {"tokens": ["a", "man", "hanging", "out", "on", "a", "motorcycle", "wearing", "a", "ball", "cap"], "raw": "A man hanging out on a motorcycle wearing a ball cap", "sent_id": 28913, "sent": "a man hanging out on a motorcycle wearing a ball cap"}], "file_name": "COCO_train2014_000000509914_207700.jpg", "ann_id": 207700, "sent_ids": [28912, 28913], "ref_id": 16099}, {"segmentation": [[332.77, 223.69, 344.59, 231.17, 372.16, 240.23, 385.55, 258.74, 387.91, 283.55, 388.7, 302.85, 393.03, 307.97, 394.61, 315.06, 391.06, 323.72, 391.06, 372.95, 395.39, 385.95, 377.28, 387.53, 365.86, 381.22, 374.52, 369.8, 372.16, 335.54, 362.7, 304.82, 344.98, 289.46, 343.8, 281.58, 326.47, 281.58, 325.29, 323.33, 320.96, 382.41, 303.63, 383.19, 306.39, 374.13, 310.72, 368.62, 310.72, 336.33, 302.84, 293.0, 295.36, 273.31, 290.24, 263.86, 294.18, 242.59, 295.36, 230.38, 288.66, 207.93, 284.72, 185.88, 281.97, 171.7, 263.06, 176.03, 262.67, 171.7, 269.36, 161.86, 269.36, 157.52, 274.48, 153.58, 278.42, 140.59, 281.18, 139.8, 284.72, 148.07, 289.84, 148.07, 303.24, 141.38, 302.84, 149.25, 297.72, 157.13, 306.78, 172.49, 316.63, 200.85, 331.59, 218.96]], "area": 11438.925799999999, "iscrowd": 0, "image_id": 177959, "bbox": [262.67, 139.8, 132.72, 247.73], "category_id": 25, "id": 1414574, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "next", "to", "zebra", "in", "a", "zoo"], "raw": "A giraffe next to zebra in a zoo.", "sent_id": 28926, "sent": "a giraffe next to zebra in a zoo"}, {"tokens": ["a", "giraffe", "next", "to", "a", "zebra"], "raw": "A giraffe next to a zebra", "sent_id": 28927, "sent": "a giraffe next to a zebra"}], "file_name": "COCO_train2014_000000177959_1414574.jpg", "ann_id": 1414574, "sent_ids": [28926, 28927], "ref_id": 16105}, {"segmentation": [[463.82, 213.57, 450.88, 239.46, 447.64, 272.9, 460.58, 255.64, 468.13, 229.75, 474.61, 270.74, 464.9, 304.18, 464.9, 355.96, 478.92, 366.74, 483.24, 355.96, 489.71, 351.64, 482.16, 294.47, 503.73, 262.11, 547.96, 271.82, 533.93, 353.8, 538.25, 345.17, 558.74, 271.82, 580.31, 279.37, 586.79, 303.1, 587.87, 322.52, 593.26, 346.25, 608.36, 345.17, 605.12, 325.75, 626.7, 353.8, 618.07, 321.44, 613.75, 302.02, 632.09, 296.63, 608.36, 273.98, 605.12, 213.57, 584.63, 198.47, 554.43, 197.39, 512.36, 202.79, 491.87, 194.16]], "area": 14756.106750000006, "iscrowd": 0, "image_id": 292271, "bbox": [447.64, 194.16, 184.45, 172.58], "category_id": 24, "id": 588928, "split": "val", "sentences": [{"tokens": ["the", "zebra", "eating", "grass", "on", "the", "right", "that", "is", "not", "next", "to", "any", "animals"], "raw": "The zebra eating grass on the right that is not next to any animals", "sent_id": 28933, "sent": "the zebra eating grass on the right that is not next to any animals"}, {"tokens": ["a", "zebra", "eating", "grass", "in", "front", "of", "several", "other", "eating", "animals"], "raw": "a zebra eating grass in front of several other eating animals", "sent_id": 28934, "sent": "a zebra eating grass in front of several other eating animals"}], "file_name": "COCO_train2014_000000292271_588928.jpg", "ann_id": 588928, "sent_ids": [28933, 28934], "ref_id": 16109}, {"segmentation": [[258.53, 27.33, 220.15, 87.41, 191.79, 134.14, 141.73, 147.48, 160.08, 179.19, 170.92, 193.38, 176.77, 209.23, 163.41, 230.09, 126.7, 233.43, 99.17, 240.93, 63.29, 265.13, 54.94, 282.65, 61.62, 288.5, 54.11, 320.2, 65.8, 353.58, 86.65, 374.44, 121.7, 385.29, 179.27, 371.93, 205.13, 342.73, 213.48, 335.22, 221.82, 316.03, 239.34, 329.38, 248.52, 334.38, 275.23, 331.88, 281.9, 321.04, 288.58, 325.21, 309.44, 327.72, 322.78, 364.43, 333.64, 366.93, 330.3, 360.25, 318.61, 326.88, 347.82, 316.86, 347.82, 311.85, 346.15, 305.19, 360.33, 301.01, 376.18, 291.83, 388.7, 297.67, 442.1, 287.66, 466.3, 280.15, 531.38, 254.28, 548.9, 236.76, 548.9, 206.73, 538.06, 192.54, 514.69, 176.68, 516.36, 145.81, 498.84, 136.64, 489.66, 135.81, 485.49, 136.64, 456.29, 129.13, 427.92, 132.47, 397.04, 130.8, 382.03, 139.13, 360.33, 132.47, 370.35, 127.46, 366.17, 108.27, 355.32, 104.93, 344.48, 112.44, 332.8, 113.27, 329.46, 114.11, 326.12, 120.78, 291.91, 129.13, 260.2, 129.96, 260.2, 124.95, 291.91, 114.11, 303.59, 104.93, 296.91, 99.09, 294.42, 92.41, 291.91, 89.91, 290.24, 42.34, 271.89, 24.82]], "area": 87094.08145, "iscrowd": 0, "image_id": 475441, "bbox": [54.11, 24.82, 494.79, 360.47], "category_id": 4, "id": 151898, "split": "val", "sentences": [{"tokens": ["red", "motorcycle", "with", "a", "black", "seat"], "raw": "Red motorcycle with a black seat.", "sent_id": 28945, "sent": "red motorcycle with a black seat"}, {"tokens": ["a", "red", "and", "black", "motorcycle", "parked", "outside"], "raw": "a red and black motorcycle parked outside", "sent_id": 28946, "sent": "a red and black motorcycle parked outside"}], "file_name": "COCO_train2014_000000475441_151898.jpg", "ann_id": 151898, "sent_ids": [28945, 28946], "ref_id": 16115}, {"segmentation": [[230.27, 63.24, 255.14, 90.27, 385.95, 104.32, 433.51, 95.68, 465.95, 81.62, 459.46, 56.76, 383.78, 38.38, 327.57, 34.05, 271.35, 43.78, 240.0, 50.27]], "area": 11968.81475, "iscrowd": 0, "image_id": 539941, "bbox": [230.27, 34.05, 235.68, 70.27], "category_id": 59, "id": 1076580, "split": "val", "sentences": [{"tokens": ["a", "pizza", "in", "the", "background", "with", "ham", "on", "it"], "raw": "A pizza in the background with ham on it", "sent_id": 29016, "sent": "a pizza in the background with ham on it"}, {"tokens": ["a", "pizza", "covered", "in", "red", "onions", "on", "a", "wooden", "platter", "behind", "a", "pepperoni", "pizza"], "raw": "A pizza covered in red onions on a wooden platter behind a pepperoni pizza", "sent_id": 29017, "sent": "a pizza covered in red onions on a wooden platter behind a pepperoni pizza"}], "file_name": "COCO_train2014_000000539941_1076580.jpg", "ann_id": 1076580, "sent_ids": [29016, 29017], "ref_id": 16142}, {"segmentation": [[208.4, 231.24, 230.25, 166.63, 268.47, 153.89, 281.21, 166.63, 286.67, 194.84, 280.3, 195.75, 271.2, 204.85, 262.1, 205.76, 283.94, 247.63, 266.65, 284.94, 238.44, 305.87, 217.51, 312.24, 226.61, 320.43, 244.81, 322.25, 250.27, 337.72, 222.97, 331.35, 210.22, 333.17, 204.76, 321.34, 180.19, 353.19, 172.91, 349.55, 175.64, 319.52, 151.98, 312.24, 185.65, 258.55]], "area": 12741.16945, "iscrowd": 0, "image_id": 400850, "bbox": [151.98, 153.89, 134.69, 199.3], "category_id": 16, "id": 41518, "split": "val", "sentences": [{"tokens": ["green", "bird"], "raw": "green bird", "sent_id": 29041, "sent": "green bird"}, {"tokens": ["bird", "on", "left"], "raw": "bird on left", "sent_id": 29042, "sent": "bird on left"}], "file_name": "COCO_train2014_000000400850_41518.jpg", "ann_id": 41518, "sent_ids": [29041, 29042], "ref_id": 16152}, {"segmentation": [[311.12, 164.25, 310.33, 152.46, 311.9, 143.83, 311.9, 143.83, 303.25, 139.89, 303.25, 139.11, 303.25, 131.25, 303.25, 127.32, 304.83, 125.74, 310.33, 123.39, 311.9, 122.6, 316.62, 118.67, 322.9, 117.11, 333.91, 115.53, 351.19, 114.75, 355.91, 114.75, 370.84, 114.75, 383.41, 117.11, 395.2, 119.46, 405.42, 123.39, 409.35, 126.53, 415.64, 128.89, 427.42, 134.39, 432.14, 137.53, 431.35, 143.83, 427.42, 150.11, 421.92, 154.04, 417.99, 157.97, 414.85, 165.04, 414.85, 172.9, 414.85, 179.18, 413.28, 189.4, 410.92, 190.19, 409.35, 190.97, 404.63, 192.55, 401.49, 194.91, 397.56, 193.33, 393.63, 188.62, 390.49, 186.26, 381.85, 180.76, 377.13, 176.04, 376.34, 175.26, 363.77, 172.11, 357.48, 168.97, 345.7, 164.25, 329.97, 162.68, 323.69, 162.68, 318.98, 162.68, 320.54, 163.47]], "area": 6357.441800000003, "iscrowd": 0, "image_id": 254176, "bbox": [303.25, 114.75, 128.89, 80.16], "category_id": 88, "id": 1674464, "split": "val", "sentences": [{"tokens": ["a", "stuffed", "bear", "riding", "sidecar", "on", "a", "motorcycle"], "raw": "A stuffed bear riding sidecar on a motorcycle.", "sent_id": 29185, "sent": "a stuffed bear riding sidecar on a motorcycle"}, {"tokens": ["a", "teddy", "bear", "doll", "wearing", "glasses"], "raw": "A teddy bear doll wearing glasses", "sent_id": 29186, "sent": "a teddy bear doll wearing glasses"}], "file_name": "COCO_train2014_000000254176_1674464.jpg", "ann_id": 1674464, "sent_ids": [29185, 29186], "ref_id": 16205}, {"segmentation": [[168.43, 411.34, 150.7, 289.75, 139.72, 255.96, 149.85, 232.32, 175.19, 210.92, 200.52, 101.99, 227.54, 70.18, 274.83, 63.43, 339.85, 96.36, 363.49, 148.71, 361.8, 187.56, 396.43, 206.98, 416.69, 237.67, 408.25, 301.0, 288.34, 311.98, 255.41, 334.78, 258.79, 367.71, 217.41, 363.49, 208.96, 371.93, 198.83, 375.31, 214.88, 396.71, 222.47, 413.6, 197.99, 412.75]], "area": 56061.308650000006, "iscrowd": 0, "image_id": 45226, "bbox": [139.72, 63.43, 276.97, 350.17], "category_id": 1, "id": 494243, "split": "val", "sentences": [{"tokens": ["a", "woman", "blowing", "out", "birthday", "candles"], "raw": "A woman blowing out birthday candles", "sent_id": 29222, "sent": "a woman blowing out birthday candles"}, {"tokens": ["a", "woman", "wearing", "thick", "glasses", "blows", "out", "the", "candles", "on", "her", "birthday", "cake"], "raw": "A woman wearing thick glasses blows out the candles on her birthday cake.", "sent_id": 29223, "sent": "a woman wearing thick glasses blows out the candles on her birthday cake"}], "file_name": "COCO_train2014_000000045226_494243.jpg", "ann_id": 494243, "sent_ids": [29222, 29223], "ref_id": 16221}, {"segmentation": [[343.73, 631.37, 360.99, 572.4, 290.52, 501.93, 245.93, 448.72, 202.79, 381.12, 194.16, 359.55, 178.34, 373.93, 159.64, 376.81, 146.7, 391.19, 148.13, 415.64, 149.57, 422.83, 132.31, 434.34, 100.67, 440.09, 87.73, 427.15, 84.85, 419.96, 93.48, 395.51, 69.03, 373.93, 73.35, 345.17, 70.47, 317.84, 89.17, 289.08, 90.61, 261.75, 80.54, 253.12, 83.42, 244.49, 70.47, 234.43, 66.16, 234.43, 66.16, 230.11, 73.35, 221.48, 40.27, 212.85, 4.31, 159.64, 5.75, 146.7, 40.27, 145.26, 80.54, 153.89, 94.92, 175.46, 96.36, 117.93, 87.73, 60.4, 117.93, 40.27, 122.25, 48.9, 135.19, 89.17, 143.82, 123.69, 155.33, 125.12, 162.52, 119.37, 169.71, 107.87, 178.34, 89.17, 178.34, 73.35, 181.21, 57.53, 184.09, 48.9, 201.35, 48.9, 215.73, 53.21, 215.73, 60.4, 209.98, 73.35, 209.98, 83.42, 207.1, 96.36, 207.1, 106.43, 207.1, 116.49, 207.1, 123.69, 211.42, 135.19, 211.42, 148.13, 215.73, 159.64, 221.48, 171.15, 228.67, 171.15, 238.74, 162.52, 243.06, 152.45, 248.81, 143.82, 257.44, 136.63, 263.19, 135.19, 273.26, 132.31, 286.2, 130.88, 296.27, 129.44, 302.02, 129.44, 323.6, 128.0, 325.03, 135.19, 322.16, 148.13, 316.4, 156.76, 309.21, 168.27, 306.34, 175.46, 300.58, 189.84, 293.39, 198.47, 280.45, 205.66, 258.88, 212.85, 251.69, 214.29, 237.3, 214.29, 232.99, 218.61, 232.99, 228.67, 235.87, 240.18, 253.12, 250.25, 258.88, 253.12, 266.07, 261.75, 268.94, 271.82, 271.82, 271.82, 283.33, 280.45, 294.83, 289.08, 304.9, 306.34, 304.9, 309.21, 307.78, 306.34, 316.4, 310.65, 320.72, 322.16, 332.22, 326.47, 342.29, 329.35, 343.73, 332.22, 350.92, 342.29, 356.67, 352.36, 365.3, 359.55, 371.06, 366.74, 376.81, 372.49, 379.69, 378.25, 394.07, 385.44, 398.38, 378.25, 407.01, 375.37, 414.2, 379.69, 422.83, 384.0, 424.27, 384.0, 428.58, 384.0, 434.0, 385.44, 434.0, 398.38, 434.0, 496.18]], "area": 97197.81735000006, "iscrowd": 0, "image_id": 564812, "bbox": [4.31, 40.27, 429.69, 591.1], "category_id": 25, "id": 596273, "split": "val", "sentences": [{"tokens": ["a", "geraffee", "was", "eting", "in", "grass"], "raw": "a geraffee was eting in grass", "sent_id": 29328, "sent": "a geraffee was eting in grass"}, {"tokens": ["he", "had", "a", "neck", "of", "the", "beautiful", "giraffe", "who", "is", "chewing", "on", "some", "food", "in", "his", "pen"], "raw": "He had a neck of the beautiful giraffe who is chewing on some food in his pen.", "sent_id": 29329, "sent": "he had a neck of the beautiful giraffe who is chewing on some food in his pen"}], "file_name": "COCO_train2014_000000564812_596273.jpg", "ann_id": 596273, "sent_ids": [29328, 29329], "ref_id": 16258}, {"segmentation": [[149.81, 119.94, 157.72, 70.92, 160.88, 28.22, 164.05, 9.25, 164.05, 4.5, 369.63, 10.83, 409.16, 10.83, 447.12, 10.83, 456.6, 9.25, 448.7, 47.2, 440.79, 63.01, 445.53, 97.8, 474.0, 118.36, 480.33, 145.25, 466.09, 181.62, 458.19, 187.94, 445.53, 164.22, 424.98, 127.85, 423.4, 145.25, 436.05, 203.76, 372.79, 176.87, 331.67, 176.87, 300.05, 175.29, 277.91, 173.71, 244.7, 176.87, 217.81, 184.78, 213.07, 184.78, 211.49, 129.43, 190.93, 172.13, 167.21, 178.46, 140.33, 176.87, 140.33, 156.32, 140.33, 131.01, 149.81, 110.46], [113.44, 123.11, 108.7, 99.39, 91.3, 96.22, 83.4, 88.32, 66.0, 86.73, 51.77, 86.73, 43.86, 97.8, 40.7, 113.62, 78.65, 127.85, 97.63, 123.11, 107.12, 105.71]], "area": 53344.40409999999, "iscrowd": 0, "image_id": 153814, "bbox": [40.7, 4.5, 439.63, 199.26], "category_id": 1, "id": 2160528, "split": "val", "sentences": [{"tokens": ["the", "woman", "with", "the", "black", "tank", "top", "is", "sitting", "in", "front", "of", "a", "pizza", "that", "is", "on", "the", "table"], "raw": "The woman with  the black tank top is sitting in front of a pizza that is on the table.", "sent_id": 29355, "sent": "the woman with the black tank top is sitting in front of a pizza that is on the table"}, {"tokens": ["a", "lady", "with", "black", "tee", "on", "a", "resturant"], "raw": "A lady with black tee on a resturant", "sent_id": 29356, "sent": "a lady with black tee on a resturant"}], "file_name": "COCO_train2014_000000153814_2160528.jpg", "ann_id": 2160528, "sent_ids": [29355, 29356], "ref_id": 16266}, {"segmentation": [[127.52, 327.34, 127.52, 285.0, 140.99, 267.04, 141.95, 256.77, 134.25, 237.2, 134.9, 220.85, 147.59, 207.29, 150.54, 203.16, 165.3, 198.43, 179.76, 198.14, 193.34, 202.86, 209.28, 207.29, 226.4, 212.6, 243.22, 210.53, 257.39, 211.72, 267.13, 219.39, 282.18, 239.17, 294.29, 247.43, 307.86, 246.25, 316.42, 253.61, 322.33, 261.58, 335.31, 263.65, 344.76, 266.6, 349.48, 279.58, 349.19, 286.67, 338.56, 297.0, 325.57, 300.54, 317.6, 299.07, 296.94, 313.82, 288.97, 313.82, 285.43, 309.1, 286.02, 301.43, 287.5, 296.7, 287.79, 291.98, 290.15, 286.67, 278.05, 288.14, 268.61, 287.55, 255.62, 292.57, 252.96, 293.16, 255.03, 304.38, 254.14, 316.19, 252.96, 333.3, 261.52, 345.11, 262.7, 348.95, 252.96, 351.31, 250.01, 346.0, 247.35, 341.86, 244.7, 338.62, 245.58, 312.64, 243.22, 299.66, 241.45, 298.77, 240.27, 317.07, 236.73, 325.93, 234.37, 342.75, 237.91, 353.67, 238.79, 360.76, 224.92, 360.46, 225.22, 349.83, 221.97, 343.93, 226.69, 334.78, 229.94, 318.55, 229.64, 299.36, 224.63, 286.96, 203.37, 281.95, 190.68, 279.29, 181.83, 277.81, 173.27, 274.57, 164.12, 289.32, 161.17, 301.13, 165.89, 317.96, 175.92, 330.94, 179.76, 339.21, 167.36, 338.32, 165.3, 333.01, 159.69, 331.83, 157.33, 328.58, 156.15, 316.19, 148.47, 295.52, 144.93, 292.28, 142.27, 291.69, 137.55, 304.97, 138.44, 324.74, 144.34, 340.39, 141.39, 342.75, 134.9, 342.75, 131.94, 338.62, 129.58, 332.71, 127.22, 327.4]], "area": 16985.1573, "iscrowd": 0, "image_id": 338819, "bbox": [127.22, 198.14, 222.26, 162.62], "category_id": 20, "id": 65326, "split": "val", "sentences": [{"tokens": ["the", "ram", "on", "the", "left", "who", "is", "head", "butting", "another", "ram", "standing", "in", "the", "middle", "of", "the", "road"], "raw": "The ram on the left who is head butting another ram standing in the middle of the road.", "sent_id": 29409, "sent": "the ram on the left who is head butting another ram standing in the middle of the road"}, {"tokens": ["ram", "on", "left", "butting", "other", "ram"], "raw": "ram on left butting other ram", "sent_id": 29410, "sent": "ram on left butting other ram"}], "file_name": "COCO_train2014_000000338819_65326.jpg", "ann_id": 65326, "sent_ids": [29409, 29410], "ref_id": 16288}, {"segmentation": [[225.95, 51.35, 109.19, 104.32, 50.81, 132.43, 18.38, 182.16, 8.65, 196.22, 1.08, 192.97, 0.0, 304.32, 48.65, 355.14, 109.19, 391.89, 151.35, 423.24, 197.84, 449.19, 290.81, 470.81, 638.92, 472.97, 640.0, 61.08, 621.62, 66.49, 610.81, 66.49, 587.03, 60.0, 501.62, 45.95, 396.76, 52.43, 294.05, 58.92, 263.78, 54.59]], "area": 236240.53220000002, "iscrowd": 0, "image_id": 555358, "bbox": [0.0, 45.95, 640.0, 427.02], "category_id": 59, "id": 1074388, "split": "val", "sentences": [{"tokens": ["pizza", "with", "broccoli", "topping"], "raw": "pizza with broccoli topping", "sent_id": 29540, "sent": "pizza with broccoli topping"}, {"tokens": ["a", "pizza", "with", "cheese", ",", "sauce", "and", "broccoli"], "raw": "A pizza with cheese, sauce and broccoli.", "sent_id": 29541, "sent": "a pizza with cheese , sauce and broccoli"}], "file_name": "COCO_train2014_000000555358_1074388.jpg", "ann_id": 1074388, "sent_ids": [29540, 29541], "ref_id": 16337}, {"segmentation": [[99.01, 296.99, 86.1, 316.36, 94.71, 382.01, 68.88, 384.16, 51.66, 392.77, 38.74, 389.54, 26.91, 377.7, 27.98, 363.71, 19.37, 354.03, 11.84, 333.58, 15.07, 272.23, 16.14, 227.03, 22.6, 201.2, 36.59, 183.98, 64.57, 160.3, 104.39, 145.24, 153.9, 129.09, 208.79, 128.02, 291.66, 129.09, 313.18, 149.54, 332.56, 188.29, 351.93, 211.96, 388.52, 213.04, 432.65, 208.74, 454.17, 205.51, 466.01, 205.51, 464.93, 213.04, 443.41, 222.73, 392.83, 235.64, 356.23, 237.79, 314.26, 239.95, 311.03, 245.33, 283.05, 233.49, 248.61, 233.49, 249.69, 258.24, 262.6, 298.06, 260.45, 357.26, 244.3, 359.41, 230.31, 354.03, 217.4, 365.87, 209.87, 368.02, 181.88, 364.79, 171.12, 354.03, 175.43, 333.58, 180.81, 296.99, 182.96, 277.61]], "area": 57768.79220000001, "iscrowd": 0, "image_id": 298639, "bbox": [11.84, 128.02, 454.17, 264.75], "category_id": 22, "id": 582581, "split": "val", "sentences": [{"tokens": ["an", "elephant", "standing", "at", "the", "edge", "of", "some", "water", "and", "tapping", "another", "elephant", "with", "it", "'", "s", "trunk"], "raw": "An elephant standing at the edge of some water and tapping another elephant with it's trunk.", "sent_id": 29609, "sent": "an elephant standing at the edge of some water and tapping another elephant with it ' s trunk"}, {"tokens": ["elephant", "standing", "next", "to", "water", "hole", "with", "trunk", "on", "baby", "elephant"], "raw": "Elephant standing next to water hole with trunk on baby elephant", "sent_id": 29610, "sent": "elephant standing next to water hole with trunk on baby elephant"}], "file_name": "COCO_train2014_000000298639_582581.jpg", "ann_id": 582581, "sent_ids": [29609, 29610], "ref_id": 16364}, {"segmentation": [[458.67, 94.04, 503.76, 145.85, 541.19, 204.38, 572.85, 253.32, 581.49, 287.87, 565.18, 295.54, 527.75, 303.22, 515.28, 308.98, 488.41, 307.06, 467.3, 298.42, 448.11, 283.07, 400.13, 304.18, 379.02, 296.5, 372.31, 284.99, 358.87, 263.88, 354.07, 244.69, 359.83, 217.82, 363.67, 195.75, 363.67, 188.07, 361.75, 173.68, 342.56, 166.0, 341.6, 151.61, 344.48, 143.93, 355.03, 129.54, 363.67, 120.9, 367.51, 108.43, 372.31, 95.96, 384.78, 78.68, 406.85, 71.97, 429.88, 71.97, 452.91, 79.64, 458.67, 86.36, 466.34, 95.96]], "area": 36918.08460000001, "iscrowd": 0, "image_id": 313724, "bbox": [341.6, 71.97, 239.89, 237.01], "category_id": 23, "id": 586760, "split": "val", "sentences": [{"tokens": ["bear", "on", "right"], "raw": "bear on right", "sent_id": 29699, "sent": "bear on right"}, {"tokens": ["a", "bear", "attacking"], "raw": "a bear attacking", "sent_id": 29700, "sent": "a bear attacking"}], "file_name": "COCO_train2014_000000313724_586760.jpg", "ann_id": 586760, "sent_ids": [29699, 29700], "ref_id": 16398}, {"segmentation": [[0.49, 342.28, 22.34, 339.41, 26.33, 338.61, 40.53, 338.29, 63.67, 340.37, 67.02, 339.89, 74.35, 341.16, 77.55, 344.35, 81.37, 355.68, 85.04, 362.22, 90.79, 376.58, 91.43, 379.77, 92.06, 382.8, 91.75, 386.15, 90.15, 388.39, 90.15, 389.5, 91.27, 392.7, 91.59, 395.73, 92.06, 396.52, 100.04, 396.21, 106.42, 400.19, 111.37, 404.66, 120.3, 411.84, 131.31, 415.51, 137.69, 416.15, 140.25, 416.31, 143.44, 419.5, 142.48, 421.89, 142.48, 422.21, 145.99, 426.52, 149.02, 435.13, 149.66, 441.84, 149.82, 452.05, 148.22, 458.27, 148.22, 463.53, 148.22, 468.48, 148.86, 474.7, 150.14, 480.0, 0.39, 480.0]], "area": 16500.9785, "iscrowd": 0, "image_id": 212635, "bbox": [0.39, 338.29, 149.75, 141.71], "category_id": 63, "id": 117893, "split": "val", "sentences": [{"tokens": ["brown", "chair", "left", "side"], "raw": "brown chair left side.", "sent_id": 29701, "sent": "brown chair left side"}, {"tokens": ["brown", "sofa"], "raw": "brown sofa", "sent_id": 29702, "sent": "brown sofa"}], "file_name": "COCO_train2014_000000212635_117893.jpg", "ann_id": 117893, "sent_ids": [29701, 29702], "ref_id": 16399}, {"segmentation": [[196.59, 624.22, 200.9, 588.34, 187.98, 516.59, 200.9, 520.9, 213.81, 507.98, 200.9, 467.8, 231.03, 444.84, 252.56, 441.97, 271.21, 444.84, 287.0, 452.02, 297.04, 437.67, 299.91, 410.4, 302.78, 381.7, 314.26, 374.53, 337.22, 373.09, 345.83, 391.75, 367.35, 387.44, 365.92, 398.92, 350.13, 420.45, 340.09, 490.76, 341.52, 548.16, 342.96, 629.96, 344.39, 629.96, 328.61, 631.39, 309.96, 563.95, 285.56, 572.56, 287.0, 629.96, 269.78, 628.52, 268.34, 582.6, 256.86, 611.3, 255.43, 629.96, 236.77, 629.96, 236.77, 599.82, 235.34, 553.9, 218.12, 631.39, 199.46, 629.96]], "area": 26427.34029999999, "iscrowd": 0, "image_id": 22287, "bbox": [187.98, 373.09, 179.37, 258.3], "category_id": 24, "id": 592576, "split": "val", "sentences": [{"tokens": ["a", "zebra", "which", "is", "near", "the", "giraffe"], "raw": "A zebra which is near the giraffe", "sent_id": 29759, "sent": "a zebra which is near the giraffe"}, {"tokens": ["zebra", "standing", "next", "to", "a", "giraffe"], "raw": "Zebra standing next to a giraffe", "sent_id": 29760, "sent": "zebra standing next to a giraffe"}], "file_name": "COCO_train2014_000000022287_592576.jpg", "ann_id": 592576, "sent_ids": [29759, 29760], "ref_id": 16418}, {"segmentation": [[640.0, 246.98, 598.31, 147.42, 578.21, 103.39, 553.32, 76.58, 511.2, 54.57, 480.57, 46.91, 436.53, 47.87, 381.01, 67.01, 341.76, 138.81, 340.8, 168.49, 344.63, 202.95, 350.37, 235.5, 360.9, 279.53, 371.43, 321.65, 415.47, 386.75, 423.13, 402.07, 427.91, 413.56, 436.53, 416.43, 640.0, 418.34, 640.0, 259.43]], "area": 90157.92564999999, "iscrowd": 0, "image_id": 102208, "bbox": [340.8, 46.91, 299.2, 371.43], "category_id": 1, "id": 1247149, "split": "val", "sentences": [{"tokens": ["a", "brown", "haired", "girl", "with", "an", "orange", "in", "her", "mouth"], "raw": "a brown haired girl with an orange in her mouth", "sent_id": 29905, "sent": "a brown haired girl with an orange in her mouth"}, {"tokens": ["girl"], "raw": "girl", "sent_id": 29906, "sent": "girl"}], "file_name": "COCO_train2014_000000102208_1247149.jpg", "ann_id": 1247149, "sent_ids": [29905, 29906], "ref_id": 16474}, {"segmentation": [[226.26, 335.39, 213.01, 348.64, 218.81, 370.16, 217.15, 375.12, 224.6, 418.99, 244.47, 478.58, 255.23, 503.41, 263.5, 517.48, 268.47, 541.48, 275.92, 542.31, 303.23, 527.41, 310.68, 524.93, 325.58, 533.21, 329.72, 541.48, 336.34, 538.17, 350.41, 536.52, 359.51, 553.9, 286.68, 557.0, 242.81, 552.24, 236.19, 519.96, 231.22, 516.65, 231.22, 510.86, 234.53, 508.38, 218.81, 462.03, 202.26, 382.57, 197.29, 341.19]], "area": 6124.471150000001, "iscrowd": 0, "image_id": 535358, "bbox": [197.29, 335.39, 162.22, 221.61], "category_id": 31, "id": 1434073, "split": "val", "sentences": [{"tokens": ["man", "'", "s", "black", "shoulder", "bag"], "raw": "Man's black shoulder bag.", "sent_id": 29938, "sent": "man ' s black shoulder bag"}, {"tokens": ["the", "bag", "over", "the", "shoulder", "of", "the", "man", "closest", "to", "the", "horse"], "raw": "The bag over the shoulder of the man closest to the horse.", "sent_id": 29939, "sent": "the bag over the shoulder of the man closest to the horse"}], "file_name": "COCO_train2014_000000535358_1434073.jpg", "ann_id": 1434073, "sent_ids": [29938, 29939], "ref_id": 16487}, {"segmentation": [[375.0, 241.65, 354.86, 228.46, 347.88, 212.93, 344.77, 203.62, 330.03, 221.47, 333.13, 230.78, 330.8, 239.32, 327.7, 244.76, 323.82, 247.08, 302.08, 230.01, 310.62, 212.16, 313.73, 205.17, 298.98, 195.08, 310.62, 175.67, 319.94, 174.12, 322.26, 160.15, 333.91, 149.28, 346.33, 139.19, 344.77, 119.01, 333.91, 107.37, 323.82, 94.18, 339.34, 89.52, 344.0, 82.53, 350.98, 74.77, 359.52, 68.56, 364.95, 63.9, 373.49, 62.35]], "area": 7769.548050000002, "iscrowd": 0, "image_id": 396042, "bbox": [298.98, 62.35, 76.02, 184.73], "category_id": 64, "id": 25066, "split": "val", "sentences": [{"tokens": ["glass", "window", "pane", "on", "the", "side", "of", "a", "cat", "sitting", "in", "bottom", "of", "a", "flower", "pot"], "raw": "Glass window pane on the side of a cat sitting in bottom of a flower pot.", "sent_id": 29960, "sent": "glass window pane on the side of a cat sitting in bottom of a flower pot"}, {"tokens": ["the", "lighter", "colored", "green", "plant"], "raw": "the lighter colored green plant", "sent_id": 29961, "sent": "the lighter colored green plant"}], "file_name": "COCO_train2014_000000396042_25066.jpg", "ann_id": 25066, "sent_ids": [29960, 29961], "ref_id": 16495}, {"segmentation": [[279.03, 223.13, 286.15, 187.9, 308.26, 173.65, 305.26, 189.4, 296.27, 196.89, 289.9, 212.63, 278.65, 235.49, 260.66, 228.75, 256.91, 223.5, 270.78, 224.25, 279.03, 223.13], [305.26, 153.04, 317.63, 146.29, 325.5, 145.54, 331.5, 155.66, 342.37, 152.67, 346.12, 152.67, 329.62, 129.43, 334.5, 124.93, 356.98, 130.55, 364.85, 135.05, 369.35, 133.18, 372.35, 129.8, 369.35, 123.81, 365.23, 121.18, 351.36, 120.81, 346.49, 120.43, 340.49, 120.06, 331.12, 118.93, 319.51, 121.18, 318.38, 121.93, 312.76, 120.81, 306.76, 120.81, 303.76, 117.06, 297.39, 114.81, 293.64, 112.56, 284.65, 124.93, 289.52, 130.18, 293.27, 139.17, 299.64, 144.42, 301.14, 144.42]], "area": 2418.28765, "iscrowd": 0, "image_id": 268197, "bbox": [256.91, 112.56, 115.44, 122.93], "category_id": 1, "id": 525147, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "surfing", "board", "standing", "back", "of", "other", "man"], "raw": "A man with surfing board standing back of other man", "sent_id": 29982, "sent": "a man with surfing board standing back of other man"}, {"tokens": ["an", "sea", "skater", "skating", "on", "the", "long", "waves"], "raw": "An sea skater skating on the long waves", "sent_id": 29983, "sent": "an sea skater skating on the long waves"}], "file_name": "COCO_train2014_000000268197_525147.jpg", "ann_id": 525147, "sent_ids": [29982, 29983], "ref_id": 16503}, {"segmentation": [[144.15, 146.42, 134.35, 151.32, 147.58, 165.53, 167.66, 177.28, 193.62, 179.73, 296.98, 177.77, 345.96, 176.3, 442.46, 175.32, 492.91, 172.39, 552.18, 164.06, 579.13, 152.3, 580.6, 143.98, 585.0, 136.14, 576.19, 134.18, 561.98, 134.67, 540.92, 134.67, 530.14, 145.44, 530.14, 153.28, 529.65, 159.16, 516.43, 163.57, 510.55, 162.59, 508.59, 152.3, 467.44, 153.77, 459.6, 156.71, 454.71, 158.67, 447.85, 158.18, 422.87, 153.77, 414.05, 154.75, 397.39, 160.63, 383.68, 157.2, 376.82, 156.22, 377.8, 165.04, 362.62, 167.0, 362.13, 155.73, 349.39, 155.73, 342.53, 156.22, 336.65, 164.06, 325.88, 164.06, 324.41, 157.69, 320.0, 157.69, 318.04, 161.12, 302.86, 164.55, 301.39, 159.16, 291.1, 156.71, 286.2, 161.12, 286.2, 164.55, 268.08, 166.51, 266.12, 157.69, 241.63, 156.71, 181.86, 155.73, 170.11, 154.75, 159.33, 154.75, 148.56, 152.79]], "area": 8355.035249999997, "iscrowd": 0, "image_id": 501493, "bbox": [134.35, 134.18, 450.65, 45.55], "category_id": 9, "id": 179965, "split": "val", "sentences": [{"tokens": ["a", "long", "white", "boat"], "raw": "A long white boat.", "sent_id": 30008, "sent": "a long white boat"}, {"tokens": ["boat"], "raw": "boat", "sent_id": 30009, "sent": "boat"}], "file_name": "COCO_train2014_000000501493_179965.jpg", "ann_id": 179965, "sent_ids": [30008, 30009], "ref_id": 16512}, {"segmentation": [[122.11, 296.5, 96.63, 297.16, 65.26, 318.07, 67.22, 318.07, 89.44, 343.55, 112.31, 348.78, 148.91, 363.81, 156.75, 367.73, 161.98, 352.7, 158.71, 326.56, 158.06, 301.08, 143.03, 301.08], [231.25, 318.07, 278.95, 337.02, 310.32, 355.32, 331.88, 370.35, 335.8, 379.5, 335.15, 398.45, 317.51, 398.45, 270.46, 398.45, 231.25, 391.91, 227.98, 384.72, 229.94, 374.27, 218.18, 339.63, 218.83, 307.61]], "area": 10754.94405, "iscrowd": 0, "image_id": 342585, "bbox": [65.26, 296.5, 270.54, 101.95], "category_id": 42, "id": 652130, "split": "val", "sentences": [{"tokens": ["a", "surfboard", "being", "held", "by", "a", "man"], "raw": "a surfboard being held by a man", "sent_id": 30179, "sent": "a surfboard being held by a man"}, {"tokens": ["a", "surf", "board", "held", "by", "a", "man", "who", "is", "looking", "at", "water"], "raw": "A surf board held by a man who is looking at water.", "sent_id": 30180, "sent": "a surf board held by a man who is looking at water"}], "file_name": "COCO_train2014_000000342585_652130.jpg", "ann_id": 652130, "sent_ids": [30179, 30180], "ref_id": 16581}, {"segmentation": [[502.49, 404.49, 484.12, 401.94, 483.61, 394.29, 484.12, 387.15, 471.88, 376.94, 472.39, 372.86, 478.51, 368.78, 483.61, 352.45, 482.59, 339.7, 476.98, 327.96, 468.82, 320.31, 471.37, 311.12, 473.41, 301.94, 483.61, 285.61, 486.67, 266.73, 491.27, 254.49, 492.29, 249.89, 493.31, 244.28, 503.0, 233.57, 509.12, 225.91, 518.31, 223.36, 523.92, 228.46, 522.9, 247.34, 518.82, 250.4, 528.51, 267.75, 547.39, 286.12, 555.55, 292.75, 551.47, 293.77, 536.68, 288.16, 535.66, 293.26, 540.25, 294.79, 540.76, 297.86, 533.1, 298.37, 522.9, 292.75, 512.7, 292.24, 510.65, 303.98, 512.7, 314.18, 515.76, 328.98, 517.29, 347.86, 516.27, 352.96, 500.96, 366.23, 491.78, 372.86, 491.78, 384.09, 491.27, 391.74, 499.43, 401.43]], "area": 5819.330849999998, "iscrowd": 0, "image_id": 100312, "bbox": [468.82, 223.36, 86.73, 181.13], "category_id": 1, "id": 482931, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "shorts", "and", "a", "white", "sweater", "pushing", "a", "baby", "carriage"], "raw": "A woman wearing shorts and a white sweater pushing a baby carriage.", "sent_id": 30270, "sent": "a woman wearing shorts and a white sweater pushing a baby carriage"}, {"tokens": ["a", "woman", "wearing", "a", "sweater", "and", "shorts", "pushing", "a", "baby", "stroller"], "raw": "a woman wearing a sweater and shorts pushing a baby stroller", "sent_id": 30271, "sent": "a woman wearing a sweater and shorts pushing a baby stroller"}], "file_name": "COCO_train2014_000000100312_482931.jpg", "ann_id": 482931, "sent_ids": [30270, 30271], "ref_id": 16614}, {"segmentation": [[189.71, 329.6, 185.94, 290.46, 189.71, 273.14, 194.22, 265.62, 196.48, 252.82, 196.48, 236.26, 195.73, 226.47, 185.94, 218.94, 173.15, 223.46, 167.88, 222.71, 163.36, 216.68, 162.61, 212.92, 177.66, 202.38, 202.51, 190.34, 219.07, 171.51, 228.85, 154.95, 242.4, 155.71, 251.44, 163.23, 250.69, 179.04, 248.43, 188.08, 249.18, 190.34, 256.71, 200.12, 264.24, 206.14, 274.78, 218.19, 274.78, 226.47, 274.78, 231.74, 277.79, 234.75, 272.52, 241.53, 264.24, 243.03, 261.98, 239.27, 258.97, 233.25, 249.18, 249.05, 249.93, 273.14, 242.4, 284.44, 230.36, 285.94, 223.58, 294.22, 225.84, 297.99, 222.08, 300.25, 209.28, 301.75, 207.02, 304.76, 204.76, 318.31, 204.01, 323.58, 204.01, 329.6, 191.21, 328.85]], "area": 8966.574250000001, "iscrowd": 0, "image_id": 454923, "bbox": [162.61, 154.95, 115.18, 174.65], "category_id": 1, "id": 451765, "split": "val", "sentences": [{"tokens": ["the", "man", "inside", "the", "glass", ",", "with", "his", "back", "turned"], "raw": "The man inside the glass, with his back turned.", "sent_id": 30300, "sent": "the man inside the glass , with his back turned"}, {"tokens": ["a", "man", "with", "his", "back", "turned", "toward", "the", "camera", ",", "enjoying", "a", "conversation", "with", "a", "friend"], "raw": "A man with his back turned toward the camera, enjoying a conversation with a friend.", "sent_id": 30301, "sent": "a man with his back turned toward the camera , enjoying a conversation with a friend"}], "file_name": "COCO_train2014_000000454923_451765.jpg", "ann_id": 451765, "sent_ids": [30300, 30301], "ref_id": 16624}, {"segmentation": [[155.33, 326.39, 164.39, 319.59, 171.64, 295.59, 143.1, 262.98, 170.73, 244.86, 174.81, 243.05, 167.11, 233.08, 163.94, 224.48, 163.03, 221.31, 162.13, 226.74, 156.69, 221.76, 157.14, 208.17, 166.66, 208.17, 169.37, 203.64, 170.01, 182.76, 162.61, 177.24, 157.2, 175.16, 151.5, 178.65, 150.67, 190.75, 148.09, 198.66, 144.01, 203.64, 134.95, 209.08, 124.08, 210.89, 113.66, 214.51, 107.32, 216.78, 115.02, 226.29, 124.99, 220.4, 143.1, 218.14, 153.07, 215.87, 150.8, 219.5, 148.54, 225.84, 136.76, 236.71, 124.08, 253.47, 119.55, 260.26, 127.7, 281.55, 144.92, 307.36, 148.99, 305.1, 149.9, 306.91, 150.8, 313.25, 151.26, 323.67], [201.61, 206.82, 189.22, 176.97, 189.47, 168.11, 196.55, 176.71, 201.11, 186.58, 204.9, 189.62, 206.42, 192.15, 204.9, 193.67, 204.9, 202.77, 203.39, 205.81], [172.3, 175.07, 177.88, 169.71, 182.77, 168.78, 183.24, 164.59, 181.14, 162.03, 183.7, 162.03, 187.9, 158.77, 180.91, 154.11, 180.21, 143.64, 177.19, 139.45, 170.9, 138.28, 170.43, 136.19, 163.45, 136.88, 158.56, 139.91, 156.0, 146.2, 153.67, 151.79, 152.74, 155.51, 153.9, 159.47, 154.83, 163.66, 160.19, 165.29, 161.12, 165.99, 157.86, 169.48, 166.71, 171.34]], "area": 5007.80375, "iscrowd": 0, "image_id": 171581, "bbox": [107.32, 136.19, 99.1, 190.2], "category_id": 1, "id": 212155, "split": "val", "sentences": [{"tokens": ["a", "man", "riding", "a", "horse"], "raw": "A man riding a horse.", "sent_id": 30308, "sent": "a man riding a horse"}, {"tokens": ["a", "guy", "in", "a", "red", "shirt", "and", "jeans", "on", "top", "of", "a", "brown", "horse"], "raw": "A guy in a red shirt and jeans on top of a brown horse", "sent_id": 30309, "sent": "a guy in a red shirt and jeans on top of a brown horse"}], "file_name": "COCO_train2014_000000171581_212155.jpg", "ann_id": 212155, "sent_ids": [30308, 30309], "ref_id": 16628}, {"segmentation": [[181.02, 144.97, 156.23, 159.99, 150.22, 209.56, 143.46, 287.68, 156.23, 279.42, 169.0, 217.07, 178.77, 223.83, 174.26, 294.44, 184.78, 279.42, 204.3, 205.81, 213.32, 214.82, 226.84, 188.53, 222.33, 180.27, 229.09, 172.76, 277.91, 159.24, 278.67, 144.97, 312.47, 162.24, 322.98, 152.48, 292.94, 117.93, 286.93, 109.66, 259.14, 109.66, 247.12, 116.42, 247.12, 116.42, 247.12, 120.18, 235.85, 138.21, 220.08, 160.74, 207.31, 146.47, 181.02, 145.72]], "area": 10242.747000000001, "iscrowd": 0, "image_id": 276444, "bbox": [143.46, 109.66, 179.52, 184.78], "category_id": 24, "id": 590159, "split": "val", "sentences": [{"tokens": ["the", "bigger", "zebra", "on", "the", "left"], "raw": "The bigger zebra on the left.", "sent_id": 30466, "sent": "the bigger zebra on the left"}, {"tokens": ["the", "two", "zebras"], "raw": "The two zebras.", "sent_id": 30467, "sent": "the two zebras"}], "file_name": "COCO_train2014_000000276444_590159.jpg", "ann_id": 590159, "sent_ids": [30466, 30467], "ref_id": 16684}, {"segmentation": [[312.81, 164.85, 298.79, 230.65, 303.1, 292.13, 336.54, 314.79, 343.01, 330.97, 341.93, 351.46, 328.99, 353.62, 312.81, 360.09, 306.34, 369.8, 310.65, 389.21, 352.72, 400.0, 378.61, 394.61, 392.63, 375.19, 381.84, 361.17, 376.45, 354.7, 364.58, 349.3, 360.27, 349.3, 358.11, 348.22, 355.86, 347.6, 356.25, 313.81, 382.1, 299.1, 394.82, 280.81, 395.21, 220.38, 384.48, 160.35, 367.39, 155.98, 343.53, 153.99, 332.8, 154.39, 311.33, 159.16, 311.73, 161.55]], "area": 16936.011449999995, "iscrowd": 0, "image_id": 204529, "bbox": [298.79, 153.99, 96.42, 246.01], "category_id": 46, "id": 666556, "split": "val", "sentences": [{"tokens": ["glass", "in", "front", "of", "the", "pinot", "bottle"], "raw": "Glass in front of the Pinot bottle.", "sent_id": 30475, "sent": "glass in front of the pinot bottle"}, {"tokens": ["glass", "in", "front", "of", "pinot", "blanco", "bottle"], "raw": "glass in front of Pinot Blanco bottle", "sent_id": 30476, "sent": "glass in front of pinot blanco bottle"}], "file_name": "COCO_train2014_000000204529_666556.jpg", "ann_id": 666556, "sent_ids": [30475, 30476], "ref_id": 16688}, {"segmentation": [[203.42, 96.23, 216.68, 104.44, 216.05, 114.54, 226.15, 118.96, 228.67, 132.21, 247.61, 138.52, 250.13, 156.83, 236.88, 159.35, 234.35, 167.56, 274.12, 168.19, 281.69, 185.87, 284.85, 213.01, 267.81, 237.62, 243.19, 236.36, 238.14, 223.74, 232.46, 232.57, 231.2, 284.33, 159.87, 283.07, 159.87, 218.06, 151.67, 206.7, 154.19, 190.92, 159.87, 184.6, 158.61, 166.3, 140.3, 153.04, 142.2, 144.84, 178.81, 147.99, 183.86, 142.94, 169.97, 125.9, 173.13, 114.54, 176.28, 113.91, 185.75, 96.87, 200.9, 94.97]], "area": 16238.20485, "iscrowd": 0, "image_id": 458751, "bbox": [140.3, 94.97, 144.55, 189.36], "category_id": 11, "id": 1808941, "split": "val", "sentences": [{"tokens": ["a", "blue", "fire", "hydrant", "on", "a", "street"], "raw": "A blue fire hydrant on a street", "sent_id": 30499, "sent": "a blue fire hydrant on a street"}, {"tokens": ["a", "blue", "fire", "hydrant", "being", "stood", "on"], "raw": "a blue fire hydrant being stood on", "sent_id": 30500, "sent": "a blue fire hydrant being stood on"}], "file_name": "COCO_train2014_000000458751_1808941.jpg", "ann_id": 1808941, "sent_ids": [30499, 30500], "ref_id": 16696}, {"segmentation": [[300.64, 136.64, 305.22, 147.97, 304.68, 158.76, 300.37, 168.21, 296.86, 168.21, 291.74, 173.06, 283.37, 173.6, 295.51, 198.42, 304.68, 195.18, 309.81, 195.45, 314.4, 201.12, 307.92, 209.48, 300.91, 211.1, 303.07, 222.97, 303.07, 222.97, 309.27, 226.47, 303.87, 228.63, 308.19, 233.49, 305.76, 237.26, 300.64, 280.96, 297.13, 319.27, 290.93, 318.46, 289.85, 320.34, 294.7, 326.28, 294.16, 336.26, 293.62, 347.05, 287.15, 346.51, 294.97, 352.72, 304.68, 357.84, 305.49, 364.04, 284.45, 363.24, 270.16, 360.54, 283.37, 368.9, 286.88, 373.76, 284.45, 375.37, 262.87, 376.99, 245.61, 372.14, 246.96, 359.19, 249.65, 349.75, 255.86, 311.44, 260.18, 301.19, 263.95, 285.82, 260.98, 272.33, 253.97, 259.92, 248.04, 255.07, 242.37, 218.65, 242.1, 182.23, 246.96, 170.63, 247.23, 170.09, 264.22, 152.56, 266.11, 150.4, 270.97, 152.56, 279.33, 137.99, 285.53, 132.33, 296.05, 132.6, 298.75, 135.03]], "area": 11237.224699999997, "iscrowd": 0, "image_id": 129438, "bbox": [242.1, 132.33, 72.3, 244.66], "category_id": 1, "id": 1203408, "split": "val", "sentences": [{"tokens": ["man", "in", "tan", "jacket"], "raw": "man in tan jacket", "sent_id": 30591, "sent": "man in tan jacket"}, {"tokens": ["a", "man", "in", "a", "beige", "coat", "watching", "two", "men", "play", "a", "game"], "raw": "A man in a beige coat watching two men play a game.", "sent_id": 30592, "sent": "a man in a beige coat watching two men play a game"}], "file_name": "COCO_train2014_000000129438_1203408.jpg", "ann_id": 1203408, "sent_ids": [30591, 30592], "ref_id": 16734}, {"segmentation": [[341.21, 290.53, 350.17, 286.8, 350.92, 258.42, 353.16, 242.74, 351.67, 223.33, 362.87, 193.47, 376.3, 204.67, 398.7, 238.26, 409.16, 271.12, 420.36, 287.54, 427.82, 284.56, 423.34, 266.64, 412.89, 244.24, 403.18, 212.88, 395.72, 191.23, 384.52, 167.33, 386.76, 146.43, 380.78, 130.75, 394.22, 132.24, 425.58, 143.44, 442.76, 144.19, 449.48, 146.43, 447.98, 137.47, 404.68, 124.03, 389.74, 106.11, 375.56, 102.38, 374.07, 101.63, 371.83, 88.19, 369.59, 82.22, 358.39, 79.23, 349.43, 85.95, 346.44, 97.9, 328.52, 85.95, 315.83, 68.78, 304.63, 53.1, 306.12, 40.41, 305.37, 32.94, 296.41, 41.15, 293.43, 35.93, 291.19, 30.7, 282.23, 38.17, 286.71, 50.86, 297.91, 56.83, 316.57, 93.42, 332.25, 120.3, 338.97, 183.76, 336.73, 214.37, 336.73, 233.78, 341.96, 272.61, 333.75, 284.56, 333.75, 292.02, 342.71, 289.78]], "area": 10339.421799999998, "iscrowd": 0, "image_id": 111000, "bbox": [282.23, 30.7, 167.25, 261.32], "category_id": 1, "id": 453687, "split": "val", "sentences": [{"tokens": ["a", "guy", "in", "a", "black", "shirt", "and", "red", "shorts"], "raw": "A guy in a black shirt and red shorts.", "sent_id": 30688, "sent": "a guy in a black shirt and red shorts"}, {"tokens": ["a", "man", "wearing", "a", "black", "shirt", "and", "red", "shorts", "jumping", "to", "catch", "a", "frisbee"], "raw": "A man wearing a black shirt and red shorts jumping to catch a frisbee.", "sent_id": 30689, "sent": "a man wearing a black shirt and red shorts jumping to catch a frisbee"}], "file_name": "COCO_train2014_000000111000_453687.jpg", "ann_id": 453687, "sent_ids": [30688, 30689], "ref_id": 16775}, {"segmentation": [[349.93, 102.71, 352.97, 95.76, 364.26, 104.01, 369.91, 121.82, 380.33, 131.8, 382.5, 144.83, 394.22, 145.27, 402.47, 140.49, 406.81, 139.19, 408.55, 179.57, 395.96, 193.9, 402.47, 197.37, 411.59, 194.77, 414.63, 180.87, 422.45, 130.5, 426.36, 112.26, 418.11, 83.6, 406.38, 78.83, 395.09, 84.47, 386.41, 139.62, 382.5, 135.71, 384.67, 112.26, 372.08, 90.12, 358.18, 74.92, 356.44, 65.37, 350.8, 66.24, 350.36, 74.05, 342.55, 71.01, 339.07, 62.33, 338.21, 77.09, 337.34, 115.3, 345.59, 114.87]], "area": 4035.842300000002, "iscrowd": 0, "image_id": 74217, "bbox": [337.34, 62.33, 89.02, 135.04], "category_id": 19, "id": 54079, "split": "val", "sentences": [{"tokens": ["the", "horse", "that", "is", "looking", "towards", "the", "motorcyles"], "raw": "The horse that is looking towards the motorcyles.", "sent_id": 30728, "sent": "the horse that is looking towards the motorcyles"}, {"tokens": ["a", "white", "horse", "right", "of", "another"], "raw": "A white horse right of another.", "sent_id": 30729, "sent": "a white horse right of another"}], "file_name": "COCO_train2014_000000074217_54079.jpg", "ann_id": 54079, "sent_ids": [30728, 30729], "ref_id": 16790}, {"segmentation": [[45.48, 63.25, 97.27, 61.75, 128.05, 69.25, 155.07, 76.76, 170.08, 96.27, 165.58, 115.04, 138.55, 132.3, 99.52, 146.56, 52.24, 160.07, 43.98, 164.58, 65.0, 271.16, 84.51, 382.25, 109.28, 382.25, 123.54, 388.25, 115.29, 398.01, 101.02, 401.77, 92.77, 413.77, 80.01, 447.55, 59.74, 455.81, 29.72, 464.06, 13.96, 419.78, 37.97, 401.77, 54.49, 390.51, 37.22, 295.18, 15.46, 170.58, 2.7, 171.33, 0.0, 165.33, 0.0, 150.32, 0.0, 59.49, 0.0, 39.23, 0.0, 31.72, 3.45, 24.22, 14.71, 28.72, 10.95, 51.24, 14.71, 71.5, 16.21, 73.76]], "area": 25774.763649999994, "iscrowd": 0, "image_id": 290185, "bbox": [0.0, 24.22, 170.08, 439.84], "category_id": 67, "id": 1959809, "split": "val", "sentences": [{"tokens": ["napkins", "stacked", "on", "a", "round", ",", "brown", "table"], "raw": "Napkins stacked on a round, brown table.", "sent_id": 30777, "sent": "napkins stacked on a round , brown table"}, {"tokens": ["a", "round", "brown", "table"], "raw": "A round brown table", "sent_id": 30778, "sent": "a round brown table"}], "file_name": "COCO_train2014_000000290185_1959809.jpg", "ann_id": 1959809, "sent_ids": [30777, 30778], "ref_id": 16808}, {"segmentation": [[410.33, 186.72, 457.59, 193.17, 474.78, 198.54, 479.07, 217.87, 488.74, 229.69, 487.67, 270.51, 495.19, 346.77, 495.19, 386.52, 462.96, 417.67, 451.15, 426.26, 439.33, 410.15, 407.11, 445.6, 396.36, 471.38, 237.39, 472.45, 218.05, 365.03, 191.2, 341.4, 192.27, 266.21, 197.64, 250.1, 211.61, 241.51, 267.47, 215.73, 270.69, 193.17, 249.2, 174.91, 240.61, 145.91, 233.09, 109.38, 222.35, 72.86, 233.09, 44.94, 243.83, 29.9, 278.21, 8.41, 322.25, 5.19, 349.1, 25.6, 371.66, 47.08, 377.03, 81.46, 383.47, 97.57, 382.4, 125.5, 370.58, 137.31, 365.21, 136.24, 368.44, 154.5, 381.33, 166.32, 404.96, 174.91]], "area": 96166.58839999998, "iscrowd": 0, "image_id": 39812, "bbox": [191.2, 5.19, 303.99, 467.26], "category_id": 1, "id": 482492, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "tuxedo", "and", "standing", "between", "two", "women"], "raw": "A man wearing a tuxedo and standing between two women.", "sent_id": 30801, "sent": "a man wearing a tuxedo and standing between two women"}, {"tokens": ["a", "man", "in", "a", "tux", "standing", "next", "to", "two", "woman", "for", "a", "picture"], "raw": "A man in a tux standing next to two woman for a picture", "sent_id": 30802, "sent": "a man in a tux standing next to two woman for a picture"}], "file_name": "COCO_train2014_000000039812_482492.jpg", "ann_id": 482492, "sent_ids": [30801, 30802], "ref_id": 16819}, {"segmentation": [[277.51, 114.74, 262.37, 101.28, 243.86, 92.02, 213.57, 89.5, 186.65, 93.7, 162.26, 111.37, 141.23, 139.13, 133.66, 160.16, 131.13, 173.62, 131.97, 179.51, 133.66, 187.08, 137.02, 192.13, 139.54, 199.7, 124.4, 203.91, 122.72, 206.43, 131.13, 219.05, 126.93, 225.78, 120.2, 231.67, 131.13, 245.97, 121.88, 251.86, 111.78, 254.38, 104.21, 260.27, 99.16, 265.32, 95.8, 270.37, 91.59, 277.94, 90.75, 298.13, 95.8, 324.21, 98.32, 341.03, 109.26, 351.13, 114.31, 346.92, 115.99, 331.78, 113.47, 308.22, 115.99, 298.13, 121.88, 280.46, 128.61, 260.27, 131.97, 253.54, 140.39, 236.72, 141.23, 226.62, 143.75, 218.21, 154.69, 208.96, 165.62, 199.7, 169.83, 198.86, 168.99, 219.89, 179.92, 238.4, 206.0, 237.56, 225.35, 227.46, 226.19, 214.0, 231.24, 198.86, 238.81, 183.72, 257.32, 129.88]], "area": 16538.293100000003, "iscrowd": 0, "image_id": 87522, "bbox": [90.75, 89.5, 186.76, 261.63], "category_id": 52, "id": 1044277, "split": "val", "sentences": [{"tokens": ["the", "bananas", "closest", "to", "the", "hand", "on", "top"], "raw": "The bananas closest to the hand on top.", "sent_id": 30830, "sent": "the bananas closest to the hand on top"}, {"tokens": ["left", "most", "three", "banana", "on", "the", "head", "of", "the", "girl"], "raw": "left most three banana on the head of the girl", "sent_id": 30831, "sent": "left most three banana on the head of the girl"}], "file_name": "COCO_train2014_000000087522_1044277.jpg", "ann_id": 1044277, "sent_ids": [30830, 30831], "ref_id": 16831}, {"segmentation": [[251.33, 401.26, 232.99, 420.67, 241.62, 419.6, 235.15, 439.01, 234.07, 441.17, 222.2, 449.8, 242.7, 443.33, 257.8, 441.17, 270.74, 441.17, 280.45, 441.17, 292.31, 444.4, 312.81, 444.4, 325.75, 448.72, 350.56, 448.72, 365.66, 451.96, 391.55, 454.11, 416.36, 454.11, 434.7, 455.19, 434.7, 455.19, 434.7, 450.88, 433.62, 444.4, 431.46, 440.09, 430.38, 430.38, 430.38, 417.44, 432.54, 400.18, 443.33, 391.55, 457.35, 429.3, 463.82, 431.46, 480.0, 435.78, 490.79, 435.78, 495.1, 434.7, 496.18, 432.54, 498.34, 431.46, 498.34, 431.46, 503.73, 422.83, 504.81, 422.83, 519.91, 405.57, 526.38, 400.18, 538.25, 392.63, 551.19, 385.08, 546.88, 378.61, 541.48, 371.06, 538.25, 363.51, 532.85, 353.8, 519.91, 349.48, 485.39, 349.48, 483.24, 384.0, 465.98, 368.9, 453.03, 360.27, 437.93, 351.64, 435.78, 348.4, 422.83, 333.3, 409.89, 324.67, 404.49, 317.12, 405.57, 312.81, 423.91, 308.49, 429.3, 299.87, 436.85, 283.69, 437.93, 282.61, 439.01, 265.35, 443.33, 263.19, 449.8, 253.48, 454.11, 243.78, 457.35, 231.91, 454.11, 217.89, 451.96, 210.34, 449.8, 199.55, 430.38, 189.84, 406.65, 182.29, 380.76, 175.82, 357.03, 172.58, 349.48, 172.58, 324.67, 172.58, 324.67, 172.58, 312.81, 174.74, 305.26, 180.13, 292.31, 188.76, 284.76, 206.02, 280.45, 226.52, 276.13, 249.17, 283.69, 267.51, 285.84, 291.24, 289.08, 307.42, 289.08, 312.81, 277.21, 312.81, 227.6, 328.99, 220.04, 358.11, 215.73, 362.43, 207.1, 368.9, 279.37, 324.67, 279.37, 327.91, 270.74, 338.7, 267.51, 339.78, 261.03, 341.93, 252.4, 343.01, 250.25, 344.09, 239.46, 349.48, 234.07, 352.72, 229.75, 358.11, 229.75, 359.19, 227.6, 367.82, 216.81, 377.53, 180.13, 386.16, 170.43, 390.47, 169.35, 395.87, 166.11, 402.34, 163.96, 412.04, 163.96, 422.83, 163.96, 427.15, 166.11, 436.85, 177.98, 448.72, 193.08, 451.96, 203.87, 448.72, 216.81, 439.01, 225.44, 431.46, 229.75, 421.75, 236.22, 414.2, 241.62, 409.89]], "area": 58171.22344999999, "iscrowd": 0, "image_id": 173032, "bbox": [163.96, 172.58, 387.23, 282.61], "category_id": 1, "id": 489969, "split": "val", "sentences": [{"tokens": ["a", "small", ",", "one", "-", "year", "-", "old", ",", "female", "human", "holding", "food", "and", "smashing", "said", "food", "on", "their", "face"], "raw": "A small, one-year-old, female human holding food and smashing said food on their face.", "sent_id": 30863, "sent": "a small , one - year - old , female human holding food and smashing said food on their face"}, {"tokens": ["a", "girl", "celebrating", "her", "birthday", "holding", "cake", "with", "icing", "smeared", "all", "over", "her", "face"], "raw": "A girl celebrating her birthday holding cake with icing smeared all over her face.", "sent_id": 30864, "sent": "a girl celebrating her birthday holding cake with icing smeared all over her face"}], "file_name": "COCO_train2014_000000173032_489969.jpg", "ann_id": 489969, "sent_ids": [30863, 30864], "ref_id": 16843}, {"segmentation": [[292.75, 62.81, 303.15, 47.83, 341.84, 49.91, 352.66, 56.99, 348.5, 83.19, 354.32, 96.92, 352.66, 127.29, 358.06, 136.86, 358.06, 166.39, 360.97, 191.35, 339.34, 184.28, 332.27, 179.7, 318.54, 178.87, 317.3, 170.14, 295.25, 157.24, 298.99, 131.86, 311.47, 127.7, 307.73, 124.79, 292.34, 115.64, 293.58, 101.5, 301.49, 86.94, 298.99, 77.37, 295.25, 63.23]], "area": 7219.782349999999, "iscrowd": 0, "image_id": 346344, "bbox": [292.34, 47.83, 68.63, 143.52], "category_id": 10, "id": 404226, "split": "val", "sentences": [{"tokens": ["traffic", "lights", "not", "above", "the", "bus"], "raw": "Traffic lights not above the bus.", "sent_id": 31057, "sent": "traffic lights not above the bus"}, {"tokens": ["a", "traffic", "light"], "raw": "A traffic light.", "sent_id": 31058, "sent": "a traffic light"}], "file_name": "COCO_train2014_000000346344_404226.jpg", "ann_id": 404226, "sent_ids": [31057, 31058], "ref_id": 16922}, {"segmentation": [[275.54, 277.4, 286.71, 364.9, 500.0, 377.0, 500.0, 305.32, 488.7, 309.98, 353.73, 276.47]], "area": 18000.600099999992, "iscrowd": 0, "image_id": 230893, "bbox": [275.54, 276.47, 224.46, 100.53], "category_id": 8, "id": 1796392, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "truck"], "raw": "the back of a truck", "sent_id": 31100, "sent": "the back of a truck"}], "file_name": "COCO_train2014_000000230893_1796392.jpg", "ann_id": 1796392, "sent_ids": [31100], "ref_id": 16935}, {"segmentation": [[289.41, 470.77, 282.79, 495.57, 286.1, 520.38, 282.79, 541.88, 281.14, 566.68, 274.52, 578.26, 271.21, 599.76, 256.33, 621.26, 243.1, 627.87, 219.95, 627.87, 224.91, 621.26, 236.49, 598.11, 236.49, 594.8, 224.91, 581.57, 210.03, 558.42, 200.1, 495.57, 203.41, 479.04, 219.95, 429.42, 223.26, 412.89, 223.26, 389.73, 221.6, 376.5, 213.33, 376.5, 210.03, 381.46, 203.41, 381.46, 223.25, 333.43, 226.8, 316.59, 230.34, 313.04, 235.66, 310.38, 239.2, 307.72, 235.66, 297.09, 232.11, 288.23, 232.11, 281.14, 235.66, 265.19, 235.66, 263.41, 240.98, 259.87, 251.61, 258.1, 258.7, 254.55, 266.68, 259.87, 274.65, 267.84, 276.42, 275.82, 277.31, 282.91, 278.2, 290.0, 271.99, 298.86, 266.87, 304.91, 270.67, 310.14, 279.22, 318.68, 292.52, 326.28, 298.22, 331.98, 304.87, 353.35, 310.57, 371.88, 313.41, 395.15, 310.57, 401.32, 288.24, 406.54, 290.14, 411.29, 287.29, 420.32, 289.67, 432.66, 293.94, 442.16, 292.99, 452.61, 289.67, 459.26, 288.24, 473.51, 287.77, 475.88]], "area": 24756.052699999993, "iscrowd": 0, "image_id": 39159, "bbox": [200.1, 254.55, 113.31, 373.32], "category_id": 1, "id": 2151988, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "a", "tank", "top", "on"], "raw": "a woman with a tank top on", "sent_id": 31152, "sent": "a woman with a tank top on"}, {"tokens": ["a", "woman", "wearing", "brown", "or", "tan", "cargo", "pants"], "raw": "A woman wearing brown or tan cargo pants.", "sent_id": 31153, "sent": "a woman wearing brown or tan cargo pants"}], "file_name": "COCO_train2014_000000039159_2151988.jpg", "ann_id": 2151988, "sent_ids": [31152, 31153], "ref_id": 16957}, {"segmentation": [[564.52, 202.92, 585.68, 188.5, 602.03, 179.84, 633.77, 176.95, 640.0, 180.8, 637.61, 335.64, 621.27, 339.48, 602.03, 342.37, 576.07, 341.41, 556.83, 340.45, 540.48, 340.45, 527.98, 340.45, 527.02, 337.56, 531.83, 309.67, 541.44, 277.93, 549.14, 260.62, 551.06, 247.16, 546.25, 233.7, 545.29, 226.96, 550.1, 219.27, 554.91, 221.19]], "area": 14611.961100000002, "iscrowd": 0, "image_id": 45226, "bbox": [527.02, 176.95, 112.98, 165.42], "category_id": 1, "id": 531930, "split": "val", "sentences": [{"tokens": ["a", "set", "of", "hands", "is", "clapping", "for", "the", "girl", "blowing", "out", "candles"], "raw": "A set of hands is clapping for the girl blowing out candles.", "sent_id": 31215, "sent": "a set of hands is clapping for the girl blowing out candles"}, {"tokens": ["the", "man", "who", "is", "about", "to", "clap"], "raw": "the man who is about to clap", "sent_id": 31216, "sent": "the man who is about to clap"}], "file_name": "COCO_train2014_000000045226_531930.jpg", "ann_id": 531930, "sent_ids": [31215, 31216], "ref_id": 16983}, {"segmentation": [[602.97, 308.04, 551.63, 255.61, 551.63, 255.61, 547.26, 256.7, 549.45, 304.76, 549.45, 316.78, 547.44, 329.89, 540.4, 348.99, 511.22, 381.23, 488.28, 399.8, 471.89, 421.64, 469.71, 432.57, 456.6, 451.14, 454.41, 451.14, 443.49, 458.78, 443.49, 478.45, 636.8, 480.3, 638.81, 325.5]], "area": 25087.72589999999, "iscrowd": 0, "image_id": 545832, "bbox": [443.49, 255.61, 195.32, 224.69], "category_id": 3, "id": 349974, "split": "val", "sentences": [{"tokens": ["front", "grill", "of", "a", "car", "behind", "a", "parking", "meter"], "raw": "Front grill of a car behind a parking meter.", "sent_id": 31230, "sent": "front grill of a car behind a parking meter"}, {"tokens": ["the", "grill", "of", "a", "dodge", "truck", "sits", "behind", "a", "parking", "meter"], "raw": "The grill of a Dodge truck sits behind a parking meter.", "sent_id": 31231, "sent": "the grill of a dodge truck sits behind a parking meter"}], "file_name": "COCO_train2014_000000545832_349974.jpg", "ann_id": 349974, "sent_ids": [31230, 31231], "ref_id": 16989}, {"segmentation": [[522.33, 1.86, 563.88, 75.81, 615.29, 139.19, 640.0, 149.75, 640.0, 2.91]], "area": 10429.38, "iscrowd": 0, "image_id": 534155, "bbox": [522.33, 1.86, 117.67, 147.89], "category_id": 5, "id": 247238, "split": "val", "sentences": [{"tokens": ["the", "bottom", "of", "the", "silver", "and", "yellow", "plane", "on", "the", "right"], "raw": "The bottom of the silver and yellow plane on the right", "sent_id": 31352, "sent": "the bottom of the silver and yellow plane on the right"}, {"tokens": ["body", "of", "the", "huge", "silver", "plane", ",", "behind", "the", "red", "and", "blue"], "raw": "body of the huge silver plane, behind the red and blue", "sent_id": 31353, "sent": "body of the huge silver plane , behind the red and blue"}], "file_name": "COCO_train2014_000000534155_247238.jpg", "ann_id": 247238, "sent_ids": [31352, 31353], "ref_id": 17033}, {"segmentation": [[207.57, 347.39, 226.31, 335.86, 237.84, 335.86, 246.49, 338.74, 263.78, 350.27, 266.67, 360.36, 268.11, 370.45, 268.11, 383.42, 262.34, 405.05, 263.78, 418.02, 273.87, 430.99, 281.08, 439.64, 288.29, 455.5, 295.5, 475.68, 296.94, 480.0, 305.59, 494.41, 304.14, 497.3, 298.38, 497.3, 291.17, 498.74, 276.76, 498.74, 272.43, 497.3, 268.11, 511.71, 270.99, 531.89, 270.99, 556.4, 281.08, 611.17, 270.99, 625.59, 256.58, 625.59, 240.72, 627.03, 237.84, 609.73, 221.98, 609.73, 211.89, 615.5, 204.68, 605.41, 187.39, 523.24, 183.06, 504.5, 200.36, 468.47, 196.04, 428.11, 204.68, 406.49, 206.13, 374.77]], "area": 21408.19185, "iscrowd": 0, "image_id": 339051, "bbox": [183.06, 335.86, 122.53, 291.17], "category_id": 1, "id": 463485, "split": "val", "sentences": [{"tokens": ["a", "small", "child"], "raw": "a small child", "sent_id": 31362, "sent": "a small child"}, {"tokens": ["a", "boy", "looking", "in", "a", "refrigerator"], "raw": "A boy looking in a refrigerator.", "sent_id": 31363, "sent": "a boy looking in a refrigerator"}], "file_name": "COCO_train2014_000000339051_463485.jpg", "ann_id": 463485, "sent_ids": [31362, 31363], "ref_id": 17038}, {"segmentation": [[19.4, 283.12, 20.98, 374.02, 56.55, 384.3, 217.0, 370.86, 215.41, 283.12, 177.48, 275.23, 25.73, 280.75], [20.19, 378.29, 19.4, 467.61, 47.07, 488.95, 216.21, 464.44, 217.79, 462.07, 217.79, 375.92, 217.79, 372.76, 54.98, 390.14, 22.57, 376.71]], "area": 38340.80345000001, "iscrowd": 0, "image_id": 404899, "bbox": [19.4, 275.23, 198.39, 213.72], "category_id": 78, "id": 1641087, "split": "val", "sentences": [{"tokens": ["two", "stacked", "microwaves"], "raw": "two stacked microwaves", "sent_id": 31367, "sent": "two stacked microwaves"}, {"tokens": ["a", "red", "microwave", "ontop", "of", "a", "black", "microwave"], "raw": "A red microwave ontop of a black microwave.", "sent_id": 31368, "sent": "a red microwave ontop of a black microwave"}], "file_name": "COCO_train2014_000000404899_1641087.jpg", "ann_id": 1641087, "sent_ids": [31367, 31368], "ref_id": 17041}, {"segmentation": [[511.29, 253.1, 503.6, 244.95, 494.99, 228.19, 490.46, 217.32, 471.9, 202.83, 439.29, 167.06, 423.44, 148.49, 413.94, 122.23, 414.39, 117.25, 399.44, 119.96, 396.73, 127.66, 394.01, 137.17, 390.84, 142.15, 398.54, 158.0, 417.11, 182.45, 432.95, 199.66, 458.31, 221.4, 475.07, 232.27, 496.8, 254.0, 492.73, 255.81, 478.69, 249.47, 468.73, 231.36, 464.65, 235.89, 466.92, 246.3, 477.33, 263.06, 511.75, 270.76, 519.9, 269.85, 545.26, 269.85, 566.99, 266.68, 573.33, 270.3, 586.92, 269.4, 582.84, 263.96, 567.45, 266.68, 549.33, 254.91, 546.62, 246.3, 540.73, 251.29, 546.62, 257.62, 537.11, 263.06, 531.67, 265.32, 523.97, 258.98, 518.09, 254.0]], "area": 5223.698399999999, "iscrowd": 0, "image_id": 551316, "bbox": [390.84, 117.25, 196.08, 153.51], "category_id": 32, "id": 293346, "split": "val", "sentences": [{"tokens": ["a", "blue", "striped", "tie", "on", "a", "man", "flying", "up", "in", "the", "air"], "raw": "A blue striped tie on a man flying up in the air", "sent_id": 31383, "sent": "a blue striped tie on a man flying up in the air"}, {"tokens": ["a", "blue", "tie", "being", "worn", "by", "a", "man"], "raw": "a blue tie being worn by a man", "sent_id": 31384, "sent": "a blue tie being worn by a man"}], "file_name": "COCO_train2014_000000551316_293346.jpg", "ann_id": 293346, "sent_ids": [31383, 31384], "ref_id": 17048}, {"segmentation": [[550.76, 436.71, 546.77, 257.12, 462.96, 258.11, 460.96, 432.72, 460.96, 437.71, 472.93, 435.71, 475.93, 399.79, 530.8, 385.83, 532.8, 434.72, 542.78, 436.71], [458.97, 336.94, 407.08, 349.91, 409.08, 442.14, 420.05, 443.25, 420.05, 379.4, 459.96, 388.38, 459.96, 332.5]], "area": 15840.118900000003, "iscrowd": 0, "image_id": 108499, "bbox": [407.08, 257.12, 143.68, 186.13], "category_id": 62, "id": 289792, "split": "val", "sentences": [{"tokens": ["chair", "close", "to", "yellow", "bag"], "raw": "chair close to yellow bag", "sent_id": 31420, "sent": "chair close to yellow bag"}, {"tokens": ["the", "outermost", "right", "hand", "chair", "in", "the", "photo", ".", "it", "is", "front", "of", "the", "bag", "that", "says", "\"", "je", "suis", "\""], "raw": "The outermost right hand chair in the photo. It is front of the bag that says \"Je Suis\"", "sent_id": 31421, "sent": "the outermost right hand chair in the photo . it is front of the bag that says \" je suis \""}], "file_name": "COCO_train2014_000000108499_289792.jpg", "ann_id": 289792, "sent_ids": [31420, 31421], "ref_id": 17063}, {"segmentation": [[402.01, 165.82, 430.93, 179.31, 462.74, 188.95, 478.17, 203.41, 504.2, 223.66, 517.69, 245.83, 518.66, 247.76, 481.06, 287.29, 373.09, 319.1, 294.03, 325.85, 219.8, 315.24, 162.92, 296.93, 141.71, 284.39, 107.01, 270.9, 89.66, 267.04, 105.08, 241.98, 91.58, 220.77, 95.44, 207.27, 131.11, 187.02, 163.89, 166.78, 165.82, 165.82, 179.31, 162.92, 194.74, 162.92, 229.44, 159.07, 268.97, 155.21, 285.36, 154.25, 296.93, 141.71, 301.75, 139.79, 314.28, 145.57, 318.13, 150.39, 375.98, 151.36, 402.97, 167.74]], "area": 55653.71185000001, "iscrowd": 0, "image_id": 128398, "bbox": [89.66, 139.79, 429.0, 186.06], "category_id": 59, "id": 1074677, "split": "val", "sentences": [{"tokens": ["feta", "cheese", "coveres", "the", "foccacia", "on", "the", "table"], "raw": "feta cheese coveres the foccacia on the table.", "sent_id": 31475, "sent": "feta cheese coveres the foccacia on the table"}, {"tokens": ["a", "white", "mixture", "with", "herbs", "that", "is", "spread", "on", "top", "of", "some", "dough"], "raw": "A white mixture with herbs that is spread on top of some dough.", "sent_id": 31476, "sent": "a white mixture with herbs that is spread on top of some dough"}], "file_name": "COCO_train2014_000000128398_1074677.jpg", "ann_id": 1074677, "sent_ids": [31475, 31476], "ref_id": 17084}, {"segmentation": [[338.07, 128.99, 362.76, 69.48, 462.15, 73.28, 474.81, 116.96, 478.61, 165.07, 469.11, 201.79, 434.29, 223.95, 414.67, 233.44, 407.7, 258.77, 407.7, 266.36, 402.64, 272.06, 394.41, 258.13, 391.88, 235.97, 379.85, 222.68, 359.59, 213.18, 339.33, 194.19, 328.57, 156.84], [414.53, 332.0, 414.53, 341.6, 455.79, 353.11, 459.62, 360.79, 439.47, 363.67, 411.65, 363.67, 379.02, 363.67, 350.24, 358.87, 337.76, 349.28, 353.11, 344.48, 382.86, 339.68, 392.46, 337.76, 397.25, 329.13, 410.69, 333.92]], "area": 22388.281949999997, "iscrowd": 0, "image_id": 90569, "bbox": [328.57, 69.48, 150.04, 294.19], "category_id": 46, "id": 662248, "split": "val", "sentences": [{"tokens": ["glass", "if", "wine", "on", "the", "riht"], "raw": "glass if wine on the riht", "sent_id": 31477, "sent": "glass if wine on the riht"}, {"tokens": ["a", "wine", "glass", "to", "the", "right", "of", "another", "wine", "glass"], "raw": "a wine glass to the right of another wine glass", "sent_id": 31478, "sent": "a wine glass to the right of another wine glass"}], "file_name": "COCO_train2014_000000090569_662248.jpg", "ann_id": 662248, "sent_ids": [31477, 31478], "ref_id": 17085}, {"segmentation": [[212.31, 26.45, 223.63, 7.14, 242.27, 2.48, 248.93, 1.82, 320.17, 18.46, 326.83, 29.78, 328.83, 34.44, 324.83, 95.03, 328.83, 105.68, 334.82, 114.34, 341.48, 120.33, 354.13, 122.33, 358.79, 123.0, 358.79, 128.32, 358.79, 145.63, 353.46, 152.29, 332.16, 154.29, 313.51, 156.95, 307.52, 159.62, 298.2, 159.62, 288.21, 156.29, 277.56, 154.96, 265.57, 154.29, 239.61, 150.29, 228.95, 145.63, 226.95, 140.31, 223.63, 124.33, 221.63, 111.01, 217.63, 101.69, 216.3, 91.7, 224.29, 37.77, 220.96, 32.44]], "area": 16455.45379999999, "iscrowd": 0, "image_id": 209603, "bbox": [212.31, 1.82, 146.48, 157.8], "category_id": 62, "id": 2121388, "split": "val", "sentences": [{"tokens": ["a", "red", "jacket", "hanging", "on", "the", "back", "of", "a", "chair"], "raw": "A red jacket hanging on the back of a chair.", "sent_id": 31538, "sent": "a red jacket hanging on the back of a chair"}, {"tokens": ["a", "red", "jacket", "on", "a", "chair"], "raw": "a red jacket on a chair", "sent_id": 31539, "sent": "a red jacket on a chair"}], "file_name": "COCO_train2014_000000209603_2121388.jpg", "ann_id": 2121388, "sent_ids": [31538, 31539], "ref_id": 17108}, {"segmentation": [[152.79, 239.13, 122.43, 239.13, 80.69, 266.64, 73.1, 285.61, 82.59, 317.86, 99.67, 342.52, 102.51, 378.57, 103.46, 439.28, 123.38, 484.81, 161.32, 493.35, 193.58, 452.56, 189.78, 435.49, 179.35, 416.51, 189.78, 403.23, 187.88, 384.26, 194.52, 349.16, 180.3, 298.89, 172.71, 277.07, 180.3, 271.38, 154.68, 246.72, 151.84, 235.33]], "area": 21044.769899999996, "iscrowd": 0, "image_id": 309, "bbox": [73.1, 235.33, 121.42, 258.02], "category_id": 88, "id": 1996153, "split": "val", "sentences": [{"tokens": ["the", "legs", "of", "a", "teddy", "bear", "laying", "on", "some", "grass"], "raw": "The legs of a teddy bear laying on some grass.", "sent_id": 31561, "sent": "the legs of a teddy bear laying on some grass"}, {"tokens": ["the", "feet", "of", "the", "teddy", "bear"], "raw": "The feet of the teddy bear.", "sent_id": 31562, "sent": "the feet of the teddy bear"}], "file_name": "COCO_train2014_000000000309_1996153.jpg", "ann_id": 1996153, "sent_ids": [31561, 31562], "ref_id": 17115}, {"segmentation": [[110.21, 234.2, 93.4, 250.03, 89.44, 271.79, 96.36, 278.71, 93.4, 294.54, 86.47, 303.44, 83.5, 319.27, 82.51, 325.2, 85.48, 340.04, 104.28, 339.05, 112.19, 340.04, 115.16, 350.92, 131.97, 356.86, 142.85, 341.03, 137.91, 328.17, 169.56, 317.29, 188.35, 310.37, 167.58, 295.53, 154.72, 286.63, 152.74, 263.87, 145.82, 244.09, 135.93, 238.16, 114.17, 233.21, 108.23, 234.2], [96.36, 366.75, 104.28, 390.49, 121.09, 402.36, 140.87, 403.35, 153.73, 402.36, 147.8, 386.53, 136.92, 380.6, 130.98, 376.64, 118.12, 372.68, 106.25, 370.7, 98.34, 367.74], [168.57, 376.64, 167.58, 395.43, 165.6, 405.32, 170.55, 411.26, 187.36, 405.32, 200.22, 403.35, 197.26, 392.46, 190.33, 383.56, 188.35, 385.54, 191.32, 374.66, 191.32, 368.73, 191.32, 366.75, 169.56, 374.66]], "area": 9292.884500000004, "iscrowd": 0, "image_id": 100611, "bbox": [82.51, 233.21, 117.71, 178.05], "category_id": 1, "id": 483527, "split": "val", "sentences": [{"tokens": ["a", "messy", "baby", "eating", "while", "sitting", "in", "a", "stroller"], "raw": "A messy baby eating while sitting in a stroller.", "sent_id": 31621, "sent": "a messy baby eating while sitting in a stroller"}, {"tokens": ["a", "blonde", "baby", "with", "a", "yellow", "shirt", ",", "bib", ",", "and", "messy", "face", ",", "sitting", "in", "a", "grey", "stroller"], "raw": "a blonde baby with a yellow shirt, bib, and messy face, sitting in a grey stroller.", "sent_id": 31622, "sent": "a blonde baby with a yellow shirt , bib , and messy face , sitting in a grey stroller"}], "file_name": "COCO_train2014_000000100611_483527.jpg", "ann_id": 483527, "sent_ids": [31621, 31622], "ref_id": 17140}, {"segmentation": [[42.4, 2.74, 47.87, 33.51, 71.81, 51.97, 96.43, 71.12, 86.17, 73.17, 67.02, 83.43, 24.62, 99.85, 43.08, 110.1, 76.59, 95.74, 92.32, 110.1, 132.67, 118.31, 164.81, 119.68, 183.96, 114.89, 201.74, 112.15, 179.86, 97.11, 177.81, 91.64, 192.17, 77.28, 207.9, 72.49, 226.36, 67.7, 241.41, 59.5, 249.61, 54.71, 263.29, 45.82, 244.83, 45.82, 237.3, 45.82, 211.32, 51.29, 207.9, 51.29, 186.7, 60.18, 170.28, 61.55, 151.14, 69.75, 148.4, 70.44, 142.93, 66.34, 129.25, 54.03, 116.94, 42.4, 102.58, 32.14, 84.8, 26.67, 75.91, 19.15, 68.39, 12.99, 60.18, 6.15, 55.39, 5.47]], "area": 9939.577850000001, "iscrowd": 0, "image_id": 365231, "bbox": [24.62, 2.74, 238.67, 116.94], "category_id": 16, "id": 41098, "split": "val", "sentences": [{"tokens": ["a", "bird", "is", "flying", "in", "front", "of", "two", "others"], "raw": "A bird is flying in front of two others.", "sent_id": 31668, "sent": "a bird is flying in front of two others"}, {"tokens": ["a", "bird", "is", "flying", "in", "front", "of", "two", "others"], "raw": "A bird is flying in front of two others.", "sent_id": 31669, "sent": "a bird is flying in front of two others"}], "file_name": "COCO_train2014_000000365231_41098.jpg", "ann_id": 41098, "sent_ids": [31668, 31669], "ref_id": 17156}, {"segmentation": [[0.0, 441.0, 8.4, 448.93, 8.4, 458.84, 39.14, 491.56, 83.75, 543.11, 94.65, 573.84, 105.56, 619.45, 160.09, 640.0, 318.71, 640.0, 384.14, 640.0, 359.35, 614.49, 335.56, 589.71, 326.64, 575.83, 310.78, 583.76, 280.04, 602.59, 253.27, 598.63, 218.58, 553.03, 218.58, 526.26, 241.38, 498.5, 251.29, 472.72, 255.26, 447.94, 246.34, 436.04, 203.71, 425.14, 178.92, 387.46, 152.15, 367.64, 137.28, 312.12, 151.16, 289.32, 162.07, 275.44, 187.84, 270.48, 201.72, 252.64, 219.57, 228.84, 241.38, 227.85, 266.16, 225.87, 258.23, 214.96, 279.05, 186.21, 291.94, 170.35, 314.74, 153.5, 331.59, 132.68, 334.57, 114.83, 330.6, 73.2, 292.93, 37.51, 231.46, 20.65, 187.84, 24.62, 150.17, 53.37, 141.25, 87.08, 142.24, 122.77, 154.14, 132.68, 156.12, 143.58, 152.15, 158.46, 136.29, 162.42, 122.41, 182.25, 102.58, 189.19, 82.76, 200.09, 54.01, 210.01, 26.25, 234.79, 0.0, 271.47], [427.76, 349.79, 427.76, 366.65, 426.77, 371.6, 407.93, 381.52, 398.02, 393.41, 396.03, 399.36, 377.2, 407.29, 357.37, 411.26, 318.71, 430.09, 292.93, 441.0, 291.94, 453.89, 306.81, 460.83, 272.11, 477.68, 284.01, 489.58, 318.71, 524.28, 347.46, 514.36, 327.63, 529.23, 330.6, 539.15, 339.53, 539.15, 373.23, 515.35, 420.82, 469.75, 429.74, 460.83, 453.53, 443.97, 470.39, 421.17, 472.37, 379.53, 459.48, 359.71, 450.56, 351.77], [536.7, 606.81, 539.6, 632.06, 537.11, 640.0, 601.69, 640.0, 598.38, 629.58, 585.96, 613.43, 563.19, 602.26, 554.09, 599.77, 549.12, 602.67, 544.57, 603.5, 540.01, 606.4, 536.7, 603.5]], "area": 130088.26434999998, "iscrowd": 0, "image_id": 125774, "bbox": [0.0, 20.65, 601.69, 619.35], "category_id": 1, "id": 432688, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "the", "chair", "and", "holding", "the", "brown", "color", "teddy"], "raw": "A MAN SITTING THE CHAIR AND HOLDING THE BROWN COLOR TEDDY", "sent_id": 31691, "sent": "a man sitting the chair and holding the brown color teddy"}, {"tokens": ["a", "man", "wearing", "a", "car", "shirt", "and", "santa", "hat"], "raw": "A man wearing a car shirt and santa hat.", "sent_id": 31692, "sent": "a man wearing a car shirt and santa hat"}], "file_name": "COCO_train2014_000000125774_432688.jpg", "ann_id": 432688, "sent_ids": [31691, 31692], "ref_id": 17164}, {"segmentation": [[442.68, 374.39, 433.26, 354.38, 437.97, 330.83, 440.33, 307.29, 447.39, 269.61, 461.52, 243.71, 469.76, 230.76, 495.66, 223.69, 502.72, 223.69, 499.19, 211.92, 496.84, 197.79, 490.95, 178.96, 499.19, 173.07, 494.48, 157.76, 499.19, 142.46, 509.79, 131.86, 541.58, 125.98, 569.83, 134.22, 582.78, 161.3, 576.9, 190.73, 569.83, 208.39, 566.3, 211.92, 579.25, 224.87, 611.04, 246.06, 626.34, 270.79, 628.7, 313.17, 625.17, 336.72, 612.22, 348.49, 599.27, 341.43, 583.96, 335.54, 560.41, 330.83, 534.51, 340.25, 522.74, 353.2, 519.21, 373.22, 509.79, 379.1, 489.77, 382.64, 452.1, 384.99, 449.74, 370.86, 446.21, 369.68]], "area": 30327.412449999996, "iscrowd": 0, "image_id": 571719, "bbox": [433.26, 125.98, 195.44, 259.01], "category_id": 1, "id": 2205125, "split": "val", "sentences": [{"tokens": ["an", "older", "smiling", "woman", "in", "a", "purple", "blouse"], "raw": "An older smiling woman in a purple blouse.", "sent_id": 31797, "sent": "an older smiling woman in a purple blouse"}, {"tokens": ["a", "woman", "in", "a", "purple", "shirt", "and", "sunglasses", "laughing"], "raw": "A woman in a purple shirt and sunglasses laughing.", "sent_id": 31798, "sent": "a woman in a purple shirt and sunglasses laughing"}], "file_name": "COCO_train2014_000000571719_2205125.jpg", "ann_id": 2205125, "sent_ids": [31797, 31798], "ref_id": 17199}, {"segmentation": [[493.77, 395.11, 476.84, 390.54, 455.79, 371.32, 431.53, 326.48, 418.26, 283.92, 419.64, 259.21, 430.16, 229.01, 460.82, 191.48, 479.58, 172.26, 482.78, 163.11, 492.39, 167.69, 495.14, 178.21, 499.71, 181.87, 512.99, 163.11, 513.9, 144.81, 518.48, 161.28, 517.56, 164.49, 529.0, 161.74, 531.75, 171.35, 566.07, 208.87, 586.2, 234.96, 592.61, 246.4, 606.34, 266.99, 613.66, 296.27, 610.91, 322.36, 607.71, 336.08, 592.15, 367.2, 570.64, 390.54, 563.78, 393.74, 517.56, 397.86]], "area": 33473.2836, "iscrowd": 0, "image_id": 543838, "bbox": [418.26, 144.81, 195.4, 253.05], "category_id": 86, "id": 2197336, "split": "val", "sentences": [{"tokens": ["the", "vase", "from", "the", "right"], "raw": "the vase from the right", "sent_id": 31886, "sent": "the vase from the right"}, {"tokens": ["teardrop", "shaped", "vase", "on", "the", "right"], "raw": "Teardrop shaped vase on the right.", "sent_id": 31887, "sent": "teardrop shaped vase on the right"}], "file_name": "COCO_train2014_000000543838_2197336.jpg", "ann_id": 2197336, "sent_ids": [31886, 31887], "ref_id": 17235}, {"segmentation": [[561.98, 235.15, 565.21, 160.72, 616.99, 155.33, 640.0, 161.8, 638.56, 368.9, 560.9, 243.78]], "area": 11443.400999999994, "iscrowd": 0, "image_id": 550308, "bbox": [560.9, 155.33, 79.1, 213.57], "category_id": 54, "id": 1552299, "split": "val", "sentences": [{"tokens": ["the", "top", "piece", "of", "bread", "for", "the", "sandwich", "furthest", "to", "the", "right"], "raw": "The top piece of bread for the sandwich furthest to the right", "sent_id": 32123, "sent": "the top piece of bread for the sandwich furthest to the right"}, {"tokens": ["the", "top", "bun", "of", "the", "sandwich", "on", "the", "right"], "raw": "the top bun of the sandwich on the right", "sent_id": 32124, "sent": "the top bun of the sandwich on the right"}], "file_name": "COCO_train2014_000000550308_1552299.jpg", "ann_id": 1552299, "sent_ids": [32123, 32124], "ref_id": 17327}, {"segmentation": [[264.34, 154.55, 266.05, 150.01, 266.39, 148.76, 267.41, 146.83, 266.05, 140.93, 259.01, 128.8, 254.82, 119.73, 253.0, 117.12, 253.57, 114.62, 250.51, 104.3, 249.03, 85.36, 248.81, 79.69, 244.84, 72.09, 243.59, 70.05, 244.04, 67.78, 244.38, 66.87, 244.16, 64.72, 243.36, 62.34, 244.72, 60.41, 246.2, 59.05, 247.22, 60.41, 252.44, 66.87, 254.93, 70.05, 257.99, 70.39, 261.51, 68.8, 263.66, 69.82, 263.78, 71.18, 258.11, 75.04, 256.86, 78.1, 256.75, 86.27, 258.9, 98.18, 262.53, 109.18, 267.97, 116.78, 275.35, 125.17, 278.52, 126.19, 279.88, 125.85, 279.77, 122.45, 279.54, 118.14, 280.0, 115.87, 280.79, 114.39, 284.42, 107.14, 285.89, 103.28, 290.43, 101.24, 292.02, 100.9, 299.16, 103.96, 302.57, 107.36, 307.67, 119.16, 304.72, 124.6, 302.45, 127.89, 300.53, 132.43, 308.81, 139.12, 314.93, 146.95, 313.34, 152.16, 311.87, 153.75, 304.38, 157.38, 301.09, 170.31, 300.53, 179.61, 303.25, 191.75, 299.5, 204.45, 299.5, 216.7, 295.19, 241.99, 294.17, 246.64, 293.27, 250.61, 297.24, 264.79, 296.22, 281.23, 294.97, 298.81, 297.58, 302.9, 301.43, 308.68, 300.53, 311.63, 293.72, 314.92, 287.82, 314.92, 280.68, 315.26, 278.41, 314.13, 278.18, 311.86, 279.43, 308.46, 280.79, 305.96, 282.95, 301.99, 286.23, 301.65, 286.92, 288.83, 285.33, 275.34, 283.17, 260.03, 279.66, 255.38, 279.09, 251.18, 279.2, 241.08, 276.71, 236.43, 274.1, 222.26, 273.08, 215.45, 268.2, 221.12, 265.48, 223.84, 262.76, 222.82, 260.49, 223.05, 256.52, 233.94, 251.76, 247.89, 249.26, 254.13, 248.47, 259.57, 248.58, 264.22, 243.25, 270.01, 235.88, 273.18, 225.9, 272.39, 223.29, 270.8, 220.45, 269.33, 220.0, 267.28, 222.61, 263.88, 224.87, 262.07, 235.42, 256.62, 238.03, 258.1, 240.87, 257.3, 240.98, 255.6, 241.55, 238.36, 243.48, 233.94, 246.42, 221.12, 248.24, 217.15, 248.69, 214.77, 247.33, 210.57, 251.53, 197.87, 253.23, 190.61, 253.68, 182.56, 260.72, 165.09]], "area": 7822.224049999999, "iscrowd": 0, "image_id": 111000, "bbox": [220.0, 59.05, 94.93, 256.21], "category_id": 1, "id": 2198394, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "the", "middle", "wearing", "a", "pure", "white", "t", "-", "shirt"], "raw": "a person in the middle wearing a pure white t-shirt", "sent_id": 32147, "sent": "a person in the middle wearing a pure white t - shirt"}, {"tokens": ["a", "man", "jump", "and", "to", "try", "catch", "the", "flying", "plate", "and", "wearing", "white", "color", "t", "shirt"], "raw": "A MAN JUMP AND TO TRY CATCH THE FLYING PLATE AND WEARING WHITE COLOR T SHIRT", "sent_id": 32148, "sent": "a man jump and to try catch the flying plate and wearing white color t shirt"}], "file_name": "COCO_train2014_000000111000_2198394.jpg", "ann_id": 2198394, "sent_ids": [32147, 32148], "ref_id": 17339}, {"segmentation": [[5.75, 343.73, 181.21, 355.24, 201.35, 569.53, 174.02, 579.6, 2.88, 589.66]], "area": 43783.952999999994, "iscrowd": 0, "image_id": 500662, "bbox": [2.88, 343.73, 198.47, 245.93], "category_id": 33, "id": 1187659, "split": "val", "sentences": [{"tokens": ["a", "blue", "piece", "of", "luggage", "with", "a", "blue", "pattern", "on", "it"], "raw": "A blue piece of luggage with a blue pattern on it.", "sent_id": 32254, "sent": "a blue piece of luggage with a blue pattern on it"}, {"tokens": ["a", "blue", "suitcase", "which", "is", "in", "the", "front", "of", "other", "blue", "suitcase", "with", "checked", "designs"], "raw": "A blue suitcase which is in the front of other blue suitcase with checked designs", "sent_id": 32255, "sent": "a blue suitcase which is in the front of other blue suitcase with checked designs"}], "file_name": "COCO_train2014_000000500662_1187659.jpg", "ann_id": 1187659, "sent_ids": [32254, 32255], "ref_id": 17374}, {"segmentation": [[0.0, 527.71, 20.5, 507.76, 13.64, 500.28, 2.42, 480.34, 0.0, 459.15, 6.79, 427.37, 16.76, 403.69, 37.32, 403.69, 56.02, 403.06, 77.21, 407.43, 85.31, 410.54, 95.28, 417.4, 96.53, 427.99, 100.89, 446.69, 106.5, 472.86, 101.51, 484.7, 93.41, 489.69, 82.19, 499.66, 79.08, 506.52, 76.58, 517.11, 80.95, 526.46, 90.92, 539.55, 98.4, 553.26, 111.48, 573.82, 130.18, 590.65, 134.54, 597.51, 145.14, 593.14, 157.6, 594.39, 161.97, 607.48, 161.34, 615.58, 155.73, 633.03, 135.79, 640.0, 1.18, 639.88]], "area": 24720.231649999998, "iscrowd": 0, "image_id": 330785, "bbox": [0.0, 403.06, 161.97, 236.94], "category_id": 1, "id": 1717998, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "grey", "shirt", "with", "a", "purse", "walking", "by", "a", "pile", "of", "plush", "bears"], "raw": "A woman in a grey shirt with a purse walking by a pile of plush bears.", "sent_id": 32300, "sent": "a woman in a grey shirt with a purse walking by a pile of plush bears"}, {"tokens": ["woman", "with", "short", "bob", "haircut", "and", "glasses", "with", "a", "purse", "on", "her", "right", "shoulder"], "raw": "Woman with short bob haircut and glasses with a purse on her right shoulder", "sent_id": 32301, "sent": "woman with short bob haircut and glasses with a purse on her right shoulder"}], "file_name": "COCO_train2014_000000330785_1717998.jpg", "ann_id": 1717998, "sent_ids": [32300, 32301], "ref_id": 17390}, {"segmentation": [[73.35, 474.61, 119.73, 472.45, 134.83, 471.37, 131.6, 338.7, 111.1, 197.39, 103.55, 160.72, 97.08, 148.85, 100.31, 134.83, 117.57, 129.44, 128.36, 136.99, 133.75, 106.79, 135.91, 96.0, 129.44, 76.58, 135.91, 65.8, 135.91, 51.78, 101.39, 34.52, 49.62, 39.91, 47.46, 51.78, 50.7, 93.84, 58.25, 111.1, 52.85, 127.28, 1.08, 186.61, 2.16, 326.83, 16.18, 351.64, 31.28, 366.74, 36.67, 372.13, 42.07, 403.42, 59.33, 442.25, 66.88, 467.06, 72.27, 474.61]], "area": 41935.33734999999, "iscrowd": 0, "image_id": 449158, "bbox": [1.08, 34.52, 134.83, 440.09], "category_id": 1, "id": 255756, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "green", "shirt", "and", "the", "wrist", "watch"], "raw": "The man with the green shirt and the wrist watch.", "sent_id": 32348, "sent": "the man with the green shirt and the wrist watch"}, {"tokens": ["the", "bearded", "standing", "man", "in", "green", "shirt", "and", "jeans", "wearing", "sunglasses", "and", "wristwatch"], "raw": "The bearded standing man in green shirt and jeans wearing sunglasses and wristwatch.", "sent_id": 32349, "sent": "the bearded standing man in green shirt and jeans wearing sunglasses and wristwatch"}], "file_name": "COCO_train2014_000000449158_255756.jpg", "ann_id": 255756, "sent_ids": [32348, 32349], "ref_id": 17408}, {"segmentation": [[232.91, 373.47, 227.3, 368.77, 224.23, 368.77, 219.53, 364.61, 215.19, 359.91, 225.13, 346.7, 232.37, 332.23, 233.82, 327.17, 240.51, 317.22, 247.02, 311.25, 228.21, 302.75, 222.24, 300.4, 227.85, 291.72, 233.64, 286.65, 265.11, 300.4, 268.18, 303.47, 272.16, 307.27, 272.7, 309.8, 269.09, 315.95, 261.13, 325.9, 254.07, 334.4, 245.93, 343.08, 239.42, 349.23, 233.82, 356.29, 230.74, 361.35, 229.84, 365.69, 231.1, 369.49], [275.69, 261.08, 288.9, 256.92, 295.23, 261.08, 296.49, 263.43, 294.86, 267.23, 293.78, 269.22, 291.43, 270.49, 288.35, 271.39, 286.54, 271.39, 285.1, 269.76, 279.31, 271.03, 274.06, 265.42, 264.66, 260.72, 256.7, 253.85, 251.45, 248.78, 243.86, 244.26, 235.72, 239.2, 229.75, 237.03, 226.31, 232.69, 225.41, 226.9, 226.86, 218.94, 232.46, 202.48, 237.43, 191.32, 243.06, 178.3, 251.85, 171.97, 264.17, 164.58, 269.45, 163.53, 276.13, 162.12, 270.99, 173.2, 269.6, 182.25, 267.51, 185.97, 265.88, 191.54, 266.58, 194.79, 265.19, 201.75, 258.45, 207.09, 254.97, 212.43, 251.26, 221.48, 247.31, 226.13, 246.61, 229.61, 245.69, 234.72, 243.13, 238.43, 249.83, 244.74, 258.56, 251.79, 265.0, 256.99, 272.96, 260.52]], "area": 4054.4029499999997, "iscrowd": 0, "image_id": 97563, "bbox": [215.19, 162.12, 81.3, 211.35], "category_id": 1, "id": 1758505, "split": "val", "sentences": [{"tokens": ["the", "man", "running", "behind", "the", "frisbee"], "raw": "The man running behind the frisbee", "sent_id": 32394, "sent": "the man running behind the frisbee"}, {"tokens": ["a", "guy", "with", "adidas", "sockjs"], "raw": "a guy with adidas sockjs", "sent_id": 32395, "sent": "a guy with adidas sockjs"}], "file_name": "COCO_train2014_000000097563_1758505.jpg", "ann_id": 1758505, "sent_ids": [32394, 32395], "ref_id": 17427}, {"segmentation": [[63.33, 3.9, 54.69, 72.03, 65.25, 105.61, 82.52, 132.48, 108.43, 146.88, 118.98, 155.51, 129.54, 161.27, 139.13, 167.99, 143.93, 186.22, 151.61, 172.78, 161.2, 154.55, 174.64, 145.92, 192.87, 139.2, 206.3, 136.32, 219.74, 124.81, 222.62, 117.13, 227.41, 99.86, 229.33, 91.22, 232.21, 82.59, 234.13, 58.6, 236.05, 40.37, 229.33, 15.42, 223.58, 1.98, 223.58, 1.98]], "area": 23976.3409, "iscrowd": 0, "image_id": 431112, "bbox": [54.69, 1.98, 181.36, 184.24], "category_id": 46, "id": 663601, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "water"], "raw": "A glass of water.", "sent_id": 32407, "sent": "a glass of water"}, {"tokens": ["glass", "of", "water", "in", "table"], "raw": "glass of water in table", "sent_id": 32408, "sent": "glass of water in table"}], "file_name": "COCO_train2014_000000431112_663601.jpg", "ann_id": 663601, "sent_ids": [32407, 32408], "ref_id": 17433}, {"segmentation": [[77.23, 173.54, 82.81, 166.43, 82.81, 159.83, 82.81, 153.73, 82.81, 147.13, 82.81, 143.06, 79.77, 141.54, 81.8, 138.49, 86.88, 136.46, 93.99, 137.98, 101.1, 142.05, 108.72, 144.59, 111.77, 147.63, 111.77, 150.17, 115.83, 148.65, 121.93, 152.21, 121.93, 158.81, 122.94, 158.3, 124.47, 153.22, 136.66, 158.81, 142.25, 162.37, 134.63, 166.94, 130.05, 175.57, 123.96, 180.65, 118.88, 179.13, 114.82, 191.32, 114.31, 203.51, 114.31, 220.27, 115.32, 229.92, 116.85, 235.51, 128.02, 247.19, 132.09, 252.27, 122.94, 252.78, 119.9, 262.43, 116.85, 266.49, 107.7, 271.57, 98.56, 283.26, 106.69, 282.75, 105.16, 287.83, 99.58, 289.86, 96.53, 296.97, 97.55, 302.05, 92.97, 304.08, 95.51, 311.7, 101.1, 314.75, 92.97, 320.85, 89.93, 326.94, 85.35, 328.97, 79.26, 331.0, 67.07, 333.04, 57.42, 332.02, 56.4, 321.35, 52.34, 319.83, 45.23, 318.31, 36.08, 312.72, 30.5, 310.18, 15.77, 309.67, 7.13, 302.05, 7.13, 293.42, 7.13, 282.24, 6.62, 273.61, 3.57, 263.96, 1.03, 261.42, 0.53, 225.35, 1.03, 209.6, 1.54, 192.84, 7.64, 187.76, 18.31, 181.16, 29.99, 175.57, 44.72, 171.51, 52.34, 171.51, 63.51, 171.51, 70.62, 171.51]], "area": 17214.739849999998, "iscrowd": 0, "image_id": 566319, "bbox": [0.53, 136.46, 141.72, 196.58], "category_id": 64, "id": 292128, "split": "val", "sentences": [{"tokens": ["the", "smaller", "of", "the", "two", "clay", "pots"], "raw": "The smaller of the two clay pots.", "sent_id": 32409, "sent": "the smaller of the two clay pots"}, {"tokens": ["the", "left", "pot", "in", "the", "right", "hand", "picture"], "raw": "the left pot in the right hand picture", "sent_id": 32410, "sent": "the left pot in the right hand picture"}], "file_name": "COCO_train2014_000000566319_292128.jpg", "ann_id": 292128, "sent_ids": [32409, 32410], "ref_id": 17434}, {"segmentation": [[107.04, 377.62, 114.06, 353.55, 111.3, 293.12, 110.55, 278.32, 83.97, 260.52, 69.68, 250.99, 45.11, 243.47, 15.02, 236.2, 0.0, 220.65, 0.48, 296.38, 0.0, 300.39, 0.0, 350.54, 0.0, 400.44, 8.0, 385.14, 14.77, 375.11, 37.34, 364.33, 43.1, 363.33, 49.87, 355.3, 48.87, 346.02, 49.87, 318.94, 56.14, 311.67, 66.67, 306.66, 76.95, 308.92, 87.73, 316.69, 89.74, 324.46, 88.24, 334.99, 89.99, 340.01, 87.99, 345.27, 81.22, 352.79, 79.46, 362.57, 103.28, 375.11]], "area": 11505.175649999997, "iscrowd": 0, "image_id": 457225, "bbox": [0.0, 220.65, 114.06, 179.79], "category_id": 22, "id": 585886, "split": "val", "sentences": [{"tokens": ["the", "elephant", "behind", "the", "man", "wearing", "a", "gray", "shirt"], "raw": "The elephant behind the man wearing a gray shirt.", "sent_id": 32416, "sent": "the elephant behind the man wearing a gray shirt"}], "file_name": "COCO_train2014_000000457225_585886.jpg", "ann_id": 585886, "sent_ids": [32416], "ref_id": 17438}, {"segmentation": [[634.98, 255.81, 616.68, 195.55, 609.15, 180.48, 604.84, 146.04, 597.31, 119.13, 581.17, 98.68, 557.49, 101.91, 542.42, 112.68, 532.74, 121.29, 527.35, 140.66, 529.51, 163.26, 539.19, 178.33, 542.42, 180.48, 542.42, 191.24, 540.27, 208.46, 521.97, 227.83, 498.3, 238.59, 462.78, 248.28, 438.03, 246.13, 415.43, 241.82, 405.74, 232.14, 393.9, 227.83, 385.29, 224.6, 384.22, 234.29, 383.14, 242.9, 376.68, 240.75, 370.22, 232.14, 370.22, 238.59, 373.45, 270.88, 388.52, 270.88, 406.82, 276.26, 421.88, 280.57, 446.64, 284.87, 464.93, 288.1, 481.08, 298.86, 463.86, 340.84, 463.86, 345.14, 470.31, 362.36, 473.54, 367.74, 474.62, 382.81, 477.85, 404.33, 480.0, 417.25, 480.0, 425.86, 480.0, 445.23, 474.62, 464.6, 471.39, 466.76, 484.3, 468.91, 506.91, 468.91, 509.06, 468.91, 538.12, 468.91, 546.73, 468.91, 571.48, 467.83, 591.93, 469.99, 608.07, 468.91, 625.29, 469.99, 628.52, 469.99]], "area": 50608.03015, "iscrowd": 0, "image_id": 136651, "bbox": [370.22, 98.68, 264.76, 371.31], "category_id": 1, "id": 192712, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "bink", "sweater", "covering", "a", "white", "dress", "with", "pink", "flowers"], "raw": "A woman in a bink sweater covering a white dress with pink flowers", "sent_id": 32549, "sent": "a woman in a bink sweater covering a white dress with pink flowers"}, {"tokens": ["a", "woman", "wearing", "a", "backpack", "taking", "a", "picture", "on", "her", "phone"], "raw": "A woman wearing a backpack taking a picture on her phone.", "sent_id": 32550, "sent": "a woman wearing a backpack taking a picture on her phone"}], "file_name": "COCO_train2014_000000136651_192712.jpg", "ann_id": 192712, "sent_ids": [32549, 32550], "ref_id": 17487}, {"segmentation": [[495.17, 161.5, 513.75, 173.57, 547.2, 182.86, 585.29, 207.02, 589.01, 219.1, 607.59, 235.82, 609.45, 243.25, 626.17, 255.33, 606.66, 251.61, 612.23, 274.84, 615.02, 280.41, 600.15, 269.26, 590.86, 269.26, 585.29, 261.83, 564.85, 262.76, 541.63, 253.47, 536.05, 253.47, 531.73, 277.08, 532.55, 286.92, 528.45, 289.38, 521.89, 286.92, 524.35, 275.44, 521.07, 261.5, 519.43, 252.48, 517.79, 245.92, 509.59, 245.1, 507.95, 264.78, 497.29, 292.66, 494.01, 294.3, 494.01, 289.38, 493.19, 267.24, 489.91, 239.36, 474.33, 222.14, 462.85, 195.07, 472.69, 186.87, 466.13, 174.57, 470.23, 157.35, 470.23, 153.25, 459.57, 156.53, 450.55, 164.73, 447.27, 160.63, 459.57, 144.23, 479.25, 131.11, 489.91, 141.77, 493.19, 155.71]], "area": 11247.434250000004, "iscrowd": 0, "image_id": 266816, "bbox": [447.27, 131.11, 178.9, 163.19], "category_id": 16, "id": 42998, "split": "val", "sentences": [{"tokens": ["a", "bird", "facing", "towards", "the", "cat", "in", "the", "picture"], "raw": "A bird facing towards the cat in the picture.", "sent_id": 32607, "sent": "a bird facing towards the cat in the picture"}, {"tokens": ["the", "bird", "that", "is", "farthest", "from", "the", "cat"], "raw": "The bird that is farthest from the cat.", "sent_id": 32608, "sent": "the bird that is farthest from the cat"}], "file_name": "COCO_train2014_000000266816_42998.jpg", "ann_id": 42998, "sent_ids": [32607, 32608], "ref_id": 17508}, {"segmentation": [[260.95, 477.01, 255.74, 421.6, 283.12, 367.49, 282.46, 418.99, 291.59, 418.34, 292.9, 345.32, 296.15, 327.07, 294.2, 319.9, 236.18, 303.6, 210.1, 299.69, 187.94, 220.15, 179.46, 210.38, 169.68, 214.29, 144.91, 221.46, 130.57, 232.54, 125.35, 243.62, 120.14, 243.51, 114.27, 247.42, 122.74, 289.8, 133.18, 371.14, 133.83, 401.13, 141.65, 429.81, 145.56, 448.72, 150.13, 459.8, 159.25, 457.19, 161.86, 440.9, 159.9, 422.64, 160.56, 408.3, 238.79, 431.12, 242.05, 456.54, 245.96, 475.45, 259.65, 477.98]], "area": 25815.474799999993, "iscrowd": 0, "image_id": 140821, "bbox": [114.27, 210.38, 181.88, 267.6], "category_id": 62, "id": 374027, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "with", "a", "black", "bag", "sitting", "on", "top", "of", "it", "next", "to", "a", "toilet"], "raw": "A wooden chair with a black bag sitting on top of it next to a toilet.", "sent_id": 32619, "sent": "a wooden chair with a black bag sitting on top of it next to a toilet"}, {"tokens": ["the", "wood", "chair", "with", "the", "bag", "on", "it"], "raw": "The wood chair with the bag on it", "sent_id": 32620, "sent": "the wood chair with the bag on it"}], "file_name": "COCO_train2014_000000140821_374027.jpg", "ann_id": 374027, "sent_ids": [32619, 32620], "ref_id": 17512}, {"segmentation": [[113.04, 22.34, 82.37, 38.06, 56.68, 92.89, 42.88, 133.15, 28.31, 182.23, 12.2, 212.9, 4.53, 252.4, 0.0, 291.89, 9.9, 298.79, 29.07, 326.78, 40.19, 344.42, 56.68, 354.01, 56.3, 370.11, 57.83, 417.66, 55.91, 426.0, 257.22, 426.0, 236.89, 340.97, 239.96, 295.34, 227.69, 251.24, 266.8, 273.87, 293.64, 244.34, 271.79, 241.28, 236.13, 233.61, 228.84, 228.24, 203.15, 192.96, 198.93, 182.99, 200.85, 135.83, 190.11, 81.38, 185.9, 60.68, 180.53, 44.96, 169.41, 33.07, 142.95, 26.55, 123.78, 21.57]], "area": 73185.81519999998, "iscrowd": 0, "image_id": 543642, "bbox": [0.0, 21.57, 293.64, 404.43], "category_id": 1, "id": 429146, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "sunglasses", "in", "her", "hair"], "raw": "A woman with sunglasses in her hair.", "sent_id": 32700, "sent": "a woman with sunglasses in her hair"}, {"tokens": ["a", "woman"], "raw": "A woman.", "sent_id": 32701, "sent": "a woman"}], "file_name": "COCO_train2014_000000543642_429146.jpg", "ann_id": 429146, "sent_ids": [32700, 32701], "ref_id": 17537}, {"segmentation": [[89.17, 601.17, 120.81, 573.84, 110.74, 522.07, 107.87, 486.11, 90.61, 467.42, 73.35, 465.98, 73.35, 421.39, 79.1, 365.3, 80.54, 346.61, 87.73, 306.34, 69.03, 313.53, 53.21, 296.27, 73.35, 230.11, 89.17, 220.04, 97.8, 202.79, 99.24, 158.2, 102.11, 142.38, 130.88, 132.31, 143.82, 132.31, 139.51, 153.89, 152.45, 179.78, 146.7, 207.1, 146.7, 217.17, 182.65, 231.55, 204.22, 307.78, 234.43, 395.51, 235.87, 412.76, 221.48, 422.83, 215.73, 419.96, 215.73, 381.12, 179.78, 302.02, 178.34, 330.79, 186.97, 402.7, 205.66, 451.6, 208.54, 455.91, 172.58, 480.36, 179.78, 520.63, 169.71, 569.53, 191.28, 606.92, 168.27, 619.87, 149.57, 589.66, 143.82, 535.01, 142.38, 589.66, 142.38, 598.29, 110.74, 611.24]], "area": 44023.3959, "iscrowd": 0, "image_id": 171210, "bbox": [53.21, 132.31, 182.66, 487.56], "category_id": 1, "id": 468285, "split": "val", "sentences": [{"tokens": ["lady", "walking", "and", "talking", "on", "a", "cell", "phone"], "raw": "Lady walking and talking on a cell phone.", "sent_id": 32797, "sent": "lady walking and talking on a cell phone"}, {"tokens": ["a", "woman", "in", "a", "black", "tank", "top", "and", "skirt", "on", "a", "phone"], "raw": "A woman in a black tank top and skirt on a phone.", "sent_id": 32798, "sent": "a woman in a black tank top and skirt on a phone"}], "file_name": "COCO_train2014_000000171210_468285.jpg", "ann_id": 468285, "sent_ids": [32797, 32798], "ref_id": 17579}, {"segmentation": [[350.32, 339.85, 344.48, 378.24, 336.13, 374.9, 341.14, 339.85, 351.16, 338.18], [343.64, 303.98, 341.97, 285.62, 339.47, 282.28, 343.64, 277.27, 365.34, 274.77, 393.7, 273.1, 393.7, 268.1, 421.24, 275.6, 427.09, 316.49, 427.92, 339.02, 427.92, 381.57, 426.25, 409.94, 417.9, 409.1, 417.9, 319.83, 402.89, 315.65, 399.55, 351.53, 393.7, 345.7, 392.87, 313.15, 354.49, 298.13, 351.99, 306.48, 347.82, 303.14], [449.62, 307.32, 462.13, 298.97, 466.3, 303.14, 470.47, 380.74, 477.98, 375.73, 473.81, 309.81, 472.97, 279.78, 464.63, 279.78, 459.62, 285.62, 449.62, 282.28, 449.62, 277.27, 444.61, 280.61, 448.78, 308.14], [477.15, 223.87, 475.48, 218.03, 385.37, 211.36, 383.7, 217.19, 477.15, 224.71]], "area": 6139.221050000001, "iscrowd": 0, "image_id": 257102, "bbox": [336.13, 211.36, 141.85, 198.58], "category_id": 62, "id": 1584143, "split": "val", "sentences": [{"tokens": ["chair", "in", "kitchen", "near", "counter", "top"], "raw": "Chair in kitchen near counter top.", "sent_id": 32844, "sent": "chair in kitchen near counter top"}], "file_name": "COCO_train2014_000000257102_1584143.jpg", "ann_id": 1584143, "sent_ids": [32844], "ref_id": 17598}, {"segmentation": [[402.27, 349.55, 401.12, 328.92, 398.83, 306.0, 403.42, 287.66, 410.29, 280.79, 428.63, 280.79, 452.7, 283.08, 482.49, 286.52, 511.15, 284.22, 526.04, 281.93, 550.11, 278.49, 575.33, 278.49, 595.96, 281.93, 608.56, 283.08, 607.42, 312.88, 607.42, 339.24, 613.15, 359.87, 613.15, 366.74, 599.39, 373.62, 562.72, 378.2, 566.16, 395.39, 518.02, 396.54, 473.33, 396.54, 403.42, 386.22, 396.54, 383.93, 403.42, 363.3]], "area": 22397.519199999995, "iscrowd": 0, "image_id": 404899, "bbox": [396.54, 278.49, 216.61, 118.05], "category_id": 78, "id": 1118849, "split": "val", "sentences": [{"tokens": ["the", "oven", "on", "which", "the", "girl", "has", "her", "left", "hand"], "raw": "The oven on which the girl has her left hand", "sent_id": 32852, "sent": "the oven on which the girl has her left hand"}, {"tokens": ["a", "black", "and", "white", "microwave", "next", "to", "a", "white", "bowl"], "raw": "A black and white microwave next to a white bowl.", "sent_id": 32853, "sent": "a black and white microwave next to a white bowl"}], "file_name": "COCO_train2014_000000404899_1118849.jpg", "ann_id": 1118849, "sent_ids": [32852, 32853], "ref_id": 17602}, {"segmentation": [[631.49, 425.59, 622.38, 464.38, 620.7, 473.82, 616.65, 474.49, 612.94, 474.49, 610.58, 479.89, 480.05, 478.88, 479.04, 479.55, 420.02, 472.81, 395.39, 480.0, 201.46, 480.0, 192.35, 454.93, 190.33, 450.55, 185.27, 421.2, 176.16, 409.4, 175.49, 397.59, 179.54, 396.58, 178.19, 391.52, 167.73, 389.16, 163.01, 373.98, 164.69, 370.27, 160.65, 357.79, 171.44, 334.18, 175.83, 332.5, 179.87, 332.16, 202.81, 327.1, 208.2, 324.4, 225.07, 321.71, 226.75, 321.71, 314.45, 317.32, 401.13, 313.95, 460.49, 315.3, 526.26, 315.97, 579.55, 317.66, 603.83, 320.69, 609.23, 324.07, 614.96, 326.43, 629.13, 327.1, 634.86, 328.11, 640.0, 336.21, 640.0, 354.71, 636.4, 365.13, 636.4, 377.93, 638.19, 395.8, 636.11, 398.77, 629.85, 406.81, 629.85, 408.3, 628.96, 414.85, 628.36, 418.72, 630.45, 423.78]], "area": 72847.11490000002, "iscrowd": 0, "image_id": 212635, "bbox": [160.65, 313.95, 479.35, 166.05], "category_id": 63, "id": 117877, "split": "val", "sentences": [{"tokens": ["white", "colour", "shoppa"], "raw": "white colour shoppa", "sent_id": 32868, "sent": "white colour shoppa"}, {"tokens": ["a", "sofa", "covered", "with", "2", "blankets", "and", "has", "3", "pillows", "on", "it"], "raw": "A sofa covered with 2 blankets and has 3 pillows on it.", "sent_id": 32869, "sent": "a sofa covered with 2 blankets and has 3 pillows on it"}], "file_name": "COCO_train2014_000000212635_117877.jpg", "ann_id": 117877, "sent_ids": [32868, 32869], "ref_id": 17609}, {"segmentation": [[213.56, 198.27, 213.56, 187.92, 213.27, 180.15, 220.17, 110.81, 227.08, 88.66, 232.54, 79.16, 242.33, 72.54, 256.71, 67.94, 321.16, 61.32, 465.02, 57.87, 509.61, 57.87, 536.08, 60.17, 551.33, 64.78, 564.28, 76.28, 574.06, 87.5, 578.95, 97.86, 592.47, 143.32, 593.62, 160.3, 594.49, 171.8, 594.2, 179.28, 593.62, 184.46, 602.25, 200.0, 612.61, 236.25, 621.24, 276.24, 624.7, 296.1, 621.24, 310.77, 613.76, 324.0, 601.1, 336.95, 589.59, 342.7, 576.94, 347.88, 512.2, 355.94, 347.05, 363.13, 277.14, 361.98, 240.03, 359.39, 226.5, 355.36, 213.56, 346.73, 205.21, 335.51, 200.32, 314.51, 203.49, 265.89, 210.68, 214.1, 213.56, 204.03]], "area": 114580.69880000001, "iscrowd": 0, "image_id": 510976, "bbox": [200.32, 57.87, 424.38, 305.26], "category_id": 77, "id": 329367, "split": "val", "sentences": [{"tokens": ["phone", "that", "slides", "up"], "raw": "phone that slides up", "sent_id": 33027, "sent": "phone that slides up"}, {"tokens": ["phone", "on", "right"], "raw": "phone on right", "sent_id": 33028, "sent": "phone on right"}], "file_name": "COCO_train2014_000000510976_329367.jpg", "ann_id": 329367, "sent_ids": [33027, 33028], "ref_id": 17679}, {"segmentation": [[191.57, 296.99, 198.03, 188.29, 207.71, 166.76, 230.31, 159.23, 249.69, 152.77, 302.42, 162.46, 351.93, 180.75, 378.83, 197.97, 393.9, 225.96, 413.27, 269.0, 450.94, 380.93, 454.17, 408.91, 436.95, 402.46, 426.19, 430.44, 393.9, 428.29, 294.89, 365.87, 192.65, 303.44]], "area": 45786.47055, "iscrowd": 0, "image_id": 219943, "bbox": [191.57, 152.77, 262.6, 277.67], "category_id": 54, "id": 313306, "split": "val", "sentences": [{"tokens": ["half", "of", "a", "sandwich", "laying", "between", "fries", "and", "a", "pickle"], "raw": "Half of a sandwich laying between fries and a pickle", "sent_id": 33066, "sent": "half of a sandwich laying between fries and a pickle"}, {"tokens": ["a", "half", "of", "a", "sandwich", "up", "against", "a", "pickle", "and", "fries", "behind", "it"], "raw": "A half of a sandwich up against a pickle and fries behind it.", "sent_id": 33067, "sent": "a half of a sandwich up against a pickle and fries behind it"}], "file_name": "COCO_train2014_000000219943_313306.jpg", "ann_id": 313306, "sent_ids": [33066, 33067], "ref_id": 17693}, {"segmentation": [[174.16, 219.1, 193.26, 222.47, 187.64, 204.49, 170.79, 197.75, 156.18, 140.45, 157.3, 113.48, 168.54, 126.97, 189.89, 170.79, 212.36, 214.61, 246.07, 231.46, 278.65, 240.45, 285.39, 303.37, 298.88, 330.34, 298.88, 359.55, 302.25, 404.49, 287.64, 395.51, 282.02, 360.67, 279.78, 322.47, 279.78, 301.12, 259.55, 279.78, 234.83, 274.16, 197.75, 240.45, 198.88, 223.6]], "area": 7446.659450000002, "iscrowd": 0, "image_id": 510611, "bbox": [156.18, 113.48, 146.07, 291.01], "category_id": 25, "id": 596247, "split": "val", "sentences": [{"tokens": ["a", "large", "giraffe", "standing", "behind", "the", "tree"], "raw": "A large giraffe standing behind the tree.", "sent_id": 33103, "sent": "a large giraffe standing behind the tree"}, {"tokens": ["the", "tallest", "giraffe", "with", "its", "face", "hidden"], "raw": "The tallest giraffe with its face hidden.", "sent_id": 33104, "sent": "the tallest giraffe with its face hidden"}], "file_name": "COCO_train2014_000000510611_596247.jpg", "ann_id": 596247, "sent_ids": [33103, 33104], "ref_id": 17710}, {"segmentation": [[266.44, 561.17, 317.25, 629.84, 480.0, 632.58, 479.31, 436.19, 480.0, 404.6, 329.61, 407.35, 315.88, 425.2, 293.91, 437.56, 276.05, 419.71, 232.1, 430.7]], "area": 47348.1559, "iscrowd": 0, "image_id": 228215, "bbox": [232.1, 404.6, 247.9, 227.98], "category_id": 63, "id": 113304, "split": "val", "sentences": [{"tokens": ["a", "brown", "couch", "with", "a", "blue", "jacket"], "raw": "A brown couch with a blue jacket.", "sent_id": 33266, "sent": "a brown couch with a blue jacket"}, {"tokens": ["a", "couch", "with", "blue", "cover"], "raw": "a couch with blue cover", "sent_id": 33267, "sent": "a couch with blue cover"}], "file_name": "COCO_train2014_000000228215_113304.jpg", "ann_id": 113304, "sent_ids": [33266, 33267], "ref_id": 17772}, {"segmentation": [[120.95, 329.38, 110.39, 273.65, 105.11, 246.08, 98.66, 229.07, 98.66, 209.13, 104.53, 185.66, 118.6, 169.24, 127.99, 160.44, 152.63, 148.71, 164.36, 139.91, 162.6, 137.56, 125.06, 148.71, 96.31, 175.1, 89.86, 200.91, 91.03, 234.35, 96.9, 254.29, 100.42, 275.41, 122.12, 349.91]], "area": 2139.85005, "iscrowd": 0, "image_id": 58403, "bbox": [89.86, 137.56, 74.5, 212.35], "category_id": 62, "id": 375853, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "the", "chair", "that", "the", "girl", "in", "the", "purple", "t", "-", "shirt", "is", "sitting", "in"], "raw": "The back of the chair that the girl in the purple t-shirt is sitting in", "sent_id": 33319, "sent": "the back of the chair that the girl in the purple t - shirt is sitting in"}, {"tokens": ["a", "chair", "with", "a", "metal", "frame"], "raw": "A chair with a metal frame.", "sent_id": 33320, "sent": "a chair with a metal frame"}], "file_name": "COCO_train2014_000000058403_375853.jpg", "ann_id": 375853, "sent_ids": [33319, 33320], "ref_id": 17792}, {"segmentation": [[4.31, 540.76, 174.02, 516.31, 79.1, 627.06, 349.48, 628.49, 427.0, 563.78, 417.08, 418.52, 342.29, 353.8, 270.38, 345.17, 211.42, 340.85, 165.39, 343.73, 100.67, 362.43, 60.4, 396.94, 7.19, 411.33]], "area": 95503.17979999998, "iscrowd": 0, "image_id": 329724, "bbox": [4.31, 340.85, 422.69, 287.64], "category_id": 59, "id": 1072014, "split": "val", "sentences": [{"tokens": ["pizza", "pie", "in", "a", "box", "with", "one", "slice", "missing"], "raw": "Pizza pie in a box with one slice missing", "sent_id": 33328, "sent": "pizza pie in a box with one slice missing"}, {"tokens": ["pizza", "with", "a", "slice", "missing"], "raw": "Pizza with a slice missing.", "sent_id": 33329, "sent": "pizza with a slice missing"}], "file_name": "COCO_train2014_000000329724_1072014.jpg", "ann_id": 1072014, "sent_ids": [33328, 33329], "ref_id": 17795}, {"segmentation": [[184.0, 375.0, 163.5, 373.35, 170.5, 353.85, 188.5, 341.85, 210.0, 338.35, 208.5, 289.35, 196.0, 266.85, 173.0, 248.85, 157.5, 217.85, 155.5, 169.35, 161.0, 102.35, 168.0, 72.35, 211.5, 70.85, 277.0, 71.85, 278.5, 72.85, 288.0, 145.35, 283.5, 217.35, 263.5, 252.35, 241.0, 270.85, 230.5, 284.35, 232.5, 332.35, 237.0, 340.85, 268.0, 352.35, 278.0, 369.35, 276.5, 373.35]], "area": 28139.6, "iscrowd": 0, "image_id": 80590, "bbox": [155.5, 70.85, 132.5, 304.15], "category_id": 46, "id": 2183125, "split": "val", "sentences": [{"tokens": ["a", "wine", "glass", "betweent", "wo", "other", "glasses"], "raw": "A wine glass betweent wo other glasses.", "sent_id": 33330, "sent": "a wine glass betweent wo other glasses"}, {"tokens": ["the", "clear", "glass", "in", "the", "middle"], "raw": "The clear glass in the middle.", "sent_id": 33331, "sent": "the clear glass in the middle"}], "file_name": "COCO_train2014_000000080590_2183125.jpg", "ann_id": 2183125, "sent_ids": [33330, 33331], "ref_id": 17796}, {"segmentation": [[227.76, 360.0, 205.28, 324.54, 189.96, 311.77, 184.85, 304.62, 178.21, 283.17, 171.06, 267.85, 158.8, 248.44, 136.33, 247.42, 133.78, 245.88, 134.29, 229.54, 137.35, 225.45, 135.31, 219.83, 21.4, 232.6, 0.0, 212.68, 0.0, 360.0]], "area": 24394.7323, "iscrowd": 0, "image_id": 78274, "bbox": [0.0, 212.68, 227.76, 147.32], "category_id": 63, "id": 115400, "split": "val", "sentences": [{"tokens": ["a", "futon", "in", "front", "of", "a", "tv", ",", "right", "next", "to", "a", "glass", "door"], "raw": "A futon in front of a tv, right next to a glass door", "sent_id": 33352, "sent": "a futon in front of a tv , right next to a glass door"}, {"tokens": ["the", "couch"], "raw": "The couch.", "sent_id": 33353, "sent": "the couch"}], "file_name": "COCO_train2014_000000078274_115400.jpg", "ann_id": 115400, "sent_ids": [33352, 33353], "ref_id": 17803}, {"segmentation": [[248.61, 161.43, 228.16, 182.96, 228.16, 251.84, 248.61, 262.6, 255.07, 424.04, 279.82, 398.21, 302.42, 393.9, 292.74, 406.82, 327.17, 402.51, 340.09, 303.5, 318.57, 217.4, 322.87, 214.17, 351.93, 234.62, 356.23, 216.32, 318.57, 160.36, 297.04, 151.75, 300.27, 116.23, 275.52, 107.62, 259.37, 114.08, 251.84, 124.84]], "area": 24571.9902, "iscrowd": 0, "image_id": 77332, "bbox": [228.16, 107.62, 128.07, 316.42], "category_id": 1, "id": 195988, "split": "val", "sentences": [{"tokens": ["a", "female", "in", "a", "long", "blue", "jacket", "standing", "next", "to", "the", "table"], "raw": "A female in a long blue jacket standing next to the table", "sent_id": 33426, "sent": "a female in a long blue jacket standing next to the table"}, {"tokens": ["a", "woman", "wearing", "a", "blue", "coat", "holding", "a", "camera"], "raw": "A woman wearing a blue coat holding a camera.", "sent_id": 33427, "sent": "a woman wearing a blue coat holding a camera"}], "file_name": "COCO_train2014_000000077332_195988.jpg", "ann_id": 195988, "sent_ids": [33426, 33427], "ref_id": 17835}, {"segmentation": [[4.69, 148.15, 36.57, 154.71, 70.32, 172.52, 82.51, 189.4, 95.64, 210.97, 100.33, 255.04, 97.51, 275.66, 98.45, 282.23, 102.2, 282.23, 108.77, 282.23, 114.39, 282.23, 127.52, 281.29, 143.46, 230.66, 176.28, 217.53, 199.72, 200.65, 220.34, 193.15, 252.22, 168.77, 261.6, 180.03, 260.66, 202.53, 261.6, 219.41, 252.22, 226.91, 236.28, 229.72, 223.16, 240.97, 202.53, 252.22, 177.21, 264.41, 144.4, 270.04, 139.71, 272.85, 135.96, 285.98, 156.58, 285.98, 169.71, 297.23, 171.59, 301.92, 152.83, 312.23, 139.71, 313.17, 129.39, 323.48, 120.95, 338.49, 120.02, 345.99, 119.08, 346.92, 130.33, 349.74, 132.21, 358.18, 139.71, 370.37, 141.58, 375.05, 126.58, 375.05, 107.83, 375.99, 105.02, 391.93, 98.45, 410.68, 88.14, 408.81, 86.26, 394.74, 85.32, 371.3, 73.14, 376.93, 69.38, 387.24, 66.57, 396.62, 60.95, 406.0, 59.07, 404.12, 59.07, 390.06, 60.01, 375.05, 48.76, 365.68, 32.82, 355.36, 26.25, 344.11, 20.63, 328.17, 16.88, 315.05, 16.88, 311.29, 33.75, 315.05, 39.38, 320.67, 59.07, 345.05, 66.57, 338.49, 70.32, 320.67, 79.7, 309.42, 77.82, 296.29, 63.76, 269.1, 56.26, 215.66, 54.38, 214.72, 32.82, 214.72, 4.69, 201.59, 0.94, 192.22]], "area": 21762.643650000005, "iscrowd": 0, "image_id": 533050, "bbox": [0.94, 148.15, 260.66, 262.53], "category_id": 16, "id": 44145, "split": "val", "sentences": [{"tokens": ["the", "second", "bird", "from", "the", "front"], "raw": "the second bird  from the front", "sent_id": 33549, "sent": "the second bird from the front"}, {"tokens": ["bird", "flying", "back"], "raw": "bird flying back", "sent_id": 33550, "sent": "bird flying back"}], "file_name": "COCO_train2014_000000533050_44145.jpg", "ann_id": 44145, "sent_ids": [33549, 33550], "ref_id": 17885}, {"segmentation": [[313.54, 165.29, 305.02, 155.07, 305.87, 115.87, 316.95, 80.09, 335.7, 73.27, 335.7, 63.05, 342.51, 56.23, 342.51, 34.08, 347.62, 24.71, 357.85, 25.56, 363.81, 24.71, 371.48, 30.67, 372.33, 47.71, 373.18, 53.68, 382.56, 65.61, 384.26, 73.27, 398.74, 75.83, 414.93, 113.32, 408.97, 124.39, 381.7, 117.58, 336.55, 120.99, 330.58, 135.47, 322.91, 140.58, 333.99, 154.22, 333.99, 168.7]], "area": 7185.362400000002, "iscrowd": 0, "image_id": 253907, "bbox": [305.02, 24.71, 109.91, 143.99], "category_id": 1, "id": 197289, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "grey", "hooded", "sweatshirt"], "raw": "A man wearing a grey hooded sweatshirt.", "sent_id": 33663, "sent": "a man wearing a grey hooded sweatshirt"}, {"tokens": ["a", "smiling", "man", "with", "brown", "hair", "wearing", "a", "gray", "sweatshirt"], "raw": "A smiling man with brown hair wearing a gray sweatshirt.", "sent_id": 33664, "sent": "a smiling man with brown hair wearing a gray sweatshirt"}], "file_name": "COCO_train2014_000000253907_197289.jpg", "ann_id": 197289, "sent_ids": [33663, 33664], "ref_id": 17923}, {"segmentation": [[4.55, 374.1, 60.05, 397.89, 149.9, 426.0, 185.14, 426.0, 284.68, 370.58, 314.63, 344.15, 345.46, 315.96, 342.82, 304.51, 358.67, 315.96, 370.13, 302.75, 385.1, 307.16, 385.1, 290.42, 392.15, 289.54, 397.43, 283.37, 398.31, 272.8, 404.48, 256.06, 398.31, 249.9, 386.86, 239.33, 377.17, 233.16, 365.72, 226.11, 344.58, 231.4, 317.27, 252.54, 311.11, 254.3, 306.7, 254.3, 268.82, 271.04, 265.3, 272.8, 251.2, 282.49, 240.63, 293.94, 223.02, 298.35, 177.21, 303.63, 164.88, 300.99, 132.28, 272.8, 127.88, 265.75, 106.74, 263.11, 96.17, 259.59, 74.14, 240.21, 67.98, 234.04, 53.0, 224.35, 47.72, 216.42, 36.27, 219.95, 1.03, 143.31, 3.67, 375.87]], "area": 49271.592949999984, "iscrowd": 0, "image_id": 86654, "bbox": [1.03, 143.31, 403.45, 282.69], "category_id": 1, "id": 1731018, "split": "val", "sentences": [{"tokens": ["an", "arm", "with", "dark", "blue", "sleeves"], "raw": "An arm with dark blue sleeves.", "sent_id": 33725, "sent": "an arm with dark blue sleeves"}, {"tokens": ["person", "in", "dark", "blue", "shirt", "holding", "a", "fork"], "raw": "person in dark blue shirt holding a fork", "sent_id": 33726, "sent": "person in dark blue shirt holding a fork"}], "file_name": "COCO_train2014_000000086654_1731018.jpg", "ann_id": 1731018, "sent_ids": [33725, 33726], "ref_id": 17947}, {"segmentation": [[134.83, 149.93, 152.09, 145.62, 166.11, 146.7, 176.9, 156.4, 181.21, 172.58, 190.92, 193.08, 189.84, 218.97, 211.42, 217.89, 232.99, 216.81, 258.88, 216.81, 255.64, 221.12, 239.46, 243.78, 229.75, 264.27, 226.52, 277.21, 216.81, 289.08, 213.57, 296.63, 211.42, 309.57, 212.49, 321.44, 201.71, 302.02, 184.45, 271.82, 170.43, 262.11, 155.33, 249.17, 143.46, 240.54, 136.99, 238.38, 128.36, 190.92, 125.12, 167.19, 124.04, 156.4]], "area": 9638.038050000001, "iscrowd": 0, "image_id": 550760, "bbox": [124.04, 145.62, 134.84, 175.82], "category_id": 1, "id": 567722, "split": "val", "sentences": [{"tokens": ["man", "seated", "on", "far", "end", "of", "couch", ",", "to", "left", "of", "man", "in", "plaid"], "raw": "man seated on far end of couch, to left of man in plaid", "sent_id": 33770, "sent": "man seated on far end of couch , to left of man in plaid"}, {"tokens": ["man", "in", "middle", "with", "solid", "grey", "shirt"], "raw": "man in middle with solid grey shirt.", "sent_id": 33771, "sent": "man in middle with solid grey shirt"}], "file_name": "COCO_train2014_000000550760_567722.jpg", "ann_id": 567722, "sent_ids": [33770, 33771], "ref_id": 17969}, {"segmentation": [[129.61, 263.86, 129.79, 253.48, 123.6, 236.17, 121.05, 226.15, 118.31, 219.22, 118.68, 215.4, 120.5, 211.75, 123.41, 210.11, 127.24, 209.02, 131.61, 207.93, 132.16, 199.54, 129.43, 195.72, 128.33, 191.89, 128.33, 188.06, 129.43, 183.15, 131.61, 180.23, 134.16, 178.95, 138.72, 178.77, 142.91, 179.32, 146.92, 181.14, 148.92, 183.15, 148.92, 185.33, 148.74, 185.7, 149.47, 188.43, 150.93, 190.8, 150.38, 191.89, 150.2, 193.17, 152.39, 196.99, 150.2, 197.54, 150.38, 200.27, 148.74, 200.82, 149.83, 202.82, 149.11, 204.28, 148.92, 206.1, 148.2, 206.29, 160.04, 206.83, 167.14, 207.74, 174.62, 209.93, 179.72, 207.38, 183.54, 206.83, 185.18, 208.11, 185.18, 211.57, 184.64, 211.75, 187.19, 215.03, 185.0, 219.04, 182.09, 220.32, 183.0, 223.23, 189.92, 229.79, 187.92, 233.25, 186.46, 234.89, 189.19, 244.37, 190.83, 253.3, 196.3, 264.59, 200.31, 278.44, 197.39, 295.39, 198.67, 301.76, 194.11, 307.23, 188.65, 313.43, 181.9, 314.52, 174.43, 313.43, 175.71, 322.17, 175.71, 324.18, 172.61, 324.18, 171.52, 326.36, 170.97, 334.56, 170.61, 336.75, 156.58, 337.11, 155.85, 326.18, 148.92, 326.18, 149.29, 318.16, 149.29, 313.79, 144.37, 325.09, 141.82, 331.46, 139.63, 336.93, 137.44, 338.02, 135.26, 340.39, 136.53, 343.85, 135.99, 343.49, 131.8, 342.76, 132.16, 345.49, 137.26, 350.41, 132.16, 353.69, 131.25, 362.44, 132.71, 368.27, 133.07, 373.19, 131.61, 378.11, 133.62, 383.03, 136.17, 387.22, 135.44, 387.95, 130.34, 387.95, 122.87, 386.86, 121.41, 384.49, 124.14, 380.66, 125.6, 377.02, 126.15, 369.73, 124.87, 352.78, 124.51, 347.32, 125.42, 338.94, 127.42, 334.74, 130.52, 328.18, 129.43, 324.36, 123.41, 319.44, 125.42, 309.78, 127.06, 302.86, 127.06, 297.03, 127.42, 283.73, 127.06, 278.08, 127.79, 272.97, 128.7, 269.88, 129.79, 267.69], [158.95, 360.2, 162.04, 356.0, 165.69, 355.82, 168.42, 357.46, 170.06, 357.64, 170.24, 362.93, 168.97, 371.86, 170.61, 375.14, 176.98, 378.23, 183.36, 379.87, 185.73, 381.15, 186.46, 384.43, 184.45, 385.89, 176.98, 385.89, 168.42, 385.89, 164.96, 385.16, 161.31, 385.52, 159.13, 383.15, 159.67, 378.05, 160.04, 373.5, 159.31, 364.02]], "area": 9355.873050000002, "iscrowd": 0, "image_id": 159957, "bbox": [118.31, 178.77, 82.0, 209.18], "category_id": 1, "id": 482673, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "black", "shorts", "holding", "a", "towel"], "raw": "A man in black shorts holding a towel.", "sent_id": 33901, "sent": "a man in black shorts holding a towel"}, {"tokens": ["the", "man", "with", "the", "yellow", "and", "white", "towel"], "raw": "The man with the yellow and white towel.", "sent_id": 33902, "sent": "the man with the yellow and white towel"}], "file_name": "COCO_train2014_000000159957_482673.jpg", "ann_id": 482673, "sent_ids": [33901, 33902], "ref_id": 18021}, {"segmentation": [[515.02, 341.95, 516.55, 155.71, 516.04, 151.12, 638.5, 148.57, 629.82, 356.58, 628.29, 359.14, 518.08, 343.83, 515.53, 343.32]], "area": 23875.411800000013, "iscrowd": 0, "image_id": 271488, "bbox": [515.02, 148.57, 123.48, 210.57], "category_id": 79, "id": 1642582, "split": "val", "sentences": [{"tokens": ["a", "closed", ",", "double", "wall", "oven"], "raw": "A closed, double wall oven", "sent_id": 33930, "sent": "a closed , double wall oven"}, {"tokens": ["a", "stainless", "steel", "double", "oven", "with", "tinted", "glass"], "raw": "A stainless steel double oven with tinted glass.", "sent_id": 33931, "sent": "a stainless steel double oven with tinted glass"}], "file_name": "COCO_train2014_000000271488_1642582.jpg", "ann_id": 1642582, "sent_ids": [33930, 33931], "ref_id": 18032}, {"segmentation": [[26.97, 131.6, 28.04, 299.87, 35.6, 327.91, 46.38, 336.54, 55.01, 311.73, 111.1, 335.46, 121.89, 277.21, 118.65, 255.64, 114.34, 235.15, 119.73, 193.08, 138.07, 174.74, 154.25, 147.78, 168.27, 148.85, 190.92, 159.64, 187.69, 176.9, 207.1, 199.55, 221.12, 221.12, 208.18, 243.78, 210.34, 272.9, 212.49, 310.65, 200.63, 337.62, 392.63, 338.7, 403.42, 340.85, 407.73, 358.11, 421.75, 371.06, 446.56, 360.27, 442.25, 345.17, 485.39, 337.62, 471.37, 250.25, 474.61, 140.22, 465.98, 90.61, 460.58, 51.78, 368.9, 49.62, 369.98, 42.07, 319.28, 32.36, 201.71, 44.22, 163.96, 61.48, 142.38, 89.53, 96.0, 112.18, 106.79, 91.69, 80.9, 101.39, 71.19, 120.81]], "area": 106891.64335, "iscrowd": 0, "image_id": 352185, "bbox": [26.97, 32.36, 458.42, 338.7], "category_id": 6, "id": 166248, "split": "val", "sentences": [{"tokens": ["a", "bus", "with", "a", "red", "front", "is", "in", "behind", "a", "man", "on", "a", "bike"], "raw": "A bus with a red front is in behind a man on a bike.", "sent_id": 34010, "sent": "a bus with a red front is in behind a man on a bike"}, {"tokens": ["the", "big", "red", "bus"], "raw": "The big red bus", "sent_id": 34011, "sent": "the big red bus"}], "file_name": "COCO_train2014_000000352185_166248.jpg", "ann_id": 166248, "sent_ids": [34010, 34011], "ref_id": 18059}, {"segmentation": [[304.7, 255.93, 282.73, 300.83, 258.85, 347.63, 252.16, 354.32, 248.34, 345.72, 255.98, 322.8, 280.82, 263.58, 302.78, 199.58, 319.98, 177.61, 335.26, 153.73, 347.68, 53.44, 334.3, 50.58, 330.48, 46.75, 335.26, 41.02, 342.9, 46.75, 350.54, 40.07, 346.72, 24.79, 349.59, 16.19, 352.45, 22.88, 357.23, 31.47, 359.14, 33.38, 362.96, 32.43, 362.0, 18.1, 365.83, 16.19, 368.69, 27.65, 369.65, 36.25, 375.38, 45.8, 381.11, 56.31, 381.11, 61.08, 359.14, 63.95, 355.32, 124.12, 361.05, 183.34, 362.0, 212.95, 365.83, 268.35, 368.69, 304.65, 356.27, 341.9, 352.45, 361.0, 339.08, 361.96, 343.86, 345.72, 358.18, 289.36, 349.59, 238.74, 343.86, 256.89, 337.17, 287.45, 334.3, 344.76, 334.3, 363.87, 323.8, 368.64, 321.89, 361.0, 319.02, 296.05, 318.07, 321.84, 316.16, 356.23, 304.7, 359.09, 307.56, 339.99, 306.61, 318.02, 293.23, 335.21, 293.23, 317.06, 303.74, 297.96, 315.2, 277.9, 306.61, 259.75]], "area": 14363.219600000008, "iscrowd": 0, "image_id": 387293, "bbox": [248.34, 16.19, 132.77, 352.45], "category_id": 25, "id": 596381, "split": "val", "sentences": [{"tokens": ["smaller", "giraffe", "looking", "larger", "giraffe"], "raw": "smaller giraffe looking larger giraffe", "sent_id": 34031, "sent": "smaller giraffe looking larger giraffe"}, {"tokens": ["the", "shorter", "of", "the", "fighting", "giraffes"], "raw": "The shorter of the fighting giraffes.", "sent_id": 34032, "sent": "the shorter of the fighting giraffes"}], "file_name": "COCO_train2014_000000387293_596381.jpg", "ann_id": 596381, "sent_ids": [34031, 34032], "ref_id": 18068}, {"segmentation": [[370.75, 2.34, 335.19, 15.44, 335.81, 39.78, 345.79, 68.48, 349.54, 90.95, 358.9, 110.91, 368.88, 119.03, 381.99, 120.9, 400.71, 120.9, 416.31, 120.27, 422.55, 120.27, 443.76, 114.03, 448.75, 114.03, 465.6, 110.91, 476.21, 110.29, 478.71, 99.06, 474.34, 89.07, 466.85, 87.2, 456.87, 90.95, 448.13, 93.44, 438.15, 70.35, 428.16, 45.39, 405.7, 29.79, 385.11, 21.06, 373.87, 14.82, 369.51, 4.83]], "area": 9714.68725, "iscrowd": 0, "image_id": 33992, "bbox": [335.19, 2.34, 143.52, 118.56], "category_id": 16, "id": 43852, "split": "val", "sentences": [{"tokens": ["dark", "chicken", "closest", "to", "the", "fence"], "raw": "dark chicken closest to the fence", "sent_id": 34064, "sent": "dark chicken closest to the fence"}], "file_name": "COCO_train2014_000000033992_43852.jpg", "ann_id": 43852, "sent_ids": [34064], "ref_id": 18079}, {"segmentation": [[130.46, 380.18, 144.14, 358.58, 159.97, 335.55, 166.45, 326.19, 174.37, 315.39, 183.73, 310.35, 212.52, 308.91, 225.48, 309.63, 239.87, 328.35, 246.35, 359.3, 242.03, 435.6, 218.28, 463.68, 182.29, 473.75, 159.97, 468.72, 147.02, 479.51, 141.26, 488.87, 129.02, 491.03, 113.9, 460.8, 125.42, 437.76]], "area": 16766.63015, "iscrowd": 0, "image_id": 339579, "bbox": [113.9, 308.91, 132.45, 182.12], "category_id": 54, "id": 2219129, "split": "val", "sentences": [{"tokens": ["the", "baked", "chicken", "on", "the", "plate"], "raw": "The baked chicken on the plate.", "sent_id": 34097, "sent": "the baked chicken on the plate"}, {"tokens": ["a", "piece", "of", "meat", "with", "mushrooms", "on", "top"], "raw": "A piece of meat with mushrooms on top.", "sent_id": 34098, "sent": "a piece of meat with mushrooms on top"}], "file_name": "COCO_train2014_000000339579_2219129.jpg", "ann_id": 2219129, "sent_ids": [34097, 34098], "ref_id": 18092}, {"segmentation": [[181.36, 234.73, 201.53, 248.17, 210.5, 342.3, 227.31, 378.16, 234.03, 408.42, 226.19, 483.5, 207.14, 547.75, 231.79, 562.32, 241.88, 571.28, 227.31, 580.25, 183.6, 561.2, 179.12, 551.11, 167.92, 554.47, 184.73, 586.97, 222.83, 626.19, 172.4, 629.55, 145.5, 595.94, 118.61, 591.45, 102.92, 530.94, 64.82, 495.08, 67.06, 471.55, 92.84, 397.59, 58.1, 385.26, 53.62, 333.7, 62.58, 258.62, 60.34, 242.94, 86.11, 231.73, 104.04, 214.92, 113.01, 199.23, 107.4, 188.03, 96.2, 170.1, 95.08, 127.51, 107.4, 100.62, 145.5, 99.5, 164.55, 133.12, 171.28, 166.74, 170.16, 179.06, 169.04, 190.27, 170.16, 210.44]], "area": 60829.2603, "iscrowd": 0, "image_id": 385704, "bbox": [53.62, 99.5, 188.26, 530.05], "category_id": 1, "id": 507438, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "buttoned", "jacket"], "raw": "the man in the buttoned jacket", "sent_id": 34174, "sent": "the man in the buttoned jacket"}, {"tokens": ["a", "young", "man", "dressed", "in", "a", "texido", "holding", "some", "clothing", "standing", "in", "a", "parking", "lot", "with", "another", "man"], "raw": "A young man dressed in a Texido holding some clothing standing in a parking lot with another man.", "sent_id": 34175, "sent": "a young man dressed in a texido holding some clothing standing in a parking lot with another man"}], "file_name": "COCO_train2014_000000385704_507438.jpg", "ann_id": 507438, "sent_ids": [34174, 34175], "ref_id": 18120}, {"segmentation": [[12.64, 281.46, 44.66, 273.88, 100.28, 273.88, 170.22, 267.13, 224.16, 264.61, 284.83, 264.61, 298.31, 267.13, 309.27, 285.67, 326.12, 321.91, 330.34, 330.34, 317.7, 340.45, 279.78, 340.45, 210.67, 347.19, 119.66, 350.56, 41.29, 356.46, 1.69, 359.83, 0.0, 349.72, 1.69, 326.97, 0.84, 306.74, 2.53, 290.73, 2.53, 289.04]], "area": 24910.62945, "iscrowd": 0, "image_id": 498690, "bbox": [0.0, 264.61, 330.34, 95.22], "category_id": 76, "id": 1116434, "split": "val", "sentences": [{"tokens": ["a", "toshiba", "keyboard", "connected", "to", "the", "laptop"], "raw": "A Toshiba keyboard connected to the laptop.", "sent_id": 34191, "sent": "a toshiba keyboard connected to the laptop"}, {"tokens": ["black", "computer", "keyboard"], "raw": "Black computer keyboard.", "sent_id": 34192, "sent": "black computer keyboard"}], "file_name": "COCO_train2014_000000498690_1116434.jpg", "ann_id": 1116434, "sent_ids": [34191, 34192], "ref_id": 18127}, {"segmentation": [[204.89, 143.56, 216.75, 70.44, 309.63, 53.64, 349.16, 82.3, 358.05, 163.33, 333.35, 186.05, 290.86, 193.96, 244.42, 201.86, 220.7, 190.99]], "area": 18072.939950000007, "iscrowd": 0, "image_id": 149202, "bbox": [204.89, 53.64, 153.16, 148.22], "category_id": 61, "id": 1088110, "split": "val", "sentences": [{"tokens": ["a", "white", "cake", "with", "blue", ",", "green", ",", "and", "yellow", "poke", "-", "a", "-", "dots", "on", "it", "next", "to", "three", "other", "decorated", "cakes", "on", "a", "platter"], "raw": "A white cake with blue, green, and yellow poke-a-dots on it next to three other decorated cakes on a platter.", "sent_id": 34219, "sent": "a white cake with blue , green , and yellow poke - a - dots on it next to three other decorated cakes on a platter"}, {"tokens": ["the", "cake", "with", "the", "yellow", "circles"], "raw": "The cake with the yellow circles.", "sent_id": 34220, "sent": "the cake with the yellow circles"}], "file_name": "COCO_train2014_000000149202_1088110.jpg", "ann_id": 1088110, "sent_ids": [34219, 34220], "ref_id": 18139}, {"segmentation": [[203.23, 308.39, 211.12, 307.41, 219.01, 211.71, 220.0, 210.73, 395.61, 207.77, 394.62, 214.67, 396.59, 222.57, 399.55, 222.57, 386.73, 313.33, 368.97, 316.29, 362.06, 317.27, 325.56, 316.29, 319.64, 317.27, 312.74, 319.25, 296.95, 321.22, 277.22, 325.17, 276.23, 329.11, 209.15, 332.07, 201.26, 312.34, 203.23, 305.43]], "area": 20402.4433, "iscrowd": 0, "image_id": 259514, "bbox": [201.26, 207.77, 198.29, 124.3], "category_id": 73, "id": 1099484, "split": "val", "sentences": [{"tokens": ["hp", "computer", "lid"], "raw": "hp computer lid", "sent_id": 34227, "sent": "hp computer lid"}, {"tokens": ["an", "open", "black", "hp", "laptop", "in", "front", "of", "a", "woman", "wearing", "a", "grey", "t", "-", "shirt"], "raw": "An open black HP laptop in front of a woman wearing a grey t-shirt.", "sent_id": 34228, "sent": "an open black hp laptop in front of a woman wearing a grey t - shirt"}], "file_name": "COCO_train2014_000000259514_1099484.jpg", "ann_id": 1099484, "sent_ids": [34227, 34228], "ref_id": 18143}, {"segmentation": [[560.02, 320.4, 586.83, 261.05, 607.89, 207.44, 603.1, 187.34, 610.76, 169.15, 640.0, 195.0, 640.0, 234.25, 638.52, 269.67, 608.84, 257.22, 570.55, 329.98, 555.24, 318.49]], "area": 4399.714599999998, "iscrowd": 0, "image_id": 31812, "bbox": [555.24, 169.15, 84.76, 160.83], "category_id": 62, "id": 376735, "split": "val", "sentences": [{"tokens": ["the", "wooden", "chair", "on", "the", "right"], "raw": "The wooden chair on the right.", "sent_id": 34285, "sent": "the wooden chair on the right"}, {"tokens": ["a", "wooden", "chair", "leg", "in", "the", "background", "of", "the", "photo"], "raw": "A wooden chair leg in the background of the photo.", "sent_id": 34286, "sent": "a wooden chair leg in the background of the photo"}], "file_name": "COCO_train2014_000000031812_376735.jpg", "ann_id": 376735, "sent_ids": [34285, 34286], "ref_id": 18164}, {"segmentation": [[1.03, 327.98, 85.31, 319.76, 90.45, 323.87, 96.62, 322.84, 105.87, 349.56, 107.92, 395.82, 146.98, 403.01, 168.57, 412.26, 174.73, 448.24, 178.84, 469.82, 169.59, 474.96, 3.08, 473.93, 1.03, 332.09]], "area": 20437.814549999996, "iscrowd": 0, "image_id": 496053, "bbox": [1.03, 319.76, 177.81, 155.2], "category_id": 63, "id": 98531, "split": "val", "sentences": [{"tokens": ["a", "sofa", "with", "a", "white", "cloth", "and", "a", "brown", "pillow", "on", "it"], "raw": "A sofa with a white cloth and a brown pillow on it", "sent_id": 34289, "sent": "a sofa with a white cloth and a brown pillow on it"}, {"tokens": ["a", "brown", "chair", "with", "a", "white", "blanket", "on", "the", "back", "and", "a", "pillow", "with", "a", "dog", "on", "it", "in", "the", "seat"], "raw": "A brown chair with a white blanket on the back and a pillow with a dog on it in the seat.", "sent_id": 34290, "sent": "a brown chair with a white blanket on the back and a pillow with a dog on it in the seat"}], "file_name": "COCO_train2014_000000496053_98531.jpg", "ann_id": 98531, "sent_ids": [34289, 34290], "ref_id": 18165}, {"segmentation": [[330.79, 182.35, 341.27, 188.24, 348.47, 199.37, 349.13, 213.13, 349.13, 222.95, 346.51, 230.15, 351.75, 236.05, 358.95, 236.05, 366.81, 236.05, 372.05, 239.32, 375.32, 244.56, 387.76, 245.21, 398.89, 257.66, 398.89, 277.3, 392.35, 294.33, 384.49, 313.97, 380.56, 319.21, 383.18, 327.72, 387.11, 335.58, 387.11, 339.51, 362.88, 339.51, 349.78, 340.82, 343.89, 341.48, 342.58, 329.69, 345.85, 321.18, 350.44, 312.66, 353.06, 302.19, 349.78, 302.84, 341.27, 305.46, 328.83, 308.73, 317.69, 311.35, 309.84, 311.35, 311.15, 321.83, 317.04, 332.96, 317.69, 337.55, 307.22, 337.55, 292.81, 336.89, 281.68, 337.55, 278.4, 337.55, 266.62, 320.52, 262.69, 311.35, 262.69, 304.8, 267.27, 302.19, 275.78, 291.71, 283.64, 289.74, 291.5, 289.09, 301.98, 287.78, 309.18, 282.54, 298.7, 281.89, 286.92, 283.19, 282.33, 283.19, 273.16, 281.23, 266.62, 279.92, 256.79, 277.96, 246.97, 280.58, 243.7, 287.78, 243.7, 294.98, 243.7, 298.26, 241.73, 300.88, 235.84, 301.53, 231.91, 301.53, 229.29, 302.19, 224.05, 296.95, 225.36, 290.4, 226.02, 287.12, 229.29, 281.23, 230.6, 277.3, 232.56, 268.13, 235.84, 262.89, 239.11, 260.28, 245.01, 258.31, 250.24, 257.0, 256.14, 256.35, 264.0, 253.07, 269.89, 250.45, 273.16, 248.49, 277.09, 245.87, 283.64, 243.9, 292.81, 241.28, 298.05, 238.67, 307.22, 236.05, 311.8, 235.39, 316.38, 232.12, 320.97, 230.15, 322.93, 226.22, 321.62, 223.6, 320.97, 222.95, 318.35, 220.33, 314.42, 219.67, 312.45, 218.37, 312.45, 214.44, 312.45, 211.82, 312.45, 208.54, 312.45, 199.37, 315.07, 194.79, 318.35, 190.21, 325.55, 184.97, 327.52, 183.66]], "area": 13651.964249999997, "iscrowd": 0, "image_id": 499966, "bbox": [224.05, 182.35, 174.84, 159.13], "category_id": 1, "id": 196806, "split": "val", "sentences": [{"tokens": ["a", "middle", "aged", "man", "sitting", "on", "a", "sofa", "with", "black", "dog"], "raw": "A middle aged man sitting on a sofa with black dog.", "sent_id": 34307, "sent": "a middle aged man sitting on a sofa with black dog"}, {"tokens": ["a", "man", "seated", "on", "a", "sofa"], "raw": "A man seated on a sofa.", "sent_id": 34308, "sent": "a man seated on a sofa"}], "file_name": "COCO_train2014_000000499966_196806.jpg", "ann_id": 196806, "sent_ids": [34307, 34308], "ref_id": 18173}, {"segmentation": [[62.36, 133.25, 74.83, 125.31, 96.35, 124.18, 112.21, 127.58, 114.48, 146.84, 116.75, 166.1, 109.95, 186.5, 117.88, 192.16, 130.34, 191.03, 177.93, 187.63, 182.46, 180.83, 188.13, 184.23, 196.06, 203.49, 184.73, 203.49, 155.27, 203.49, 100.88, 266.94, 108.82, 283.93, 125.81, 294.13, 113.35, 326.99, 102.02, 359.85, 86.16, 390.44, 77.09, 388.17, 62.36, 417.63, 14.78, 406.3, 0.05, 415.36, 0.05, 350.78, 18.18, 325.86, 34.04, 274.87, 35.17, 235.22, 21.57, 222.75, 3.45, 212.56, 0.0, 186.5, 18.18, 191.03, 26.11, 191.03, 56.7, 192.16, 64.63, 191.03, 66.89, 180.83, 65.76, 170.63, 62.36, 157.04, 57.83, 145.71, 60.1, 133.25], [243.64, 155.91, 260.64, 142.31, 266.3, 130.98, 271.97, 123.05, 275.37, 136.64, 281.03, 128.71, 287.83, 124.18, 293.5, 121.92, 288.96, 132.11, 300.29, 128.71, 303.69, 127.58, 292.36, 138.91, 305.96, 136.64, 288.96, 143.44, 277.63, 155.91, 266.3, 158.17, 245.91, 175.17, 239.11, 152.51]], "area": 26586.31355, "iscrowd": 0, "image_id": 97563, "bbox": [0.0, 121.92, 305.96, 295.71], "category_id": 1, "id": 1749635, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "with", "a", "red", "design"], "raw": "a man in a white shirt with a red design", "sent_id": 34358, "sent": "a man in a white shirt with a red design"}, {"tokens": ["a", "man", "in", "white", "trying", "to", "catch", "a", "frisbie"], "raw": "A man in white trying to catch a Frisbie.", "sent_id": 34359, "sent": "a man in white trying to catch a frisbie"}], "file_name": "COCO_train2014_000000097563_1749635.jpg", "ann_id": 1749635, "sent_ids": [34358, 34359], "ref_id": 18198}, {"segmentation": [[379.14, 61.96, 407.27, 80.85, 428.26, 89.25, 463.11, 91.77, 497.12, 85.05, 512.66, 80.43, 541.21, 78.33, 593.7, 93.45, 638.2, 137.96, 640.0, 162.31, 639.46, 192.54, 640.0, 221.09, 636.94, 229.91, 618.89, 238.31, 610.07, 248.39, 560.11, 251.74, 557.59, 233.27, 558.85, 212.7, 524.42, 211.86, 504.68, 204.72, 497.12, 214.79, 468.57, 235.37, 453.46, 242.93, 454.72, 268.96, 450.1, 276.52, 421.55, 277.36, 404.75, 256.36, 396.35, 206.82, 391.73, 184.98, 387.95, 155.59, 361.08, 136.28, 332.95, 130.82, 322.87, 134.6, 319.09, 130.82, 305.66, 131.66, 288.86, 129.56, 285.92, 126.62, 279.21, 126.2, 277.53, 123.26, 268.71, 111.08, 283.82, 101.01, 302.72, 85.47, 317.83, 72.04, 340.51, 56.08, 337.99, 41.8, 343.45, 38.45, 350.17, 27.11, 357.72, 28.79, 379.14, 62.38]], "area": 44733.48350000001, "iscrowd": 0, "image_id": 90310, "bbox": [268.71, 27.11, 371.29, 250.25], "category_id": 23, "id": 587579, "split": "val", "sentences": [{"tokens": ["the", "right", "most", "black", "bear"], "raw": "The right most black bear", "sent_id": 34388, "sent": "the right most black bear"}, {"tokens": ["bear", "behind", "another", "bear"], "raw": "bear behind another bear", "sent_id": 34389, "sent": "bear behind another bear"}], "file_name": "COCO_train2014_000000090310_587579.jpg", "ann_id": 587579, "sent_ids": [34388, 34389], "ref_id": 18209}, {"segmentation": [[61.04, 248.5, 54.65, 255.38, 44.33, 261.28, 34.99, 265.71, 27.12, 273.08, 29.09, 283.4, 33.02, 297.17, 39.41, 308.48, 51.7, 320.28, 79.23, 342.89, 70.87, 327.16, 70.87, 322.73, 93.0, 313.39, 120.03, 299.14, 114.14, 298.64, 107.74, 295.69, 103.32, 289.8, 95.95, 283.4, 92.5, 274.56, 92.01, 268.16, 92.01, 267.18, 80.71, 264.23, 70.87, 254.89, 61.04, 250.96], [122.98, 366.98, 144.12, 365.01, 169.19, 360.59, 163.3, 365.99, 143.14, 367.96]], "area": 4182.356400000001, "iscrowd": 0, "image_id": 55873, "bbox": [27.12, 248.5, 142.07, 119.46], "category_id": 53, "id": 1048608, "split": "val", "sentences": [{"tokens": ["the", "first", "slice", "of", "apple", "next", "to", "the", "orange", "wedges"], "raw": "The first slice of apple next to the orange wedges", "sent_id": 34442, "sent": "the first slice of apple next to the orange wedges"}, {"tokens": ["the", "slice", "of", "apple", "that", "has", "two", "green", "grapes", "on", "it", "and", "it", "is", "next", "to", "an", "orange", "slice"], "raw": "The slice of apple that has two green grapes on it and it is next to an orange slice.", "sent_id": 34443, "sent": "the slice of apple that has two green grapes on it and it is next to an orange slice"}], "file_name": "COCO_train2014_000000055873_1048608.jpg", "ann_id": 1048608, "sent_ids": [34442, 34443], "ref_id": 18231}, {"segmentation": [[306.98, 164.56, 315.75, 188.68, 317.94, 211.7, 324.52, 238.02, 310.27, 302.7, 294.92, 310.38, 296.02, 279.68, 281.76, 293.93, 291.63, 325.72, 275.19, 329.01, 262.03, 304.89, 255.45, 313.66, 260.93, 330.11, 243.39, 337.78, 241.2, 315.86, 214.89, 311.47, 229.14, 341.07, 209.4, 339.98, 200.63, 353.13, 191.86, 291.74, 199.54, 255.56, 198.44, 229.25, 264.22, 184.29, 265.32, 155.79, 235.72, 128.38, 274.09, 134.96, 315.75, 141.54, 357.41, 139.34, 322.33, 162.37]], "area": 18108.89085, "iscrowd": 0, "image_id": 71970, "bbox": [191.86, 128.38, 165.55, 224.75], "category_id": 21, "id": 72710, "split": "val", "sentences": [{"tokens": ["a", "statue", "of", "three", "cows", ",", "the", "second", "on", "the", "back", "of", "the", "first", "and", "the", "third", "on", "the", "back", "of", "the", "second"], "raw": "A statue of three cows, the second on the back of the first and the third on the back of the second.", "sent_id": 34446, "sent": "a statue of three cows , the second on the back of the first and the third on the back of the second"}, {"tokens": ["the", "middle", "and", "top", "cows", "of", "a", "statue", "of", "three", "cows"], "raw": "the middle and top cows of a statue of three cows.", "sent_id": 34447, "sent": "the middle and top cows of a statue of three cows"}], "file_name": "COCO_train2014_000000071970_72710.jpg", "ann_id": 72710, "sent_ids": [34446, 34447], "ref_id": 18233}, {"segmentation": [[187.61, 48.84, 213.14, 38.85, 244.22, 28.86, 291.96, 18.87, 336.36, 12.21, 348.58, 15.54, 422.95, 61.06, 566.16, 150.98, 576.15, 165.41, 583.92, 194.27, 586.14, 230.9, 587.25, 252.0, 583.92, 266.43, 572.82, 274.2, 570.6, 278.64, 569.49, 360.79, 567.27, 398.53, 566.16, 408.52, 563.94, 412.96, 558.39, 412.96, 556.17, 411.85, 545.07, 426.28, 535.07, 419.62, 533.96, 415.18, 414.07, 451.82, 390.76, 482.9, 382.99, 490.67, 368.56, 494.0, 348.58, 492.89, 330.81, 484.01, 321.93, 472.91, 316.38, 452.93, 313.05, 449.6, 277.53, 445.16, 263.1, 445.16, 254.22, 446.27, 250.89, 458.48, 228.68, 456.26, 210.92, 452.93, 208.7, 449.6, 196.49, 464.03, 175.4, 459.59, 157.64, 450.71, 149.87, 435.16, 144.31, 422.95, 139.87, 407.41, 136.54, 388.54, 139.87, 330.81, 142.09, 263.1, 146.53, 219.8, 147.64, 190.94, 156.53, 152.09, 167.63, 106.57, 170.96, 77.71, 182.06, 62.17, 185.39, 52.18]], "area": 166185.89395, "iscrowd": 0, "image_id": 545850, "bbox": [136.54, 12.21, 450.71, 481.79], "category_id": 6, "id": 165529, "split": "val", "sentences": [{"tokens": ["a", "red", "double", "decker", "bus"], "raw": "a red double decker bus", "sent_id": 34480, "sent": "a red double decker bus"}, {"tokens": ["a", "red", "bus", "that", "is", "two", "stories"], "raw": "A red bus that is two stories.", "sent_id": 34481, "sent": "a red bus that is two stories"}], "file_name": "COCO_train2014_000000545850_165529.jpg", "ann_id": 165529, "sent_ids": [34480, 34481], "ref_id": 18244}, {"segmentation": [[161.53, 426.0, 156.72, 413.23, 153.29, 398.82, 151.92, 382.35, 170.45, 350.77, 175.19, 335.06, 187.63, 314.0, 196.25, 301.55, 205.82, 272.83, 231.67, 179.02, 220.18, 153.17, 222.09, 138.81, 232.62, 118.71, 262.3, 113.92, 288.15, 125.41, 306.34, 131.15, 312.08, 103.39, 335.06, 77.54, 342.71, 67.97, 371.43, 66.05, 384.84, 77.54, 392.49, 86.16, 401.11, 118.71, 399.2, 131.15, 395.37, 147.42, 393.45, 153.17, 405.9, 159.87, 419.3, 176.14, 420.26, 184.76, 424.09, 201.03, 430.79, 213.48, 435.57, 238.37, 433.66, 251.77, 419.3, 260.39, 395.37, 269.0, 385.79, 280.49, 372.39, 260.39, 367.6, 257.51, 344.63, 290.06, 326.44, 316.87, 315.91, 336.97, 295.81, 370.48, 312.08, 420.26]], "area": 55026.114149999994, "iscrowd": 0, "image_id": 267957, "bbox": [151.92, 66.05, 283.65, 359.95], "category_id": 1, "id": 460867, "split": "val", "sentences": [{"tokens": ["player", "about", "to", "swing", "a", "baseball"], "raw": "Player about to swing a baseball", "sent_id": 34489, "sent": "player about to swing a baseball"}, {"tokens": ["a", "man", "playing", "baseball"], "raw": "A man playing baseball", "sent_id": 34490, "sent": "a man playing baseball"}], "file_name": "COCO_train2014_000000267957_460867.jpg", "ann_id": 460867, "sent_ids": [34489, 34490], "ref_id": 18249}, {"segmentation": [[390.27, 288.05, 390.27, 331.5, 387.95, 341.35, 382.73, 351.19, 379.84, 385.96, 376.36, 394.07, 369.99, 398.12, 348.55, 396.38, 343.92, 397.54, 339.86, 403.34, 337.55, 406.81, 334.07, 409.13, 333.49, 415.5, 331.17, 418.4, 322.48, 419.56, 311.48, 421.29, 306.84, 419.56, 306.26, 406.23, 306.26, 399.28, 306.26, 387.11, 306.26, 376.69, 301.63, 374.95, 280.77, 374.37, 283.67, 367.42, 290.62, 336.71, 300.47, 303.69, 308.58, 288.63, 315.53, 278.78, 321.9, 271.83, 328.86, 266.61, 334.07, 257.92, 336.39, 251.55, 354.93, 245.76, 359.56, 241.12, 353.77, 240.54, 346.81, 232.43, 343.92, 223.74, 342.76, 208.1, 339.86, 197.09, 335.23, 188.4, 336.39, 180.29, 335.81, 173.34, 335.81, 164.07, 345.08, 142.05, 354.35, 131.63, 365.35, 125.83, 376.36, 123.52, 382.73, 121.78, 390.84, 121.2, 399.53, 121.2, 419.23, 131.05, 430.82, 149.59, 441.25, 175.66, 446.46, 182.03, 445.3, 197.67, 437.77, 209.26, 434.29, 212.73, 433.14, 226.06, 436.61, 230.69, 466.16, 241.12, 486.43, 243.44, 510.19, 255.03, 517.14, 261.4, 526.41, 284.57, 540.89, 315.28, 539.15, 330.34, 536.84, 334.97, 533.94, 361.04, 531.04, 396.96, 525.83, 427.09, 516.56, 424.77, 495.13, 423.61, 501.5, 360.46, 500.92, 357.57, 462.1, 356.99, 455.15, 359.31, 452.83, 371.47, 456.89, 396.96, 456.89, 403.91, 451.67, 404.49, 440.09, 405.65, 430.82, 409.13, 423.87, 409.13, 420.39, 403.91, 420.39, 390.59, 420.39, 358.15, 416.34, 345.98, 412.28, 337.29, 410.54, 313.54, 409.38, 286.89, 391.42, 286.31]], "area": 42495.46469999999, "iscrowd": 0, "image_id": 265625, "bbox": [280.77, 121.2, 260.12, 305.89], "category_id": 1, "id": 433472, "split": "val", "sentences": [{"tokens": ["a", "woman", "looking", "at", "a", "phone"], "raw": "A woman looking at a phone.", "sent_id": 34491, "sent": "a woman looking at a phone"}, {"tokens": ["a", "woman", "on", "her", "phone", "at", "a", "diner", "table"], "raw": "A woman on her phone at a diner table.", "sent_id": 34492, "sent": "a woman on her phone at a diner table"}], "file_name": "COCO_train2014_000000265625_433472.jpg", "ann_id": 433472, "sent_ids": [34491, 34492], "ref_id": 18250}, {"segmentation": [[217.91, 333.31, 233.11, 316.21, 237.86, 311.46, 249.26, 304.81, 253.06, 301.96, 251.16, 283.91, 253.06, 268.71, 253.06, 249.71, 255.91, 229.76, 257.81, 216.46, 268.26, 205.06, 279.66, 196.51, 282.51, 193.66, 278.71, 183.21, 283.46, 178.46, 292.01, 173.71, 298.66, 173.71, 304.36, 176.56, 304.36, 178.46, 306.26, 188.91, 306.26, 189.86, 306.26, 198.41, 307.21, 205.06, 310.06, 210.76, 310.06, 219.31, 310.06, 225.96, 311.01, 232.61, 314.81, 233.56, 317.66, 232.61, 328.11, 233.56, 328.11, 238.31, 328.11, 244.96, 314.81, 244.96, 307.21, 243.06, 299.61, 243.06, 307.21, 260.16, 315.76, 272.51, 320.51, 279.16, 332.86, 309.56, 335.71, 328.56, 341.41, 336.16, 339.51, 341.86, 323.36, 336.16, 310.06, 300.06, 285.36, 281.06, 270.16, 315.26, 250.21, 328.56, 242.61, 334.26]], "area": 7910.863750000003, "iscrowd": 0, "image_id": 418569, "bbox": [217.91, 173.71, 123.5, 168.15], "category_id": 1, "id": 459435, "split": "val", "sentences": [{"tokens": ["the", "man", "playing", "in", "a", "water"], "raw": "The man playing in a water", "sent_id": 34505, "sent": "the man playing in a water"}, {"tokens": ["it", "is", "a", "man", "in", "a", "gray", "t", "-", "shirt", "and", "black", "shorts", "standing", "at", "the", "shoreline", "on", "a", "beach", "preparing", "to", "catch", "a", "frisbee", "that", "another", "guy", "has", "thrown", "to", "him"], "raw": "It is a man in a gray t-shirt and black shorts standing at the shoreline on a beach preparing to catch a Frisbee that another guy has thrown to him.", "sent_id": 34506, "sent": "it is a man in a gray t - shirt and black shorts standing at the shoreline on a beach preparing to catch a frisbee that another guy has thrown to him"}], "file_name": "COCO_train2014_000000418569_459435.jpg", "ann_id": 459435, "sent_ids": [34505, 34506], "ref_id": 18256}, {"segmentation": [[180.89, 217.02, 200.99, 128.01, 219.18, 110.79, 252.68, 106.0, 266.08, 92.6, 266.08, 65.8, 278.52, 44.74, 291.92, 39.96, 302.45, 43.79, 315.85, 65.8, 313.93, 101.21, 307.23, 112.7, 323.5, 127.06, 333.07, 177.78, 314.89, 189.27, 295.75, 198.84, 232.58, 240.95, 218.22, 260.09, 213.44, 271.58], [248.85, 285.94, 295.75, 287.85, 301.49, 288.81, 309.15, 336.66, 305.32, 355.81, 276.6, 355.81, 256.51, 338.58]], "area": 21603.936, "iscrowd": 0, "image_id": 176342, "bbox": [180.89, 39.96, 152.18, 315.85], "category_id": 1, "id": 518093, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "purple", "tie"], "raw": "A man wearing a purple tie.", "sent_id": 34562, "sent": "a man wearing a purple tie"}, {"tokens": ["a", "man", "wearing", "a", "black", "suit"], "raw": "A man wearing a black suit.", "sent_id": 34563, "sent": "a man wearing a black suit"}], "file_name": "COCO_train2014_000000176342_518093.jpg", "ann_id": 518093, "sent_ids": [34562, 34563], "ref_id": 18277}, {"segmentation": [[297.45, 409.23, 286.71, 407.08, 287.79, 400.64, 296.38, 392.05, 299.6, 411.38], [301.74, 410.31, 310.34, 404.94, 314.63, 399.57, 323.22, 395.27, 318.93, 357.69, 315.7, 337.28, 312.48, 316.88, 315.7, 296.48, 331.81, 330.84, 325.37, 281.45, 321.07, 239.57, 320.0, 229.9, 322.07, 233.5, 331.74, 285.05, 337.11, 339.81, 355.36, 377.4, 358.58, 390.28, 346.77, 410.68, 358.58, 422.5, 375.77, 390.28, 366.1, 360.21, 353.21, 326.93, 347.85, 295.78, 346.77, 241.02, 363.95, 229.21, 355.36, 186.25, 352.14, 176.59, 333.89, 165.85, 325.3, 162.63, 326.37, 155.11, 331.74, 145.45, 325.3, 128.27, 313.48, 121.83, 300.6, 128.27, 295.23, 143.3, 301.67, 161.56, 302.74, 169.07, 292.01, 176.59, 279.12, 187.33, 274.83, 198.07, 264.09, 209.88, 265.16, 230.28, 272.68, 241.02, 279.12, 244.24, 278.05, 270.01, 281.27, 288.27, 289.86, 301.15, 283.42, 259.27, 282.34, 227.06, 289.86, 250.68, 292.01, 294.71, 293.08, 320.48, 298.45, 330.15, 300.6, 354.85, 304.89, 376.32, 307.04, 388.13, 300.6, 393.5, 300.6, 409.61]], "area": 14836.651800000001, "iscrowd": 0, "image_id": 335524, "bbox": [264.09, 121.83, 111.68, 300.67], "category_id": 1, "id": 437650, "split": "val", "sentences": [{"tokens": ["woman", "in", "the", "pink", "jacket"], "raw": "Woman in the pink jacket.", "sent_id": 34568, "sent": "woman in the pink jacket"}, {"tokens": ["a", "woman", "in", "a", "red", "jacket"], "raw": "A woman in a red jacket.", "sent_id": 34569, "sent": "a woman in a red jacket"}], "file_name": "COCO_train2014_000000335524_437650.jpg", "ann_id": 437650, "sent_ids": [34568, 34569], "ref_id": 18279}, {"segmentation": [[530.47, 139.7, 535.84, 169.77, 536.91, 186.95, 531.54, 196.61, 537.99, 213.8, 545.5, 227.75, 550.87, 228.83, 582.01, 239.57, 599.19, 246.01, 621.74, 258.9, 633.56, 269.63, 640.0, 282.52, 640.0, 427.49, 637.85, 436.08, 619.6, 443.59, 615.3, 450.04, 619.6, 464.0, 622.82, 473.66, 406.98, 473.66, 413.42, 443.59, 417.72, 411.38, 420.94, 399.57, 422.01, 387.75, 404.83, 396.35, 375.84, 395.27, 367.25, 388.83, 357.58, 361.98, 357.58, 340.51, 365.1, 330.84, 375.84, 313.66, 381.21, 292.18, 377.99, 280.37, 379.06, 267.49, 379.06, 255.67, 385.5, 248.16, 400.54, 242.79, 390.87, 255.67, 391.95, 264.26, 405.91, 268.56, 414.5, 270.71, 418.79, 268.56, 427.38, 257.82, 429.53, 239.57, 440.27, 230.98, 440.27, 222.39, 440.27, 221.31, 435.97, 214.87, 441.34, 203.06, 456.38, 195.54, 451.01, 185.88, 437.05, 171.92, 440.27, 148.29, 457.45, 131.11, 475.7, 120.37, 490.74, 113.93, 512.21, 119.3, 524.03, 126.82, 525.1, 131.11, 534.77, 145.07]], "area": 67933.45425000002, "iscrowd": 0, "image_id": 41818, "bbox": [357.58, 113.93, 282.42, 359.73], "category_id": 1, "id": 470955, "split": "val", "sentences": [{"tokens": ["a", "woman", "holding", "a", "glass", "of", "orange", "juice", "and", "smiling", "at", "the", "camera", "with", "her", "hand", "on", "her", "hip"], "raw": "A woman holding a glass of orange juice and smiling at the camera with her hand on her hip.", "sent_id": 34616, "sent": "a woman holding a glass of orange juice and smiling at the camera with her hand on her hip"}, {"tokens": ["a", "lady", "in", "black", "over", "coat", "holding", "a", "glass", "of", "juice", "and", "posing"], "raw": "A lady in black over coat holding a glass of juice and posing.", "sent_id": 34617, "sent": "a lady in black over coat holding a glass of juice and posing"}], "file_name": "COCO_train2014_000000041818_470955.jpg", "ann_id": 470955, "sent_ids": [34616, 34617], "ref_id": 18299}, {"segmentation": [[333.63, 287.3, 207.71, 292.68, 184.04, 303.44, 164.66, 287.3, 180.81, 252.86, 177.58, 218.42, 212.02, 203.35, 245.38, 206.58, 294.89, 211.96, 329.33, 232.41, 334.71, 250.71, 337.94, 275.46]], "area": 12644.08635, "iscrowd": 0, "image_id": 447574, "bbox": [164.66, 203.35, 173.28, 100.09], "category_id": 54, "id": 313489, "split": "val", "sentences": [{"tokens": ["half", "of", "the", "sandwich", "on", "the", "back", "of", "the", "plate"], "raw": "half of the sandwich on the back of the plate", "sent_id": 34635, "sent": "half of the sandwich on the back of the plate"}, {"tokens": ["sandwich", "in", "the", "top", "corner", "of", "the", "plate"], "raw": "sandwich in the top corner of the plate.", "sent_id": 34636, "sent": "sandwich in the top corner of the plate"}], "file_name": "COCO_train2014_000000447574_313489.jpg", "ann_id": 313489, "sent_ids": [34635, 34636], "ref_id": 18309}, {"segmentation": [[266.43, 261.11, 305.26, 172.66, 321.44, 150.0, 340.85, 143.53, 351.64, 141.38, 364.58, 137.06, 360.27, 106.86, 357.03, 80.97, 360.27, 63.71, 367.82, 43.22, 377.53, 31.35, 391.55, 17.33, 418.52, 22.72, 426.07, 25.96, 434.7, 46.45, 439.01, 68.03, 436.85, 101.47, 415.28, 129.51, 432.54, 143.53, 455.19, 155.4, 468.13, 162.95, 476.76, 171.58, 484.31, 217.96, 481.08, 306.41, 470.29, 319.35, 410.97, 346.32, 384.0, 351.71, 377.53, 342.0, 360.27, 320.43, 347.33, 309.64, 344.09, 276.21, 349.48, 255.71, 351.64, 242.77, 344.09, 217.96, 325.75, 209.33, 325.75, 227.67, 325.75, 239.53, 335.46, 251.4, 343.01, 289.15, 332.22, 305.33, 319.28, 306.41, 310.65, 318.27, 296.63, 318.27, 263.19, 281.6]], "area": 42046.19514999999, "iscrowd": 0, "image_id": 464650, "bbox": [263.19, 17.33, 221.12, 334.38], "category_id": 1, "id": 487069, "split": "val", "sentences": [{"tokens": ["the", "blonde", "woman", "using", "a", "stick", "blender"], "raw": "The blonde woman using a stick blender.", "sent_id": 34695, "sent": "the blonde woman using a stick blender"}, {"tokens": ["a", "blonde", "woman", "with", "a", "mixer"], "raw": "A blonde woman with a mixer.", "sent_id": 34696, "sent": "a blonde woman with a mixer"}], "file_name": "COCO_train2014_000000464650_487069.jpg", "ann_id": 487069, "sent_ids": [34695, 34696], "ref_id": 18337}, {"segmentation": [[246.87, 306.89, 274.34, 271.85, 289.49, 268.06, 312.22, 270.9, 394.62, 284.16, 413.57, 287.0, 420.2, 294.58, 421.14, 311.63, 426.83, 335.31, 434.4, 335.31, 442.93, 367.51, 437.25, 370.35, 441.03, 386.45, 461.87, 398.77, 455.24, 416.45, 459.98, 436.34, 454.29, 466.65, 131.32, 463.81, 146.47, 457.18, 143.63, 453.39, 167.31, 418.35, 192.88, 395.62, 200.46, 384.25, 215.61, 365.31, 222.24, 349.21, 234.56, 330.26, 241.19, 314.16, 257.29, 297.11]], "area": 44445.9024, "iscrowd": 0, "image_id": 390474, "bbox": [131.32, 268.06, 330.55, 198.59], "category_id": 33, "id": 2081195, "split": "val", "sentences": [{"tokens": ["a", "blue", "and", "black", "duffle", "bag"], "raw": "A blue and black duffle bag", "sent_id": 34773, "sent": "a blue and black duffle bag"}, {"tokens": ["a", "blue", "bag", "resting", "on", "a", "bed", "surrounded", "by", "other", "luggage"], "raw": "A blue bag resting on a bed surrounded by other luggage", "sent_id": 34774, "sent": "a blue bag resting on a bed surrounded by other luggage"}], "file_name": "COCO_train2014_000000390474_2081195.jpg", "ann_id": 2081195, "sent_ids": [34773, 34774], "ref_id": 18373}, {"segmentation": [[253.75, 369.38, 275.0, 361.88, 276.25, 355.63, 257.5, 354.38, 256.25, 338.13, 270.0, 315.63, 291.25, 305.63, 293.75, 300.63, 290.0, 286.88, 290.0, 274.38, 302.5, 274.38, 325.0, 284.38, 316.25, 299.38, 342.5, 316.88, 337.5, 344.38, 330.0, 371.88, 316.25, 371.88, 315.0, 358.13, 283.75, 355.63, 273.75, 374.38], [248.75, 440.63, 252.5, 451.88, 251.25, 468.13, 281.25, 468.13, 277.5, 454.38, 275.0, 436.88]], "area": 5799.21875, "iscrowd": 0, "image_id": 419324, "bbox": [248.75, 274.38, 93.75, 193.75], "category_id": 1, "id": 2176949, "split": "val", "sentences": [{"tokens": ["man", "with", "a", "grey", "shirt"], "raw": "man with a grey shirt", "sent_id": 34789, "sent": "man with a grey shirt"}, {"tokens": ["a", "guy", "in", "blue", "shirt", "sitting", "on", "a", "chair"], "raw": "A guy in blue shirt sitting on a chair.", "sent_id": 34790, "sent": "a guy in blue shirt sitting on a chair"}], "file_name": "COCO_train2014_000000419324_2176949.jpg", "ann_id": 2176949, "sent_ids": [34789, 34790], "ref_id": 18378}, {"segmentation": [[174.93, 343.84, 174.93, 332.57, 172.28, 309.37, 173.61, 293.46, 177.59, 274.23, 182.89, 256.33, 184.21, 240.42, 205.43, 260.31, 211.39, 278.87, 214.05, 282.19, 222.66, 271.58, 216.7, 256.99, 211.39, 242.41, 203.44, 228.49, 197.47, 218.54, 192.83, 196.67, 194.82, 182.75, 179.57, 162.86, 165.65, 164.85, 145.1, 184.07, 152.39, 201.97, 142.45, 213.9, 137.81, 228.49, 132.51, 246.39, 126.54, 267.6, 131.18, 286.16, 137.15, 297.43, 135.16, 314.01, 123.23, 322.62, 119.91, 336.55, 127.87, 339.86, 140.46, 333.89, 147.75, 330.58, 149.74, 352.46, 171.62, 345.16]], "area": 9124.31725, "iscrowd": 0, "image_id": 413391, "bbox": [119.91, 162.86, 102.75, 189.6], "category_id": 1, "id": 559713, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "chasing", "a", "ball"], "raw": "A young boy chasing a ball.", "sent_id": 34859, "sent": "a young boy chasing a ball"}, {"tokens": ["little", "boy", "chasing", "a", "soccer", "ball"], "raw": "little boy chasing a soccer ball", "sent_id": 34860, "sent": "little boy chasing a soccer ball"}], "file_name": "COCO_train2014_000000413391_559713.jpg", "ann_id": 559713, "sent_ids": [34859, 34860], "ref_id": 18399}, {"segmentation": [[445.55, 391.54, 480.0, 306.77, 480.0, 172.54, 476.84, 160.43, 365.83, 133.19, 290.14, 237.13, 243.71, 307.78, 262.89, 322.91, 302.25, 337.04, 413.26, 373.37, 443.54, 385.49]], "area": 39277.56870000001, "iscrowd": 0, "image_id": 503022, "bbox": [243.71, 133.19, 236.29, 258.35], "category_id": 51, "id": 1903758, "split": "val", "sentences": [{"tokens": ["purple", "box", "with", "salad", "greens", ",", "sliced", "almonds", "and", "purple", "flowers"], "raw": "Purple box with salad greens, sliced almonds and purple flowers", "sent_id": 34878, "sent": "purple box with salad greens , sliced almonds and purple flowers"}, {"tokens": ["purple", "container", "with", "purple", "flowers", ",", "green", "leaves", "and", "sliced", "almonds"], "raw": "Purple container with purple flowers, green leaves and sliced almonds", "sent_id": 34879, "sent": "purple container with purple flowers , green leaves and sliced almonds"}], "file_name": "COCO_train2014_000000503022_1903758.jpg", "ann_id": 1903758, "sent_ids": [34878, 34879], "ref_id": 18407}, {"segmentation": [[155.07, 369.96, 167.99, 381.89, 183.97, 383.89, 191.97, 381.89, 199.56, 376.29, 205.96, 365.5, 207.95, 348.31, 204.36, 319.94, 195.16, 294.76, 184.37, 276.77, 183.04, 275.24, 198.09, 270.15, 197.6, 265.54, 203.25, 258.34, 207.48, 248.47, 204.31, 242.47, 197.96, 232.59, 190.19, 226.59, 188.08, 218.13, 183.49, 217.07, 174.32, 219.54, 173.26, 215.66, 174.32, 213.19, 180.32, 210.72, 178.91, 199.07, 176.44, 194.49, 173.97, 192.02, 155.62, 190.96, 137.98, 195.19, 122.1, 204.37, 111.87, 204.37, 110.11, 199.43, 110.46, 195.55, 90.1, 188.43, 69.69, 175.26, 68.1, 173.44, 69.47, 171.51, 71.95, 170.96, 71.95, 169.04, 70.57, 167.66, 73.05, 161.62, 69.47, 157.22, 75.52, 150.35, 84.87, 146.77, 92.84, 143.47, 96.69, 139.35, 108.23, 133.3, 107.13, 131.1, 117.58, 124.78, 115.93, 121.21, 112.9, 119.83, 95.31, 130.01, 91.74, 127.53, 81.84, 128.36, 70.57, 135.78, 64.25, 137.43, 56.55, 134.4, 42.81, 132.48, 35.39, 134.13, 25.22, 144.02, 23.84, 155.29, 24.39, 158.87, 19.44, 161.89, 18.34, 166.57, 16.42, 164.92, 15.6, 163.27, 1.03, 174.54, 0.75, 184.16, 0.2, 191.3, 10.1, 182.51, 15.32, 182.51, 23.84, 177.56, 26.32, 186.91, 22.19, 190.21, 15.05, 192.13, 10.92, 192.4, 8.17, 195.98, 7.35, 198.18, 10.1, 202.85, 15.87, 202.3, 21.37, 195.7, 26.32, 194.33, 27.14, 205.32, 26.86, 212.99, 18.86, 222.98, 16.86, 230.57, 36.85, 250.16, 31.65, 256.15, 22.86, 266.14, 23.26, 283.73, 25.26, 292.12, 34.45, 315.7, 41.64, 325.69, 58.43, 341.28, 69.22, 346.88, 79.21, 346.08, 58.03, 374.06, 68.42, 374.45, 71.22, 374.06, 69.62, 369.66, 96.4, 337.68, 104.79, 320.5, 111.59, 318.1, 129.97, 332.49, 141.56, 349.68, 155.55, 370.86]], "area": 30426.04619999999, "iscrowd": 0, "image_id": 287140, "bbox": [0.2, 119.83, 207.75, 264.06], "category_id": 4, "id": 151613, "split": "val", "sentences": [{"tokens": ["the", "racing", "bike", ",", "having", "white", "and", "black", "colors"], "raw": "the racing bike, having white and black colors", "sent_id": 34934, "sent": "the racing bike , having white and black colors"}, {"tokens": ["white", "colour", "motor", "cycle"], "raw": "white colour motor cycle", "sent_id": 34935, "sent": "white colour motor cycle"}], "file_name": "COCO_train2014_000000287140_151613.jpg", "ann_id": 151613, "sent_ids": [34934, 34935], "ref_id": 18429}, {"segmentation": [[527.65, 168.16, 520.38, 160.34, 513.68, 160.34, 505.3, 162.01, 502.5, 164.25, 491.88, 167.04, 461.71, 170.95, 437.12, 181.01, 429.86, 184.92, 410.3, 188.83, 409.74, 189.95, 401.36, 176.54, 393.54, 181.01, 394.65, 190.51, 372.86, 191.63, 339.33, 188.28, 328.16, 184.92, 318.66, 184.92, 296.87, 193.86, 285.69, 202.8, 275.63, 225.16, 272.28, 246.39, 263.34, 267.62, 279.54, 265.95, 279.54, 232.98, 289.6, 211.19, 327.6, 192.75, 419.8, 205.04, 446.06, 198.89, 483.5, 186.04, 515.35, 170.39], [264.16, 277.05, 259.56, 300.06, 266.0, 300.98, 279.81, 275.21], [329.51, 312.03, 342.4, 348.84, 353.45, 344.24, 335.04, 299.14], [412.35, 295.46, 405.91, 302.82, 398.55, 312.03, 375.54, 321.23, 386.58, 327.67, 370.93, 335.04, 379.22, 350.68, 393.94, 335.96, 421.56, 298.22], [442.73, 303.74, 445.49, 318.47, 454.69, 340.56, 456.53, 304.66]], "area": 5669.858799999999, "iscrowd": 0, "image_id": 182706, "bbox": [259.56, 160.34, 268.09, 190.34], "category_id": 19, "id": 57063, "split": "val", "sentences": [{"tokens": ["a", "horse", "behind", "the", "another", "horse"], "raw": "A horse behind the another horse.", "sent_id": 34938, "sent": "a horse behind the another horse"}], "file_name": "COCO_train2014_000000182706_57063.jpg", "ann_id": 57063, "sent_ids": [34938], "ref_id": 18431}, {"segmentation": [[341.17, 152.77, 313.18, 162.46, 252.91, 151.7, 202.33, 164.61, 184.04, 191.52, 186.19, 169.99, 182.96, 142.01, 206.64, 74.21, 231.39, 56.99, 256.14, 51.61, 294.89, 61.29, 337.94, 78.51, 362.69, 106.49, 354.08, 126.94, 339.01, 152.77]], "area": 15019.37145, "iscrowd": 0, "image_id": 219943, "bbox": [182.96, 51.61, 179.73, 139.91], "category_id": 54, "id": 313397, "split": "val", "sentences": [{"tokens": ["piece", "of", "bread", "nearer", "to", "the", "phone"], "raw": "piece of bread nearer to the phone", "sent_id": 34976, "sent": "piece of bread nearer to the phone"}, {"tokens": ["a", "half", "of", "sandwich", "that", "is", "not", "touching", "a", "pickle"], "raw": "A half of sandwich that is not touching a pickle.", "sent_id": 34977, "sent": "a half of sandwich that is not touching a pickle"}], "file_name": "COCO_train2014_000000219943_313397.jpg", "ann_id": 313397, "sent_ids": [34976, 34977], "ref_id": 18446}, {"segmentation": [[362.82, 274.59, 330.27, 265.97, 291.02, 268.84, 264.22, 291.82, 251.77, 310.96, 249.86, 336.81, 244.11, 377.02, 245.07, 421.05, 296.76, 417.22, 290.06, 331.07, 306.34, 310.01, 334.1, 298.52, 342.71, 304.26, 362.82, 275.54]], "area": 8401.743399999996, "iscrowd": 0, "image_id": 39802, "bbox": [244.11, 265.97, 118.71, 155.08], "category_id": 62, "id": 1590949, "split": "val", "sentences": [{"tokens": ["black", "colored", "coat", "in", "the", "chair", "of", "man", "with", "white", "shirt"], "raw": "black colored coat in the chair of man with white shirt", "sent_id": 34998, "sent": "black colored coat in the chair of man with white shirt"}, {"tokens": ["jacket", "on", "back", "of", "chair", "of", "picture", "taker"], "raw": "Jacket on back of chair of picture taker", "sent_id": 34999, "sent": "jacket on back of chair of picture taker"}], "file_name": "COCO_train2014_000000039802_1590949.jpg", "ann_id": 1590949, "sent_ids": [34998, 34999], "ref_id": 18455}, {"segmentation": [[6.99, 287.56, 29.76, 287.56, 61.07, 284.72, 74.36, 282.82, 98.08, 288.51, 116.11, 291.36, 136.03, 248.66, 184.42, 222.09, 160.7, 223.99, 107.57, 208.81, 85.74, 205.01, 81.95, 193.63, 75.31, 196.47, 71.51, 205.96, 20.27, 208.81, 6.04, 212.6]], "area": 10542.963749999999, "iscrowd": 0, "image_id": 310536, "bbox": [6.04, 193.63, 178.38, 97.73], "category_id": 28, "id": 1425130, "split": "val", "sentences": [{"tokens": ["the", "umbrella", "on", "the", "left"], "raw": "the umbrella on the left", "sent_id": 35081, "sent": "the umbrella on the left"}, {"tokens": ["one", "of", "two", "umbrellas", "on", "the", "beach"], "raw": "One of two umbrellas on the beach", "sent_id": 35082, "sent": "one of two umbrellas on the beach"}], "file_name": "COCO_train2014_000000310536_1425130.jpg", "ann_id": 1425130, "sent_ids": [35081, 35082], "ref_id": 18491}, {"segmentation": [[217.83, 65.05, 238.41, 54.43, 240.4, 49.78, 240.4, 34.51, 238.41, 29.86, 238.41, 26.54, 239.08, 18.58, 243.06, 13.27, 258.78, 8.46, 263.43, 9.79, 268.74, 14.44, 273.38, 22.4, 279.36, 40.99, 276.04, 48.96, 274.05, 53.6, 291.31, 74.18, 299.27, 96.76, 303.26, 109.37, 303.26, 138.58, 291.97, 133.93, 284.01, 127.96, 281.35, 127.96, 277.37, 128.62, 271.39, 128.62, 266.75, 130.61, 257.45, 138.58, 257.45, 146.55, 250.15, 155.84, 238.86, 154.51, 232.22, 153.18, 231.56, 148.54, 233.55, 132.6, 233.55, 129.95, 233.55, 121.32, 230.9, 102.73, 223.59, 92.11, 224.92, 81.49, 225.59, 76.84, 224.26, 70.2, 224.26, 68.87, 222.27, 66.22]], "area": 7271.955400000001, "iscrowd": 0, "image_id": 253907, "bbox": [217.83, 8.46, 85.43, 147.38], "category_id": 1, "id": 211403, "split": "val", "sentences": [{"tokens": ["the", "person", "wearing", "the", "blue", ",", "white", ",", "and", "black", "shirt"], "raw": "the person wearing the blue, white, and black shirt", "sent_id": 35097, "sent": "the person wearing the blue , white , and black shirt"}, {"tokens": ["a", "person", "with", "white", "and", "blue", "shirt", "on", "sitting", "on", "a", "motorcycle"], "raw": "A person with white and blue shirt on sitting on a motorcycle.", "sent_id": 35098, "sent": "a person with white and blue shirt on sitting on a motorcycle"}], "file_name": "COCO_train2014_000000253907_211403.jpg", "ann_id": 211403, "sent_ids": [35097, 35098], "ref_id": 18497}, {"segmentation": [[233.17, 151.32, 282.11, 154.19, 304.18, 159.95, 313.77, 175.3, 316.65, 200.25, 322.41, 227.12, 328.17, 252.07, 329.13, 270.3, 335.84, 280.86, 330.09, 292.37, 324.33, 275.1, 319.53, 248.23, 318.57, 234.8, 311.85, 265.5, 307.06, 281.81, 293.62, 283.73, 292.66, 250.15, 291.7, 230.96, 285.95, 222.32, 274.43, 207.93, 264.84, 218.48, 252.36, 244.39, 250.44, 274.14, 250.44, 294.29, 234.13, 299.09, 235.09, 264.54, 237.01, 237.68, 242.77, 215.61, 241.81, 212.73, 227.41, 241.51, 226.45, 266.46, 222.62, 285.65, 218.78, 290.45, 211.1, 285.65, 209.18, 253.03, 213.98, 229.04, 218.78, 208.89, 221.66, 196.41, 211.1, 224.24, 201.51, 215.61, 198.63, 196.41, 199.59, 178.18, 194.79, 166.67, 179.44, 152.28, 187.11, 156.11, 213.02, 158.03, 220.7, 148.44]], "area": 11783.277900000001, "iscrowd": 0, "image_id": 210279, "bbox": [179.44, 148.44, 156.4, 150.65], "category_id": 24, "id": 593240, "split": "val", "sentences": [{"tokens": ["a", "baby", "zebra", "getting", "help", "from", "his", "mother", "to", "help", "him", "stand", "up", "just", "moments", "after", "he", "was", "born"], "raw": "A baby zebra getting help from his mother to help him stand up just moments after he was born.", "sent_id": 35103, "sent": "a baby zebra getting help from his mother to help him stand up just moments after he was born"}, {"tokens": ["a", "baby", "zeebra", "struggling", "to", "walk"], "raw": "A baby zeebra struggling to walk.", "sent_id": 35104, "sent": "a baby zeebra struggling to walk"}], "file_name": "COCO_train2014_000000210279_593240.jpg", "ann_id": 593240, "sent_ids": [35103, 35104], "ref_id": 18500}, {"segmentation": [[335.34, 364.03, 307.57, 378.68, 307.19, 383.31, 590.98, 421.86, 598.69, 410.3, 607.56, 391.79, 604.86, 374.82, 601.39, 366.34, 563.22, 365.57, 562.45, 362.87, 549.72, 362.48, 549.34, 363.64, 528.9, 363.26, 525.81, 357.47, 519.26, 356.31, 499.21, 356.31, 498.05, 353.23, 495.74, 354.0, 492.65, 356.31, 482.24, 357.09, 471.83, 352.46, 464.89, 352.84, 463.35, 354.39, 441.76, 352.46, 439.44, 353.23, 424.41, 354.39, 411.3, 355.16, 407.44, 358.63, 401.66, 365.18, 392.79, 369.42, 359.63, 372.51, 342.66, 368.65, 336.11, 365.18, 335.34, 362.87]], "area": 12065.794950000005, "iscrowd": 0, "image_id": 220842, "bbox": [307.19, 352.46, 300.37, 69.4], "category_id": 79, "id": 2228271, "split": "val", "sentences": [{"tokens": ["four", "burners", "on", "top", "of", "a", "large", "stove"], "raw": "Four burners on top of a large stove", "sent_id": 35301, "sent": "four burners on top of a large stove"}, {"tokens": ["a", "stainless", "steel", "gas", "stove", "top", "with", "a", "pie"], "raw": "a stainless steel gas stove top with a pie", "sent_id": 35302, "sent": "a stainless steel gas stove top with a pie"}], "file_name": "COCO_train2014_000000220842_2228271.jpg", "ann_id": 2228271, "sent_ids": [35301, 35302], "ref_id": 18575}, {"segmentation": [[296.32, 134.93, 299.49, 113.4, 307.72, 105.81, 312.15, 102.64, 312.15, 86.18, 316.58, 76.69, 327.34, 76.69, 336.2, 83.65, 341.27, 95.04, 343.8, 102.01, 348.87, 105.17, 364.06, 115.3, 381.15, 130.5, 379.89, 147.59, 376.09, 174.81, 379.25, 188.74, 377.35, 199.5, 383.05, 266.61, 381.15, 278.0, 386.85, 286.23, 377.35, 289.4, 371.66, 280.53, 360.26, 230.52, 346.33, 188.74, 342.54, 188.11, 331.14, 212.79, 308.35, 184.94, 306.45, 184.31, 314.05, 162.78, 315.95, 155.82, 312.78, 139.36, 310.88, 137.46, 305.82, 147.59, 286.83, 150.75, 283.66, 143.16, 295.69, 135.56], [287.46, 288.13, 300.12, 274.84, 299.49, 254.58, 308.98, 265.34, 307.08, 283.07, 304.55, 290.66, 296.32, 291.93, 289.36, 289.4]], "area": 9297.4249, "iscrowd": 0, "image_id": 505924, "bbox": [283.66, 76.69, 103.19, 215.24], "category_id": 1, "id": 484138, "split": "val", "sentences": [{"tokens": ["a", "girl", "playing", "soccer", "as", "a", "goalie", "and", "has", "the", "number", "1"], "raw": "A girl playing soccer as a goalie and has the number 1.", "sent_id": 35392, "sent": "a girl playing soccer as a goalie and has the number 1"}, {"tokens": ["the", "girl", "with", "the", "number", "'", "1", "'", "on", "her", "shirt"], "raw": "The girl with the number '1' on her shirt", "sent_id": 35393, "sent": "the girl with the number ' 1 ' on her shirt"}], "file_name": "COCO_train2014_000000505924_484138.jpg", "ann_id": 484138, "sent_ids": [35392, 35393], "ref_id": 18602}, {"segmentation": [[162.82, 365.99, 156.31, 314.72, 152.87, 295.59, 151.34, 284.5, 153.25, 261.54, 163.2, 229.4, 186.92, 201.47, 206.05, 188.46, 251.2, 213.33, 307.83, 261.92, 327.34, 283.73, 330.78, 291.77, 345.32, 321.61, 339.58, 353.75, 335.76, 364.85, 334.61, 372.88, 308.59, 369.82, 308.98, 318.55, 293.67, 337.68, 291.37, 361.78, 286.02, 369.82, 258.09, 370.2, 258.09, 368.29, 261.53, 320.08, 246.99, 321.61, 241.64, 331.56, 224.03, 352.6, 219.83, 367.52, 165.49, 365.23], [163.2, 427.0, 158.98, 416.48, 155.1, 409.35, 176.16, 409.03, 177.78, 414.86, 188.79, 415.83, 188.14, 427.0], [290.38, 132.43, 307.57, 119.19, 329.87, 113.84, 339.62, 111.52, 365.87, 114.08, 412.33, 120.35, 451.12, 129.64, 492.0, 144.04, 500.6, 147.76, 541.01, 161.7, 549.14, 163.09, 555.18, 157.98, 555.18, 151.47, 555.88, 144.74, 574.23, 150.78, 574.7, 157.28, 580.5, 167.27, 581.2, 167.97, 582.29, 169.71, 581.69, 172.1, 580.5, 176.87, 580.5, 181.94, 562.02, 188.79, 559.63, 192.97, 555.16, 202.51, 555.16, 226.06, 554.56, 230.83, 551.28, 225.76, 549.79, 216.82, 548.9, 213.54, 520.28, 212.94, 497.62, 211.75, 457.08, 205.79, 435.32, 198.93, 406.4, 194.76, 388.51, 195.35, 374.2, 201.91, 365.85, 212.05, 364.07, 207.87, 353.93, 195.95, 339.02, 176.27, 330.38, 167.03], [592.54, 182.89, 597.86, 178.36, 599.23, 175.02, 613.59, 186.82, 615.75, 190.75, 613.79, 193.31, 611.03, 193.51, 607.69, 191.34, 600.61, 187.8, 593.53, 183.87, 592.15, 183.67], [600.02, 170.1, 617.72, 159.88, 625.0, 162.43, 617.72, 172.07, 621.85, 182.89, 639.36, 172.07, 639.95, 178.17, 635.42, 187.02, 631.69, 189.77, 630.9, 191.15, 615.21, 223.57, 614.67, 195.33, 615.58, 189.36, 613.77, 184.11, 599.47, 171.62]], "area": 43158.853700000014, "iscrowd": 0, "image_id": 473348, "bbox": [151.34, 111.52, 488.61, 315.48], "category_id": 25, "id": 598515, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "eating", "from", "the", "water", "jug"], "raw": "The giraffe eating from the water jug.", "sent_id": 35411, "sent": "the giraffe eating from the water jug"}], "file_name": "COCO_train2014_000000473348_598515.jpg", "ann_id": 598515, "sent_ids": [35411], "ref_id": 18611}, {"segmentation": [[85.21, 465.98, 45.3, 362.43, 37.75, 331.15, 46.38, 307.42, 50.7, 272.9, 50.7, 250.25, 49.62, 230.83, 49.62, 213.57, 57.17, 192.0, 71.19, 171.51, 87.37, 155.33, 91.69, 140.22, 89.53, 126.2, 89.53, 102.47, 107.87, 85.21, 114.34, 83.06, 134.83, 89.53, 147.78, 99.24, 152.09, 112.18, 151.01, 134.83, 142.38, 152.09, 134.83, 174.74, 133.75, 180.13, 152.09, 208.18, 162.88, 214.65, 172.58, 214.65, 177.98, 222.2, 186.61, 217.89, 194.16, 208.18, 199.55, 193.08, 212.49, 192.0, 217.89, 197.39, 216.81, 209.26, 207.1, 216.81, 197.39, 228.67, 199.55, 229.75, 204.94, 229.75, 209.26, 227.6, 221.12, 213.57, 231.91, 209.26, 237.3, 206.02, 237.3, 212.49, 245.93, 230.83, 239.46, 239.46, 227.6, 243.78, 220.04, 244.85, 211.42, 249.17, 198.47, 264.27, 188.76, 276.13, 187.69, 278.29, 187.69, 300.94, 187.69, 322.52, 188.76, 343.01, 186.61, 365.66, 177.98, 392.63, 171.51, 412.04, 169.35, 423.91, 167.19, 424.99, 129.44, 439.01, 124.04, 444.4, 125.12, 463.82, 125.12, 474.61, 130.52, 478.92, 89.53, 478.92, 80.9, 459.51]], "area": 41999.08945, "iscrowd": 0, "image_id": 433296, "bbox": [37.75, 83.06, 208.18, 395.86], "category_id": 1, "id": 199198, "split": "val", "sentences": [{"tokens": ["the", "short", "haired", "woman", "on", "the", "left", "wearing", "a", "black", "sweater"], "raw": "The short haired woman on the left wearing a black sweater.", "sent_id": 35452, "sent": "the short haired woman on the left wearing a black sweater"}, {"tokens": ["a", "woman", "dressed", "in", "black", "who", "appears", "to", "be", "talking", "to", "someone"], "raw": "A woman dressed in black who appears to be talking to someone.", "sent_id": 35453, "sent": "a woman dressed in black who appears to be talking to someone"}], "file_name": "COCO_train2014_000000433296_199198.jpg", "ann_id": 199198, "sent_ids": [35452, 35453], "ref_id": 18629}, {"segmentation": [[463.48, 312.77, 448.0, 282.84, 423.23, 265.29, 408.77, 260.13, 401.55, 246.71, 396.39, 226.06, 396.39, 215.74, 397.42, 208.52, 409.81, 206.45, 395.35, 187.87, 374.71, 177.55, 362.32, 164.13, 347.87, 152.77, 370.58, 140.39, 394.32, 135.23, 438.71, 120.77, 426.32, 123.87, 458.32, 112.52, 505.81, 112.52, 554.32, 131.1, 565.68, 154.84, 592.52, 173.42, 610.06, 184.77, 617.29, 183.74, 624.52, 194.06, 624.52, 201.29, 620.39, 213.68, 619.35, 222.97, 612.13, 222.97, 580.13, 213.68, 569.81, 220.9, 555.35, 232.26, 550.19, 240.52, 546.06, 251.87, 541.94, 264.26, 523.35, 261.16, 507.87, 261.16, 477.94, 275.61, 470.71, 285.94, 472.77, 299.35, 478.97, 309.68, 506.84, 312.77, 519.23, 321.03, 496.52, 321.03, 503.74, 330.32, 484.13, 334.45, 468.65, 326.19, 459.35, 318.97, 461.42, 309.68]], "area": 29491.589599999996, "iscrowd": 0, "image_id": 33992, "bbox": [347.87, 112.52, 276.65, 221.93], "category_id": 16, "id": 40444, "split": "val", "sentences": [{"tokens": ["chicken", "on", "right"], "raw": "chicken on right", "sent_id": 35475, "sent": "chicken on right"}, {"tokens": ["a", "chicken", "to", "the", "right", "of", "another", "chicken"], "raw": "a chicken to the right of another chicken", "sent_id": 35476, "sent": "a chicken to the right of another chicken"}], "file_name": "COCO_train2014_000000033992_40444.jpg", "ann_id": 40444, "sent_ids": [35475, 35476], "ref_id": 18641}, {"segmentation": [[215.47, 398.72, 211.36, 369.3, 208.62, 343.98, 203.83, 310.45, 207.26, 274.87, 213.41, 254.35, 206.57, 246.13, 196.31, 235.87, 190.15, 226.98, 190.15, 212.61, 191.52, 207.13, 213.41, 193.45, 219.57, 192.76, 231.2, 178.39, 261.99, 166.08, 268.84, 166.08, 286.63, 169.5, 294.84, 172.24, 298.94, 169.5, 311.94, 174.97, 320.15, 193.45, 322.21, 197.55, 313.31, 211.24, 306.39, 215.89, 307.87, 221.84, 308.62, 233.74, 320.52, 249.36, 333.9, 267.95, 346.54, 273.15, 367.36, 282.07, 371.82, 287.28, 370.34, 290.25, 371.08, 303.64, 381.49, 336.36, 388.18, 350.48, 379.26, 360.15, 369.59, 361.64, 361.41, 365.35, 354.72, 380.23, 340.59, 372.79, 333.16, 372.79, 338.36, 391.38, 337.62, 398.82, 307.13, 400.0, 219.39, 398.07]], "area": 31248.399199999993, "iscrowd": 0, "image_id": 296760, "bbox": [190.15, 166.08, 198.03, 233.92], "category_id": 18, "id": 15956, "split": "val", "sentences": [{"tokens": ["black", "dog"], "raw": "Black dog.", "sent_id": 35499, "sent": "black dog"}, {"tokens": ["a", "solid", "black", "dog"], "raw": "a solid black dog", "sent_id": 35500, "sent": "a solid black dog"}], "file_name": "COCO_train2014_000000296760_15956.jpg", "ann_id": 15956, "sent_ids": [35499, 35500], "ref_id": 18648}, {"segmentation": [[252.43, 273.05, 281.52, 270.36, 285.55, 257.38, 308.37, 251.56, 305.69, 250.67, 304.79, 247.54, 305.69, 245.3, 307.48, 244.85, 309.27, 244.85, 309.71, 247.09, 309.71, 250.22, 339.7, 252.01, 344.17, 256.49, 344.17, 264.54, 355.81, 267.68, 357.15, 280.65, 354.02, 284.68, 353.57, 293.18, 361.63, 292.74, 359.84, 277.52, 356.7, 260.07, 358.49, 244.85, 392.95, 243.96, 470.37, 252.46, 469.92, 257.83, 452.92, 261.41, 452.02, 294.53, 449.34, 299.0, 446.21, 299.45, 432.33, 299.0, 435.47, 307.06, 435.02, 316.9, 430.99, 324.06, 422.49, 324.51, 417.57, 319.59, 412.64, 327.2, 399.22, 326.75, 389.82, 323.62, 385.34, 319.59, 384.0, 309.74, 375.5, 311.98, 377.29, 325.85, 363.42, 325.41, 361.63, 311.53, 348.2, 311.98, 347.75, 320.48, 328.06, 320.03, 321.8, 303.03, 315.08, 303.48, 321.8, 318.24, 320.9, 328.99, 311.06, 337.94, 300.32, 337.94, 292.26, 331.67, 292.26, 327.2, 290.92, 320.93, 290.92, 317.35, 289.58, 313.77, 277.94, 310.64, 278.83, 322.72, 278.83, 330.33, 268.09, 330.78, 260.93, 328.99, 257.35, 324.51, 256.91, 319.59, 256.91, 315.56, 253.33, 314.22, 238.56, 311.08]], "area": 13807.22435, "iscrowd": 0, "image_id": 30519, "bbox": [238.56, 243.96, 231.81, 93.98], "category_id": 8, "id": 398113, "split": "val", "sentences": [{"tokens": ["the", "orange", "truck", "and", "trailor", "closest", "to", "the", "orange", "box", "truck"], "raw": "The orange truck and trailor closest to the orange box truck", "sent_id": 35571, "sent": "the orange truck and trailor closest to the orange box truck"}], "file_name": "COCO_train2014_000000030519_398113.jpg", "ann_id": 398113, "sent_ids": [35571], "ref_id": 18679}, {"segmentation": [[268.59, 355.87, 270.99, 339.7, 278.17, 324.12, 288.96, 309.74, 299.14, 291.17, 312.32, 283.98, 327.9, 273.2, 333.29, 263.61, 339.88, 246.24, 336.88, 230.06, 335.09, 221.67, 336.29, 211.49, 335.09, 205.5, 335.69, 197.71, 342.28, 188.13, 353.66, 186.33, 359.65, 189.32, 363.24, 194.72, 360.25, 207.3, 357.25, 216.88, 358.45, 272.0, 360.25, 276.79, 365.64, 286.22, 366.84, 304.19, 367.44, 319.77, 357.85, 340.14, 337.48, 360.51, 321.91, 370.69, 328.5, 391.66, 348.27, 391.66, 351.86, 399.45, 342.88, 400.05, 338.68, 399.45, 341.08, 413.23, 327.9, 398.25, 319.51, 400.05, 310.52, 397.05, 316.52, 389.86, 313.52, 371.89, 308.13, 373.69, 290.16, 386.87, 286.56, 395.25, 278.17, 388.66, 278.77, 377.28, 284.76, 373.09, 281.17, 359.91, 275.18, 356.91, 269.19, 356.31]], "area": 9756.564550000003, "iscrowd": 0, "image_id": 240500, "bbox": [268.59, 186.33, 98.85, 226.9], "category_id": 16, "id": 38268, "split": "val", "sentences": [{"tokens": ["a", "swan", "on", "a", "bench"], "raw": "A swan on a bench.", "sent_id": 35594, "sent": "a swan on a bench"}, {"tokens": ["white", "pelican", "standing", "on", "top", "of", "a", "bench"], "raw": "White pelican standing on top of a bench.", "sent_id": 35595, "sent": "white pelican standing on top of a bench"}], "file_name": "COCO_train2014_000000240500_38268.jpg", "ann_id": 38268, "sent_ids": [35594, 35595], "ref_id": 18687}, {"segmentation": [[311.35, 217.84, 305.95, 151.89, 302.7, 130.27, 301.62, 72.97, 257.3, 74.05, 232.43, 79.46, 206.49, 100.0, 179.46, 108.65, 157.84, 122.7, 100.54, 133.51, 99.46, 150.81, 59.46, 177.84, 27.03, 212.43, 29.19, 217.84, 36.76, 235.14, 107.03, 243.78, 251.89, 244.86, 303.78, 227.57]], "area": 33564.38105, "iscrowd": 0, "image_id": 468117, "bbox": [27.03, 72.97, 284.32, 171.89], "category_id": 59, "id": 1570269, "split": "val", "sentences": [{"tokens": ["a", "few", "slices", "of", "pizza", "among", "a", "complete", "pizza"], "raw": "A few slices of pizza among a complete pizza", "sent_id": 35629, "sent": "a few slices of pizza among a complete pizza"}, {"tokens": ["two", "slices", "of", "pizza", "sit", "next", "to", "a", "slice", "that", "has", "the", "tip", "cut", "off"], "raw": "Two slices of pizza sit next to a slice that has the tip cut off.", "sent_id": 35630, "sent": "two slices of pizza sit next to a slice that has the tip cut off"}], "file_name": "COCO_train2014_000000468117_1570269.jpg", "ann_id": 1570269, "sent_ids": [35629, 35630], "ref_id": 18697}, {"segmentation": [[504.67, 274.53, 542.7, 269.39, 572.51, 266.31, 595.12, 267.34, 638.29, 274.53, 638.29, 284.81, 640.0, 403.01, 612.59, 397.87, 608.48, 396.84, 605.4, 407.12, 594.09, 413.29, 580.73, 412.26, 575.59, 405.07, 573.53, 395.82, 568.39, 390.68, 496.45, 383.48, 492.33, 388.62, 487.19, 393.76, 469.72, 393.76, 462.53, 386.57, 456.36, 369.09, 440.94, 352.65, 440.94, 333.12, 451.22, 308.45, 451.22, 301.26, 460.47, 296.12, 471.78, 296.12, 483.08, 287.89, 491.31, 280.7]], "area": 22573.497200000005, "iscrowd": 0, "image_id": 329339, "bbox": [440.94, 266.31, 199.06, 146.98], "category_id": 3, "id": 134424, "split": "val", "sentences": [{"tokens": ["a", "white", "car", "in", "front", "of", "a", "city", "bus"], "raw": "A white car in front of a city bus.", "sent_id": 35700, "sent": "a white car in front of a city bus"}, {"tokens": ["a", "light", "-", "colored", "sedan", "in", "front", "of", "a", "bus"], "raw": "A light-colored sedan in front of a bus.", "sent_id": 35701, "sent": "a light - colored sedan in front of a bus"}], "file_name": "COCO_train2014_000000329339_134424.jpg", "ann_id": 134424, "sent_ids": [35700, 35701], "ref_id": 18722}, {"segmentation": [[183.66, 220.02, 203.16, 209.46, 230.79, 190.77, 251.92, 228.15, 264.11, 255.78, 278.74, 278.53, 289.3, 302.91, 299.86, 327.29, 328.31, 319.16, 323.43, 298.85, 323.43, 266.34, 336.43, 272.03, 394.13, 277.72, 404.7, 306.16, 421.76, 333.79, 429.89, 338.67, 449.39, 328.92, 466.46, 325.67, 480.27, 320.79, 480.27, 306.98, 476.21, 288.28, 475.4, 276.91, 487.58, 255.78, 498.96, 235.46, 506.28, 250.09, 515.21, 272.84, 524.97, 285.03, 539.59, 277.72, 537.16, 268.78, 527.4, 257.4, 510.34, 233.02, 499.77, 209.46, 492.46, 186.7, 469.71, 166.39, 396.57, 172.08, 343.75, 168.01, 329.93, 150.95, 271.42, 133.88, 238.1, 111.94, 195.85, 116.0, 198.28, 124.13, 207.22, 130.63, 211.29, 134.7, 195.85, 154.2, 169.84, 183.45, 165.78, 217.58, 179.59, 227.34]], "area": 40326.06410000001, "iscrowd": 0, "image_id": 348315, "bbox": [165.78, 111.94, 373.81, 226.73], "category_id": 24, "id": 589333, "split": "val", "sentences": [{"tokens": ["two", "black", "and", "white", "zebras", "standing", "in", "a", "field", "of", "wheat"], "raw": "Two black and white zebras standing in a field of wheat", "sent_id": 35705, "sent": "two black and white zebras standing in a field of wheat"}, {"tokens": ["a", "zebra", "standing", "in", "front", "of", "another", ",", "with", "his", "tail", "blowing", "in", "the", "wind"], "raw": "A zebra standing in front of another, with his tail blowing in the wind.", "sent_id": 35706, "sent": "a zebra standing in front of another , with his tail blowing in the wind"}], "file_name": "COCO_train2014_000000348315_589333.jpg", "ann_id": 589333, "sent_ids": [35705, 35706], "ref_id": 18725}, {"segmentation": [[410.69, 187.11, 392.46, 214.94, 379.02, 242.77, 368.47, 267.71, 369.43, 279.23, 382.86, 299.38, 434.68, 317.61, 475.94, 305.14, 495.13, 315.69, 498.97, 379.02, 565.18, 350.24, 538.31, 316.65, 498.97, 257.16, 498.01, 237.97, 457.71, 186.15, 444.27, 166.96, 427.0, 166.96]], "area": 17807.091649999995, "iscrowd": 0, "image_id": 521338, "bbox": [368.47, 166.96, 196.71, 212.06], "category_id": 88, "id": 1162793, "split": "val", "sentences": [{"tokens": ["a", "bear", "viewed", "in", "profile", ",", "sitting", "by", "the", "handle", "of", "wooden", "cart"], "raw": "A bear viewed in profile, sitting by the handle of wooden cart.", "sent_id": 35750, "sent": "a bear viewed in profile , sitting by the handle of wooden cart"}, {"tokens": ["a", "teddy", "bear", "in", "front", "of", "another", "teddy", "bear"], "raw": "A teddy bear in front of another teddy bear", "sent_id": 35751, "sent": "a teddy bear in front of another teddy bear"}], "file_name": "COCO_train2014_000000521338_1162793.jpg", "ann_id": 1162793, "sent_ids": [35750, 35751], "ref_id": 18739}, {"segmentation": [[445.64, 152.59, 256.64, 141.85, 123.49, 151.51, 75.17, 175.14, 10.74, 218.09, 1.07, 234.2, 0.0, 439.3, 28.99, 472.59, 588.46, 470.44, 614.23, 438.22, 640.0, 414.6, 638.93, 259.97, 613.15, 218.09, 587.38, 195.54, 542.28, 172.99, 505.77, 154.73, 461.74, 152.59]], "area": 193883.13749999998, "iscrowd": 0, "image_id": 219680, "bbox": [0.0, 141.85, 640.0, 330.74], "category_id": 51, "id": 717167, "split": "val", "sentences": [{"tokens": ["a", "tray", "of", "carrots", "and", "a", "mix", "of", "fruit"], "raw": "a tray of carrots and a mix of fruit", "sent_id": 35770, "sent": "a tray of carrots and a mix of fruit"}, {"tokens": ["the", "bowl", "with", "carrots", "and", "a", "blue", "elephant"], "raw": "The bowl with carrots and a blue elephant", "sent_id": 35771, "sent": "the bowl with carrots and a blue elephant"}], "file_name": "COCO_train2014_000000219680_717167.jpg", "ann_id": 717167, "sent_ids": [35770, 35771], "ref_id": 18744}, {"segmentation": [[290.6, 94.12, 297.8, 94.12, 306.97, 96.74, 313.52, 99.36, 317.45, 101.98, 322.03, 106.56, 325.3, 111.8, 329.23, 120.97, 330.54, 129.48, 331.85, 137.34, 332.51, 147.17, 332.51, 155.68, 333.82, 160.92, 336.44, 164.19, 338.4, 169.43, 339.06, 175.98, 339.06, 180.56, 337.75, 182.53, 340.36, 185.8, 344.29, 189.08, 340.36, 198.9, 333.16, 203.48, 327.27, 207.41, 323.34, 210.69, 316.79, 219.85, 317.45, 225.75, 321.37, 227.06, 323.34, 231.64, 322.03, 239.5, 320.72, 243.43, 321.37, 247.36, 320.72, 253.25, 313.52, 260.45, 310.9, 261.76, 309.59, 265.04, 312.86, 272.24, 314.83, 276.83, 316.14, 285.34, 317.45, 291.23, 319.41, 300.4, 319.41, 308.91, 319.41, 315.46, 316.79, 322.66, 315.48, 326.59, 312.86, 330.52, 310.24, 332.49, 303.69, 324.63, 298.45, 317.43, 298.45, 317.43, 295.18, 322.01, 292.56, 325.28, 287.98, 327.9, 282.74, 329.21, 278.81, 329.21, 276.84, 328.56, 276.19, 323.32, 277.5, 316.77, 284.7, 306.95, 289.29, 299.09, 289.29, 294.51, 287.32, 282.72, 284.7, 274.86, 284.05, 269.62, 284.05, 262.42, 282.74, 260.45, 271.61, 262.42, 267.02, 260.45, 265.06, 255.22, 265.71, 248.01, 267.68, 244.74, 265.71, 241.46, 261.13, 235.57, 260.47, 234.26, 265.71, 227.06, 268.99, 222.47, 268.99, 217.23, 265.71, 212.0, 261.78, 210.03, 255.89, 204.79, 248.69, 200.21, 245.41, 198.24, 242.79, 194.97, 243.45, 187.11, 246.07, 184.49, 248.03, 181.22, 247.38, 175.98, 246.07, 170.09, 246.07, 168.12, 248.69, 165.5, 255.23, 160.26, 257.85, 158.95, 257.85, 136.69, 259.82, 126.21, 265.71, 114.42, 269.64, 108.53, 280.12, 101.98]], "area": 13453.825099999998, "iscrowd": 0, "image_id": 188120, "bbox": [242.79, 94.12, 101.5, 238.37], "category_id": 38, "id": 621120, "split": "val", "sentences": [{"tokens": ["a", "huge", "fish", "kite", "that", "is", "mostly", "blue", "and", "purple"], "raw": "A huge fish kite that is mostly blue and purple.", "sent_id": 35776, "sent": "a huge fish kite that is mostly blue and purple"}, {"tokens": ["a", "giant", "fish", "kite"], "raw": "A giant fish kite.", "sent_id": 35777, "sent": "a giant fish kite"}], "file_name": "COCO_train2014_000000188120_621120.jpg", "ann_id": 621120, "sent_ids": [35776, 35777], "ref_id": 18747}, {"segmentation": [[308.32, 165.0, 334.82, 162.05, 353.47, 158.13, 353.47, 134.57, 364.27, 124.76, 406.48, 120.83, 406.48, 112.98, 417.27, 120.83, 477.15, 125.74, 484.02, 130.64, 477.15, 156.16, 472.24, 181.68, 480.09, 188.56, 483.04, 226.84, 499.72, 228.8, 503.65, 240.58, 503.65, 270.02, 495.8, 288.67, 485.0, 287.69, 480.09, 254.32, 476.17, 255.3, 471.26, 273.95, 452.61, 275.91, 442.79, 271.99, 436.9, 254.32, 428.07, 254.32, 426.11, 263.15, 410.4, 266.1, 407.46, 263.15, 402.55, 284.75, 388.81, 282.78, 380.96, 256.28, 376.05, 272.97, 354.45, 272.97, 349.55, 255.3, 348.56, 236.65, 341.69, 237.63, 338.75, 264.13, 325.01, 264.13, 318.14, 250.39, 321.08, 213.09, 309.3, 211.13, 306.36, 185.61, 302.43, 179.72, 305.38, 169.91]], "area": 23555.627049999992, "iscrowd": 0, "image_id": 507520, "bbox": [302.43, 112.98, 201.22, 175.69], "category_id": 8, "id": 2172063, "split": "val", "sentences": [{"tokens": ["a", "tractor", "with", "a", "pull", "card", "attached", "has", "two", "men", "sitting", "in", "it"], "raw": "A tractor with a pull card attached has two men sitting in it.", "sent_id": 35799, "sent": "a tractor with a pull card attached has two men sitting in it"}, {"tokens": ["fully", "loaded", "tractor", "with", "two", "persons", "on", "it"], "raw": "Fully loaded tractor with two persons on it", "sent_id": 35800, "sent": "fully loaded tractor with two persons on it"}], "file_name": "COCO_train2014_000000507520_2172063.jpg", "ann_id": 2172063, "sent_ids": [35799, 35800], "ref_id": 18755}, {"segmentation": [[318.74, 394.06, 352.61, 426.12, 387.38, 472.63, 394.16, 499.28, 363.0, 529.98, 351.71, 529.08, 336.81, 524.11, 309.71, 506.95, 298.42, 486.63, 292.55, 444.64, 275.39, 429.73, 247.39, 409.41, 264.55, 381.41, 280.36, 376.9, 296.62, 376.45, 311.97, 383.67]], "area": 11243.243500000002, "iscrowd": 0, "image_id": 183392, "bbox": [247.39, 376.45, 146.77, 153.53], "category_id": 58, "id": 1066960, "split": "val", "sentences": [{"tokens": ["the", "top", "right", "sausage", "in", "the", "pile"], "raw": "The top right sausage in the pile.", "sent_id": 35801, "sent": "the top right sausage in the pile"}], "file_name": "COCO_train2014_000000183392_1066960.jpg", "ann_id": 1066960, "sent_ids": [35801], "ref_id": 18756}, {"segmentation": [[114.9, 319.03, 139.6, 280.37, 152.48, 253.53, 158.93, 228.83, 193.29, 206.28, 219.06, 193.39, 235.17, 181.58, 223.36, 166.55, 217.99, 126.82, 231.95, 82.79, 254.5, 72.05, 284.56, 78.49, 311.41, 103.19, 313.56, 140.77, 309.26, 162.25, 302.82, 185.88, 300.67, 193.39, 298.52, 207.35, 317.85, 214.87, 337.18, 247.08, 338.26, 310.44, 350.07, 336.21, 346.85, 336.21, 320.0, 322.25, 277.05, 323.33, 258.79, 339.43, 275.97, 364.13, 311.41, 381.31, 314.63, 424.26, 321.07, 459.7, 323.22, 473.66, 169.66, 474.73, 169.66, 473.66, 171.81, 458.63, 171.81, 426.41, 171.81, 411.38, 170.74, 393.12, 144.97, 373.8, 124.56, 345.88, 115.97, 321.18]], "area": 54691.69875000001, "iscrowd": 0, "image_id": 11774, "bbox": [114.9, 72.05, 235.17, 402.68], "category_id": 1, "id": 441482, "split": "val", "sentences": [{"tokens": ["man", "holding", "two", "plates"], "raw": "man holding two plates", "sent_id": 35842, "sent": "man holding two plates"}, {"tokens": ["short", "guy", "with", "smores"], "raw": "Short guy with smores", "sent_id": 35843, "sent": "short guy with smores"}], "file_name": "COCO_train2014_000000011774_441482.jpg", "ann_id": 441482, "sent_ids": [35842, 35843], "ref_id": 18770}, {"segmentation": [[284.15, 265.47, 288.68, 299.43, 320.38, 334.53, 372.45, 333.4, 403.02, 375.28, 450.57, 350.38, 463.02, 290.38, 452.83, 281.32, 489.06, 263.21, 468.68, 193.02, 463.02, 190.75, 456.23, 196.42, 438.11, 189.62, 412.08, 176.04, 336.23, 204.34, 318.11, 258.68, 318.11, 268.87]], "area": 24742.094649999995, "iscrowd": 0, "image_id": 55873, "bbox": [284.15, 176.04, 204.91, 199.24], "category_id": 53, "id": 1048853, "split": "val", "sentences": [{"tokens": ["a", "circle", "slice", "of", "apple"], "raw": "A circle slice of apple.", "sent_id": 35860, "sent": "a circle slice of apple"}], "file_name": "COCO_train2014_000000055873_1048853.jpg", "ann_id": 1048853, "sent_ids": [35860], "ref_id": 18777}, {"segmentation": [[433.62, 385.08, 424.99, 322.52, 404.49, 254.56, 408.81, 230.83, 394.79, 227.6, 392.63, 212.49, 404.49, 167.19, 429.3, 151.01, 428.22, 119.73, 443.33, 99.24, 462.74, 100.31, 463.82, 106.79, 461.66, 141.3, 465.98, 149.93, 487.55, 156.4, 515.6, 196.31, 532.85, 174.74, 551.19, 192.0, 547.96, 206.02, 505.89, 222.2, 484.31, 196.31, 477.84, 268.58, 480.0, 328.99, 490.79, 371.06, 494.02, 408.81, 480.0, 429.3, 465.98, 416.36, 474.61, 386.16, 456.27, 334.38, 444.4, 289.08, 445.48, 334.38, 447.64, 385.08, 449.8, 404.49, 431.46, 427.15, 421.75, 407.73, 432.54, 392.63]], "area": 20290.007999999994, "iscrowd": 0, "image_id": 335524, "bbox": [392.63, 99.24, 158.56, 330.06], "category_id": 1, "id": 479023, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "awhite", "jacket"], "raw": "A woman in awhite jacket.", "sent_id": 35992, "sent": "a woman in awhite jacket"}, {"tokens": ["a", "woman", "in", "a", "white", "jacket", "on", "skis", "in", "the", "snow", "next", "to", "2", "other", "women"], "raw": "A woman in a white jacket on skis in the snow next to 2 other women", "sent_id": 35993, "sent": "a woman in a white jacket on skis in the snow next to 2 other women"}], "file_name": "COCO_train2014_000000335524_479023.jpg", "ann_id": 479023, "sent_ids": [35992, 35993], "ref_id": 18826}, {"segmentation": [[146.43, 240.29, 156.64, 249.9, 154.84, 260.71, 156.64, 266.71, 153.64, 275.72, 153.04, 285.93, 177.66, 290.73, 186.67, 336.37, 193.87, 356.79, 199.28, 403.03, 198.07, 416.24, 189.07, 417.44, 186.06, 403.03, 184.26, 387.41, 170.45, 338.17, 170.45, 359.79, 178.26, 391.02, 178.86, 438.46, 178.86, 447.47, 178.26, 463.08, 145.83, 458.28, 143.43, 439.06, 137.42, 445.66, 135.02, 452.87, 103.79, 454.07, 103.79, 411.44, 112.2, 372.4, 112.2, 371.8, 111.0, 338.77, 105.6, 366.4, 91.78, 401.83, 85.18, 413.24, 83.98, 431.25, 82.18, 436.66, 76.17, 437.26, 67.76, 425.25, 76.17, 400.63, 84.58, 362.79, 89.38, 350.78, 97.19, 300.94, 109.2, 294.34, 125.41, 285.93, 125.41, 285.33, 121.81, 276.32, 116.41, 262.51, 117.01, 243.29, 124.81, 239.09, 130.82, 234.88, 144.03, 239.09]], "area": 16859.0862, "iscrowd": 0, "image_id": 166985, "bbox": [67.76, 234.88, 131.52, 228.2], "category_id": 1, "id": 493308, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "next", "to", "a", "girl", "on", "a", "surfboard"], "raw": "a man standing next to a girl on a surfboard", "sent_id": 36117, "sent": "a man standing next to a girl on a surfboard"}, {"tokens": ["man", "standing", "in", "water", "without", "shirt"], "raw": "man standing in water without shirt", "sent_id": 36118, "sent": "man standing in water without shirt"}], "file_name": "COCO_train2014_000000166985_493308.jpg", "ann_id": 493308, "sent_ids": [36117, 36118], "ref_id": 18865}, {"segmentation": [[478.0, 613.21, 472.83, 608.92, 469.77, 594.83, 450.17, 595.44, 451.39, 604.63, 447.1, 618.72, 439.14, 617.5, 430.56, 623.62, 425.05, 630.36, 420.14, 640.0, 416.47, 640.0, 339.88, 639.55, 327.63, 607.08, 320.89, 593.6, 309.86, 571.54, 311.09, 562.35, 345.4, 550.1, 354.59, 544.59, 366.23, 529.27, 370.52, 527.43, 375.42, 532.94, 456.29, 531.11, 467.32, 513.95, 461.81, 498.63, 461.19, 482.7, 472.83, 479.64, 478.0, 481.48]], "area": 15126.729099999995, "iscrowd": 0, "image_id": 72118, "bbox": [309.86, 479.64, 168.14, 160.36], "category_id": 56, "id": 2115231, "split": "val", "sentences": [{"tokens": ["cooked", "greens", "on", "a", "blue", "and", "white", "plate"], "raw": "Cooked greens on a blue and white plate.", "sent_id": 36176, "sent": "cooked greens on a blue and white plate"}, {"tokens": ["healthy", "brucoli"], "raw": "HEALTHY BRUCOLI", "sent_id": 36177, "sent": "healthy brucoli"}], "file_name": "COCO_train2014_000000072118_2115231.jpg", "ann_id": 2115231, "sent_ids": [36176, 36177], "ref_id": 18885}, {"segmentation": [[120.62, 264.22, 161.78, 344.63, 280.49, 339.84, 364.73, 298.68, 362.82, 260.39, 385.79, 232.62, 401.11, 277.62, 428.87, 296.76, 448.98, 292.93, 475.78, 372.39, 584.91, 375.26, 576.3, 292.93, 603.1, 267.09, 637.56, 308.25, 630.86, 407.81, 343.67, 417.38, 49.78, 417.38, 12.44, 403.98, 11.49, 317.82, 50.74, 279.53]], "area": 61270.380200000014, "iscrowd": 0, "image_id": 361939, "bbox": [11.49, 232.62, 626.07, 184.76], "category_id": 9, "id": 176858, "split": "val", "sentences": [{"tokens": ["a", "bench", "in", "a", "paddle", "boat", "with", "a", "person", "wearing", "green", "sitting", ",", "and", "a", "person", "holding", "a", "red", "jacket", "sitting"], "raw": "A bench in a paddle boat with a person wearing green sitting, and a person holding a red jacket sitting.", "sent_id": 36210, "sent": "a bench in a paddle boat with a person wearing green sitting , and a person holding a red jacket sitting"}, {"tokens": ["wooden", "boat", "on", "the", "water"], "raw": "wooden boat on the water", "sent_id": 36211, "sent": "wooden boat on the water"}], "file_name": "COCO_train2014_000000361939_176858.jpg", "ann_id": 176858, "sent_ids": [36210, 36211], "ref_id": 18899}, {"segmentation": [[51.82, 249.48, 65.25, 204.38, 83.48, 177.52, 105.55, 152.57, 151.61, 127.62, 183.27, 122.82, 214.94, 127.62, 240.85, 135.3, 259.08, 145.85, 285.95, 170.8, 305.14, 190.95, 314.73, 209.18, 320.49, 235.09, 321.45, 272.51, 316.65, 299.38, 309.93, 328.17, 301.3, 337.76, 300.34, 310.89, 284.03, 275.39, 265.8, 249.48, 251.4, 237.97, 228.37, 227.41, 194.79, 218.78, 169.84, 215.9, 148.73, 219.74, 116.11, 226.45, 82.52, 229.33, 70.05, 238.93, 55.65, 249.48, 47.98, 255.24]], "area": 23257.003649999984, "iscrowd": 0, "image_id": 128475, "bbox": [47.98, 122.82, 273.47, 214.94], "category_id": 60, "id": 1080302, "split": "val", "sentences": [{"tokens": ["the", "middle", "donut"], "raw": "The middle donut.", "sent_id": 36323, "sent": "the middle donut"}, {"tokens": ["second", "sweet", "in", "the", "line"], "raw": "Second sweet in the line", "sent_id": 36324, "sent": "second sweet in the line"}], "file_name": "COCO_train2014_000000128475_1080302.jpg", "ann_id": 1080302, "sent_ids": [36323, 36324], "ref_id": 18945}, {"segmentation": [[189.71, 305.57, 69.84, 268.99, 43.43, 279.15, 2.79, 321.82, 4.82, 431.53, 39.36, 435.6, 61.71, 435.6, 86.09, 472.17, 124.7, 476.23, 169.39, 435.6, 232.38, 325.88, 187.68, 303.53]], "area": 31872.647900000004, "iscrowd": 0, "image_id": 503022, "bbox": [2.79, 268.99, 229.59, 207.24], "category_id": 51, "id": 1903880, "split": "val", "sentences": [{"tokens": ["sliced", "fruit", "in", "a", "blue", "bowl", ",", "bottom", "left", "of", "the", "tray"], "raw": "Sliced fruit in a blue bowl, bottom left of the tray.", "sent_id": 36328, "sent": "sliced fruit in a blue bowl , bottom left of the tray"}, {"tokens": ["a", "blue", "container", "with", "chopped", "fruit", "inside", "it"], "raw": "A blue container with chopped fruit inside it.", "sent_id": 36329, "sent": "a blue container with chopped fruit inside it"}], "file_name": "COCO_train2014_000000503022_1903880.jpg", "ann_id": 1903880, "sent_ids": [36328, 36329], "ref_id": 18947}, {"segmentation": [[549.49, 444.35, 530.71, 395.53, 529.46, 354.23, 525.71, 329.19, 508.18, 281.63, 490.66, 244.08, 460.62, 209.03, 439.34, 195.26, 413.06, 175.24, 378.01, 147.7, 365.49, 133.93, 369.25, 105.14, 374.25, 97.63, 386.77, 100.13, 404.29, 80.11, 403.04, 71.35, 388.02, 71.35, 376.76, 73.85, 362.99, 75.1, 352.98, 76.35, 347.97, 73.85, 347.97, 62.58, 351.72, 53.82, 357.98, 43.81, 357.98, 32.54, 345.47, 30.04, 335.45, 30.04, 324.19, 30.04, 315.42, 38.8, 309.17, 48.82, 305.41, 48.82, 296.65, 55.07, 289.14, 53.82, 279.13, 51.32, 270.36, 48.82, 269.11, 58.83, 269.11, 75.1, 272.87, 77.6, 280.38, 86.37, 291.64, 101.39, 297.9, 105.14, 301.66, 112.65, 294.15, 128.92, 294.15, 143.94, 297.9, 153.96, 297.9, 168.98, 297.9, 192.76, 306.66, 210.28, 302.91, 217.79, 299.15, 226.56, 300.4, 241.58, 304.16, 251.59, 316.68, 257.85, 315.42, 275.37, 317.93, 301.66, 329.19, 312.92, 337.96, 320.43, 346.72, 331.7, 354.23, 341.71, 357.98, 349.22, 357.98, 357.98, 357.98, 373.0, 362.99, 380.51, 374.25, 380.51, 386.77, 379.26, 396.78, 385.52, 408.05, 399.29, 416.81, 410.55, 428.08, 419.31, 444.35, 435.59, 456.87, 436.84, 470.63, 436.84, 481.9, 439.34, 488.16, 438.09, 478.14, 424.32, 465.63, 416.81, 455.61, 403.04, 453.11, 390.53, 453.11, 376.76, 453.11, 374.25, 459.37, 366.74, 466.88, 368.0, 459.37, 383.02, 459.37, 394.28, 460.62, 404.29, 466.88, 413.06, 473.14, 411.8, 486.91, 403.04, 486.91, 389.27, 485.65, 383.02, 490.66, 380.51, 499.42, 391.78, 504.43, 404.29, 511.94, 415.56, 520.7, 429.33, 528.21, 436.84, 533.22, 443.1, 544.48, 443.1, 548.24, 444.35]], "area": 52573.06965, "iscrowd": 0, "image_id": 287302, "bbox": [269.11, 30.04, 280.38, 414.31], "category_id": 24, "id": 594274, "split": "val", "sentences": [{"tokens": ["zebra", "on", "right", "side", ",", "jumping", "over", "log"], "raw": "zebra on right side, jumping over log", "sent_id": 36394, "sent": "zebra on right side , jumping over log"}], "file_name": "COCO_train2014_000000287302_594274.jpg", "ann_id": 594274, "sent_ids": [36394], "ref_id": 18969}, {"segmentation": [[441.03, 254.04, 447.17, 274.43, 456.28, 292.99, 456.61, 292.99, 460.76, 301.78, 460.92, 301.78, 462.42, 308.53, 467.55, 310.85, 524.57, 309.85, 525.23, 302.06, 536.34, 277.7, 540.81, 264.11, 543.63, 252.53, 548.71, 251.37, 550.47, 248.73, 549.01, 246.39, 549.01, 240.69, 558.37, 237.47, 560.71, 228.54, 565.84, 219.29, 568.16, 207.52, 573.13, 202.88, 573.8, 175.2, 575.12, 138.85, 580.59, 135.7, 582.91, 134.05, 580.26, 128.25, 576.12, 128.08, 578.44, 121.62, 585.73, 117.97, 573.8, 113.83, 567.5, 117.14, 566.34, 117.64, 567.67, 107.2, 563.69, 103.72, 562.03, 99.57, 564.52, 94.1, 556.06, 77.86, 551.26, 77.86, 547.61, 77.69, 542.8, 78.19, 538.49, 79.85, 538.49, 83.33, 538.49, 84.49, 538.49, 84.82, 538.66, 84.49, 538.66, 90.24, 537.67, 91.57, 538.16, 87.76, 532.03, 85.77, 530.7, 83.78, 529.54, 75.99, 522.58, 73.34, 511.48, 74.5, 508.0, 81.46, 507.5, 84.28, 510.32, 86.6, 512.14, 89.42, 512.8, 90.91, 512.97, 111.08, 514.79, 101.96, 519.27, 111.25, 518.77, 119.2, 515.95, 117.88, 513.96, 119.04, 512.64, 121.85, 508.66, 122.64, 505.84, 113.02, 498.38, 98.11, 492.58, 98.44, 490.93, 105.73, 495.24, 115.01, 496.06, 116.67, 499.88, 132.49, 496.89, 140.11, 490.26, 147.73, 487.11, 152.04, 484.13, 158.01, 482.14, 163.98, 479.82, 168.62, 477.5, 175.53, 474.19, 179.68, 469.71, 184.15, 453.14, 208.37, 454.96, 217.66, 450.65, 224.62, 450.15, 230.42, 448.0, 240.03, 448.5, 245.83, 448.99, 247.49, 444.52, 247.49, 438.55, 246.99, 434.41, 248.82, 434.24, 251.47, 436.89, 252.96, 439.88, 252.96]], "area": 20342.54399999999, "iscrowd": 0, "image_id": 217978, "bbox": [434.24, 73.34, 151.49, 237.51], "category_id": 64, "id": 26243, "split": "val", "sentences": [{"tokens": ["a", "sand", "vase", "which", "is", "adjacent", "to", "the", "black", "and", "white", "dog"], "raw": "A Sand vase which is adjacent to the black and white dog", "sent_id": 36432, "sent": "a sand vase which is adjacent to the black and white dog"}, {"tokens": ["a", "clay", "plantar", "with", "a", "small", "tree", "or", "bush"], "raw": "A clay plantar with a small tree or bush.", "sent_id": 36433, "sent": "a clay plantar with a small tree or bush"}], "file_name": "COCO_train2014_000000217978_26243.jpg", "ann_id": 26243, "sent_ids": [36432, 36433], "ref_id": 18980}, {"segmentation": [[372.05, 95.71, 372.05, 95.71, 353.39, 108.54, 352.22, 117.87, 356.89, 131.87, 366.22, 147.03, 380.21, 158.69, 372.05, 176.19, 363.88, 197.18, 366.22, 214.68, 358.05, 228.67, 344.06, 243.83, 313.73, 265.99, 302.07, 268.32, 300.9, 285.82, 313.73, 290.48, 318.4, 282.32, 325.4, 276.49, 331.23, 268.32, 359.22, 260.16, 380.21, 241.5, 391.87, 225.17, 411.7, 250.83, 411.7, 254.33, 393.04, 258.99, 376.71, 260.16, 353.39, 269.49, 340.56, 286.99, 346.39, 340.64, 368.55, 390.79, 365.05, 407.11, 352.22, 409.45, 341.72, 414.11, 337.06, 425.77, 337.06, 425.77, 340.56, 440.94, 386.04, 428.11, 422.2, 402.45, 411.7, 387.29, 390.71, 338.3, 382.54, 303.31, 418.7, 304.48, 432.69, 333.64, 452.52, 389.62, 452.52, 423.44, 452.52, 423.44, 453.69, 432.77, 443.19, 452.6, 425.7, 459.6, 408.2, 479.42, 411.7, 499.25, 528.33, 467.76, 528.33, 467.76, 528.33, 454.93, 520.17, 438.6, 512.0, 425.77, 513.17, 416.44, 499.17, 380.29, 466.52, 300.98, 485.18, 270.66, 485.18, 270.66, 485.18, 245.0, 485.18, 245.0, 485.18, 228.67, 475.85, 210.01, 459.52, 179.69, 472.35, 180.85, 487.51, 196.01, 498.01, 210.01, 503.84, 224.01, 500.34, 238.0, 503.84, 242.67, 510.84, 238.0, 513.17, 263.66, 520.17, 258.99, 548.16, 243.83, 535.33, 235.67, 527.16, 224.01, 522.5, 213.51, 522.5, 213.51, 510.84, 197.18, 488.68, 166.86, 488.68, 166.86, 475.85, 163.36, 481.68, 147.03, 481.68, 147.03, 453.69, 136.53, 453.69, 136.53, 424.53, 131.87, 400.04, 140.03, 396.54, 134.2, 398.87, 117.87, 393.04, 110.88, 389.54, 101.55, 375.55, 94.55, 367.38, 99.21, 367.38, 99.21]], "area": 41208.142700000004, "iscrowd": 0, "image_id": 147459, "bbox": [300.9, 94.55, 247.26, 404.7], "category_id": 1, "id": 469802, "split": "val", "sentences": [{"tokens": ["a", "man", "riding", "on", "a", "skateboard"], "raw": "A man riding on a skateboard.", "sent_id": 36444, "sent": "a man riding on a skateboard"}, {"tokens": ["skateboarder", "with", "black", "shoes"], "raw": "skateboarder with black shoes", "sent_id": 36445, "sent": "skateboarder with black shoes"}], "file_name": "COCO_train2014_000000147459_469802.jpg", "ann_id": 469802, "sent_ids": [36444, 36445], "ref_id": 18984}, {"segmentation": [[109.04, 427.08, 123.61, 427.91, 129.02, 423.34, 131.51, 413.76, 136.51, 403.78, 137.76, 390.88, 136.51, 385.88, 137.76, 377.56, 143.58, 358.83, 143.58, 344.68, 151.07, 317.22, 156.9, 290.58, 163.14, 265.2, 164.4, 261.28, 167.3, 263.09, 169.29, 290.26, 167.84, 305.3, 168.39, 314.9, 171.83, 331.38, 171.65, 361.09, 172.73, 375.4, 168.39, 377.94, 171.1, 384.82, 164.4, 416.7, 166.39, 421.95, 182.7, 421.05, 187.59, 412.35, 187.04, 398.95, 189.4, 367.79, 191.93, 330.66, 191.03, 316.17, 193.93, 300.95, 197.55, 284.1, 200.45, 234.11, 200.27, 221.25, 208.78, 221.43, 212.22, 220.16, 213.13, 213.28, 213.67, 208.75, 217.29, 203.13, 215.12, 199.69, 217.11, 196.43, 218.2, 184.47, 218.2, 177.95, 213.85, 167.08, 213.85, 157.48, 209.87, 153.68, 201.17, 145.35, 206.06, 139.19, 199.0, 132.85, 196.46, 131.22, 201.9, 123.97, 201.35, 104.77, 197.37, 88.65, 191.21, 84.12, 181.07, 81.77, 169.83, 87.74, 166.03, 95.89, 166.21, 105.68, 166.39, 110.57, 168.75, 118.18, 169.11, 120.17, 166.57, 123.79, 166.39, 131.22, 151.18, 132.12, 145.02, 137.74, 137.23, 147.7, 134.69, 156.03, 132.7, 175.6, 132.16, 193.35, 134.69, 202.95, 139.4, 210.02, 135.24, 218.35, 135.78, 225.96, 130.35, 237.01, 126.0, 257.84, 125.45, 278.85, 126.72, 293.34, 127.08, 326.31, 121.29, 344.61, 122.01, 379.39, 118.57, 382.1, 118.75, 386.63, 118.21, 389.53, 115.67, 406.01, 108.61, 419.96]], "area": 18703.6817, "iscrowd": 0, "image_id": 577246, "bbox": [108.61, 81.77, 109.59, 346.14], "category_id": 1, "id": 460579, "split": "val", "sentences": [{"tokens": ["the", "woman", "on", "skis", "wearing", "black"], "raw": "The woman on skis wearing black.", "sent_id": 36612, "sent": "the woman on skis wearing black"}, {"tokens": ["a", "person", "in", "black", "with", "red", "shoes"], "raw": "A person in black with red shoes.", "sent_id": 36613, "sent": "a person in black with red shoes"}], "file_name": "COCO_train2014_000000577246_460579.jpg", "ann_id": 460579, "sent_ids": [36612, 36613], "ref_id": 19045}, {"segmentation": [[117.76, 223.03, 145.52, 364.72, 148.4, 402.06, 150.31, 418.34, 0.96, 419.29, 1.91, 2.82, 303.5, 5.7, 315.94, 21.97, 306.37, 48.78, 310.2, 72.71, 334.13, 125.37, 356.15, 182.82, 375.3, 230.69, 378.17, 249.83, 402.11, 272.81, 460.51, 265.15, 501.68, 261.32, 504.55, 276.64, 492.1, 295.79, 469.13, 318.77, 406.89, 341.74, 350.41, 338.87, 299.67, 305.36, 273.82, 272.81, 244.14, 239.3, 230.73, 237.39, 217.33, 238.34, 199.14, 229.73, 187.65, 226.86, 161.8, 223.03, 148.4, 214.41, 133.08, 212.49]], "area": 117396.40129999998, "iscrowd": 0, "image_id": 470085, "bbox": [0.96, 2.82, 503.59, 416.47], "category_id": 22, "id": 582074, "split": "val", "sentences": [{"tokens": ["an", "elephant", "with", "his", "trunk", "touching", "the", "mouth", "of", "the", "other", "elephant"], "raw": "An elephant with his trunk touching the mouth of the other elephant.", "sent_id": 36634, "sent": "an elephant with his trunk touching the mouth of the other elephant"}, {"tokens": ["elephant", "with", "short", "tusks", "and", "trunk", "extended"], "raw": "elephant with short tusks and trunk extended", "sent_id": 36635, "sent": "elephant with short tusks and trunk extended"}], "file_name": "COCO_train2014_000000470085_582074.jpg", "ann_id": 582074, "sent_ids": [36634, 36635], "ref_id": 19055}, {"segmentation": [[239.44, 103.33, 241.43, 95.38, 260.31, 87.43, 272.23, 79.48, 280.18, 78.49, 303.03, 85.44, 349.72, 90.41, 364.63, 90.41, 384.5, 91.41, 400.39, 100.35, 427.22, 106.31, 439.14, 103.33, 461.0, 107.3, 474.91, 115.25, 484.84, 124.19, 494.78, 138.1, 510.68, 132.14, 518.63, 131.15, 527.57, 137.11, 536.51, 149.03, 531.54, 157.97, 517.63, 171.88, 513.66, 176.85, 511.67, 188.77, 514.65, 226.53, 513.66, 263.29, 494.78, 311.97, 472.92, 356.68, 461.99, 373.57, 448.08, 405.36, 444.11, 414.3, 444.11, 433.18, 447.09, 461.0, 423.25, 447.09, 433.18, 406.36, 433.18, 381.52, 440.14, 359.66, 433.18, 355.69, 417.28, 342.77, 420.27, 337.8, 409.34, 336.81, 410.33, 350.72, 419.27, 374.56, 422.25, 396.42, 425.23, 397.41, 424.24, 420.27, 422.25, 443.12, 422.25, 455.04, 419.27, 461.0, 397.41, 461.0, 400.39, 434.17, 391.45, 388.47, 384.5, 364.63, 377.54, 345.75, 371.58, 332.83, 348.73, 332.83, 311.97, 325.88, 312.96, 342.77, 320.91, 366.61, 316.94, 374.56, 308.0, 372.58, 297.07, 346.74, 295.08, 321.91, 289.12, 316.94, 288.13, 336.81, 284.15, 350.72, 276.2, 356.68, 264.28, 350.72, 269.25, 328.86, 267.26, 323.89, 262.29, 327.87, 261.3, 348.73, 261.3, 361.65, 261.3, 383.5, 266.27, 407.35, 265.27, 431.19, 244.41, 426.23, 242.42, 399.4, 242.42, 373.57, 242.42, 338.8, 237.45, 325.88, 235.47, 315.94, 235.47, 300.05, 235.47, 276.2, 230.5, 235.47, 230.5, 204.67, 230.5, 189.77, 232.49, 155.98, 240.44, 136.11, 249.38, 125.19, 253.35, 119.22, 244.41, 101.34]], "area": 74526.05825000002, "iscrowd": 0, "image_id": 179390, "bbox": [230.5, 78.49, 306.01, 382.51], "category_id": 21, "id": 70438, "split": "val", "sentences": [{"tokens": ["a", "cow", ",", "at", "the", "front", "of", "the", "herd"], "raw": "A cow, at the front of the herd.", "sent_id": 36745, "sent": "a cow , at the front of the herd"}, {"tokens": ["a", "cow", "with", "a", "part", "of", "the", "tail", "is", "visible"], "raw": "A cow with a part of the tail is visible", "sent_id": 36746, "sent": "a cow with a part of the tail is visible"}], "file_name": "COCO_train2014_000000179390_70438.jpg", "ann_id": 70438, "sent_ids": [36745, 36746], "ref_id": 19097}, {"segmentation": [[351.6, 199.73, 341.48, 187.77, 323.99, 194.21, 314.79, 199.73, 312.03, 188.69, 316.63, 177.64, 323.07, 159.23, 324.91, 157.39, 325.83, 157.39, 326.75, 158.31, 329.51, 155.55, 333.2, 156.47, 345.16, 167.52, 357.13, 167.52, 371.85, 171.2, 372.77, 172.12, 378.3, 173.96, 381.98, 172.12, 392.1, 172.12, 394.86, 173.04, 391.18, 187.77, 395.78, 199.73, 398.55, 208.94, 398.55, 214.46, 397.63, 219.06, 399.47, 225.51, 394.86, 224.58, 396.71, 234.71, 400.39, 246.68, 404.07, 252.2, 404.99, 261.4, 404.99, 268.77, 404.99, 270.61, 404.99, 272.45, 398.55, 273.37, 399.47, 269.69, 381.06, 222.74, 377.38, 225.51, 365.41, 254.04, 359.89, 275.21, 346.08, 275.21, 352.52, 270.61, 363.57, 226.43, 357.13, 203.42, 349.76, 190.53], [423.4, 174.88, 404.99, 188.69, 404.99, 194.21, 412.35, 218.14, 413.27, 220.9, 431.68, 215.38, 457.45, 241.15, 448.25, 250.36, 449.17, 267.85, 456.53, 270.61, 455.61, 256.8, 457.45, 249.44, 459.29, 270.61, 463.9, 273.37, 467.58, 243.91, 459.29, 226.43, 468.5, 196.97, 468.5, 187.77, 480.46, 220.9, 500.71, 250.36, 509.0, 245.75, 499.79, 236.55, 474.02, 185.01, 470.34, 181.32, 451.93, 174.88, 422.48, 170.28]], "area": 8145.944149999999, "iscrowd": 0, "image_id": 171581, "bbox": [312.03, 155.55, 196.97, 119.66], "category_id": 19, "id": 54899, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "a", "white", "dress", "riding", "a", "brown", "horse"], "raw": "A woman with a white dress riding a brown horse.", "sent_id": 36815, "sent": "a woman with a white dress riding a brown horse"}, {"tokens": ["brown", "horse", "walking", "on", "the", "beach", "carrying", "a", "woman"], "raw": "Brown horse walking on the beach carrying a woman.", "sent_id": 36816, "sent": "brown horse walking on the beach carrying a woman"}], "file_name": "COCO_train2014_000000171581_54899.jpg", "ann_id": 54899, "sent_ids": [36815, 36816], "ref_id": 19125}, {"segmentation": [[282.42, 188.02, 270.6, 180.51, 255.57, 167.62, 250.2, 152.59, 251.28, 141.85, 251.28, 135.41, 254.5, 127.89, 283.49, 101.04, 301.74, 86.01, 308.19, 77.42, 309.26, 55.94, 311.41, 39.84, 311.41, 32.32, 321.07, 24.8, 341.48, 11.92, 369.4, 8.69, 396.24, 25.88, 408.05, 40.91, 423.09, 65.61, 433.83, 95.67, 419.87, 150.44, 411.28, 154.73, 388.72, 155.81, 386.58, 174.06, 386.58, 176.21, 389.8, 176.21, 386.58, 182.65, 377.99, 196.61, 371.54, 208.43, 366.17, 225.61, 356.51, 205.2, 353.29, 195.54, 348.99, 179.43, 336.11, 175.14, 312.48, 174.06, 306.04, 176.21, 294.23, 181.58, 280.27, 182.65], [150.34, 468.29, 171.81, 450.04, 216.91, 423.19, 219.06, 421.04, 326.44, 364.13, 308.19, 399.57, 300.67, 422.12, 294.23, 448.96, 281.34, 468.29]], "area": 29709.923100000004, "iscrowd": 0, "image_id": 100667, "bbox": [150.34, 8.69, 283.49, 459.6], "category_id": 1, "id": 460001, "split": "val", "sentences": [{"tokens": ["the", "centre", "parson", "eating", "banana", "warring", "yellow", "t", "-", "shirt"], "raw": "the centre parson eating banana warring yellow t-shirt", "sent_id": 36821, "sent": "the centre parson eating banana warring yellow t - shirt"}, {"tokens": ["man", "in", "the", "middle", "of", "two", "other", "men"], "raw": "Man in the middle of two other men.", "sent_id": 36822, "sent": "man in the middle of two other men"}], "file_name": "COCO_train2014_000000100667_460001.jpg", "ann_id": 460001, "sent_ids": [36821, 36822], "ref_id": 19128}, {"segmentation": [[375.88, 297.69, 398.37, 287.77, 408.3, 251.39, 415.57, 231.55, 427.48, 207.73, 427.48, 193.84, 426.15, 180.62, 415.57, 182.6, 412.26, 167.39, 404.99, 146.88, 404.99, 134.32, 404.33, 123.07, 415.57, 134.32, 432.11, 156.14, 428.8, 150.19, 421.52, 132.99, 421.52, 122.41, 426.82, 117.78, 428.8, 117.12, 432.11, 117.12, 437.4, 124.39, 442.69, 129.02, 447.32, 145.56, 447.32, 147.54, 444.67, 150.19, 446.66, 150.85, 449.3, 150.85, 461.21, 153.5, 461.21, 163.42, 460.55, 170.69, 460.55, 190.54, 460.55, 201.12, 461.21, 204.43, 462.53, 209.06, 448.64, 207.73, 455.92, 213.03, 464.52, 222.95, 458.56, 243.45, 467.82, 261.97, 471.79, 299.67, 470.47, 318.86, 453.93, 318.86, 445.34, 311.58, 456.58, 300.34, 451.95, 273.88, 447.98, 258.67, 441.37, 250.73, 435.41, 244.11, 424.83, 247.42, 423.51, 261.97, 418.88, 271.23, 418.88, 279.83, 411.6, 293.72, 406.31, 299.67, 405.65, 306.29, 405.65, 312.9, 404.33, 314.89, 396.39, 314.89, 383.16, 308.27, 372.58, 303.64]], "area": 7649.003300000004, "iscrowd": 0, "image_id": 199331, "bbox": [372.58, 117.12, 99.21, 201.74], "category_id": 1, "id": 451845, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "shirt", "and", "blue", "shorts", "holding", "a", "green", "cone"], "raw": "A man in a blue shirt and blue shorts holding a green cone", "sent_id": 36823, "sent": "a man in a blue shirt and blue shorts holding a green cone"}, {"tokens": ["the", "guy", "in", "light", "blue", "dress"], "raw": "the guy in light blue dress", "sent_id": 36824, "sent": "the guy in light blue dress"}], "file_name": "COCO_train2014_000000199331_451845.jpg", "ann_id": 451845, "sent_ids": [36823, 36824], "ref_id": 19129}, {"segmentation": [[476.67, 435.54, 446.94, 368.15, 434.05, 339.41, 409.28, 329.5, 394.41, 329.5, 388.47, 320.59, 392.43, 305.72, 400.36, 295.81, 403.33, 278.96, 403.33, 278.96, 395.41, 275.0, 395.41, 251.22, 388.47, 237.34, 363.69, 229.41, 349.82, 234.37, 337.93, 243.29, 330.0, 258.15, 330.0, 277.97, 331.98, 303.74, 338.92, 308.69, 338.92, 320.59, 301.26, 332.48, 284.41, 346.35, 272.52, 370.14, 259.64, 413.74, 250.72, 433.56]], "area": 24924.973500000007, "iscrowd": 0, "image_id": 242090, "bbox": [250.72, 229.41, 225.95, 206.13], "category_id": 1, "id": 1240781, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "striped", "shirt", "is", "standing", "oppsite", "and", "between", "two", "men"], "raw": "A man in a striped shirt is standing oppsite and between two men", "sent_id": 36969, "sent": "a man in a striped shirt is standing oppsite and between two men"}, {"tokens": ["a", "man", "in", "a", "stripped", "shirt", "looks", "angrily", "at", "the", "camera"], "raw": "A man in a stripped shirt looks angrily at the camera.", "sent_id": 36970, "sent": "a man in a stripped shirt looks angrily at the camera"}], "file_name": "COCO_train2014_000000242090_1240781.jpg", "ann_id": 1240781, "sent_ids": [36969, 36970], "ref_id": 19188}, {"segmentation": [[1.08, 144.54, 20.49, 148.85, 35.6, 146.7, 59.33, 144.54, 100.31, 139.15, 125.12, 138.07, 138.07, 138.07, 167.19, 140.22, 184.45, 138.07, 204.94, 135.91, 221.12, 134.83, 239.46, 133.75, 250.25, 132.67, 269.66, 146.7, 292.31, 159.64, 303.1, 160.72, 307.42, 304.18, 6.47, 362.43]], "area": 57834.81855000001, "iscrowd": 0, "image_id": 71099, "bbox": [1.08, 132.67, 306.34, 229.76], "category_id": 78, "id": 1119398, "split": "val", "sentences": [{"tokens": ["a", "large", "microwave", "with", "a", "container", "in", "it", ",", "it", "is", "sitting", "next", "to", "a", "samller", "microwave", "which", "is", "sitting", "next", "to", "a", "typewriter"], "raw": "A large microwave with a container in it, it is sitting next to a samller microwave which is sitting next to a typewriter.", "sent_id": 36999, "sent": "a large microwave with a container in it , it is sitting next to a samller microwave which is sitting next to a typewriter"}, {"tokens": ["the", "microwave", "on", "the", "left"], "raw": "the microwave on the left", "sent_id": 37000, "sent": "the microwave on the left"}], "file_name": "COCO_train2014_000000071099_1119398.jpg", "ann_id": 1119398, "sent_ids": [36999, 37000], "ref_id": 19197}, {"segmentation": [[0.0, 310.44, 52.36, 290.49, 110.96, 264.31, 135.9, 248.1, 120.94, 270.55, 120.94, 288.0, 82.29, 300.47, 62.34, 311.69, 54.86, 314.18, 67.32, 351.58, 67.32, 370.29, 66.08, 390.23, 47.38, 387.74, 3.74, 374.03, 1.25, 356.57, 12.47, 360.31, 28.68, 370.29, 48.62, 372.78, 56.1, 372.78, 52.36, 357.82, 48.62, 334.13, 39.9, 320.42, 17.45, 332.88]], "area": 4770.5238500000005, "iscrowd": 0, "image_id": 149921, "bbox": [0.0, 248.1, 135.9, 142.13], "category_id": 15, "id": 2062059, "split": "val", "sentences": [{"tokens": ["an", "empty", "picnic", "table", "bench"], "raw": "an empty picnic table bench", "sent_id": 37088, "sent": "an empty picnic table bench"}, {"tokens": ["empty", "bench"], "raw": "empty bench", "sent_id": 37089, "sent": "empty bench"}], "file_name": "COCO_train2014_000000149921_2062059.jpg", "ann_id": 2062059, "sent_ids": [37088, 37089], "ref_id": 19239}, {"segmentation": [[0.96, 297.0, 2.87, 254.87, 0.96, 226.15, 4.79, 194.55, 0.0, 173.49, 0.96, 124.65, 0.0, 116.99, 13.4, 129.44, 18.19, 145.72, 39.26, 165.83, 62.24, 195.51, 53.62, 272.11, 50.75, 287.43, 63.19, 341.05, 64.15, 369.77, 51.7, 383.18, 43.09, 383.18, 42.13, 364.03, 36.38, 342.01, 30.64, 319.98, 23.94, 298.92, 22.02, 318.07, 26.81, 338.18, 22.98, 364.03, 11.49, 368.81, 0.0, 375.52, 9.57, 350.62, 7.66, 334.35, 2.87, 315.2]], "area": 11324.612200000001, "iscrowd": 0, "image_id": 174749, "bbox": [0.0, 116.99, 64.15, 266.19], "category_id": 1, "id": 495747, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "shirt", "and", "black", "watch", "standing", "at", "the", "back", "left", "of", "a", "commercial", "kitchen"], "raw": "A man wearing a black shirt and black watch standing at the back left of a commercial kitchen", "sent_id": 37118, "sent": "a man wearing a black shirt and black watch standing at the back left of a commercial kitchen"}, {"tokens": ["a", "man", "all", "in", "black"], "raw": "A man all in black.", "sent_id": 37119, "sent": "a man all in black"}], "file_name": "COCO_train2014_000000174749_495747.jpg", "ann_id": 495747, "sent_ids": [37118, 37119], "ref_id": 19247}, {"segmentation": [[163.43, 545.59, 161.1, 502.23, 153.36, 446.49, 138.65, 391.52, 138.65, 367.52, 113.1, 332.68, 102.27, 312.55, 115.43, 290.1, 167.3, 272.29, 179.69, 245.2, 191.3, 241.33, 202.91, 246.75, 216.07, 252.94, 208.33, 272.29, 206.78, 275.39, 218.4, 287.78, 235.43, 314.88, 246.27, 351.26, 244.72, 379.13, 249.36, 400.04, 245.49, 415.52, 226.91, 401.59, 225.36, 353.59, 213.75, 355.13, 212.2, 360.55, 222.27, 402.36, 226.91, 426.36, 223.04, 440.29, 236.98, 512.29, 243.17, 547.13, 226.91, 549.46, 207.56, 546.36, 196.72, 506.88, 188.2, 434.1, 187.43, 464.29, 184.33, 534.75, 171.94, 544.81]], "area": 24867.859549999997, "iscrowd": 0, "image_id": 116832, "bbox": [102.27, 241.33, 147.09, 308.13], "category_id": 1, "id": 498039, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "baby", "blue", "shirt", "standing", "next", "to", "a", "yellow", "fire", "hydrant"], "raw": "A man wearing a baby blue shirt standing next to a yellow fire hydrant.", "sent_id": 37162, "sent": "a man wearing a baby blue shirt standing next to a yellow fire hydrant"}, {"tokens": ["a", "bald", "man"], "raw": "a bald man", "sent_id": 37163, "sent": "a bald man"}], "file_name": "COCO_train2014_000000116832_498039.jpg", "ann_id": 498039, "sent_ids": [37162, 37163], "ref_id": 19263}, {"segmentation": [[275.21, 339.29, 290.11, 358.9, 284.62, 369.09, 275.21, 380.07, 278.35, 404.39, 274.43, 414.58, 254.82, 389.49, 252.47, 377.72, 266.59, 360.47, 269.72, 356.55, 277.57, 342.43, 264.23, 331.45, 256.39, 335.37, 250.9, 329.88, 246.98, 316.55, 246.19, 299.29, 243.06, 264.0, 246.98, 248.31, 252.47, 238.9, 262.66, 234.2, 250.12, 220.08, 255.61, 198.9, 265.8, 189.49, 284.62, 185.57, 297.17, 193.41, 300.31, 215.37, 299.53, 232.63, 298.74, 234.2, 316.0, 238.12, 325.41, 254.59, 321.49, 276.55, 300.31, 314.41, 294.82, 326.18, 263.45, 283.04, 253.25, 282.26, 255.61, 309.71, 272.08, 334.81]], "area": 8548.226099999998, "iscrowd": 0, "image_id": 142825, "bbox": [243.06, 185.57, 82.35, 229.01], "category_id": 1, "id": 2156379, "split": "val", "sentences": [{"tokens": ["a", "small", "child", "wearing", "blue", "and", "black", "socks"], "raw": "A small child wearing blue and black socks.", "sent_id": 37164, "sent": "a small child wearing blue and black socks"}, {"tokens": ["a", "boy", "being", "held", "by", "a", "man", "in", "a", "forest", "next", "to", "an", "elephant"], "raw": "A boy being held by a man in a forest next to an elephant", "sent_id": 37165, "sent": "a boy being held by a man in a forest next to an elephant"}], "file_name": "COCO_train2014_000000142825_2156379.jpg", "ann_id": 2156379, "sent_ids": [37164, 37165], "ref_id": 19264}, {"segmentation": [[507.81, 121.81, 511.8, 111.83, 506.81, 99.86, 492.84, 79.91, 471.89, 65.94, 455.93, 51.97, 433.98, 29.03, 419.02, 15.06, 402.06, 2.09, 499.83, 3.09, 537.74, 50.98, 550.71, 77.91, 568.67, 92.88, 575.65, 101.86, 579.64, 122.81, 563.68, 127.8, 547.71, 131.79, 528.76, 127.8, 520.78, 131.79, 506.81, 121.81], [572.66, 150.74, 585.63, 130.79, 598.59, 112.83, 602.59, 99.86, 605.58, 82.9, 595.6, 61.95, 584.63, 36.01, 575.65, 21.05, 561.68, 5.08, 556.69, 0.1, 628.52, 3.09, 638.5, 38.01, 638.5, 145.75, 603.58, 154.73, 578.64, 157.73]], "area": 16946.97425, "iscrowd": 0, "image_id": 347655, "bbox": [402.06, 0.1, 236.44, 157.63], "category_id": 1, "id": 503574, "split": "val", "sentences": [{"tokens": ["the", "bare", "legs", "and", "feet"], "raw": "The bare legs and feet.", "sent_id": 37166, "sent": "the bare legs and feet"}, {"tokens": ["a", "person", "'", "s", "sandy", "feet"], "raw": "a person's sandy feet", "sent_id": 37167, "sent": "a person ' s sandy feet"}], "file_name": "COCO_train2014_000000347655_503574.jpg", "ann_id": 503574, "sent_ids": [37166, 37167], "ref_id": 19265}, {"segmentation": [[40.9, 245.33, 81.79, 230.26, 151.75, 229.18, 238.92, 243.17, 331.48, 272.23, 368.07, 287.3, 349.78, 365.87, 288.43, 406.76, 288.43, 437.97, 258.3, 453.04, 201.26, 428.29, 159.28, 426.13, 125.92, 449.81, 26.91, 249.63, 40.9, 245.33], [104.39, 228.11, 121.61, 180.75, 195.87, 135.55, 346.55, 98.96, 333.63, 151.7, 319.64, 215.19, 102.24, 230.26]], "area": 70650.25170000001, "iscrowd": 0, "image_id": 69047, "bbox": [26.91, 98.96, 341.16, 354.08], "category_id": 54, "id": 310201, "split": "val", "sentences": [{"tokens": ["muffaleta", "with", "bites", "missing"], "raw": "muffaleta with bites missing", "sent_id": 37184, "sent": "muffaleta with bites missing"}, {"tokens": ["a", "quarter", "of", "a", "sandwich", "with", "a", "bite", "taken", "out"], "raw": "A quarter of a sandwich with a bite taken out.", "sent_id": 37185, "sent": "a quarter of a sandwich with a bite taken out"}], "file_name": "COCO_train2014_000000069047_310201.jpg", "ann_id": 310201, "sent_ids": [37184, 37185], "ref_id": 19272}, {"segmentation": [[262.1, 409.85, 275.05, 425.22, 291.22, 426.84, 274.24, 400.95, 331.67, 396.91, 334.09, 384.77, 274.24, 389.63, 271.0, 376.69, 317.11, 354.85, 331.67, 348.38, 334.9, 324.92, 351.89, 315.21, 357.55, 289.33, 335.71, 288.52, 315.49, 290.95, 303.36, 294.99, 292.03, 303.89, 285.56, 320.87, 279.09, 344.33, 278.28, 356.46, 270.19, 373.45, 255.63, 386.39, 262.1, 403.38], [177.98, 349.99, 200.63, 334.63, 224.09, 323.3, 218.43, 353.23, 213.57, 372.64], [208.72, 379.92, 198.2, 378.3, 194.16, 383.16, 196.59, 388.82, 201.44, 387.2]], "area": 6581.910000000005, "iscrowd": 0, "image_id": 224734, "bbox": [177.98, 288.52, 179.57, 138.32], "category_id": 62, "id": 380490, "split": "val", "sentences": [{"tokens": ["chair", "under", "the", "man", "in", "blue", "shirt"], "raw": "chair under the man in blue shirt", "sent_id": 37223, "sent": "chair under the man in blue shirt"}, {"tokens": ["the", "chair", "is", "holding", "the", "african", "american", "man", "as", "he", "rests"], "raw": "The chair is holding the African American man as he rests.", "sent_id": 37224, "sent": "the chair is holding the african american man as he rests"}], "file_name": "COCO_train2014_000000224734_380490.jpg", "ann_id": 380490, "sent_ids": [37223, 37224], "ref_id": 19285}, {"segmentation": [[79.64, 196.71, 14.39, 201.51, 0.96, 189.99, 0.0, 19.19, 25.91, 7.68, 122.82, 0.96, 196.71, 1.92, 261.96, 0.96, 260.04, 32.62, 244.69, 23.99, 226.45, 26.87, 217.82, 35.5, 200.55, 36.46, 179.44, 37.42, 166.96, 40.3, 161.2, 48.94, 161.2, 63.33, 133.38, 58.53, 102.67, 65.25, 100.75, 81.56, 101.71, 104.59, 81.56, 108.43, 69.09, 117.07, 68.13, 142.97, 71.01, 171.76, 73.89, 181.36]], "area": 23372.62610000001, "iscrowd": 0, "image_id": 293966, "bbox": [0.0, 0.96, 261.96, 200.55], "category_id": 8, "id": 1367709, "split": "val", "sentences": [{"tokens": ["the", "grey", "tarp", "in", "the", "back", "left"], "raw": "The grey tarp in the back left.", "sent_id": 37281, "sent": "the grey tarp in the back left"}, {"tokens": ["the", "gray", "box", "that", "is", "on", "the", "other", "side", "of", "the", "road", "behind", "the", "truck"], "raw": "The gray box that is on the other side of the road behind the truck.", "sent_id": 37282, "sent": "the gray box that is on the other side of the road behind the truck"}], "file_name": "COCO_train2014_000000293966_1367709.jpg", "ann_id": 1367709, "sent_ids": [37281, 37282], "ref_id": 19309}, {"segmentation": [[402.34, 140.22, 379.69, 104.63, 372.13, 79.82, 400.18, 47.46, 407.73, 46.38, 440.09, 58.25, 454.11, 73.35, 460.58, 93.84, 461.66, 125.12, 462.74, 140.22, 481.08, 152.09, 483.24, 152.09, 540.4, 192.0, 555.51, 231.91, 566.29, 303.1, 525.3, 320.36, 535.01, 382.92, 510.2, 467.06, 354.88, 472.45, 361.35, 406.65, 366.74, 393.71, 371.06, 340.85, 371.06, 323.6, 363.51, 291.24, 347.33, 252.4, 346.25, 239.46, 378.61, 199.55, 385.08, 185.53]], "area": 61090.31834999999, "iscrowd": 0, "image_id": 11774, "bbox": [346.25, 46.38, 220.04, 426.07], "category_id": 1, "id": 475333, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "shirt"], "raw": "A man in a red shirt.", "sent_id": 37353, "sent": "a man in a red shirt"}, {"tokens": ["a", "man", "in", "a", "red", "shirt", "eating", "sweets", "with", "his", "friend"], "raw": "A man in a red shirt eating sweets with his friend", "sent_id": 37354, "sent": "a man in a red shirt eating sweets with his friend"}], "file_name": "COCO_train2014_000000011774_475333.jpg", "ann_id": 475333, "sent_ids": [37353, 37354], "ref_id": 19340}, {"segmentation": [[204.38, 85.4, 255.24, 107.47, 293.62, 131.46, 322.41, 160.24, 356.95, 188.07, 367.51, 216.86, 382.86, 237.97, 400.13, 257.16, 418.36, 241.81, 416.44, 270.59, 417.4, 280.19, 429.88, 290.74, 452.91, 267.71, 467.3, 282.11, 469.22, 297.46, 443.31, 311.85, 430.84, 316.65, 436.6, 333.92, 443.31, 340.64, 430.84, 368.47, 427.0, 377.1, 379.02, 381.9, 346.4, 380.94, 350.24, 375.18, 346.4, 357.91, 341.6, 323.37, 332.96, 294.58, 321.45, 277.31, 296.5, 251.4, 249.48, 213.02, 221.66, 198.63, 189.99, 181.36, 161.2, 178.48, 137.22, 178.48, 125.7, 184.23, 123.78, 194.79, 130.5, 229.33, 130.5, 247.56, 122.82, 275.39, 117.07, 277.31, 107.47, 287.87, 100.75, 285.95, 98.83, 306.1, 98.83, 315.69, 95.0, 332.0, 89.24, 341.6, 80.6, 363.67, 50.86, 364.63, 35.5, 361.75, 35.5, 336.8, 33.58, 335.84, 23.99, 335.84, 10.56, 349.28, 5.76, 365.59, 1.92, 363.67, 2.88, 95.96, 29.75, 70.05, 36.46, 58.53, 64.29, 50.86, 95.96, 58.53, 132.42, 62.37, 150.65, 70.05, 191.91, 81.56, 204.38, 87.32]], "area": 72337.41765, "iscrowd": 0, "image_id": 473348, "bbox": [1.92, 50.86, 467.3, 331.04], "category_id": 25, "id": 597617, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "leaning", "down", "to", "eat"], "raw": "A giraffe leaning down to eat", "sent_id": 37369, "sent": "a giraffe leaning down to eat"}, {"tokens": ["a", "giraffe", "drinking", "water"], "raw": "A giraffe drinking water", "sent_id": 37370, "sent": "a giraffe drinking water"}], "file_name": "COCO_train2014_000000473348_597617.jpg", "ann_id": 597617, "sent_ids": [37369, 37370], "ref_id": 19347}, {"segmentation": [[10.65, 185.98, 104.42, 176.11, 173.51, 174.46, 198.19, 193.38, 213.0, 198.32, 231.92, 198.32, 245.08, 203.25, 246.72, 204.07, 265.64, 223.81, 267.29, 241.09, 268.11, 264.94, 268.11, 273.99, 257.41, 283.04, 263.17, 291.26, 263.17, 302.78, 254.95, 315.94, 237.67, 322.52, 225.34, 319.23, 209.71, 311.83, 185.85, 308.54, 155.42, 307.71, 106.07, 315.12, 68.23, 316.76, 48.49, 313.47, 43.55, 318.41, 43.55, 343.91, 12.29, 351.31, 0.78, 325.81, 0.0, 184.33, 10.65, 181.86]], "area": 35273.43980000001, "iscrowd": 0, "image_id": 371114, "bbox": [0.0, 174.46, 268.11, 176.85], "category_id": 3, "id": 2039801, "split": "val", "sentences": [{"tokens": ["the", "light", "streak"], "raw": "The light streak.", "sent_id": 37417, "sent": "the light streak"}, {"tokens": ["light", "streaks", "on", "left"], "raw": "LIGHT STREAKS ON LEFT", "sent_id": 37418, "sent": "light streaks on left"}], "file_name": "COCO_train2014_000000371114_2039801.jpg", "ann_id": 2039801, "sent_ids": [37417, 37418], "ref_id": 19365}, {"segmentation": [[142.62, 309.1, 223.43, 292.93, 280.48, 282.47, 311.86, 271.07, 326.12, 268.21, 369.85, 271.07, 381.26, 273.92, 493.39, 284.35, 503.85, 278.64, 543.79, 222.55, 564.7, 222.55, 578.96, 288.15, 589.42, 296.71, 610.34, 299.56, 609.39, 313.82, 544.74, 316.68, 474.38, 323.33, 470.57, 344.25, 474.38, 355.66, 448.71, 356.61, 459.17, 331.89, 456.31, 323.33, 426.84, 322.38, 429.69, 333.79, 427.79, 347.1, 424.94, 353.76, 414.48, 354.71, 410.68, 350.9, 408.77, 341.4, 411.63, 329.04, 400.22, 315.72, 370.74, 318.58, 367.89, 334.74, 373.6, 337.59, 358.38, 340.45, 355.53, 338.54, 355.53, 332.84, 346.02, 332.84, 343.17, 339.49, 336.51, 337.59, 335.56, 337.59, 332.71, 333.79, 335.56, 318.58, 291.83, 320.48, 278.52, 335.69, 280.42, 349.95, 278.52, 357.56, 271.86, 357.56, 267.11, 356.61, 266.16, 353.76, 265.21, 349.95, 266.16, 346.15, 267.11, 341.4, 271.86, 337.59, 274.71, 333.79, 273.76, 317.63, 203.4, 318.58, 201.5, 327.13, 204.36, 340.45, 194.85, 341.4, 189.14, 335.69, 191.04, 332.84, 196.75, 329.99, 192.0, 325.23, 194.85, 320.48, 195.8, 318.58, 164.42, 314.77, 143.51, 309.07]], "area": 21406.527600000005, "iscrowd": 0, "image_id": 549499, "bbox": [142.62, 222.55, 467.72, 135.01], "category_id": 5, "id": 160298, "split": "val", "sentences": [{"tokens": ["the", "plane", "that", "is", "in", "plain", "view"], "raw": "The plane that is in plain view", "sent_id": 37471, "sent": "the plane that is in plain view"}, {"tokens": ["a", "grey", "jet", "in", "front", "of", "another", "jet"], "raw": "a grey jet in front of another jet", "sent_id": 37472, "sent": "a grey jet in front of another jet"}], "file_name": "COCO_train2014_000000549499_160298.jpg", "ann_id": 160298, "sent_ids": [37471, 37472], "ref_id": 19386}, {"segmentation": [[251.82, 367.59, 292.34, 363.16, 296.77, 358.09, 292.34, 354.29, 282.84, 350.5, 275.25, 348.6, 272.08, 344.16, 268.28, 328.97, 265.12, 318.84, 264.48, 306.81, 261.95, 299.22, 261.95, 288.45, 261.95, 284.02, 260.05, 277.69, 258.79, 270.73, 256.89, 268.2, 254.99, 261.23, 252.46, 252.37, 252.46, 251.1, 246.76, 240.97, 242.33, 235.28, 241.06, 234.01, 239.79, 232.11, 241.69, 217.55, 246.76, 204.26, 247.39, 196.03, 248.66, 192.86, 253.09, 179.57, 258.15, 174.5, 263.22, 175.14, 267.65, 181.47, 270.81, 185.26, 282.84, 202.36, 288.54, 214.39, 291.71, 218.82, 294.87, 223.88, 298.67, 229.58, 305.63, 227.05, 309.43, 224.51, 310.06, 221.35, 305.63, 218.18, 303.73, 216.29, 298.04, 202.36, 292.34, 192.23, 285.37, 182.1, 280.94, 174.5, 278.41, 167.54, 275.25, 161.84, 270.81, 152.98, 266.38, 146.01, 261.32, 140.95, 258.15, 137.78, 254.99, 136.52, 251.82, 135.89, 254.35, 130.19, 254.35, 113.1, 252.46, 109.93, 248.02, 106.13, 242.96, 105.5, 236.63, 106.13, 232.83, 107.4, 230.93, 109.3, 230.93, 112.46, 231.56, 114.99, 229.03, 112.46, 226.5, 122.59, 226.5, 128.92, 225.23, 132.72, 215.74, 134.62, 210.04, 139.68, 205.61, 146.01, 204.98, 151.08, 200.54, 163.11, 191.68, 183.37, 177.75, 211.85, 178.39, 216.29, 180.92, 228.31, 181.55, 230.85, 188.52, 231.48, 198.01, 236.54, 201.18, 237.18, 207.51, 243.51, 208.14, 245.41, 214.47, 255.54, 217.0, 259.97, 219.54, 266.3, 218.9, 270.73, 218.27, 280.22, 217.64, 285.29, 214.47, 291.62, 213.2, 298.58, 207.51, 307.45, 204.98, 311.88, 206.24, 314.41, 218.9, 313.78, 220.8, 313.78, 223.97, 313.78, 232.83, 313.14, 237.89, 311.88, 236.63, 305.55, 229.66, 299.22, 227.77, 297.32, 225.87, 292.25, 226.5, 284.66, 234.73, 277.06, 238.53, 285.29, 238.53, 292.25, 243.59, 309.98, 244.23, 316.31, 248.66, 325.81, 250.56, 329.6, 254.35, 338.47, 254.35, 342.27, 254.35, 349.23, 251.82, 357.46, 249.92, 361.89, 249.29, 366.32, 254.99, 366.32]], "area": 12408.816699999998, "iscrowd": 0, "image_id": 199743, "bbox": [177.75, 105.5, 132.31, 262.09], "category_id": 1, "id": 195937, "split": "val", "sentences": [{"tokens": ["man", "wearing", "blue", "t", "-", "shirt", "riding", "bike", "on", "the", "sidewalk", "and", "waiting", "for", "traffic"], "raw": "Man wearing blue t-shirt riding bike on the sidewalk and waiting for traffic", "sent_id": 37496, "sent": "man wearing blue t - shirt riding bike on the sidewalk and waiting for traffic"}, {"tokens": ["the", "man", "on", "the", "bike"], "raw": "The man on the bike", "sent_id": 37497, "sent": "the man on the bike"}], "file_name": "COCO_train2014_000000199743_195937.jpg", "ann_id": 195937, "sent_ids": [37496, 37497], "ref_id": 19395}, {"segmentation": [[87.34, 376.47, 114.45, 326.78, 128.0, 298.16, 143.06, 274.07, 155.11, 249.98, 200.28, 224.38, 227.39, 210.82, 239.44, 206.31, 225.88, 183.72, 219.86, 161.13, 216.85, 132.52, 224.38, 111.44, 231.91, 84.33, 251.48, 66.26, 275.58, 64.75, 295.15, 64.75, 319.25, 73.79, 323.76, 81.32, 323.76, 103.91, 328.28, 132.52, 329.79, 170.16, 322.26, 182.21, 322.26, 209.32, 338.82, 216.85, 394.54, 228.89, 418.64, 233.41, 420.14, 234.92, 456.28, 251.48, 492.42, 222.87, 510.49, 224.38, 522.54, 239.44, 499.95, 283.11, 489.41, 311.72, 492.42, 344.85, 493.93, 390.02, 448.75, 444.24, 436.71, 448.75, 447.25, 477.36, 451.76, 495.44, 429.18, 519.53, 424.66, 521.04, 424.66, 563.2, 426.16, 605.36, 427.67, 640.0, 158.12, 640.0, 162.64, 569.22, 158.12, 516.52, 149.08, 489.41, 158.12, 471.34, 158.12, 457.79, 143.06, 460.8, 106.92, 466.82, 96.38, 456.28, 78.31, 414.12, 79.81, 400.56]], "area": 152214.32165, "iscrowd": 0, "image_id": 486014, "bbox": [78.31, 64.75, 444.23, 575.25], "category_id": 1, "id": 439579, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "purple", "baseball", "jersey", "holding", "a", "baseball", "bat"], "raw": "A man in a purple baseball jersey holding a baseball bat", "sent_id": 37506, "sent": "a man in a purple baseball jersey holding a baseball bat"}, {"tokens": ["the", "player", "with", "the", "number", "2"], "raw": "The player with the number 2.", "sent_id": 37507, "sent": "the player with the number 2"}], "file_name": "COCO_train2014_000000486014_439579.jpg", "ann_id": 439579, "sent_ids": [37506, 37507], "ref_id": 19398}, {"segmentation": [[432.06, 12.1, 413.11, 20.08, 393.17, 43.01, 389.19, 53.97, 390.68, 67.43, 385.7, 74.91, 376.23, 85.88, 367.75, 92.36, 364.26, 94.85, 361.27, 103.82, 358.28, 103.32, 352.3, 103.32, 347.81, 105.32, 340.83, 108.81, 340.83, 118.78, 340.83, 121.77, 344.82, 128.74, 341.83, 134.23, 342.33, 137.22, 341.83, 141.71, 338.77, 164.89, 342.26, 170.37, 348.24, 179.85, 349.23, 181.34, 350.23, 192.31, 351.73, 201.28, 350.23, 204.77, 364.0, 209.55, 378.78, 206.27, 381.24, 193.95, 388.63, 179.17, 393.56, 170.14, 398.48, 163.57, 400.12, 155.36, 400.94, 147.15, 413.26, 140.58, 415.72, 129.91, 425.58, 122.52, 423.94, 117.59, 420.65, 115.95, 424.76, 104.46, 440.36, 109.38, 449.39, 113.49, 446.93, 120.88, 440.03, 132.63, 438.6, 134.77, 438.6, 141.56, 436.1, 151.57, 421.44, 164.8, 423.23, 165.87, 424.3, 172.66, 424.66, 177.3, 425.73, 179.09, 436.45, 177.3, 446.1, 176.23, 447.89, 164.8, 448.25, 155.86, 451.82, 146.57, 461.47, 127.63, 469.33, 112.97, 475.05, 101.18, 478.27, 94.75, 479.34, 88.31, 475.05, 85.1, 471.84, 79.73, 477.2, 71.87, 496.14, 60.08, 521.16, 45.07, 535.81, 60.79, 536.53, 76.16, 531.88, 86.17, 528.66, 90.1, 524.73, 92.24, 521.16, 91.53, 515.8, 96.53, 514.37, 98.68, 517.94, 102.97, 524.73, 105.82, 531.52, 107.61, 540.1, 101.54, 539.74, 91.89, 546.18, 82.95, 550.82, 85.81, 555.11, 92.96, 554.4, 102.61, 548.32, 111.9, 543.67, 118.69, 539.03, 121.91, 535.81, 131.56, 546.89, 137.28, 556.9, 132.27, 560.11, 113.69, 564.4, 101.54, 569.41, 87.6, 572.98, 79.73, 567.98, 73.3, 571.55, 61.51, 580.84, 40.06, 587.99, 23.98, 590.85, 13.26, 589.42, 3.61, 589.06, 0.39, 502.93, 0.75, 446.1, 0.03, 432.88, 11.47]], "area": 24061.309699999998, "iscrowd": 0, "image_id": 568788, "bbox": [338.77, 0.03, 252.08, 209.52], "category_id": 18, "id": 15116, "split": "val", "sentences": [{"tokens": ["a", "dog", "without", "a", "collar", "eating"], "raw": "A dog without a collar eating.", "sent_id": 37530, "sent": "a dog without a collar eating"}, {"tokens": ["reflection", "of", "a", "dog", "drinking", "from", "a", "water", "bowl"], "raw": "Reflection of a dog drinking from a water bowl.", "sent_id": 37531, "sent": "reflection of a dog drinking from a water bowl"}], "file_name": "COCO_train2014_000000568788_15116.jpg", "ann_id": 15116, "sent_ids": [37530, 37531], "ref_id": 19407}, {"segmentation": [[375.85, 416.01, 375.85, 416.01, 373.92, 416.01, 372.96, 416.01, 353.68, 416.01, 332.48, 414.08, 301.64, 416.01, 287.19, 416.01, 252.49, 416.01, 253.46, 416.97, 247.68, 416.97, 238.04, 414.08, 239.0, 397.69, 243.82, 385.17, 250.57, 365.89, 255.39, 343.73, 257.31, 325.42, 260.2, 298.43, 257.31, 282.05, 243.82, 243.5, 243.82, 235.79, 252.49, 204.95, 266.95, 175.08, 265.02, 158.69, 257.31, 153.87, 274.66, 137.49, 269.84, 126.89, 266.95, 124.96, 265.02, 107.62, 266.95, 96.05, 271.77, 83.52, 284.3, 60.39, 296.83, 55.57, 315.14, 55.57, 330.56, 69.07, 339.23, 93.16, 342.12, 131.71, 342.12, 141.35, 359.47, 153.87, 383.56, 161.58, 402.83, 175.08, 419.22, 184.71, 419.22, 185.68, 419.22, 187.6, 419.22, 199.17, 417.29, 203.99, 416.33, 218.44, 411.51, 233.86, 406.69, 253.14, 406.69, 264.7, 406.69, 267.59, 404.76, 272.41, 398.02, 274.34, 387.41, 272.41, 382.6, 271.45, 380.67, 274.34, 380.67, 291.69, 377.78, 312.89, 369.1, 335.05, 375.85, 353.36, 372.96, 368.78, 369.1, 377.46, 375.85, 397.69, 375.85, 402.51, 375.85, 414.08, 377.78, 416.01, 377.78, 416.01], [159.01, 218.44, 157.09, 219.41, 151.3, 221.33, 130.1, 223.26, 122.39, 235.79, 122.39, 240.61, 142.63, 269.52, 170.58, 279.16, 165.76, 267.59, 178.29, 256.99, 173.47, 245.43, 168.65, 237.72, 168.65, 232.9, 165.76, 219.41, 141.67, 211.7, 141.67, 211.7], [486.68, 245.43, 491.5, 235.79, 491.5, 206.88, 489.57, 195.31, 488.61, 175.08, 479.93, 160.62, 477.04, 146.16, 474.15, 123.03, 474.15, 110.51, 470.29, 91.23, 450.06, 89.3, 428.85, 107.62, 436.56, 122.07, 451.02, 127.85, 469.33, 144.24, 465.48, 176.04, 470.29, 211.7, 483.79, 229.04, 483.79, 248.32, 483.79, 248.32]], "area": 47851.9668, "iscrowd": 0, "image_id": 203994, "bbox": [122.39, 55.57, 369.11, 361.4], "category_id": 1, "id": 522056, "split": "val", "sentences": [{"tokens": ["man", "with", "glasses", "and", "a", "white", "shirt"], "raw": "Man with glasses and a white shirt.", "sent_id": 37532, "sent": "man with glasses and a white shirt"}, {"tokens": ["a", "man", "wearing", "glasses", "and", "a", "white", "shirt"], "raw": "A man wearing glasses and a white shirt.", "sent_id": 37533, "sent": "a man wearing glasses and a white shirt"}], "file_name": "COCO_train2014_000000203994_522056.jpg", "ann_id": 522056, "sent_ids": [37532, 37533], "ref_id": 19408}, {"segmentation": [[179.67, 410.08, 175.0, 384.42, 183.17, 370.42, 187.83, 347.08, 193.67, 315.58, 201.83, 312.08, 196.0, 370.42, 205.33, 371.58, 211.17, 362.25, 211.17, 343.58, 225.17, 300.42, 231.0, 258.42, 233.33, 244.42, 240.33, 222.25, 245.0, 201.25, 238.0, 194.25, 231.0, 191.92, 226.33, 187.25, 219.33, 205.92, 185.5, 244.42, 161.0, 245.58, 142.33, 257.25, 138.83, 271.25, 138.83, 294.58, 144.67, 333.08, 150.5, 361.08, 157.5, 403.08, 151.67, 410.08, 171.5, 421.75]], "area": 11925.695799999998, "iscrowd": 0, "image_id": 126447, "bbox": [138.83, 187.25, 106.17, 234.5], "category_id": 19, "id": 2190850, "split": "val", "sentences": [{"tokens": ["the", "horse", "on", "the", "left", "closest", "to", "the", "camera"], "raw": "The horse on the left closest to the camera.", "sent_id": 37566, "sent": "the horse on the left closest to the camera"}, {"tokens": ["a", "horse", "with", "multiple", "brands"], "raw": "A horse with multiple brands.", "sent_id": 37567, "sent": "a horse with multiple brands"}], "file_name": "COCO_train2014_000000126447_2190850.jpg", "ann_id": 2190850, "sent_ids": [37566, 37567], "ref_id": 19420}, {"segmentation": [[238.74, 520.63, 267.51, 500.49, 281.89, 542.2, 250.25, 535.01, 234.43, 526.38], [276.13, 500.49, 276.13, 435.78, 247.37, 412.76, 232.99, 366.74, 251.69, 304.9, 322.16, 306.34, 332.22, 363.87, 326.47, 399.82, 289.08, 432.9, 284.76, 500.49]], "area": 11712.237000000001, "iscrowd": 0, "image_id": 316671, "bbox": [232.99, 304.9, 99.23, 237.3], "category_id": 46, "id": 664684, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "red", "wine", "being", "held", "by", "a", "woman"], "raw": "A glass of red wine being held by a woman.", "sent_id": 37631, "sent": "a glass of red wine being held by a woman"}, {"tokens": ["glass", "on", "right"], "raw": "glass on right", "sent_id": 37632, "sent": "glass on right"}], "file_name": "COCO_train2014_000000316671_664684.jpg", "ann_id": 664684, "sent_ids": [37631, 37632], "ref_id": 19444}, {"segmentation": [[401.12, 91.85, 394.38, 88.48, 384.27, 69.94, 371.63, 77.53, 360.67, 90.17, 358.15, 96.91, 347.19, 107.02, 348.03, 116.29, 358.99, 129.78, 385.11, 153.37, 409.55, 171.91, 416.29, 186.24, 426.4, 201.4, 451.69, 208.15, 462.64, 199.72, 464.33, 188.76, 480.34, 168.54, 481.18, 158.43, 467.7, 138.2, 460.11, 126.4, 455.06, 115.45, 451.69, 106.18, 431.46, 101.12, 412.08, 94.38]], "area": 9407.102899999998, "iscrowd": 0, "image_id": 554706, "bbox": [347.19, 69.94, 133.99, 138.21], "category_id": 58, "id": 1568435, "split": "val", "sentences": [{"tokens": ["the", "right", "-", "most", "hot", "dog", "on", "the", "far", "right", "of", "the", "lunch", "tray"], "raw": "The right-most hot dog on the far right of the lunch tray.", "sent_id": 37748, "sent": "the right - most hot dog on the far right of the lunch tray"}, {"tokens": ["a", "small", "hot", "dog", "farthers", "from", "the", "drink"], "raw": "a small hot dog farthers from the drink.", "sent_id": 37749, "sent": "a small hot dog farthers from the drink"}], "file_name": "COCO_train2014_000000554706_1568435.jpg", "ann_id": 1568435, "sent_ids": [37748, 37749], "ref_id": 19492}, {"segmentation": [[294.23, 437.19, 279.27, 606.75, 151.27, 615.06, 123.01, 606.75, 88.1, 583.48, 61.51, 608.42, 8.31, 610.08, 0.0, 640.0, 427.22, 640.0, 428.0, 463.79, 295.9, 438.86], [8.31, 455.48, 49.87, 473.77, 76.47, 470.44, 98.08, 483.74, 101.4, 520.31, 101.4, 546.91, 116.36, 540.26, 113.04, 462.13, 109.71, 435.53, 0.0, 452.16]], "area": 39898.01525000001, "iscrowd": 0, "image_id": 466825, "bbox": [0.0, 435.53, 428.0, 204.47], "category_id": 67, "id": 1962580, "split": "val", "sentences": [{"tokens": ["the", "portion", "of", "the", "table", "largely", "empty"], "raw": "The portion of the table largely empty.", "sent_id": 37927, "sent": "the portion of the table largely empty"}, {"tokens": ["a", "white", "table", "in", "a", "room"], "raw": "A white table in a room.", "sent_id": 37928, "sent": "a white table in a room"}], "file_name": "COCO_train2014_000000466825_1962580.jpg", "ann_id": 1962580, "sent_ids": [37927, 37928], "ref_id": 19567}, {"segmentation": [[179.02, 412.6, 179.02, 358.03, 182.84, 340.8, 205.82, 331.23, 209.65, 307.29, 187.63, 288.15, 166.57, 261.34, 178.06, 240.28, 194.33, 225.92, 211.56, 208.69, 187.63, 203.91, 164.66, 173.27, 174.23, 141.68, 140.72, 84.24, 172.31, 76.58, 246.98, 67.01, 283.36, 68.93, 291.98, 73.71, 283.36, 132.11, 283.36, 164.66, 267.09, 170.4, 259.43, 194.33, 233.58, 202.95, 236.45, 219.22, 273.79, 219.22, 282.4, 240.28, 281.45, 256.56, 267.09, 289.11, 257.51, 303.47, 260.39, 318.78, 262.3, 319.74, 272.83, 320.7, 295.81, 323.57, 305.38, 349.42, 310.17, 391.54, 297.72, 416.43, 294.85, 420.26, 240.28, 420.26, 190.5, 418.34]], "area": 36100.80095, "iscrowd": 0, "image_id": 223023, "bbox": [140.72, 67.01, 169.45, 353.25], "category_id": 70, "id": 1095968, "split": "val", "sentences": [{"tokens": ["a", "white", "toilet", "next", "to", "a", "bidet"], "raw": "A white toilet next to a bidet", "sent_id": 37946, "sent": "a white toilet next to a bidet"}, {"tokens": ["a", "white", "and", "tan", "toilet", "under", "a", "window", "in", "a", "bathroom"], "raw": "A white and tan toilet under a window in a bathroom.", "sent_id": 37947, "sent": "a white and tan toilet under a window in a bathroom"}], "file_name": "COCO_train2014_000000223023_1095968.jpg", "ann_id": 1095968, "sent_ids": [37946, 37947], "ref_id": 19573}, {"segmentation": [[358.11, 164.22, 371.06, 263.46, 393.71, 294.74, 402.34, 323.87, 448.72, 320.63, 470.29, 310.92, 472.45, 261.3, 470.29, 254.83, 444.4, 180.4, 429.3, 154.52, 367.82, 144.81, 349.48, 144.81]], "area": 14891.4906, "iscrowd": 0, "image_id": 41233, "bbox": [349.48, 144.81, 122.97, 179.06], "category_id": 8, "id": 1369146, "split": "val", "sentences": [{"tokens": ["a", "dark", "gray", "truck"], "raw": "a dark gray truck", "sent_id": 37997, "sent": "a dark gray truck"}, {"tokens": ["front", "end", "of", "a", "grey", "truck", "without", "the", "trailor"], "raw": "front end of a grey truck without the trailor", "sent_id": 37998, "sent": "front end of a grey truck without the trailor"}], "file_name": "COCO_train2014_000000041233_1369146.jpg", "ann_id": 1369146, "sent_ids": [37997, 37998], "ref_id": 19595}, {"segmentation": [[284.35, 109.14, 278.6, 143.61, 282.43, 187.65, 290.09, 217.33, 291.05, 297.75, 344.66, 314.98, 370.51, 314.98, 387.75, 314.98, 393.49, 311.15, 402.11, 162.76, 421.26, 132.12, 421.26, 108.19, 418.38, 88.08, 405.94, 64.15, 381.04, 63.19, 371.47, 68.93, 358.07, 70.85, 341.79, 70.85, 329.35, 67.02, 320.73, 67.98, 310.2, 70.85, 298.71, 77.55, 291.05, 88.08, 291.05, 90.0]], "area": 28504.33365, "iscrowd": 0, "image_id": 490016, "bbox": [278.6, 63.19, 142.66, 251.79], "category_id": 22, "id": 583657, "split": "val", "sentences": [{"tokens": ["elephant", "on", "the", "right"], "raw": "Elephant on the right", "sent_id": 38043, "sent": "elephant on the right"}, {"tokens": ["an", "elephant", "walking", "with", "it", "'", "s", "back", "leg", "lifted"], "raw": "An elephant walking with it's back leg lifted.", "sent_id": 38044, "sent": "an elephant walking with it ' s back leg lifted"}], "file_name": "COCO_train2014_000000490016_583657.jpg", "ann_id": 583657, "sent_ids": [38043, 38044], "ref_id": 19609}, {"segmentation": [[292.74, 466.51, 288.43, 399.07, 302.78, 364.63, 256.86, 337.36, 219.55, 328.75, 206.64, 323.01, 226.73, 301.49, 252.56, 291.44, 256.86, 304.36, 307.09, 334.49, 328.61, 338.8, 337.22, 357.45, 358.74, 370.37, 383.14, 391.89, 375.96, 446.42, 361.61, 453.6, 347.26, 460.77, 347.26, 424.9, 332.91, 439.25, 331.48, 462.21, 318.57, 466.51, 297.04, 463.64], [355.87, 525.35, 354.44, 465.08, 368.79, 462.21, 364.48, 531.09, 357.31, 529.65], [292.74, 531.09, 295.61, 509.56, 308.52, 511.0, 307.09, 538.26, 292.74, 538.26]], "area": 12538.8542, "iscrowd": 0, "image_id": 30535, "bbox": [206.64, 291.44, 176.5, 246.82], "category_id": 25, "id": 599450, "split": "val", "sentences": [{"tokens": ["the", "giraffee", "eating", "leaves", "near", "zebra"], "raw": "The giraffee eating leaves near zebra", "sent_id": 38051, "sent": "the giraffee eating leaves near zebra"}, {"tokens": ["the", "giraffe", "who", "is", "behind", "the", "zebra"], "raw": "The giraffe who is behind the zebra", "sent_id": 38052, "sent": "the giraffe who is behind the zebra"}], "file_name": "COCO_train2014_000000030535_599450.jpg", "ann_id": 599450, "sent_ids": [38051, 38052], "ref_id": 19612}, {"segmentation": [[50.85, 43.66, 63.32, 37.9, 83.47, 28.3, 115.14, 15.83, 123.77, 10.07, 141.04, 0.48, 217.8, 1.44, 313.74, 4.32, 325.26, 12.95, 354.04, 21.59, 357.88, 21.59, 381.86, 51.33, 392.42, 69.56, 395.3, 78.2, 398.18, 90.67, 391.46, 108.9, 373.23, 124.25, 371.31, 146.32, 360.76, 151.11, 357.88, 146.32, 351.16, 138.64, 338.69, 134.8, 324.3, 140.56, 322.38, 149.2, 316.62, 159.75, 306.07, 168.39, 303.19, 175.1, 293.59, 187.57, 292.64, 195.25, 292.64, 200.05, 291.68, 209.64, 287.84, 224.03, 287.84, 228.83, 288.8, 243.22, 289.76, 246.1, 292.64, 255.7, 306.07, 252.82, 322.38, 246.1, 333.89, 243.22, 344.45, 236.51, 359.8, 234.59, 368.43, 234.59, 376.11, 236.51, 378.99, 237.47, 385.7, 242.26, 384.74, 248.98, 386.66, 250.9, 389.54, 255.7, 397.22, 254.74, 405.85, 251.86, 410.65, 250.9, 424.08, 252.82, 432.72, 259.53, 434.64, 267.21, 448.07, 273.93, 457.66, 282.56, 460.54, 296.95, 460.54, 301.75, 460.54, 303.67, 460.54, 305.59, 459.58, 308.47, 449.99, 304.63, 449.03, 302.71, 441.35, 304.63, 435.59, 307.51, 437.51, 315.18, 435.59, 318.06, 423.12, 313.26, 418.32, 313.26, 424.08, 325.74, 425.04, 325.74, 434.64, 334.37, 442.31, 338.21, 448.07, 343.01, 451.91, 347.8, 447.11, 354.52, 433.68, 354.52, 428.88, 351.64, 412.57, 338.21, 403.93, 324.78, 399.14, 313.26, 386.66, 317.1, 360.76, 343.97, 359.8, 350.68, 359.8, 359.32, 347.32, 370.83, 338.69, 379.47, 335.81, 385.22, 343.49, 404.41, 352.12, 418.8, 352.12, 421.68, 86.35, 419.76, 56.61, 274.89, 35.5, 180.86, 19.19, 172.22, 9.59, 169.34, 0.96, 154.95, 10.55, 99.3, 49.89, 45.57]], "area": 131585.62924999994, "iscrowd": 0, "image_id": 2892, "bbox": [0.96, 0.48, 459.58, 421.2], "category_id": 1, "id": 455470, "split": "val", "sentences": [{"tokens": ["a", "girl", "holding", "a", "donut"], "raw": "a girl holding a donut", "sent_id": 38064, "sent": "a girl holding a donut"}, {"tokens": ["the", "woman", "who", "is", "wearing", "a", "blue", "shirt"], "raw": "The woman who is wearing a blue shirt.", "sent_id": 38065, "sent": "the woman who is wearing a blue shirt"}], "file_name": "COCO_train2014_000000002892_455470.jpg", "ann_id": 455470, "sent_ids": [38064, 38065], "ref_id": 19616}, {"segmentation": [[17.2, 175.27, 2.15, 97.85, 2.15, 65.59, 76.34, 52.69, 82.8, 52.69, 89.25, 175.27, 151.61, 192.47, 113.98, 216.13, 88.17, 233.33, 89.25, 310.75, 80.65, 307.53, 75.27, 222.58, 69.89, 165.59, 47.31, 170.97, 15.05, 182.8], [22.58, 223.66, 22.58, 207.53, 59.14, 188.17, 54.84, 216.13, 27.96, 222.58]], "area": 13302.658350000003, "iscrowd": 0, "image_id": 229678, "bbox": [2.15, 52.69, 149.46, 258.06], "category_id": 62, "id": 104452, "split": "val", "sentences": [{"tokens": ["the", "brown", "wooden", "chair", "in", "the", "back"], "raw": "the brown wooden chair in the back", "sent_id": 38068, "sent": "the brown wooden chair in the back"}, {"tokens": ["wooden", "chair", "behind", "the", "motorcycle"], "raw": "wooden chair behind the motorcycle", "sent_id": 38069, "sent": "wooden chair behind the motorcycle"}], "file_name": "COCO_train2014_000000229678_104452.jpg", "ann_id": 104452, "sent_ids": [38068, 38069], "ref_id": 19618}, {"segmentation": [[187.63, 177.1, 171.36, 197.2, 168.49, 218.27, 169.44, 230.71, 178.06, 241.24, 126.36, 266.13, 85.2, 317.82, 67.97, 290.06, 69.88, 300.59, 66.05, 316.87, 60.31, 329.31, 55.52, 343.67, 48.82, 370.48, 51.69, 385.79, 65.1, 399.2, 91.9, 403.98, 100.52, 405.9, 98.6, 420.26, 334.1, 416.43, 323.57, 306.34, 297.72, 256.56, 303.47, 233.58, 267.09, 214.44, 251.77, 200.08, 246.03, 185.72, 234.54, 170.4, 219.22, 164.66, 191.46, 168.49]], "area": 48085.9282, "iscrowd": 0, "image_id": 181929, "bbox": [48.82, 164.66, 285.28, 255.6], "category_id": 1, "id": 530318, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "jacket", "sitting", "at", "a", "table"], "raw": "A man wearing a black jacket sitting at a table", "sent_id": 38137, "sent": "a man wearing a black jacket sitting at a table"}, {"tokens": ["a", "man", "is", "sitting", "wearing", "a", "black", "jacket"], "raw": "A man is sitting wearing a black jacket.", "sent_id": 38138, "sent": "a man is sitting wearing a black jacket"}], "file_name": "COCO_train2014_000000181929_530318.jpg", "ann_id": 530318, "sent_ids": [38137, 38138], "ref_id": 19638}, {"segmentation": [[119.37, 319.28, 135.19, 299.15, 161.08, 293.39, 202.79, 289.08, 225.8, 287.64, 245.93, 286.2, 274.7, 312.09, 297.71, 325.03, 302.02, 366.74, 320.72, 388.31, 350.92, 395.51, 371.06, 373.93, 352.36, 325.03, 342.29, 300.58, 323.6, 258.88, 293.39, 214.29, 182.65, 184.09, 163.96, 185.53, 120.81, 192.72, 92.04, 237.3, 90.61, 276.13, 117.93, 277.57, 109.3, 316.4]], "area": 27105.896500000006, "iscrowd": 0, "image_id": 558276, "bbox": [90.61, 184.09, 280.45, 211.42], "category_id": 88, "id": 1161252, "split": "val", "sentences": [{"tokens": ["a", "brown", "bear"], "raw": "A brown bear.", "sent_id": 38159, "sent": "a brown bear"}, {"tokens": ["a", "brown", "stuffed", "teddy", "bear", "that", "is", "on", "top", "of", "a", "white", "teddy", "bear"], "raw": "A brown stuffed teddy bear that is on top of a white teddy bear.", "sent_id": 38160, "sent": "a brown stuffed teddy bear that is on top of a white teddy bear"}], "file_name": "COCO_train2014_000000558276_1161252.jpg", "ann_id": 1161252, "sent_ids": [38159, 38160], "ref_id": 19646}, {"segmentation": [[180.16, 108.62, 200.52, 92.08, 236.15, 95.89, 269.23, 125.16, 290.86, 164.6, 290.86, 173.51, 303.58, 182.41, 302.31, 200.23, 316.31, 225.67, 303.58, 240.94, 279.41, 249.85, 267.96, 256.21, 250.14, 258.76, 234.87, 262.57, 223.42, 262.57, 209.43, 263.85, 197.98, 265.12, 189.07, 263.85, 181.44, 260.03, 173.8, 267.66, 157.26, 263.85, 148.35, 266.39, 129.27, 256.21, 107.64, 240.94, 107.64, 210.41, 116.54, 191.32, 128.0, 179.87, 135.63, 173.51, 143.26, 151.88, 159.81, 122.61, 182.71, 109.89]], "area": 25232.453699999995, "iscrowd": 0, "image_id": 30973, "bbox": [107.64, 92.08, 208.67, 175.58], "category_id": 1, "id": 1228566, "split": "val", "sentences": [{"tokens": ["girl", "in", "red", "shirt", "on", "top", "bunk", "bed", "staring", "into", "camera"], "raw": "Girl in red shirt on top bunk bed staring into camera.", "sent_id": 38201, "sent": "girl in red shirt on top bunk bed staring into camera"}, {"tokens": ["a", "person", "in", "a", "red", "shirt"], "raw": "A person in a red shirt", "sent_id": 38202, "sent": "a person in a red shirt"}], "file_name": "COCO_train2014_000000030973_1228566.jpg", "ann_id": 1228566, "sent_ids": [38201, 38202], "ref_id": 19661}, {"segmentation": [[135.96, 226.97, 162.92, 201.12, 167.42, 188.76, 180.9, 174.16, 195.51, 170.79, 221.35, 174.16, 221.35, 164.04, 233.71, 150.56, 247.19, 140.45, 253.93, 128.09, 257.3, 117.98, 282.02, 119.1, 285.39, 133.71, 283.15, 139.33, 300.0, 169.66, 296.63, 191.01, 274.16, 191.01, 260.67, 191.01, 239.33, 206.74, 208.99, 233.71, 222.47, 266.29, 224.72, 287.64, 217.98, 314.61, 211.24, 339.33, 201.12, 369.66, 191.01, 404.49, 195.51, 442.7, 188.76, 475.28, 188.76, 494.38, 176.4, 493.26, 175.28, 465.17, 175.28, 437.08, 178.65, 394.38, 174.16, 375.28, 168.54, 416.85, 159.55, 449.44, 157.3, 469.66, 161.8, 494.38, 152.81, 492.13, 142.7, 465.17, 134.83, 460.67, 134.83, 492.13, 124.72, 488.76, 129.21, 455.06, 131.46, 420.22, 129.21, 402.25, 132.58, 370.79, 122.47, 340.45, 115.73, 371.91, 111.24, 397.75, 107.87, 419.1, 114.61, 440.45, 108.99, 456.18, 105.62, 471.91, 106.74, 491.01, 89.89, 489.89, 89.89, 461.8, 87.64, 446.07, 75.28, 450.56, 71.91, 426.97, 66.29, 410.11, 85.39, 395.51, 92.13, 394.38, 86.52, 373.03, 84.27, 342.7, 82.02, 288.76, 104.49, 251.69, 112.36, 243.82, 126.97, 226.97]], "area": 34948.072199999995, "iscrowd": 0, "image_id": 378791, "bbox": [66.29, 117.98, 233.71, 376.4], "category_id": 25, "id": 597062, "split": "val", "sentences": [{"tokens": ["baby", "giraffe", "milking"], "raw": "baby giraffe milking", "sent_id": 38229, "sent": "baby giraffe milking"}, {"tokens": ["a", "baby", "giraffe"], "raw": "A baby giraffe.", "sent_id": 38230, "sent": "a baby giraffe"}], "file_name": "COCO_train2014_000000378791_597062.jpg", "ann_id": 597062, "sent_ids": [38229, 38230], "ref_id": 19672}, {"segmentation": [[335.44, 261.99, 334.58, 257.69, 330.28, 252.53, 330.28, 232.74, 326.84, 225.86, 326.84, 217.26, 338.88, 214.68, 338.02, 200.06, 345.76, 195.76, 374.15, 191.46, 373.28, 169.96, 374.15, 159.64, 380.17, 151.89, 396.51, 151.89, 421.45, 152.75, 412.85, 232.74, 403.39, 274.89, 390.49, 274.89, 386.19, 276.61, 383.61, 284.35, 374.15, 286.07, 373.28, 277.47, 344.9, 258.55, 342.32, 263.71]], "area": 7999.883500000005, "iscrowd": 0, "image_id": 247181, "bbox": [326.84, 151.89, 94.61, 134.18], "category_id": 63, "id": 1951210, "split": "val", "sentences": [{"tokens": ["a", "brown", "sofa", "chair", "sitting", "next", "to", "window", "curtains"], "raw": "A brown sofa chair sitting next to window curtains.", "sent_id": 38407, "sent": "a brown sofa chair sitting next to window curtains"}, {"tokens": ["the", "chair", "on", "the", "far", "right", "partially", "obscured", "by", "the", "pole"], "raw": "The chair on the far right partially obscured by the pole", "sent_id": 38408, "sent": "the chair on the far right partially obscured by the pole"}], "file_name": "COCO_train2014_000000247181_1951210.jpg", "ann_id": 1951210, "sent_ids": [38407, 38408], "ref_id": 19741}, {"segmentation": [[89.17, 80.54, 132.31, 57.53, 166.83, 43.15, 191.28, 40.27, 231.55, 40.27, 287.64, 54.65, 284.76, 40.27, 290.52, 38.83, 290.52, 53.21, 335.1, 76.22, 359.55, 89.17, 392.63, 116.49, 399.82, 138.07, 421.39, 168.27, 425.71, 191.28, 428.58, 199.91, 427.15, 209.98, 415.64, 222.92, 371.06, 207.1, 313.53, 202.79, 306.34, 197.03, 274.7, 186.97, 253.12, 174.02, 240.18, 192.72, 238.74, 192.72, 212.85, 277.57, 211.42, 277.57, 240.18, 175.46, 241.62, 172.58, 235.87, 163.96, 234.43, 152.45, 234.43, 132.31, 230.11, 120.81, 181.21, 112.18, 179.78, 112.18, 178.34, 117.93, 176.9, 123.69, 176.9, 130.88, 176.9, 139.51, 179.78, 152.45, 179.78, 158.2, 169.71, 153.89, 94.92, 117.93, 73.35, 107.87, 69.03, 106.43, 86.29, 81.98]], "area": 34253.86669999999, "iscrowd": 0, "image_id": 298262, "bbox": [69.03, 38.83, 359.55, 238.74], "category_id": 28, "id": 282936, "split": "val", "sentences": [{"tokens": ["a", "black", "umbrella", "which", "a", "manis", "carrying"], "raw": "A black umbrella which a manis carrying", "sent_id": 38438, "sent": "a black umbrella which a manis carrying"}, {"tokens": ["black", "umbrella", "carried", "by", "the", "man", "in", "grey", "shirt"], "raw": "Black umbrella carried by the man in grey shirt.", "sent_id": 38439, "sent": "black umbrella carried by the man in grey shirt"}], "file_name": "COCO_train2014_000000298262_282936.jpg", "ann_id": 282936, "sent_ids": [38438, 38439], "ref_id": 19753}, {"segmentation": [[51.56, 346.72, 51.56, 327.0, 59.54, 322.3, 59.07, 303.52, 64.24, 285.68, 74.57, 270.19, 99.45, 250.94, 103.67, 248.59, 149.69, 246.71, 185.37, 246.24, 178.33, 330.75, 175.98, 359.39, 173.16, 370.66, 174.1, 385.22, 183.49, 388.03, 188.19, 389.44, 181.61, 391.79, 171.28, 391.79, 159.08, 385.69, 153.44, 365.97, 147.34, 366.91, 106.96, 369.72, 94.75, 366.44]], "area": 13975.3639, "iscrowd": 0, "image_id": 571658, "bbox": [51.56, 246.24, 136.63, 145.55], "category_id": 3, "id": 352862, "split": "val", "sentences": [{"tokens": ["there", "is", "a", "van", "parked", "next", "to", "a", "school", "bus"], "raw": "There is a van parked next to a school bus.", "sent_id": 38454, "sent": "there is a van parked next to a school bus"}, {"tokens": ["a", "gray", "car", "parked", "by", "a", "yellow", "school", "bus"], "raw": "A gray car parked by a yellow school bus.", "sent_id": 38455, "sent": "a gray car parked by a yellow school bus"}, {"tokens": ["gray", "van", "with", "tinted", "windows", "in", "parking", "lot"], "raw": "Gray van with tinted windows in parking lot.", "sent_id": 38456, "sent": "gray van with tinted windows in parking lot"}], "file_name": "COCO_train2014_000000571658_352862.jpg", "ann_id": 352862, "sent_ids": [38454, 38455, 38456], "ref_id": 19758}, {"segmentation": [[639.28, 43.05, 632.83, 45.2, 596.23, 146.37, 601.61, 204.48, 637.13, 235.7], [637.13, 292.74, 623.14, 337.94, 581.17, 343.32, 570.4, 349.78, 581.17, 363.77, 590.85, 369.15, 598.39, 373.45, 607.0, 380.99, 613.45, 385.29, 619.91, 387.44, 632.83, 389.6, 637.13, 391.75, 640.0, 392.83]], "area": 8076.607999999993, "iscrowd": 0, "image_id": 92957, "bbox": [570.4, 43.05, 69.6, 349.78], "category_id": 46, "id": 667115, "split": "val", "sentences": [{"tokens": ["the", "cup", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the cup on the right in the right hand picture", "sent_id": 38513, "sent": "the cup on the right in the right hand picture"}, {"tokens": ["a", "glass", "of", "wine", "that", "we", "can", "only", "see", "a", "little", "bit", "off", "on", "the", "side", "of", "the", "picture"], "raw": "A glass of wine that we can only see a little bit off on the side of the picture.", "sent_id": 38514, "sent": "a glass of wine that we can only see a little bit off on the side of the picture"}], "file_name": "COCO_train2014_000000092957_667115.jpg", "ann_id": 667115, "sent_ids": [38513, 38514], "ref_id": 19779}, {"segmentation": [[384.83, 350.52, 391.47, 274.61, 392.42, 248.04, 401.91, 238.55, 407.6, 236.65, 450.3, 237.6, 478.77, 267.02, 480.0, 323.95, 480.0, 355.26, 476.87, 396.06, 469.28, 387.52, 474.97, 445.4, 463.58, 458.69, 455.05, 452.04, 448.4, 436.86, 437.97, 415.99, 427.53, 396.06, 422.78, 385.62, 414.24, 374.24, 388.62, 348.62]], "area": 14484.3522, "iscrowd": 0, "image_id": 28281, "bbox": [384.83, 236.65, 95.17, 222.04], "category_id": 62, "id": 384631, "split": "val", "sentences": [{"tokens": ["a", "vacant", "chair", "with", "its", "back", "to", "a", "woman", "who", "looks", "prepared", "to", "blow", "out", "candles", "on", "a", "birthday", "cake"], "raw": "A vacant chair with its back to a woman who looks prepared to blow out candles on a birthday cake.", "sent_id": 38585, "sent": "a vacant chair with its back to a woman who looks prepared to blow out candles on a birthday cake"}, {"tokens": ["a", "blackcolour", "chair"], "raw": "a blackcolour chair", "sent_id": 38586, "sent": "a blackcolour chair"}], "file_name": "COCO_train2014_000000028281_384631.jpg", "ann_id": 384631, "sent_ids": [38585, 38586], "ref_id": 19805}, {"segmentation": [[124.72, 82.58, 138.2, 40.45, 160.96, 21.07, 195.51, 7.58, 236.8, 0.0, 278.09, 17.7, 305.06, 41.29, 321.91, 98.6, 313.48, 126.4, 289.89, 168.54, 260.39, 187.08, 210.67, 195.51, 168.54, 180.34, 128.93, 139.04, 114.61, 96.07]], "area": 29686.48015, "iscrowd": 0, "image_id": 322411, "bbox": [114.61, 0.0, 207.3, 195.51], "category_id": 51, "id": 1038888, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "onion", "cooked", "broccoli", "and", "tomatoes", "sitting", "next", "to", "other", "food", "in", "bowls"], "raw": "A bowl of onion cooked broccoli and tomatoes sitting next to other food in bowls.", "sent_id": 38636, "sent": "a bowl of onion cooked broccoli and tomatoes sitting next to other food in bowls"}, {"tokens": ["a", "cup", "of", "broccoli", "and", "tomatoes"], "raw": "A cup of broccoli and tomatoes.", "sent_id": 38637, "sent": "a cup of broccoli and tomatoes"}], "file_name": "COCO_train2014_000000322411_1038888.jpg", "ann_id": 1038888, "sent_ids": [38636, 38637], "ref_id": 19826}, {"segmentation": [[2.15, 326.54, 61.23, 195.5, 83.78, 158.98, 90.23, 157.9, 67.67, 24.71, 71.97, 6.44, 638.05, 8.59, 639.12, 469.41, 35.45, 472.63, 25.78, 449.0, 0.0, 390.99, 5.37, 326.54]], "area": 275792.3718, "iscrowd": 0, "image_id": 151729, "bbox": [0.0, 6.44, 639.12, 466.19], "category_id": 15, "id": 573111, "split": "val", "sentences": [{"tokens": ["two", "little", "girls", "interacting", "with", "each", "other", "on", "a", "bench"], "raw": "Two little girls interacting with each other on a bench.", "sent_id": 38714, "sent": "two little girls interacting with each other on a bench"}, {"tokens": ["two", "toddlers", "sitting", "on", "a", "bench"], "raw": "Two toddlers sitting on a bench", "sent_id": 38715, "sent": "two toddlers sitting on a bench"}], "file_name": "COCO_train2014_000000151729_573111.jpg", "ann_id": 573111, "sent_ids": [38714, 38715], "ref_id": 19857}, {"segmentation": [[105.34, 1.99, 105.34, 1.99, 107.33, 188.81, 113.29, 209.68, 117.26, 210.68, 393.53, 190.8, 413.41, 2.98, 108.32, 0.0]], "area": 59138.82460000001, "iscrowd": 0, "image_id": 155107, "bbox": [105.34, 0.0, 308.07, 210.68], "category_id": 72, "id": 33741, "split": "val", "sentences": [{"tokens": ["a", "white", "computer", "monitor", "that", "is", "in", "use"], "raw": "A white computer monitor that is in use", "sent_id": 38977, "sent": "a white computer monitor that is in use"}, {"tokens": ["a", "flat", "screen", "computer", "screen", "on", "a", "desk"], "raw": "a flat screen computer screen on a desk", "sent_id": 38978, "sent": "a flat screen computer screen on a desk"}], "file_name": "COCO_train2014_000000155107_33741.jpg", "ann_id": 33741, "sent_ids": [38977, 38978], "ref_id": 19956}, {"segmentation": [[94.68, 359.77, 68.17, 349.67, 47.97, 358.5, 42.92, 309.27, 17.67, 302.96, 11.36, 469.59, 21.46, 473.38, 30.3, 460.75, 49.23, 451.92, 97.2, 439.29, 108.56, 430.46, 109.82, 460.75, 127.5, 455.7, 121.18, 383.75, 95.94, 377.44]], "area": 11375.622250000002, "iscrowd": 0, "image_id": 36729, "bbox": [11.36, 302.96, 116.14, 170.42], "category_id": 62, "id": 1934769, "split": "val", "sentences": [{"tokens": ["chair", "without", "the", "curtain", "on", "it"], "raw": "Chair without the curtain on it", "sent_id": 38981, "sent": "chair without the curtain on it"}, {"tokens": ["armchair", "to", "the", "left", "of", "the", "table"], "raw": "Armchair to the left of the table.", "sent_id": 38982, "sent": "armchair to the left of the table"}], "file_name": "COCO_train2014_000000036729_1934769.jpg", "ann_id": 1934769, "sent_ids": [38981, 38982], "ref_id": 19958}, {"segmentation": [[294.02, 299.97, 286.56, 262.7, 284.49, 234.54, 312.65, 235.78, 336.67, 245.72, 354.06, 275.95, 363.59, 336.41, 366.07, 370.79, 366.49, 391.49, 353.24, 397.7, 339.16, 394.8, 351.99, 348.42, 354.89, 332.69, 349.92, 317.78, 334.19, 306.6, 309.34, 297.49]], "area": 5379.405499999999, "iscrowd": 0, "image_id": 238187, "bbox": [284.49, 234.54, 82.0, 163.16], "category_id": 52, "id": 1043413, "split": "val", "sentences": [{"tokens": ["a", "banana", "slice", "to", "the", "back", "right", "of", "an", "apple", "slice"], "raw": "a banana slice to the back right of an apple slice", "sent_id": 39004, "sent": "a banana slice to the back right of an apple slice"}], "file_name": "COCO_train2014_000000238187_1043413.jpg", "ann_id": 1043413, "sent_ids": [39004], "ref_id": 19967}, {"segmentation": [[91.69, 215.73, 161.8, 210.34, 213.57, 210.34, 232.99, 210.34, 349.48, 208.18, 364.58, 245.93, 363.51, 347.33, 340.85, 351.64, 335.46, 359.19, 323.6, 353.8, 275.06, 368.9, 263.19, 385.08, 255.64, 375.37, 227.6, 380.76, 202.79, 355.96, 203.87, 323.6, 197.39, 309.57, 183.37, 281.53, 174.74, 294.47, 165.03, 328.99, 147.78, 354.88, 147.78, 360.27, 151.01, 380.76, 83.06, 374.29]], "area": 40439.639100000015, "iscrowd": 0, "image_id": 114459, "bbox": [83.06, 208.18, 281.52, 176.9], "category_id": 6, "id": 165616, "split": "val", "sentences": [{"tokens": ["bus", "with", "orange", "paint", "on", "the", "back"], "raw": "bus with orange paint on the back", "sent_id": 39055, "sent": "bus with orange paint on the back"}, {"tokens": ["the", "bus", "that", "is", "white", ",", "blue", ",", "orange", "and", "red"], "raw": "The bus that is white, blue, orange and red.", "sent_id": 39056, "sent": "the bus that is white , blue , orange and red"}], "file_name": "COCO_train2014_000000114459_165616.jpg", "ann_id": 165616, "sent_ids": [39055, 39056], "ref_id": 19984}, {"segmentation": [[219.04, 498.35, 241.73, 529.29, 268.54, 549.91, 296.38, 568.47, 329.38, 565.38, 352.06, 557.13, 364.43, 545.78, 378.87, 526.19, 406.71, 510.72, 429.4, 493.2, 436.62, 467.42, 446.93, 436.48, 432.49, 419.98, 410.84, 408.64, 384.03, 394.2, 340.72, 386.99, 297.41, 386.99, 266.47, 399.36, 259.26, 416.89, 253.07, 443.7, 241.73, 463.29, 227.29, 481.85, 219.04, 489.07]], "area": 28307.453700000005, "iscrowd": 0, "image_id": 562456, "bbox": [219.04, 386.99, 227.89, 181.48], "category_id": 54, "id": 312575, "split": "val", "sentences": [{"tokens": ["half", "of", "sandwich", "closest", "to", "camera"], "raw": "half of sandwich closest to camera", "sent_id": 39073, "sent": "half of sandwich closest to camera"}, {"tokens": ["the", "sandwich", "that", "has", "a", "bit", "out", "of", "it"], "raw": "The sandwich that has a bit out of it.", "sent_id": 39074, "sent": "the sandwich that has a bit out of it"}], "file_name": "COCO_train2014_000000562456_312575.jpg", "ann_id": 312575, "sent_ids": [39073, 39074], "ref_id": 19991}, {"segmentation": [[84.77, 137.63, 42.89, 169.55, 29.92, 185.51, 30.92, 206.45, 61.84, 244.35, 240.36, 329.12, 248.34, 331.12, 296.21, 325.13, 321.14, 309.18, 334.11, 281.25, 330.12, 257.31, 311.17, 210.44, 264.3, 173.54, 226.4, 153.59, 178.52, 143.62, 152.59, 136.64, 111.7, 135.64]], "area": 38996.51425000001, "iscrowd": 0, "image_id": 149556, "bbox": [29.92, 135.64, 304.19, 195.48], "category_id": 74, "id": 1107182, "split": "val", "sentences": [{"tokens": ["the", "mouse", "that", "is", "closest"], "raw": "The mouse that is closest.", "sent_id": 39091, "sent": "the mouse that is closest"}, {"tokens": ["the", "dell", "mouse", "on", "the", "left"], "raw": "The Dell mouse on the left", "sent_id": 39092, "sent": "the dell mouse on the left"}], "file_name": "COCO_train2014_000000149556_1107182.jpg", "ann_id": 1107182, "sent_ids": [39091, 39092], "ref_id": 19997}, {"segmentation": [[158.36, 66.83, 177.52, 79.81, 277.66, 71.16, 330.2, 50.76, 374.09, 32.84, 379.03, 16.76, 385.21, 22.33, 385.21, 37.16, 366.05, 77.96, 356.78, 90.32, 354.93, 84.76, 357.4, 67.45, 350.6, 55.71, 345.65, 53.85, 339.47, 61.89, 333.29, 68.69, 330.82, 70.54, 324.02, 58.8, 320.93, 63.12, 319.69, 75.49, 315.36, 81.67, 298.68, 97.74, 294.35, 106.39, 292.49, 110.1, 273.95, 108.25, 241.81, 110.1, 220.79, 113.19, 211.52, 121.85, 205.95, 122.47, 189.27, 107.01, 170.72, 89.09, 154.03, 75.49, 154.03, 67.45]], "area": 6894.0319500000005, "iscrowd": 0, "image_id": 209809, "bbox": [154.03, 16.76, 231.18, 105.71], "category_id": 51, "id": 1898291, "split": "val", "sentences": [{"tokens": ["a", "brown", "straw", "basket"], "raw": "A brown straw basket.", "sent_id": 39135, "sent": "a brown straw basket"}, {"tokens": ["a", "brown", "bread", "basket", "behind", "and", "to", "the", "left", "of", "the", "cake"], "raw": "a brown bread basket behind and to the left of the cake", "sent_id": 39136, "sent": "a brown bread basket behind and to the left of the cake"}], "file_name": "COCO_train2014_000000209809_1898291.jpg", "ann_id": 1898291, "sent_ids": [39135, 39136], "ref_id": 20011}, {"segmentation": [[221.1, 331.74, 217.29, 281.23, 181.07, 245.02, 190.6, 185.93, 200.13, 162.11, 259.22, 161.15, 271.61, 221.19, 265.89, 248.83, 243.02, 285.05, 233.49, 297.43, 229.68, 332.7, 252.55, 338.41, 263.03, 350.8, 251.6, 368.91, 218.24, 377.49, 190.6, 365.1, 185.84, 353.66, 209.66, 343.18]], "area": 11582.812050000002, "iscrowd": 0, "image_id": 563525, "bbox": [181.07, 161.15, 90.54, 216.34], "category_id": 46, "id": 662660, "split": "val", "sentences": [{"tokens": ["a", "glass", "with", "wine", "being", "poured", "into", "it"], "raw": "A glass with wine being poured into it.", "sent_id": 39169, "sent": "a glass with wine being poured into it"}, {"tokens": ["a", "wine", "glass", "in", "the", "process", "of", "being", "filled"], "raw": "A wine glass in the process of being filled.", "sent_id": 39170, "sent": "a wine glass in the process of being filled"}], "file_name": "COCO_train2014_000000563525_662660.jpg", "ann_id": 662660, "sent_ids": [39169, 39170], "ref_id": 20025}, {"segmentation": [[390.0, 342.67, 395.26, 317.26, 405.78, 294.47, 411.03, 279.57, 408.4, 262.04, 406.65, 252.4, 406.65, 243.64, 406.65, 234.88, 418.92, 237.51, 423.3, 263.8, 423.3, 266.43, 423.3, 266.43, 429.44, 261.17, 441.71, 239.26, 452.22, 215.6, 456.61, 207.71, 502.18, 177.03, 482.9, 209.46, 451.35, 244.52, 445.21, 263.8, 445.21, 270.81, 435.57, 306.74, 440.83, 390.0, 415.42, 390.0, 414.54, 376.85, 420.67, 343.55, 419.8, 314.63, 412.79, 333.03, 411.03, 363.71, 404.02, 390.0, 386.49, 389.12, 390.0, 333.91], [412.79, 215.6, 406.65, 231.37, 418.04, 237.51, 417.17, 222.61]], "area": 6878.6196, "iscrowd": 0, "image_id": 445323, "bbox": [386.49, 177.03, 115.69, 212.97], "category_id": 32, "id": 295304, "split": "val", "sentences": [{"tokens": ["a", "tie", "which", "weared", "by", "a", "person", "wearing", "head", "phone"], "raw": "a tie which weared by a person wearing head phone", "sent_id": 39174, "sent": "a tie which weared by a person wearing head phone"}, {"tokens": ["black", "tie", "on", "sailor", "wearing", "sunglasses", "and", "headphones"], "raw": "Black tie on sailor wearing sunglasses and headphones", "sent_id": 39175, "sent": "black tie on sailor wearing sunglasses and headphones"}], "file_name": "COCO_train2014_000000445323_295304.jpg", "ann_id": 295304, "sent_ids": [39174, 39175], "ref_id": 20028}, {"segmentation": [[25.53, 127.94, 53.49, 37.99, 88.74, 19.75, 131.28, 31.91, 154.38, 45.28, 207.86, 58.65, 244.33, 65.95, 229.75, 109.71, 222.45, 123.08, 237.04, 148.61, 228.53, 169.27, 206.65, 178.99, 179.91, 178.99, 145.87, 160.76, 121.56, 160.76, 83.88, 159.55, 61.99, 153.47, 40.11, 152.25, 29.17, 129.16]], "area": 24221.188349999997, "iscrowd": 0, "image_id": 390474, "bbox": [25.53, 19.75, 218.8, 159.24], "category_id": 31, "id": 1836216, "split": "val", "sentences": [{"tokens": ["a", "black", "duffle", "bag", "with", "green", "stripes", "and", "a", "small", "padlock"], "raw": "A black duffle bag with green stripes and a small padlock.", "sent_id": 39246, "sent": "a black duffle bag with green stripes and a small padlock"}, {"tokens": ["a", "green", "duffel", "bag"], "raw": "A green duffel bag.", "sent_id": 39247, "sent": "a green duffel bag"}], "file_name": "COCO_train2014_000000390474_1836216.jpg", "ann_id": 1836216, "sent_ids": [39246, 39247], "ref_id": 20059}, {"segmentation": [[74.54, 237.52, 114.09, 205.25, 115.7, 189.11, 130.23, 172.97, 140.72, 162.48, 121.35, 118.09, 122.96, 82.59, 138.29, 63.22, 170.57, 44.66, 217.38, 48.69, 257.73, 74.52, 264.18, 94.69, 264.18, 118.9, 257.73, 130.2, 262.57, 141.5, 264.18, 163.28, 259.34, 185.07, 244.81, 206.05, 286.78, 212.51, 315.83, 212.51, 330.35, 205.25, 344.07, 197.18, 357.79, 189.11, 371.51, 180.23, 380.38, 155.21, 384.42, 143.92, 387.65, 139.88, 398.14, 139.07, 418.31, 139.07, 428.8, 145.53, 432.03, 164.09, 415.89, 172.16, 403.79, 179.42, 397.33, 194.76, 393.3, 206.86, 388.45, 215.74, 387.65, 235.91, 367.47, 226.23, 344.07, 229.45, 315.83, 253.66, 292.43, 259.31, 255.3, 277.87, 234.32, 294.01, 178.64, 304.5, 162.5, 298.05, 128.61, 267.38, 93.91, 255.28]], "area": 41657.78475, "iscrowd": 0, "image_id": 86654, "bbox": [74.54, 44.66, 357.49, 259.84], "category_id": 1, "id": 446120, "split": "val", "sentences": [{"tokens": ["boy", "with", "a", "strand", "of", "spaghetti", "in", "his", "mouth"], "raw": "Boy with a strand of spaghetti in his mouth.", "sent_id": 39267, "sent": "boy with a strand of spaghetti in his mouth"}, {"tokens": ["a", "boy", "is", "eating", "pizza"], "raw": "A boy is eating pizza.", "sent_id": 39268, "sent": "a boy is eating pizza"}], "file_name": "COCO_train2014_000000086654_446120.jpg", "ann_id": 446120, "sent_ids": [39267, 39268], "ref_id": 20065}, {"segmentation": [[274.96, 209.58, 374.52, 206.02, 372.15, 311.51, 356.74, 306.77, 327.11, 312.69, 323.56, 298.47, 297.48, 267.65, 289.19, 245.14, 277.33, 238.02], [162.37, 347.06, 188.44, 326.91, 201.48, 334.02, 213.33, 336.4, 200.3, 283.06, 205.04, 262.91, 215.7, 248.69, 216.89, 240.4, 216.89, 221.43, 215.7, 209.58, 155.26, 213.14, 163.56, 224.99]], "area": 13643.450499999995, "iscrowd": 0, "image_id": 220037, "bbox": [155.26, 206.02, 219.26, 141.04], "category_id": 63, "id": 2223810, "split": "val", "sentences": [{"tokens": ["a", "section", "of", "the", "black", "seating", "that", "is", "behind", "the", "woman", "in", "a", "dark", "patterned", "top"], "raw": "A section of the black seating that is behind the woman in a dark patterned top.", "sent_id": 39288, "sent": "a section of the black seating that is behind the woman in a dark patterned top"}], "file_name": "COCO_train2014_000000220037_2223810.jpg", "ann_id": 2223810, "sent_ids": [39288], "ref_id": 20074}, {"segmentation": [[290.82, 44.3, 290.02, 55.42, 289.23, 60.98, 293.2, 61.78, 292.41, 68.14, 288.43, 79.26, 292.41, 104.69, 284.46, 135.67, 274.13, 157.13, 274.13, 169.05, 266.98, 170.64, 264.6, 178.58, 265.39, 187.32, 268.57, 192.09, 274.93, 194.47, 285.26, 167.46, 296.38, 150.77, 305.12, 147.59, 310.68, 198.45, 308.3, 208.78, 328.96, 212.75, 324.19, 182.56, 321.01, 150.77, 321.01, 113.43, 321.81, 103.1, 329.75, 97.53, 328.96, 87.21, 322.6, 73.7, 317.04, 68.14, 309.89, 60.98, 313.07, 55.42, 313.07, 37.94, 306.71, 36.35, 296.38, 36.35, 290.82, 37.15, 286.84, 41.91]], "area": 5185.88375, "iscrowd": 0, "image_id": 272155, "bbox": [264.6, 36.35, 65.15, 176.4], "category_id": 1, "id": 504890, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "blue", "t", "-", "shirt", "walking", "out", "of", "the", "room"], "raw": "a man wearing a blue t-shirt walking out of the room", "sent_id": 39294, "sent": "a man wearing a blue t - shirt walking out of the room"}, {"tokens": ["a", "man", "in", "a", "dark", "shirt", "and", "jeans", "walking", "out", "of", "the", "room"], "raw": "A man in a dark shirt and jeans walking out of the room.", "sent_id": 39295, "sent": "a man in a dark shirt and jeans walking out of the room"}], "file_name": "COCO_train2014_000000272155_504890.jpg", "ann_id": 504890, "sent_ids": [39294, 39295], "ref_id": 20078}, {"segmentation": [[1.88, 169.62, 1.88, 169.62, 18.18, 167.39, 33.73, 168.88, 49.29, 171.1, 70.77, 175.54, 85.59, 187.4, 90.03, 208.88, 92.26, 224.44, 92.26, 239.25, 91.52, 254.07, 86.33, 277.03, 85.59, 286.66, 78.92, 300.0, 70.03, 306.67, 66.33, 314.08, 66.33, 324.45, 68.55, 334.82, 90.03, 348.15, 104.11, 368.15, 106.33, 386.68, 111.52, 414.09, 115.22, 425.0, 87.81, 424.46, 64.85, 425.0, 32.99, 425.0, 2.62, 425.0, 0.0, 422.98, 0.0, 392.6, 0.0, 360.75, 0.0, 313.33, 0.0, 283.7, 0.0, 260.0, 0.0, 228.14, 0.4, 201.47, 1.14, 182.95, 1.88, 175.54, 2.62, 170.36]], "area": 22800.92675, "iscrowd": 0, "image_id": 342374, "bbox": [0.0, 167.39, 115.22, 257.61], "category_id": 1, "id": 515172, "split": "val", "sentences": [{"tokens": ["a", "girl", "with", "a", "pink", "hairbow", "and", "green", "top"], "raw": "A girl with a pink hairbow and green top.", "sent_id": 39435, "sent": "a girl with a pink hairbow and green top"}, {"tokens": ["a", "little", "girl", "in", "a", "stripped", "shirt", "and", "green", "vest", "with", "her", "back", "turned", "sitting", "at", "a", "table"], "raw": "A little girl in a stripped shirt and green vest with her back turned sitting at a table.", "sent_id": 39436, "sent": "a little girl in a stripped shirt and green vest with her back turned sitting at a table"}], "file_name": "COCO_train2014_000000342374_515172.jpg", "ann_id": 515172, "sent_ids": [39435, 39436], "ref_id": 20141}, {"segmentation": [[637.22, 236.85, 558.93, 229.91, 533.16, 231.9, 514.33, 215.05, 490.55, 201.18, 465.78, 196.22, 441.99, 196.22, 407.31, 202.17, 369.65, 217.03, 336.94, 231.9, 322.08, 231.9, 246.76, 238.83, 108.02, 254.69, 109.01, 236.85, 104.06, 214.06, 94.15, 188.29, 81.26, 185.32, 70.36, 191.27, 58.47, 211.09, 56.49, 238.83, 50.54, 236.85, 32.7, 244.78, 50.54, 252.71, 21.8, 261.63, 16.85, 237.84, 10.9, 222.98, 1.98, 206.13, 0.99, 321.09, 8.92, 324.06, 18.83, 311.18, 22.79, 295.32, 67.39, 302.26, 157.57, 310.19, 256.67, 321.09, 291.36, 325.05, 323.07, 331.0, 339.92, 337.93, 345.86, 337.93, 331.0, 362.71, 330.01, 374.6, 356.76, 389.47, 356.76, 389.47, 433.07, 392.44, 577.76, 387.49, 608.48, 378.57, 615.42, 373.61, 615.42, 373.61, 610.46, 358.75, 584.7, 350.82, 548.03, 331.0, 592.62, 326.04, 624.34, 316.13, 638.21, 308.2, 638.21, 233.88]], "area": 75004.17700000001, "iscrowd": 0, "image_id": 524925, "bbox": [0.99, 185.32, 637.22, 207.12], "category_id": 5, "id": 159353, "split": "val", "sentences": [{"tokens": ["a", "small", "silver", "plane", "with", "n6594q", "printed", "on", "the", "side", "in", "black"], "raw": "A small silver plane with N6594Q printed on the side in black.", "sent_id": 39445, "sent": "a small silver plane with n6594q printed on the side in black"}, {"tokens": ["n65940", "numbered", "aeroplane"], "raw": "N65940 numbered aeroplane", "sent_id": 39446, "sent": "n65940 numbered aeroplane"}], "file_name": "COCO_train2014_000000524925_159353.jpg", "ann_id": 159353, "sent_ids": [39445, 39446], "ref_id": 20145}, {"segmentation": [[519.06, 192.61, 518.51, 176.83, 517.97, 170.3, 516.88, 154.52, 520.15, 138.2, 520.69, 125.14, 523.41, 109.91, 526.13, 101.74, 528.85, 94.67, 528.85, 85.97, 529.94, 83.79, 522.32, 81.61, 517.43, 83.25, 514.71, 79.98, 514.71, 77.8, 511.98, 75.08, 510.9, 75.63, 504.91, 81.61, 497.29, 90.32, 493.49, 91.41, 492.94, 89.23, 495.12, 85.42, 504.37, 71.28, 520.69, 57.13, 532.12, 53.86, 540.3, 53.99, 548.89, 58.63, 552.82, 56.97, 561.52, 57.89, 571.29, 58.76, 583.8, 57.13, 599.04, 65.83, 607.2, 75.63, 612.1, 84.88, 612.64, 94.13, 611.55, 103.38, 610.46, 110.45, 608.29, 108.27, 607.2, 103.38, 606.11, 93.58, 603.39, 87.6, 598.49, 90.32, 595.77, 91.95, 594.14, 94.13, 589.79, 91.41, 588.16, 88.69, 582.17, 89.77, 588.16, 93.58, 601.76, 99.57, 605.02, 101.2, 606.66, 101.74, 607.2, 108.27, 609.38, 110.99, 610.69, 110.7, 611.94, 103.76, 633.32, 111.54, 638.21, 112.63, 640.0, 113.71, 639.85, 163.23, 637.67, 170.84, 623.52, 175.74, 597.95, 182.81, 569.11, 188.25, 543.54, 191.52, 517.43, 193.15]], "area": 13624.505500000001, "iscrowd": 0, "image_id": 498297, "bbox": [492.94, 53.86, 147.06, 139.29], "category_id": 20, "id": 64389, "split": "val", "sentences": [{"tokens": ["a", "sheep", "that", "is", "next", "to", "two", "others"], "raw": "a sheep that is next to two others", "sent_id": 39471, "sent": "a sheep that is next to two others"}, {"tokens": ["the", "sheep", "which", "is", "on", "the", "extreme", "right", "hand", "side"], "raw": "The sheep which is on the extreme right hand side", "sent_id": 39472, "sent": "the sheep which is on the extreme right hand side"}], "file_name": "COCO_train2014_000000498297_64389.jpg", "ann_id": 64389, "sent_ids": [39471, 39472], "ref_id": 20154}, {"segmentation": [[185.19, 73.89, 213.98, 79.64, 235.09, 79.64, 263.88, 95.96, 274.43, 115.15, 256.2, 157.37, 237.97, 171.76, 228.37, 203.42, 231.25, 249.48, 232.21, 294.58, 232.21, 310.89, 200.55, 317.61, 170.8, 317.61, 164.08, 275.39, 160.24, 241.81, 146.81, 204.38, 124.74, 167.92, 106.51, 138.18, 96.91, 111.31, 118.02, 85.4, 131.46, 76.76, 173.68, 76.76]], "area": 25040.866100000003, "iscrowd": 0, "image_id": 490016, "bbox": [96.91, 73.89, 177.52, 243.72], "category_id": 22, "id": 580958, "split": "val", "sentences": [{"tokens": ["elephant", "walking", "in", "the", "water"], "raw": "Elephant walking in the water.", "sent_id": 39478, "sent": "elephant walking in the water"}, {"tokens": ["the", "elephant", "on", "the", "left"], "raw": "The elephant on the left.", "sent_id": 39479, "sent": "the elephant on the left"}], "file_name": "COCO_train2014_000000490016_580958.jpg", "ann_id": 580958, "sent_ids": [39478, 39479], "ref_id": 20157}, {"segmentation": [[375.59, 192.36, 370.35, 243.04, 369.77, 272.17, 366.27, 265.76, 358.7, 257.61, 343.55, 257.61, 329.57, 258.19, 341.22, 226.15, 354.04, 212.17, 353.46, 201.1, 353.46, 188.28, 361.03, 180.13, 368.6, 180.71, 373.85, 186.54], [373.26, 272.17, 413.46, 280.91, 421.61, 284.4, 416.37, 288.48, 409.96, 296.05, 412.88, 302.46, 427.44, 312.36, 450.74, 322.85, 454.24, 334.5, 398.31, 329.26, 384.91, 317.61, 384.33, 305.96, 378.51, 304.79, 374.43, 294.89, 378.51, 283.82]], "area": 4565.768999999998, "iscrowd": 0, "image_id": 439765, "bbox": [329.57, 180.13, 124.67, 154.37], "category_id": 32, "id": 1440214, "split": "val", "sentences": [{"tokens": ["a", "blue", "striped", "tie"], "raw": "A blue striped tie.", "sent_id": 39584, "sent": "a blue striped tie"}, {"tokens": ["a", "blue", "striped", "tie"], "raw": "A blue striped tie.", "sent_id": 39585, "sent": "a blue striped tie"}], "file_name": "COCO_train2014_000000439765_1440214.jpg", "ann_id": 1440214, "sent_ids": [39584, 39585], "ref_id": 20198}, {"segmentation": [[373.36, 301.68, 381.53, 310.43, 382.7, 327.37, 390.29, 343.72, 385.04, 357.15, 372.77, 355.98, 365.77, 344.88, 365.77, 315.69], [292.78, 291.75, 243.15, 273.65, 212.2, 277.15, 195.85, 290.58, 201.69, 299.92, 204.03, 301.09, 222.71, 290.58, 276.43, 307.52, 295.7, 312.19, 303.29, 312.77]], "area": 2893.8164500000007, "iscrowd": 0, "image_id": 46592, "bbox": [195.85, 273.65, 194.44, 83.5], "category_id": 18, "id": 1402655, "split": "val", "sentences": [{"tokens": ["the", "corgi", "behind", "the", "other", "corgi"], "raw": "The corgi behind the other corgi", "sent_id": 39598, "sent": "the corgi behind the other corgi"}, {"tokens": ["the", "dog", "closest", "to", "the", "man"], "raw": "The dog closest to the man.", "sent_id": 39599, "sent": "the dog closest to the man"}], "file_name": "COCO_train2014_000000046592_1402655.jpg", "ann_id": 1402655, "sent_ids": [39598, 39599], "ref_id": 20205}, {"segmentation": [[203.4, 263.45, 198.9, 156.12, 240.18, 137.35, 243.18, 141.11, 316.74, 142.61, 319.74, 180.13, 320.49, 222.17, 318.99, 285.21, 295.72, 286.71, 231.92, 288.22]], "area": 16640.833, "iscrowd": 0, "image_id": 81768, "bbox": [198.9, 137.35, 121.59, 150.87], "category_id": 6, "id": 164625, "split": "val", "sentences": [{"tokens": ["a", "bus", "with", "the", "front", "facing", "the", "camera"], "raw": "A bus with the front facing the camera.", "sent_id": 39622, "sent": "a bus with the front facing the camera"}, {"tokens": ["a", "double", "decker", "bus", "numbered", "94"], "raw": "A double decker bus numbered 94.", "sent_id": 39623, "sent": "a double decker bus numbered 94"}], "file_name": "COCO_train2014_000000081768_164625.jpg", "ann_id": 164625, "sent_ids": [39622, 39623], "ref_id": 20215}, {"segmentation": [[77.0, 419.0, 131.0, 375.0, 194.0, 337.0, 236.0, 298.0, 236.0, 284.0, 236.0, 277.0, 187.0, 303.0, 86.0, 349.0, 26.0, 389.0, 18.0, 408.0, 23.0, 418.0]], "area": 9401.0, "iscrowd": 0, "image_id": 477580, "bbox": [18.0, 277.0, 218.0, 142.0], "category_id": 57, "id": 1062573, "split": "val", "sentences": [{"tokens": ["the", "carrot", "to", "the", "left", "of", "the", "broccol"], "raw": "The carrot to the left of the broccol.", "sent_id": 39652, "sent": "the carrot to the left of the broccol"}, {"tokens": ["a", "carrot", "going", "across", "the", "others"], "raw": "a carrot going across the others.", "sent_id": 39653, "sent": "a carrot going across the others"}], "file_name": "COCO_train2014_000000477580_1062573.jpg", "ann_id": 1062573, "sent_ids": [39652, 39653], "ref_id": 20228}, {"segmentation": [[121.7, 473.91, 12.66, 473.91, 52.58, 371.68, 73.02, 340.53, 95.42, 317.16, 101.26, 302.56, 125.6, 280.16, 174.28, 273.35, 181.1, 259.72, 197.65, 255.82, 221.99, 249.98, 249.25, 252.9, 266.77, 267.51, 273.59, 277.24, 273.59, 283.08, 286.25, 292.82, 278.46, 312.29, 249.25, 316.19, 236.59, 323.0, 229.78, 328.84, 218.09, 319.11, 215.17, 322.03, 212.25, 333.71, 208.36, 358.05, 198.62, 376.55, 197.65, 384.34, 194.73, 398.95, 202.52, 415.5, 219.07, 398.95, 229.78, 400.89, 224.91, 423.29, 217.12, 433.02, 200.57, 430.1, 195.7, 430.1, 184.02, 421.34, 176.23, 415.5, 169.41, 420.37, 169.41, 394.08, 149.94, 419.39, 131.44, 448.6, 124.62, 457.36]], "area": 30404.10835, "iscrowd": 0, "image_id": 568788, "bbox": [12.66, 249.98, 273.59, 223.93], "category_id": 18, "id": 3560, "split": "val", "sentences": [{"tokens": ["dog", "with", "purple", "collar", "looking", "in", "the", "mirror"], "raw": "dog with purple collar looking in the mirror", "sent_id": 39705, "sent": "dog with purple collar looking in the mirror"}, {"tokens": ["a", "dog", "eting"], "raw": "a dog eting", "sent_id": 39706, "sent": "a dog eting"}], "file_name": "COCO_train2014_000000568788_3560.jpg", "ann_id": 3560, "sent_ids": [39705, 39706], "ref_id": 20248}, {"segmentation": [[354.55, 266.43, 405.79, 240.81, 435.51, 245.93, 492.89, 282.82, 520.56, 314.59, 529.78, 315.61, 536.95, 356.6, 513.38, 351.48, 498.01, 322.79, 475.47, 293.07, 447.8, 282.82, 428.33, 283.85, 425.26, 308.44, 410.91, 360.7, 400.67, 371.97, 402.71, 328.93, 389.39, 339.18, 382.22, 373.0, 369.92, 371.97, 383.24, 330.98, 370.95, 327.91, 357.63, 339.18, 343.28, 299.22]], "area": 10506.729800000003, "iscrowd": 0, "image_id": 77380, "bbox": [343.28, 240.81, 193.67, 132.19], "category_id": 25, "id": 600743, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "in", "the", "back", "of", "a", "row", "of", "three", "giraffes"], "raw": "A giraffe in the back of a row of three giraffes.", "sent_id": 39716, "sent": "a giraffe in the back of a row of three giraffes"}, {"tokens": ["the", "giraffe", "with", "its", "head", "the", "lowest"], "raw": "The giraffe with its head the lowest", "sent_id": 39717, "sent": "the giraffe with its head the lowest"}], "file_name": "COCO_train2014_000000077380_600743.jpg", "ann_id": 600743, "sent_ids": [39716, 39717], "ref_id": 20251}, {"segmentation": [[105.76, 24.31, 63.21, 26.74, 34.04, 83.88, 27.96, 131.28, 38.9, 137.36, 42.55, 153.16, 59.56, 150.73, 65.64, 150.73, 109.4, 164.1, 136.15, 160.46, 160.46, 173.83, 175.04, 177.48, 189.63, 183.55, 243.12, 160.46, 212.73, 114.26, 239.47, 68.07, 221.24, 58.35, 203.0, 51.05, 161.67, 46.19, 148.3, 41.33, 137.36, 43.76, 123.99, 32.82, 108.19, 23.1]], "area": 23877.2402, "iscrowd": 0, "image_id": 390474, "bbox": [27.96, 23.1, 215.16, 160.45], "category_id": 33, "id": 2081823, "split": "val", "sentences": [{"tokens": ["an", "ugly", "green", "suitcase"], "raw": "An ugly green suitcase.", "sent_id": 39750, "sent": "an ugly green suitcase"}], "file_name": "COCO_train2014_000000390474_2081823.jpg", "ann_id": 2081823, "sent_ids": [39750], "ref_id": 20264}, {"segmentation": [[297.75, 219.2, 264.24, 180.9, 267.11, 139.73, 269.99, 103.35, 256.58, 94.73, 250.84, 133.03, 245.09, 156.97, 232.65, 169.41, 232.65, 183.77, 252.75, 225.9, 238.39, 227.81, 219.24, 225.9, 202.97, 232.6, 164.67, 220.15, 158.93, 223.03, 150.31, 212.49, 141.7, 220.15, 151.27, 230.69, 163.72, 231.64, 180.95, 241.22, 174.25, 249.83, 173.29, 267.07, 185.74, 279.51, 198.18, 278.56, 216.37, 298.66, 222.12, 294.83, 240.31, 337.91, 248.92, 336.0, 253.71, 320.68, 233.61, 272.81, 287.22, 269.94, 315.94, 253.66, 320.73, 246.96, 349.45, 229.73, 380.09, 234.51, 410.72, 223.03, 421.26, 233.56, 448.06, 207.71, 435.62, 201.01, 422.21, 207.71, 373.39, 207.71, 348.49, 202.92, 320.73, 208.67]], "area": 15059.872600000004, "iscrowd": 0, "image_id": 28230, "bbox": [141.7, 94.73, 306.36, 243.18], "category_id": 1, "id": 473342, "split": "val", "sentences": [{"tokens": ["a", "woman", "doing", "acrobatics", "on", "a", "street", "corner"], "raw": "A woman doing acrobatics on a street corner.", "sent_id": 39758, "sent": "a woman doing acrobatics on a street corner"}, {"tokens": ["a", "girl", "doing", "pole", "tricks"], "raw": "a girl doing pole tricks", "sent_id": 39759, "sent": "a girl doing pole tricks"}], "file_name": "COCO_train2014_000000028230_473342.jpg", "ann_id": 473342, "sent_ids": [39758, 39759], "ref_id": 20269}, {"segmentation": [[418.52, 257.44, 465.98, 264.63, 480.0, 273.26, 480.0, 519.19, 463.1, 513.44, 470.29, 461.66, 425.71, 438.65, 419.96, 322.16, 414.2, 266.07]], "area": 11879.468450000004, "iscrowd": 0, "image_id": 347972, "bbox": [414.2, 257.44, 65.8, 261.75], "category_id": 7, "id": 173448, "split": "val", "sentences": [{"tokens": ["a", "green", "and", "orange", "traincar", "standing", "to", "the", "left", "of", "the", "fully", "visible", "traincar"], "raw": "A green and orange traincar standing to the left of the fully visible traincar", "sent_id": 39800, "sent": "a green and orange traincar standing to the left of the fully visible traincar"}, {"tokens": ["green", "boxcar", "on", "the", "other", "side", "of", "the", "track"], "raw": "Green boxcar on the other side of the track", "sent_id": 39801, "sent": "green boxcar on the other side of the track"}], "file_name": "COCO_train2014_000000347972_173448.jpg", "ann_id": 173448, "sent_ids": [39800, 39801], "ref_id": 20287}, {"segmentation": [[41.16, 19.15, 87.11, 0.96, 142.64, 0.0, 148.38, 44.99, 152.21, 108.18, 91.9, 134.02, 81.37, 128.28]], "area": 10737.507150000001, "iscrowd": 0, "image_id": 493707, "bbox": [41.16, 0.0, 111.05, 134.02], "category_id": 47, "id": 679170, "split": "val", "sentences": [{"tokens": ["a", "glass", "wirh", "a", "juice"], "raw": "A GLASS WIRH A JUICE", "sent_id": 39813, "sent": "a glass wirh a juice"}, {"tokens": ["a", "yellow", "-", "colored", "beverage", "in", "a", "glass"], "raw": "A yellow-colored beverage in a glass.", "sent_id": 39814, "sent": "a yellow - colored beverage in a glass"}], "file_name": "COCO_train2014_000000493707_679170.jpg", "ann_id": 679170, "sent_ids": [39813, 39814], "ref_id": 20292}, {"segmentation": [[0.0, 220.62, 27.85, 197.77, 45.69, 187.06, 54.26, 182.06, 82.11, 219.91, 114.24, 217.76, 142.8, 215.62, 154.22, 217.76, 158.5, 220.62, 149.94, 238.47, 160.65, 249.89, 165.64, 257.75, 162.79, 319.15, 162.79, 332.0, 2.14, 332.0]], "area": 19761.91775, "iscrowd": 0, "image_id": 247181, "bbox": [0.0, 182.06, 165.64, 149.94], "category_id": 63, "id": 116939, "split": "val", "sentences": [{"tokens": ["a", "leather", "couch", "with", "a", "plaid", "throw", "on", "the", "back"], "raw": "A leather couch with a plaid throw on the back", "sent_id": 39823, "sent": "a leather couch with a plaid throw on the back"}, {"tokens": ["a", "brown", "leather", "sofa", "with", "a", "brown", ",", "red", ",", "and", "white", "blanket", "laying", "on", "the", "back", "of", "it"], "raw": "A brown leather sofa with a brown, red, and white blanket laying on the back of it.", "sent_id": 39824, "sent": "a brown leather sofa with a brown , red , and white blanket laying on the back of it"}], "file_name": "COCO_train2014_000000247181_116939.jpg", "ann_id": 116939, "sent_ids": [39823, 39824], "ref_id": 20296}, {"segmentation": [[204.89, 158.01, 207.13, 162.94, 207.13, 188.02, 187.87, 189.36, 177.57, 202.34, 176.23, 210.4, 224.6, 210.85, 258.63, 205.93, 254.6, 186.67, 246.98, 179.5, 242.06, 177.27, 238.03, 177.27, 231.76, 183.98, 231.76, 176.37, 241.16, 172.79, 238.92, 170.55, 234.0, 169.2, 224.15, 169.2, 221.91, 170.1, 223.25, 177.27, 227.28, 179.06, 225.49, 198.32, 219.67, 196.52, 219.67, 191.6, 218.32, 161.59, 218.32, 154.88, 218.32, 152.64, 215.64, 145.92, 218.77, 140.54, 216.53, 128.0, 211.61, 130.69, 208.02, 145.03, 208.02, 153.08], [177.57, 223.84, 190.11, 237.72, 204.0, 241.75, 222.36, 238.62, 228.62, 229.66, 237.13, 250.71, 245.64, 252.05, 251.91, 244.89, 254.6, 232.8, 260.42, 230.11, 261.32, 224.29, 255.94, 216.68, 176.23, 222.94]], "area": 4155.8511, "iscrowd": 0, "image_id": 204420, "bbox": [176.23, 128.0, 85.09, 124.05], "category_id": 2, "id": 129734, "split": "val", "sentences": [{"tokens": ["a", "bicycle", "is", "standing", "without", "a", "person"], "raw": "a bicycle is standing without a person", "sent_id": 39844, "sent": "a bicycle is standing without a person"}, {"tokens": ["a", "yellow", "bicycle", "standing", "in", "the", "grass"], "raw": "A yellow bicycle standing in the grass", "sent_id": 39845, "sent": "a yellow bicycle standing in the grass"}], "file_name": "COCO_train2014_000000204420_129734.jpg", "ann_id": 129734, "sent_ids": [39844, 39845], "ref_id": 20302}, {"segmentation": [[16.27, 206.38, 0.0, 425.82, 68.46, 436.53, 109.94, 340.19, 103.25, 321.45, 103.25, 294.69, 128.67, 258.56, 132.68, 237.15, 83.17, 201.03]], "area": 21821.97615, "iscrowd": 0, "image_id": 187563, "bbox": [0.0, 201.03, 132.68, 235.5], "category_id": 10, "id": 1804697, "split": "val", "sentences": [{"tokens": ["a", "cross", "light", "that", "is", "lit", "up", "to", "say", "do", "not", "cross"], "raw": "A cross light that is lit up to say do not cross.", "sent_id": 39879, "sent": "a cross light that is lit up to say do not cross"}, {"tokens": ["a", "pedestrian", "do", "not", "walk", "symbol", "of", "a", "red", "standing", "man"], "raw": "A pedestrian do not walk symbol of a red standing man.", "sent_id": 39880, "sent": "a pedestrian do not walk symbol of a red standing man"}], "file_name": "COCO_train2014_000000187563_1804697.jpg", "ann_id": 1804697, "sent_ids": [39879, 39880], "ref_id": 20316}, {"segmentation": [[272.35, 144.02, 279.74, 140.52, 288.31, 132.74, 297.26, 134.29, 308.55, 141.69, 313.22, 138.96, 313.61, 144.8, 314.38, 150.25, 315.16, 157.26, 314.77, 163.49, 315.16, 165.43, 318.67, 166.99, 320.22, 167.77, 324.12, 170.1, 327.62, 173.61, 327.62, 174.38, 333.07, 179.45, 344.75, 180.22, 349.81, 178.28, 357.2, 177.11, 365.77, 184.89, 362.26, 197.74, 362.65, 210.2, 364.21, 214.87, 360.32, 219.15, 361.09, 228.49, 364.21, 250.68, 369.27, 257.29, 354.87, 260.41, 352.14, 242.89, 354.87, 228.49, 347.86, 233.16, 341.24, 240.56, 326.84, 242.5, 327.62, 256.52, 321.39, 253.4, 321.39, 243.67, 319.83, 243.67, 307.77, 245.23, 301.93, 253.01, 303.1, 272.86, 299.59, 284.93, 288.31, 281.82, 289.86, 268.97, 290.64, 254.18, 296.09, 245.62, 295.31, 241.72, 288.31, 234.33, 282.47, 226.15, 281.69, 243.28, 281.69, 252.23, 278.18, 256.13, 274.68, 227.32, 273.9, 213.7, 273.9, 192.29, 273.9, 186.84, 272.74, 178.28, 273.12, 170.88, 272.74, 146.75]], "area": 8082.957300000002, "iscrowd": 0, "image_id": 204339, "bbox": [272.35, 132.74, 96.92, 152.19], "category_id": 62, "id": 100854, "split": "val", "sentences": [{"tokens": ["a", "brown", "antique", "wooden", "chair", "in", "a", "living", "room"], "raw": "A brown antique wooden chair in a living room.", "sent_id": 39902, "sent": "a brown antique wooden chair in a living room"}, {"tokens": ["wooden", "carved", "chair", "with", "a", "brown", "cat", "laying", "in", "it"], "raw": "Wooden carved chair with a brown cat laying in it.", "sent_id": 39903, "sent": "wooden carved chair with a brown cat laying in it"}], "file_name": "COCO_train2014_000000204339_100854.jpg", "ann_id": 100854, "sent_ids": [39902, 39903], "ref_id": 20325}, {"segmentation": [[177.93, 108.97, 183.45, 70.34, 197.24, 60.69, 205.52, 57.93, 215.17, 55.17, 227.59, 53.79, 237.24, 55.17, 251.03, 55.17, 260.69, 53.79, 275.86, 55.17, 289.66, 59.31, 303.45, 75.86, 306.21, 86.9, 310.34, 111.72, 307.59, 153.1, 307.59, 173.79, 304.83, 194.48, 297.93, 249.66, 299.31, 299.31, 307.59, 303.45, 315.86, 314.48, 311.72, 336.55, 307.59, 342.07, 284.14, 343.45, 252.41, 346.21, 237.24, 361.38, 217.93, 377.93, 194.48, 384.83, 173.79, 383.45, 169.66, 364.14, 183.45, 343.45, 187.59, 326.9, 177.93, 310.34, 184.83, 245.52, 183.45, 223.45, 183.45, 206.9, 177.93, 195.86, 190.34, 177.93, 205.52, 164.14, 224.83, 148.97, 235.86, 139.31, 241.38, 132.41, 246.9, 120.0, 242.76, 114.48, 238.62, 108.97, 226.21, 96.55, 217.93, 93.79, 198.62, 91.03]], "area": 33754.10464999998, "iscrowd": 0, "image_id": 104692, "bbox": [169.66, 53.79, 146.2, 331.04], "category_id": 16, "id": 37897, "split": "val", "sentences": [{"tokens": ["an", "older", "bird", "with", "a", "yellow", "beak", "and", "a", "red", "patch", "of", "feathers", "sitting", "next", "to", "a", "grey", "bird", "on", "a", "tree", "branch"], "raw": "An older bird with a yellow beak and a red patch of feathers sitting next to a grey bird on a tree branch", "sent_id": 40019, "sent": "an older bird with a yellow beak and a red patch of feathers sitting next to a grey bird on a tree branch"}, {"tokens": ["bird", "with", "a", "rounded", "yellow", "beak"], "raw": "bird with a rounded yellow beak", "sent_id": 40020, "sent": "bird with a rounded yellow beak"}], "file_name": "COCO_train2014_000000104692_37897.jpg", "ann_id": 37897, "sent_ids": [40019, 40020], "ref_id": 20374}, {"segmentation": [[258.01, 1.91, 239.07, 42.7, 237.54, 57.24, 234.57, 225.94, 243.85, 224.78, 248.48, 232.89, 253.7, 232.31, 262.4, 219.56, 271.68, 216.66, 276.32, 215.5, 267.62, 241.01, 262.4, 257.83, 261.82, 261.31, 272.84, 258.99, 276.89, 241.01, 295.45, 242.75, 303.57, 254.35, 337.78, 241.01, 340.09, 123.31, 340.81, 94.32, 335.33, 95.01, 332.59, 90.9, 337.39, 78.57, 335.33, 73.09, 336.7, 64.19, 325.75, 34.75, 323.69, 21.05, 333.02, 13.04, 329.28, 0.77, 258.86, 1.83]], "area": 23370.684999999994, "iscrowd": 0, "image_id": 477580, "bbox": [234.57, 0.77, 106.24, 260.54], "category_id": 44, "id": 79534, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "red", "wine", ",", "labeled", "chocovine", ",", "which", "has", "a", "picture", "of", "a", "windmill", "on", "it"], "raw": "A bottle of red wine, labeled ChocoVine, which has a picture of a windmill on it.", "sent_id": 40029, "sent": "a bottle of red wine , labeled chocovine , which has a picture of a windmill on it"}, {"tokens": ["a", "bottle", "of", "wine", "which", "is", "kept", "in", "the", "middle", "of", "vegetables"], "raw": "A bottle of wine which is kept in the  middle of vegetables", "sent_id": 40030, "sent": "a bottle of wine which is kept in the middle of vegetables"}], "file_name": "COCO_train2014_000000477580_79534.jpg", "ann_id": 79534, "sent_ids": [40029, 40030], "ref_id": 20377}, {"segmentation": [[38.56, 0.96, 54.95, 136.89, 178.35, 106.04, 202.45, 103.15, 213.05, 99.3, 214.02, 1.93]], "area": 19507.7431, "iscrowd": 0, "image_id": 48707, "bbox": [38.56, 0.96, 175.46, 135.93], "category_id": 47, "id": 1508485, "split": "val", "sentences": [{"tokens": ["the", "flower", "on", "the", "table"], "raw": "The flower on the table.", "sent_id": 40035, "sent": "the flower on the table"}, {"tokens": ["a", "green", "blurry", "object", "that", "resembles", "a", "tree", "behind", "the", "main", "course"], "raw": "A green blurry object that resembles a tree behind the main course.", "sent_id": 40036, "sent": "a green blurry object that resembles a tree behind the main course"}], "file_name": "COCO_train2014_000000048707_1508485.jpg", "ann_id": 1508485, "sent_ids": [40035, 40036], "ref_id": 20378}, {"segmentation": [[29.87, 286.35, 33.99, 317.25, 28.84, 351.24, 25.75, 375.97, 59.74, 374.94, 103.0, 384.21, 144.21, 389.36, 158.63, 385.24, 213.22, 356.39, 245.15, 339.91, 247.21, 311.07, 245.15, 305.92, 245.15, 302.83, 283.26, 290.47, 279.14, 268.84, 250.3, 261.63, 234.85, 260.6, 221.46, 231.76, 186.44, 233.82, 179.23, 236.91, 132.88, 241.03, 104.03, 241.03, 95.79, 236.91, 84.46, 242.06, 72.1, 242.06, 60.77, 238.97, 52.53, 243.09, 42.23, 251.33, 40.17, 256.48, 38.11, 281.2, 27.81, 286.35], [256.48, 330.64, 266.78, 327.55, 267.81, 313.13, 253.39, 313.13, 255.45, 327.55]], "area": 29654.6683, "iscrowd": 0, "image_id": 52518, "bbox": [25.75, 231.76, 257.51, 157.6], "category_id": 63, "id": 112551, "split": "val", "sentences": [{"tokens": ["white", "couch"], "raw": "white couch", "sent_id": 40164, "sent": "white couch"}, {"tokens": ["a", "couch", "against", "the", "wall"], "raw": "A couch against the wall.", "sent_id": 40165, "sent": "a couch against the wall"}], "file_name": "COCO_train2014_000000052518_112551.jpg", "ann_id": 112551, "sent_ids": [40164, 40165], "ref_id": 20427}, {"segmentation": [[283.01, 396.22, 270.04, 399.76, 268.86, 385.61, 273.58, 380.89, 258.25, 363.2, 253.53, 351.41, 261.79, 344.33, 283.01, 337.26, 284.19, 331.36, 287.73, 327.82, 284.19, 311.31, 277.12, 294.81, 281.83, 293.63, 277.12, 278.3, 267.68, 278.3, 253.53, 270.04, 229.95, 242.92, 221.69, 245.28, 216.98, 231.13, 219.34, 228.77, 222.87, 233.49, 231.13, 240.56, 234.66, 240.56, 235.84, 239.38, 228.77, 225.23, 245.28, 238.2, 261.79, 251.17, 281.83, 253.53, 297.16, 253.53, 299.52, 253.53, 298.34, 235.84, 306.6, 226.41, 304.24, 214.62, 312.49, 207.54, 323.11, 201.65, 346.69, 202.83, 365.56, 221.69, 363.2, 245.28, 347.87, 257.07, 347.87, 260.61, 359.66, 272.4, 369.1, 287.73, 373.81, 313.67, 363.2, 340.79, 356.12, 340.79, 371.45, 364.38, 366.74, 390.32, 345.51, 386.78, 326.64, 398.58, 321.93, 398.58, 319.57, 411.55, 308.96, 400.94, 303.06, 398.58, 312.49, 385.61, 321.93, 378.53, 316.03, 373.81, 300.7, 379.71, 299.52, 380.89, 303.06, 387.96, 300.7, 392.68, 292.45, 393.86]], "area": 16756.349449999998, "iscrowd": 0, "image_id": 295613, "bbox": [216.98, 201.65, 156.83, 209.9], "category_id": 1, "id": 2156722, "split": "val", "sentences": [{"tokens": ["baby", "wearing", "overalls"], "raw": "Baby wearing overalls.", "sent_id": 40325, "sent": "baby wearing overalls"}, {"tokens": ["the", "baby", "holding", "the", "phone"], "raw": "The baby holding the phone.", "sent_id": 40326, "sent": "the baby holding the phone"}], "file_name": "COCO_train2014_000000295613_2156722.jpg", "ann_id": 2156722, "sent_ids": [40325, 40326], "ref_id": 20486}, {"segmentation": [[159.31, 469.35, 150.6, 454.54, 153.21, 447.57, 101.81, 435.38, 97.45, 426.66, 102.68, 422.31, 120.98, 433.63, 154.08, 440.6, 152.34, 429.28, 160.18, 426.66, 168.89, 424.92, 181.09, 393.56, 207.22, 373.52, 229.0, 357.84, 246.42, 346.52, 272.56, 340.42, 304.79, 342.16, 333.54, 350.87, 364.9, 374.39, 373.62, 380.49, 371.87, 387.46, 316.12, 388.33, 295.21, 386.59, 269.07, 394.43, 253.39, 420.57, 242.94, 433.63, 242.94, 444.09, 243.81, 452.8, 162.79, 468.48]], "area": 12894.30625, "iscrowd": 0, "image_id": 562456, "bbox": [97.45, 340.42, 276.17, 128.93], "category_id": 54, "id": 311309, "split": "val", "sentences": [{"tokens": ["left", "half", "of", "sandwich", "on", "plate", "closest", "to", "silverware"], "raw": "Left half of sandwich on plate closest to silverware.", "sent_id": 40391, "sent": "left half of sandwich on plate closest to silverware"}, {"tokens": ["the", "half", "of", "the", "sandwich", "closer", "to", "the", "silverware"], "raw": "The half of the sandwich closer to the silverware.", "sent_id": 40392, "sent": "the half of the sandwich closer to the silverware"}], "file_name": "COCO_train2014_000000562456_311309.jpg", "ann_id": 311309, "sent_ids": [40391, 40392], "ref_id": 20511}, {"segmentation": [[137.53, 235.17, 204.92, 261.3, 314.94, 270.93, 427.71, 265.43, 464.84, 237.92, 460.72, 209.04, 416.71, 182.91, 330.07, 180.16, 277.81, 180.16, 211.79, 180.16, 156.78, 184.29, 137.53, 184.29]], "area": 25438.986, "iscrowd": 0, "image_id": 153814, "bbox": [137.53, 180.16, 327.31, 90.77], "category_id": 59, "id": 1072500, "split": "val", "sentences": [{"tokens": ["a", "large", "pizza", "in", "front", "of", "a", "woman", "and", "behind", "another", "pizza"], "raw": "A large pizza in front of a woman and behind another pizza", "sent_id": 40454, "sent": "a large pizza in front of a woman and behind another pizza"}, {"tokens": ["a", "pizza", "in", "front", "of", "a", "woman", "in", "a", "black", "tank", "top"], "raw": "A pizza in front of a woman in a black tank top.", "sent_id": 40455, "sent": "a pizza in front of a woman in a black tank top"}], "file_name": "COCO_train2014_000000153814_1072500.jpg", "ann_id": 1072500, "sent_ids": [40454, 40455], "ref_id": 20537}, {"segmentation": [[158.64, 229.73, 179.6, 216.26, 188.58, 204.29, 197.56, 186.33, 203.54, 161.64, 204.29, 153.4, 216.26, 145.17, 213.27, 132.45, 208.78, 121.98, 219.26, 102.52, 225.24, 98.78, 239.46, 101.02, 245.45, 107.01, 249.94, 115.99, 252.18, 126.47, 249.19, 133.2, 271.64, 144.42, 282.86, 152.66, 289.6, 165.38, 288.85, 180.34, 288.85, 193.07, 270.14, 203.54, 250.69, 199.05, 234.97, 209.53, 226.74, 222.25, 221.5, 236.47, 219.26, 243.2, 217.76, 254.43, 188.58, 254.43, 185.58, 302.32, 193.81, 326.27, 154.9, 329.26, 166.87, 316.54, 169.87, 309.8, 155.65, 309.8, 155.65, 229.73]], "area": 11859.5736, "iscrowd": 0, "image_id": 306561, "bbox": [154.9, 98.78, 134.7, 230.48], "category_id": 1, "id": 204788, "split": "val", "sentences": [{"tokens": ["man", "in", "a", "white", "long", "sleeve", "shirt", "wit", "a", "tie", "on"], "raw": "Man in a white long sleeve shirt wit a tie on.", "sent_id": 40543, "sent": "man in a white long sleeve shirt wit a tie on"}, {"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "black", "pants"], "raw": "A man in a white shirt and black pants", "sent_id": 40544, "sent": "a man in a white shirt and black pants"}], "file_name": "COCO_train2014_000000306561_204788.jpg", "ann_id": 204788, "sent_ids": [40543, 40544], "ref_id": 20572}, {"segmentation": [[445.59, 507.48, 438.71, 540.49, 429.09, 547.36, 385.08, 558.36, 380.95, 551.49, 367.2, 534.98, 357.57, 506.1, 385.08, 481.35, 389.2, 466.22, 360.32, 435.96, 346.57, 409.83, 353.45, 369.95, 358.95, 346.57, 352.07, 327.32, 346.57, 316.31, 336.94, 319.07, 316.31, 346.57, 305.31, 347.95, 302.56, 319.07, 302.56, 270.93, 319.07, 211.79, 358.95, 174.66, 336.94, 148.53, 323.19, 111.4, 347.95, 66.01, 391.96, 56.39, 419.46, 72.89, 435.96, 105.9, 435.96, 123.78, 433.21, 141.65, 433.21, 163.66, 444.22, 180.16, 442.84, 210.42, 457.97, 213.17, 467.6, 211.79, 475.85, 213.17, 495.1, 210.42, 504.73, 207.67, 510.23, 215.92, 511.6, 232.42, 506.1, 264.05, 507.48, 295.69, 512.98, 310.81, 510.23, 324.57, 496.48, 303.94, 486.85, 310.81, 490.98, 330.07, 495.1, 345.2, 500.6, 371.33, 504.73, 383.7, 448.34, 412.58, 426.34, 441.47, 462.09, 467.6, 507.48, 474.47, 517.11, 511.6, 514.36, 562.49, 510.23, 574.87, 474.47, 533.61, 455.22, 540.49]], "area": 64754.373000000014, "iscrowd": 0, "image_id": 119714, "bbox": [302.56, 56.39, 214.55, 518.48], "category_id": 1, "id": 531162, "split": "val", "sentences": [{"tokens": ["boy", "in", "a", "white", "abercrombie", "shirt", "with", "other", "boys"], "raw": "Boy in a white Abercrombie shirt with other boys.", "sent_id": 40553, "sent": "boy in a white abercrombie shirt with other boys"}, {"tokens": ["the", "boy", "with", "the", "abercrombie", "shirt"], "raw": "The boy with the Abercrombie shirt.", "sent_id": 40554, "sent": "the boy with the abercrombie shirt"}], "file_name": "COCO_train2014_000000119714_531162.jpg", "ann_id": 531162, "sent_ids": [40553, 40554], "ref_id": 20577}, {"segmentation": [[26.97, 183.43, 63.22, 175.43, 76.87, 177.78, 100.88, 185.79, 98.52, 193.79, 84.87, 193.32, 90.99, 210.74, 94.29, 230.98, 94.76, 249.34, 90.52, 260.17, 88.64, 279.94, 88.17, 287.47, 83.46, 297.83, 81.1, 302.54, 67.92, 295.0, 65.57, 288.41, 64.63, 274.76, 64.63, 271.0, 47.68, 269.11, 34.5, 248.87, 28.38, 227.68, 30.26, 216.86, 34.97, 210.74, 30.26, 199.44, 22.26, 189.08]], "area": 6095.239750000001, "iscrowd": 0, "image_id": 120782, "bbox": [22.26, 175.43, 78.62, 127.11], "category_id": 4, "id": 245508, "split": "val", "sentences": [{"tokens": ["a", "blue", "motorcycle", "next", "to", "a", "woman", "in", "jeans"], "raw": "A blue motorcycle next to a woman in jeans.", "sent_id": 40582, "sent": "a blue motorcycle next to a woman in jeans"}, {"tokens": ["a", "byek", "on", "foot", "path"], "raw": "a byek on foot path", "sent_id": 40583, "sent": "a byek on foot path"}], "file_name": "COCO_train2014_000000120782_245508.jpg", "ann_id": 245508, "sent_ids": [40582, 40583], "ref_id": 20588}, {"segmentation": [[189.55, 350.75, 345.62, 328.46, 306.89, 364.25, 174.3, 375.98, 189.55, 352.51], [384.34, 323.18, 407.22, 317.9, 363.8, 352.51, 352.66, 358.96, 337.4, 360.73, 384.34, 324.94], [450.05, 313.2, 516.93, 304.99, 487.6, 346.64, 394.31, 354.86]], "area": 7499.5976500000015, "iscrowd": 0, "image_id": 276874, "bbox": [174.3, 304.99, 342.63, 70.99], "category_id": 35, "id": 2202771, "split": "val", "sentences": [{"tokens": ["blue", "white", "and", "red", "skis", "near", "bottom", "of", "stack"], "raw": "blue white and red skis near bottom of stack", "sent_id": 40592, "sent": "blue white and red skis near bottom of stack"}, {"tokens": ["electric", "blue", "ski", "with", "#", "404", "writtin", "on", "it"], "raw": "Electric blue ski with #404 writtin on it.", "sent_id": 40593, "sent": "electric blue ski with # 404 writtin on it"}], "file_name": "COCO_train2014_000000276874_2202771.jpg", "ann_id": 2202771, "sent_ids": [40592, 40593], "ref_id": 20592}, {"segmentation": [[475.26, 190.81, 373.33, 201.48, 376.89, 311.7, 398.22, 320.0, 406.52, 297.48, 411.26, 290.37, 431.41, 285.63, 457.48, 277.33, 476.44, 271.41, 488.3, 269.04, 483.56, 194.37, 476.44, 187.26], [439.7, 304.59, 434.96, 324.74, 455.11, 336.59, 489.48, 344.89, 500.15, 343.7, 510.81, 340.15, 526.22, 328.3, 496.59, 317.63, 465.78, 311.7, 439.7, 306.96]], "area": 12501.557900000005, "iscrowd": 0, "image_id": 220037, "bbox": [373.33, 187.26, 152.89, 157.63], "category_id": 63, "id": 2224011, "split": "val", "sentences": [{"tokens": ["the", "empty", "booth", ",", "behind", "a", "empty", "table"], "raw": "The empty booth, behind a empty table.", "sent_id": 40620, "sent": "the empty booth , behind a empty table"}, {"tokens": ["empty", "booth"], "raw": "empty booth", "sent_id": 40621, "sent": "empty booth"}], "file_name": "COCO_train2014_000000220037_2224011.jpg", "ann_id": 2224011, "sent_ids": [40620, 40621], "ref_id": 20602}, {"segmentation": [[20.31, 253.77, 15.03, 235.29, 17.01, 179.19, 18.33, 161.38, 12.39, 158.74, 25.59, 93.4, 60.57, 80.86, 71.13, 81.52, 72.45, 87.46, 234.14, 93.4, 222.26, 148.84, 221.6, 202.95, 223.58, 229.35, 224.24, 255.09, 157.58, 255.09, 141.08, 262.35, 121.94, 263.01, 113.37, 257.07, 26.91, 258.39, 20.97, 251.79]], "area": 34766.288799999995, "iscrowd": 0, "image_id": 358289, "bbox": [12.39, 80.86, 221.75, 182.15], "category_id": 6, "id": 248319, "split": "val", "sentences": [{"tokens": ["white", "and", "blue", "bus", "with", "tan", "fox", "banner"], "raw": "White and blue bus with Tan fox banner.", "sent_id": 40642, "sent": "white and blue bus with tan fox banner"}], "file_name": "COCO_train2014_000000358289_248319.jpg", "ann_id": 248319, "sent_ids": [40642], "ref_id": 20609}, {"segmentation": [[497.04, 61.51, 329.14, 73.14, 329.14, 73.14, 319.17, 101.4, 319.17, 206.13, 347.43, 222.75, 500.36, 217.77]], "area": 27106.882000000005, "iscrowd": 0, "image_id": 500662, "bbox": [319.17, 61.51, 181.19, 161.24], "category_id": 33, "id": 1841793, "split": "val", "sentences": [{"tokens": ["luggage", "with", "colorful", "stripes", "on", "a", "green", "table"], "raw": "Luggage with colorful stripes on a green table.", "sent_id": 40647, "sent": "luggage with colorful stripes on a green table"}, {"tokens": ["a", "striped", "suitcase"], "raw": "A striped suitcase.", "sent_id": 40648, "sent": "a striped suitcase"}], "file_name": "COCO_train2014_000000500662_1841793.jpg", "ann_id": 1841793, "sent_ids": [40647, 40648], "ref_id": 20611}, {"segmentation": [[380.9, 369.55, 365.42, 337.55, 363.35, 316.9, 362.32, 296.26, 358.19, 280.77, 345.81, 249.81, 340.65, 222.97, 347.87, 193.03, 353.03, 179.61, 368.52, 161.03, 379.87, 147.61, 406.71, 136.26, 414.97, 135.23, 445.94, 142.45, 455.23, 149.68, 471.74, 171.35, 475.87, 180.65, 482.06, 196.13, 488.26, 200.26, 502.71, 206.45, 515.1, 209.55, 527.48, 205.42, 529.55, 208.52, 529.55, 215.74, 524.39, 227.1, 521.29, 231.23, 525.42, 244.65, 525.42, 252.9, 524.39, 260.13, 519.23, 272.52, 514.06, 279.74, 507.87, 292.13, 503.74, 297.29, 499.61, 305.55, 497.55, 309.68, 496.52, 314.84, 493.42, 325.16, 490.32, 334.45, 485.16, 347.87, 478.97, 358.19, 473.81, 366.45, 468.65, 384.0, 462.45, 387.1, 459.35, 392.26, 443.87, 393.29, 412.9, 379.87, 408.77, 368.52, 406.71, 331.35, 403.61, 328.26, 401.55, 339.61, 402.58, 352.0, 403.61, 377.81, 381.94, 373.68]], "area": 32750.24865000001, "iscrowd": 0, "image_id": 473500, "bbox": [340.65, 135.23, 188.9, 258.06], "category_id": 17, "id": 52926, "split": "val", "sentences": [{"tokens": ["orange", "tabby", "cat", "standing", "in", "a", "sink"], "raw": "Orange tabby cat standing in a sink.", "sent_id": 40651, "sent": "orange tabby cat standing in a sink"}, {"tokens": ["a", "domestic", "cat", "stands", "in", "a", "sink", "in", "the", "bathroom", "while", "another", "cat", "sleeps", "on", "top", "of", "the", "toilet"], "raw": "A domestic cat stands in a sink in the bathroom while another cat sleeps on top of the toilet.", "sent_id": 40652, "sent": "a domestic cat stands in a sink in the bathroom while another cat sleeps on top of the toilet"}], "file_name": "COCO_train2014_000000473500_52926.jpg", "ann_id": 52926, "sent_ids": [40651, 40652], "ref_id": 20613}, {"segmentation": [[378.61, 241.62, 368.9, 200.63, 360.27, 170.43, 358.11, 153.17, 361.35, 135.91, 372.13, 124.04, 385.08, 117.57, 398.02, 114.34, 405.57, 114.34, 415.28, 114.34, 418.52, 115.42, 429.3, 126.2, 437.93, 140.22, 441.17, 156.4, 447.64, 176.9, 451.96, 198.47, 464.9, 217.89, 470.29, 235.15, 471.37, 244.85, 496.18, 268.58, 511.28, 302.02, 512.36, 337.62, 512.36, 376.45, 508.04, 402.34, 509.12, 440.09, 505.89, 450.88, 503.73, 458.43, 500.49, 472.45, 339.78, 473.53, 338.7, 460.58, 344.09, 430.38, 348.4, 419.6, 352.72, 400.18, 354.88, 385.08, 363.51, 354.88, 364.58, 345.17, 366.74, 314.97, 368.9, 295.55, 373.21, 261.03, 374.29, 240.54, 367.82, 223.28]], "area": 44205.22485, "iscrowd": 0, "image_id": 513683, "bbox": [338.7, 114.34, 173.66, 359.19], "category_id": 1, "id": 1708352, "split": "val", "sentences": [{"tokens": ["the", "lady", "in", "white", "shirt"], "raw": "the lady in white shirt", "sent_id": 40768, "sent": "the lady in white shirt"}, {"tokens": ["woman", "drinking", "wine"], "raw": "woman drinking wine", "sent_id": 40769, "sent": "woman drinking wine"}], "file_name": "COCO_train2014_000000513683_1708352.jpg", "ann_id": 1708352, "sent_ids": [40768, 40769], "ref_id": 20657}, {"segmentation": [[442.33, 204.05, 464.93, 148.09, 487.53, 97.51, 515.52, 83.52, 549.96, 74.91, 549.96, 53.38, 555.34, 31.86, 565.02, 18.94, 587.62, 10.33, 615.61, 22.17, 626.37, 36.16, 628.52, 57.69, 628.52, 65.22, 627.44, 74.91, 615.61, 91.05, 637.13, 96.43, 640.0, 101.81, 640.0, 235.26, 626.37, 238.49, 600.54, 243.87, 559.64, 244.95, 513.36, 246.03, 445.56, 237.42, 435.87, 225.58]], "area": 33124.37965, "iscrowd": 0, "image_id": 578523, "bbox": [435.87, 10.33, 204.13, 235.7], "category_id": 1, "id": 558691, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "mustache"], "raw": "The man with the mustache", "sent_id": 40774, "sent": "the man with the mustache"}, {"tokens": ["a", "man", "wearing", "glasses", "and", "a", "pin", "striped", "shirt", "is", "smiling"], "raw": "A man wearing glasses and a pin striped shirt is smiling.", "sent_id": 40775, "sent": "a man wearing glasses and a pin striped shirt is smiling"}], "file_name": "COCO_train2014_000000578523_558691.jpg", "ann_id": 558691, "sent_ids": [40774, 40775], "ref_id": 20660}, {"segmentation": [[112.03, 35.37, 87.27, 34.75, 74.89, 39.7, 68.09, 47.13, 60.66, 65.08, 65.61, 66.32, 69.32, 63.84, 73.66, 58.89, 86.65, 57.65, 94.08, 62.6, 91.61, 66.94, 77.37, 76.84, 64.37, 89.84, 53.23, 102.22, 32.19, 105.93, 19.19, 106.55, 22.9, 126.36, 42.71, 131.31, 59.42, 139.35, 95.94, 151.73, 140.5, 160.4, 156.6, 168.44, 180.74, 176.49, 183.83, 160.4, 182.59, 133.16, 181.97, 112.74, 168.36, 93.55, 160.93, 84.89, 155.98, 76.84, 159.69, 71.89, 183.83, 76.22, 189.4, 74.36, 191.88, 68.79, 191.88, 61.37, 185.69, 47.75, 178.88, 40.94, 159.07, 35.37, 148.55, 36.61, 137.41, 37.23]], "area": 14762.317199999998, "iscrowd": 0, "image_id": 498297, "bbox": [19.19, 34.75, 172.69, 141.74], "category_id": 20, "id": 62942, "split": "val", "sentences": [{"tokens": ["a", "sheep", "to", "the", "left", "of", "the", "picture"], "raw": "a sheep to the left of the picture", "sent_id": 40778, "sent": "a sheep to the left of the picture"}, {"tokens": ["a", "horned", "sheep", "to", "the", "left", "of", "two", "other", "horned", "sheep"], "raw": "A horned sheep to the left of two other horned sheep.", "sent_id": 40779, "sent": "a horned sheep to the left of two other horned sheep"}], "file_name": "COCO_train2014_000000498297_62942.jpg", "ann_id": 62942, "sent_ids": [40778, 40779], "ref_id": 20662}, {"segmentation": [[492.33, 322.84, 492.33, 301.26, 492.33, 293.03, 544.75, 282.75, 542.7, 274.53, 537.56, 271.45, 547.84, 264.25, 563.25, 259.11, 636.23, 259.11, 638.29, 270.42, 637.26, 330.04, 636.23, 373.2, 611.56, 376.29, 591.01, 370.12, 582.78, 363.95, 589.98, 352.65, 576.62, 348.54, 560.17, 341.34, 548.87, 321.81, 536.53, 306.39, 506.72, 312.56, 506.72, 312.56]], "area": 10446.758200000002, "iscrowd": 0, "image_id": 323133, "bbox": [492.33, 259.11, 145.96, 117.18], "category_id": 63, "id": 116641, "split": "val", "sentences": [{"tokens": ["the", "bed", "and", "pillow", "next", "to", "the", "window", "on", "the", "right"], "raw": "The bed and pillow next to the window on the right", "sent_id": 40784, "sent": "the bed and pillow next to the window on the right"}, {"tokens": ["a", "gray", "ottoman"], "raw": "a gray ottoman", "sent_id": 40785, "sent": "a gray ottoman"}], "file_name": "COCO_train2014_000000323133_116641.jpg", "ann_id": 116641, "sent_ids": [40784, 40785], "ref_id": 20665}, {"segmentation": [[138.2, 20.22, 219.94, 103.65, 251.12, 160.96, 249.44, 180.34, 264.61, 266.29, 247.75, 293.26, 226.69, 290.73, 179.49, 230.9, 177.81, 186.24, 125.56, 135.67, 121.35, 16.85]], "area": 19657.092049999996, "iscrowd": 0, "image_id": 24404, "bbox": [121.35, 16.85, 143.26, 276.41], "category_id": 24, "id": 588900, "split": "val", "sentences": [{"tokens": ["the", "zebra", "with", "no", "greenery", "covering", "part", "of", "him", "or", "her"], "raw": "The zebra with no greenery covering part of him or her.", "sent_id": 40793, "sent": "the zebra with no greenery covering part of him or her"}, {"tokens": ["larger", "zebra", "on", "left"], "raw": "Larger zebra on left.", "sent_id": 40794, "sent": "larger zebra on left"}], "file_name": "COCO_train2014_000000024404_588900.jpg", "ann_id": 588900, "sent_ids": [40793, 40794], "ref_id": 20669}, {"segmentation": [[327.51, 191.85, 334.91, 184.45, 347.97, 184.45, 343.18, 161.38, 358.85, 153.98, 374.52, 157.9, 379.31, 182.27, 386.27, 182.71, 391.06, 166.6, 398.02, 159.64, 411.08, 160.95, 416.74, 172.26, 417.17, 180.1, 423.27, 184.01, 426.32, 195.33, 429.36, 221.45, 447.64, 296.62, 453.74, 339.71, 447.64, 360.6, 438.5, 358.86, 433.72, 359.73, 421.96, 361.91, 415.87, 354.07, 362.77, 260.17, 340.13, 219.68]], "area": 13846.603350000005, "iscrowd": 0, "image_id": 325545, "bbox": [327.51, 153.98, 126.23, 207.93], "category_id": 57, "id": 1063269, "split": "val", "sentences": [{"tokens": ["a", "pile", "of", "carrots", "peeled", "on", "a", "cutting", "board"], "raw": "A pile of carrots peeled on a cutting board.", "sent_id": 40897, "sent": "a pile of carrots peeled on a cutting board"}, {"tokens": ["peeled", "carrots", "laying", "on", "top", "of", "a", "cutting", "board"], "raw": "Peeled carrots laying on top of a cutting board.", "sent_id": 40898, "sent": "peeled carrots laying on top of a cutting board"}], "file_name": "COCO_train2014_000000325545_1063269.jpg", "ann_id": 1063269, "sent_ids": [40897, 40898], "ref_id": 20715}, {"segmentation": [[0.0, 195.72, 8.82, 201.36, 16.07, 217.47, 24.12, 227.95, 45.07, 240.03, 76.49, 251.31, 100.66, 261.78, 101.46, 273.87, 87.77, 265.81, 54.74, 262.59, 49.1, 265.81, 35.4, 260.98, 40.24, 281.12, 42.65, 295.62, 65.21, 320.59, 51.51, 381.01, 40.24, 379.4, 42.65, 392.29, 29.76, 399.54, 12.04, 392.29, 6.4, 379.4, 22.51, 368.93, 35.4, 334.29, 16.87, 319.78, 3.98, 326.23, 6.4, 384.23, 0.76, 390.68]], "area": 8131.312400000001, "iscrowd": 0, "image_id": 105358, "bbox": [0.0, 195.72, 101.46, 203.82], "category_id": 1, "id": 461754, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "black", "t", "-", "shirt", "sitting", "with", "his", "legs", "open"], "raw": "A man wearing black t-shirt sitting with his legs open", "sent_id": 40948, "sent": "a man wearing black t - shirt sitting with his legs open"}, {"tokens": ["man", "sitting", "in", "chair", "holding", "onto", "back", "of", "couch"], "raw": "Man sitting in chair holding onto back of couch.", "sent_id": 40949, "sent": "man sitting in chair holding onto back of couch"}], "file_name": "COCO_train2014_000000105358_461754.jpg", "ann_id": 461754, "sent_ids": [40948, 40949], "ref_id": 20739}, {"segmentation": [[66.55, 44.06, 127.53, 63.77, 229.73, 116.98, 334.46, 169.34, 434.97, 206.5, 442.57, 227.62, 440.03, 236.06, 436.66, 245.35, 432.43, 255.49, 418.07, 254.65, 417.23, 271.54, 405.41, 292.65, 353.04, 276.6, 248.31, 234.38, 219.59, 211.57, 205.24, 201.44, 138.51, 180.32, 127.53, 167.65, 57.43, 138.09, 21.11, 121.2, 32.94, 91.64, 57.43, 90.79, 55.74, 84.04, 44.76, 78.13, 48.99, 67.15, 54.05, 66.3, 54.9, 60.39]], "area": 38964.009550000024, "iscrowd": 0, "image_id": 312282, "bbox": [21.11, 44.06, 421.46, 248.59], "category_id": 54, "id": 310567, "split": "val", "sentences": [{"tokens": ["a", "grilled", "sandwich", "cut", "in", "half"], "raw": "A grilled sandwich cut in half", "sent_id": 41003, "sent": "a grilled sandwich cut in half"}, {"tokens": ["a", "sandwish", "on", "a", "plate", ",", "on", "the", "table"], "raw": "A sandwish on a plate, on the table", "sent_id": 41004, "sent": "a sandwish on a plate , on the table"}], "file_name": "COCO_train2014_000000312282_310567.jpg", "ann_id": 310567, "sent_ids": [41003, 41004], "ref_id": 20759}, {"segmentation": [[258.23, 279.75, 251.06, 333.03, 246.96, 374.02, 252.08, 396.57, 252.08, 406.81, 249.01, 413.99, 239.78, 417.06, 237.73, 357.63, 236.71, 322.79, 238.76, 308.44, 232.61, 311.51, 220.31, 383.24, 217.24, 421.16, 209.04, 422.18, 209.04, 388.37, 212.12, 338.16, 210.07, 298.19, 196.75, 298.19, 195.72, 307.42, 191.62, 310.49, 185.47, 307.42, 179.33, 307.42, 161.91, 330.98, 158.83, 359.68, 151.66, 395.54, 145.51, 407.84, 134.24, 402.71, 137.31, 377.1, 136.29, 358.65, 129.11, 379.15, 121.94, 404.76, 111.69, 409.89, 110.67, 398.62, 117.84, 346.36, 125.02, 327.91, 129.11, 310.49, 136.29, 249.01, 159.86, 228.51, 190.6, 202.89, 205.97, 183.42, 223.39, 175.23, 257.2, 148.58, 294.09, 102.47, 312.54, 76.85, 323.81, 61.48, 327.91, 49.19, 337.13, 46.11, 346.36, 49.19, 351.48, 60.46, 357.63, 63.53, 363.78, 78.9, 378.12, 96.32, 382.22, 105.55, 371.97, 110.67, 337.13, 93.25, 299.22, 149.61, 268.48, 202.89, 259.25, 220.31, 258.23, 231.59, 261.3, 241.83, 268.48, 251.06, 256.18, 265.4]], "area": 26415.68910000001, "iscrowd": 0, "image_id": 77380, "bbox": [110.67, 46.11, 271.55, 376.07], "category_id": 25, "id": 597690, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "with", "its", "head", "up"], "raw": "a giraffe with its head up", "sent_id": 41050, "sent": "a giraffe with its head up"}, {"tokens": ["the", "giraffe", "that", "is", "standing", "tallest"], "raw": "the giraffe that is standing tallest", "sent_id": 41051, "sent": "the giraffe that is standing tallest"}], "file_name": "COCO_train2014_000000077380_597690.jpg", "ann_id": 597690, "sent_ids": [41050, 41051], "ref_id": 20778}, {"segmentation": [[241.62, 5.51, 224.36, 40.03, 189.84, 70.23, 184.09, 78.86, 188.4, 133.51, 174.02, 142.14, 146.7, 139.27, 138.07, 126.32, 123.69, 119.13, 126.56, 106.19, 149.57, 70.23, 166.83, 25.65, 174.02, 17.02, 179.78, 4.07]], "area": 7313.022499999998, "iscrowd": 0, "image_id": 1407, "bbox": [123.69, 4.07, 117.93, 138.07], "category_id": 1, "id": 1257503, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "black", "suit", "sitting"], "raw": "A man in a black suit sitting", "sent_id": 41054, "sent": "a man in a black suit sitting"}, {"tokens": ["the", "man", "to", "the", "far", "left", "of", "the", "guy", "in", "the", "wheelchair"], "raw": "The man to the far left of the guy in the wheelchair", "sent_id": 41055, "sent": "the man to the far left of the guy in the wheelchair"}], "file_name": "COCO_train2014_000000001407_1257503.jpg", "ann_id": 1257503, "sent_ids": [41054, 41055], "ref_id": 20779}, {"segmentation": [[351.91, 131.16, 304.73, 133.49, 304.73, 158.54, 297.74, 173.11, 292.5, 167.86, 289.0, 150.97, 276.77, 145.73, 272.11, 157.38, 277.35, 168.45, 287.83, 169.61, 293.08, 177.18, 277.93, 181.26, 270.36, 185.34, 270.36, 194.08, 294.83, 199.9, 294.83, 214.47, 295.41, 226.12, 295.41, 231.94, 293.66, 238.93, 285.5, 244.76, 282.59, 252.91, 282.59, 262.82, 283.17, 269.23, 289.0, 283.21, 279.68, 287.28, 273.27, 279.13, 279.68, 268.06, 282.59, 243.59, 279.1, 230.19, 270.94, 230.19, 266.86, 234.86, 258.13, 243.01, 256.38, 259.9, 262.2, 274.47, 271.52, 287.87, 279.68, 290.2, 290.16, 290.2, 293.08, 294.86, 297.74, 306.51, 300.07, 308.26, 311.14, 308.84, 312.88, 295.44, 323.37, 300.68, 328.61, 318.16, 334.44, 325.73, 353.08, 314.66, 357.74, 288.45, 383.37, 266.89, 378.13, 244.76, 364.73, 239.52, 363.57, 222.62, 365.9, 208.06, 379.29, 196.99, 386.87, 188.25, 386.87, 178.93, 386.87, 159.71, 368.81, 155.05, 363.57, 134.08]], "area": 15784.247999999998, "iscrowd": 0, "image_id": 395013, "bbox": [256.38, 131.16, 130.49, 194.57], "category_id": 4, "id": 151142, "split": "val", "sentences": [{"tokens": ["a", "police", "bike", "without", "red", "and", "blue", "lights", "on"], "raw": "a police bike without red and blue lights on", "sent_id": 41057, "sent": "a police bike without red and blue lights on"}], "file_name": "COCO_train2014_000000395013_151142.jpg", "ann_id": 151142, "sent_ids": [41057], "ref_id": 20781}, {"segmentation": [[1.0, 244.5, 2.0, 294.5, 25.0, 310.5, 68.0, 318.5, 119.0, 313.5, 162.0, 297.5, 194.0, 272.5, 215.0, 234.5, 203.0, 194.5, 165.0, 176.5, 140.0, 172.5, 112.0, 179.5, 72.0, 191.5, 45.0, 197.5, 32.0, 206.5, 11.0, 222.5, 18.0, 232.5, 24.0, 238.5, 18.0, 242.5, 7.0, 241.5, 2.0, 233.5, 5.0, 248.5]], "area": 23181.0, "iscrowd": 0, "image_id": 444344, "bbox": [1.0, 172.5, 214.0, 146.0], "category_id": 59, "id": 1077636, "split": "val", "sentences": [{"tokens": ["large", "pizza", "sitting", "on", "stand", "on", "the", "left", "side", "of", "the", "table"], "raw": "Large pizza sitting on stand on the left side of the table.", "sent_id": 41066, "sent": "large pizza sitting on stand on the left side of the table"}, {"tokens": ["pizza", "with", "green", "vegetables"], "raw": "Pizza with green vegetables", "sent_id": 41067, "sent": "pizza with green vegetables"}], "file_name": "COCO_train2014_000000444344_1077636.jpg", "ann_id": 1077636, "sent_ids": [41066, 41067], "ref_id": 20785}, {"segmentation": [[637.48, 207.1, 639.64, 467.06, 640.0, 471.37, 591.1, 471.37, 549.03, 429.3, 563.06, 389.39, 564.13, 303.1, 569.53, 278.29, 591.1, 241.62]], "area": 17402.184600000008, "iscrowd": 0, "image_id": 255016, "bbox": [549.03, 207.1, 90.97, 264.27], "category_id": 1, "id": 488832, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "the", "black", "shirt", "who", "'", "s", "shoulder", "is", "only", "seen"], "raw": "The person in the black shirt who's shoulder is only seen", "sent_id": 41154, "sent": "the person in the black shirt who ' s shoulder is only seen"}, {"tokens": ["black", "shirt", "and", "half", "of", "an", "arm"], "raw": "black shirt and half of an arm", "sent_id": 41155, "sent": "black shirt and half of an arm"}], "file_name": "COCO_train2014_000000255016_488832.jpg", "ann_id": 488832, "sent_ids": [41154, 41155], "ref_id": 20816}, {"segmentation": [[46.58, 203.96, 45.6, 193.69, 45.6, 188.31, 42.18, 171.19, 40.22, 167.77, 37.29, 161.9, 31.91, 161.41, 25.55, 161.41, 16.26, 161.9, 8.43, 170.21, 5.99, 173.64, 2.08, 181.95, 3.05, 193.2, 3.54, 196.13, 0.12, 203.96, 0.0, 209.83, 0.0, 239.66, 2.56, 267.54, 0.61, 319.87, 6.97, 361.93, 11.86, 347.75, 14.79, 328.18, 19.19, 308.13, 28.49, 279.28, 27.02, 260.69, 31.42, 250.91, 37.29, 243.08, 39.24, 236.73, 52.2, 232.18, 44.33, 215.33, 42.09, 201.84]], "area": 5599.730700000001, "iscrowd": 0, "image_id": 370727, "bbox": [0.0, 161.41, 52.2, 200.52], "category_id": 1, "id": 484738, "split": "val", "sentences": [{"tokens": ["man", "with", "his", "back", "to", "the", "camera", "in", "black", "jacket"], "raw": "Man with his back to the camera in black jacket", "sent_id": 41256, "sent": "man with his back to the camera in black jacket"}], "file_name": "COCO_train2014_000000370727_484738.jpg", "ann_id": 484738, "sent_ids": [41256], "ref_id": 20855}, {"segmentation": [[625.71, 129.53, 600.1, 98.8, 533.51, 85.63, 496.19, 120.02, 488.14, 158.07, 499.12, 189.53, 532.78, 185.87, 543.02, 171.97, 565.71, 175.63, 563.51, 189.53, 601.56, 208.56, 623.51, 183.68, 638.88, 168.31, 638.88, 123.68]], "area": 12495.3406, "iscrowd": 0, "image_id": 343158, "bbox": [488.14, 85.63, 150.74, 122.93], "category_id": 4, "id": 2048291, "split": "val", "sentences": [{"tokens": ["front", "wheel", "of", "the", "bike", "that", "'", "s", "not", "fully", "in", "the", "photo"], "raw": "Front wheel of the bike that's not fully in the photo.", "sent_id": 41357, "sent": "front wheel of the bike that ' s not fully in the photo"}, {"tokens": ["the", "tire", "of", "a", "partially", "visible", "bike", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the tire of a partially visible bike on the right in the right hand picture", "sent_id": 41358, "sent": "the tire of a partially visible bike on the right in the right hand picture"}], "file_name": "COCO_train2014_000000343158_2048291.jpg", "ann_id": 2048291, "sent_ids": [41357, 41358], "ref_id": 20892}, {"segmentation": [[212.14, 245.51, 232.5, 290.51, 226.07, 344.08, 244.29, 358.01, 257.14, 467.3, 300.0, 472.65, 290.36, 350.51, 295.71, 284.08, 303.21, 245.51, 290.36, 209.08, 283.93, 186.58, 273.21, 180.15, 247.5, 190.87, 242.14, 194.08, 244.29, 219.8, 242.14, 250.87, 218.57, 228.37]], "area": 15782.116050000002, "iscrowd": 0, "image_id": 392201, "bbox": [212.14, 180.15, 91.07, 292.5], "category_id": 1, "id": 193540, "split": "val", "sentences": [{"tokens": ["a", "man", "taking", "a", "photo", "next", "to", "a", "train"], "raw": "A man taking a photo next to a train", "sent_id": 41400, "sent": "a man taking a photo next to a train"}, {"tokens": ["a", "man", "standing", "in", "fron", "of", "a", "passenger", "train", "holding", "something", "in", "his", "hands"], "raw": "A man standing in fron of a passenger train holding something in his hands.", "sent_id": 41401, "sent": "a man standing in fron of a passenger train holding something in his hands"}], "file_name": "COCO_train2014_000000392201_193540.jpg", "ann_id": 193540, "sent_ids": [41400, 41401], "ref_id": 20907}, {"segmentation": [[178.46, 378.35, 181.88, 370.15, 179.83, 346.91, 177.09, 322.99, 175.73, 301.81, 176.41, 291.56, 185.29, 277.89, 207.16, 269.01, 231.08, 275.84, 242.01, 292.24, 255.68, 308.64, 252.26, 324.36, 254.31, 339.39, 257.73, 346.23, 248.85, 363.31, 241.33, 374.93, 246.8, 385.86, 245.43, 404.32, 252.26, 415.25, 257.05, 426.87, 244.75, 456.94, 237.23, 478.12, 235.18, 499.99, 224.93, 510.92, 200.33, 515.02, 189.39, 521.86, 185.29, 527.32, 179.14, 527.32, 172.99, 525.27, 178.46, 505.46, 181.88, 494.52, 185.98, 480.85, 186.66, 476.07, 172.31, 489.74, 159.32, 498.62, 153.17, 503.41, 149.07, 486.32, 155.22, 477.44, 172.31, 459.67, 182.56, 449.42, 182.56, 441.9, 182.56, 431.65, 185.98, 424.82, 181.88, 411.83, 181.88, 398.85, 180.51, 385.18], [292.58, 365.36, 309.67, 402.95, 322.65, 438.48, 319.92, 463.09, 313.09, 477.44, 291.22, 510.24, 271.4, 515.71, 261.15, 506.82, 260.46, 487.0, 280.97, 487.69, 289.85, 486.32, 289.17, 474.02, 296.68, 469.92, 302.15, 467.19, 302.83, 456.25, 298.73, 450.1, 298.73, 436.43, 302.83, 422.08, 306.25, 407.73, 298.73, 402.27, 288.48, 398.85, 296.68, 391.33, 298.73, 388.6], [167.98, 576.44, 167.98, 590.55, 161.76, 625.81, 163.83, 640.0, 231.88, 640.0, 234.36, 600.5, 240.59, 639.92, 304.89, 639.92, 303.23, 627.47, 302.4, 567.31, 297.43, 509.23, 282.91, 510.48, 267.55, 516.28, 261.33, 536.2, 252.62, 553.62, 238.1, 567.31, 227.73, 577.69, 209.06, 582.25, 187.07, 583.08, 177.94, 581.84], [117.67, 500.98, 116.73, 516.02, 121.43, 520.72, 127.07, 519.78, 125.66, 510.85]], "area": 30842.53359999999, "iscrowd": 0, "image_id": 457225, "bbox": [116.73, 269.01, 205.92, 370.99], "category_id": 1, "id": 492161, "split": "val", "sentences": [{"tokens": ["the", "woman", "with", "a", "leah", "around", "her", "neck"], "raw": "the woman with a leah around her neck", "sent_id": 41426, "sent": "the woman with a leah around her neck"}, {"tokens": ["a", "woman", "holding", "flowers"], "raw": "A woman holding flowers.", "sent_id": 41427, "sent": "a woman holding flowers"}], "file_name": "COCO_train2014_000000457225_492161.jpg", "ann_id": 492161, "sent_ids": [41426, 41427], "ref_id": 20915}, {"segmentation": [[628.51, 186.15, 569.97, 192.87, 543.11, 275.39, 533.51, 259.08, 502.8, 262.92, 498.97, 285.95, 536.39, 291.7, 531.59, 318.57, 539.27, 416.44, 637.14, 422.2, 639.06, 189.03, 631.38, 187.11]], "area": 22796.746149999988, "iscrowd": 0, "image_id": 307136, "bbox": [498.97, 186.15, 140.09, 236.05], "category_id": 3, "id": 361076, "split": "val", "sentences": [{"tokens": ["red", "van", "approaching", "woman"], "raw": "red van approaching woman", "sent_id": 41438, "sent": "red van approaching woman"}, {"tokens": ["the", "reddish", "truck"], "raw": "The reddish truck", "sent_id": 41439, "sent": "the reddish truck"}], "file_name": "COCO_train2014_000000307136_361076.jpg", "ann_id": 361076, "sent_ids": [41438, 41439], "ref_id": 20922}, {"segmentation": [[391.69, 167.82, 435.53, 175.45, 452.68, 162.11, 473.65, 144.95, 491.76, 136.37, 516.54, 94.44, 541.32, 85.86, 539.41, 56.32, 560.38, 83.96, 579.44, 84.91, 598.5, 86.82, 609.93, 88.72, 628.04, 70.62, 639.48, 70.62, 639.48, 88.81, 635.66, 99.29, 615.65, 115.49, 628.04, 142.18, 627.09, 164.1, 626.13, 181.25, 622.32, 222.23, 629.95, 261.31, 626.13, 275.6, 617.56, 290.85, 609.93, 304.19, 590.87, 301.33, 570.86, 282.27, 568.95, 299.43, 568.0, 317.53, 559.42, 350.89, 544.17, 383.29, 538.46, 393.78, 431.72, 393.78, 417.42, 392.82, 388.83, 394.73, 405.03, 368.04, 379.3, 345.17, 371.68, 390.92, 354.52, 389.01, 371.68, 335.64, 369.77, 304.19, 369.77, 282.27, 381.21, 259.4, 376.44, 214.61]], "area": 60814.945999999996, "iscrowd": 0, "image_id": 441972, "bbox": [354.52, 56.32, 284.96, 338.41], "category_id": 19, "id": 274598, "split": "val", "sentences": [{"tokens": ["horse", "closest", "to", "yellow", "line", "on", "road"], "raw": "horse closest to yellow line on road", "sent_id": 41462, "sent": "horse closest to yellow line on road"}, {"tokens": ["second", "horse", "to", "the", "person", "left"], "raw": "second horse to the person left", "sent_id": 41463, "sent": "second horse to the person left"}], "file_name": "COCO_train2014_000000441972_274598.jpg", "ann_id": 274598, "sent_ids": [41462, 41463], "ref_id": 20932}, {"segmentation": [[166.0, 88.85, 171.0, 75.35, 176.0, 67.35, 180.5, 58.85, 185.5, 48.35, 188.5, 42.85, 193.5, 40.85, 199.0, 40.85, 209.0, 47.35, 219.0, 48.85, 231.5, 51.35, 238.0, 55.85, 246.0, 61.35, 249.0, 67.35, 252.0, 73.85, 254.0, 78.85, 256.0, 84.35, 256.0, 88.35, 256.0, 92.85, 258.5, 97.35, 261.0, 104.35, 263.5, 111.85, 265.0, 117.35, 264.0, 120.85, 253.5, 120.35, 241.5, 120.35, 236.5, 121.35, 236.0, 123.35, 245.5, 126.85, 251.0, 127.85, 255.0, 128.85, 255.0, 131.85, 255.0, 134.35, 254.0, 140.35, 252.5, 147.85, 247.5, 152.85, 242.5, 162.85, 239.0, 168.85, 227.5, 175.85, 222.5, 177.85, 219.0, 177.85, 214.0, 178.85, 207.0, 178.85, 202.5, 178.35, 194.0, 176.35, 189.0, 176.35, 182.5, 173.85, 170.0, 171.35, 167.0, 169.35, 160.0, 163.35, 154.0, 162.85, 147.0, 156.85, 141.0, 147.85, 136.0, 140.35, 136.0, 132.85, 135.5, 127.85, 135.0, 120.85, 133.0, 117.35, 133.5, 113.35, 135.0, 107.85, 136.0, 98.85, 136.5, 93.35, 134.0, 86.85, 132.5, 83.85, 131.0, 80.85, 133.5, 74.35, 134.0, 72.85, 137.0, 71.35, 140.0, 71.85, 143.5, 77.85, 150.5, 82.85, 157.0, 86.85, 163.0, 90.85, 165.0, 92.35, 165.5, 88.85]], "area": 12811.75, "iscrowd": 0, "image_id": 246641, "bbox": [131.0, 40.85, 134.0, 138.0], "category_id": 54, "id": 310133, "split": "val", "sentences": [{"tokens": ["a", "food", "on", "tabule"], "raw": "a food on tabule", "sent_id": 41498, "sent": "a food on tabule"}, {"tokens": ["a", "meatball", "sandwich"], "raw": "a meatball sandwich", "sent_id": 41499, "sent": "a meatball sandwich"}], "file_name": "COCO_train2014_000000246641_310133.jpg", "ann_id": 310133, "sent_ids": [41498, 41499], "ref_id": 20943}, {"segmentation": [[319.28, 474.61, 312.81, 450.88, 339.78, 416.36, 338.7, 399.1, 314.97, 379.69, 313.89, 328.99, 275.06, 333.3, 242.7, 304.18, 201.71, 268.58, 166.11, 251.33, 155.33, 225.44, 179.06, 213.57, 209.26, 229.75, 254.56, 276.13, 302.02, 268.58, 302.02, 252.4, 322.52, 230.83, 355.96, 226.52, 354.88, 217.89, 340.85, 207.1, 320.36, 218.97, 309.57, 166.11, 320.36, 125.12, 322.52, 92.76, 340.85, 66.88, 388.31, 62.56, 431.46, 77.66, 459.51, 100.31, 459.51, 122.97, 442.25, 167.19, 443.33, 202.79, 428.22, 209.26, 494.02, 248.09, 506.97, 258.88, 483.24, 272.9, 499.42, 293.39, 535.01, 296.63, 565.21, 398.02, 584.63, 447.64, 588.94, 471.37, 552.27, 474.61, 537.17, 453.03, 515.6, 434.7, 489.71, 365.66, 476.76, 390.47, 499.42, 473.53]], "area": 79437.12594999999, "iscrowd": 0, "image_id": 485014, "bbox": [155.33, 62.56, 433.61, 412.05], "category_id": 1, "id": 469701, "split": "val", "sentences": [{"tokens": ["a", "women", "wearing", "black", "dress", "holding", "a", "phone", "in", "the", "right", "hand"], "raw": "a women wearing black dress  holding a phone in the right hand", "sent_id": 41531, "sent": "a women wearing black dress holding a phone in the right hand"}, {"tokens": ["a", "blonde", "woman", "playing", "wii"], "raw": "A blonde woman playing Wii.", "sent_id": 41532, "sent": "a blonde woman playing wii"}], "file_name": "COCO_train2014_000000485014_469701.jpg", "ann_id": 469701, "sent_ids": [41531, 41532], "ref_id": 20957}, {"segmentation": [[324.15, 177.23, 258.04, 175.39, 247.02, 183.66, 247.02, 196.51, 227.73, 194.68, 221.31, 208.45, 216.71, 213.04, 198.35, 209.37, 190.08, 197.43, 183.66, 190.08, 175.39, 174.47, 174.47, 157.94, 181.82, 141.42, 190.08, 127.64, 193.76, 121.21, 229.57, 111.11, 269.06, 75.3, 294.77, 67.03, 449.96, 78.97, 470.16, 115.7, 474.75, 147.84, 474.75, 154.27, 470.16, 158.86, 448.12, 151.52, 411.39, 144.17, 407.72, 144.17, 404.04, 128.56, 395.78, 125.8, 396.7, 114.78, 404.96, 105.6, 397.62, 87.24, 387.51, 77.14, 369.15, 76.22, 359.97, 83.56, 355.37, 97.34, 358.13, 108.36, 358.13, 118.46, 341.6, 124.89, 333.34, 139.58, 325.07, 160.7, 330.58, 170.8]], "area": 20888.5837, "iscrowd": 0, "image_id": 129371, "bbox": [174.47, 67.03, 300.28, 146.01], "category_id": 3, "id": 133165, "split": "val", "sentences": [{"tokens": ["a", "police", "suv"], "raw": "A police SUV.", "sent_id": 41555, "sent": "a police suv"}, {"tokens": ["a", "police", "van", "accompanies", "a", "officer", "on", "a", "motorcycle"], "raw": "A police van accompanies a officer on a motorcycle.", "sent_id": 41556, "sent": "a police van accompanies a officer on a motorcycle"}], "file_name": "COCO_train2014_000000129371_133165.jpg", "ann_id": 133165, "sent_ids": [41555, 41556], "ref_id": 20965}, {"segmentation": [[0.01, 163.04, 38.87, 161.64, 72.12, 158.14, 101.88, 150.78, 106.08, 136.78, 102.58, 135.38, 95.23, 136.44, 74.58, 131.54, 70.37, 126.64, 75.63, 119.99, 78.43, 121.04, 76.68, 125.94, 84.38, 126.99, 89.28, 124.19, 93.13, 124.19, 95.58, 119.99, 92.43, 118.59, 105.38, 116.84, 112.39, 117.54, 121.84, 109.83, 146.34, 108.78, 154.4, 112.63, 160.7, 114.03, 158.95, 116.84, 161.4, 121.74, 160.35, 136.79, 164.55, 144.84, 161.4, 149.39, 155.1, 166.2, 152.65, 169.0, 154.75, 174.6, 152.3, 183.0, 151.25, 186.15, 150.2, 211.01, 148.44, 220.78, 138.64, 243.54, 119.04, 255.44, 99.78, 262.09, 92.78, 263.14, 85.78, 265.59, 82.28, 266.29, 81.93, 264.19, 78.43, 266.29, 76.33, 264.19, 74.93, 261.39, 70.37, 264.89, 66.17, 266.99, 57.07, 270.85, 45.17, 273.65, 40.27, 274.0, 33.61, 276.45, 28.36, 279.25, 25.91, 281.0, 23.81, 282.75, 22.76, 283.45, 21.36, 284.15, 21.01, 284.5, 14.01, 283.1, 1.06, 278.55, 0.0, 278.2]], "area": 19017.23985000001, "iscrowd": 0, "image_id": 397760, "bbox": [0.0, 108.78, 164.55, 175.72], "category_id": 20, "id": 63898, "split": "val", "sentences": [{"tokens": ["the", "sheep", "on", "the", "far", "left"], "raw": "The sheep on the far left", "sent_id": 41604, "sent": "the sheep on the far left"}, {"tokens": ["the", "lamb", "on", "the", "left", "side", "looking", "away"], "raw": "The lamb on the left side looking away", "sent_id": 41605, "sent": "the lamb on the left side looking away"}], "file_name": "COCO_train2014_000000397760_63898.jpg", "ann_id": 63898, "sent_ids": [41604, 41605], "ref_id": 20984}, {"segmentation": [[535.5, 386.57, 533.45, 305.37, 547.84, 297.14, 575.59, 296.12, 577.64, 260.14, 612.59, 260.14, 640.0, 264.25, 640.0, 404.04, 551.95, 392.73, 551.95, 409.18, 541.67, 408.15, 537.56, 389.65]], "area": 13011.733149999998, "iscrowd": 0, "image_id": 130163, "bbox": [533.45, 260.14, 106.55, 149.04], "category_id": 63, "id": 117372, "split": "val", "sentences": [{"tokens": ["the", "chair", "to", "the", "right", "of", "the", "fireplace"], "raw": "the chair to the right of the fireplace", "sent_id": 41710, "sent": "the chair to the right of the fireplace"}, {"tokens": ["brown", "chair", "on", "far", "right", "of", "picture"], "raw": "Brown chair on far right of picture.", "sent_id": 41711, "sent": "brown chair on far right of picture"}], "file_name": "COCO_train2014_000000130163_117372.jpg", "ann_id": 117372, "sent_ids": [41710, 41711], "ref_id": 21024}, {"segmentation": [[481.91, 328.51, 476.68, 282.86, 471.44, 242.45, 463.21, 228.98, 435.52, 150.41, 419.06, 142.93, 397.36, 136.94, 374.91, 135.44, 374.19, 124.19, 365.5, 110.28, 348.52, 98.51, 330.01, 104.76, 312.05, 116.74, 309.8, 124.22, 309.8, 140.68, 314.48, 154.06, 322.52, 160.61, 331.69, 166.59, 341.23, 171.36, 350.21, 180.34, 341.23, 189.32, 337.49, 213.27, 341.98, 236.47, 344.97, 249.94, 346.47, 271.64, 344.97, 294.09, 343.48, 312.8, 347.22, 329.26]], "area": 25281.034499999998, "iscrowd": 0, "image_id": 44637, "bbox": [309.8, 98.51, 172.11, 230.75], "category_id": 1, "id": 465363, "split": "val", "sentences": [{"tokens": ["the", "blonde", "woman", "in", "the", "black", "coat", "with", "a", "water", "bottle", "in", "her", "pocket"], "raw": "The blonde woman in the black coat with a water bottle in her pocket.", "sent_id": 41833, "sent": "the blonde woman in the black coat with a water bottle in her pocket"}, {"tokens": ["girl", "in", "black", "coat", "with", "red", "hair"], "raw": "Girl in black coat with red hair.", "sent_id": 41834, "sent": "girl in black coat with red hair"}], "file_name": "COCO_train2014_000000044637_465363.jpg", "ann_id": 465363, "sent_ids": [41833, 41834], "ref_id": 21077}, {"segmentation": [[274.59, 402.16, 291.89, 418.38, 290.81, 328.65, 289.73, 321.08, 314.59, 409.73, 324.32, 407.57, 335.14, 391.35, 326.49, 271.35, 325.41, 245.41, 339.46, 300.54, 348.11, 290.81, 341.62, 274.59, 337.3, 192.43, 320.0, 176.22, 325.41, 167.57, 325.41, 153.51, 307.03, 150.27, 297.3, 156.76, 291.89, 156.76, 291.89, 170.81, 270.27, 172.97, 259.46, 180.54, 234.59, 233.51, 240.0, 281.08, 247.57, 273.51, 241.08, 298.38, 254.05, 301.62, 273.51, 403.24]], "area": 18781.317450000006, "iscrowd": 0, "image_id": 174876, "bbox": [234.59, 150.27, 113.52, 268.11], "category_id": 1, "id": 465449, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "printed", "blouse", "bending", "over", "to", "pull", "an", "object", "out", "of", "a", "drawer"], "raw": "A woman wearing a printed blouse bending over to pull an object out of a drawer.", "sent_id": 41871, "sent": "a woman wearing a printed blouse bending over to pull an object out of a drawer"}, {"tokens": ["woman", "in", "blue", "pants", "opening", "a", "drawer"], "raw": "Woman in blue pants opening a drawer", "sent_id": 41872, "sent": "woman in blue pants opening a drawer"}], "file_name": "COCO_train2014_000000174876_465449.jpg", "ann_id": 465449, "sent_ids": [41871, 41872], "ref_id": 21093}, {"segmentation": [[19.25, 279.18, 30.26, 265.43, 39.88, 270.93, 38.51, 254.43, 26.13, 244.8, 27.51, 229.67, 37.13, 233.8, 48.13, 200.79, 66.01, 166.41, 83.89, 158.16, 105.9, 151.28, 130.65, 155.41, 159.53, 171.91, 182.91, 188.41, 188.41, 202.17, 181.54, 222.8, 160.91, 261.3, 149.91, 280.56, 133.4, 297.06, 126.53, 301.19, 118.27, 316.31, 114.15, 335.57, 114.15, 345.2, 130.65, 371.33, 130.65, 419.46, 141.65, 422.21, 184.29, 434.59, 198.04, 434.59, 229.67, 416.71, 251.68, 424.96, 257.18, 444.22, 276.43, 451.09, 294.31, 471.72, 294.31, 495.1, 276.43, 511.6, 264.05, 511.6, 243.42, 500.6, 206.29, 504.73, 156.78, 508.85, 134.78, 504.73, 132.03, 528.11, 126.53, 580.37, 127.9, 601.0, 9.63, 594.12]], "area": 63721.641500000005, "iscrowd": 0, "image_id": 119714, "bbox": [9.63, 151.28, 284.68, 449.72], "category_id": 1, "id": 502659, "split": "val", "sentences": [{"tokens": ["a", "young", "man", "with", "a", "grey", "t", "-", "shirt", "on"], "raw": "A young man with a grey t-shirt on.", "sent_id": 41910, "sent": "a young man with a grey t - shirt on"}, {"tokens": ["left", "most", "person"], "raw": "left most person", "sent_id": 41911, "sent": "left most person"}], "file_name": "COCO_train2014_000000119714_502659.jpg", "ann_id": 502659, "sent_ids": [41910, 41911], "ref_id": 21108}, {"segmentation": [[0.0, 77.7, 19.68, 59.05, 46.62, 58.01, 61.12, 52.83, 98.42, 65.27, 147.11, 68.37, 161.61, 80.8, 180.26, 82.88, 192.69, 104.63, 220.66, 101.52, 247.59, 112.92, 242.41, 135.71, 224.8, 136.75, 193.72, 151.25, 213.41, 170.93, 219.62, 192.69, 219.62, 223.77, 200.98, 255.88, 190.62, 299.39, 170.93, 344.97, 163.68, 381.23, 159.54, 401.95, 152.29, 422.67, 133.64, 411.27, 109.81, 328.4, 92.2, 290.07, 94.27, 333.58, 100.49, 362.58, 87.02, 338.76, 66.3, 300.43, 63.19, 317.0, 44.55, 305.61, 27.97, 304.57, 13.47, 326.33, 5.18, 320.11]], "area": 56100.543800000014, "iscrowd": 0, "image_id": 179390, "bbox": [0.0, 52.83, 247.59, 369.84], "category_id": 21, "id": 76733, "split": "val", "sentences": [{"tokens": ["a", "darker", "brown", "cow", "with", "white", "around", "the", "nose", ",", "beside", "a", "lighter", "cow"], "raw": "A darker brown cow with white around the nose, beside a lighter cow", "sent_id": 41976, "sent": "a darker brown cow with white around the nose , beside a lighter cow"}, {"tokens": ["a", "dark", "colored", "cow", "standing", "to", "the", "left", "some", "another", "cows"], "raw": "A dark colored cow standing to the left some another cows.", "sent_id": 41977, "sent": "a dark colored cow standing to the left some another cows"}], "file_name": "COCO_train2014_000000179390_76733.jpg", "ann_id": 76733, "sent_ids": [41976, 41977], "ref_id": 21131}, {"segmentation": [[543.22, 112.55, 554.66, 59.18, 571.81, 10.58, 583.25, 7.72, 599.45, 0.0, 638.52, 1.05, 640.0, 155.43, 608.03, 164.96, 576.58, 177.35, 564.19, 144.95, 601.36, 125.89, 604.21, 109.69, 577.53, 103.02, 561.33, 111.6, 543.22, 119.22, 542.27, 111.6]], "area": 11916.858699999997, "iscrowd": 0, "image_id": 491249, "bbox": [542.27, 0.0, 97.73, 177.35], "category_id": 1, "id": 440041, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "the", "green", "dress", "located", "in", "the", "top", "right", "corner", "of", "the", "photo"], "raw": "A girl in the green dress located in the top right corner of the photo.", "sent_id": 42053, "sent": "a girl in the green dress located in the top right corner of the photo"}, {"tokens": ["a", "woman", "in", "a", "sleeveless", "top", "with", "dark", "hair", "and", "part", "of", "a", "pair", "of", "tongs"], "raw": "A woman in a sleeveless top with dark hair and part of a pair of tongs", "sent_id": 42054, "sent": "a woman in a sleeveless top with dark hair and part of a pair of tongs"}], "file_name": "COCO_train2014_000000491249_440041.jpg", "ann_id": 440041, "sent_ids": [42053, 42054], "ref_id": 21156}, {"segmentation": [[283.97, 231.93, 196.67, 355.69, 202.43, 383.51, 191.87, 419.0, 7.67, 419.0, 29.74, 365.28, 53.72, 350.89, 118.96, 330.74, 154.46, 307.72, 152.54, 298.12, 281.09, 193.55, 282.05, 187.8, 281.09, 180.12, 292.61, 178.2, 310.84, 197.39, 343.45, 201.23, 345.37, 206.98, 345.37, 211.78, 345.37, 212.74, 341.53, 216.58, 336.74, 217.54, 330.98, 218.5]], "area": 24430.354250000008, "iscrowd": 0, "image_id": 8300, "bbox": [7.67, 178.2, 337.7, 240.8], "category_id": 25, "id": 599213, "split": "val", "sentences": [{"tokens": ["the", "two", "giraffe", "necks", "togther", "eating"], "raw": "The two giraffe necks togther eating.", "sent_id": 42061, "sent": "the two giraffe necks togther eating"}], "file_name": "COCO_train2014_000000008300_599213.jpg", "ann_id": 599213, "sent_ids": [42061], "ref_id": 21160}, {"segmentation": [[399.18, 49.14, 395.34, 0.0, 640.0, 0.0, 622.76, 83.69, 508.57, 84.65, 492.26, 70.25, 459.63, 61.62]], "area": 17189.518450000003, "iscrowd": 0, "image_id": 183435, "bbox": [395.34, 0.0, 244.66, 84.65], "category_id": 62, "id": 1592328, "split": "val", "sentences": [{"tokens": ["a", "chair", "at", "the", "front", "of", "a", "table"], "raw": "a chair at the front of a table.", "sent_id": 42134, "sent": "a chair at the front of a table"}, {"tokens": ["a", "wall", "is", "striped", "with", "the", "colors", "brown", "and", "white"], "raw": "A wall is striped with the colors brown and white.", "sent_id": 42135, "sent": "a wall is striped with the colors brown and white"}], "file_name": "COCO_train2014_000000183435_1592328.jpg", "ann_id": 1592328, "sent_ids": [42134, 42135], "ref_id": 21187}, {"segmentation": [[411.14, 271.23, 510.39, 296.74, 556.41, 312.82, 550.31, 328.9, 522.03, 352.19, 451.06, 328.9, 374.54, 302.84, 367.33, 301.17, 400.05, 278.44, 405.04, 270.12, 412.24, 271.79]], "area": 7389.387049999992, "iscrowd": 0, "image_id": 456658, "bbox": [367.33, 270.12, 189.08, 82.07], "category_id": 76, "id": 1114578, "split": "val", "sentences": [{"tokens": ["a", "computer", "keyboard", "on", "a", "table"], "raw": "a computer keyboard on a table", "sent_id": 42239, "sent": "a computer keyboard on a table"}, {"tokens": ["an", "white", "color", "external", "keyboard", "front", "of", "the", "monitor"], "raw": "AN WHITE COLOR EXTERNAL KEYBOARD FRONT OF THE MONITOR", "sent_id": 42240, "sent": "an white color external keyboard front of the monitor"}], "file_name": "COCO_train2014_000000456658_1114578.jpg", "ann_id": 1114578, "sent_ids": [42239, 42240], "ref_id": 21223}, {"segmentation": [[234.91, 354.28, 288.26, 349.4, 340.64, 348.74, 387.82, 353.95, 409.29, 361.11, 381.31, 364.69, 325.03, 370.87, 267.44, 384.53, 254.43, 383.56, 207.58, 393.64, 200.1, 395.92, 187.74, 382.25, 174.72, 376.4, 153.58, 374.45, 111.93, 391.69, 145.12, 365.34, 197.5, 359.16, 237.84, 353.62, 237.84, 353.62]], "area": 6214.0416000000005, "iscrowd": 0, "image_id": 477580, "bbox": [111.93, 348.74, 297.36, 47.18], "category_id": 57, "id": 1063773, "split": "val", "sentences": [{"tokens": ["a", "carrot", "stacked", "in", "the", "middle", "of", "two", "other", "carrots"], "raw": "A carrot stacked in the middle of two other carrots.", "sent_id": 42241, "sent": "a carrot stacked in the middle of two other carrots"}, {"tokens": ["the", "middle", "carrot", "that", "'", "s", "laying", "down", "with", "two", "other", "carrots", ",", "on", "either", "side"], "raw": "The middle carrot that's laying down with two other carrots, on either side.", "sent_id": 42242, "sent": "the middle carrot that ' s laying down with two other carrots , on either side"}], "file_name": "COCO_train2014_000000477580_1063773.jpg", "ann_id": 1063773, "sent_ids": [42241, 42242], "ref_id": 21224}, {"segmentation": [[0.52, 217.01, 16.48, 215.13, 38.08, 216.54, 60.14, 217.95, 86.44, 212.31, 95.83, 210.91, 101.46, 206.68, 117.89, 207.62, 133.86, 209.97, 146.53, 215.6, 158.27, 232.97, 169.54, 256.92, 177.05, 276.64, 179.4, 289.78, 179.4, 309.5, 179.4, 324.06, 184.1, 325.47, 190.67, 327.81, 195.83, 325.0, 207.57, 327.34, 215.08, 327.34, 213.67, 332.51, 209.92, 337.67, 201.0, 339.08, 192.55, 335.8, 182.69, 335.8, 181.28, 336.73, 179.4, 341.43, 182.22, 346.12, 181.75, 352.7, 178.46, 360.21, 170.95, 376.17, 171.42, 385.56, 170.01, 398.24, 172.36, 404.34, 171.89, 407.63, 161.09, 408.57, 152.17, 408.57, 147.94, 408.1, 150.76, 402.47, 153.11, 399.18, 154.05, 397.3, 158.27, 393.55, 159.21, 391.67, 154.52, 391.2, 151.7, 388.85, 141.84, 376.64, 133.86, 363.03, 133.86, 355.05, 139.96, 345.66, 142.31, 335.33, 146.53, 327.81, 140.9, 320.77, 134.8, 308.09, 128.69, 301.05, 123.06, 307.62, 112.26, 310.44, 102.4, 290.72, 93.48, 276.64, 86.91, 272.88, 77.52, 268.66, 71.88, 267.25, 65.31, 268.19, 59.21, 268.19, 45.12, 269.12, 30.1, 269.12, 12.25, 269.59, 0.0, 270.06, 0.52, 255.04, 0.99, 218.89], [102.68, 375.14, 102.68, 383.68, 101.26, 390.8, 101.26, 398.63, 104.81, 411.44, 118.34, 411.44, 114.78, 400.76, 108.37, 383.68, 104.81, 377.99], [69.23, 361.62, 68.52, 367.31, 66.39, 372.3, 64.25, 376.57, 66.39, 385.11, 67.1, 390.09, 64.25, 397.2, 67.81, 403.61, 76.35, 409.3, 70.65, 397.91, 72.79, 390.09, 72.79, 379.41, 77.06, 367.31, 78.48, 363.76, 74.21, 364.47]], "area": 16356.747900000022, "iscrowd": 0, "image_id": 292271, "bbox": [0.0, 206.68, 215.08, 204.76], "category_id": 24, "id": 590807, "split": "val", "sentences": [{"tokens": ["the", "zebra", "that", "is", "behind", "the", "goat", ",", "eating"], "raw": "the zebra that is behind the goat, eating", "sent_id": 42255, "sent": "the zebra that is behind the goat , eating"}], "file_name": "COCO_train2014_000000292271_590807.jpg", "ann_id": 590807, "sent_ids": [42255], "ref_id": 21230}, {"segmentation": [[122.19, 10.11, 154.21, 24.44, 169.38, 33.71, 203.93, 48.88, 234.27, 64.89, 224.16, 108.71, 227.53, 120.51, 235.96, 112.08, 256.18, 73.31, 273.88, 77.53, 278.09, 114.61, 277.25, 159.27, 279.78, 176.12, 297.47, 190.45, 300.0, 171.07, 292.42, 113.76, 302.53, 69.1, 312.64, 57.3, 338.76, 80.06, 350.56, 115.45, 352.25, 136.52, 367.42, 167.7, 380.9, 181.18, 384.27, 188.76, 412.08, 169.38, 412.92, 128.09, 413.76, 93.54, 411.24, 71.63, 395.22, 42.13, 353.09, 4.21, 123.88, 0.84]], "area": 23699.380200000007, "iscrowd": 0, "image_id": 24404, "bbox": [122.19, 0.84, 291.57, 189.61], "category_id": 24, "id": 592174, "split": "val", "sentences": [{"tokens": ["zebra", "in", "the", "back", "side"], "raw": "zebra in the back side", "sent_id": 42270, "sent": "zebra in the back side"}, {"tokens": ["the", "zebra", "in", "the", "back"], "raw": "The zebra in the back", "sent_id": 42271, "sent": "the zebra in the back"}], "file_name": "COCO_train2014_000000024404_592174.jpg", "ann_id": 592174, "sent_ids": [42270, 42271], "ref_id": 21237}, {"segmentation": [[186.1, 332.9, 186.1, 294.79, 174.89, 245.46, 188.34, 207.34, 199.55, 202.86, 197.31, 168.11, 199.55, 143.44, 209.64, 116.54, 245.52, 121.02, 255.61, 128.87, 278.03, 144.56, 281.39, 183.8, 278.03, 214.07, 304.93, 235.37, 310.54, 238.73, 322.87, 257.79, 325.11, 260.03, 350.9, 262.28, 347.53, 279.09, 338.57, 303.76, 335.2, 314.97, 325.11, 328.42, 284.75, 335.15, 242.15, 338.51, 204.04, 329.54, 198.43, 329.54]], "area": 24430.89085, "iscrowd": 0, "image_id": 426705, "bbox": [174.89, 116.54, 176.01, 221.97], "category_id": 1, "id": 459592, "split": "val", "sentences": [{"tokens": ["a", "woman", "sitting", "in", "front", "of", "a", "laptop"], "raw": "A woman sitting in front of a laptop.", "sent_id": 42320, "sent": "a woman sitting in front of a laptop"}, {"tokens": ["the", "woman", "with", "glasses"], "raw": "the woman with glasses", "sent_id": 42321, "sent": "the woman with glasses"}], "file_name": "COCO_train2014_000000426705_459592.jpg", "ann_id": 459592, "sent_ids": [42320, 42321], "ref_id": 21255}, {"segmentation": [[179.72, 432.11, 174.81, 389.88, 174.81, 347.65, 184.63, 335.87, 233.73, 314.26, 243.55, 303.46, 251.41, 286.76, 254.35, 264.17, 203.29, 274.98, 184.63, 280.87, 153.2, 299.53, 136.51, 306.4, 109.99, 312.3, 109.99, 295.6, 121.78, 280.87, 137.49, 274.0, 164.99, 265.16, 164.0, 253.37, 136.51, 259.26, 121.78, 267.12, 105.08, 268.1, 90.35, 241.59, 108.03, 243.55, 110.97, 245.52, 153.2, 238.64, 221.95, 198.38, 237.66, 183.65, 243.55, 168.91, 243.55, 152.22, 232.75, 155.17, 214.09, 159.09, 204.27, 160.08, 202.3, 143.38, 212.13, 108.03, 212.13, 98.21, 200.34, 98.21, 180.7, 92.31, 184.63, 84.46, 212.13, 67.76, 232.75, 56.96, 263.19, 60.89, 294.62, 103.12, 302.48, 126.69, 325.06, 159.09, 335.87, 163.02, 367.29, 211.14, 374.17, 257.3, 373.18, 288.73, 363.36, 301.49, 340.78, 312.3, 329.97, 337.83, 318.19, 353.54, 289.71, 367.29, 238.64, 392.83, 239.62, 421.3]], "area": 47123.4866, "iscrowd": 0, "image_id": 226176, "bbox": [90.35, 56.96, 283.82, 375.15], "category_id": 1, "id": 217857, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "helmet"], "raw": "A man in a helmet.", "sent_id": 42328, "sent": "a man in a helmet"}, {"tokens": ["a", "man", "driving", "a", "motorcycle", "with", "a", "helmet", "on"], "raw": "A man driving a motorcycle with a helmet on", "sent_id": 42329, "sent": "a man driving a motorcycle with a helmet on"}], "file_name": "COCO_train2014_000000226176_217857.jpg", "ann_id": 217857, "sent_ids": [42328, 42329], "ref_id": 21259}, {"segmentation": [[473.51, 457.84, 446.49, 310.81, 438.92, 304.32, 447.57, 146.49, 190.27, 146.49, 187.03, 146.49, 200.0, 309.73, 204.32, 310.81, 196.76, 310.81, 158.92, 453.51, 167.57, 466.49, 469.19, 466.49, 475.68, 457.84]], "area": 85246.46705000002, "iscrowd": 0, "image_id": 344073, "bbox": [158.92, 146.49, 316.76, 320.0], "category_id": 73, "id": 1102619, "split": "val", "sentences": [{"tokens": ["a", "laptop", "which", "is", "in", "front", "of", "other", "two", "laptops"], "raw": "A laptop which is in front of other two laptops", "sent_id": 42358, "sent": "a laptop which is in front of other two laptops"}, {"tokens": ["a", "laptop", "in", "front", "of", "the", "two", "laptops"], "raw": "A laptop in front of the two laptops", "sent_id": 42359, "sent": "a laptop in front of the two laptops"}], "file_name": "COCO_train2014_000000344073_1102619.jpg", "ann_id": 1102619, "sent_ids": [42358, 42359], "ref_id": 21268}, {"segmentation": [[194.75, 391.15, 203.59, 396.59, 202.91, 408.84, 200.87, 418.36, 202.91, 423.8, 198.15, 429.93, 200.87, 457.82, 206.31, 470.06, 196.11, 488.43, 200.19, 527.89, 203.59, 563.95, 197.47, 571.43, 183.18, 600.0, 183.18, 640.0, 146.44, 634.7, 135.56, 629.26, 140.32, 590.48, 158.01, 551.7, 155.97, 523.13, 150.53, 512.92, 147.13, 486.39, 160.73, 474.15, 165.38, 430.71, 165.98, 412.1, 179.79, 403.69, 183.39, 390.48, 188.8, 391.08]], "area": 10388.211550000002, "iscrowd": 0, "image_id": 345981, "bbox": [135.56, 390.48, 70.75, 249.52], "category_id": 1, "id": 427673, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "yellow", "backpack"], "raw": "A man with yellow backpack", "sent_id": 42395, "sent": "a man with yellow backpack"}, {"tokens": ["a", "man", "on", "skis", "wearing", "a", "red", "head", "covering"], "raw": "A man on skis wearing a red head covering.", "sent_id": 42396, "sent": "a man on skis wearing a red head covering"}], "file_name": "COCO_train2014_000000345981_427673.jpg", "ann_id": 427673, "sent_ids": [42395, 42396], "ref_id": 21286}, {"segmentation": [[192.78, 312.68, 186.69, 346.78, 179.38, 393.05, 167.2, 474.65, 152.59, 550.15, 139.19, 583.03, 100.22, 563.54, 127.02, 419.84, 144.06, 361.39, 158.68, 317.55, 153.81, 310.24, 180.6, 311.46]], "area": 12019.37535, "iscrowd": 0, "image_id": 354391, "bbox": [100.22, 310.24, 92.56, 272.79], "category_id": 32, "id": 1443319, "split": "val", "sentences": [{"tokens": ["the", "black", "tie", "being", "worn", "by", "a", "man"], "raw": "The black tie being worn by a man.", "sent_id": 42455, "sent": "the black tie being worn by a man"}, {"tokens": ["man", "wear", "black", "tie"], "raw": "man wear black tie", "sent_id": 42456, "sent": "man wear black tie"}], "file_name": "COCO_train2014_000000354391_1443319.jpg", "ann_id": 1443319, "sent_ids": [42455, 42456], "ref_id": 21312}, {"segmentation": [[94.5, 170.89, 181.48, 171.97, 216.91, 173.04, 215.84, 421.09, 186.85, 455.46, 181.48, 321.23, 95.57, 321.23]], "area": 21946.184400000006, "iscrowd": 0, "image_id": 564271, "bbox": [94.5, 170.89, 122.41, 284.57], "category_id": 82, "id": 332835, "split": "val", "sentences": [{"tokens": ["a", "black", "colored", "fridge", "which", "is", "kept", "at", "the", "left", "corner", "of", "the", "room"], "raw": "A black colored fridge which is kept at the left corner of the room", "sent_id": 42484, "sent": "a black colored fridge which is kept at the left corner of the room"}, {"tokens": ["a", "black", "refrigerator", "in", "between", "the", "counter", "and", "the", "window", ",", "inside", "a", "small", "kitchen"], "raw": "A black refrigerator in between the counter and the window, inside a small kitchen.", "sent_id": 42485, "sent": "a black refrigerator in between the counter and the window , inside a small kitchen"}], "file_name": "COCO_train2014_000000564271_332835.jpg", "ann_id": 332835, "sent_ids": [42484, 42485], "ref_id": 21322}, {"segmentation": [[290.16, 143.46, 417.44, 131.6, 485.39, 158.56, 476.76, 256.72, 313.89, 289.08, 310.65, 169.35, 305.26, 154.25, 278.29, 145.62]], "area": 22818.96755, "iscrowd": 0, "image_id": 71099, "bbox": [278.29, 131.6, 207.1, 157.48], "category_id": 78, "id": 1120014, "split": "val", "sentences": [{"tokens": ["silver", "plated", "microwave"], "raw": "Silver plated microwave", "sent_id": 42506, "sent": "silver plated microwave"}, {"tokens": ["the", "silver", "microwave"], "raw": "The silver microwave", "sent_id": 42507, "sent": "the silver microwave"}], "file_name": "COCO_train2014_000000071099_1120014.jpg", "ann_id": 1120014, "sent_ids": [42506, 42507], "ref_id": 21331}, {"segmentation": [[131.49, 397.98, 136.25, 372.26, 143.87, 356.06, 142.92, 350.34, 141.02, 337.0, 109.57, 327.48, 106.71, 306.51, 107.67, 278.88, 109.57, 267.45, 112.43, 249.34, 128.63, 226.48, 149.59, 220.76, 158.17, 213.14, 152.45, 205.52, 144.83, 188.37, 138.16, 163.59, 155.31, 136.91, 187.7, 138.82, 207.71, 146.44, 209.62, 157.88, 209.62, 162.64, 209.62, 168.36, 217.24, 175.98, 214.38, 181.7, 215.33, 188.37, 213.43, 198.85, 213.43, 206.47, 200.09, 208.37, 195.33, 220.76, 192.47, 226.48, 222.0, 236.01, 228.67, 244.58, 236.3, 252.2, 240.11, 257.92, 223.91, 293.17, 219.15, 288.41, 215.33, 300.8, 214.38, 319.85, 215.33, 329.38, 216.29, 338.91, 202.0, 377.02, 200.09, 405.61, 198.18, 416.09, 135.3, 417.99, 134.35, 400.84]], "area": 23041.60025, "iscrowd": 0, "image_id": 513748, "bbox": [106.71, 136.91, 133.4, 281.08], "category_id": 1, "id": 502936, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "black", "holding", "her", "surfboard"], "raw": "A girl in black holding her surfboard.", "sent_id": 42522, "sent": "a girl in black holding her surfboard"}, {"tokens": ["the", "surfer", "who", "is", "standing", ",", "holding", "his", "board", "upright", ",", "looking", "to", "the", "right", ","], "raw": "The surfer who is standing, holding his board upright, looking to the right,", "sent_id": 42523, "sent": "the surfer who is standing , holding his board upright , looking to the right ,"}], "file_name": "COCO_train2014_000000513748_502936.jpg", "ann_id": 502936, "sent_ids": [42522, 42523], "ref_id": 21338}, {"segmentation": [[552.67, 235.53, 587.28, 274.63, 591.77, 285.53, 561.0, 315.01, 551.39, 318.85, 552.03, 336.8, 551.39, 356.02, 550.75, 372.05, 527.68, 372.05, 518.7, 374.61, 515.5, 352.82, 508.45, 375.25, 491.78, 373.33, 482.81, 363.07, 485.38, 329.75, 486.02, 313.72, 468.71, 286.17, 466.15, 277.83, 475.76, 252.2, 488.58, 237.46, 497.55, 231.69, 502.04, 220.15, 498.19, 214.38, 496.91, 206.69, 497.55, 201.57, 499.48, 195.16, 502.68, 188.75, 516.14, 179.78, 528.96, 181.7, 537.29, 188.75, 546.9, 213.74, 546.26, 227.2, 546.26, 231.69, 555.23, 235.53]], "area": 14018.559399999996, "iscrowd": 0, "image_id": 419324, "bbox": [466.15, 179.78, 125.62, 195.47], "category_id": 1, "id": 2176944, "split": "val", "sentences": [{"tokens": ["a", "woman", "watching", "another", "woman", "wii"], "raw": "A woman watching another woman wii.", "sent_id": 42641, "sent": "a woman watching another woman wii"}, {"tokens": ["a", "woman", "standing", "with", "her", "hands", "on", "her", "hips"], "raw": "a woman standing with her hands on her hips", "sent_id": 42642, "sent": "a woman standing with her hands on her hips"}], "file_name": "COCO_train2014_000000419324_2176944.jpg", "ann_id": 2176944, "sent_ids": [42641, 42642], "ref_id": 21391}, {"segmentation": [[140.48, 225.41, 138.93, 211.48, 151.32, 199.86, 143.58, 159.61, 154.42, 141.02, 177.64, 132.51, 197.77, 133.28, 204.74, 157.28, 208.61, 200.64, 248.87, 223.86, 270.55, 261.8, 279.84, 285.02, 270.55, 292.77, 272.87, 318.31, 289.9, 351.61, 299.97, 380.25, 306.16, 390.31, 329.38, 403.48, 332.48, 417.41, 317.77, 432.9, 309.26, 427.48, 310.8, 415.86, 306.93, 408.9, 295.32, 403.48, 260.48, 351.61, 251.19, 326.06, 240.35, 288.9, 240.35, 312.12, 247.32, 334.57, 239.58, 343.09, 238.03, 409.67, 230.29, 435.99, 234.16, 446.06, 239.58, 448.38, 237.26, 454.57, 232.61, 457.67, 198.55, 461.54, 193.9, 469.28, 193.13, 487.09, 202.42, 509.54, 210.16, 531.99, 238.03, 562.19, 225.64, 579.99, 195.45, 568.38, 181.51, 546.7, 163.71, 520.38, 155.97, 536.64, 150.55, 548.25, 113.38, 583.86, 121.9, 601.67, 113.38, 610.19, 101.0, 608.64, 80.87, 606.31, 73.13, 597.8, 80.87, 577.67, 90.93, 555.99, 115.71, 528.12, 124.22, 512.64, 131.97, 502.57, 139.71, 486.31, 155.97, 465.41, 140.48, 443.73, 131.19, 446.06, 124.22, 435.99, 128.87, 429.02, 131.19, 427.48, 121.9, 413.54, 121.13, 399.61, 133.51, 357.8, 136.61, 346.19, 128.87, 353.15, 94.03, 401.15, 75.45, 411.99, 50.68, 411.99, 54.55, 399.61, 66.93, 391.86, 63.84, 378.7, 78.55, 370.19, 89.38, 369.41, 111.84, 335.35, 131.97, 311.35, 125.0, 307.48, 110.29, 301.28, 111.84, 285.8, 115.71, 250.19, 118.03, 231.61]], "area": 50324.13489999997, "iscrowd": 0, "image_id": 552184, "bbox": [50.68, 132.51, 281.8, 477.68], "category_id": 1, "id": 491711, "split": "val", "sentences": [{"tokens": ["a", "girl", "wearing", "white", "t", "-", "shirt", "who", "is", "kicking", "the", "foot", "ball"], "raw": "A GIRL WEARING WHITE T-SHIRT WHO IS KICKING THE FOOT BALL", "sent_id": 42657, "sent": "a girl wearing white t - shirt who is kicking the foot ball"}, {"tokens": ["a", "girl", ",", "who", "is", "not", "wearing", "a", "headband", ",", "and", "is", "attempting", "to", "kick", "the", "soccer", "ball"], "raw": "A girl, who is not wearing a headband, and is attempting to kick the soccer ball.", "sent_id": 42658, "sent": "a girl , who is not wearing a headband , and is attempting to kick the soccer ball"}], "file_name": "COCO_train2014_000000552184_491711.jpg", "ann_id": 491711, "sent_ids": [42657, 42658], "ref_id": 21399}, {"segmentation": [[306.34, 443.33, 294.47, 422.83, 277.21, 401.26, 261.03, 374.29, 252.4, 361.35, 244.85, 345.17, 248.09, 312.81, 294.47, 294.47, 292.31, 267.51, 290.16, 259.96, 272.9, 256.72, 258.88, 264.27, 243.78, 283.69, 235.15, 284.76, 218.97, 252.4, 210.34, 240.54, 198.47, 226.52, 185.53, 210.34, 185.53, 208.18, 221.12, 201.71, 234.07, 200.63, 221.12, 136.99, 230.83, 119.73, 231.91, 100.31, 237.3, 76.58, 221.12, 46.38, 207.1, 33.44, 183.37, 24.81, 129.44, 45.3, 117.57, 76.58, 113.26, 110.02, 106.79, 140.22, 111.1, 167.19, 91.69, 198.47, 78.74, 211.42, 56.09, 227.6, 72.27, 252.4, 91.69, 331.15, 111.1, 393.71, 115.42, 434.7, 136.99, 480.0, 254.56, 480.0, 309.57, 480.0]], "area": 65392.12195000001, "iscrowd": 0, "image_id": 578523, "bbox": [56.09, 24.81, 253.48, 455.19], "category_id": 1, "id": 443430, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "the", "blue", "shirt"], "raw": "The person in the blue shirt", "sent_id": 42702, "sent": "the person in the blue shirt"}, {"tokens": ["a", "woman", "smiling", "with", "a", "knife", "in", "a", "blue", "shirt"], "raw": "A woman smiling with a knife in a blue shirt", "sent_id": 42703, "sent": "a woman smiling with a knife in a blue shirt"}], "file_name": "COCO_train2014_000000578523_443430.jpg", "ann_id": 443430, "sent_ids": [42702, 42703], "ref_id": 21415}, {"segmentation": [[514.52, 4.31, 362.43, 0.0, 346.25, 88.45, 337.62, 167.19, 353.8, 225.44, 385.08, 252.4, 410.97, 265.35, 406.65, 346.25, 398.02, 384.0, 351.64, 395.87, 338.7, 417.44, 348.4, 442.25, 377.53, 458.43, 426.07, 467.06, 464.9, 454.11, 473.53, 429.3, 461.66, 406.65, 426.07, 388.31, 413.12, 384.0, 420.67, 322.52, 434.7, 263.19, 499.42, 226.52, 524.22, 127.28, 520.99, 50.7, 514.52, 3.24]], "area": 51271.94090000002, "iscrowd": 0, "image_id": 92957, "bbox": [337.62, 0.0, 186.6, 467.06], "category_id": 46, "id": 664635, "split": "val", "sentences": [{"tokens": ["a", "wineglass", "with", "some", "red", "wine", "in", "it", "and", "a", "tag", "with", "the", "number", "64", "directly", "behind", "it"], "raw": "A wineglass with some red wine in it and a tag with the number 64 directly behind it.", "sent_id": 42749, "sent": "a wineglass with some red wine in it and a tag with the number 64 directly behind it"}, {"tokens": ["a", "wine", "glass", "on", "a", "wooden", "table"], "raw": "A wine glass on a wooden table", "sent_id": 42750, "sent": "a wine glass on a wooden table"}], "file_name": "COCO_train2014_000000092957_664635.jpg", "ann_id": 664635, "sent_ids": [42749, 42750], "ref_id": 21434}, {"segmentation": [[622.99, 215.87, 583.01, 207.56, 556.88, 204.79, 545.8, 266.14, 535.11, 262.18, 544.22, 199.24, 544.22, 196.08, 537.48, 193.3, 537.09, 186.18, 541.44, 146.99, 544.61, 146.99, 555.3, 143.83, 559.65, 143.83, 562.42, 162.43, 560.44, 177.08, 578.65, 172.72, 580.63, 139.87, 590.53, 139.47, 595.28, 136.7, 596.07, 167.97, 617.45, 160.85, 619.42, 160.85, 619.82, 165.99, 627.74, 167.57]], "area": 5149.300099999998, "iscrowd": 0, "image_id": 547636, "bbox": [535.11, 136.7, 92.63, 129.44], "category_id": 67, "id": 118695, "split": "val", "sentences": [{"tokens": ["a", "dining", "table", "with", "chairs"], "raw": "A dining table with chairs.", "sent_id": 42752, "sent": "a dining table with chairs"}, {"tokens": ["wooden", "dining", "room", "table", "surrounded", "by", "cloth", "-", "seated", "chairs"], "raw": "wooden dining room table surrounded by cloth-seated chairs", "sent_id": 42753, "sent": "wooden dining room table surrounded by cloth - seated chairs"}], "file_name": "COCO_train2014_000000547636_118695.jpg", "ann_id": 118695, "sent_ids": [42752, 42753], "ref_id": 21435}, {"segmentation": [[12.6, 246.0, 34.8, 247.2, 100.2, 244.2, 102.0, 238.8, 103.2, 232.2, 103.8, 223.8, 103.2, 220.8, 102.0, 211.8, 104.4, 208.2, 112.8, 204.0, 129.0, 202.2, 147.0, 202.2, 169.2, 204.6, 178.2, 204.6, 222.6, 207.0, 239.4, 207.0, 249.6, 202.8, 249.6, 192.0, 224.4, 139.2, 187.8, 123.6, 166.2, 117.6, 163.8, 95.4, 167.4, 79.8, 165.6, 69.0, 163.8, 66.0, 161.4, 67.2, 152.4, 42.6, 147.6, 35.4, 135.0, 30.0, 117.0, 24.0, 105.6, 31.8, 94.8, 46.2, 93.6, 61.2, 94.8, 76.2, 100.8, 92.4, 106.8, 108.0, 112.2, 121.2, 67.2, 141.0, 40.8, 158.4, 21.6, 213.6]], "area": 24222.95999999999, "iscrowd": 0, "image_id": 402264, "bbox": [12.6, 24.0, 237.0, 223.2], "category_id": 1, "id": 1226370, "split": "val", "sentences": [{"tokens": ["a", "balding", "man", "with", "a", "black", "shirt", "looking", "down"], "raw": "A balding man with a black shirt looking down.", "sent_id": 42754, "sent": "a balding man with a black shirt looking down"}, {"tokens": ["a", "man", "in", "a", "black", "t", "-", "shirt", "looking", "down"], "raw": "A man in a black t-shirt looking down", "sent_id": 42755, "sent": "a man in a black t - shirt looking down"}], "file_name": "COCO_train2014_000000402264_1226370.jpg", "ann_id": 1226370, "sent_ids": [42754, 42755], "ref_id": 21436}, {"segmentation": [[109.3, 484.67, 103.55, 477.48, 148.13, 460.22, 224.36, 434.34, 270.38, 372.49, 266.07, 337.98, 286.2, 268.94, 300.58, 261.75, 260.31, 243.06, 258.88, 218.61, 247.37, 195.6, 256.0, 181.21, 251.69, 169.71, 257.44, 151.01, 273.26, 128.0, 286.2, 122.25, 329.35, 117.93, 366.74, 145.26, 363.87, 195.6, 362.43, 217.17, 391.19, 230.11, 424.27, 241.62, 424.27, 245.93, 425.0, 359.55, 425.0, 497.62, 424.27, 560.9, 244.49, 559.46, 254.56, 490.43, 256.0, 480.36, 195.6, 493.3, 179.78, 520.63, 166.83, 533.57, 151.01, 532.13, 138.07, 530.7, 129.44, 530.7, 117.93, 526.38, 120.81, 516.31, 143.82, 481.8, 117.93, 490.43]], "area": 73438.45420000001, "iscrowd": 0, "image_id": 512561, "bbox": [103.55, 117.93, 321.45, 442.97], "category_id": 1, "id": 513172, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "a", "lanyard", ",", "holding", "a", "wii", "remote", "control"], "raw": "A man in a white shirt and a lanyard, holding a Wii remote control.", "sent_id": 42756, "sent": "a man in a white shirt and a lanyard , holding a wii remote control"}, {"tokens": ["a", "man", "with", "hairy", "forearms", "and", "a", "receding", "hair", "line", "holding", "a", "toy", "steering", "wheel"], "raw": "A man with hairy forearms and a receding hair line holding a toy steering wheel.", "sent_id": 42757, "sent": "a man with hairy forearms and a receding hair line holding a toy steering wheel"}], "file_name": "COCO_train2014_000000512561_513172.jpg", "ann_id": 513172, "sent_ids": [42756, 42757], "ref_id": 21437}, {"segmentation": [[167.98, 341.98, 195.75, 330.87, 194.36, 393.35, 149.93, 371.14, 163.82, 346.15], [249.89, 326.71, 317.92, 321.16, 373.45, 360.03, 329.02, 362.81, 308.2, 386.41, 251.28, 391.96, 236.01, 393.35, 229.07, 362.81, 240.17, 337.82]], "area": 8291.813900000001, "iscrowd": 0, "image_id": 360002, "bbox": [149.93, 321.16, 223.52, 72.19], "category_id": 3, "id": 133906, "split": "val", "sentences": [{"tokens": ["a", "red", "sedan"], "raw": "a red sedan.", "sent_id": 42768, "sent": "a red sedan"}, {"tokens": ["a", "red", "car"], "raw": "a red car", "sent_id": 42769, "sent": "a red car"}], "file_name": "COCO_train2014_000000360002_133906.jpg", "ann_id": 133906, "sent_ids": [42768, 42769], "ref_id": 21441}, {"segmentation": [[65.8, 3.24, 62.56, 298.79, 88.45, 271.82, 73.35, 186.61, 94.92, 108.94, 163.96, 40.99, 201.71, 53.93, 224.36, 87.37, 261.03, 84.13, 325.75, 28.04, 406.65, 80.9, 439.01, 183.37, 420.67, 269.66, 528.54, 252.4, 537.17, 232.99, 537.17, 232.99, 499.42, 169.35, 509.12, 149.93, 595.42, 238.38, 636.4, 209.26, 629.93, 126.2, 640.0, 112.18, 544.72, 0.0]], "area": 70622.28854999998, "iscrowd": 0, "image_id": 11282, "bbox": [62.56, 0.0, 577.44, 298.79], "category_id": 1, "id": 1736453, "split": "val", "sentences": [{"tokens": ["person", "behind", "the", "brown", "donut"], "raw": "Person behind the brown donut.", "sent_id": 42772, "sent": "person behind the brown donut"}, {"tokens": ["the", "person", "in", "the", "black", "sweater", "with", "the", "white", "zipper"], "raw": "The person in the black sweater with the white zipper.", "sent_id": 42773, "sent": "the person in the black sweater with the white zipper"}], "file_name": "COCO_train2014_000000011282_1736453.jpg", "ann_id": 1736453, "sent_ids": [42772, 42773], "ref_id": 21443}, {"segmentation": [[71.38, 159.33, 35.69, 179.72, 34.41, 228.16, 67.56, 279.14, 112.17, 298.26, 170.8, 285.52, 187.37, 252.38, 188.64, 212.86, 205.21, 228.16, 230.71, 260.02, 240.9, 274.04, 249.83, 298.26, 285.52, 319.93, 331.4, 326.3, 369.64, 311.01, 373.47, 316.11, 365.82, 349.25, 367.09, 347.97, 374.74, 325.03, 398.96, 331.4, 410.43, 336.5, 439.75, 331.4, 472.89, 356.9, 545.54, 363.27, 597.8, 349.25, 636.04, 294.44, 624.57, 234.53, 590.15, 198.84, 527.7, 188.64, 490.73, 189.92, 461.41, 215.41, 441.02, 206.49, 432.1, 203.94, 411.7, 221.79, 412.98, 189.92, 420.63, 146.58, 406.61, 147.86, 372.19, 126.19, 299.54, 126.19, 265.12, 119.81, 253.65, 122.36, 220.51, 121.09, 234.53, 99.42, 288.07, 93.05, 313.56, 98.15, 311.01, 86.67, 248.55, 63.73, 209.04, 77.75, 136.39, 93.05, 145.31, 105.79, 119.81, 112.17, 108.34, 90.5, 35.69, 84.13, 28.04, 94.32, 28.04, 117.27, 72.65, 127.46, 66.28, 141.48, 71.38, 154.23]], "area": 102192.13845000001, "iscrowd": 0, "image_id": 343158, "bbox": [28.04, 63.73, 608.0, 299.54], "category_id": 4, "id": 1792058, "split": "val", "sentences": [{"tokens": ["the", "black", ",", "silver", ",", "and", "red", "motorcycle", "in", "the", "front"], "raw": "The black,silver,and red motorcycle in the front.", "sent_id": 42805, "sent": "the black , silver , and red motorcycle in the front"}, {"tokens": ["the", "motorcycle", "closest", "to", "the", "camera"], "raw": "The motorcycle closest to the camera.", "sent_id": 42806, "sent": "the motorcycle closest to the camera"}], "file_name": "COCO_train2014_000000343158_1792058.jpg", "ann_id": 1792058, "sent_ids": [42805, 42806], "ref_id": 21455}, {"segmentation": [[260.61, 281.99, 244.57, 286.0, 233.55, 283.0, 233.55, 265.96, 233.55, 260.94, 219.51, 258.94, 215.5, 246.91, 213.5, 226.86, 211.5, 210.83, 216.51, 189.78, 224.53, 178.75, 231.54, 171.74, 239.56, 167.73, 255.6, 165.72, 269.63, 164.72, 286.67, 164.72, 301.71, 164.72, 304.71, 175.74, 301.71, 183.76, 300.7, 198.8, 297.7, 210.83, 296.69, 214.84, 302.71, 236.89, 310.73, 254.93, 312.73, 264.95, 301.71, 271.97, 297.7, 273.97, 297.7, 287.01, 299.7, 294.02, 287.67, 288.01, 271.64, 271.97, 269.63, 261.95, 264.62, 254.93, 258.61, 262.95, 262.62, 272.97, 257.6, 280.99], [263.62, 295.02, 265.62, 273.97, 293.69, 307.05, 270.63, 300.04, 266.62, 289.01]], "area": 9768.123399999997, "iscrowd": 0, "image_id": 81372, "bbox": [211.5, 164.72, 101.23, 142.33], "category_id": 88, "id": 1161034, "split": "val", "sentences": [{"tokens": ["a", "small", "blonde", "teddy", "bear", "with", "a", "pink", "bow", "sitting", "in", "the", "lap", "of", "a", "larger", "teddy", "bear"], "raw": "A small blonde teddy bear with a pink bow sitting in the lap of a larger teddy bear", "sent_id": 42830, "sent": "a small blonde teddy bear with a pink bow sitting in the lap of a larger teddy bear"}, {"tokens": ["a", "teddy", "bear", "with", "a", "pink", "ribbon", "around", "its", "neck", "sitting", "on", "a", "bigger", "teddy", "bear", "'", "s", "lap"], "raw": "A teddy bear with a pink ribbon around its neck sitting on a bigger teddy bear's lap.", "sent_id": 42831, "sent": "a teddy bear with a pink ribbon around its neck sitting on a bigger teddy bear ' s lap"}], "file_name": "COCO_train2014_000000081372_1161034.jpg", "ann_id": 1161034, "sent_ids": [42830, 42831], "ref_id": 21463}, {"segmentation": [[298.62, 363.07, 242.76, 311.51, 233.09, 316.88, 228.8, 309.36, 235.24, 299.69, 415.7, 267.47, 480.15, 312.58]], "area": 12719.843049999994, "iscrowd": 0, "image_id": 155107, "bbox": [228.8, 267.47, 251.35, 95.6], "category_id": 76, "id": 1116219, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "gray", "wireless", "keyboard", "for", "a", "desktop", "computer"], "raw": "A white and gray wireless keyboard for a desktop computer.", "sent_id": 42844, "sent": "a white and gray wireless keyboard for a desktop computer"}, {"tokens": ["white", "keyboard", "sitting", "in", "front", "of", "an", "imac", "computer", "on", "a", "desk"], "raw": "white keyboard sitting in front of an iMac computer on a desk", "sent_id": 42845, "sent": "white keyboard sitting in front of an imac computer on a desk"}], "file_name": "COCO_train2014_000000155107_1116219.jpg", "ann_id": 1116219, "sent_ids": [42844, 42845], "ref_id": 21466}, {"segmentation": [[220.13, 300.77, 237.32, 290.04, 279.19, 278.22, 308.19, 325.47, 355.44, 416.75, 387.65, 446.82, 388.72, 474.73, 584.16, 472.59, 560.54, 445.74, 497.18, 423.19, 474.63, 406.01, 448.86, 381.31, 400.54, 357.69, 356.51, 307.22, 301.74, 233.12, 289.93, 230.98, 274.9, 223.46, 273.83, 195.54, 263.09, 205.2, 262.01, 219.16, 234.09, 244.94, 199.73, 291.11, 202.95, 301.85]], "area": 26761.525699999995, "iscrowd": 0, "image_id": 444346, "bbox": [199.73, 195.54, 384.43, 279.19], "category_id": 25, "id": 596317, "split": "val", "sentences": [{"tokens": ["giraffe", "looking", "to", "the", "left", "side"], "raw": "giraffe looking to the left side", "sent_id": 42911, "sent": "giraffe looking to the left side"}, {"tokens": ["two", "giraffes", "in", "wilderness", "crossing", "their", "necks"], "raw": "Two giraffes in wilderness crossing their necks.", "sent_id": 42912, "sent": "two giraffes in wilderness crossing their necks"}], "file_name": "COCO_train2014_000000444346_596317.jpg", "ann_id": 596317, "sent_ids": [42911, 42912], "ref_id": 21495}, {"segmentation": [[12.91, 261.47, 228.16, 243.17, 481.08, 250.71, 640.0, 266.85, 637.13, 473.49, 1.08, 473.49, 1.08, 263.62, 12.91, 258.24]], "area": 141245.63809999998, "iscrowd": 0, "image_id": 92323, "bbox": [1.08, 243.17, 638.92, 230.32], "category_id": 67, "id": 390645, "split": "val", "sentences": [{"tokens": ["a", "toasted", "sandwich", "is", "shown", "on", "a", "plate", "in", "an", "outdoor", "dining", "area"], "raw": "A toasted sandwich is shown on a plate in an outdoor dining area.", "sent_id": 42937, "sent": "a toasted sandwich is shown on a plate in an outdoor dining area"}, {"tokens": ["a", "sandwich", "on", "a", "tabletop"], "raw": "a sandwich on a tabletop", "sent_id": 42938, "sent": "a sandwich on a tabletop"}], "file_name": "COCO_train2014_000000092323_390645.jpg", "ann_id": 390645, "sent_ids": [42937, 42938], "ref_id": 21504}, {"segmentation": [[210.35, 421.3, 210.35, 417.46, 215.15, 400.19, 228.58, 375.24, 237.22, 367.56, 250.65, 357.01, 263.13, 350.29, 276.56, 344.53, 288.07, 340.7, 327.42, 333.02, 337.01, 333.02, 348.53, 333.02, 361.96, 335.9, 371.56, 340.7, 380.19, 349.33, 406.1, 374.28, 418.57, 393.47, 418.57, 412.66, 416.65, 418.42, 419.53, 424.18, 215.15, 427.0]], "area": 15172.234800000002, "iscrowd": 0, "image_id": 83000, "bbox": [210.35, 333.02, 209.18, 93.98], "category_id": 51, "id": 1540636, "split": "val", "sentences": [{"tokens": ["a", "metal", "bowl", "with", "dough", "in", "it"], "raw": "A metal bowl with dough in it.", "sent_id": 43099, "sent": "a metal bowl with dough in it"}], "file_name": "COCO_train2014_000000083000_1540636.jpg", "ann_id": 1540636, "sent_ids": [43099], "ref_id": 21567}, {"segmentation": [[293.64, 84.97, 382.28, 71.46, 437.99, 73.15, 476.82, 79.06, 542.67, 185.42, 548.58, 279.97, 544.36, 307.83, 539.29, 323.02, 535.91, 324.71, 529.17, 316.27, 503.84, 326.4, 504.68, 347.5, 499.62, 350.04, 485.27, 350.88, 464.16, 336.53, 453.19, 333.15, 345.13, 338.22, 341.76, 342.44, 335.01, 359.32, 322.34, 365.23, 311.37, 361.85, 306.3, 353.41, 302.92, 339.07, 272.54, 337.38, 267.47, 286.72, 270.85, 280.82, 274.23, 179.52, 281.82, 103.54]], "area": 66956.76495, "iscrowd": 0, "image_id": 273439, "bbox": [267.47, 71.46, 281.11, 293.77], "category_id": 6, "id": 165984, "split": "val", "sentences": [{"tokens": ["a", "bus", "that", "is", "close", "to", "the", "camera"], "raw": "A bus that is close to the camera", "sent_id": 43124, "sent": "a bus that is close to the camera"}, {"tokens": ["a", "fullington", "bus", "being", "cheered", "on", "its", "way", "into", "town"], "raw": "A Fullington bus being cheered on its way into town.", "sent_id": 43125, "sent": "a fullington bus being cheered on its way into town"}], "file_name": "COCO_train2014_000000273439_165984.jpg", "ann_id": 165984, "sent_ids": [43124, 43125], "ref_id": 21576}, {"segmentation": [[51.82, 342.53, 53.71, 237.21, 39.48, 250.49, 48.97, 204.0, 56.56, 128.09, 84.08, 98.67, 157.14, 94.88, 201.74, 100.57, 276.7, 165.1, 257.72, 221.08, 246.33, 270.42, 248.23, 309.32, 227.36, 307.42, 212.17, 260.93, 181.81, 257.13, 163.78, 352.02, 138.16, 352.02, 112.54, 318.81, 104.0, 247.65, 99.26, 228.67, 80.28, 266.62, 77.44, 340.63, 85.98, 341.58, 88.82, 344.43, 54.66, 356.76]], "area": 40824.4653, "iscrowd": 0, "image_id": 142825, "bbox": [39.48, 94.88, 237.22, 261.88], "category_id": 22, "id": 581590, "split": "val", "sentences": [{"tokens": ["gray", "elephant", "standing", "on", "dirt", "and", "leaves"], "raw": "Gray elephant standing on dirt and leaves.", "sent_id": 43220, "sent": "gray elephant standing on dirt and leaves"}, {"tokens": ["a", "eliphant", "in", "the", "place"], "raw": "a eliphant in the place", "sent_id": 43221, "sent": "a eliphant in the place"}], "file_name": "COCO_train2014_000000142825_581590.jpg", "ann_id": 581590, "sent_ids": [43220, 43221], "ref_id": 21610}, {"segmentation": [[344.8, 307.97, 365.77, 369.21, 392.62, 369.21, 371.64, 303.77, 370.81, 287.83, 360.74, 296.22, 359.9, 304.61, 352.35, 308.81], [324.66, 153.6, 328.02, 142.7, 331.38, 135.99, 333.05, 130.95, 340.6, 124.24, 347.32, 123.4, 354.03, 126.76, 354.03, 126.76, 359.9, 118.37, 362.42, 113.34, 369.13, 112.5, 375.84, 113.34, 378.36, 115.01, 377.52, 120.89, 368.29, 127.6, 362.42, 128.44, 359.9, 129.28, 367.45, 146.89, 369.13, 159.48, 370.81, 167.87, 375.0, 182.13, 369.97, 187.16, 368.29, 199.75, 364.09, 227.43, 373.32, 271.89, 354.03, 229.95, 343.12, 205.62, 339.77, 180.45]], "area": 5480.433650000001, "iscrowd": 0, "image_id": 377019, "bbox": [324.66, 112.5, 67.96, 256.71], "category_id": 1, "id": 195187, "split": "val", "sentences": [{"tokens": ["a", "boy", "playing", "video", "game", "with", "his", "friends"], "raw": "A boy playing video game with his friends", "sent_id": 43222, "sent": "a boy playing video game with his friends"}, {"tokens": ["a", "young", "boy", "holding", "up", "a", "wii", "remote", "and", "facing", "the", "tv"], "raw": "A young boy holding up a wii remote and facing the tv", "sent_id": 43223, "sent": "a young boy holding up a wii remote and facing the tv"}], "file_name": "COCO_train2014_000000377019_195187.jpg", "ann_id": 195187, "sent_ids": [43222, 43223], "ref_id": 21611}, {"segmentation": [[378.86, 307.36, 376.63, 289.53, 377.74, 280.61, 361.03, 263.9, 354.34, 236.04, 367.71, 208.19, 381.09, 152.47, 391.11, 131.3, 422.31, 114.59, 441.26, 107.9, 437.91, 92.3, 442.37, 63.33, 473.57, 34.36, 508.11, 34.36, 528.17, 45.5, 538.2, 70.01, 540.43, 87.84, 537.09, 113.47, 568.29, 136.87, 581.66, 170.3, 581.66, 209.3, 566.06, 282.84, 556.03, 273.93, 531.51, 282.84, 499.2, 289.53, 425.66, 306.24, 404.49, 310.7, 398.91, 306.24, 385.54, 305.13]], "area": 42915.61189999999, "iscrowd": 0, "image_id": 58403, "bbox": [354.34, 34.36, 227.32, 276.34], "category_id": 1, "id": 2155959, "split": "val", "sentences": [{"tokens": ["woman", "in", "blue", "shirt"], "raw": "woman in blue shirt", "sent_id": 43384, "sent": "woman in blue shirt"}, {"tokens": ["a", "girl", "wearing", "blue", "colored", "top", "holding", "a", "spoon", "in", "her", "hands"], "raw": "A Girl wearing blue colored top holding a spoon in her hands", "sent_id": 43385, "sent": "a girl wearing blue colored top holding a spoon in her hands"}], "file_name": "COCO_train2014_000000058403_2155959.jpg", "ann_id": 2155959, "sent_ids": [43384, 43385], "ref_id": 21670}, {"segmentation": [[386.88, 434.34, 384.0, 388.31, 395.51, 362.43, 405.57, 323.6, 394.07, 276.13, 388.31, 261.75, 362.43, 243.06, 352.36, 227.24, 343.73, 189.84, 333.66, 163.96, 325.03, 142.38, 320.72, 128.0, 313.53, 116.49, 286.2, 112.18, 264.63, 109.3, 224.36, 113.62, 220.04, 117.93, 220.04, 148.13, 211.42, 199.91, 202.79, 221.48, 202.79, 243.06, 192.72, 289.08, 182.65, 316.4, 181.21, 340.85, 182.65, 371.06, 179.78, 398.38, 171.15, 419.96, 174.02, 432.9, 179.78, 451.6, 207.1, 464.54, 221.48, 464.54, 270.38, 450.16, 325.03, 450.16, 358.11, 447.28, 411.33, 434.34, 391.19, 430.02]], "area": 59848.249749999995, "iscrowd": 0, "image_id": 316671, "bbox": [171.15, 109.3, 240.18, 355.24], "category_id": 1, "id": 433014, "split": "val", "sentences": [{"tokens": ["lady", "holding", "glass", "on", "the", "hand"], "raw": "lady holding glass on the hand", "sent_id": 43402, "sent": "lady holding glass on the hand"}, {"tokens": ["a", "woman", "in", "a", "black", "dress", "is", "making", "a", "strange", "face", "while", "reaching", "for", "her", "wine", "glass", "which", "is", "on", "a", "table", "with", "food", "and", "dishes"], "raw": "a woman in a black dress is making a strange face while reaching for her wine glass which is on a table with food and dishes", "sent_id": 43403, "sent": "a woman in a black dress is making a strange face while reaching for her wine glass which is on a table with food and dishes"}], "file_name": "COCO_train2014_000000316671_433014.jpg", "ann_id": 433014, "sent_ids": [43402, 43403], "ref_id": 21676}, {"segmentation": [[284.08, 418.36, 273.68, 417.06, 258.09, 419.65, 256.79, 433.3, 252.25, 425.5, 247.05, 415.11, 239.9, 415.11, 232.11, 413.81, 219.76, 396.27, 208.72, 378.73, 200.27, 381.33, 201.57, 411.21, 205.47, 432.65, 203.52, 443.04, 203.52, 453.44, 208.72, 452.79, 210.02, 436.55, 216.51, 434.6, 219.11, 446.29, 215.86, 450.19, 217.81, 456.68, 212.62, 468.38, 204.82, 480.72, 203.52, 502.81, 208.72, 517.1, 215.86, 528.15, 228.21, 541.79, 258.09, 548.29, 273.68, 538.54, 281.48, 526.85, 291.22, 525.55, 296.42, 527.5, 297.07, 532.04, 302.92, 531.4, 304.87, 528.8, 314.61, 539.19, 320.46, 540.49, 321.11, 534.64, 312.01, 528.15, 315.26, 517.75, 317.21, 514.5, 327.6, 522.95, 343.85, 517.75, 346.44, 515.15, 347.74, 530.75, 362.04, 550.88, 386.72, 566.48, 420.51, 560.63, 442.59, 538.54, 446.49, 506.06, 437.4, 482.67, 414.01, 465.78, 394.52, 458.63, 391.92, 450.19, 370.48, 452.79, 369.18, 426.8, 374.38, 394.32, 371.78, 383.92, 359.44, 383.27, 335.4, 385.22, 338.0, 374.83, 327.6, 372.23, 321.11, 378.73, 319.16, 385.87, 307.47, 385.77, 299.67, 392.92, 310.71, 397.46, 323.06, 400.06, 314.61, 407.86, 334.1, 403.31, 338.65, 402.66, 345.8, 405.26, 349.69, 416.95, 352.94, 435.79, 356.84, 446.84, 346.44, 472.82, 336.05, 486.65, 315.91, 489.9, 302.27, 486.65, 290.57, 469.76, 282.78, 435.98, 280.83, 430.13, 289.28, 424.28, 289.28, 419.08, 286.68, 419.08]], "area": 23997.104699999996, "iscrowd": 0, "image_id": 520063, "bbox": [200.27, 372.23, 246.22, 194.25], "category_id": 2, "id": 125877, "split": "val", "sentences": [{"tokens": ["dark", "bike", "parked", "in", "the", "street"], "raw": "dark bike parked in the street", "sent_id": 43452, "sent": "dark bike parked in the street"}, {"tokens": ["a", "parked", "bike", "with", "a", "passenger", "seat", "on", "the", "back"], "raw": "A parked bike with a passenger seat on the back.", "sent_id": 43453, "sent": "a parked bike with a passenger seat on the back"}], "file_name": "COCO_train2014_000000520063_125877.jpg", "ann_id": 125877, "sent_ids": [43452, 43453], "ref_id": 21695}, {"segmentation": [[127.62, 244.69, 121.86, 308.02, 122.82, 335.84, 140.09, 364.63, 164.08, 382.86, 175.6, 409.73, 176.56, 427.0, 187.11, 427.0, 187.11, 401.09, 193.83, 372.31, 221.66, 351.2, 230.29, 318.57, 222.62, 270.59, 214.94, 235.09, 163.12, 235.09, 131.46, 238.93, 129.54, 243.73]], "area": 13940.494, "iscrowd": 0, "image_id": 235582, "bbox": [121.86, 235.09, 108.43, 191.91], "category_id": 46, "id": 662369, "split": "val", "sentences": [{"tokens": ["an", "empty", "wine", "glass", "on", "the", "table", "with", "the", "birthday", "cake", "with", "candles"], "raw": "An empty wine glass on the table with the birthday cake with candles.", "sent_id": 43457, "sent": "an empty wine glass on the table with the birthday cake with candles"}, {"tokens": ["the", "wine", "glass", "in", "front", "of", "the", "picture"], "raw": "the wine glass in front of the picture", "sent_id": 43458, "sent": "the wine glass in front of the picture"}], "file_name": "COCO_train2014_000000235582_662369.jpg", "ann_id": 662369, "sent_ids": [43457, 43458], "ref_id": 21698}, {"segmentation": [[353.8, 6.32, 341.6, 56.23, 357.13, 96.16, 371.55, 110.58, 375.98, 129.43, 359.35, 131.65, 349.36, 139.41, 371.55, 164.92, 379.31, 185.99, 375.98, 221.49, 403.71, 249.21, 425.89, 237.01, 444.75, 232.58, 465.82, 214.83, 458.05, 199.3, 463.6, 171.58, 475.8, 162.7, 504.64, 160.49, 527.93, 153.83, 547.89, 142.74, 554.55, 126.1, 540.13, 109.47, 577.84, 69.54, 577.84, 59.56, 601.13, 38.49, 596.69, 0.78]], "area": 39923.09145, "iscrowd": 0, "image_id": 197289, "bbox": [341.6, 0.78, 259.53, 248.43], "category_id": 54, "id": 1909039, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "on", "the", "right", "side", "of", "the", "plate", "has", "tomato", "on", "it"], "raw": "The sandwich on the right side of the plate has tomato on it.", "sent_id": 43459, "sent": "the sandwich on the right side of the plate has tomato on it"}], "file_name": "COCO_train2014_000000197289_1909039.jpg", "ann_id": 1909039, "sent_ids": [43459], "ref_id": 21699}, {"segmentation": [[67.96, 53.93, 88.45, 97.08, 231.91, 107.87, 320.36, 102.47, 347.33, 100.31, 351.64, 89.53, 375.37, 90.61, 373.21, 51.78, 347.33, 55.01, 248.09, 49.62, 188.76, 50.7, 169.35, 49.62, 136.99, 49.62, 73.35, 49.62]], "area": 15111.832, "iscrowd": 0, "image_id": 510027, "bbox": [67.96, 49.62, 307.41, 58.25], "category_id": 54, "id": 311773, "split": "val", "sentences": [{"tokens": ["half", "of", "an", "egg", "salad", "sandwich", "with", "the", "other", "half", "below", "it"], "raw": "Half of an egg salad sandwich with the other half below it.", "sent_id": 43481, "sent": "half of an egg salad sandwich with the other half below it"}, {"tokens": ["the", "very", "top", "piece", "of", "bread", "on", "the", "top", "slice", "of", "sandwich"], "raw": "The very top piece of bread on the top slice of sandwich.", "sent_id": 43482, "sent": "the very top piece of bread on the top slice of sandwich"}], "file_name": "COCO_train2014_000000510027_311773.jpg", "ann_id": 311773, "sent_ids": [43481, 43482], "ref_id": 21707}, {"segmentation": [[254.53, 176.42, 375.0, 186.14, 440.09, 185.17, 456.61, 190.03, 468.26, 184.2, 500.0, 174.48, 498.38, 214.31, 476.04, 214.31, 466.32, 219.17, 435.23, 251.23, 371.11, 235.69, 281.74, 211.4, 250.65, 201.68]], "area": 10903.99365, "iscrowd": 0, "image_id": 335376, "bbox": [250.65, 174.48, 249.35, 76.75], "category_id": 49, "id": 1892617, "split": "val", "sentences": [{"tokens": ["the", "metal", "pizza", "knife", "with", "the", "wooden", "handle"], "raw": "The metal pizza knife with the wooden handle.", "sent_id": 43497, "sent": "the metal pizza knife with the wooden handle"}, {"tokens": ["the", "pizza", "serving", "utensil"], "raw": "The pizza serving utensil.", "sent_id": 43498, "sent": "the pizza serving utensil"}], "file_name": "COCO_train2014_000000335376_1892617.jpg", "ann_id": 1892617, "sent_ids": [43497, 43498], "ref_id": 21712}, {"segmentation": [[504.41, 339.61, 501.13, 335.85, 512.39, 326.46, 516.62, 314.72, 519.44, 302.99, 524.6, 291.25, 536.81, 292.19, 543.38, 295.94, 553.24, 296.41, 553.24, 293.13, 568.74, 295.0, 570.61, 295.94, 580.47, 295.47, 597.85, 299.23, 614.28, 298.29, 626.49, 295.94, 631.65, 295.47, 629.3, 305.33, 640.0, 310.03, 639.63, 404.87, 639.63, 479.99, 323.18, 479.52, 286.09, 479.99, 287.5, 458.86, 291.25, 438.2, 294.07, 416.14, 302.05, 396.89, 310.97, 384.68, 326.0, 377.17, 347.13, 372.0, 379.99, 364.02, 412.39, 358.86, 431.64, 352.28, 452.3, 347.59, 475.77, 345.24, 492.67, 341.48]], "area": 49379.22469999999, "iscrowd": 0, "image_id": 238630, "bbox": [286.09, 291.25, 353.91, 188.74], "category_id": 65, "id": 315729, "split": "val", "sentences": [{"tokens": ["a", "made", "bed", "to", "the", "right", "of", "the", "photo"], "raw": "A made bed to the right of the photo.", "sent_id": 43512, "sent": "a made bed to the right of the photo"}, {"tokens": ["the", "bed", "closest", "to", "the", "viewer"], "raw": "The bed closest to the viewer", "sent_id": 43513, "sent": "the bed closest to the viewer"}], "file_name": "COCO_train2014_000000238630_315729.jpg", "ann_id": 315729, "sent_ids": [43512, 43513], "ref_id": 21718}, {"segmentation": [[232.38, 286.15, 276.85, 222.4, 322.99, 204.78, 318.79, 156.96, 323.83, 132.63, 336.41, 111.66, 372.48, 101.59, 405.2, 110.82, 418.62, 135.99, 421.14, 166.19, 397.65, 213.17, 451.34, 245.89, 479.87, 286.99, 479.03, 370.05, 425.34, 368.37, 380.87, 368.37, 380.87, 363.34, 400.17, 361.66, 397.65, 350.75, 413.59, 349.91, 401.85, 328.1, 397.65, 338.17, 335.57, 323.91, 254.19, 323.07, 225.67, 329.78, 248.32, 345.72, 260.91, 358.3, 247.48, 365.85, 222.32, 368.37, 217.28, 315.52, 225.67, 296.22]], "area": 38086.704, "iscrowd": 0, "image_id": 99451, "bbox": [217.28, 101.59, 262.59, 268.46], "category_id": 1, "id": 508469, "split": "val", "sentences": [{"tokens": ["boy", "with", "black", "and", "gray", "shirt", ",", "longer", "brown", "hair"], "raw": "Boy with black and gray shirt, longer brown hair.", "sent_id": 43547, "sent": "boy with black and gray shirt , longer brown hair"}], "file_name": "COCO_train2014_000000099451_508469.jpg", "ann_id": 508469, "sent_ids": [43547], "ref_id": 21731}, {"segmentation": [[164.32, 475.14, 170.81, 427.57, 139.46, 432.97, 125.41, 427.57, 111.35, 427.57, 105.95, 424.32, 99.46, 409.19, 98.38, 392.97, 98.38, 362.7, 117.84, 352.97, 125.41, 340.0, 132.97, 318.38, 144.86, 332.43, 152.43, 335.68, 169.73, 324.86, 176.22, 319.46, 189.19, 297.84, 198.92, 292.43, 190.27, 255.68, 182.7, 239.46, 166.49, 238.38, 150.27, 228.65, 151.35, 222.16, 161.08, 220.0, 172.97, 214.59, 165.41, 196.22, 155.68, 175.68, 142.7, 169.19, 121.08, 172.43, 110.27, 176.76, 103.78, 188.65, 103.78, 208.11, 104.86, 220.0, 108.11, 236.22, 90.81, 244.86, 74.59, 292.43, 78.92, 297.84, 69.19, 322.7, 44.32, 364.86, 30.27, 399.46, 41.08, 426.49, 52.97, 430.81, 55.14, 409.19, 54.05, 387.57, 69.19, 368.11, 82.16, 351.89, 76.76, 394.05, 83.24, 452.43, 87.57, 472.97]], "area": 22141.394549999997, "iscrowd": 0, "image_id": 115505, "bbox": [30.27, 169.19, 168.65, 305.95], "category_id": 1, "id": 1201428, "split": "val", "sentences": [{"tokens": ["a", "young", "woman", "who", "is", "standing", "by", "a", "building", "and", "talking", "on", "a", "cellphone"], "raw": "A young woman who is standing by a building and talking on a cellphone.", "sent_id": 43556, "sent": "a young woman who is standing by a building and talking on a cellphone"}, {"tokens": ["the", "woman", "in", "black", "outfit"], "raw": "The woman in black outfit", "sent_id": 43557, "sent": "the woman in black outfit"}], "file_name": "COCO_train2014_000000115505_1201428.jpg", "ann_id": 1201428, "sent_ids": [43556, 43557], "ref_id": 21734}, {"segmentation": [[5.55, 372.65, 28.84, 326.07, 48.8, 306.11, 66.55, 289.47, 76.53, 272.84, 2.22, 82.07, 2.22, 378.2]], "area": 10600.934400000002, "iscrowd": 0, "image_id": 183435, "bbox": [2.22, 82.07, 74.31, 296.13], "category_id": 62, "id": 1936071, "split": "val", "sentences": [{"tokens": ["the", "chair", "on", "the", "left", "of", "the", "fruit"], "raw": "the chair on the left of the fruit", "sent_id": 43597, "sent": "the chair on the left of the fruit"}, {"tokens": ["a", "chair", "near", "to", "the", "table", "full", "of", "vegetables"], "raw": "A chair near to the table full of vegetables", "sent_id": 43598, "sent": "a chair near to the table full of vegetables"}], "file_name": "COCO_train2014_000000183435_1936071.jpg", "ann_id": 1936071, "sent_ids": [43597, 43598], "ref_id": 21750}, {"segmentation": [[414.84, 15.02, 409.36, 25.98, 411.19, 79.9, 473.34, 79.9, 494.35, 108.24, 513.54, 121.94, 527.25, 137.47, 534.57, 163.07, 519.02, 196.88, 511.72, 214.24, 514.45, 295.57, 517.2, 318.42, 591.22, 320.25, 582.08, 367.77, 606.75, 378.73, 621.38, 363.2, 623.21, 338.53, 626.86, 315.68, 640.0, 313.85, 639.66, 0.39, 416.68, 1.31]], "area": 50096.74424999999, "iscrowd": 0, "image_id": 293966, "bbox": [409.36, 0.39, 230.64, 378.34], "category_id": 8, "id": 395929, "split": "val", "sentences": [{"tokens": ["a", "red", "trailer", "on", "the", "right", "side", "of", "the", "picture"], "raw": "A red trailer on the right side of the picture", "sent_id": 43674, "sent": "a red trailer on the right side of the picture"}], "file_name": "COCO_train2014_000000293966_395929.jpg", "ann_id": 395929, "sent_ids": [43674], "ref_id": 21780}, {"segmentation": [[207.79, 399.88, 255.42, 399.88, 254.15, 375.11, 255.42, 355.42, 255.42, 347.8, 262.41, 338.91, 273.84, 332.56, 278.92, 330.66, 294.16, 327.48, 297.34, 326.21, 310.04, 320.5, 293.53, 303.35, 282.73, 296.36, 276.38, 284.93, 271.3, 277.95, 263.04, 272.23, 253.52, 265.25, 244.63, 264.61, 227.48, 276.68, 200.17, 300.81, 189.38, 321.13, 197.0, 343.99, 199.54, 356.69, 202.71, 392.89]], "area": 8994.770300000002, "iscrowd": 0, "image_id": 455117, "bbox": [189.38, 264.61, 120.66, 135.27], "category_id": 22, "id": 582982, "split": "val", "sentences": [{"tokens": ["the", "backside", "of", "the", "biggest", "elephant"], "raw": "The backside of the biggest elephant.", "sent_id": 43675, "sent": "the backside of the biggest elephant"}, {"tokens": ["back", "of", "an", "adult", "elephant", "with", "two", "baby", "elephants", "flanking", "it", ".", "one", "baby", "elephant", "has", "spikey", "brown", "hair"], "raw": "Back of an adult elephant with two baby elephants flanking it.  One baby elephant has spikey brown hair.", "sent_id": 43676, "sent": "back of an adult elephant with two baby elephants flanking it . one baby elephant has spikey brown hair"}], "file_name": "COCO_train2014_000000455117_582982.jpg", "ann_id": 582982, "sent_ids": [43675, 43676], "ref_id": 21781}, {"segmentation": [[181.21, 463.64, 281.53, 419.42, 262.11, 417.26, 323.6, 352.54, 334.38, 329.89, 336.54, 294.29, 348.4, 252.22, 355.96, 223.1, 376.45, 182.11, 371.06, 156.22, 347.33, 137.89, 331.15, 122.79, 307.42, 114.16, 286.92, 109.84, 269.66, 102.29, 241.62, 91.51, 226.52, 90.43, 200.63, 96.9, 161.8, 104.45, 143.46, 118.47, 107.87, 140.04, 78.74, 209.08, 60.4, 265.17, 52.85, 287.82, 62.56, 296.45, 99.24, 339.6, 126.2, 362.25, 133.75, 410.79, 132.67, 412.94, 153.17, 451.78, 179.06, 451.78]], "area": 79320.07475000001, "iscrowd": 0, "image_id": 428407, "bbox": [52.85, 90.43, 323.6, 373.21], "category_id": 53, "id": 1551883, "split": "val", "sentences": [{"tokens": ["a", "bunch", "of", "apples", "in", "a", "sack"], "raw": "A bunch of apples in a sack.", "sent_id": 43738, "sent": "a bunch of apples in a sack"}, {"tokens": ["a", "bag", "of", "green", "apples"], "raw": "a bag of green apples", "sent_id": 43739, "sent": "a bag of green apples"}], "file_name": "COCO_train2014_000000428407_1551883.jpg", "ann_id": 1551883, "sent_ids": [43738, 43739], "ref_id": 21803}, {"segmentation": [[248.21, 265.51, 225.5, 239.67, 212.98, 234.19, 216.11, 209.92, 279.53, 210.7, 284.23, 228.71, 320.25, 231.84, 324.16, 245.15, 343.74, 268.64, 339.82, 281.95, 338.26, 289.78, 327.29, 289.78, 313.2, 296.83, 296.76, 296.83, 291.28, 292.13, 283.45, 276.47, 271.7, 268.64]], "area": 6412.62905, "iscrowd": 0, "image_id": 234516, "bbox": [212.98, 209.92, 130.76, 86.91], "category_id": 8, "id": 395326, "split": "val", "sentences": [{"tokens": ["a", "pickup", "truck", "directly", "beneath", "the", "shadow", "of", "the", "sign"], "raw": "A pickup truck directly beneath the shadow of the sign.", "sent_id": 43800, "sent": "a pickup truck directly beneath the shadow of the sign"}, {"tokens": ["the", "truck", "parked", "inthe", "middle"], "raw": "The truck parked inthe middle.", "sent_id": 43801, "sent": "the truck parked inthe middle"}], "file_name": "COCO_train2014_000000234516_395326.jpg", "ann_id": 395326, "sent_ids": [43800, 43801], "ref_id": 21826}, {"segmentation": [[325.96, 239.01, 327.73, 228.42, 336.55, 206.36, 350.67, 197.54, 356.85, 196.65, 348.91, 179.89, 346.26, 151.64, 350.67, 134.88, 355.97, 123.4, 370.09, 120.76, 385.97, 119.87, 402.74, 132.23, 410.68, 156.94, 412.45, 172.83, 412.45, 191.36, 409.8, 198.42, 429.22, 206.36, 436.28, 221.36, 439.81, 234.6, 434.51, 236.37, 436.28, 252.25, 431.86, 252.25, 430.1, 258.43, 428.33, 269.9, 426.57, 278.73, 379.8, 287.55, 375.38, 285.79, 373.62, 260.19, 370.09, 246.07, 336.55, 246.07, 333.02, 248.72, 322.43, 250.49]], "area": 11420.371800000003, "iscrowd": 0, "image_id": 24689, "bbox": [322.43, 119.87, 117.38, 167.68], "category_id": 1, "id": 444708, "split": "val", "sentences": [{"tokens": ["a", "little", "girl", "with", "a", "blue", "dress", "is", "sitting", "at", "a", "table", "between", "an", "adult", "and", "a", "little", "boy"], "raw": "A little girl with a blue dress is sitting at a table between an adult and a little boy", "sent_id": 43880, "sent": "a little girl with a blue dress is sitting at a table between an adult and a little boy"}, {"tokens": ["little", "girl", "with", "blond", "hair", "wearing", "a", "blue", "dress", "looking", "down"], "raw": "Little girl with blond hair wearing a blue dress looking down", "sent_id": 43881, "sent": "little girl with blond hair wearing a blue dress looking down"}], "file_name": "COCO_train2014_000000024689_444708.jpg", "ann_id": 444708, "sent_ids": [43880, 43881], "ref_id": 21859}, {"segmentation": [[305.62, 148.99, 398.26, 140.39, 417.36, 157.58, 421.18, 185.28, 443.15, 212.98, 444.1, 269.33, 432.64, 297.02, 430.73, 319.94, 415.45, 338.09, 400.17, 366.74, 400.17, 374.38, 319.94, 382.02, 308.48, 359.1, 279.83, 310.39, 266.46, 266.46, 270.28, 208.2, 290.34, 179.55, 297.98, 148.99, 304.66, 149.94]], "area": 33581.71324999999, "iscrowd": 0, "image_id": 79611, "bbox": [266.46, 140.39, 177.64, 241.63], "category_id": 85, "id": 335012, "split": "val", "sentences": [{"tokens": ["clock", "mounted", "to", "wall"], "raw": "clock mounted to wall", "sent_id": 43916, "sent": "clock mounted to wall"}, {"tokens": ["a", "clock", "on", "the", "wall", "that", "says", "black", "&", "blue"], "raw": "A clock on the wall that says Black & Blue.", "sent_id": 43917, "sent": "a clock on the wall that says black & blue"}], "file_name": "COCO_train2014_000000079611_335012.jpg", "ann_id": 335012, "sent_ids": [43916, 43917], "ref_id": 21876}, {"segmentation": [[334.34, 357.45, 340.07, 271.47, 340.07, 238.04, 340.07, 207.47, 346.76, 183.59, 353.45, 177.86, 358.22, 163.53, 363.95, 128.18, 372.55, 97.62, 385.92, 83.29, 391.66, 78.51, 377.33, 51.76, 382.1, 30.75, 401.21, 20.24, 430.82, 25.02, 445.15, 44.12, 447.06, 69.91, 437.51, 78.51, 467.12, 106.21, 477.63, 127.23, 469.03, 159.71, 458.52, 177.86, 444.19, 238.04, 427.0, 278.16, 438.46, 315.41, 448.97, 347.89, 457.57, 370.82, 456.61, 384.19, 447.06, 391.83, 442.28, 384.19, 431.78, 368.91, 420.31, 351.71, 405.98, 331.65, 397.39, 302.04, 391.66, 276.25, 377.33, 270.52, 366.82, 307.77, 361.09, 335.47, 359.18, 358.4, 359.18, 379.42, 352.49, 397.57, 334.34, 399.48, 335.3, 386.1, 337.21, 374.64]], "area": 30080.921649999982, "iscrowd": 0, "image_id": 549599, "bbox": [334.34, 20.24, 143.29, 379.24], "category_id": 1, "id": 499397, "split": "val", "sentences": [{"tokens": ["a", "woman", "carrying", "a", "gray", "bag"], "raw": "A woman carrying a gray bag", "sent_id": 43926, "sent": "a woman carrying a gray bag"}, {"tokens": ["a", "lady", "in", "a", "blue", "shirt", "sits", "on", "a", "brown", "bench", "holding", "her", "purse", "in", "front", "of", "her"], "raw": "A lady in a blue shirt sits on a brown bench holding her purse in front of her.", "sent_id": 43927, "sent": "a lady in a blue shirt sits on a brown bench holding her purse in front of her"}], "file_name": "COCO_train2014_000000549599_499397.jpg", "ann_id": 499397, "sent_ids": [43926, 43927], "ref_id": 21881}, {"segmentation": [[19.02, 308.2, 80.65, 277.81, 109.31, 247.42, 148.38, 230.05, 210.9, 178.83, 265.59, 126.74, 282.95, 100.69, 295.11, 115.45, 315.08, 114.58, 319.42, 125.87, 348.94, 145.84, 349.81, 168.41, 336.79, 173.62, 323.76, 163.2, 280.36, 164.07, 259.52, 189.24, 223.05, 239.6, 149.25, 302.12, 115.39, 332.5, 37.25, 356.82, 9.46, 417.6, 3.39, 425.0, 0.0, 322.09]], "area": 22976.368800000004, "iscrowd": 0, "image_id": 8300, "bbox": [0.0, 100.69, 349.81, 324.31], "category_id": 25, "id": 599353, "split": "val", "sentences": [{"tokens": ["the", "tallest", "giraffe", "on", "the", "left"], "raw": "the tallest giraffe on the left", "sent_id": 43930, "sent": "the tallest giraffe on the left"}], "file_name": "COCO_train2014_000000008300_599353.jpg", "ann_id": 599353, "sent_ids": [43930], "ref_id": 21883}, {"segmentation": [[36.25, 237.58, 36.25, 246.61, 27.22, 250.82, 23.01, 253.23, 27.22, 308.0, 50.09, 350.13, 90.42, 348.92, 107.27, 371.19, 118.1, 376.01, 118.1, 371.79, 128.33, 372.4, 134.95, 377.81, 128.33, 362.16, 118.1, 360.36, 121.11, 345.91, 113.89, 338.09, 97.04, 333.27, 87.41, 333.27, 68.75, 309.2, 65.74, 297.76, 65.14, 285.73, 66.94, 279.11, 78.98, 271.88, 83.19, 266.47, 95.23, 256.24, 101.25, 236.37, 91.62, 218.92, 81.39, 209.89, 63.33, 205.08, 50.69, 213.5, 41.67, 222.53]], "area": 7996.0400500000005, "iscrowd": 0, "image_id": 74356, "bbox": [23.01, 205.08, 111.94, 172.73], "category_id": 1, "id": 448994, "split": "val", "sentences": [{"tokens": ["a", "lady", "in", "a", "pink", "shirt", "preparing", "food"], "raw": "A lady in a pink shirt preparing food.", "sent_id": 43969, "sent": "a lady in a pink shirt preparing food"}, {"tokens": ["woman", "in", "a", "blue", "apron", "preparing", "food"], "raw": "woman in a blue apron preparing food", "sent_id": 43970, "sent": "woman in a blue apron preparing food"}], "file_name": "COCO_train2014_000000074356_448994.jpg", "ann_id": 448994, "sent_ids": [43969, 43970], "ref_id": 21901}, {"segmentation": [[365.7, 217.56, 372.42, 251.15, 385.85, 270.34, 391.61, 308.72, 382.97, 361.49, 383.93, 391.24, 381.05, 397.96, 403.12, 395.08, 443.43, 403.71, 450.14, 398.92, 429.03, 387.4, 425.19, 366.29, 431.91, 354.78, 432.87, 294.33, 441.51, 285.69, 450.14, 237.71, 501.0, 232.91, 508.67, 223.32, 500.04, 222.36, 459.74, 220.44, 453.02, 204.13, 443.43, 189.73, 442.47, 185.9, 409.84, 205.09, 394.49, 207.97, 371.46, 216.6, 374.34, 240.59]], "area": 11986.932299999997, "iscrowd": 0, "image_id": 558824, "bbox": [365.7, 185.9, 142.97, 217.81], "category_id": 1, "id": 498520, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "dark", "clothing", "holding", "an", "umbrella", "in", "the", "background"], "raw": "A person in dark clothing holding an umbrella in the background.", "sent_id": 43990, "sent": "a person in dark clothing holding an umbrella in the background"}, {"tokens": ["a", "woman", "wearing", "capris", "and", "holding", "an", "umbrella"], "raw": "A woman wearing capris and holding an umbrella.", "sent_id": 43991, "sent": "a woman wearing capris and holding an umbrella"}], "file_name": "COCO_train2014_000000558824_498520.jpg", "ann_id": 498520, "sent_ids": [43990, 43991], "ref_id": 21911}, {"segmentation": [[433.84, 183.45, 451.59, 194.54, 459.36, 205.08, 461.58, 212.29, 457.7, 236.15, 452.7, 253.9, 449.38, 261.11, 443.27, 267.21, 444.94, 281.08, 447.16, 286.07, 448.82, 297.72, 447.16, 307.71, 443.27, 319.36, 443.27, 326.57, 442.16, 338.77, 444.38, 342.65, 442.16, 351.53, 442.16, 355.97, 438.28, 362.07, 427.19, 360.41, 419.98, 359.3, 418.87, 345.98, 424.97, 343.21, 427.19, 332.67, 430.51, 322.13, 425.52, 323.79, 417.76, 340.99, 416.09, 349.31, 410.54, 353.75, 395.01, 355.97, 380.03, 353.19, 369.5, 344.87, 370.05, 331.56, 376.15, 322.13, 378.37, 317.69, 373.93, 302.16, 373.38, 287.18, 369.5, 271.09, 367.28, 251.68, 374.49, 233.37, 381.7, 222.28, 388.36, 198.98, 397.23, 190.1, 407.22, 185.11, 418.31, 182.34, 427.19, 182.89]], "area": 12429.842950000002, "iscrowd": 0, "image_id": 494257, "bbox": [367.28, 182.34, 94.3, 179.73], "category_id": 1, "id": 1713977, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "an", "orange", "shirt", "bending", "down", "on", "a", "tennis", "court"], "raw": "A man in an orange shirt bending down on a tennis court", "sent_id": 44036, "sent": "a man in an orange shirt bending down on a tennis court"}, {"tokens": ["the", "person", "in", "the", "orange", "shirt"], "raw": "the person in the orange shirt", "sent_id": 44037, "sent": "the person in the orange shirt"}], "file_name": "COCO_train2014_000000494257_1713977.jpg", "ann_id": 1713977, "sent_ids": [44036, 44037], "ref_id": 21931}, {"segmentation": [[140.04, 76.79, 126.51, 67.99, 125.84, 53.78, 127.86, 44.99, 131.92, 42.28, 142.75, 37.55, 146.13, 37.55, 155.6, 44.99, 159.66, 52.43, 168.46, 63.93, 173.19, 77.46, 175.9, 88.96, 174.55, 104.52, 171.84, 111.97, 169.13, 128.88, 166.43, 160.0, 188.75, 189.77, 204.31, 237.8, 199.58, 241.18, 180.63, 243.89, 171.84, 244.57, 167.78, 236.45, 170.49, 225.62, 171.16, 208.03, 150.87, 183.68, 140.04, 213.45, 137.34, 231.04, 130.57, 249.3, 123.13, 249.3, 108.25, 244.57, 96.07, 237.8, 100.8, 224.95, 106.89, 220.21, 117.04, 210.06, 122.45, 194.5, 121.78, 172.85, 127.86, 153.91, 129.89, 141.73, 125.84, 123.47, 125.84, 110.61, 113.66, 103.17, 98.1, 95.05, 94.71, 84.9, 98.77, 80.17, 101.48, 79.49, 114.33, 80.17, 123.13, 86.26, 127.19, 90.32, 131.25, 91.67]], "area": 10341.964, "iscrowd": 0, "image_id": 337621, "bbox": [94.71, 37.55, 109.6, 211.75], "category_id": 1, "id": 1225339, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "purple", "wig", "and", "fairy", "wings"], "raw": "A woman in a purple wig and fairy wings.", "sent_id": 44173, "sent": "a woman in a purple wig and fairy wings"}, {"tokens": ["a", "girl", "with", "purple", "hair", "and", "angel", "wings", "in", "ski", "gear"], "raw": "A girl with purple hair and angel wings in ski gear", "sent_id": 44174, "sent": "a girl with purple hair and angel wings in ski gear"}], "file_name": "COCO_train2014_000000337621_1225339.jpg", "ann_id": 1225339, "sent_ids": [44173, 44174], "ref_id": 21984}, {"segmentation": [[425.9, 223.25, 430.69, 222.81, 432.0, 221.51, 432.87, 218.46, 435.92, 218.46, 435.05, 215.85, 445.49, 217.59, 444.62, 230.65, 447.23, 234.13, 455.5, 233.69, 457.24, 224.12, 488.15, 224.99, 493.81, 222.81, 495.11, 225.86, 499.03, 223.68, 500.77, 224.99, 503.82, 224.99, 507.74, 231.95, 523.41, 232.39, 526.45, 228.91, 529.94, 225.42, 529.94, 221.51, 539.95, 220.2, 544.3, 218.02, 546.91, 198.0, 542.99, 159.89, 532.62, 125.94, 524.73, 125.23, 517.56, 118.06, 477.41, 118.77, 465.22, 129.53, 437.97, 141.0, 433.11, 148.37, 428.69, 157.96, 426.11, 161.27, 423.53, 162.01, 422.05, 157.96, 421.32, 155.74, 418.0, 155.74, 415.79, 159.43, 415.42, 163.48, 416.16, 164.22, 417.63, 166.06, 419.84, 166.8, 421.32, 163.48, 425.0, 162.75, 425.74, 175.65, 422.79, 178.23, 423.9, 172.33, 418.74, 172.7, 417.63, 178.59, 418.37, 183.02, 424.63, 183.02, 422.79, 198.5, 422.79, 206.97, 423.9, 208.45, 423.16, 211.4, 425.74, 223.56]], "area": 11631.085149999992, "iscrowd": 0, "image_id": 346562, "bbox": [415.42, 118.06, 131.49, 116.07], "category_id": 6, "id": 2049492, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "white", "van"], "raw": "The back of a white van.", "sent_id": 44266, "sent": "the back of a white van"}, {"tokens": ["the", "white", "van"], "raw": "The white van", "sent_id": 44267, "sent": "the white van"}], "file_name": "COCO_train2014_000000346562_2049492.jpg", "ann_id": 2049492, "sent_ids": [44266, 44267], "ref_id": 22018}, {"segmentation": [[133.75, 368.54, 148.13, 348.4, 158.2, 313.89, 159.64, 302.38, 146.7, 295.19, 126.56, 288.0, 110.74, 282.25, 109.3, 276.49, 122.25, 260.67, 140.94, 237.66, 132.31, 218.97, 148.13, 223.28, 169.71, 226.16, 212.85, 236.22, 264.63, 247.73, 296.27, 257.8, 335.1, 292.31, 349.48, 319.64, 253.12, 362.79, 228.67, 362.79, 220.04, 339.78, 186.97, 361.35, 159.64, 358.47, 155.33, 377.17, 139.51, 378.61]], "area": 21551.857300000007, "iscrowd": 0, "image_id": 295370, "bbox": [109.3, 218.97, 240.18, 159.64], "category_id": 23, "id": 587893, "split": "val", "sentences": [{"tokens": ["a", "brown", "bear", "lying", "down", "on", "a", "concrete", "ground"], "raw": "A brown bear lying down on a concrete ground", "sent_id": 44316, "sent": "a brown bear lying down on a concrete ground"}, {"tokens": ["brown", "bear", "laying", "on", "some", "concrete"], "raw": "Brown bear laying on some concrete.", "sent_id": 44317, "sent": "brown bear laying on some concrete"}], "file_name": "COCO_train2014_000000295370_587893.jpg", "ann_id": 587893, "sent_ids": [44316, 44317], "ref_id": 22036}, {"segmentation": [[356.43, 409.89, 336.42, 402.27, 318.31, 388.92, 317.36, 406.08, 309.73, 408.94, 288.77, 403.22, 291.62, 389.88, 295.44, 383.21, 295.44, 375.58, 227.77, 312.68, 220.15, 308.87, 204.9, 311.73, 193.46, 317.45, 188.7, 308.87, 187.74, 302.2, 198.23, 288.86, 181.07, 265.98, 181.07, 247.88, 181.07, 242.16, 195.37, 260.27, 228.72, 290.76, 264.94, 322.21, 308.78, 365.1, 350.71, 403.22, 364.05, 408.94]], "area": 4759.5045, "iscrowd": 0, "image_id": 433723, "bbox": [181.07, 242.16, 182.98, 167.73], "category_id": 41, "id": 642682, "split": "val", "sentences": [{"tokens": ["the", "skateboard", "of", "the", "boy", "wearing", "red", "and", "white", "tennis", "shoes"], "raw": "The skateboard of the boy wearing red and white tennis shoes.", "sent_id": 44361, "sent": "the skateboard of the boy wearing red and white tennis shoes"}, {"tokens": ["a", "skate", "board", "that", "is", "being", "used", "for", "tricks", "by", "a", "kid", "with", "red", "and", "white", "shoes"], "raw": "A skate board that is being used for tricks by a kid with red and white shoes", "sent_id": 44362, "sent": "a skate board that is being used for tricks by a kid with red and white shoes"}], "file_name": "COCO_train2014_000000433723_642682.jpg", "ann_id": 642682, "sent_ids": [44361, 44362], "ref_id": 22049}, {"segmentation": [[352.72, 472.52, 361.35, 453.11, 369.98, 393.78, 337.62, 351.71, 328.99, 325.82, 348.4, 290.23, 361.35, 242.77, 350.56, 219.04, 339.78, 186.68, 368.9, 157.56, 399.1, 156.48, 405.57, 170.5, 414.2, 182.36, 414.2, 212.57, 446.56, 216.88, 455.19, 234.14, 460.58, 253.56, 463.82, 274.05, 477.84, 309.64, 461.66, 366.81, 463.82, 413.2, 476.76, 455.26, 473.53, 473.6, 421.75, 472.52, 420.67, 431.53, 408.81, 472.52]], "area": 32454.732849999997, "iscrowd": 0, "image_id": 416076, "bbox": [328.99, 156.48, 148.85, 317.12], "category_id": 1, "id": 1717382, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "red", "and", "black", "dress", "standing", "in", "sides", "holding", "skiing", "poles", "in", "hand", "wearing", "black", "helmet"], "raw": "A boy in red and black dress standing in sides holding skiing poles in hand wearing black helmet.", "sent_id": 44394, "sent": "a boy in red and black dress standing in sides holding skiing poles in hand wearing black helmet"}, {"tokens": ["a", "boy", "in", "a", "red", "jacket"], "raw": "A boy in a red jacket.", "sent_id": 44395, "sent": "a boy in a red jacket"}], "file_name": "COCO_train2014_000000416076_1717382.jpg", "ann_id": 1717382, "sent_ids": [44394, 44395], "ref_id": 22062}, {"segmentation": [[295.61, 203.87, 299.51, 211.99, 307.3, 240.56, 305.35, 284.72, 304.05, 287.32, 303.4, 294.78, 305.68, 307.77, 303.4, 307.77, 299.51, 309.07, 296.59, 311.67, 295.29, 310.69, 292.37, 304.52, 290.74, 300.3, 291.72, 289.59, 291.72, 285.04, 289.77, 259.07, 287.82, 266.21, 286.52, 299.98, 275.16, 301.6, 260.22, 307.12, 256.98, 313.61, 256.65, 318.16, 261.2, 325.3, 265.74, 328.22, 263.47, 358.42, 260.87, 365.89, 256.33, 371.4, 250.48, 360.04, 235.55, 299.98, 231.0, 309.72, 226.13, 298.35, 226.78, 287.96, 233.6, 285.37, 237.17, 268.48, 233.6, 258.42, 226.78, 249.65, 224.19, 247.38, 223.54, 231.47, 210.22, 219.46, 208.28, 206.8, 217.37, 194.46, 241.39, 171.08, 260.55, 165.56, 273.54, 165.56, 282.63, 173.03, 285.22, 181.15, 290.09, 188.94, 293.66, 195.76]], "area": 11183.286850000006, "iscrowd": 0, "image_id": 454144, "bbox": [208.28, 165.56, 99.02, 205.84], "category_id": 1, "id": 1712575, "split": "val", "sentences": [{"tokens": ["a", "woman", "bending", "over", "to", "pick", "something", "up", "off", "a", "table"], "raw": "A woman bending over to pick something up off a table.", "sent_id": 44443, "sent": "a woman bending over to pick something up off a table"}, {"tokens": ["a", "woman", "leaning", "over", "wearing", "a", "white", "jacket"], "raw": "A woman leaning over wearing a white jacket.", "sent_id": 44444, "sent": "a woman leaning over wearing a white jacket"}], "file_name": "COCO_train2014_000000454144_1712575.jpg", "ann_id": 1712575, "sent_ids": [44443, 44444], "ref_id": 22080}, {"segmentation": [[283.14, 56.83, 300.26, 52.07, 321.18, 49.22, 332.59, 32.1, 354.47, 19.74, 366.83, 15.93, 374.44, 15.93, 370.63, 39.71, 365.88, 51.12, 363.03, 55.88, 355.42, 72.99, 355.42, 84.41, 355.42, 101.52, 350.66, 116.74, 345.91, 131.0, 356.37, 203.28, 356.37, 204.23, 347.81, 207.08, 347.81, 206.13, 331.64, 139.56, 326.89, 138.61, 326.89, 235.73, 309.77, 240.37, 309.77, 240.37, 303.11, 242.27, 303.95, 212.05, 294.2, 173.55, 291.7, 160.49, 289.8, 156.68, 272.56, 145.27, 259.37, 139.56, 247.0, 130.05, 246.05, 127.2, 247.0, 124.35, 239.4, 116.74, 227.03, 114.84, 225.13, 107.23, 227.98, 83.45, 236.54, 78.7, 275.53, 71.09]], "area": 14604.437050000002, "iscrowd": 0, "image_id": 35945, "bbox": [225.13, 15.93, 149.31, 226.34], "category_id": 62, "id": 375409, "split": "val", "sentences": [{"tokens": ["a", "green", ",", "unoccupied", "chair", "near", "a", "colorful", "fire", "hydrant"], "raw": "A green, unoccupied chair near a colorful fire hydrant.", "sent_id": 44621, "sent": "a green , unoccupied chair near a colorful fire hydrant"}, {"tokens": ["an", "empty", "green", "chair", "between", "a", "fire", "hydrant", "and", "a", "seated", "man"], "raw": "An empty green chair between a fire hydrant and a seated man", "sent_id": 44622, "sent": "an empty green chair between a fire hydrant and a seated man"}], "file_name": "COCO_train2014_000000035945_375409.jpg", "ann_id": 375409, "sent_ids": [44621, 44622], "ref_id": 22152}, {"segmentation": [[476.63, 251.25, 475.94, 228.36, 471.78, 222.11, 469.7, 207.54, 467.61, 190.2, 466.92, 167.3, 469.0, 155.51, 472.47, 145.1, 480.1, 138.16, 492.59, 136.08, 505.08, 133.31, 508.55, 135.39, 512.02, 141.63, 514.79, 150.65, 519.65, 160.36, 522.42, 168.69, 544.63, 177.71, 559.19, 183.26, 563.36, 188.81, 560.58, 201.99, 558.5, 210.32, 557.11, 226.27, 557.11, 234.6, 556.42, 242.23, 549.48, 242.93, 543.93, 243.62, 541.16, 233.21, 530.06, 232.52, 512.71, 233.21, 499.53, 237.38, 489.12, 238.76, 487.04, 242.23, 486.35, 258.19]], "area": 7429.148499999999, "iscrowd": 0, "image_id": 204339, "bbox": [466.92, 133.31, 96.44, 124.88], "category_id": 62, "id": 103685, "split": "val", "sentences": [{"tokens": ["black", "chair", "that", "is", "to", "the", "left", "of", "the", "tv"], "raw": "Black chair that is to the left of the tv.", "sent_id": 44636, "sent": "black chair that is to the left of the tv"}, {"tokens": ["a", "black", "chair", "with", "wooden", "arms"], "raw": "A black chair with wooden arms.", "sent_id": 44637, "sent": "a black chair with wooden arms"}], "file_name": "COCO_train2014_000000204339_103685.jpg", "ann_id": 103685, "sent_ids": [44636, 44637], "ref_id": 22157}, {"segmentation": [[255.21, 328.92, 245.86, 328.43, 242.41, 320.55, 243.89, 303.33, 248.32, 274.29, 255.21, 223.1, 248.81, 208.83, 250.29, 200.46, 244.38, 197.02, 241.43, 191.11, 241.43, 182.75, 248.81, 166.51, 256.69, 146.33, 268.5, 142.88, 276.87, 142.39, 282.28, 136.48, 280.31, 127.13, 284.74, 120.24, 292.12, 116.31, 302.95, 119.26, 307.87, 131.56, 304.92, 138.95, 298.03, 145.84, 304.92, 153.22, 305.9, 172.9, 310.33, 177.83, 312.3, 186.19, 310.82, 191.61, 307.87, 199.97, 300.0, 201.45, 298.03, 232.46, 295.57, 264.94, 289.66, 286.1, 289.66, 303.33, 298.03, 321.04, 294.09, 325.47, 283.26, 323.01, 278.83, 314.15, 275.39, 299.39, 279.82, 268.87, 276.87, 243.28, 270.96, 266.41, 268.01, 285.12, 263.58, 299.88]], "area": 8874.53705, "iscrowd": 0, "image_id": 577206, "bbox": [241.43, 116.31, 70.87, 212.61], "category_id": 1, "id": 437639, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "all", "black", "skis", "with", "a", "woman"], "raw": "A man wearing all black skis with a woman", "sent_id": 44650, "sent": "a man wearing all black skis with a woman"}, {"tokens": ["an", "old", "man", "skiing"], "raw": "An old man skiing", "sent_id": 44651, "sent": "an old man skiing"}], "file_name": "COCO_train2014_000000577206_437639.jpg", "ann_id": 437639, "sent_ids": [44650, 44651], "ref_id": 22163}, {"segmentation": [[349.77, 423.91, 372.58, 407.73, 382.95, 399.44, 370.5, 372.48, 369.26, 335.57, 373.41, 304.05, 376.31, 294.51, 380.87, 282.07, 390.83, 272.94, 402.44, 265.06, 428.15, 257.6, 453.04, 255.11, 476.26, 260.92, 491.19, 268.38, 507.78, 279.16, 514.83, 289.53, 523.54, 306.54, 524.78, 323.54, 519.39, 327.27, 519.39, 340.54, 528.1, 352.57, 535.57, 361.28, 528.93, 367.92, 506.54, 368.33, 501.97, 374.55, 529.76, 382.43, 551.33, 391.14, 558.38, 402.75, 601.51, 412.29, 612.29, 421.42, 613.95, 424.0]], "area": 25601.5823, "iscrowd": 0, "image_id": 270248, "bbox": [349.77, 255.11, 264.18, 168.89], "category_id": 1, "id": 458848, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "orange", "jersey", "and", "blue", "helmet"], "raw": "A man in orange jersey and blue helmet.", "sent_id": 44704, "sent": "a man in orange jersey and blue helmet"}, {"tokens": ["catcher", "of", "baseball", "game"], "raw": "catcher of baseball game", "sent_id": 44705, "sent": "catcher of baseball game"}], "file_name": "COCO_train2014_000000270248_458848.jpg", "ann_id": 458848, "sent_ids": [44704, 44705], "ref_id": 22182}, {"segmentation": [[419.96, 176.9, 404.13, 135.19, 395.51, 100.67, 381.12, 66.16, 371.06, 74.79, 369.62, 80.54, 360.99, 63.28, 356.67, 61.84, 355.24, 89.17, 336.54, 102.11, 309.21, 110.74, 293.39, 125.12, 290.52, 130.88, 195.6, 175.46, 139.51, 211.42, 109.3, 238.74, 67.6, 263.19, 28.76, 310.65, 15.82, 342.29, 31.64, 391.19, 35.96, 448.72, 51.78, 507.69, 51.78, 573.84, 50.34, 595.42, 50.34, 602.61, 58.97, 605.48, 63.28, 595.42, 61.84, 496.18, 61.84, 487.55, 61.84, 487.55, 57.53, 447.28, 74.79, 353.8, 77.66, 350.92, 77.66, 353.8, 81.98, 392.63, 70.47, 412.76, 69.03, 450.16, 69.03, 512.0, 69.03, 589.66, 76.22, 592.54, 79.1, 552.27, 77.66, 477.48, 90.61, 419.96, 122.25, 388.31, 142.38, 369.62, 155.33, 444.4, 155.33, 504.81, 166.83, 588.22, 166.83, 612.67, 166.83, 612.67, 174.02, 616.99, 189.84, 592.54, 198.47, 451.6, 212.85, 325.03, 225.8, 279.01, 263.19, 240.18, 337.98, 156.76, 352.36, 146.7, 388.31, 169.71, 412.76, 181.21]], "area": 61087.23030000001, "iscrowd": 0, "image_id": 74663, "bbox": [15.82, 61.84, 404.14, 555.15], "category_id": 25, "id": 594983, "split": "val", "sentences": [{"tokens": ["giraffe", "nearest", "the", "camera"], "raw": "Giraffe nearest the camera", "sent_id": 44785, "sent": "giraffe nearest the camera"}, {"tokens": ["a", "giraffe", "stands", "near", "his", "fence"], "raw": "A giraffe stands near his fence.", "sent_id": 44786, "sent": "a giraffe stands near his fence"}], "file_name": "COCO_train2014_000000074663_594983.jpg", "ann_id": 594983, "sent_ids": [44785, 44786], "ref_id": 22218}, {"segmentation": [[324.48, 237.92, 324.48, 237.92, 345.23, 231.48, 360.26, 231.48, 371.7, 225.04, 392.45, 215.02, 403.9, 211.44, 416.78, 212.16, 424.65, 210.73, 421.07, 198.57, 419.64, 194.27, 411.77, 189.26, 412.49, 185.69, 413.2, 177.1, 414.63, 169.95, 418.93, 162.79, 428.23, 162.08, 435.38, 160.64, 443.25, 162.08, 462.57, 171.38, 471.16, 174.24, 479.03, 179.96, 484.04, 184.26, 493.34, 195.7, 496.92, 200.71, 499.78, 207.15, 501.92, 217.88, 504.79, 226.47, 506.22, 236.49, 507.65, 244.36, 508.36, 260.1, 503.35, 276.55, 496.92, 295.16, 496.2, 302.31, 492.62, 310.9, 489.76, 320.2, 482.61, 325.21, 458.99, 331.65, 423.22, 341.66, 393.17, 348.82, 369.56, 354.54, 350.24, 360.98, 337.36, 359.55, 328.06, 359.55, 303.73, 351.68, 294.43, 328.07, 295.15, 318.77, 295.15, 298.73, 296.58, 291.58, 298.72, 280.13, 303.02, 272.26, 310.17, 251.51, 319.47, 244.36, 321.62, 240.06, 325.2, 240.06]], "area": 28034.17655, "iscrowd": 0, "image_id": 377329, "bbox": [294.43, 160.64, 213.93, 200.34], "category_id": 21, "id": 71165, "split": "val", "sentences": [{"tokens": ["a", "black", "cow", "with", "a", "white", "splattered", "stripe", "on", "its", "back"], "raw": "A black cow with a white splattered stripe on its back.", "sent_id": 44872, "sent": "a black cow with a white splattered stripe on its back"}, {"tokens": ["a", "black", "cow", "with", "a", "white", "stripe"], "raw": "A black cow with a white stripe.", "sent_id": 44873, "sent": "a black cow with a white stripe"}], "file_name": "COCO_train2014_000000377329_71165.jpg", "ann_id": 71165, "sent_ids": [44872, 44873], "ref_id": 22248}, {"segmentation": [[245.73, 413.4, 148.57, 400.51, 108.92, 393.57, 85.12, 385.64, 53.4, 360.85, 49.43, 341.03, 48.44, 306.33, 52.41, 284.52, 82.15, 256.76, 114.87, 240.9, 139.65, 227.02, 165.43, 227.02, 190.21, 224.04, 207.06, 224.04, 214.99, 223.05, 214.0, 228.01, 226.89, 222.06, 252.67, 222.06, 271.5, 229.0, 283.4, 224.04, 296.29, 216.11, 301.24, 207.19, 310.17, 202.23, 316.12, 190.34, 320.08, 180.42, 338.92, 145.73, 365.68, 119.95, 415.25, 112.02, 454.91, 114.99, 487.62, 123.91, 512.41, 158.61, 534.22, 189.35, 530.25, 225.04, 529.26, 240.9, 566.94, 259.73, 598.66, 288.48, 632.37, 307.32, 640.0, 316.24, 640.0, 334.09, 639.31, 342.02, 583.79, 318.23, 567.93, 311.29, 602.62, 340.04, 627.41, 372.75, 639.31, 388.61, 639.31, 415.38, 639.31, 502.62, 640.0, 637.45, 588.75, 640.0, 536.2, 635.47, 515.38, 616.63, 455.9, 575.98, 376.59, 523.44, 315.12, 488.74, 285.38, 454.04, 282.41, 450.08, 259.61, 429.26, 247.71, 415.38, 239.78, 413.4]], "area": 176616.51355, "iscrowd": 0, "image_id": 219966, "bbox": [48.44, 112.02, 591.56, 527.98], "category_id": 1, "id": 491493, "split": "val", "sentences": [{"tokens": ["a", "sleeping", "infant", "with", "blond", "hair", "wearing", "a", "red", "shirt", "that", "has", "white", "stripes"], "raw": "A sleeping infant with blond hair wearing a red shirt that has white stripes.", "sent_id": 44883, "sent": "a sleeping infant with blond hair wearing a red shirt that has white stripes"}, {"tokens": ["sleeping", "baby"], "raw": "sleeping baby", "sent_id": 44884, "sent": "sleeping baby"}], "file_name": "COCO_train2014_000000219966_491493.jpg", "ann_id": 491493, "sent_ids": [44883, 44884], "ref_id": 22253}, {"segmentation": [[1.95, 195.78, 43.83, 204.55, 116.88, 132.47, 118.83, 130.52, 107.14, 120.78, 112.99, 112.01, 112.99, 108.12, 89.61, 124.68, 75.97, 149.03, 42.86, 140.26, 22.4, 114.94, 33.12, 88.64, 22.4, 51.62, 0.0, 24.35]], "area": 7876.174999999998, "iscrowd": 0, "image_id": 581670, "bbox": [0.0, 24.35, 118.83, 180.2], "category_id": 1, "id": 2003541, "split": "val", "sentences": [{"tokens": ["a", "man", "holding", "a", "sandwich", "near", "a", "table"], "raw": "A man holding a sandwich near a table.", "sent_id": 44903, "sent": "a man holding a sandwich near a table"}, {"tokens": ["black", "color", "over", "coat", "of", "the", "man", "who", "is", "having", "food"], "raw": "Black color over coat of the man who is having food", "sent_id": 44904, "sent": "black color over coat of the man who is having food"}], "file_name": "COCO_train2014_000000581670_2003541.jpg", "ann_id": 2003541, "sent_ids": [44903, 44904], "ref_id": 22262}, {"segmentation": [[33.4, 425.84, 158.57, 343.06, 161.59, 327.92, 175.73, 308.74, 219.13, 295.62, 250.42, 291.58, 262.54, 292.59, 259.51, 288.55, 270.61, 276.44, 274.65, 276.44, 272.63, 262.31, 280.71, 255.24, 303.92, 248.18, 310.99, 241.11, 318.06, 241.11, 319.07, 248.18, 356.42, 249.19, 369.54, 247.17, 371.7, 269.35, 380.36, 263.94, 396.58, 265.56, 401.99, 266.64, 409.03, 259.61, 409.57, 250.41, 417.14, 254.74, 430.12, 249.87, 447.43, 260.69, 459.33, 256.36, 469.61, 231.48, 492.33, 249.87, 496.66, 271.51, 504.77, 274.22, 513.97, 278.0, 517.21, 276.92, 525.33, 275.3, 524.79, 265.56, 531.28, 259.61, 542.64, 259.07, 564.28, 259.61, 582.13, 263.4, 583.75, 265.02, 586.46, 258.53, 593.49, 262.31, 590.24, 267.72, 599.98, 275.84, 596.73, 283.41, 599.44, 290.98, 639.47, 302.34, 638.93, 428.0, 31.99, 427.84]], "area": 81297.97535000002, "iscrowd": 0, "image_id": 246927, "bbox": [31.99, 231.48, 607.48, 196.52], "category_id": 67, "id": 123027, "split": "val", "sentences": [{"tokens": ["the", "blue", "table", "that", "has", "the", "man", "with", "striped", "shirt", "in", "the", "foreground"], "raw": "The blue table that has the man with striped shirt in the foreground.", "sent_id": 44923, "sent": "the blue table that has the man with striped shirt in the foreground"}, {"tokens": ["the", "table", "of", "food"], "raw": "the table of food", "sent_id": 44924, "sent": "the table of food"}], "file_name": "COCO_train2014_000000246927_123027.jpg", "ann_id": 123027, "sent_ids": [44923, 44924], "ref_id": 22271}, {"segmentation": [[4.95, 351.07, 493.26, 334.78, 499.91, 296.31, 492.52, 291.14, 482.9, 311.11, 479.94, 305.2, 479.94, 319.99, 238.75, 324.43, 242.45, 288.91, 196.57, 291.88, 230.61, 311.11, 210.63, 331.09, 124.81, 328.13, 132.95, 303.72, 84.86, 299.27, 66.36, 320.73, 13.1, 319.99, 12.36, 327.39, 2.74, 329.61, 2.74, 353.29], [510.27, 337.74, 525.81, 335.52, 530.25, 300.01, 510.27, 302.24, 505.83, 335.52]], "area": 12588.617899999992, "iscrowd": 0, "image_id": 513221, "bbox": [2.74, 288.91, 527.51, 64.38], "category_id": 67, "id": 391780, "split": "val", "sentences": [{"tokens": ["a", "blue", "cloth", "on", "a", "table"], "raw": "A blue cloth on a table", "sent_id": 44936, "sent": "a blue cloth on a table"}, {"tokens": ["a", "long", "picnic", "table", "adorned", "with", "a", "blue", "and", "pink", "pastel", "cloth", ",", "and", "two", "sheet", "cakes"], "raw": "A long picnic table adorned with a blue and pink pastel cloth, and two sheet cakes.", "sent_id": 44937, "sent": "a long picnic table adorned with a blue and pink pastel cloth , and two sheet cakes"}], "file_name": "COCO_train2014_000000513221_391780.jpg", "ann_id": 391780, "sent_ids": [44936, 44937], "ref_id": 22277}, {"segmentation": [[363.13, 69.17, 215.7, 86.46, 237.54, 305.8, 396.81, 283.04, 364.04, 70.99]], "area": 33838.93280000001, "iscrowd": 0, "image_id": 524866, "bbox": [215.7, 69.17, 181.11, 236.63], "category_id": 77, "id": 325255, "split": "val", "sentences": [{"tokens": ["the", "cell", "phone", "on", "top"], "raw": "The cell phone on top", "sent_id": 44952, "sent": "the cell phone on top"}, {"tokens": ["the", "phone", "in", "pink"], "raw": "the phone in pink", "sent_id": 44953, "sent": "the phone in pink"}], "file_name": "COCO_train2014_000000524866_325255.jpg", "ann_id": 325255, "sent_ids": [44952, 44953], "ref_id": 22283}, {"segmentation": [[3.38, 193.61, 101.31, 168.84, 101.31, 150.83, 97.93, 150.83, 103.56, 132.82, 113.69, 121.57, 144.08, 115.94, 164.34, 112.56, 181.22, 121.57, 184.6, 127.19, 184.6, 133.95, 178.97, 135.07, 176.72, 139.58, 177.85, 146.33, 212.74, 133.95, 211.62, 127.19, 118.19, 78.79, 81.04, 84.42, 76.54, 57.41, 66.41, 57.41, 61.91, 40.52, 54.03, 33.77, 52.9, 25.89, 45.02, 20.26, 40.52, 29.27, 39.4, 38.27, 32.64, 41.65, 32.64, 46.15, 37.15, 52.9, 42.77, 58.53, 37.15, 61.91, 23.64, 63.03, 19.14, 63.03, 11.26, 68.66, 18.01, 76.54, 25.89, 84.42, 28.14, 90.05, 29.27, 94.55, 28.14, 96.8, 1.13, 96.8]], "area": 14360.939049999999, "iscrowd": 0, "image_id": 210187, "bbox": [1.13, 20.26, 211.61, 173.35], "category_id": 67, "id": 2226511, "split": "val", "sentences": [{"tokens": ["the", "table", "to", "the", "top", "left", "with", "the", "ketchup", "bottle", "on", "it"], "raw": "The table to the top left with the ketchup bottle on it.", "sent_id": 44981, "sent": "the table to the top left with the ketchup bottle on it"}, {"tokens": ["table", "in", "background", "far", "left"], "raw": "Table in background far left.", "sent_id": 44982, "sent": "table in background far left"}], "file_name": "COCO_train2014_000000210187_2226511.jpg", "ann_id": 2226511, "sent_ids": [44981, 44982], "ref_id": 22296}, {"segmentation": [[473.82, 47.27, 478.77, 39.29, 488.94, 33.52, 500.77, 35.99, 509.02, 43.14, 510.12, 50.29, 510.95, 65.69, 512.05, 66.52, 513.42, 67.62, 518.65, 66.52, 523.32, 70.65, 529.65, 78.62, 541.75, 92.37, 556.33, 108.05, 562.93, 133.35, 565.95, 146.0, 562.93, 154.26, 566.23, 175.98, 570.35, 197.44, 571.18, 204.31, 571.18, 216.69, 554.95, 219.16, 554.4, 228.51, 551.65, 240.62, 551.65, 248.59, 557.98, 252.99, 569.25, 259.32, 586.31, 282.97, 593.18, 291.22, 601.98, 297.27, 614.91, 299.75, 619.31, 301.95, 620.69, 308.27, 620.14, 313.5, 617.11, 321.2, 618.21, 328.9, 612.98, 340.18, 597.31, 348.43, 594.28, 339.08, 594.28, 327.25, 590.71, 313.5, 588.23, 306.07, 582.18, 298.92, 557.7, 280.77, 534.33, 265.64, 531.3, 261.52, 526.07, 249.14, 521.67, 229.06, 510.12, 245.02, 506.82, 251.62, 517.27, 271.69, 519.47, 281.05, 519.75, 287.92, 527.72, 309.92, 535.15, 322.3, 548.35, 334.13, 540.1, 343.2, 523.32, 347.33, 513.7, 352.83, 498.3, 353.1, 490.6, 344.3, 491.15, 340.45, 502.7, 336.33, 509.57, 329.18, 512.6, 315.15, 503.52, 298.65, 494.45, 279.4, 487.29, 263.44, 479.87, 251.34, 484.82, 233.19, 486.47, 212.84, 489.49, 199.64, 495.55, 186.43, 499.67, 177.63, 500.5, 172.41, 496.92, 164.43, 490.87, 164.16, 483.72, 155.63, 485.92, 150.96, 484.54, 147.1, 487.02, 144.9, 490.87, 147.93, 486.47, 115.2, 486.74, 96.77, 490.6, 86.05, 487.84, 86.05, 480.97, 86.05, 477.67, 79.45, 474.92, 73.12, 471.07, 70.37, 473.54, 63.49, 470.52, 58.27]], "area": 19044.949249999994, "iscrowd": 0, "image_id": 199331, "bbox": [470.52, 33.52, 150.17, 319.58], "category_id": 1, "id": 483838, "split": "val", "sentences": [{"tokens": ["man", "on", "the", "right", "in", "the", "red", "pinney"], "raw": "Man on the right in the red pinney", "sent_id": 45020, "sent": "man on the right in the red pinney"}, {"tokens": ["a", "man", "with", "red", "sleeveless", "overcoat", "trying", "to", "get", "the", "ball"], "raw": "A man with red sleeveless overcoat trying to get the ball", "sent_id": 45021, "sent": "a man with red sleeveless overcoat trying to get the ball"}], "file_name": "COCO_train2014_000000199331_483838.jpg", "ann_id": 483838, "sent_ids": [45020, 45021], "ref_id": 22313}, {"segmentation": [[46.76, 398.6, 38.51, 358.72, 41.26, 328.46, 137.53, 298.21, 207.67, 278.95, 222.8, 278.95, 265.43, 278.95, 339.69, 309.21, 407.08, 386.22, 426.34, 424.73, 445.59, 461.87, 430.46, 492.12, 411.21, 475.62, 419.46, 504.5, 434.59, 536.13, 422.21, 554.01, 389.2, 554.01, 145.78, 518.25, 96.27, 507.25, 93.52, 500.37, 77.02, 499.0, 61.89, 493.5, 59.14, 493.5, 35.76, 500.37, 33.01, 490.75, 24.76, 481.12, 19.25, 464.62, 26.13, 452.24, 34.38, 419.23]], "area": 85870.31079999999, "iscrowd": 0, "image_id": 392167, "bbox": [19.25, 278.95, 426.34, 275.06], "category_id": 54, "id": 308516, "split": "val", "sentences": [{"tokens": ["an", "egg", "salad", "sandwich", "with", "an", "orange", "toothpick", "holding", "it", "together"], "raw": "An egg salad sandwich with an orange toothpick holding it together.", "sent_id": 45079, "sent": "an egg salad sandwich with an orange toothpick holding it together"}, {"tokens": ["a", "delicious", "looking", "sandwich", "showing", "it", "'", "s", "contents", "with", "egg", "salad", ",", "tomatoes", "and", "cucumbers"], "raw": "A delicious looking sandwich showing it's contents with egg salad, tomatoes and cucumbers.", "sent_id": 45080, "sent": "a delicious looking sandwich showing it ' s contents with egg salad , tomatoes and cucumbers"}], "file_name": "COCO_train2014_000000392167_308516.jpg", "ann_id": 308516, "sent_ids": [45079, 45080], "ref_id": 22339}, {"segmentation": [[302.96, 14.96, 447.58, 73.56, 471.27, 71.06, 513.66, 18.7, 522.39, 0.0, 297.97, 0.0]], "area": 10135.319, "iscrowd": 0, "image_id": 74201, "bbox": [297.97, 0.0, 224.42, 73.56], "category_id": 51, "id": 1899660, "split": "val", "sentences": [{"tokens": ["glass", "bowl", "right", "top", "corner"], "raw": "glass bowl right top corner", "sent_id": 45099, "sent": "glass bowl right top corner"}, {"tokens": ["the", "empty", "container", "at", "the", "top", "of", "the", "other", "containers"], "raw": "The empty container at the top of the other containers", "sent_id": 45100, "sent": "the empty container at the top of the other containers"}], "file_name": "COCO_train2014_000000074201_1899660.jpg", "ann_id": 1899660, "sent_ids": [45099, 45100], "ref_id": 22345}, {"segmentation": [[34.24, 147.56, 82.39, 219.78, 106.04, 264.59, 99.38, 283.69, 74.94, 296.13, 100.27, 328.11, 35.85, 338.33, 30.52, 317.01, 27.41, 307.23, 0.76, 303.68, 0.0, 231.71, 0.0, 210.39, 0.0, 142.87, 0.0, 127.32, 0.0, 108.22, 0.0, 102.89, 6.98, 134.87, 10.53, 142.42, 28.3, 142.42]], "area": 14246.801950000001, "iscrowd": 0, "image_id": 235582, "bbox": [0.0, 102.89, 106.04, 235.44], "category_id": 1, "id": 2164795, "split": "val", "sentences": [{"tokens": ["person", "with", "their", "hands", "clasped", "at", "the", "table"], "raw": "Person with their hands clasped at the table.", "sent_id": 45113, "sent": "person with their hands clasped at the table"}, {"tokens": ["a", "person", "off", "screen", "with", "their", "hands", "balled", "up"], "raw": "A person off screen with their hands balled up", "sent_id": 45114, "sent": "a person off screen with their hands balled up"}], "file_name": "COCO_train2014_000000235582_2164795.jpg", "ann_id": 2164795, "sent_ids": [45113, 45114], "ref_id": 22348}, {"segmentation": [[464.96, 404.13, 455.23, 396.22, 455.84, 369.45, 457.66, 348.77, 446.71, 312.26, 444.88, 303.74, 440.63, 274.53, 433.32, 272.1, 411.42, 275.75, 408.38, 287.31, 413.24, 296.44, 398.64, 298.26, 397.42, 283.66, 400.47, 269.06, 432.11, 254.45, 445.49, 248.37, 440.02, 239.24, 451.58, 227.07, 463.75, 227.07, 472.87, 233.16, 472.87, 241.68, 488.08, 247.15, 511.21, 269.06, 513.03, 275.14, 506.34, 283.66, 492.34, 289.14, 499.65, 323.82, 500.86, 342.07, 488.08, 356.68, 507.56, 372.5, 505.12, 377.97, 495.99, 378.58, 476.52, 373.1, 472.87, 362.15, 476.52, 354.24, 483.22, 337.2, 475.31, 325.04, 469.83, 324.43, 476.52, 354.24, 469.83, 365.19, 468.01, 382.23, 482.0, 401.7, 476.52, 405.96, 464.96, 403.53]], "area": 8280.251449999996, "iscrowd": 0, "image_id": 160188, "bbox": [397.42, 227.07, 115.61, 178.89], "category_id": 1, "id": 471110, "split": "val", "sentences": [{"tokens": ["a", "guy", "riding", "a", "skateboard"], "raw": "A guy riding a skateboard.", "sent_id": 45129, "sent": "a guy riding a skateboard"}, {"tokens": ["guy", "with", "arms", "out", "skateboarding", "with", "headband", "on"], "raw": "Guy with arms out skateboarding with headband on.", "sent_id": 45130, "sent": "guy with arms out skateboarding with headband on"}], "file_name": "COCO_train2014_000000160188_471110.jpg", "ann_id": 471110, "sent_ids": [45129, 45130], "ref_id": 22355}, {"segmentation": [[58.73, 444.24, 55.72, 460.8, 58.73, 474.35, 94.87, 508.99, 188.24, 570.73, 225.88, 573.74, 287.62, 627.95, 292.14, 630.96, 368.94, 627.95, 317.74, 575.25, 302.68, 575.25, 292.14, 543.62, 155.11, 471.34, 112.94, 433.69, 81.32, 427.67, 66.26, 430.68, 58.73, 445.74]], "area": 20678.003600000007, "iscrowd": 0, "image_id": 175116, "bbox": [55.72, 427.67, 313.22, 203.29], "category_id": 57, "id": 1062483, "split": "val", "sentences": [{"tokens": ["a", "long", "carrot", "that", "is", "slightly", "curved"], "raw": "A long carrot that is slightly curved", "sent_id": 45155, "sent": "a long carrot that is slightly curved"}], "file_name": "COCO_train2014_000000175116_1062483.jpg", "ann_id": 1062483, "sent_ids": [45155], "ref_id": 22364}, {"segmentation": [[193.37, 424.9, 192.86, 415.25, 187.27, 410.67, 189.3, 394.91, 188.28, 376.1, 203.03, 376.61, 223.87, 379.66, 265.05, 374.57, 268.1, 380.67, 269.63, 404.57, 277.76, 401.01, 281.32, 393.89, 296.57, 390.33, 299.62, 395.42, 297.59, 403.04, 300.13, 425.0], [315.39, 424.9, 301.66, 398.47, 300.13, 394.4, 330.13, 397.96, 345.89, 397.96, 343.86, 378.64, 345.38, 361.86, 379.44, 362.37, 389.61, 359.83, 399.27, 351.19, 397.24, 387.28, 399.27, 425.0, 316.91, 425.0], [485.19, 359.32, 506.04, 360.34, 507.05, 332.38, 541.62, 333.9, 549.76, 329.83, 548.23, 351.69, 549.25, 374.57, 549.25, 382.2, 551.79, 424.4, 509.59, 424.9, 508.07, 410.67, 499.43, 404.06, 488.24, 418.8, 484.68, 360.34]], "area": 14042.947199999997, "iscrowd": 0, "image_id": 254726, "bbox": [187.27, 329.83, 364.52, 95.17], "category_id": 62, "id": 105281, "split": "val", "sentences": [{"tokens": ["the", "fold", "up", "chairs", "in", "front"], "raw": "The fold up chairs in front.", "sent_id": 45164, "sent": "the fold up chairs in front"}, {"tokens": ["a", "row", "of", "collapsible", "lawn", "chairs", "in", "multiple", "colors"], "raw": "A row of collapsible lawn chairs in multiple colors", "sent_id": 45165, "sent": "a row of collapsible lawn chairs in multiple colors"}], "file_name": "COCO_train2014_000000254726_105281.jpg", "ann_id": 105281, "sent_ids": [45164, 45165], "ref_id": 22369}, {"segmentation": [[226.38, 260.24, 275.21, 231.43, 283.51, 223.13, 287.91, 216.3, 289.86, 213.37, 294.25, 205.55, 299.14, 200.67, 306.46, 199.69, 312.32, 203.11, 316.72, 210.92, 316.23, 217.76, 317.2, 221.18, 327.95, 218.74, 343.57, 225.57, 356.27, 229.97, 370.43, 238.27, 386.05, 249.01, 396.31, 255.85, 411.93, 265.12, 419.74, 269.52, 424.14, 271.47, 421.7, 277.33, 415.35, 274.89, 411.93, 277.82, 415.84, 281.73, 422.19, 284.66, 417.3, 288.56, 407.05, 288.56, 397.77, 288.56, 393.38, 293.45, 381.17, 294.91, 380.19, 294.91, 374.82, 296.37, 372.87, 296.37, 372.38, 296.86, 372.38, 301.75, 375.31, 305.16, 379.22, 314.93, 382.63, 322.74, 384.59, 333.0, 387.52, 338.86, 387.52, 340.32, 382.63, 339.34, 378.24, 324.21, 378.24, 320.3, 375.8, 307.12, 370.92, 304.68, 368.96, 296.86, 358.71, 296.37, 343.57, 294.91, 335.76, 295.89, 342.11, 322.74, 335.76, 339.34, 339.67, 347.16, 336.25, 348.13, 331.85, 341.79, 330.39, 334.95, 336.25, 318.35, 333.32, 301.26, 329.41, 293.45, 312.81, 281.24, 304.51, 269.03, 297.18, 259.75, 293.28, 247.55, 293.77, 236.32, 295.72, 225.08, 294.74, 225.08, 225.89, 260.73]], "area": 7700.212150000003, "iscrowd": 0, "image_id": 418847, "bbox": [225.89, 199.69, 198.25, 148.44], "category_id": 16, "id": 44148, "split": "val", "sentences": [{"tokens": ["the", "brown", "birds", "with", "the", "long", "beak", "are", "in", "the", "water"], "raw": "The brown birds with the long beak are in the water.", "sent_id": 45238, "sent": "the brown birds with the long beak are in the water"}], "file_name": "COCO_train2014_000000418847_44148.jpg", "ann_id": 44148, "sent_ids": [45238], "ref_id": 22399}, {"segmentation": [[64.29, 400.13, 48.94, 342.56, 25.91, 299.38, 17.27, 282.11, 22.07, 223.58, 35.5, 178.48, 61.41, 152.57, 74.84, 137.22, 78.68, 113.23, 78.68, 86.36, 85.4, 64.29, 101.71, 44.14, 121.86, 36.46, 162.16, 63.33, 167.92, 96.91, 167.92, 127.62, 171.76, 165.04, 178.48, 192.87, 178.48, 230.29, 171.76, 261.96, 180.4, 304.18, 166.0, 324.33, 129.54, 327.21, 113.23, 332.0, 98.83, 344.48, 170.8, 370.39, 321.45, 415.49]], "area": 44344.8626, "iscrowd": 0, "image_id": 24689, "bbox": [17.27, 36.46, 304.18, 379.03], "category_id": 1, "id": 424626, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "black", "shirt", "holding", "a", "knife"], "raw": "A woman in a black shirt holding a knife.", "sent_id": 45248, "sent": "a woman in a black shirt holding a knife"}, {"tokens": ["a", "woman", "in", "a", "black", "sweater", "preparing", "to", "eat"], "raw": "A woman in a black sweater preparing to eat.", "sent_id": 45249, "sent": "a woman in a black sweater preparing to eat"}], "file_name": "COCO_train2014_000000024689_424626.jpg", "ann_id": 424626, "sent_ids": [45248, 45249], "ref_id": 22405}, {"segmentation": [[310.69, 632.98, 283.49, 630.12, 287.79, 601.48, 276.33, 559.96, 266.31, 521.3, 272.04, 426.81, 246.26, 412.49, 251.99, 388.15, 272.04, 412.49, 279.19, 409.62, 273.47, 379.56, 287.79, 362.38, 264.88, 322.29, 251.99, 290.79, 259.15, 280.76, 277.76, 300.81, 293.51, 328.01, 313.56, 292.22, 327.87, 265.02, 319.28, 244.97, 325.01, 217.77, 340.76, 193.43, 382.28, 194.86, 388.01, 222.06, 372.26, 259.29, 382.28, 313.7, 375.12, 356.65, 359.37, 379.56, 353.65, 418.21, 340.76, 449.71, 327.87, 479.78, 325.01, 514.14, 332.17, 559.96, 332.17, 601.48, 336.47, 625.82, 325.01, 625.82, 313.56, 620.09]], "area": 29964.507850000005, "iscrowd": 0, "image_id": 142825, "bbox": [246.26, 193.43, 141.75, 439.55], "category_id": 1, "id": 1710919, "split": "val", "sentences": [{"tokens": ["man", "in", "blue", "holding", "child"], "raw": "Man in blue holding child", "sent_id": 45264, "sent": "man in blue holding child"}, {"tokens": ["a", "man", "holding", "a", "little", "boy", ",", "both", "with", "dark", "hair", ",", "the", "boy", "is", "wearing", "blue", "striped", "socks", "and", "the", "man", "is", "wearing", "jeans", "that", "go", "just", "below", "his", "knees"], "raw": "a man holding a little boy, both with dark hair, the boy is wearing blue striped socks and the man is wearing jeans that go just below his knees", "sent_id": 45265, "sent": "a man holding a little boy , both with dark hair , the boy is wearing blue striped socks and the man is wearing jeans that go just below his knees"}], "file_name": "COCO_train2014_000000142825_1710919.jpg", "ann_id": 1710919, "sent_ids": [45264, 45265], "ref_id": 22410}, {"segmentation": [[607.28, 181.21, 613.75, 204.94, 629.93, 217.89, 640.0, 229.75, 639.64, 269.66, 590.02, 290.16, 525.3, 308.49, 512.36, 323.6, 500.49, 328.99, 477.84, 318.2, 449.8, 279.37, 450.88, 267.51, 454.11, 256.72, 442.25, 229.75, 454.11, 220.04, 459.51, 202.79, 501.57, 190.92, 564.13, 177.98, 605.12, 172.58, 607.28, 173.66]], "area": 20654.031800000004, "iscrowd": 0, "image_id": 529929, "bbox": [442.25, 172.58, 197.75, 156.41], "category_id": 61, "id": 1084232, "split": "val", "sentences": [{"tokens": ["brownie", "with", "white", "top"], "raw": "brownie with white top", "sent_id": 45266, "sent": "brownie with white top"}, {"tokens": ["a", "piece", "of", "chocolate", "cake", "with", "white", "frosting", "and", "toppings", "on", "it"], "raw": "A piece of chocolate cake with white frosting and toppings on it.", "sent_id": 45267, "sent": "a piece of chocolate cake with white frosting and toppings on it"}], "file_name": "COCO_train2014_000000529929_1084232.jpg", "ann_id": 1084232, "sent_ids": [45266, 45267], "ref_id": 22411}, {"segmentation": [[65.68, 549.89, 58.6, 541.89, 55.06, 534.81, 48.62, 526.76, 38.0, 509.06, 36.23, 494.34, 36.23, 480.71, 40.36, 477.0, 38.15, 459.99, 39.4, 433.7, 56.93, 384.87, 64.44, 360.45, 36.44, 308.49, 22.83, 293.52, 43.24, 241.14, 69.77, 199.64, 105.9, 157.62, 153.93, 146.27, 166.15, 143.65, 172.26, 138.41, 178.37, 106.98, 201.95, 82.53, 219.93, 79.09, 233.76, 81.5, 245.61, 92.16, 258.64, 109.93, 264.26, 127.1, 261.89, 142.21, 254.19, 150.79, 248.05, 148.97, 245.72, 152.58, 237.01, 155.13, 225.97, 154.49, 215.57, 159.38, 208.35, 164.9, 203.04, 165.32, 191.37, 169.99, 179.48, 179.55, 172.44, 188.05, 167.82, 195.66, 166.44, 201.43, 166.44, 204.66, 162.98, 204.66, 159.75, 208.12, 159.29, 211.58, 148.21, 213.89, 119.83, 233.04, 108.73, 245.27, 109.28, 284.51, 135.71, 285.6, 130.53, 296.23, 136.53, 315.03, 136.25, 336.83, 135.68, 366.17, 140.95, 392.75, 153.12, 412.08, 144.63, 423.74, 145.69, 437.52, 144.63, 446.0, 143.57, 455.54, 146.75, 484.7, 147.28, 496.89, 146.75, 505.37, 140.39, 512.79, 148.88, 527.1, 143.7, 539.42, 102.88, 542.6, 92.81, 547.37, 76.91, 554.79], [171.15, 549.5, 168.01, 556.5, 180.25, 553.7, 182.69, 548.45], [171.61, 236.99, 185.15, 230.72, 188.66, 231.47, 189.14, 234.15, 191.11, 234.57, 193.63, 233.73, 194.33, 237.8, 192.93, 239.2, 194.61, 241.3, 194.75, 243.68, 188.02, 247.18, 189.7, 249.98, 188.02, 252.36, 173.04, 257.97, 166.59, 260.63, 141.1, 258.25, 142.08, 253.76, 141.66, 252.5, 148.66, 251.52, 164.49, 241.72, 172.34, 236.95]], "area": 43040.962199999994, "iscrowd": 0, "image_id": 101832, "bbox": [22.83, 79.09, 241.43, 477.41], "category_id": 1, "id": 447310, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "is", "helping", "a", "little", "girl", "try", "to", "stand", "on", "a", "skateboard"], "raw": "A young boy is helping a little girl try to stand on a skateboard.", "sent_id": 45282, "sent": "a young boy is helping a little girl try to stand on a skateboard"}, {"tokens": ["a", "boy", "helping", "a", "girl", "ride", "a", "skateboard"], "raw": "A boy helping a girl ride a skateboard.", "sent_id": 45283, "sent": "a boy helping a girl ride a skateboard"}], "file_name": "COCO_train2014_000000101832_447310.jpg", "ann_id": 447310, "sent_ids": [45282, 45283], "ref_id": 22415}, {"segmentation": [[488.76, 221.63, 475.28, 288.2, 340.45, 301.69, 334.55, 294.94, 325.28, 265.45, 356.46, 260.39, 367.42, 181.18, 495.51, 189.61, 489.61, 224.16]], "area": 14606.342199999997, "iscrowd": 0, "image_id": 304757, "bbox": [325.28, 181.18, 170.23, 120.51], "category_id": 73, "id": 1102641, "split": "val", "sentences": [{"tokens": ["a", "silver", "apple", "laptop", "with", "a", "sticker", "on", "the", "corner"], "raw": "A silver Apple laptop with a sticker on the corner.", "sent_id": 45397, "sent": "a silver apple laptop with a sticker on the corner"}, {"tokens": ["apple", "laptop"], "raw": "apple laptop", "sent_id": 45398, "sent": "apple laptop"}], "file_name": "COCO_train2014_000000304757_1102641.jpg", "ann_id": 1102641, "sent_ids": [45397, 45398], "ref_id": 22456}, {"segmentation": [[466.9, 203.64, 437.88, 196.07, 426.52, 215.0, 423.37, 230.14, 424.0, 243.39, 438.51, 275.57, 460.59, 303.33, 479.52, 330.46, 504.13, 348.13, 534.41, 363.9, 542.61, 368.32, 560.28, 363.27, 572.9, 363.9, 586.78, 361.38, 595.61, 355.7, 596.24, 349.39, 596.24, 335.51, 586.78, 326.04, 572.9, 319.1, 555.86, 307.75, 531.89, 287.56, 504.13, 264.21, 483.94, 240.87, 471.32, 222.57, 468.79, 212.47]], "area": 12366.949550000003, "iscrowd": 0, "image_id": 205757, "bbox": [423.37, 196.07, 172.87, 172.25], "category_id": 52, "id": 1044409, "split": "val", "sentences": [{"tokens": ["the", "fry", "on", "top", "of", "the", "pile", "of", "fries"], "raw": "The fry on top of the pile of fries", "sent_id": 45413, "sent": "the fry on top of the pile of fries"}, {"tokens": ["the", "french", "fry", "on", "top", "of", "the", "stack", "with", "4", "darker", "lines", "on", "it"], "raw": "The french fry on top of the stack with 4 darker lines on it", "sent_id": 45414, "sent": "the french fry on top of the stack with 4 darker lines on it"}], "file_name": "COCO_train2014_000000205757_1044409.jpg", "ann_id": 1044409, "sent_ids": [45413, 45414], "ref_id": 22463}, {"segmentation": [[474.55, 12.15, 436.14, 134.67, 444.37, 152.96, 468.15, 153.87, 475.46, 157.53, 499.23, 179.47, 502.89, 181.3, 557.75, 186.79, 544.95, 219.7, 552.27, 220.62, 600.73, 89.87, 550.44, 147.47, 546.78, 163.01, 542.21, 176.73, 526.66, 166.67, 519.35, 151.13, 516.61, 122.78, 528.49, 89.87, 537.64, 67.01, 538.55, 49.64, 543.12, 23.12, 539.46, 6.66]], "area": 14461.739849999996, "iscrowd": 0, "image_id": 88671, "bbox": [436.14, 6.66, 164.59, 213.96], "category_id": 62, "id": 103065, "split": "val", "sentences": [{"tokens": ["a", "bar", "stool", "with", "a", "person", "sitting", "on", "it"], "raw": "A bar stool with a person sitting on it.", "sent_id": 45419, "sent": "a bar stool with a person sitting on it"}, {"tokens": ["the", "barstool", "with", "the", "man", "'", "s", "foot", "resting", "on", "the", "bottom"], "raw": "The barstool with the man's foot resting on the bottom.", "sent_id": 45420, "sent": "the barstool with the man ' s foot resting on the bottom"}], "file_name": "COCO_train2014_000000088671_103065.jpg", "ann_id": 103065, "sent_ids": [45419, 45420], "ref_id": 22466}, {"segmentation": [[301.83, 223.47, 310.08, 208.49, 361.76, 214.48, 370.75, 220.48, 373.74, 232.46, 416.0, 241.45, 414.2, 280.4, 405.21, 287.89, 391.72, 284.89, 387.23, 282.65, 381.99, 276.66, 343.79, 274.41, 340.03, 265.42, 323.56, 242.95, 319.07, 231.71, 283.11, 227.96, 280.87, 224.22, 299.58, 224.22]], "area": 5134.517350000003, "iscrowd": 0, "image_id": 234516, "bbox": [280.87, 208.49, 135.13, 79.4], "category_id": 8, "id": 396447, "split": "val", "sentences": [{"tokens": ["a", "truck", "right", "beneath", "the", "\"", "glass", "\"", "sign"], "raw": "A truck right beneath the \"Glass\" sign.", "sent_id": 45576, "sent": "a truck right beneath the \" glass \" sign"}, {"tokens": ["pick", "up", "truck", "in", "front", "of", "door", "with", "word", "glass", "on", "it"], "raw": "pick up truck in front of door with word GLASS on it", "sent_id": 45577, "sent": "pick up truck in front of door with word glass on it"}], "file_name": "COCO_train2014_000000234516_396447.jpg", "ann_id": 396447, "sent_ids": [45576, 45577], "ref_id": 22527}, {"segmentation": [[4.31, 478.92, 23.01, 458.79, 89.17, 448.72, 102.11, 461.66, 116.49, 476.04, 169.71, 478.92, 211.42, 494.74, 243.06, 529.26, 256.0, 599.73, 240.18, 629.93, 221.48, 637.12, 23.01, 637.12, 4.31, 640.0]], "area": 39322.15539999999, "iscrowd": 0, "image_id": 566301, "bbox": [4.31, 448.72, 251.69, 191.28], "category_id": 59, "id": 1073277, "split": "val", "sentences": [{"tokens": ["the", "first", "pizza", "from", "the", "front"], "raw": "the first pizza from the front", "sent_id": 45597, "sent": "the first pizza from the front"}, {"tokens": ["pizza", "at", "the", "bottom", "left", "with", "the", "green", "and", "yellow", "toppings"], "raw": "Pizza at the bottom left with  the green and yellow toppings.", "sent_id": 45598, "sent": "pizza at the bottom left with the green and yellow toppings"}], "file_name": "COCO_train2014_000000566301_1073277.jpg", "ann_id": 1073277, "sent_ids": [45597, 45598], "ref_id": 22537}, {"segmentation": [[89.17, 292.95, 158.2, 294.39, 159.64, 246.93, 189.84, 255.56, 205.66, 298.71, 209.98, 290.08, 235.87, 291.52, 244.49, 297.27, 277.57, 297.27, 304.9, 305.9, 254.56, 321.72, 283.33, 331.79, 299.15, 314.53, 312.09, 328.91, 356.67, 327.47, 359.55, 337.54, 330.79, 347.61, 312.09, 420.95, 267.51, 380.68, 258.88, 370.62, 256.0, 379.25, 244.49, 367.74, 215.73, 354.8, 240.18, 385.0, 220.04, 390.75, 175.46, 338.98]], "area": 15700.322999999993, "iscrowd": 0, "image_id": 116040, "bbox": [89.17, 246.93, 270.38, 174.02], "category_id": 5, "id": 161430, "split": "val", "sentences": [{"tokens": ["a", "fighter", "jet", "in", "the", "middle"], "raw": "A fighter jet in the middle.", "sent_id": 45646, "sent": "a fighter jet in the middle"}, {"tokens": ["2", "air", "force", "jets", "in", "between", "the", "outer", "jets"], "raw": "2 air force jets in between the outer jets", "sent_id": 45647, "sent": "2 air force jets in between the outer jets"}], "file_name": "COCO_train2014_000000116040_161430.jpg", "ann_id": 161430, "sent_ids": [45646, 45647], "ref_id": 22554}, {"segmentation": [[0.0, 30.17, 31.14, 37.69, 48.32, 43.06, 48.32, 34.47, 70.87, 20.51, 111.68, 26.95, 178.26, 50.57, 217.99, 70.98, 237.32, 86.01, 267.38, 83.86, 263.09, 95.67, 238.39, 123.59, 235.17, 124.67, 256.64, 147.22, 258.79, 167.62, 268.46, 193.39, 292.08, 251.38, 278.12, 287.89, 259.87, 290.04, 249.13, 285.74, 235.17, 258.9, 214.77, 249.23, 190.07, 239.57, 175.03, 225.61, 161.07, 196.61, 95.57, 207.35, 88.05, 224.53, 73.02, 270.71, 62.28, 307.22, 53.69, 366.28, 68.72, 423.19, 50.47, 421.04, 40.81, 416.75, 33.29, 403.86, 38.66, 361.98, 37.58, 326.55, 40.81, 271.78, 23.62, 268.56, 21.48, 360.91, 10.74, 379.16, 20.4, 441.45, 0.0, 440.37]], "area": 59575.48624999999, "iscrowd": 0, "image_id": 306837, "bbox": [0.0, 20.51, 292.08, 420.94], "category_id": 24, "id": 589998, "split": "val", "sentences": [{"tokens": ["zebra", "standing", "on", "the", "left", "corner", "without", "eating", "grass"], "raw": "zebra standing on the left corner without eating grass", "sent_id": 45665, "sent": "zebra standing on the left corner without eating grass"}, {"tokens": ["zebra", "whose", "head", "is", "not", "facing", "down"], "raw": "zebra whose head is not facing down", "sent_id": 45666, "sent": "zebra whose head is not facing down"}], "file_name": "COCO_train2014_000000306837_589998.jpg", "ann_id": 589998, "sent_ids": [45665, 45666], "ref_id": 22561}, {"segmentation": [[402.59, 48.84, 393.57, 51.85, 392.44, 31.57, 379.3, 21.42, 361.27, 12.03, 361.27, 0.0, 533.29, 0.0, 640.0, 0.0, 639.59, 33.07, 638.84, 38.7, 609.54, 54.1, 599.77, 63.49, 594.14, 71.75, 544.56, 94.67, 541.56, 79.64, 541.93, 72.88, 539.3, 68.37, 527.66, 67.25, 518.27, 68.0, 512.26, 73.63, 512.26, 84.15, 508.13, 93.54, 507.0, 114.57, 472.45, 133.35, 450.29, 140.11, 438.27, 127.72, 422.87, 118.33, 419.86, 111.57, 408.22, 95.42, 414.61, 78.89, 406.72, 71.0, 417.61, 36.45, 418.74, 24.05, 402.96, 35.32], [449.65, 255.29, 449.65, 242.2, 451.93, 236.5, 451.93, 205.76, 454.21, 191.53, 467.3, 185.27, 496.9, 189.25, 488.93, 231.95, 478.69, 324.18, 472.99, 377.69, 457.05, 356.63, 449.08, 346.95, 429.73, 324.74, 433.71, 310.51], [523.66, 245.04, 526.51, 198.93, 527.08, 185.27, 546.43, 175.59, 582.87, 171.6, 627.84, 163.63, 625.0, 169.33, 617.6, 180.71, 609.63, 188.68, 619.3, 244.47, 615.32, 326.45, 611.9, 369.72, 566.93, 359.47, 545.29, 349.22, 507.72, 332.15]], "area": 47183.45195, "iscrowd": 0, "image_id": 173032, "bbox": [361.27, 0.0, 278.73, 377.69], "category_id": 1, "id": 2005271, "split": "val", "sentences": [{"tokens": ["man", "standing", "in", "the", "backside", "with", "ash", "color", "pant", "and", "blue", "color", "t", "-", "shirt"], "raw": "man standing in the backside with ash color pant and blue color t-shirt", "sent_id": 45686, "sent": "man standing in the backside with ash color pant and blue color t - shirt"}, {"tokens": ["a", "person", "standing", "in", "a", "blue", "and", "white", "shirt", "with", "khaki", "shorts"], "raw": "A person standing in a blue and white shirt with khaki shorts.", "sent_id": 45687, "sent": "a person standing in a blue and white shirt with khaki shorts"}], "file_name": "COCO_train2014_000000173032_2005271.jpg", "ann_id": 2005271, "sent_ids": [45686, 45687], "ref_id": 22571}, {"segmentation": [[208.65, 428.65, 345.95, 437.3, 431.35, 424.32, 481.08, 425.41, 495.14, 425.41, 504.86, 478.38, 340.54, 480.0, 169.73, 480.0]], "area": 15306.10985, "iscrowd": 0, "image_id": 513683, "bbox": [169.73, 424.32, 335.13, 55.68], "category_id": 84, "id": 1654363, "split": "val", "sentences": [{"tokens": ["a", "wine", "list", "at", "fine", "dining", "establishment", "or", "lodge", "of", "some", "sort"], "raw": "a wine list at fine dining establishment or lodge of some sort", "sent_id": 45733, "sent": "a wine list at fine dining establishment or lodge of some sort"}, {"tokens": ["the", "menu", "in", "front", "of", "the", "man", "and", "woman"], "raw": "The menu in front of the man and woman.", "sent_id": 45734, "sent": "the menu in front of the man and woman"}], "file_name": "COCO_train2014_000000513683_1654363.jpg", "ann_id": 1654363, "sent_ids": [45733, 45734], "ref_id": 22589}, {"segmentation": [[135.4, 363.56, 134.14, 400.64, 148.46, 417.49, 155.21, 403.59, 172.06, 383.78, 202.82, 342.91, 221.36, 323.95, 232.74, 316.78, 233.58, 307.09, 229.37, 283.07, 212.94, 219.86, 196.92, 206.38, 154.35, 201.63, 145.28, 178.24, 127.14, 158.67, 113.77, 151.99, 95.63, 195.43, 115.2, 222.16, 90.02, 247.17, 92.3, 337.49, 110.94, 323.18, 128.24, 340.48, 135.27, 366.98]], "area": 21844.36415, "iscrowd": 0, "image_id": 193682, "bbox": [90.02, 151.99, 143.56, 265.5], "category_id": 1, "id": 2166595, "split": "val", "sentences": [{"tokens": ["net"], "raw": "net", "sent_id": 45775, "sent": "net"}], "file_name": "COCO_train2014_000000193682_2166595.jpg", "ann_id": 2166595, "sent_ids": [45775], "ref_id": 22604}, {"segmentation": [[166.11, 42.34, 119.73, 47.73, 3.24, 32.63, 1.08, 2.43, 367.82, 2.43, 359.19, 17.53, 330.07, 14.29, 308.49, 15.37, 283.69, 30.47, 251.33, 31.55, 217.89, 26.16, 211.42, 31.55, 206.02, 40.18, 180.13, 32.63, 176.9, 42.34]], "area": 11223.06035, "iscrowd": 0, "image_id": 516106, "bbox": [1.08, 2.43, 366.74, 45.3], "category_id": 28, "id": 1428974, "split": "val", "sentences": [{"tokens": ["the", "yellow", "table", "shade", "above", "the", "man", "in", "the", "foreground"], "raw": "The yellow table shade above the man in the foreground", "sent_id": 45780, "sent": "the yellow table shade above the man in the foreground"}, {"tokens": ["white", "umbrella", "on", "the", "left"], "raw": "White umbrella on the left.", "sent_id": 45781, "sent": "white umbrella on the left"}], "file_name": "COCO_train2014_000000516106_1428974.jpg", "ann_id": 1428974, "sent_ids": [45780, 45781], "ref_id": 22606}, {"segmentation": [[561.69, 19.74, 555.96, 4.46, 544.5, 0.0, 456.61, 4.46, 457.57, 12.1, 454.7, 14.97, 427.0, 30.25, 426.04, 35.98, 445.15, 41.71, 451.84, 42.67, 454.7, 51.27, 458.52, 59.86, 466.17, 65.59, 466.17, 76.1, 474.76, 87.57, 475.72, 88.52, 491.96, 84.7, 482.4, 98.07, 463.3, 124.82, 448.02, 143.93, 426.04, 180.23, 414.58, 198.38, 400.25, 210.79, 385.92, 218.44, 382.1, 226.08, 374.46, 227.99, 373.51, 227.03, 361.09, 227.99, 350.58, 229.9, 345.8, 233.72, 341.98, 245.18, 341.98, 249.0, 347.71, 252.82, 363.95, 254.74, 376.37, 253.78, 389.74, 252.82, 389.74, 270.97, 372.55, 292.95, 359.18, 285.3, 342.94, 281.48, 332.43, 294.86, 326.7, 310.14, 332.43, 317.78, 341.98, 319.69, 361.09, 322.56, 374.46, 323.51, 385.92, 322.56, 398.34, 322.56, 401.21, 324.47, 416.49, 328.29, 427.0, 326.38, 429.87, 325.42, 430.82, 407.58, 426.04, 419.04, 547.36, 420.95, 557.87, 391.34, 578.89, 365.55, 588.44, 348.35, 588.44, 334.98, 599.9, 321.6, 605.63, 296.77, 624.74, 242.32, 629.51, 187.87, 634.29, 140.1, 631.43, 111.45, 617.1, 67.5, 606.59, 59.86, 606.59, 57.0, 619.96, 51.27, 602.77, 16.88, 578.89, 13.06, 558.83, 24.52, 555.96, 26.43]], "area": 78146.13, "iscrowd": 0, "image_id": 438071, "bbox": [326.7, 0.0, 307.59, 420.95], "category_id": 1, "id": 1715647, "split": "val", "sentences": [{"tokens": ["man", "in", "black", "jacket", "getting", "a", "drink"], "raw": "man in black jacket getting a drink", "sent_id": 45832, "sent": "man in black jacket getting a drink"}, {"tokens": ["the", "man", "in", "the", "black", "sweatshirt"], "raw": "The man in the black sweatshirt.", "sent_id": 45833, "sent": "the man in the black sweatshirt"}], "file_name": "COCO_train2014_000000438071_1715647.jpg", "ann_id": 1715647, "sent_ids": [45832, 45833], "ref_id": 22631}, {"segmentation": [[1.91, 127.14, 119.41, 145.29, 113.68, 181.59, 116.54, 250.37, 107.94, 314.37, 95.53, 349.72, 83.11, 422.32, 0.0, 420.41, 0.96, 130.01]], "area": 30290.272050000003, "iscrowd": 0, "image_id": 121619, "bbox": [0.0, 127.14, 119.41, 295.18], "category_id": 3, "id": 351073, "split": "val", "sentences": [{"tokens": ["part", "of", "the", "back", "of", "a", "shinny", "grey", "car"], "raw": "part of the back of a shinny grey car", "sent_id": 45901, "sent": "part of the back of a shinny grey car"}, {"tokens": ["a", "white", "car"], "raw": "A white car.", "sent_id": 45902, "sent": "a white car"}], "file_name": "COCO_train2014_000000121619_351073.jpg", "ann_id": 351073, "sent_ids": [45901, 45902], "ref_id": 22655}, {"segmentation": [[210.86, 501.35, 173.19, 488.56, 139.79, 444.5, 134.11, 401.86, 145.48, 362.06, 175.32, 325.82, 211.57, 310.19, 227.91, 307.34, 254.92, 315.16, 274.82, 321.56, 297.56, 347.14, 313.9, 382.67, 308.93, 426.73, 287.61, 467.24, 259.89, 486.43, 232.18, 499.93, 215.12, 502.06]], "area": 26253.071100000005, "iscrowd": 0, "image_id": 295970, "bbox": [134.11, 307.34, 179.79, 194.72], "category_id": 55, "id": 1053437, "split": "val", "sentences": [{"tokens": ["rotten", "fruit", "with", "a", "face", "carved", "into", "it"], "raw": "Rotten fruit with a face carved into it", "sent_id": 45947, "sent": "rotten fruit with a face carved into it"}, {"tokens": ["rotting", "orange", "with", "face", "drawn", "on", "it"], "raw": "rotting orange with face drawn on it", "sent_id": 45948, "sent": "rotting orange with face drawn on it"}], "file_name": "COCO_train2014_000000295970_1053437.jpg", "ann_id": 1053437, "sent_ids": [45947, 45948], "ref_id": 22674}, {"segmentation": [[301.6, 403.71, 350.7, 397.31, 352.3, 393.04, 383.78, 391.97, 407.8, 394.11, 411.0, 395.17, 427.54, 395.71, 443.55, 378.1, 444.62, 376.5, 427.01, 372.76, 432.34, 371.16, 446.75, 373.29, 455.29, 365.82, 440.35, 359.42, 445.15, 355.15, 472.9, 360.49, 489.44, 365.82, 494.25, 367.96, 484.11, 370.63, 468.63, 407.98, 469.7, 408.51, 500.12, 382.9, 515.06, 385.57, 511.86, 403.71, 526.27, 393.57, 540.14, 397.31, 523.06, 426.66, 368.84, 426.13, 310.14, 412.78, 299.47, 405.85, 303.73, 400.51]], "area": 8114.819999999999, "iscrowd": 0, "image_id": 171478, "bbox": [299.47, 355.15, 240.67, 71.51], "category_id": 5, "id": 162547, "split": "val", "sentences": [{"tokens": ["a", "blue", "plane", "flying", "under", "the", "other", "planes"], "raw": "A blue plane flying under the other planes.", "sent_id": 45952, "sent": "a blue plane flying under the other planes"}, {"tokens": ["the", "plane", "below", "the", "one", "spitting", "out", "smoke"], "raw": "The plane below the one spitting out smoke.", "sent_id": 45953, "sent": "the plane below the one spitting out smoke"}], "file_name": "COCO_train2014_000000171478_162547.jpg", "ann_id": 162547, "sent_ids": [45952, 45953], "ref_id": 22675}, {"segmentation": [[312.02, 4.55, 310.1, 11.25, 307.23, 25.6, 307.23, 45.7, 310.1, 67.72, 297.66, 81.12, 286.18, 95.47, 275.65, 98.34, 267.99, 120.36, 261.29, 138.54, 244.06, 165.34, 249.81, 167.26, 249.81, 168.21, 242.15, 181.61, 229.71, 224.68, 216.31, 246.7, 213.44, 260.09, 214.39, 264.88, 211.52, 275.41, 214.39, 277.32, 223.96, 269.67, 238.32, 262.97, 247.89, 264.88, 245.02, 243.82, 246.93, 224.68, 273.73, 173.95, 275.65, 174.91, 278.52, 189.27, 276.6, 194.05, 262.25, 221.81, 249.81, 253.4, 254.59, 265.84, 240.23, 279.24, 232.58, 291.68, 218.22, 320.39, 210.56, 344.32, 204.82, 355.81, 203.86, 371.12, 196.21, 383.56, 184.72, 387.39, 172.28, 382.6, 166.54, 382.6, 156.97, 382.6, 152.18, 393.13, 165.58, 414.19, 187.59, 418.98, 208.65, 417.06, 221.09, 387.39, 262.25, 322.31, 268.95, 304.12, 299.58, 273.49, 329.25, 248.61, 368.49, 284.98, 391.46, 326.14, 401.99, 373.03, 410.6, 398.88, 412.51, 417.06, 458.46, 418.02, 454.63, 412.28, 440.27, 397.92, 434.53, 355.81, 422.09, 297.42, 411.56, 273.49, 404.86, 250.52, 387.63, 205.54, 381.89, 160.56, 397.2, 170.13, 421.13, 215.11, 422.09, 226.6, 419.21, 236.17, 412.51, 240.0, 411.56, 255.31, 416.34, 262.97, 430.7, 261.05, 431.66, 279.24, 439.31, 264.88, 440.27, 234.25, 439.31, 215.11, 431.66, 178.74, 411.56, 146.2, 405.81, 110.79, 388.59, 85.9, 381.89, 54.32, 390.5, 25.6, 378.06, 0.72]], "area": 48200.958849999995, "iscrowd": 0, "image_id": 288234, "bbox": [152.18, 0.72, 306.28, 418.26], "category_id": 1, "id": 457145, "split": "val", "sentences": [{"tokens": ["a", "boy", "playing", "baseball", "wearing", "a", "blue", "and", "white", "uniform"], "raw": "A boy playing baseball wearing a blue and white uniform.", "sent_id": 45980, "sent": "a boy playing baseball wearing a blue and white uniform"}, {"tokens": ["child", "player", "morgan"], "raw": "Child player MORGAN", "sent_id": 45981, "sent": "child player morgan"}], "file_name": "COCO_train2014_000000288234_457145.jpg", "ann_id": 457145, "sent_ids": [45980, 45981], "ref_id": 22686}, {"segmentation": [[489.37, 221.66, 540.23, 215.9, 581.49, 227.41, 599.72, 254.28, 598.76, 283.07, 590.12, 297.46, 569.97, 305.14, 546.94, 305.14, 519.12, 306.1, 499.93, 308.98, 486.49, 304.18, 486.49, 290.74, 474.02, 286.91, 463.46, 286.91, 438.51, 293.62, 415.49, 295.54, 391.5, 299.38, 361.75, 297.46, 365.59, 278.27, 375.18, 258.12, 389.58, 245.64, 411.65, 236.05, 439.47, 231.25, 455.79, 228.37, 470.18, 224.53]], "area": 15984.080100000003, "iscrowd": 0, "image_id": 50601, "bbox": [361.75, 215.9, 237.97, 93.08], "category_id": 23, "id": 587528, "split": "val", "sentences": [{"tokens": ["a", "black", "dog", "sitting", "outside", "a", "chainlinked", "fence"], "raw": "A black dog sitting outside a chainlinked fence", "sent_id": 46069, "sent": "a black dog sitting outside a chainlinked fence"}, {"tokens": ["a", "black", "animal", "right", "next", "to", "a", "fencepost"], "raw": "A black animal right next to a fencepost.", "sent_id": 46070, "sent": "a black animal right next to a fencepost"}], "file_name": "COCO_train2014_000000050601_587528.jpg", "ann_id": 587528, "sent_ids": [46069, 46070], "ref_id": 22723}, {"segmentation": [[113.92, 176.49, 137.18, 160.45, 154.83, 155.64, 178.9, 149.22, 201.36, 139.59, 226.23, 130.77, 223.83, 121.94, 206.18, 129.16, 178.1, 129.16, 154.83, 125.15, 148.42, 117.93, 164.46, 100.28, 170.08, 90.65, 156.44, 81.83, 146.01, 81.03, 137.18, 85.84, 125.15, 101.89, 126.76, 107.5, 109.11, 100.28, 89.05, 102.69, 69.8, 108.3, 81.03, 117.93, 68.99, 131.57, 62.58, 140.39, 67.39, 146.81, 63.38, 169.27, 39.31, 194.95, 21.66, 226.23, 18.45, 264.74, 5.62, 285.6, 13.64, 299.24, 27.28, 275.97, 30.49, 265.54, 31.29, 251.1, 55.36, 225.43, 88.25, 210.19, 89.05, 239.07, 99.48, 237.47, 96.27, 258.32, 87.44, 296.03, 110.71, 299.24]], "area": 13650.504199999998, "iscrowd": 0, "image_id": 535234, "bbox": [5.62, 81.03, 220.61, 218.21], "category_id": 1, "id": 450709, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "in", "a", "texas", "jersey"], "raw": "A baseball player in a Texas jersey", "sent_id": 46190, "sent": "a baseball player in a texas jersey"}, {"tokens": ["the", "man", "in", "the", "blue", "shirt"], "raw": "The man in the blue shirt.", "sent_id": 46191, "sent": "the man in the blue shirt"}], "file_name": "COCO_train2014_000000535234_450709.jpg", "ann_id": 450709, "sent_ids": [46190, 46191], "ref_id": 22758}, {"segmentation": [[497.26, 388.31, 366.74, 423.91, 253.48, 428.22, 161.8, 420.67, 8.63, 386.16, 0.0, 285.84, 0.0, 201.71, 40.99, 181.21, 106.79, 111.1, 319.28, 35.6, 637.48, 160.72, 640.0, 296.63, 502.65, 387.24]], "area": 189058.49285, "iscrowd": 0, "image_id": 517985, "bbox": [0.0, 35.6, 640.0, 392.62], "category_id": 51, "id": 1532012, "split": "val", "sentences": [{"tokens": ["chinese", "food", "rests", "in", "a", "blue", "dish", "with", "broccoli", "and", "tiny", "corn"], "raw": "Chinese food rests in a blue dish with broccoli and tiny corn.", "sent_id": 46225, "sent": "chinese food rests in a blue dish with broccoli and tiny corn"}, {"tokens": ["a", "dish", "of", "food", "containing", "broccoli", ",", "mushroom", ",", "beansprouts", "and", "corn"], "raw": "A dish of food containing broccoli, mushroom, beansprouts and corn.", "sent_id": 46226, "sent": "a dish of food containing broccoli , mushroom , beansprouts and corn"}], "file_name": "COCO_train2014_000000517985_1532012.jpg", "ann_id": 1532012, "sent_ids": [46225, 46226], "ref_id": 22767}, {"segmentation": [[410.16, 87.37, 394.79, 102.74, 387.51, 127.82, 399.64, 162.61, 413.39, 179.6, 438.47, 207.91, 451.42, 215.19, 474.07, 210.34, 489.44, 207.91, 504.81, 200.63, 520.18, 194.16, 546.88, 178.79, 552.54, 163.42, 550.92, 125.39, 541.21, 121.35, 535.55, 85.75, 519.37, 86.56, 446.56, 105.17, 440.09, 84.94, 427.96, 86.56, 419.06, 88.18, 412.58, 84.13, 409.35, 88.99]], "area": 15976.108099999998, "iscrowd": 0, "image_id": 246641, "bbox": [387.51, 84.13, 165.03, 131.06], "category_id": 54, "id": 312388, "split": "val", "sentences": [{"tokens": ["the", "sandwhich", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the sandwhich on the right in the right hand picture", "sent_id": 46240, "sent": "the sandwhich on the right in the right hand picture"}], "file_name": "COCO_train2014_000000246641_312388.jpg", "ann_id": 312388, "sent_ids": [46240], "ref_id": 22770}, {"segmentation": [[146.13, 372.27, 154.67, 370.13, 155.73, 348.8, 162.13, 325.33, 172.8, 334.93, 197.33, 342.4, 214.4, 342.4, 224.0, 352.0, 230.4, 370.13, 231.47, 388.27, 244.27, 389.33, 252.8, 381.87, 262.4, 373.33, 257.07, 365.87, 258.13, 353.07, 259.2, 341.33, 262.4, 334.93, 270.93, 325.33, 279.47, 313.6, 283.73, 305.07, 285.87, 296.53, 283.73, 288.0, 283.73, 278.4, 302.93, 276.27, 316.8, 258.13, 311.47, 244.27, 307.2, 238.93, 305.07, 232.53, 286.93, 222.93, 274.13, 224.0, 261.33, 232.53, 235.73, 248.53, 221.87, 256.0, 208.0, 257.07, 194.13, 254.93, 189.87, 249.6, 178.13, 248.53, 166.4, 248.53, 149.33, 256.0, 147.2, 262.4, 144.0, 270.93, 141.87, 280.53, 138.67, 309.33, 140.8, 323.2, 145.07, 338.13, 145.07, 348.8, 141.87, 358.4, 141.87, 368.0]], "area": 15924.831950000002, "iscrowd": 0, "image_id": 124694, "bbox": [138.67, 222.93, 178.13, 166.4], "category_id": 20, "id": 62264, "split": "val", "sentences": [{"tokens": ["sheep", "under", "arm", "of", "woman", "wearing", "dark", "top"], "raw": "Sheep under arm of woman wearing dark top", "sent_id": 46282, "sent": "sheep under arm of woman wearing dark top"}, {"tokens": ["a", "sheep", "being", "petted", "by", "a", "blonde", "woman"], "raw": "A sheep being petted by a blonde woman.", "sent_id": 46283, "sent": "a sheep being petted by a blonde woman"}], "file_name": "COCO_train2014_000000124694_62264.jpg", "ann_id": 62264, "sent_ids": [46282, 46283], "ref_id": 22788}, {"segmentation": [[251.66, 292.97, 241.46, 292.97, 241.46, 283.55, 246.95, 263.16, 255.58, 231.0, 265.78, 218.45, 239.11, 188.64, 220.44, 171.09, 220.36, 165.77, 226.55, 150.2, 221.85, 141.57, 220.28, 124.32, 217.14, 121.96, 223.42, 100.78, 230.48, 88.23, 233.61, 77.25, 240.67, 74.9, 250.09, 63.92, 244.6, 57.64, 244.6, 50.58, 250.09, 41.17, 256.36, 38.81, 261.85, 37.25, 272.05, 38.81, 275.97, 43.52, 278.33, 51.37, 279.11, 56.07, 284.6, 59.21, 279.11, 59.21, 273.62, 67.05, 271.27, 75.68, 272.05, 82.74, 270.48, 87.45, 271.27, 101.57, 269.7, 106.27, 279.87, 122.82, 274.84, 124.84, 280.88, 135.91, 284.91, 147.99, 292.96, 159.07, 298.0, 161.08, 287.93, 166.11, 285.91, 167.12, 279.87, 168.13, 280.88, 160.07, 275.85, 149.0, 269.81, 142.96, 265.78, 151.01, 265.78, 165.11, 260.75, 168.13, 271.39, 183.78, 285.91, 209.4, 283.9, 220.48, 279.87, 223.5, 262.76, 265.78, 262.76, 274.84, 270.81, 282.89, 274.84, 283.9, 275.85, 293.97, 251.69, 291.96], [278.28, 284.8, 286.17, 285.24, 289.23, 288.3, 284.85, 292.69, 278.72, 292.25, 277.4, 285.67]], "area": 9191.173599999995, "iscrowd": 0, "image_id": 419714, "bbox": [217.14, 37.25, 80.86, 256.72], "category_id": 1, "id": 222482, "split": "val", "sentences": [{"tokens": ["an", "officer", "riding", "a", "horse", "and", "wearing", "a", "helmet"], "raw": "An officer riding a horse and wearing a helmet.", "sent_id": 46346, "sent": "an officer riding a horse and wearing a helmet"}, {"tokens": ["a", "picture", "of", "a", "police", "officer", "sitting", "on", "a", "horse", "wearing", "a", "white", "shirt", "with", "black", "pants"], "raw": "A picture of a police officer sitting on a horse wearing a white shirt with black pants.", "sent_id": 46347, "sent": "a picture of a police officer sitting on a horse wearing a white shirt with black pants"}], "file_name": "COCO_train2014_000000419714_222482.jpg", "ann_id": 222482, "sent_ids": [46346, 46347], "ref_id": 22812}, {"segmentation": [[536.47, 67.76, 581.65, 67.76, 596.33, 62.12, 597.46, 0.0, 533.08, 1.13, 434.82, 0.0, 431.44, 116.33, 533.08, 85.84, 521.79, 81.32, 526.31, 71.15, 538.73, 65.51]], "area": 14134.631400000006, "iscrowd": 0, "image_id": 243307, "bbox": [431.44, 0.0, 166.02, 116.33], "category_id": 72, "id": 124437, "split": "val", "sentences": [{"tokens": ["the", "tv", "on", "top", "of", "the", "dresser"], "raw": "The TV on top of the dresser.", "sent_id": 46408, "sent": "the tv on top of the dresser"}, {"tokens": ["a", "silver", "boxed", "tv", "on", "a", "shelf"], "raw": "A silver boxed tv on a shelf.", "sent_id": 46409, "sent": "a silver boxed tv on a shelf"}], "file_name": "COCO_train2014_000000243307_124437.jpg", "ann_id": 124437, "sent_ids": [46408, 46409], "ref_id": 22837}, {"segmentation": [[383.0, 629.93, 7.19, 632.81, 11.51, 437.21, 355.24, 451.6, 383.0, 503.37]], "area": 68953.60224999998, "iscrowd": 0, "image_id": 339579, "bbox": [7.19, 437.21, 375.81, 195.6], "category_id": 67, "id": 1614007, "split": "val", "sentences": [{"tokens": ["a", "blue", "table", "cloth"], "raw": "A  blue table cloth.", "sent_id": 46476, "sent": "a blue table cloth"}], "file_name": "COCO_train2014_000000339579_1614007.jpg", "ann_id": 1614007, "sent_ids": [46476], "ref_id": 22864}, {"segmentation": [[90.58, 237.65, 94.89, 222.56, 93.81, 205.31, 91.65, 156.78, 87.34, 120.12, 87.34, 103.95, 93.81, 88.85, 114.3, 73.75, 142.33, 66.21, 146.65, 65.13, 138.02, 60.82, 132.63, 47.88, 120.77, 39.25, 115.38, 26.31, 125.08, 9.06, 136.94, 0.0, 233.99, 0.43, 245.85, 30.62, 248.01, 57.58, 233.99, 64.05, 230.75, 60.82, 223.2, 76.99, 216.73, 86.69, 251.24, 107.18, 255.55, 119.04, 254.47, 138.45, 242.61, 192.37, 241.54, 207.46, 250.16, 237.65, 259.87, 246.28, 254.47, 251.67, 250.16, 255.98, 250.16, 263.53, 245.85, 264.61, 222.13, 250.59, 216.73, 236.58, 186.54, 233.34, 159.59, 234.42, 129.39, 239.81, 129.39, 247.36, 118.61, 321.76, 117.53, 329.31, 103.52, 328.23, 105.67, 246.28, 93.81, 241.97]], "area": 35652.414450000004, "iscrowd": 0, "image_id": 235582, "bbox": [87.34, 0.0, 172.53, 329.31], "category_id": 1, "id": 560665, "split": "val", "sentences": [{"tokens": ["a", "lady", "wearing", "a", "purple", "shirt", "with", "a", "birthday", "cake"], "raw": "A lady wearing a purple shirt with a birthday cake", "sent_id": 46521, "sent": "a lady wearing a purple shirt with a birthday cake"}, {"tokens": ["a", "server", "wearing", "burgandy", "button", "up", "shirt"], "raw": "A server wearing burgandy button up shirt.", "sent_id": 46522, "sent": "a server wearing burgandy button up shirt"}], "file_name": "COCO_train2014_000000235582_560665.jpg", "ann_id": 560665, "sent_ids": [46521, 46522], "ref_id": 22882}, {"segmentation": [[375.14, 200.0, 370.81, 195.68, 350.27, 161.08, 344.86, 132.97, 340.54, 122.16, 339.46, 107.03, 341.62, 89.73, 347.03, 73.51, 362.16, 56.22, 390.27, 38.92, 420.54, 27.03, 447.57, 22.7, 472.43, 21.62, 513.51, 31.35, 541.62, 48.65, 555.68, 63.78, 563.24, 94.05, 561.08, 122.16, 552.43, 158.92, 535.14, 183.78, 516.76, 176.22, 469.19, 174.05, 417.3, 180.54]], "area": 30470.631999999998, "iscrowd": 0, "image_id": 29473, "bbox": [339.46, 21.62, 223.78, 178.38], "category_id": 51, "id": 717761, "split": "val", "sentences": [{"tokens": ["the", "bowl", "of", "rasberries"], "raw": "the bowl of rasberries.", "sent_id": 46525, "sent": "the bowl of rasberries"}, {"tokens": ["the", "bowl", "in", "which", "yoghurt", "and", "strawberries", "are", "kept"], "raw": "The bowl in which yoghurt and strawberries are kept", "sent_id": 46526, "sent": "the bowl in which yoghurt and strawberries are kept"}], "file_name": "COCO_train2014_000000029473_717761.jpg", "ann_id": 717761, "sent_ids": [46525, 46526], "ref_id": 22884}, {"segmentation": [[233.51, 81.44, 410.81, 114.59, 423.78, 127.57, 428.11, 156.4, 357.48, 330.81, 351.71, 325.05, 320.0, 244.32, 220.54, 196.76, 141.26, 179.46]], "area": 33376.333150000006, "iscrowd": 0, "image_id": 16836, "bbox": [141.26, 81.44, 286.85, 249.37], "category_id": 60, "id": 1572360, "split": "val", "sentences": [{"tokens": ["a", "square", "doughnut", "lying", "partially", "under", "a", "round", "doughnut"], "raw": "A square doughnut lying partially under a round doughnut.", "sent_id": 46527, "sent": "a square doughnut lying partially under a round doughnut"}, {"tokens": ["this", "is", "a", "square", "donut", "with", "nuts", "and", "glaze"], "raw": "This is a square donut with nuts and glaze.", "sent_id": 46528, "sent": "this is a square donut with nuts and glaze"}], "file_name": "COCO_train2014_000000016836_1572360.jpg", "ann_id": 1572360, "sent_ids": [46527, 46528], "ref_id": 22885}, {"segmentation": [[460.58, 417.4, 457.71, 400.13, 458.67, 376.14, 474.98, 317.61, 498.01, 312.81, 507.6, 297.46, 496.09, 237.01, 496.09, 198.63, 495.13, 147.77, 480.73, 109.39, 467.3, 96.91, 471.14, 86.36, 452.91, 64.29, 458.67, 46.06, 437.56, 23.99, 426.04, 18.23, 401.09, 25.91, 393.42, 53.73, 396.29, 77.72, 389.58, 87.32, 403.01, 134.34, 407.81, 207.26, 418.36, 279.23, 427.96, 355.99, 434.68, 384.78, 436.6, 406.85, 424.12, 417.4, 434.68, 421.24, 461.54, 421.24], [337.76, 257.16, 309.93, 241.81, 304.18, 214.94, 304.18, 199.59, 318.57, 165.04, 320.49, 157.37, 333.92, 212.06]], "area": 28967.175799999997, "iscrowd": 0, "image_id": 129361, "bbox": [304.18, 18.23, 203.42, 403.01], "category_id": 1, "id": 443707, "split": "val", "sentences": [{"tokens": ["a", "woman", "holding", "a", "snowboard"], "raw": "A woman holding a snowboard.", "sent_id": 46531, "sent": "a woman holding a snowboard"}, {"tokens": ["a", "blond", "girl", "is", "holding", "ice", "skate", "board"], "raw": "A blond girl is holding ice skate board.", "sent_id": 46532, "sent": "a blond girl is holding ice skate board"}], "file_name": "COCO_train2014_000000129361_443707.jpg", "ann_id": 443707, "sent_ids": [46531, 46532], "ref_id": 22887}, {"segmentation": [[294.97, 291.53, 340.46, 237.77, 401.11, 186.77, 421.78, 155.07, 482.43, 131.64, 537.57, 150.93, 577.54, 199.18, 581.68, 243.28, 584.43, 274.99, 589.95, 301.18, 555.49, 376.99, 441.08, 397.66, 421.78, 393.53, 412.14, 392.15, 355.62, 316.34]], "area": 50729.62154999999, "iscrowd": 0, "image_id": 392167, "bbox": [294.97, 131.64, 294.98, 266.02], "category_id": 54, "id": 1553399, "split": "val", "sentences": [{"tokens": ["a", "half", "of", "a", "sandwich", "above", "another", "one"], "raw": "A half of a sandwich above another one.", "sent_id": 46533, "sent": "a half of a sandwich above another one"}, {"tokens": ["half", "an", "egg", "salad", "sandwich", "with", "a", "blue", "toothpick", "in", "it"], "raw": "Half an egg salad sandwich with a blue toothpick in it", "sent_id": 46534, "sent": "half an egg salad sandwich with a blue toothpick in it"}], "file_name": "COCO_train2014_000000392167_1553399.jpg", "ann_id": 1553399, "sent_ids": [46533, 46534], "ref_id": 22888}, {"segmentation": [[112.46, 274.56, 80.05, 267.89, 67.66, 271.7, 53.37, 269.8, 51.46, 269.8, 46.7, 270.75, 40.98, 267.89, 40.98, 262.17, 41.93, 258.36, 40.98, 241.21, 37.17, 230.72, 36.21, 224.05, 45.74, 208.8, 54.32, 201.18, 66.71, 187.84, 76.24, 165.92, 81.01, 160.2, 92.44, 139.23, 102.93, 119.22, 108.64, 116.36, 115.32, 115.41, 123.89, 108.74, 123.89, 89.68, 123.89, 84.91, 144.86, 73.47, 164.87, 70.62, 191.56, 69.66, 202.04, 65.85, 213.48, 54.41, 225.87, 35.35, 231.58, 59.18, 243.02, 62.04, 251.6, 69.66, 255.41, 83.96, 263.03, 86.82, 268.75, 94.44, 279.23, 101.11, 279.23, 101.11, 314.5, 116.36, 322.12, 118.27, 332.6, 122.08, 345.95, 123.98, 352.62, 132.56, 352.62, 140.19, 357.38, 144.0, 357.38, 152.58, 357.38, 164.01, 390.74, 122.08, 393.6, 125.89, 393.6, 152.58, 376.44, 174.49, 366.91, 184.02, 362.15, 184.98, 374.54, 207.85, 381.21, 221.19, 370.72, 236.44, 362.15, 255.5, 354.52, 267.89, 316.4, 279.33, 107.69, 277.42]], "area": 56297.23425000001, "iscrowd": 0, "image_id": 466093, "bbox": [36.21, 35.35, 357.39, 243.98], "category_id": 9, "id": 180419, "split": "val", "sentences": [{"tokens": ["the", "large", "ship"], "raw": "the large ship", "sent_id": 46541, "sent": "the large ship"}, {"tokens": ["a", "blue", "boat"], "raw": "a blue boat", "sent_id": 46542, "sent": "a blue boat"}], "file_name": "COCO_train2014_000000466093_180419.jpg", "ann_id": 180419, "sent_ids": [46541, 46542], "ref_id": 22891}, {"segmentation": [[415.49, 154.19, 425.08, 157.07, 434.68, 164.75, 434.68, 174.34, 428.92, 186.82, 446.19, 198.33, 452.91, 198.33, 453.87, 211.77, 460.58, 234.8, 460.58, 234.8, 462.5, 237.68, 460.58, 240.55, 456.75, 237.68, 451.95, 247.27, 463.46, 281.81, 463.46, 291.41, 428.92, 303.88, 425.08, 311.56, 426.04, 321.16, 446.19, 367.21, 447.15, 372.01, 437.56, 386.41, 431.8, 388.32, 425.08, 387.37, 427.0, 381.61, 434.68, 371.05, 424.12, 348.98, 423.16, 343.23, 423.16, 358.58, 418.36, 374.89, 416.44, 382.57, 409.73, 386.41, 376.14, 377.77, 372.31, 374.89, 381.9, 371.05, 404.93, 371.05, 408.77, 362.42, 412.61, 351.86, 409.73, 332.67, 409.73, 319.24, 407.81, 311.56, 405.89, 301.97, 395.33, 296.21, 390.54, 291.41, 401.09, 267.42, 401.09, 246.31, 401.09, 246.31, 399.17, 241.51, 403.01, 237.68, 394.38, 232.88, 394.38, 223.28, 394.38, 211.77, 397.25, 195.46, 408.77, 190.66, 414.53, 188.74, 407.81, 178.18, 407.81, 173.39, 405.89, 168.59, 405.89, 158.03]], "area": 9517.562100000001, "iscrowd": 0, "image_id": 39580, "bbox": [372.31, 154.19, 91.15, 234.13], "category_id": 1, "id": 488728, "split": "val", "sentences": [{"tokens": ["woman", "wearing", "white", "dress", "with", "flowers", "standing", "near", "barricade"], "raw": "Woman wearing white dress with flowers standing near barricade", "sent_id": 46615, "sent": "woman wearing white dress with flowers standing near barricade"}], "file_name": "COCO_train2014_000000039580_488728.jpg", "ann_id": 488728, "sent_ids": [46615], "ref_id": 22919}, {"segmentation": [[173.27, 109.37, 184.76, 80.65, 197.2, 66.29, 201.03, 57.68, 201.99, 41.4, 212.52, 27.04, 223.05, 22.26, 237.41, 26.09, 246.98, 35.66, 261.34, 54.81, 246.98, 55.76, 246.98, 65.34, 239.33, 74.91, 227.84, 85.44, 238.37, 153.41, 238.37, 204.14, 225.92, 212.76, 230.71, 252.01, 230.71, 264.46, 218.27, 316.15, 220.18, 342.0, 250.81, 355.4, 251.77, 358.27, 225.92, 367.84, 211.56, 368.8, 196.25, 366.89, 194.33, 357.31, 200.08, 339.12, 197.2, 315.19, 176.14, 355.4, 176.14, 362.1, 177.1, 371.67, 186.67, 379.33, 196.25, 383.16, 199.12, 386.03, 194.33, 392.73, 171.36, 399.43, 158.91, 393.69, 131.15, 382.2, 129.24, 372.63, 141.68, 357.31, 160.83, 342.95, 183.8, 299.88, 195.29, 284.56, 197.2, 272.11, 180.93, 275.94, 175.19, 268.28, 175.19, 246.27, 168.49, 218.5, 162.74, 204.14, 160.83, 183.08, 165.61, 159.15, 171.36, 109.37]], "area": 20769.89585, "iscrowd": 0, "image_id": 212757, "bbox": [129.24, 22.26, 132.1, 377.17], "category_id": 1, "id": 563674, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "black", "shirt", "with", "one", "prosthetic", "leg", "holding", "a", "golf", "club"], "raw": "A man in a black shirt with one prosthetic leg holding a golf club.", "sent_id": 46658, "sent": "a man in a black shirt with one prosthetic leg holding a golf club"}, {"tokens": ["a", "man", "with", "one", "prosthetic", "leg", "holding", "a", "golf", "club"], "raw": "A man with one prosthetic leg holding a golf club.", "sent_id": 46659, "sent": "a man with one prosthetic leg holding a golf club"}], "file_name": "COCO_train2014_000000212757_563674.jpg", "ann_id": 563674, "sent_ids": [46658, 46659], "ref_id": 22934}, {"segmentation": [[285.64, 287.14, 237.04, 291.62, 212.36, 261.71, 221.33, 246.01, 216.85, 233.3, 234.05, 228.06, 256.48, 170.49, 287.88, 146.56, 292.37, 133.85, 290.87, 116.65, 308.82, 94.96, 307.32, 68.05, 326.77, 59.82, 355.18, 77.02, 368.64, 77.02, 382.1, 72.53, 393.32, 91.23, 396.31, 109.92, 403.78, 130.11, 400.05, 145.06, 395.56, 136.84, 384.34, 157.03, 398.55, 168.24, 418.74, 190.68, 435.19, 228.81, 432.2, 243.02, 453.14, 257.23, 461.36, 274.42, 462.11, 285.64, 436.68, 299.1, 406.77, 294.61, 390.32, 293.86], [228.81, 284.89, 185.44, 290.13, 168.99, 292.37, 139.08, 288.63, 127.86, 273.68, 123.38, 253.49, 138.33, 237.04, 149.55, 226.57, 117.4, 225.07, 112.91, 213.11, 121.88, 187.68, 130.86, 163.01, 148.8, 144.32, 159.27, 131.6, 136.84, 127.12, 142.82, 114.41, 171.23, 108.42, 169.74, 91.23, 180.95, 54.59, 172.73, 38.14, 185.44, 22.43, 204.88, 26.92, 207.87, 37.39, 225.07, 37.39, 240.77, 27.67, 252.74, 31.41, 257.97, 53.09, 269.19, 80.01, 269.94, 100.95, 263.21, 116.65, 258.72, 123.38, 270.68, 127.86, 280.41, 136.09, 287.88, 147.31]], "area": 64856.2279, "iscrowd": 0, "image_id": 264016, "bbox": [112.91, 22.43, 349.2, 276.67], "category_id": 88, "id": 1162929, "split": "val", "sentences": [{"tokens": ["3", "teddy", "bears", "sitting", "on", "a", "bed"], "raw": "3 teddy bears sitting on a bed.", "sent_id": 46710, "sent": "3 teddy bears sitting on a bed"}, {"tokens": ["group", "of", "three", "teddy", "bears", "sitting"], "raw": "group of three teddy bears sitting", "sent_id": 46711, "sent": "group of three teddy bears sitting"}], "file_name": "COCO_train2014_000000264016_1162929.jpg", "ann_id": 1162929, "sent_ids": [46710, 46711], "ref_id": 22949}, {"segmentation": [[214.08, 138.37, 277.24, 20.25, 295.28, 0.57, 177.99, 0.0, 99.25, 0.0, 9.84, 1.39, 8.2, 1.39, 0.0, 2.21, 1.64, 27.64, 1.64, 181.02, 8.2, 146.57, 12.3, 100.64, 25.43, 85.87, 45.11, 71.93, 92.69, 68.65, 113.19, 93.25, 139.44, 144.11, 139.44, 168.72, 186.19, 154.77, 191.93, 145.75]], "area": 29157.27500000001, "iscrowd": 0, "image_id": 37160, "bbox": [0.0, 0.0, 295.28, 181.02], "category_id": 28, "id": 1424551, "split": "val", "sentences": [{"tokens": ["rainbow", "colored", "umbrella", "over", "a", "gent"], "raw": "rainbow colored umbrella over a gent", "sent_id": 46715, "sent": "rainbow colored umbrella over a gent"}, {"tokens": ["a", "striped", "umbrella", "above", "a", "man", "'", "s", "head"], "raw": "A striped umbrella above a man's head.", "sent_id": 46716, "sent": "a striped umbrella above a man ' s head"}], "file_name": "COCO_train2014_000000037160_1424551.jpg", "ann_id": 1424551, "sent_ids": [46715, 46716], "ref_id": 22952}, {"segmentation": [[465.19, 191.13, 472.33, 187.36, 483.24, 202.46, 484.91, 228.48, 479.04, 256.17, 468.13, 257.43, 429.11, 249.87, 415.68, 241.9, 406.87, 227.64, 397.64, 226.8, 402.26, 245.26, 370.37, 224.7, 358.2, 216.31, 345.19, 213.37, 341.0, 214.63, 344.35, 228.48, 344.77, 243.16, 339.32, 255.75, 328.83, 262.04, 319.18, 264.98, 307.43, 258.69, 302.39, 255.33, 288.55, 257.43, 283.09, 257.01, 281.83, 252.81, 300.29, 251.13, 321.69, 259.11, 327.99, 254.91, 335.12, 238.97, 338.06, 223.44, 339.74, 208.34, 349.39, 202.46, 358.2, 200.36, 368.69, 203.72, 380.86, 203.72, 389.67, 201.2, 409.39, 197.43, 435.4, 200.36, 450.09, 200.78, 453.86, 197.85, 463.93, 197.43, 464.35, 192.39]], "area": 6246.11795, "iscrowd": 0, "image_id": 132889, "bbox": [281.83, 187.36, 203.08, 77.62], "category_id": 59, "id": 1076954, "split": "val", "sentences": [{"tokens": ["slice", "of", "pizza", "on", "plate", "with", "cheese", "stringing", "from", "pan"], "raw": "slice of pizza on plate with cheese stringing from pan", "sent_id": 46822, "sent": "slice of pizza on plate with cheese stringing from pan"}, {"tokens": ["pizza", "to", "the", "right", "in", "plate"], "raw": "pizza to the right in plate", "sent_id": 46823, "sent": "pizza to the right in plate"}], "file_name": "COCO_train2014_000000132889_1076954.jpg", "ann_id": 1076954, "sent_ids": [46822, 46823], "ref_id": 22989}, {"segmentation": [[310.86, 68.6, 315.66, 83.95, 320.46, 101.22, 328.14, 185.66, 327.18, 211.56, 323.34, 236.51, 331.01, 276.8, 337.73, 311.34, 334.85, 338.21, 329.09, 368.91, 340.61, 357.4, 346.36, 323.82, 360.76, 360.28, 376.11, 367.95, 380.91, 360.28, 381.86, 347.8, 393.38, 306.55, 399.14, 300.79, 405.85, 323.82, 406.81, 359.32, 412.57, 353.56, 412.57, 314.22, 407.77, 284.48, 416.41, 252.82, 417.36, 222.11, 394.34, 199.09, 371.31, 196.21, 354.04, 172.22, 347.32, 158.79, 334.85, 92.59, 332.93, 71.48, 331.97, 54.21, 327.18, 45.57, 318.54, 44.61, 312.78, 53.25, 302.23, 53.25, 300.31, 55.17]], "area": 15277.421000000004, "iscrowd": 0, "image_id": 526713, "bbox": [300.31, 44.61, 117.05, 324.3], "category_id": 25, "id": 596604, "split": "val", "sentences": [{"tokens": ["giraffe", "looking", "at", "camera"], "raw": "giraffe looking at camera", "sent_id": 46828, "sent": "giraffe looking at camera"}, {"tokens": ["a", "giraffe", "standing", "to", "the", "standing", "to", "the", "right", "of", "2", "other", "giraffes"], "raw": "A giraffe standing to the standing to the right of 2 other giraffes.", "sent_id": 46829, "sent": "a giraffe standing to the standing to the right of 2 other giraffes"}], "file_name": "COCO_train2014_000000526713_596604.jpg", "ann_id": 596604, "sent_ids": [46828, 46829], "ref_id": 22992}, {"segmentation": [[174.93, 218.41, 158.92, 218.41, 151.55, 219.43, 138.33, 218.66, 133.5, 217.14, 133.76, 212.56, 131.22, 211.55, 128.17, 213.83, 128.42, 222.22, 128.17, 228.07, 126.13, 246.62, 124.1, 261.87, 123.34, 266.19, 121.81, 280.42, 121.05, 297.95, 119.78, 309.39, 119.02, 317.27, 115.97, 351.83, 118.25, 353.61, 122.07, 352.34, 128.67, 287.53, 136.04, 287.79, 149.51, 290.58, 155.61, 293.89, 155.1, 320.57, 154.34, 337.6, 153.83, 358.69, 154.09, 367.59, 152.82, 382.33, 156.88, 383.09, 159.17, 381.82, 160.44, 370.64, 161.46, 345.22, 162.73, 325.15, 163.24, 310.66, 164.51, 297.7, 176.2, 295.67, 193.43, 292.5, 194.91, 335.51, 199.85, 334.02, 197.38, 290.52, 214.19, 288.05, 216.17, 268.27, 206.28, 262.83, 192.44, 258.88, 180.57, 260.86, 164.75, 268.27, 165.74, 227.73, 175.63, 226.25, 175.63, 219.33]], "area": 5794.712099999999, "iscrowd": 0, "image_id": 257102, "bbox": [115.97, 211.55, 100.2, 171.54], "category_id": 62, "id": 375848, "split": "val", "sentences": [{"tokens": ["chair", "pushed", "up", "to", "table", "with", "nothing", "in", "front", "of", "it"], "raw": "chair pushed up to table with nothing in front of it", "sent_id": 46834, "sent": "chair pushed up to table with nothing in front of it"}, {"tokens": ["wooden", "chair", "with", "nothing", "in", "front", "of", "it"], "raw": "Wooden chair with nothing in front of it", "sent_id": 46835, "sent": "wooden chair with nothing in front of it"}], "file_name": "COCO_train2014_000000257102_375848.jpg", "ann_id": 375848, "sent_ids": [46834, 46835], "ref_id": 22994}, {"segmentation": [[7.23, 343.74, 202.32, 353.03, 302.45, 360.26, 317.94, 422.19, 318.97, 471.74, 0.0, 471.74, 3.1, 346.84, 7.23, 346.84], [355.1, 466.58, 398.45, 416.0, 430.45, 420.13, 434.58, 424.26, 433.55, 472.77, 356.13, 473.81]], "area": 40908.63315000001, "iscrowd": 0, "image_id": 130163, "bbox": [0.0, 343.74, 434.58, 130.07], "category_id": 63, "id": 112620, "split": "val", "sentences": [{"tokens": ["brown", "leather", "chair", "with", "a", "coffee", "table", "in", "front", "of", "it"], "raw": "Brown leather chair with a coffee table in front of it", "sent_id": 46982, "sent": "brown leather chair with a coffee table in front of it"}, {"tokens": ["a", "light", "brown", "leather", "couch"], "raw": "A light brown leather couch.", "sent_id": 46983, "sent": "a light brown leather couch"}], "file_name": "COCO_train2014_000000130163_112620.jpg", "ann_id": 112620, "sent_ids": [46982, 46983], "ref_id": 23050}, {"segmentation": [[514.14, 1.55, 496.55, 20.17, 488.28, 38.79, 486.21, 46.03, 485.17, 52.24, 486.21, 66.72, 486.21, 76.03, 486.21, 88.45, 484.14, 98.79, 482.07, 109.14, 482.07, 120.52, 483.1, 129.83, 485.17, 140.17, 487.24, 145.34, 492.41, 165.0, 496.55, 172.24, 502.76, 177.41, 508.97, 179.48, 514.14, 185.69, 520.34, 190.86, 521.38, 199.14, 524.48, 205.34, 526.55, 209.48, 527.59, 214.66, 534.83, 217.76, 537.93, 219.83, 561.72, 214.66, 570.0, 211.55, 568.97, 220.86, 532.76, 229.14, 521.38, 230.17, 495.52, 249.83, 485.17, 261.21, 477.93, 267.41, 467.59, 285.0, 465.52, 298.45, 458.28, 328.45, 457.24, 337.76, 429.31, 419.48, 422.07, 415.34, 382.76, 383.28, 356.9, 339.83, 349.66, 323.28, 344.48, 307.76, 337.24, 294.31, 324.83, 264.31, 319.66, 253.97, 311.38, 255.0, 306.21, 267.41, 309.31, 278.79, 311.38, 282.93, 307.24, 285.0, 261.72, 268.45, 249.31, 259.14, 237.93, 259.14, 234.83, 261.21, 240.0, 268.45, 246.21, 274.66, 257.59, 283.97, 261.72, 287.07, 262.76, 299.48, 263.79, 310.86, 263.79, 319.14, 273.1, 326.38, 281.38, 331.55, 296.9, 335.69, 307.24, 338.79, 317.59, 352.24, 355.86, 411.21, 407.59, 474.31, 483.1, 473.28, 492.41, 453.62, 495.52, 462.93, 497.59, 470.17, 499.66, 475.34, 640.0, 473.28, 640.0, 2.59]], "area": 89205.47605, "iscrowd": 0, "image_id": 524476, "bbox": [234.83, 1.55, 405.17, 473.79], "category_id": 1, "id": 189646, "split": "val", "sentences": [{"tokens": ["the", "woman", "on", "the", "right", "holding", "the", "blow", "dryer"], "raw": "the woman on the right holding the blow dryer", "sent_id": 46999, "sent": "the woman on the right holding the blow dryer"}, {"tokens": ["a", "woman", "holding", "a", "blow", "dryer"], "raw": "A woman holding a blow dryer.", "sent_id": 47000, "sent": "a woman holding a blow dryer"}], "file_name": "COCO_train2014_000000524476_189646.jpg", "ann_id": 189646, "sent_ids": [46999, 47000], "ref_id": 23058}, {"segmentation": [[58.9, 152.31, 99.81, 226.33, 167.02, 220.49, 169.94, 237.05, 112.47, 248.73, 117.34, 257.5, 171.89, 245.81, 219.62, 262.37, 242.99, 321.79, 212.8, 373.41, 20.92, 365.62, 9.23, 183.47, 7.28, 154.25, 17.02, 143.54, 47.21, 143.54]], "area": 34038.674100000004, "iscrowd": 0, "image_id": 286690, "bbox": [7.28, 143.54, 235.71, 229.87], "category_id": 62, "id": 1938042, "split": "val", "sentences": [{"tokens": ["a", "black", "office", "chair", "with", "a", "coat", "hanging", "on", "it"], "raw": "A black office chair with a coat hanging on it", "sent_id": 47005, "sent": "a black office chair with a coat hanging on it"}, {"tokens": ["computer", "chair"], "raw": "computer chair", "sent_id": 47006, "sent": "computer chair"}], "file_name": "COCO_train2014_000000286690_1938042.jpg", "ann_id": 1938042, "sent_ids": [47005, 47006], "ref_id": 23061}, {"segmentation": [[383.46, 137.28, 373.5, 137.71, 378.27, 145.51, 378.27, 154.17, 376.53, 169.77, 373.07, 180.6, 365.7, 199.23, 366.57, 204.42, 415.09, 208.32, 423.32, 208.76, 425.92, 194.03, 425.05, 184.93, 418.12, 176.27, 407.72, 171.93, 390.83, 169.33, 389.53, 166.3, 386.5, 154.61, 383.46, 145.08, 383.9, 140.74], [340.58, 113.45, 333.21, 116.05, 325.42, 122.12, 319.35, 135.55, 319.78, 140.74, 328.02, 135.11, 328.45, 129.91, 336.25, 122.98, 344.48, 119.52]], "area": 2407.1647, "iscrowd": 0, "image_id": 523484, "bbox": [319.35, 113.45, 106.57, 95.31], "category_id": 62, "id": 1598202, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "nearly", "hidden", "by", "a", "young", "man", "in", "a", "light", "colored", "shirt"], "raw": "A wooden chair nearly hidden by a young man in a light colored shirt.", "sent_id": 47011, "sent": "a wooden chair nearly hidden by a young man in a light colored shirt"}, {"tokens": ["a", "dark", "brown", "wooden", "chair", "sits", "in", "the", "background", "to", "the", "man", "'", "s", "left"], "raw": "A dark brown wooden chair sits in the background to the man's left.", "sent_id": 47012, "sent": "a dark brown wooden chair sits in the background to the man ' s left"}], "file_name": "COCO_train2014_000000523484_1598202.jpg", "ann_id": 1598202, "sent_ids": [47011, 47012], "ref_id": 23063}, {"segmentation": [[18.74, 206.17, 18.74, 219.66, 21.73, 233.9, 28.48, 236.9, 35.97, 237.65, 46.47, 246.64, 65.95, 248.89, 78.69, 248.89, 87.68, 267.62, 106.42, 260.88, 110.92, 215.91, 245.82, 196.43, 247.32, 188.93, 250.31, 185.18, 254.81, 152.96, 235.32, 149.96, 170.12, 152.96, 169.37, 167.2, 160.38, 167.2, 158.88, 172.44, 47.21, 187.43, 32.98, 191.93, 23.98, 197.18, 18.74, 200.92]], "area": 12060.4824, "iscrowd": 0, "image_id": 53232, "bbox": [18.74, 149.96, 236.07, 117.66], "category_id": 65, "id": 316607, "split": "val", "sentences": [{"tokens": ["the", "bed", "closest", "to", "window"], "raw": "The bed closest to window.", "sent_id": 47034, "sent": "the bed closest to window"}, {"tokens": ["a", "bed", "with", "a", "brown", "cylindrical", "pillow", "near", "the", "window"], "raw": "A bed with a brown cylindrical pillow near the window", "sent_id": 47035, "sent": "a bed with a brown cylindrical pillow near the window"}], "file_name": "COCO_train2014_000000053232_316607.jpg", "ann_id": 316607, "sent_ids": [47034, 47035], "ref_id": 23071}, {"segmentation": [[481.57, 26.49, 511.25, 18.83, 548.59, 19.79, 581.14, 26.49, 606.99, 38.93, 626.14, 50.42, 628.05, 60.0, 640.0, 56.17, 640.0, 83.93, 621.35, 91.59, 606.03, 121.27, 596.46, 134.67, 594.54, 149.99, 619.44, 146.16, 637.63, 139.46, 639.54, 171.06, 606.99, 172.01, 593.59, 175.84, 586.89, 181.59, 580.18, 194.99, 577.31, 208.39, 572.52, 217.01, 539.02, 231.37, 467.21, 214.14, 446.15, 198.82, 438.49, 179.67, 443.28, 169.14, 443.28, 146.16, 478.7, 61.91, 470.08, 40.85, 480.61, 25.53]], "area": 30361.573949999998, "iscrowd": 0, "image_id": 239596, "bbox": [438.49, 18.83, 201.51, 212.54], "category_id": 47, "id": 1505334, "split": "val", "sentences": [{"tokens": ["blue", "mug", "in", "the", "right", "hand", "picture"], "raw": "blue mug in the right hand picture", "sent_id": 47057, "sent": "blue mug in the right hand picture"}, {"tokens": ["a", "blue", "coffed", "mug", "with", "old", "taos", "guesthouse", "on", "it"], "raw": "A blue coffed mug with Old Taos Guesthouse on it.", "sent_id": 47058, "sent": "a blue coffed mug with old taos guesthouse on it"}], "file_name": "COCO_train2014_000000239596_1505334.jpg", "ann_id": 1505334, "sent_ids": [47057, 47058], "ref_id": 23078}, {"segmentation": [[108.43, 140.74, 115.49, 140.38, 124.31, 139.32, 123.25, 143.91, 125.37, 148.85, 134.9, 161.56, 147.25, 174.96, 161.36, 190.49, 163.48, 194.02, 155.01, 198.96, 138.08, 185.2, 124.31, 164.38, 116.9, 151.67, 110.55, 152.73], [200.18, 207.78, 211.47, 221.9, 208.65, 239.54, 206.18, 250.48, 204.77, 285.41, 199.83, 285.76, 195.59, 268.12, 190.3, 250.12, 180.42, 254.01, 171.95, 259.3, 183.6, 244.13]], "area": 1991.8477999999996, "iscrowd": 0, "image_id": 334080, "bbox": [108.43, 139.32, 103.04, 146.44], "category_id": 25, "id": 1414153, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "that", "is", "standing", "behind", "the", "dried", "tree"], "raw": "A giraffe that is standing behind the dried tree", "sent_id": 47087, "sent": "a giraffe that is standing behind the dried tree"}, {"tokens": ["the", "giraffe", "on", "the", "far", "left", "hidden", "behind", "the", "trees"], "raw": "the giraffe on the far left hidden behind the trees", "sent_id": 47088, "sent": "the giraffe on the far left hidden behind the trees"}], "file_name": "COCO_train2014_000000334080_1414153.jpg", "ann_id": 1414153, "sent_ids": [47087, 47088], "ref_id": 23088}, {"segmentation": [[640.0, 201.99, 616.04, 184.08, 621.74, 171.87, 625.81, 164.55, 625.81, 158.04, 622.55, 149.08, 612.79, 129.55, 608.72, 119.79, 598.14, 109.21, 583.49, 107.58, 577.79, 105.96, 560.7, 105.96, 541.18, 112.46, 538.73, 117.35, 526.52, 131.18, 520.01, 157.23, 521.64, 171.87, 525.71, 189.78, 541.18, 208.5, 543.61, 216.64, 545.24, 223.96, 544.43, 224.77, 529.78, 233.73, 511.06, 254.89, 480.13, 264.65, 466.3, 269.53, 431.3, 278.49, 413.39, 281.74, 408.52, 284.19, 391.42, 292.32, 393.86, 307.79, 406.88, 311.86, 410.14, 311.86, 429.67, 308.6, 454.9, 302.09, 465.48, 302.09, 473.62, 302.09, 491.53, 297.21, 501.29, 295.58, 521.64, 286.62, 528.15, 284.19, 537.1, 282.56, 540.35, 287.44, 543.61, 298.02, 547.68, 303.71, 574.54, 315.11, 634.76, 310.23]], "area": 24186.801799999994, "iscrowd": 0, "image_id": 177019, "bbox": [391.42, 105.96, 248.58, 209.15], "category_id": 1, "id": 2162283, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "a", "black", "helmet", "flashing", "a", "peace", "sign"], "raw": "A man in a white shirt and a black helmet flashing a peace sign", "sent_id": 47140, "sent": "a man in a white shirt and a black helmet flashing a peace sign"}, {"tokens": ["the", "man", "with", "the", "black", "helmet", "on", "the", "right"], "raw": "the man with the black helmet on the right", "sent_id": 47141, "sent": "the man with the black helmet on the right"}], "file_name": "COCO_train2014_000000177019_2162283.jpg", "ann_id": 2162283, "sent_ids": [47140, 47141], "ref_id": 23109}, {"segmentation": [[531.36, 3.45, 632.84, 1.53, 637.63, 1.53, 639.54, 62.81, 638.59, 198.76, 639.54, 202.59, 623.27, 219.82, 639.54, 228.44, 640.0, 235.14, 634.76, 254.29, 613.69, 236.09, 585.93, 214.07, 574.44, 200.67, 604.12, 148.97, 634.76, 100.14, 609.86, 32.17, 599.33, 30.25, 592.63, 59.93, 599.33, 78.12, 560.08, 131.74, 553.38, 143.23, 550.5, 148.97, 551.46, 168.12, 553.38, 178.65, 533.27, 176.74, 515.08, 159.5, 511.25, 134.61, 508.38, 114.5, 535.19, 57.06]], "area": 17528.783449999995, "iscrowd": 0, "image_id": 88671, "bbox": [508.38, 1.53, 131.62, 252.76], "category_id": 1, "id": 225942, "split": "val", "sentences": [{"tokens": ["the", "jeans", "with", "the", "hole", "in", "the", "knee"], "raw": "The jeans with the hole in the knee.", "sent_id": 47148, "sent": "the jeans with the hole in the knee"}, {"tokens": ["a", "man", "with", "bare", "feet", "and", "blue", "jeans"], "raw": "A man with bare feet and blue jeans.", "sent_id": 47149, "sent": "a man with bare feet and blue jeans"}], "file_name": "COCO_train2014_000000088671_225942.jpg", "ann_id": 225942, "sent_ids": [47148, 47149], "ref_id": 23112}, {"segmentation": [[446.79, 146.79, 435.83, 153.05, 433.49, 155.2, 425.47, 180.82, 425.47, 186.49, 399.46, 187.08, 385.37, 189.43, 378.53, 193.73, 376.39, 200.93, 380.17, 207.05, 382.51, 207.05, 389.71, 211.9, 380.17, 208.49, 375.49, 208.85, 366.5, 211.72, 360.02, 218.02, 357.14, 223.42, 358.94, 230.8, 360.74, 238.54, 364.34, 240.16, 362.36, 266.25, 427.68, 296.85, 460.62, 310.35, 492.65, 327.08, 498.23, 329.96, 507.41, 325.64, 516.23, 323.12, 529.73, 322.94, 543.04, 329.24, 550.42, 334.46, 564.1, 329.78, 597.03, 316.83, 607.29, 309.63, 609.81, 294.87, 615.39, 281.55, 617.01, 270.75, 624.03, 250.96, 625.65, 246.46, 634.11, 215.5, 635.19, 209.75, 638.61, 194.27, 637.89, 188.87, 632.13, 188.51, 622.05, 179.33, 608.01, 178.25, 597.39, 173.93, 550.96, 160.97, 538.9, 162.41, 535.3, 167.99, 518.03, 163.85, 513.35, 155.22, 479.87, 150.36, 473.22, 148.92], [538.43, 336.93, 532.26, 333.28, 528.34, 331.88, 516.98, 332.3, 508.28, 333.84, 507.16, 334.96, 525.81, 342.4]], "area": 37021.372350000005, "iscrowd": 0, "image_id": 55226, "bbox": [357.14, 146.79, 281.47, 195.61], "category_id": 63, "id": 116666, "split": "val", "sentences": [{"tokens": ["the", "beige", "and", "brown", "duel", "recliner"], "raw": "The beige and brown duel recliner.", "sent_id": 47188, "sent": "the beige and brown duel recliner"}, {"tokens": ["a", "love", "seat", "with", "light", "brown", "seats", "and", "dark", "brown", "sides"], "raw": "A love seat with light brown seats and dark brown sides", "sent_id": 47189, "sent": "a love seat with light brown seats and dark brown sides"}], "file_name": "COCO_train2014_000000055226_116666.jpg", "ann_id": 116666, "sent_ids": [47188, 47189], "ref_id": 23129}, {"segmentation": [[499.64, 104.13, 485.74, 98.02, 465.72, 92.46, 403.45, 106.36, 363.42, 138.05, 351.75, 160.29, 337.85, 194.2, 333.4, 223.67, 358.42, 267.03, 372.87, 298.17, 402.9, 309.84, 462.39, 329.3, 497.41, 322.07]], "area": 30715.363849999998, "iscrowd": 0, "image_id": 313209, "bbox": [333.4, 92.46, 166.24, 236.84], "category_id": 51, "id": 1040349, "split": "val", "sentences": [{"tokens": ["the", "bowl", "of", "carrots"], "raw": "The bowl of carrots.", "sent_id": 47196, "sent": "the bowl of carrots"}, {"tokens": ["a", "small", "bowl", "full", "of", "seasoned", "carrots", "located", "on", "the", "right", "side"], "raw": "A small bowl full of seasoned carrots located on the right side.", "sent_id": 47197, "sent": "a small bowl full of seasoned carrots located on the right side"}], "file_name": "COCO_train2014_000000313209_1040349.jpg", "ann_id": 1040349, "sent_ids": [47196, 47197], "ref_id": 23132}, {"segmentation": [[45.0, 351.01, 52.34, 328.97, 63.36, 308.77, 75.3, 302.34, 89.99, 288.57, 94.58, 282.14, 107.44, 280.3, 112.95, 279.39, 126.72, 294.08, 121.21, 313.36, 118.46, 317.95, 122.13, 337.24, 133.15, 364.79, 145.09, 373.97, 154.27, 378.56, 167.13, 395.09, 165.29, 410.7, 168.05, 420.8, 128.56, 421.72, 129.48, 414.37, 126.72, 407.95, 122.13, 401.52, 118.46, 382.23, 103.77, 371.21, 96.42, 371.21, 84.48, 374.89, 67.95, 375.81]], "area": 7754.3715, "iscrowd": 0, "image_id": 545948, "bbox": [45.0, 279.39, 123.05, 142.33], "category_id": 1, "id": 189032, "split": "val", "sentences": [{"tokens": ["a", "person", "sitting", "in", "a", "chair"], "raw": "A person sitting in a chair.", "sent_id": 47265, "sent": "a person sitting in a chair"}, {"tokens": ["a", "woman", "sitting", "in", "a", "white", "plastic", "chair"], "raw": "A woman sitting in a white plastic chair.", "sent_id": 47266, "sent": "a woman sitting in a white plastic chair"}], "file_name": "COCO_train2014_000000545948_189032.jpg", "ann_id": 189032, "sent_ids": [47265, 47266], "ref_id": 23157}, {"segmentation": [[169.71, 122.25, 234.43, 140.94, 234.43, 125.12, 264.63, 122.25, 307.78, 419.96, 198.47, 465.98, 195.6, 421.39, 129.44, 358.11, 145.26, 310.65, 129.44, 264.63, 155.33, 212.85, 132.31, 191.28, 148.13, 129.44]], "area": 44008.49109999999, "iscrowd": 0, "image_id": 521726, "bbox": [129.44, 122.25, 178.34, 343.73], "category_id": 10, "id": 405532, "split": "val", "sentences": [{"tokens": ["the", "traffic", "signal", "has", "3", "colours", "of", "light"], "raw": "The traffic signal has 3 colours of light", "sent_id": 47315, "sent": "the traffic signal has 3 colours of light"}, {"tokens": ["a", "signal", "post", ",", "green", "signal", "is", "glowing"], "raw": "A signal post, green signal is glowing", "sent_id": 47316, "sent": "a signal post , green signal is glowing"}], "file_name": "COCO_train2014_000000521726_405532.jpg", "ann_id": 405532, "sent_ids": [47315, 47316], "ref_id": 23178}, {"segmentation": [[385.47, 261.08, 427.0, 256.72, 424.11, 430.59, 411.64, 425.61, 392.32, 425.61, 386.71, 372.63, 381.1, 363.91, 371.76, 395.07, 362.41, 393.2, 373.0, 360.79, 374.25, 348.33, 368.02, 343.34, 330.62, 307.82, 326.88, 296.6, 328.75, 284.76, 334.99, 271.67, 349.32, 257.34, 366.15, 256.09, 376.74, 256.72]], "area": 10996.798050000001, "iscrowd": 0, "image_id": 127214, "bbox": [326.88, 256.09, 100.12, 174.5], "category_id": 22, "id": 585493, "split": "val", "sentences": [{"tokens": ["elephant", "in", "rear", "of", "procession"], "raw": "Elephant in rear of procession.", "sent_id": 47319, "sent": "elephant in rear of procession"}, {"tokens": ["an", "african", "elephant", "walking", "behind", "the", "group", "of", "elephants"], "raw": "An African elephant walking behind the group of elephants", "sent_id": 47320, "sent": "an african elephant walking behind the group of elephants"}], "file_name": "COCO_train2014_000000127214_585493.jpg", "ann_id": 585493, "sent_ids": [47319, 47320], "ref_id": 23180}, {"segmentation": [[508.76, 151.2, 508.76, 159.62, 506.23, 164.66, 499.5, 167.19, 471.75, 192.0, 460.39, 222.7, 461.65, 228.59, 455.76, 260.13, 454.08, 268.54, 465.02, 285.79, 464.18, 297.56, 482.26, 308.85, 490.25, 321.05, 481.0, 327.36, 497.4, 339.97, 516.33, 358.48, 522.64, 370.68, 514.64, 381.19, 514.64, 392.97, 519.69, 414.42, 515.49, 418.2, 515.91, 427.45, 565.53, 428.71, 568.48, 413.99, 568.9, 410.21, 569.32, 372.36, 578.99, 380.77, 588.24, 379.93, 581.52, 396.75, 578.15, 411.89, 571.42, 428.71, 621.89, 427.03, 618.1, 413.15, 624.41, 411.47, 634.93, 363.95, 634.09, 359.32, 599.18, 321.47, 586.56, 302.54, 584.04, 274.79, 582.36, 266.37, 573.94, 198.66, 568.06, 189.83, 554.18, 181.42, 549.55, 178.48, 542.82, 173.01, 543.66, 167.12, 556.7, 154.5, 556.7, 154.08, 559.65, 146.93, 559.22, 130.95, 560.91, 110.76, 554.6, 95.2, 536.51, 83.85, 515.91, 85.53, 502.03, 93.52, 492.35, 108.66, 489.41, 128.85, 499.08, 148.19, 507.49, 151.14]], "area": 33063.977699999996, "iscrowd": 0, "image_id": 226817, "bbox": [454.08, 83.85, 180.85, 344.86], "category_id": 1, "id": 205281, "split": "val", "sentences": [{"tokens": ["an", "asian", "boy", "in", "a", "green", "long", "sleeved", "shirt", "playing", "wii"], "raw": "an asian boy in a green long sleeved shirt playing wii", "sent_id": 47474, "sent": "an asian boy in a green long sleeved shirt playing wii"}, {"tokens": ["oriental", "boy", "in", "green", "shirt"], "raw": "oriental boy in green shirt", "sent_id": 47475, "sent": "oriental boy in green shirt"}], "file_name": "COCO_train2014_000000226817_205281.jpg", "ann_id": 205281, "sent_ids": [47474, 47475], "ref_id": 23237}, {"segmentation": [[162.24, 153.91, 158.31, 134.27, 157.6, 128.91, 157.96, 124.63, 160.46, 121.06, 162.96, 119.63, 165.46, 118.2, 230.81, 111.41, 236.16, 112.84, 239.38, 116.06, 241.52, 119.99, 246.52, 144.27, 239.02, 143.55, 231.88, 143.2, 224.02, 142.84, 217.59, 142.84, 213.31, 142.84, 210.45, 141.41, 208.67, 140.7, 197.24, 140.7, 194.02, 139.98, 191.52, 139.27, 189.74, 139.27, 184.38, 141.41, 181.53, 143.55, 180.1, 146.41, 179.03, 148.2, 175.81, 149.27, 171.88, 149.63, 167.6, 151.41, 165.1, 152.13], [262.59, 162.48, 280.8, 167.84, 282.94, 170.69, 284.73, 173.55, 285.09, 180.34, 284.37, 196.05, 291.16, 198.91, 293.3, 201.76, 294.37, 209.98, 191.88, 229.97, 187.6, 228.9, 172.96, 221.05, 173.67, 235.33, 170.1, 236.05, 166.53, 202.48, 169.38, 199.62, 170.1, 196.76, 170.1, 194.26, 171.88, 191.76, 173.67, 189.26, 173.31, 185.69, 169.74, 183.91, 165.81, 182.12, 164.38, 178.55, 164.74, 176.77, 166.53, 176.05, 168.67, 178.55, 171.88, 181.41, 176.17, 181.05, 181.88, 180.34, 190.81, 177.12, 192.6, 179.98, 195.81, 184.98, 198.67, 190.69, 200.45, 196.41, 202.6, 199.98, 207.24, 200.33, 214.74, 201.05, 222.95, 201.76, 230.81, 201.05, 239.02, 199.98, 244.73, 200.33, 249.38, 198.91, 254.38, 196.05, 259.73, 193.91, 264.37, 193.91, 264.73, 188.55, 262.23, 180.34, 259.38, 172.48, 258.66, 167.84, 258.66, 165.34, 260.8, 164.27, 262.95, 164.27]], "area": 6535.1932, "iscrowd": 0, "image_id": 376505, "bbox": [157.6, 111.41, 136.77, 124.64], "category_id": 62, "id": 2121477, "split": "val", "sentences": [{"tokens": ["the", "armchair", "with", "a", "bag", "in", "it"], "raw": "The armchair with a bag in it.", "sent_id": 47500, "sent": "the armchair with a bag in it"}], "file_name": "COCO_train2014_000000376505_2121477.jpg", "ann_id": 2121477, "sent_ids": [47500], "ref_id": 23250}, {"segmentation": [[288.97, 86.91, 299.46, 77.22, 313.18, 70.76, 305.11, 53.0, 304.3, 38.48, 308.34, 26.37, 313.99, 21.52, 323.68, 19.1, 341.43, 26.37, 348.7, 40.09, 343.05, 60.27, 344.66, 63.5, 351.93, 68.34, 358.39, 74.8, 371.3, 82.87, 378.57, 105.47, 388.25, 124.84, 389.87, 128.88, 377.76, 136.95, 385.83, 178.92, 390.67, 200.72, 397.94, 223.32, 395.52, 233.81, 393.9, 238.65, 400.36, 284.66, 397.94, 316.14, 418.92, 342.78, 418.92, 349.24, 406.01, 351.66, 397.13, 345.2, 389.87, 341.17, 383.41, 341.97, 384.22, 304.84, 375.34, 286.28, 363.23, 272.56, 355.96, 260.45, 354.35, 251.57, 353.54, 247.53, 340.63, 247.53, 343.05, 267.71, 340.63, 283.86, 337.4, 304.84, 335.78, 320.99, 341.43, 329.06, 340.63, 341.17, 336.59, 354.08, 322.87, 355.7, 316.41, 352.47, 320.45, 329.06, 317.22, 310.49, 313.18, 292.74, 315.61, 279.01, 317.22, 269.33, 312.38, 247.53, 303.5, 248.34, 293.81, 165.2, 293.0, 117.58, 288.16, 90.94, 289.78, 82.06], [209.06, 93.36, 213.9, 83.68, 224.39, 78.83, 232.47, 81.26, 233.27, 85.29, 226.82, 90.94, 216.32, 94.17, 212.29, 93.36]], "area": 22979.283399999993, "iscrowd": 0, "image_id": 259443, "bbox": [209.06, 19.1, 209.86, 336.6], "category_id": 1, "id": 1719959, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "blue", "shirt"], "raw": "a man with blue shirt", "sent_id": 47549, "sent": "a man with blue shirt"}, {"tokens": ["a", "man", "with", "in", "blue", "shirt", "with", "tennis", "racket", "on", "his", "hand"], "raw": "A man with in blue shirt with tennis racket on his hand.", "sent_id": 47550, "sent": "a man with in blue shirt with tennis racket on his hand"}], "file_name": "COCO_train2014_000000259443_1719959.jpg", "ann_id": 1719959, "sent_ids": [47549, 47550], "ref_id": 23271}, {"segmentation": [[210.48, 147.65, 220.1, 142.24, 227.62, 124.8, 235.73, 121.19, 250.17, 119.99, 261.29, 122.69, 264.6, 136.22, 270.61, 142.54, 278.43, 147.95, 279.63, 147.95, 280.83, 144.34, 292.56, 144.04, 295.26, 149.45, 287.45, 159.37, 279.63, 170.2, 272.41, 171.7, 266.1, 181.92, 267.0, 193.65, 273.92, 198.76, 280.23, 211.99, 277.83, 224.01, 265.5, 237.54, 256.18, 245.36, 246.86, 248.37, 238.44, 256.79, 229.72, 248.37, 224.31, 235.74, 208.68, 224.92, 204.77, 216.2, 204.17, 205.98, 211.08, 197.26, 217.09, 191.84, 219.2, 186.73, 214.69, 181.32, 197.25, 169.0, 200.56, 155.47]], "area": 7722.849300000001, "iscrowd": 0, "image_id": 74217, "bbox": [197.25, 119.99, 98.01, 136.8], "category_id": 4, "id": 1362052, "split": "val", "sentences": [{"tokens": ["police", "biker", "4th", "from", "left"], "raw": "police biker 4th from left", "sent_id": 47559, "sent": "police biker 4th from left"}, {"tokens": ["the", "middle", "police", "motorcycle", "in", "a", "line", "of", "them", "on", "the", "street"], "raw": "The middle police motorcycle in a line of them on the street.", "sent_id": 47560, "sent": "the middle police motorcycle in a line of them on the street"}], "file_name": "COCO_train2014_000000074217_1362052.jpg", "ann_id": 1362052, "sent_ids": [47559, 47560], "ref_id": 23275}, {"segmentation": [[428.45, 208.53, 449.63, 208.53, 460.0, 199.96, 467.22, 184.63, 478.49, 177.42, 496.52, 178.77, 532.58, 188.24, 550.16, 194.1, 562.34, 195.45, 560.08, 202.67, 558.28, 213.04, 564.59, 236.03, 557.38, 246.39, 555.57, 283.36, 541.6, 294.18, 517.26, 303.2, 489.31, 309.06, 447.38, 311.31, 444.22, 298.24, 455.49, 294.18, 443.77, 278.85, 418.98, 281.56, 418.08, 271.19, 430.7, 264.43, 415.37, 245.04, 412.67, 236.03, 412.67, 229.71, 412.67, 221.15, 417.63, 213.04, 422.14, 210.33]], "area": 14967.34325, "iscrowd": 0, "image_id": 140210, "bbox": [412.67, 177.42, 151.92, 133.89], "category_id": 15, "id": 576817, "split": "val", "sentences": [{"tokens": ["a", "large", "wooden", "bench", "in", "the", "foreground", "of", "the", "picture", "with", "another", "wooden", "bench", "in", "the", "background"], "raw": "A large wooden bench in the foreground of the picture with another wooden bench in the background.", "sent_id": 47563, "sent": "a large wooden bench in the foreground of the picture with another wooden bench in the background"}, {"tokens": ["cut", "out", "log", "closest", "to", "camera"], "raw": "cut out log closest to camera", "sent_id": 47564, "sent": "cut out log closest to camera"}], "file_name": "COCO_train2014_000000140210_576817.jpg", "ann_id": 576817, "sent_ids": [47563, 47564], "ref_id": 23276}, {"segmentation": [[61.57, 493.48, 0.0, 497.78, 0.0, 490.62, 0.0, 288.74, 54.41, 215.72, 128.86, 167.04, 164.65, 152.72, 167.52, 148.43, 164.65, 126.95, 151.77, 125.52, 147.47, 73.97, 150.34, 65.38, 148.9, 46.77, 131.72, 38.18, 131.72, 32.45, 146.04, 35.32, 144.61, 12.41, 144.61, 0.0, 336.47, 0.95, 346.49, 0.95, 342.19, 29.59, 340.76, 46.77, 339.33, 73.97, 336.47, 79.7, 336.47, 86.86, 343.62, 98.31, 343.62, 125.52, 335.03, 132.68, 326.44, 146.99, 312.13, 144.13, 304.97, 148.43, 320.72, 167.04, 409.49, 208.56, 420.94, 235.76, 478.21, 351.74, 479.64, 370.35, 480.0, 484.89, 458.17, 484.89, 462.46, 473.44, 420.94, 459.12, 383.71, 461.98, 362.24, 470.57, 365.1, 482.03, 320.72, 480.6, 241.97, 473.44, 196.15, 479.16, 186.13, 461.98, 174.68, 459.12, 161.79, 461.98, 160.36, 463.42, 136.02, 450.53, 93.06, 450.53, 63.0, 470.57, 58.7, 483.46, 57.27, 490.62, 55.84, 490.62]], "area": 160883.4144499999, "iscrowd": 0, "image_id": 327404, "bbox": [0.0, 0.0, 480.0, 497.78], "category_id": 1, "id": 1709421, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "glasses", "and", "a", "striped", "shirt"], "raw": "A man with glasses and a striped shirt.", "sent_id": 47666, "sent": "a man with glasses and a striped shirt"}, {"tokens": ["the", "guy", "with", "his", "arms", "on", "the", "table"], "raw": "the guy with his arms on the table.", "sent_id": 47667, "sent": "the guy with his arms on the table"}], "file_name": "COCO_train2014_000000327404_1709421.jpg", "ann_id": 1709421, "sent_ids": [47666, 47667], "ref_id": 23316}, {"segmentation": [[104.22, 158.71, 74.35, 91.84, 56.18, 77.56, 9.43, 52.24, 0.0, 39.25, 0.0, 0.0, 121.74, 0.0, 108.76, 29.52, 93.18, 71.07, 118.5, 156.76, 139.27, 158.06, 163.29, 167.15, 142.52, 188.57, 114.68, 218.36, 90.01, 213.82, 72.48, 195.64, 79.62, 172.92, 98.45, 161.88]], "area": 12547.76055, "iscrowd": 0, "image_id": 21595, "bbox": [0.0, 0.0, 163.29, 218.36], "category_id": 46, "id": 662602, "split": "val", "sentences": [{"tokens": ["a", "clear", "wine", "glass", "with", "liquid", "inside", "of", "it"], "raw": "A clear wine glass with liquid inside of it", "sent_id": 47715, "sent": "a clear wine glass with liquid inside of it"}, {"tokens": ["empty", "clear", "glass", "margarita", "glass"], "raw": "Empty clear glass margarita glass", "sent_id": 47716, "sent": "empty clear glass margarita glass"}], "file_name": "COCO_train2014_000000021595_662602.jpg", "ann_id": 662602, "sent_ids": [47715, 47716], "ref_id": 23333}, {"segmentation": [[70.92, 209.83, 64.75, 214.96, 62.7, 226.27, 78.12, 233.47, 76.06, 270.47, 84.28, 287.94, 92.51, 299.25, 118.2, 293.08, 144.93, 295.14, 162.4, 286.91, 189.12, 268.41, 201.46, 254.02, 193.23, 243.74, 166.51, 237.58, 153.15, 230.38, 149.04, 212.91, 145.95, 208.8, 149.04, 186.19, 142.87, 181.05, 131.56, 188.24, 116.15, 188.24, 104.84, 188.24, 87.37, 197.49]], "area": 9643.33, "iscrowd": 0, "image_id": 470977, "bbox": [62.7, 181.05, 138.76, 118.2], "category_id": 20, "id": 62944, "split": "val", "sentences": [{"tokens": ["a", "baby", "sheep", "laying", "to", "the", "left", "of", "another", "baby", "sheep"], "raw": "A baby sheep laying to the left of another baby sheep.", "sent_id": 47899, "sent": "a baby sheep laying to the left of another baby sheep"}, {"tokens": ["baby", "sheep", "facing", "adult", "sheep"], "raw": "baby sheep facing adult sheep", "sent_id": 47900, "sent": "baby sheep facing adult sheep"}], "file_name": "COCO_train2014_000000470977_62944.jpg", "ann_id": 62944, "sent_ids": [47899, 47900], "ref_id": 23403}, {"segmentation": [[66.04, 82.63, 18.6, 100.66, 4.36, 109.2, 27.13, 152.85, 18.6, 152.85, 26.19, 172.78, 36.62, 259.12, 43.27, 248.68, 46.11, 219.27, 130.56, 225.91, 146.69, 273.35, 150.49, 267.66, 144.79, 225.91, 176.11, 194.6, 181.8, 222.12, 187.49, 212.63, 188.44, 195.55, 200.78, 178.47, 198.88, 162.34, 183.7, 159.49, 178.0, 140.51, 184.65, 129.13, 178.0, 124.38, 155.23, 124.38, 148.59, 124.38, 159.98, 151.9, 132.46, 167.08, 135.3, 155.7, 93.55, 153.8, 96.4, 124.38]], "area": 16843.481499999998, "iscrowd": 0, "image_id": 581256, "bbox": [4.36, 82.63, 196.42, 190.72], "category_id": 62, "id": 1592167, "split": "val", "sentences": [{"tokens": ["black", "chair", "with", "a", "stuffed", "animal", "on", "it"], "raw": "Black chair with a stuffed animal on it", "sent_id": 47978, "sent": "black chair with a stuffed animal on it"}, {"tokens": ["the", "chair", "with", "the", "stuffed", "animal", "owl", "sitting", "in", "it"], "raw": "The chair with the stuffed animal owl sitting in it.", "sent_id": 47979, "sent": "the chair with the stuffed animal owl sitting in it"}], "file_name": "COCO_train2014_000000581256_1592167.jpg", "ann_id": 1592167, "sent_ids": [47978, 47979], "ref_id": 23429}, {"segmentation": [[0.77, 308.49, 40.6, 296.23, 76.6, 310.79, 111.83, 308.49, 128.68, 306.96, 128.68, 313.85, 174.64, 304.66, 186.13, 292.4, 194.55, 302.36, 197.62, 295.47, 202.21, 283.98, 211.4, 272.49, 237.45, 265.6, 282.64, 271.72, 278.81, 297.0, 278.81, 306.19, 278.81, 316.15, 278.81, 319.21, 0.0, 318.45]], "area": 6576.313749999992, "iscrowd": 0, "image_id": 332204, "bbox": [0.0, 265.6, 282.64, 53.61], "category_id": 67, "id": 119880, "split": "val", "sentences": [{"tokens": ["wood", "table"], "raw": "wood table", "sent_id": 48041, "sent": "wood table"}], "file_name": "COCO_train2014_000000332204_119880.jpg", "ann_id": 119880, "sent_ids": [48041], "ref_id": 23447}, {"segmentation": [[302.58, 449.21, 294.36, 286.28, 295.73, 243.84, 177.99, 305.45, 161.56, 310.92, 158.82, 286.28, 260.13, 213.72, 262.87, 205.5, 265.61, 179.49, 283.41, 143.89, 340.91, 124.72, 336.81, 89.13, 340.91, 38.47, 355.97, 12.45, 413.48, 8.35, 435.38, 24.78, 438.12, 64.48, 428.54, 104.19, 413.48, 126.09, 420.32, 153.47, 423.06, 156.21, 418.95, 179.49, 439.49, 223.3, 446.34, 234.25, 435.38, 271.22, 428.54, 305.45, 446.34, 335.57, 442.23, 352.0, 439.49, 383.49, 338.17, 395.81], [421.69, 535.46, 423.06, 603.92, 376.51, 608.15, 364.19, 472.61]], "area": 59786.1725, "iscrowd": 0, "image_id": 541949, "bbox": [158.82, 8.35, 287.52, 599.8], "category_id": 1, "id": 483579, "split": "val", "sentences": [{"tokens": ["a", "man", "is", "standing", "with", "two", "ladies"], "raw": "A man is standing with two ladies.", "sent_id": 48065, "sent": "a man is standing with two ladies"}, {"tokens": ["man", "in", "the", "middle", "of", "two", "ladies"], "raw": "man in the middle of two ladies", "sent_id": 48066, "sent": "man in the middle of two ladies"}], "file_name": "COCO_train2014_000000541949_483579.jpg", "ann_id": 483579, "sent_ids": [48065, 48066], "ref_id": 23458}, {"segmentation": [[545.05, 297.02, 562.15, 284.58, 569.93, 279.13, 570.71, 257.36, 565.26, 238.7, 557.49, 212.27, 548.16, 162.5, 543.49, 143.07, 545.82, 134.51, 545.82, 124.4, 541.94, 98.75, 551.27, 77.75, 552.82, 66.09, 552.82, 55.98, 541.16, 49.76, 549.71, 40.43, 557.49, 31.1, 575.37, 28.77, 584.7, 31.88, 591.7, 45.1, 593.25, 55.98, 597.14, 66.09, 602.58, 76.2, 610.36, 111.19, 611.91, 150.84, 607.25, 160.95, 602.58, 165.61, 595.59, 196.71, 600.25, 237.15, 603.36, 283.8, 602.58, 306.35, 579.26, 311.79, 555.16, 312.57, 551.27, 312.57, 562.93, 303.24, 560.6, 301.68, 545.05, 300.9]], "area": 13506.817500000003, "iscrowd": 0, "image_id": 401982, "bbox": [541.16, 28.77, 70.75, 283.8], "category_id": 1, "id": 1210002, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "his", "hand", "touching", "his", "face"], "raw": "The man with his hand touching his face.", "sent_id": 48074, "sent": "the man with his hand touching his face"}, {"tokens": ["man", "standing", "in", "maroon", "and", "white", "uniform", "with", "two", "of", "his", "fingers", "on", "his", "face"], "raw": "Man standing in maroon and white uniform with two of his fingers on his face.", "sent_id": 48075, "sent": "man standing in maroon and white uniform with two of his fingers on his face"}], "file_name": "COCO_train2014_000000401982_1210002.jpg", "ann_id": 1210002, "sent_ids": [48074, 48075], "ref_id": 23460}, {"segmentation": [[255.58, 140.51, 203.22, 94.38, 168.31, 81.91, 107.22, 75.68, 96.0, 104.35, 107.22, 113.08, 88.52, 128.04, 114.7, 155.47, 173.3, 171.68, 215.69, 160.46, 255.58, 141.76]], "area": 10279.319400000002, "iscrowd": 0, "image_id": 29473, "bbox": [88.52, 75.68, 167.06, 96.0], "category_id": 54, "id": 1909413, "split": "val", "sentences": [{"tokens": ["the", "bread", "that", "it", "vertical", "in", "the", "container"], "raw": "The bread that it vertical in the container.", "sent_id": 48117, "sent": "the bread that it vertical in the container"}], "file_name": "COCO_train2014_000000029473_1909413.jpg", "ann_id": 1909413, "sent_ids": [48117], "ref_id": 23477}, {"segmentation": [[135.5, 284.19, 117.17, 256.25, 111.05, 231.8, 124.15, 199.5, 134.63, 189.89, 134.63, 178.54, 130.26, 163.7, 156.46, 162.83, 170.43, 160.21, 179.16, 152.35, 194.0, 153.22, 201.86, 157.59, 211.46, 165.45, 222.81, 156.71, 237.66, 160.21, 235.91, 175.05, 227.18, 185.53, 240.28, 199.5, 249.01, 234.42, 245.52, 254.5, 230.67, 283.32, 219.32, 299.91, 208.84, 328.72, 213.21, 360.15, 213.21, 366.27, 206.22, 366.27, 195.75, 352.3, 193.13, 331.34, 194.87, 314.75, 202.73, 295.54, 184.4, 310.38, 181.78, 332.21, 176.54, 350.55, 175.66, 363.65, 166.06, 362.77, 158.2, 357.53, 158.2, 324.35, 156.46, 314.75, 150.34, 335.71, 151.22, 352.3, 150.34, 369.76, 138.12, 361.9, 138.12, 345.31, 133.75, 325.23, 132.88, 313.88, 132.01, 296.41, 133.75, 283.32]], "area": 19718.499500000005, "iscrowd": 0, "image_id": 227198, "bbox": [111.05, 152.35, 137.96, 217.41], "category_id": 21, "id": 72399, "split": "val", "sentences": [{"tokens": ["face", "of", "cow", "standing", "in", "front", "of", "sun"], "raw": "face of cow standing in front of sun", "sent_id": 48188, "sent": "face of cow standing in front of sun"}, {"tokens": ["a", "cow", "who", "is", "facing", "straight", "the", "camera"], "raw": "A cow who is facing straight the camera", "sent_id": 48189, "sent": "a cow who is facing straight the camera"}], "file_name": "COCO_train2014_000000227198_72399.jpg", "ann_id": 72399, "sent_ids": [48188, 48189], "ref_id": 23500}, {"segmentation": [[302.09, 211.24, 292.37, 188.81, 293.86, 167.12, 305.08, 153.66, 320.78, 153.66, 328.26, 154.41, 367.14, 158.9, 383.59, 167.12, 387.33, 183.57, 379.11, 200.77, 367.89, 217.97, 393.32, 249.37, 406.03, 267.32, 405.28, 286.01, 400.79, 291.25, 384.34, 284.52, 391.07, 294.99, 389.58, 309.94, 383.59, 316.67, 379.11, 323.4, 361.16, 315.18, 352.19, 315.18, 341.72, 301.72, 346.95, 289.75, 327.51, 294.99, 334.99, 308.45, 332.75, 318.17, 329.01, 323.4, 317.79, 322.65, 293.86, 323.4, 285.64, 295.73, 280.41, 280.78, 285.64, 275.55, 275.17, 260.59, 278.16, 241.15, 287.88, 229.93, 300.59, 214.98]], "area": 15781.364799999994, "iscrowd": 0, "image_id": 264016, "bbox": [275.17, 153.66, 130.86, 169.74], "category_id": 88, "id": 1159468, "split": "val", "sentences": [{"tokens": ["a", "small", "white", "bear", "with", "little", "brown", "bow", "tie"], "raw": "A small white bear with little brown bow tie.", "sent_id": 48195, "sent": "a small white bear with little brown bow tie"}, {"tokens": ["the", "smallest", "white", "teddy", "bear", "sitting", "in", "front", "of", "the", "other", "white", "bear"], "raw": "the smallest white teddy bear sitting in front of the other white bear.", "sent_id": 48196, "sent": "the smallest white teddy bear sitting in front of the other white bear"}], "file_name": "COCO_train2014_000000264016_1159468.jpg", "ann_id": 1159468, "sent_ids": [48195, 48196], "ref_id": 23504}, {"segmentation": [[62.76, 220.73, 58.54, 224.96, 64.45, 226.65, 66.99, 232.56, 62.76, 241.01, 55.16, 246.09, 52.62, 248.62, 47.55, 253.69, 45.86, 260.45, 45.02, 264.68, 34.88, 286.65, 34.03, 293.41, 38.26, 302.7, 39.95, 304.39, 37.41, 311.15, 37.41, 317.07, 38.26, 322.98, 40.79, 334.81, 40.79, 339.88, 40.79, 344.11, 40.79, 358.47, 41.64, 364.39, 50.93, 367.77, 61.07, 361.85, 62.76, 353.4, 64.45, 338.19, 64.45, 328.9, 70.37, 322.98, 79.66, 325.52, 85.58, 325.52, 123.6, 309.46, 125.29, 317.07, 119.38, 322.98, 110.93, 334.81, 109.24, 339.04, 105.86, 343.26, 105.86, 345.8, 105.86, 350.02, 122.76, 355.09, 143.04, 360.16, 150.64, 355.94, 145.57, 328.05, 149.8, 317.07, 149.8, 301.01, 132.05, 288.34, 125.29, 289.18, 110.08, 290.03, 105.86, 280.73, 109.24, 262.99, 121.07, 262.14, 160.79, 249.47, 172.62, 240.17, 176.0, 206.37, 154.02, 208.9, 149.8, 216.51, 144.73, 224.11, 137.12, 235.1, 122.76, 235.1, 114.31, 233.41, 109.24, 232.56, 90.65, 204.68, 81.35, 199.61, 59.38, 215.66, 63.61, 221.58]], "area": 12270.6422, "iscrowd": 0, "image_id": 432138, "bbox": [34.03, 199.61, 141.97, 168.16], "category_id": 1, "id": 539656, "split": "val", "sentences": [{"tokens": ["a", "kid", "playing", "baseball", ",", "squatting", "down", "because", "he", "is", "playing", "catcher"], "raw": "A kid playing baseball, squatting down because he is playing catcher.", "sent_id": 48263, "sent": "a kid playing baseball , squatting down because he is playing catcher"}, {"tokens": ["a", "young", "man", "squatted", "down", "behind", "the", "batter", "acting", "as", "a", "catcher", "for", "a", "baseball", "game"], "raw": "A young man squatted down behind the batter acting as a catcher for a baseball game.", "sent_id": 48264, "sent": "a young man squatted down behind the batter acting as a catcher for a baseball game"}], "file_name": "COCO_train2014_000000432138_539656.jpg", "ann_id": 539656, "sent_ids": [48263, 48264], "ref_id": 23531}, {"segmentation": [[244.76, 227.63, 230.15, 232.34, 217.89, 236.11, 199.51, 239.88, 199.51, 238.47, 220.25, 226.69, 235.81, 219.14, 246.65, 210.66, 255.13, 207.83, 249.0, 205.0, 233.92, 200.29, 224.02, 199.82, 215.54, 199.82, 212.71, 193.22, 206.11, 190.86, 203.28, 187.09, 203.28, 183.79, 199.51, 173.42, 199.98, 168.24, 201.87, 168.24, 204.22, 175.78, 206.11, 166.82, 211.29, 168.71, 214.59, 174.37, 214.59, 180.96, 219.31, 173.42, 223.08, 173.42, 219.78, 180.49, 227.79, 177.66, 230.62, 178.61, 229.21, 180.49, 237.22, 180.96, 246.18, 185.68, 257.49, 187.56, 273.04, 188.98, 288.13, 195.58, 303.68, 204.06, 319.71, 194.63, 330.08, 188.03, 349.4, 186.15, 366.37, 180.49, 380.98, 164.0, 372.97, 176.72, 378.16, 178.61, 376.74, 182.85, 364.96, 185.68, 351.76, 196.99, 332.43, 210.19, 327.25, 212.55, 336.21, 216.32, 333.38, 220.09, 353.17, 228.1, 351.76, 233.76, 325.36, 242.71, 315.47, 244.13, 299.44, 243.18, 292.37, 245.07, 270.21, 241.77, 248.53, 237.06, 243.35, 228.57]], "area": 6336.5082, "iscrowd": 0, "image_id": 365231, "bbox": [199.51, 164.0, 181.47, 81.07], "category_id": 16, "id": 42035, "split": "val", "sentences": [{"tokens": ["the", "middle", "flying", "bird"], "raw": "the middle flying bird", "sent_id": 48309, "sent": "the middle flying bird"}, {"tokens": ["a", "bird", "flying", "in", "between", "two", "other", "birds"], "raw": "A bird flying in between two other birds.", "sent_id": 48310, "sent": "a bird flying in between two other birds"}], "file_name": "COCO_train2014_000000365231_42035.jpg", "ann_id": 42035, "sent_ids": [48309, 48310], "ref_id": 23548}, {"segmentation": [[188.33, 231.88, 202.82, 237.68, 224.06, 234.78, 233.72, 234.78, 240.48, 224.16, 244.35, 225.12, 240.48, 240.58, 236.62, 246.37, 260.76, 253.13, 291.67, 254.1, 326.44, 253.13, 340.93, 260.86, 378.59, 284.04, 386.32, 300.46, 399.84, 305.28, 407.57, 288.87, 414.33, 284.04, 422.05, 284.04, 420.12, 301.42, 419.15, 301.42, 414.33, 312.04, 405.63, 312.04, 377.63, 312.04, 368.93, 302.39, 365.07, 312.04, 332.23, 308.18, 249.18, 307.22, 250.14, 307.22, 250.14, 307.22, 223.1, 307.22, 221.17, 305.28, 219.24, 295.63, 216.34, 288.87, 211.51, 282.11, 209.58, 278.24, 202.82, 273.41, 197.99, 263.76, 197.99, 260.86, 197.02, 256.03, 193.16, 252.17, 190.26, 246.37, 188.33, 241.54, 188.33, 236.71, 188.33, 235.75]], "area": 10204.939550000005, "iscrowd": 0, "image_id": 427467, "bbox": [188.33, 224.16, 233.72, 87.88], "category_id": 18, "id": 6819, "split": "val", "sentences": [{"tokens": ["white", "dog", "on", "back", "of", "truck"], "raw": "white dog on back of truck", "sent_id": 48315, "sent": "white dog on back of truck"}, {"tokens": ["a", "white", "dog", "in", "the", "back", "of", "a", "truck"], "raw": "A white dog in the back of a truck.", "sent_id": 48316, "sent": "a white dog in the back of a truck"}], "file_name": "COCO_train2014_000000427467_6819.jpg", "ann_id": 6819, "sent_ids": [48315, 48316], "ref_id": 23550}, {"segmentation": [[413.43, 186.59, 433.8, 188.08, 456.64, 201.98, 461.11, 224.33, 461.11, 230.79, 454.66, 235.26, 436.78, 247.18, 440.75, 261.09, 442.24, 256.12, 465.09, 263.07, 466.58, 267.54, 462.11, 272.51, 439.76, 276.48, 426.35, 276.98, 425.35, 290.89, 425.35, 294.36, 410.45, 292.87, 403.0, 299.83, 391.08, 297.84, 378.67, 297.34, 378.67, 289.4, 373.2, 281.45, 383.14, 274.99, 388.1, 272.01, 390.59, 249.17, 396.05, 241.22, 390.59, 214.9, 394.06, 193.54, 411.45, 186.59]], "area": 6359.630450000001, "iscrowd": 0, "image_id": 254176, "bbox": [373.2, 186.59, 93.38, 113.24], "category_id": 88, "id": 1674800, "split": "val", "sentences": [{"tokens": ["small", "teddy", "bear", "next", "to", "teddy", "bear", "in", "goggles"], "raw": "Small teddy bear next to teddy bear in goggles", "sent_id": 48384, "sent": "small teddy bear next to teddy bear in goggles"}, {"tokens": ["legs", "of", "brown", "teddy", "bear", "hanging", "outside", "black", "car"], "raw": "Legs of brown teddy bear hanging outside black car", "sent_id": 48385, "sent": "legs of brown teddy bear hanging outside black car"}], "file_name": "COCO_train2014_000000254176_1674800.jpg", "ann_id": 1674800, "sent_ids": [48384, 48385], "ref_id": 23578}, {"segmentation": [[419.46, 136.76, 295.14, 160.54, 280.0, 161.62, 248.65, 161.62, 215.14, 161.62, 194.59, 154.05, 170.81, 149.73, 153.51, 149.73, 142.7, 158.38, 140.54, 172.43, 140.54, 177.84, 100.54, 184.32, 89.73, 180.0, 77.84, 178.92, 80.0, 189.73, 82.16, 196.22, 58.38, 212.43, 55.14, 222.16, 68.11, 227.57, 45.41, 256.76, 37.84, 291.35, 38.92, 342.16, 55.14, 373.51, 70.27, 384.32, 76.76, 390.81, 88.65, 398.38, 107.03, 400.54, 136.22, 402.7, 161.08, 400.54, 191.35, 398.38, 212.97, 388.65, 234.59, 372.43, 246.49, 358.38, 255.14, 358.38, 274.59, 361.62, 296.22, 361.62, 305.95, 361.62, 315.68, 372.43, 321.08, 385.41, 322.16, 391.89, 290.81, 401.62, 270.27, 408.11, 270.27, 411.35, 307.03, 414.59, 365.41, 394.05, 372.97, 384.32, 362.16, 363.78, 358.92, 354.05, 424.86, 333.51, 418.38, 315.14, 431.35, 270.81, 451.89, 257.84, 456.22, 247.03, 444.32, 234.05, 444.32, 225.41, 457.3, 190.81, 475.68, 192.97, 480.0, 210.27, 458.38, 240.54, 450.81, 279.46, 450.81, 297.84, 454.05, 311.89, 464.86, 325.95, 477.84, 331.35, 507.03, 336.76, 536.22, 344.32, 556.76, 334.59, 571.89, 315.14, 582.7, 295.68, 590.27, 277.3, 595.68, 260.0, 592.43, 222.16, 585.95, 204.86, 580.54, 195.14, 581.62, 185.41, 563.24, 183.24, 529.73, 178.92, 521.08, 160.54, 525.41, 150.81, 526.49, 145.41, 538.38, 145.41, 548.11, 140.0, 542.7, 132.43, 526.49, 120.54, 508.11, 112.97, 492.97, 103.24, 476.76, 92.43, 469.19, 85.95, 452.97, 85.95, 435.68, 85.95, 425.95, 94.59, 418.38, 103.24, 394.59, 105.41, 387.03, 118.38, 387.03, 121.62, 411.89, 123.78, 420.54, 124.86]], "area": 113728.42169999999, "iscrowd": 0, "image_id": 11426, "bbox": [37.84, 85.95, 557.84, 328.64], "category_id": 4, "id": 149531, "split": "val", "sentences": [{"tokens": ["a", "black", "motorcycle", "on", "green", "grass", "near", "a", "sign", "that", "reads", "141", "parked", "near", "other", "vehicles"], "raw": "A black motorcycle on green grass near a sign that reads 141 parked near other vehicles.", "sent_id": 48388, "sent": "a black motorcycle on green grass near a sign that reads 141 parked near other vehicles"}, {"tokens": ["the", "black", "motorcycle", "in", "front"], "raw": "the black motorcycle in front", "sent_id": 48389, "sent": "the black motorcycle in front"}], "file_name": "COCO_train2014_000000011426_149531.jpg", "ann_id": 149531, "sent_ids": [48388, 48389], "ref_id": 23580}, {"segmentation": [[373.97, 261.66, 363.32, 273.49, 376.34, 310.18, 392.9, 317.28, 386.99, 343.31, 376.34, 350.41, 379.89, 365.8, 378.7, 375.27, 376.34, 383.55, 383.44, 375.27, 397.64, 382.37, 378.7, 456.92, 376.34, 477.04, 402.37, 382.37, 427.22, 381.18, 479.3, 482.96, 482.85, 480.59, 435.51, 382.37, 486.61, 370.4, 487.32, 366.09, 469.36, 338.07, 428.41, 341.66, 417.63, 338.07, 393.21, 287.77, 376.68, 263.35]], "area": 6597.944699999998, "iscrowd": 0, "image_id": 382469, "bbox": [363.32, 261.66, 124.0, 221.3], "category_id": 62, "id": 377908, "split": "val", "sentences": [{"tokens": ["a", "rear", "facing", "chair", "with", "a", "blue", "towel", "on", "top"], "raw": "A rear facing chair with a blue towel on top", "sent_id": 48394, "sent": "a rear facing chair with a blue towel on top"}, {"tokens": ["chair", "on", "the", "right", "side"], "raw": "chair on the right side", "sent_id": 48395, "sent": "chair on the right side"}], "file_name": "COCO_train2014_000000382469_377908.jpg", "ann_id": 377908, "sent_ids": [48394, 48395], "ref_id": 23581}, {"segmentation": [[67.1, 339.61, 2.06, 325.16, 2.06, 301.42, 7.23, 297.29, 15.48, 297.29, 14.45, 271.48, 180.65, 265.29, 279.74, 257.03, 290.06, 297.29, 369.55, 301.42, 372.65, 368.52, 313.81, 385.03, 300.39, 356.13, 67.1, 345.81, 67.1, 338.58]], "area": 28752.98644999999, "iscrowd": 0, "image_id": 130163, "bbox": [2.06, 257.03, 370.59, 128.0], "category_id": 63, "id": 115636, "split": "val", "sentences": [{"tokens": ["the", "gray", "couch", "that", "has", "the", "brown", "and", "blue", "throw", "pillow", "on", "it"], "raw": "The gray couch that has the brown and blue throw pillow on it.", "sent_id": 48399, "sent": "the gray couch that has the brown and blue throw pillow on it"}, {"tokens": ["a", "beige", "colored", "couch", "that", "seats", "two", "people", "with", "a", "blue", "and", "brown", "accent", "pillow", "on", "it"], "raw": "A beige colored couch that seats two people with a blue and brown accent pillow on it.", "sent_id": 48400, "sent": "a beige colored couch that seats two people with a blue and brown accent pillow on it"}], "file_name": "COCO_train2014_000000130163_115636.jpg", "ann_id": 115636, "sent_ids": [48399, 48400], "ref_id": 23583}, {"segmentation": [[414.53, 208.89, 414.53, 220.41, 403.97, 224.25, 414.53, 256.87, 443.31, 259.75, 445.23, 265.51, 487.45, 253.99, 496.09, 239.6, 488.41, 232.88, 476.9, 223.29, 458.67, 224.25, 450.03, 219.45, 448.11, 189.7, 450.99, 177.23, 446.19, 158.04, 448.11, 142.69, 450.99, 105.26, 454.83, 96.63, 510.48, 52.49, 523.91, 12.19, 522.96, 1.63, 362.71, 1.63, 368.47, 28.5, 384.78, 55.37, 408.77, 81.27, 426.04, 89.91, 434.68, 99.51, 432.76, 145.56]], "area": 16714.410150000007, "iscrowd": 0, "image_id": 431112, "bbox": [362.71, 1.63, 161.2, 263.88], "category_id": 46, "id": 664379, "split": "val", "sentences": [{"tokens": ["glass", "of", "wine", "in", "table"], "raw": "glass of wine in table", "sent_id": 48434, "sent": "glass of wine in table"}, {"tokens": ["a", "glass", "of", "wine"], "raw": "a glass of wine", "sent_id": 48435, "sent": "a glass of wine"}], "file_name": "COCO_train2014_000000431112_664379.jpg", "ann_id": 664379, "sent_ids": [48434, 48435], "ref_id": 23596}, {"segmentation": [[301.68, 128.46, 302.75, 37.48, 306.47, 19.39, 312.33, 8.21, 320.31, 1.83, 375.11, 1.83, 387.88, 10.34, 393.73, 26.3, 393.2, 50.78, 390.01, 78.45, 360.21, 74.19, 321.9, 76.32, 309.67, 77.38, 302.75, 124.2]], "area": 6555.7733499999995, "iscrowd": 0, "image_id": 80590, "bbox": [301.68, 1.83, 92.05, 126.63], "category_id": 44, "id": 88869, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "2007", "vintage", "chardonnay", "with", "a", "yellow", "label"], "raw": "A bottle of 2007 vintage Chardonnay with a yellow label.", "sent_id": 48440, "sent": "a bottle of 2007 vintage chardonnay with a yellow label"}, {"tokens": ["bottle", "with", "2007", "label"], "raw": "bottle with 2007 label", "sent_id": 48441, "sent": "bottle with 2007 label"}], "file_name": "COCO_train2014_000000080590_88869.jpg", "ann_id": 88869, "sent_ids": [48440, 48441], "ref_id": 23599}, {"segmentation": [[250.44, 260.04, 261.96, 261.0, 269.63, 260.04, 286.91, 257.16, 301.3, 260.04, 308.98, 258.12, 324.33, 253.32, 355.03, 259.08, 366.55, 232.21, 391.5, 152.57, 387.66, 145.85, 365.59, 143.93, 362.71, 152.57, 357.91, 163.12, 354.07, 191.91, 350.24, 200.55, 345.44, 220.7, 340.64, 230.29, 295.54, 233.17, 268.67, 234.13, 249.48, 257.16, 247.56, 256.2, 247.56, 260.04]], "area": 4930.64245, "iscrowd": 0, "image_id": 230436, "bbox": [247.56, 143.93, 143.94, 117.07], "category_id": 73, "id": 1097669, "split": "val", "sentences": [{"tokens": ["a", "lap", "top", "that", "a", "man", "is", "using"], "raw": "A lap top that a  man is using", "sent_id": 48572, "sent": "a lap top that a man is using"}, {"tokens": ["a", "silver", "laptop", "being", "used", "by", "a", "man"], "raw": "a silver laptop being used by a man", "sent_id": 48573, "sent": "a silver laptop being used by a man"}], "file_name": "COCO_train2014_000000230436_1097669.jpg", "ann_id": 1097669, "sent_ids": [48572, 48573], "ref_id": 23646}, {"segmentation": [[197.72, 380.79, 187.21, 384.61, 181.48, 384.61, 150.91, 389.39, 141.36, 383.65, 136.59, 373.15, 137.54, 368.37, 141.36, 361.69, 145.18, 358.82, 146.14, 355.96, 150.91, 353.09, 159.51, 351.18, 162.38, 351.18, 171.93, 350.22, 178.61, 351.18, 241.65, 320.61, 255.03, 319.66, 260.76, 317.75, 266.49, 315.84, 270.31, 313.93, 279.86, 315.84, 285.59, 317.75, 295.14, 322.52, 300.87, 323.48, 303.74, 325.39, 309.47, 329.21, 316.16, 338.76, 316.16, 340.67, 322.84, 345.45, 341.95, 351.18, 356.27, 351.18, 377.29, 336.85, 407.85, 328.26, 430.78, 332.08, 441.28, 335.9, 487.13, 365.51, 617.99, 397.98, 623.72, 409.44, 623.72, 411.35, 623.72, 413.26, 234.97, 419.95, 224.46, 408.49]], "area": 29658.311149999994, "iscrowd": 0, "image_id": 419110, "bbox": [136.59, 313.93, 487.13, 106.02], "category_id": 1, "id": 1254732, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "white", "pants"], "raw": "A man in white pants.", "sent_id": 48574, "sent": "a man in white pants"}, {"tokens": ["a", "man", "in", "white", "trousers"], "raw": "a man in white trousers", "sent_id": 48575, "sent": "a man in white trousers"}], "file_name": "COCO_train2014_000000419110_1254732.jpg", "ann_id": 1254732, "sent_ids": [48574, 48575], "ref_id": 23647}, {"segmentation": [[332.19, 1.7, 347.78, 23.02, 420.78, 15.64, 486.39, 0.87, 515.92, 12.36, 588.1, 57.47, 640.0, 73.05, 639.78, 2.52, 545.45, 0.05, 337.11, 0.87]], "area": 8016.207249999999, "iscrowd": 0, "image_id": 37160, "bbox": [332.19, 0.05, 307.81, 73.0], "category_id": 28, "id": 1425006, "split": "val", "sentences": [{"tokens": ["outer", "edge", "of", "a", "solid", "navy", "blue", "umbrella"], "raw": "Outer edge of a solid navy blue umbrella", "sent_id": 48580, "sent": "outer edge of a solid navy blue umbrella"}, {"tokens": ["the", "edge", "of", "a", "blue", "umbrella"], "raw": "The edge of a blue umbrella.", "sent_id": 48581, "sent": "the edge of a blue umbrella"}], "file_name": "COCO_train2014_000000037160_1425006.jpg", "ann_id": 1425006, "sent_ids": [48580, 48581], "ref_id": 23650}, {"segmentation": [[390.18, 151.97, 456.59, 158.41, 500.95, 166.83, 501.94, 175.51, 496.24, 201.03, 495.99, 252.33, 495.5, 272.15, 485.59, 276.12, 419.42, 268.19, 391.17, 260.5, 380.27, 258.52, 372.09, 248.36, 374.08, 192.11, 375.56, 153.95, 376.8, 150.73]], "area": 13755.259200000004, "iscrowd": 0, "image_id": 456658, "bbox": [372.09, 150.73, 129.85, 125.39], "category_id": 72, "id": 1969132, "split": "val", "sentences": [{"tokens": ["a", "computer", "screen", "turned", "on", "with", "a", "program", "on", "it"], "raw": "A computer screen turned on with a program on it", "sent_id": 48640, "sent": "a computer screen turned on with a program on it"}, {"tokens": ["a", "black", "color", "monitor", "near", "by", "cpu"], "raw": "A BLACK COLOR MONITOR NEAR BY CPU", "sent_id": 48641, "sent": "a black color monitor near by cpu"}], "file_name": "COCO_train2014_000000456658_1969132.jpg", "ann_id": 1969132, "sent_ids": [48640, 48641], "ref_id": 23674}, {"segmentation": [[2.87, 92.88, 232.08, 155.91, 229.21, 178.83, 260.73, 169.28, 282.7, 177.88, 303.71, 191.25, 288.43, 207.49, 289.38, 208.44, 282.7, 218.95, 276.01, 218.95, 264.55, 211.31, 243.54, 217.04, 236.85, 225.63, 226.35, 222.77, 217.75, 212.26, 180.51, 212.26, 176.69, 220.86, 158.54, 208.44, 112.7, 206.53, 102.19, 211.31, 99.33, 217.04, 89.78, 217.04, 79.27, 213.22, 63.99, 199.85, 42.02, 200.8, 31.52, 211.31, 5.73, 208.44]], "area": 22047.03465, "iscrowd": 0, "image_id": 286051, "bbox": [2.87, 92.88, 300.84, 132.75], "category_id": 7, "id": 172150, "split": "val", "sentences": [{"tokens": ["a", "red", "train"], "raw": "A red train.", "sent_id": 48648, "sent": "a red train"}, {"tokens": ["a", "red", "train", "next", "to", "track", "d"], "raw": "A red train next to Track D", "sent_id": 48649, "sent": "a red train next to track d"}], "file_name": "COCO_train2014_000000286051_172150.jpg", "ann_id": 172150, "sent_ids": [48648, 48649], "ref_id": 23677}, {"segmentation": [[167.53, 126.62, 159.79, 108.22, 154.94, 94.66, 153.01, 65.61, 167.53, 44.3, 188.84, 34.62, 221.76, 24.94, 249.85, 46.24, 256.63, 107.25, 260.5, 130.49, 279.87, 141.14, 305.05, 160.51, 313.76, 209.9, 304.08, 261.23, 305.05, 297.06, 298.27, 327.08, 280.84, 331.92, 272.12, 338.7, 261.47, 354.19, 251.78, 404.55, 186.9, 422.95, 136.54, 423.92, 138.48, 409.39, 99.74, 217.65, 106.52, 180.85, 134.61, 160.51, 154.94, 145.02]], "area": 57617.44599999999, "iscrowd": 0, "image_id": 58403, "bbox": [99.74, 24.94, 214.02, 398.98], "category_id": 1, "id": 434049, "split": "val", "sentences": [{"tokens": ["girl", "in", "purple", "t", "-", "shirt"], "raw": "Girl in purple t-shirt.", "sent_id": 48761, "sent": "girl in purple t - shirt"}, {"tokens": ["a", "woman", "in", "a", "purple", "t", "-", "shirt", "which", "has", "lettering", "across", "the", "front"], "raw": "A woman in a purple t-shirt which has lettering across the front.", "sent_id": 48762, "sent": "a woman in a purple t - shirt which has lettering across the front"}], "file_name": "COCO_train2014_000000058403_434049.jpg", "ann_id": 434049, "sent_ids": [48761, 48762], "ref_id": 23723}, {"segmentation": [[261.34, 312.22, 275.86, 275.36, 278.1, 251.91, 303.78, 222.87, 343.99, 207.23, 381.96, 203.88, 414.35, 202.77, 437.81, 194.95, 457.91, 201.65, 469.08, 237.39, 479.13, 283.18, 464.61, 339.02, 454.56, 345.72, 450.09, 335.67, 457.91, 315.57, 457.91, 277.6, 429.99, 274.24, 435.57, 294.35, 446.74, 327.85], [446.74, 330.09, 462.38, 362.48, 435.57, 361.36, 425.52, 327.85], [389.78, 325.62, 375.26, 358.01, 380.85, 373.64, 357.39, 378.11, 357.39, 359.13, 365.21, 323.39, 384.2, 324.5], [326.12, 321.15, 323.89, 333.44, 332.82, 371.41, 301.55, 372.53, 301.55, 344.61, 300.43, 323.39, 289.27, 337.91, 275.86, 375.88, 255.76, 361.36, 269.16, 336.79, 279.21, 316.69]], "area": 25625.4777, "iscrowd": 0, "image_id": 363331, "bbox": [255.76, 194.95, 223.37, 183.16], "category_id": 22, "id": 580420, "split": "val", "sentences": [{"tokens": ["the", "front", "elephant", "in", "the", "right", "hand", "picture"], "raw": "the front elephant in the right hand picture", "sent_id": 48803, "sent": "the front elephant in the right hand picture"}, {"tokens": ["an", "elephant", "leading", "another", "elephant", "which", "is", "holding", "its", "tail"], "raw": "an elephant leading another elephant which is holding its tail", "sent_id": 48804, "sent": "an elephant leading another elephant which is holding its tail"}], "file_name": "COCO_train2014_000000363331_580420.jpg", "ann_id": 580420, "sent_ids": [48803, 48804], "ref_id": 23741}, {"segmentation": [[104.35, 256.56, 127.32, 233.58, 123.49, 196.25, 122.53, 168.49, 115.83, 157.0, 126.36, 147.42, 128.28, 147.42, 148.38, 138.81, 148.38, 106.26, 157.96, 89.99, 151.25, 66.05, 164.66, 44.99, 190.5, 45.95, 196.25, 78.5, 216.35, 110.09, 232.62, 163.7, 236.45, 179.97, 171.36, 180.93, 172.31, 246.98, 177.1, 267.09, 132.11, 266.13, 104.35, 265.17]], "area": 13902.643300000002, "iscrowd": 0, "image_id": 555794, "bbox": [104.35, 44.99, 132.1, 222.1], "category_id": 1, "id": 480944, "split": "val", "sentences": [{"tokens": ["a", "refree", "sitting", "on", "the", "chair", "on", "the", "tennis", "court"], "raw": "A refree sitting on the chair on the tennis court", "sent_id": 48818, "sent": "a refree sitting on the chair on the tennis court"}, {"tokens": ["a", "woman", "wearing", "black", "sitting", "down"], "raw": "A woman wearing black sitting down.", "sent_id": 48819, "sent": "a woman wearing black sitting down"}], "file_name": "COCO_train2014_000000555794_480944.jpg", "ann_id": 480944, "sent_ids": [48818, 48819], "ref_id": 23747}, {"segmentation": [[252.8, 153.99, 280.76, 131.62, 296.42, 123.79, 305.37, 120.43, 310.96, 139.45, 310.96, 155.11, 302.01, 161.82, 297.54, 164.06, 286.35, 185.31, 263.98, 217.75, 199.11, 302.76, 147.65, 351.98, 105.15, 379.94, 88.37, 394.48, 70.47, 413.5, 57.05, 434.75, 54.81, 439.22, 53.69, 444.82, 35.79, 452.65, 22.37, 470.54, 15.66, 454.88, 11.19, 451.53, 12.3, 444.82, 49.22, 425.8, 72.71, 396.72, 101.79, 378.82, 104.03, 372.11, 46.98, 410.14, 98.43, 369.87, 123.04, 356.45, 140.94, 344.15, 170.02, 321.77, 190.16, 307.23, 195.75, 300.52, 190.16, 292.69, 194.63, 275.91, 201.34, 253.54, 210.29, 226.7, 223.71, 196.5, 243.85, 168.53]], "area": 9813.192000000003, "iscrowd": 0, "image_id": 45680, "bbox": [11.19, 120.43, 299.77, 350.11], "category_id": 38, "id": 623700, "split": "val", "sentences": [{"tokens": ["a", "bright", ",", "multi", "-", "colored", "windsock", "hanging", "from", "a", "tent"], "raw": "A bright, multi-colored windsock hanging from a tent.", "sent_id": 48841, "sent": "a bright , multi - colored windsock hanging from a tent"}, {"tokens": ["a", "yellow", ",", "blue", "and", "pink", "fish", "kite"], "raw": "A yellow, blue and pink fish kite.", "sent_id": 48842, "sent": "a yellow , blue and pink fish kite"}], "file_name": "COCO_train2014_000000045680_623700.jpg", "ann_id": 623700, "sent_ids": [48841, 48842], "ref_id": 23755}, {"segmentation": [[318.75, 353.69, 327.36, 354.65, 328.32, 343.16, 362.78, 297.21, 362.78, 293.38, 371.4, 291.47, 381.93, 299.13, 390.54, 302.96, 404.9, 330.72, 422.13, 343.16, 435.53, 349.86, 464.25, 346.99, 479.56, 328.8, 484.35, 307.74, 482.43, 280.94, 467.12, 252.22, 456.59, 243.61, 454.67, 237.87, 442.23, 234.04, 428.83, 229.25, 402.03, 237.87, 424.04, 201.49, 428.83, 180.43, 429.79, 167.99, 427.87, 161.29, 405.86, 167.03, 366.61, 179.48, 333.11, 177.56, 317.79, 155.55, 328.32, 153.63, 328.32, 145.97, 323.54, 139.27, 316.84, 138.32, 315.88, 134.49, 347.47, 129.7, 346.51, 126.83, 327.36, 127.79, 321.62, 124.92, 310.14, 124.92, 290.99, 127.79, 276.63, 131.62, 263.23, 131.62, 263.23, 140.23, 255.57, 142.15, 243.13, 142.15, 232.6, 142.15, 223.03, 140.23, 216.33, 139.27, 216.33, 143.1, 230.69, 144.06, 239.3, 147.89, 233.56, 148.85, 225.9, 150.76, 224.94, 156.5, 217.29, 157.46, 217.29, 164.16, 225.9, 164.16, 232.6, 152.67, 241.22, 152.67, 246.0, 153.63, 250.79, 159.38, 251.75, 168.95, 257.49, 175.65, 259.4, 187.13, 254.62, 188.09, 251.75, 195.75, 249.83, 220.64, 246.96, 227.34, 235.47, 229.25, 225.9, 238.82, 220.16, 258.92, 220.16, 290.51, 235.47, 317.31, 261.32, 335.5, 279.5, 332.63, 291.95, 313.49, 292.91, 277.11, 286.2, 254.14, 278.55, 241.69, 267.06, 233.08, 271.85, 210.11, 271.85, 197.66, 282.38, 207.24, 289.08, 220.64, 295.78, 243.61, 304.39, 257.01, 306.31, 271.37, 314.92, 286.68, 310.14, 294.34, 323.54, 289.56, 336.94, 293.38, 346.51, 287.64, 353.21, 296.26, 335.02, 320.19, 323.54, 346.03, 317.79, 354.65]], "area": 33963.15665000001, "iscrowd": 0, "image_id": 287140, "bbox": [216.33, 124.92, 268.02, 229.73], "category_id": 4, "id": 150180, "split": "val", "sentences": [{"tokens": ["a", "red", "dirt", "bike"], "raw": "A red dirt bike", "sent_id": 48859, "sent": "a red dirt bike"}, {"tokens": ["a", "silver", ",", "black", ",", "and", "red", "motor", "bike", "parked", "next", "to", "other", "motor", "bikes"], "raw": "A silver, black, and red motor bike parked next to other motor bikes.", "sent_id": 48860, "sent": "a silver , black , and red motor bike parked next to other motor bikes"}], "file_name": "COCO_train2014_000000287140_150180.jpg", "ann_id": 150180, "sent_ids": [48859, 48860], "ref_id": 23758}, {"segmentation": [[1.92, 80.78, 42.32, 82.71, 89.44, 89.44, 106.75, 90.4, 122.14, 91.36, 132.72, 89.44, 146.18, 87.52, 171.18, 88.48, 179.84, 92.32, 192.34, 105.79, 205.81, 122.14, 220.23, 149.07, 231.77, 171.18, 243.31, 217.35, 255.82, 231.77, 266.39, 239.47, 285.63, 249.08, 316.4, 252.93, 329.87, 254.85, 341.41, 261.59, 342.37, 265.43, 342.37, 271.2, 332.75, 273.13, 318.33, 274.09, 304.86, 274.09, 292.36, 269.28, 262.55, 266.39, 243.31, 259.66, 223.12, 245.24, 214.46, 240.43, 203.88, 226.0, 199.07, 235.62, 199.07, 245.24, 199.07, 251.97, 190.42, 249.08, 181.76, 238.5, 172.15, 232.73, 161.57, 229.85, 143.3, 228.89, 132.72, 224.08, 131.75, 234.66, 127.91, 250.05, 125.02, 261.59, 124.06, 269.28, 105.79, 375.07, 104.83, 385.65, 108.67, 398.15, 115.41, 403.92, 117.33, 410.65, 111.56, 414.5, 88.48, 413.54, 73.09, 414.5, 67.32, 413.54, 63.47, 405.84, 65.4, 395.26, 67.32, 387.57, 66.36, 366.41, 61.55, 296.21, 60.59, 274.09, 55.78, 270.24, 50.01, 288.51, 50.01, 314.48, 50.97, 326.02, 50.97, 342.37, 49.05, 353.91, 42.32, 362.57, 25.97, 378.91, 8.66, 387.57, 1.92, 391.42]], "area": 51813.732350000006, "iscrowd": 0, "image_id": 489167, "bbox": [1.92, 80.78, 340.45, 333.72], "category_id": 22, "id": 581826, "split": "val", "sentences": [{"tokens": ["a", "female", "indian", "elephant", "holding", "the", "tail", "of", "another", "elephant"], "raw": "A female Indian elephant holding the tail of another elephant", "sent_id": 48887, "sent": "a female indian elephant holding the tail of another elephant"}, {"tokens": ["an", "elephant", "that", "is", "holding", "the", "tail", "of", "another", "elephant"], "raw": "An elephant that is holding the tail of another elephant.", "sent_id": 48888, "sent": "an elephant that is holding the tail of another elephant"}], "file_name": "COCO_train2014_000000489167_581826.jpg", "ann_id": 581826, "sent_ids": [48887, 48888], "ref_id": 23768}, {"segmentation": [[182.29, 235.15, 174.74, 320.36, 204.94, 330.07, 203.87, 340.85, 220.04, 338.7, 223.28, 326.83, 331.15, 355.96, 453.03, 341.93, 445.48, 255.64, 455.19, 254.56, 456.27, 231.91, 441.17, 226.52, 445.48, 210.34, 349.48, 203.87, 311.73, 214.65, 183.37, 231.91]], "area": 34563.6128, "iscrowd": 0, "image_id": 260395, "bbox": [174.74, 203.87, 281.53, 152.09], "category_id": 6, "id": 167832, "split": "val", "sentences": [{"tokens": ["red", "city", "bus", "on", "route", "193"], "raw": "Red city bus on route 193", "sent_id": 48940, "sent": "red city bus on route 193"}, {"tokens": ["the", "red", "single", "deck", "bus"], "raw": "The red single deck bus.", "sent_id": 48941, "sent": "the red single deck bus"}], "file_name": "COCO_train2014_000000260395_167832.jpg", "ann_id": 167832, "sent_ids": [48940, 48941], "ref_id": 23789}, {"segmentation": [[285.36, 420.03, 276.68, 411.35, 268.0, 368.93, 265.11, 339.05, 241.98, 320.73, 241.01, 290.85, 233.3, 277.35, 213.05, 282.17, 213.05, 267.71, 224.62, 247.46, 225.59, 218.54, 226.55, 193.48, 239.08, 175.16, 258.36, 157.81, 275.72, 142.38, 281.5, 128.89, 274.75, 114.43, 275.72, 98.04, 281.5, 74.9, 294.03, 52.73, 316.21, 50.8, 333.56, 60.44, 348.02, 88.4, 349.95, 111.53, 339.34, 141.42, 339.34, 150.1, 354.77, 166.49, 371.16, 181.91, 380.8, 252.29, 399.11, 304.34, 410.68, 307.24, 422.25, 333.26, 420.32, 384.36, 427.07, 418.1, 370.19, 419.06, 344.16, 336.16, 327.78, 331.34, 335.49, 388.22, 342.24, 420.03, 324.88, 421.96, 282.47, 420.03]], "area": 44672.17555, "iscrowd": 0, "image_id": 226817, "bbox": [213.05, 50.8, 214.02, 371.16], "category_id": 1, "id": 198401, "split": "val", "sentences": [{"tokens": ["male", "child", "in", "a", "short", "sleeved", "yellow", "shirt", "with", "a", "collar"], "raw": "Male child in a short sleeved yellow shirt with a collar.", "sent_id": 48942, "sent": "male child in a short sleeved yellow shirt with a collar"}], "file_name": "COCO_train2014_000000226817_198401.jpg", "ann_id": 198401, "sent_ids": [48942], "ref_id": 23790}, {"segmentation": [[180.8, 209.72, 181.48, 222.7, 183.53, 225.44, 186.94, 238.42, 200.61, 250.71, 419.9, 299.22, 470.45, 266.42, 509.39, 257.54, 521.68, 256.86, 554.47, 257.54, 564.04, 270.52, 566.77, 275.99, 581.12, 259.59, 587.95, 230.9, 577.02, 225.44, 569.5, 215.19, 566.77, 183.08, 459.52, 191.28, 344.07, 204.26, 286.68, 203.58, 212.22, 189.91, 192.41, 187.18, 188.99, 185.81, 178.75, 204.26, 180.11, 215.19]], "area": 30027.981050000002, "iscrowd": 0, "image_id": 473879, "bbox": [178.75, 183.08, 409.2, 116.14], "category_id": 9, "id": 176421, "split": "val", "sentences": [{"tokens": ["the", "blue", "dock", "with", "bikes", "in", "the", "right", "hand", "picture"], "raw": "the blue dock with bikes in the right hand picture", "sent_id": 48945, "sent": "the blue dock with bikes in the right hand picture"}, {"tokens": ["the", "blue", "boat", "nearest", "to", "the", "camera"], "raw": "the blue boat nearest to the camera", "sent_id": 48946, "sent": "the blue boat nearest to the camera"}], "file_name": "COCO_train2014_000000473879_176421.jpg", "ann_id": 176421, "sent_ids": [48945, 48946], "ref_id": 23792}, {"segmentation": [[60.24, 413.38, 43.95, 425.45, 34.9, 432.09, 33.09, 425.45, 31.28, 423.03, 23.43, 422.43, 21.62, 416.4, 25.24, 408.55, 23.43, 398.29, 22.22, 372.34, 24.64, 354.84, 22.83, 348.2, 21.62, 343.37, 21.02, 339.75, 13.78, 322.25, 10.76, 304.15, 10.16, 274.58, 10.16, 258.89, 13.78, 248.03, 24.04, 237.77, 35.5, 219.06, 41.54, 208.8, 42.14, 205.18, 45.62, 192.04, 51.76, 178.88, 58.78, 175.37, 71.07, 179.76, 76.33, 196.43, 70.19, 208.71, 64.92, 216.61, 67.56, 224.51, 68.43, 251.71, 72.82, 264.87, 85.11, 265.74, 87.74, 272.76, 78.96, 281.54, 64.05, 281.54, 59.66, 281.54, 57.9, 298.21, 58.78, 314.0, 59.66, 333.31, 58.78, 338.57, 50.68, 368.81, 48.42, 392.45, 54.05, 399.21, 57.43, 412.73]], "area": 9799.327149999997, "iscrowd": 0, "image_id": 45680, "bbox": [10.16, 175.37, 77.58, 256.72], "category_id": 1, "id": 467918, "split": "val", "sentences": [{"tokens": ["man"], "raw": "Man", "sent_id": 49044, "sent": "man"}, {"tokens": ["the", "person", "in", "the", "white", "shirt"], "raw": "The person in the white shirt.", "sent_id": 49045, "sent": "the person in the white shirt"}], "file_name": "COCO_train2014_000000045680_467918.jpg", "ann_id": 467918, "sent_ids": [49044, 49045], "ref_id": 23831}, {"segmentation": [[34.21, 185.0, 35.17, 338.6, 26.53, 390.44, 16.93, 429.8, 3.49, 506.6, 1.57, 518.12, 21.73, 536.0, 34.21, 492.2, 54.37, 500.84, 63.97, 496.04, 70.69, 482.6, 66.85, 474.92, 50.53, 460.52, 40.93, 453.8, 38.05, 449.96, 57.25, 360.68, 61.09, 324.2, 80.29, 325.16, 95.65, 325.16, 104.29, 304.04, 92.77, 292.52, 76.45, 275.24, 67.81, 222.44, 57.25, 198.44, 47.65, 193.64]], "area": 12026.9952, "iscrowd": 0, "image_id": 210363, "bbox": [1.57, 185.0, 102.72, 351.0], "category_id": 41, "id": 1860489, "split": "val", "sentences": [{"tokens": ["skateboard", "positioned", "upright", "in", "hands", "of", "person", "on", "top", "of", "ramp"], "raw": "skateboard positioned upright in hands of person on top of ramp", "sent_id": 49098, "sent": "skateboard positioned upright in hands of person on top of ramp"}], "file_name": "COCO_train2014_000000210363_1860489.jpg", "ann_id": 1860489, "sent_ids": [49098], "ref_id": 23848}, {"segmentation": [[196.15, 74.78, 198.41, 51.11, 209.68, 26.3, 227.72, 17.29, 253.65, 12.78, 293.1, 39.83, 296.49, 64.63, 297.61, 91.69, 289.72, 127.76, 279.58, 144.67, 263.79, 149.18, 266.05, 190.89, 279.58, 226.97, 338.2, 247.26, 374.27, 242.75, 401.33, 240.5, 420.49, 248.39, 423.87, 261.91, 413.73, 277.7, 382.16, 283.33, 353.98, 283.33, 329.18, 283.33, 308.89, 281.08, 262.67, 294.61, 279.58, 331.81, 344.96, 370.14, 381.03, 379.16, 381.03, 394.94, 268.3, 389.3, 260.41, 410.72, 119.5, 418.61, 126.26, 369.01, 198.41, 278.82, 240.12, 246.13, 248.01, 210.06, 254.77, 192.02, 246.88, 179.62, 218.7, 155.95, 201.79, 140.16, 201.79, 102.96]], "area": 42596.687650000014, "iscrowd": 0, "image_id": 460362, "bbox": [119.5, 12.78, 304.37, 405.83], "category_id": 1, "id": 437790, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "blue", "dress", "serving", "some", "sweets"], "raw": "A  MAN WEARING BLUE DRESS SERVING SOME SWEETS", "sent_id": 49120, "sent": "a man wearing blue dress serving some sweets"}, {"tokens": ["the", "man", "with", "the", "bald", "head"], "raw": "The man with the bald head", "sent_id": 49121, "sent": "the man with the bald head"}], "file_name": "COCO_train2014_000000460362_437790.jpg", "ann_id": 437790, "sent_ids": [49120, 49121], "ref_id": 23856}, {"segmentation": [[254.77, 388.5, 251.31, 348.15, 246.7, 310.11, 245.55, 267.45, 244.4, 231.71, 240.94, 207.51, 225.95, 190.21, 221.34, 175.23, 221.34, 154.48, 216.73, 132.57, 219.03, 109.52, 234.02, 96.84, 236.33, 78.39, 237.48, 55.33, 254.77, 55.33, 270.91, 83.0, 274.37, 94.53, 299.73, 103.75, 320.48, 125.66, 338.93, 141.8, 347.0, 141.8, 355.07, 154.48, 353.91, 169.46, 321.63, 161.39, 295.12, 148.71, 310.11, 190.21, 320.48, 220.19, 312.41, 299.73, 317.02, 355.07, 307.8, 408.09, 295.12, 418.47, 266.3, 409.25, 231.71, 409.25]], "area": 25672.165450000004, "iscrowd": 0, "image_id": 577246, "bbox": [216.73, 55.33, 138.34, 363.14], "category_id": 1, "id": 461821, "split": "val", "sentences": [{"tokens": ["a", "blonde", "woman", "wearing", "a", "blue", ",", "red", ",", "and", "white", "ski", "suit", "and", "orange", "cap"], "raw": "a blonde woman wearing a blue, red, and white ski suit and orange cap", "sent_id": 49144, "sent": "a blonde woman wearing a blue , red , and white ski suit and orange cap"}, {"tokens": ["a", "woman", "on", "skies"], "raw": "A woman on skies", "sent_id": 49145, "sent": "a woman on skies"}], "file_name": "COCO_train2014_000000577246_461821.jpg", "ann_id": 461821, "sent_ids": [49144, 49145], "ref_id": 23865}, {"segmentation": [[121.75, 121.86, 196.16, 72.58, 242.54, 122.83, 258.97, 151.82, 311.15, 178.87, 309.21, 200.13, 280.22, 219.46, 261.87, 274.53, 229.98, 318.02, 199.06, 329.61, 206.79, 340.24, 280.22, 341.21, 285.06, 315.12, 295.69, 287.1, 322.74, 257.14, 445.46, 234.92, 467.69, 223.32, 521.8, 136.35, 534.36, 120.89, 628.09, 157.61, 628.09, 196.26, 610.7, 238.78, 635.82, 337.34, 616.49, 372.13, 568.18, 360.53, 557.55, 401.12, 502.47, 418.51, 432.9, 397.25, 419.37, 358.6, 358.49, 334.44, 264.76, 355.7, 161.37, 340.24, 133.35, 374.06, 87.93, 397.25, 24.16, 381.79, 2.9, 361.5, 10.63, 259.07, 61.84, 236.85, 108.22, 233.95, 126.58, 229.12, 133.35, 214.62, 122.72, 190.47, 129.48, 143.12]], "area": 109524.52640000002, "iscrowd": 0, "image_id": 268428, "bbox": [2.9, 72.58, 632.92, 345.93], "category_id": 4, "id": 149598, "split": "val", "sentences": [{"tokens": ["front", "most", "motorcycle"], "raw": "front most motorcycle", "sent_id": 49228, "sent": "front most motorcycle"}, {"tokens": ["a", "motor", "cycle", "in", "front", "carrying", "a", "man", "and", "a", "lady"], "raw": "A motor cycle in front carrying a man and a lady", "sent_id": 49229, "sent": "a motor cycle in front carrying a man and a lady"}], "file_name": "COCO_train2014_000000268428_149598.jpg", "ann_id": 149598, "sent_ids": [49228, 49229], "ref_id": 23899}, {"segmentation": [[198.69, 284.79, 217.17, 253.99, 251.04, 206.77, 262.34, 229.36, 266.44, 211.9, 271.58, 159.55, 260.28, 133.89, 239.75, 110.28, 216.14, 94.88, 196.64, 108.22, 186.37, 140.05, 157.63, 160.58, 130.94, 167.76, 162.76, 186.24, 187.4, 169.82, 198.69, 164.68, 188.43, 217.04, 149.42, 259.13, 132.99, 285.82, 156.6, 291.97, 183.29, 264.26, 198.69, 244.75, 178.16, 281.71, 174.05, 288.89]], "area": 13400.0331, "iscrowd": 0, "image_id": 56616, "bbox": [130.94, 94.88, 140.64, 197.09], "category_id": 1, "id": 427367, "split": "val", "sentences": [{"tokens": ["a", "man", "skiing", "wearing", "gold", "ski", "goggles", "and", "executing", "a", "turn"], "raw": "A man skiing wearing gold ski goggles and executing a turn.", "sent_id": 49236, "sent": "a man skiing wearing gold ski goggles and executing a turn"}, {"tokens": ["a", "skier", "on", "the", "top", "portion", "of", "the", "card"], "raw": "a skier on the top portion of the card", "sent_id": 49237, "sent": "a skier on the top portion of the card"}], "file_name": "COCO_train2014_000000056616_427367.jpg", "ann_id": 427367, "sent_ids": [49236, 49237], "ref_id": 23903}, {"segmentation": [[458.28, 326.25, 481.1, 349.07, 506.77, 365.24, 523.88, 369.99, 530.54, 373.79, 538.14, 388.06, 589.49, 402.18, 609.45, 413.59, 611.35, 421.2, 616.11, 425.0, 494.41, 425.0, 491.55, 416.44, 494.41, 405.98, 494.41, 398.38, 478.24, 382.21, 462.08, 365.1, 437.36, 328.97, 434.51, 327.07, 442.11, 310.91, 462.08, 330.87]], "area": 6255.54325, "iscrowd": 0, "image_id": 8300, "bbox": [434.51, 310.91, 181.6, 114.09], "category_id": 25, "id": 598357, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "standing", "behind", "three", "other", "giraffes", ",", "facing", "the", "opposite", "direction"], "raw": "A giraffe standing behind three other giraffes, facing the opposite direction.", "sent_id": 49242, "sent": "a giraffe standing behind three other giraffes , facing the opposite direction"}], "file_name": "COCO_train2014_000000008300_598357.jpg", "ann_id": 598357, "sent_ids": [49242], "ref_id": 23906}, {"segmentation": [[201.04, 417.33, 202.0, 388.75, 224.86, 309.66, 235.34, 270.6, 259.16, 219.15, 277.27, 194.37, 313.47, 189.61, 340.15, 241.06, 348.73, 262.02, 344.92, 302.99, 333.48, 360.16, 334.44, 377.31, 318.24, 418.28]], "area": 24085.559249999995, "iscrowd": 0, "image_id": 513748, "bbox": [201.04, 189.61, 147.69, 228.67], "category_id": 42, "id": 646942, "split": "val", "sentences": [{"tokens": ["a", "skate", "board", "which", "is", "held", "by", "a", "lady"], "raw": "A skate board which is held by a lady", "sent_id": 49253, "sent": "a skate board which is held by a lady"}, {"tokens": ["surfboard", "with", "a", "black", "and", "yellow", "design", "on", "it"], "raw": "Surfboard with a black and yellow design on it.", "sent_id": 49254, "sent": "surfboard with a black and yellow design on it"}], "file_name": "COCO_train2014_000000513748_646942.jpg", "ann_id": 646942, "sent_ids": [49253, 49254], "ref_id": 23910}, {"segmentation": [[567.95, 223.6, 565.73, 212.51, 564.25, 206.59, 562.77, 199.93, 561.29, 198.45, 556.85, 194.01, 550.93, 192.53, 544.27, 190.31, 534.65, 189.57, 528.73, 189.57, 521.33, 190.31, 515.41, 194.01, 510.23, 197.71, 503.57, 204.37, 499.13, 211.03, 496.17, 215.46, 488.03, 218.42, 481.37, 221.38, 477.67, 228.78, 472.49, 239.14, 469.53, 248.02, 468.05, 259.86, 465.09, 268.0, 461.39, 279.1, 457.69, 287.24, 452.51, 296.86, 451.03, 305.74, 445.11, 322.76, 441.41, 358.28, 430.31, 382.7, 431.79, 392.32, 446.59, 407.86, 468.05, 413.78, 495.43, 424.88, 514.67, 433.02, 542.05, 450.77, 556.11, 465.57, 573.13, 487.03, 576.83, 499.61, 585.71, 488.51, 589.41, 476.67, 591.63, 466.31, 591.63, 460.39, 583.49, 455.95, 570.91, 450.03, 546.49, 442.64, 532.43, 438.2, 530.95, 433.76, 513.19, 424.14, 501.35, 418.22, 502.09, 412.3, 508.01, 409.34, 516.89, 414.52, 537.61, 418.96, 553.89, 424.14, 569.43, 428.58, 579.05, 430.06, 585.71, 430.06, 589.41, 420.44, 589.41, 413.78, 589.41, 409.34, 584.97, 406.38, 576.09, 405.64, 560.55, 403.42, 559.81, 398.98, 557.59, 393.8, 555.37, 392.32, 549.45, 390.84, 545.01, 390.1, 542.79, 373.9, 547.23, 361.32, 546.49, 350.22, 546.49, 342.08, 547.97, 333.94, 550.19, 322.84, 553.15, 313.96, 554.63, 306.56, 554.63, 298.42, 554.63, 289.54, 553.15, 285.1, 550.19, 283.62, 546.49, 279.92, 542.79, 278.44, 540.57, 276.96, 544.73, 271.13, 546.19, 269.18, 553.52, 270.64, 558.89, 269.67, 563.28, 268.69, 564.74, 266.74, 567.19, 261.85, 567.19, 259.9, 567.67, 255.51, 569.63, 253.55, 569.63, 251.11, 568.65, 249.16, 568.16, 248.18, 569.63, 246.72, 571.09, 244.28, 571.09, 241.84, 569.14, 238.91, 567.67, 237.93, 566.7, 233.05, 566.7, 231.1, 566.7, 229.14, 566.7, 226.22]], "area": 24355.64295000001, "iscrowd": 0, "image_id": 104344, "bbox": [430.31, 189.57, 161.32, 310.04], "category_id": 1, "id": 541152, "split": "val", "sentences": [{"tokens": ["a", "women", "sitting", "and", "taking", "notes"], "raw": "A women sitting and taking notes .", "sent_id": 49269, "sent": "a women sitting and taking notes"}, {"tokens": ["a", "woman", "in", "a", "green", "shirt", "and", "ponytail", "is", "behind", "the", "man", "posing"], "raw": "A woman in a green shirt and ponytail is behind the man posing", "sent_id": 49270, "sent": "a woman in a green shirt and ponytail is behind the man posing"}], "file_name": "COCO_train2014_000000104344_541152.jpg", "ann_id": 541152, "sent_ids": [49269, 49270], "ref_id": 23916}, {"segmentation": [[146.04, 534.25, 177.54, 532.82, 219.06, 534.25, 280.63, 519.94, 289.22, 508.48, 287.79, 489.87, 293.51, 474.12, 304.97, 465.53, 356.51, 465.53, 390.87, 445.48, 413.78, 428.3, 439.55, 431.17, 451.0, 233.58, 448.14, 219.26, 423.8, 207.81, 406.62, 206.38, 390.87, 207.81, 356.51, 200.65, 337.9, 187.77, 327.87, 176.31, 317.85, 166.29, 312.13, 150.54, 293.51, 136.22, 277.76, 136.22, 274.9, 136.22, 250.56, 119.04, 249.13, 119.04, 260.58, 110.45, 254.85, 78.95, 254.85, 61.77, 209.04, 47.45, 197.58, 41.73, 178.97, 47.45, 168.95, 57.48, 168.95, 58.91, 161.79, 43.16, 160.36, 61.77, 147.47, 67.5, 143.18, 78.95, 137.45, 83.25, 137.45, 86.11, 131.72, 96.13, 134.59, 104.72, 143.18, 106.16, 140.31, 126.2, 138.88, 133.36, 140.31, 140.52, 134.59, 161.99, 143.18, 163.43, 150.34, 170.58, 154.63, 177.74, 157.49, 184.9, 163.22, 190.63, 166.09, 200.65, 173.24, 194.92, 191.86, 190.63, 191.86, 203.52, 177.54, 219.26, 144.61, 226.42, 154.63, 236.45, 111.68, 246.47, 91.63, 252.2, 63.0, 276.54, 58.7, 295.15, 42.95, 299.44, 28.64, 319.49, 30.07, 330.94, 14.32, 339.53, 18.61, 361.01, 14.32, 393.94, 21.48, 416.85, 38.66, 431.17, 68.72, 434.03, 104.52, 422.58, 110.25, 418.28, 127.43, 395.37, 148.9, 434.03, 161.79, 459.8, 164.65, 471.26, 128.86, 489.87, 94.5, 501.32, 98.79, 514.21, 114.54, 521.37, 140.31, 524.23, 146.04, 531.39]], "area": 126162.31955000006, "iscrowd": 0, "image_id": 20188, "bbox": [14.32, 41.73, 436.68, 492.52], "category_id": 1, "id": 426803, "split": "val", "sentences": [{"tokens": ["a", "man", "holding", "a", "purple", "hat", "sitting", "on", "a", "skateboard"], "raw": "A man holding a purple hat sitting on a skateboard.", "sent_id": 49275, "sent": "a man holding a purple hat sitting on a skateboard"}, {"tokens": ["man", "sitting", "on", "skateboard"], "raw": "man sitting on skateboard", "sent_id": 49276, "sent": "man sitting on skateboard"}], "file_name": "COCO_train2014_000000020188_426803.jpg", "ann_id": 426803, "sent_ids": [49275, 49276], "ref_id": 23919}, {"segmentation": [[138.2, 215.54, 122.47, 143.63, 110.11, 155.99, 105.62, 162.73, 98.88, 155.99, 104.49, 133.52, 104.49, 113.3, 104.49, 88.58, 111.24, 86.33, 113.48, 103.18, 117.98, 97.57, 117.98, 85.21, 123.6, 89.7, 128.09, 103.18, 139.33, 141.39, 165.17, 211.05, 175.28, 230.15, 188.76, 264.98, 194.38, 308.8, 183.15, 341.39, 189.89, 413.3, 206.74, 457.12, 183.15, 462.73, 178.65, 461.61, 174.16, 441.39, 170.79, 378.46, 159.55, 368.35, 157.3, 406.55, 157.3, 458.24, 141.57, 462.73, 137.08, 458.24, 125.84, 443.63, 135.96, 408.8, 119.1, 306.55, 119.1, 252.62]], "area": 17174.3446, "iscrowd": 0, "image_id": 490062, "bbox": [98.88, 85.21, 107.86, 377.52], "category_id": 25, "id": 594469, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "with", "its", "head", "in", "the", "sun"], "raw": "a giraffe with its head in the sun", "sent_id": 49378, "sent": "a giraffe with its head in the sun"}, {"tokens": ["the", "two", "giraffe", "standing", "up"], "raw": "The two giraffe standing up.", "sent_id": 49379, "sent": "the two giraffe standing up"}], "file_name": "COCO_train2014_000000490062_594469.jpg", "ann_id": 594469, "sent_ids": [49378, 49379], "ref_id": 23961}, {"segmentation": [[467.37, 120.42, 470.31, 115.52, 469.33, 110.61, 467.7, 107.34, 464.75, 107.02, 463.45, 112.25, 463.12, 117.48, 466.06, 125.32, 466.39, 131.86, 460.18, 141.67, 458.87, 143.63, 457.56, 153.77, 454.29, 161.29, 448.41, 163.9, 443.5, 167.83, 443.18, 177.96, 441.87, 182.87, 435.98, 188.75, 438.93, 191.04, 445.14, 197.25, 453.31, 204.77, 457.56, 213.27, 462.14, 220.79, 462.47, 222.1, 466.39, 226.02, 479.79, 232.56, 492.87, 237.79, 495.49, 244.33, 497.45, 249.56, 499.41, 242.7, 497.78, 218.18, 499.08, 169.79, 486.66, 177.03, 483.72, 171.8, 490.58, 162.65, 494.51, 157.74, 497.78, 153.49, 494.18, 149.24, 490.58, 143.03, 487.97, 138.13, 483.06, 136.49, 480.45, 138.78, 474.89, 143.03, 470.64, 146.95, 470.64, 143.03, 470.64, 136.82, 469.33, 131.59, 468.02, 125.05, 467.04, 122.76, 466.39, 121.78]], "area": 4245.391899999997, "iscrowd": 0, "image_id": 254176, "bbox": [435.98, 107.02, 63.43, 142.54], "category_id": 4, "id": 1360583, "split": "val", "sentences": [{"tokens": ["double", "headlight", "on", "motorcycle", "over", "the", "right", "side", "of", "teddy", "bear"], "raw": "double headlight on motorcycle over the right side of teddy bear.", "sent_id": 49445, "sent": "double headlight on motorcycle over the right side of teddy bear"}, {"tokens": ["a", "black", "motor", "bike", "with", "two", "head", "lights"], "raw": "A black motor bike with two head lights.", "sent_id": 49446, "sent": "a black motor bike with two head lights"}], "file_name": "COCO_train2014_000000254176_1360583.jpg", "ann_id": 1360583, "sent_ids": [49445, 49446], "ref_id": 23982}, {"segmentation": [[371.39, 269.58, 371.39, 269.58, 404.08, 253.91, 437.45, 262.77, 459.92, 281.16, 461.28, 293.41, 475.59, 315.89, 470.14, 347.9, 469.46, 347.9, 464.69, 357.43, 446.98, 369.69, 444.26, 371.73, 419.74, 376.5, 397.95, 366.97, 383.65, 351.98, 377.52, 322.7, 359.81, 328.83, 349.6, 309.76, 357.09, 294.09, 371.39, 272.98], [285.58, 247.78, 285.58, 247.78, 293.75, 247.78, 291.03, 258.0, 312.82, 287.97, 346.19, 332.23, 342.78, 339.04, 342.1, 339.04, 340.06, 333.59, 340.06, 333.59, 330.53, 332.23, 329.84, 331.55, 320.31, 319.29, 325.08, 315.21, 289.66, 268.22, 289.66, 268.22, 283.53, 272.3, 281.49, 279.11, 297.84, 290.69, 306.01, 317.93, 302.6, 328.15, 286.26, 345.17, 255.61, 356.07, 246.76, 352.66, 235.18, 347.9, 234.5, 347.9, 219.52, 328.15, 216.79, 303.63, 228.37, 285.92, 244.03, 275.71, 244.72, 275.71, 252.89, 273.66, 270.59, 272.3, 270.59, 272.3], [278.77, 237.57, 285.58, 237.57, 291.03, 236.21, 296.47, 219.18, 308.73, 224.63, 316.22, 229.4, 319.63, 224.63, 303.28, 213.05, 324.4, 206.24, 303.97, 204.88, 295.11, 202.84, 295.11, 202.84, 292.39, 208.97, 295.79, 212.37, 285.58, 225.31, 284.9, 228.03, 282.85, 234.84, 282.85, 234.84]], "area": 17401.22025, "iscrowd": 0, "image_id": 380820, "bbox": [216.79, 202.84, 258.8, 173.66], "category_id": 2, "id": 128174, "split": "val", "sentences": [{"tokens": ["the", "bicycle", "the", "zebra", "is", "on"], "raw": "the bicycle the zebra is on", "sent_id": 49489, "sent": "the bicycle the zebra is on"}, {"tokens": ["the", "bike", "the", "zebra", "is", "riding"], "raw": "The bike the zebra is riding.", "sent_id": 49490, "sent": "the bike the zebra is riding"}], "file_name": "COCO_train2014_000000380820_128174.jpg", "ann_id": 128174, "sent_ids": [49489, 49490], "ref_id": 23999}, {"segmentation": [[339.62, 45.46, 349.24, 56.16, 353.52, 72.2, 348.18, 89.85, 341.76, 117.13, 339.62, 153.5, 342.29, 179.7, 343.9, 195.21, 359.41, 234.79, 379.73, 234.79, 394.17, 162.05, 377.59, 101.62, 372.78, 83.43, 367.96, 72.74, 367.96, 51.34, 372.78, 42.79, 365.82, 37.44, 361.55, 35.3, 352.99, 35.3, 348.18, 33.16]], "area": 7076.0271999999995, "iscrowd": 0, "image_id": 205223, "bbox": [339.62, 33.16, 54.55, 201.63], "category_id": 32, "id": 296455, "split": "val", "sentences": [{"tokens": ["second", "tie", "from", "right"], "raw": "second tie from right", "sent_id": 49518, "sent": "second tie from right"}], "file_name": "COCO_train2014_000000205223_296455.jpg", "ann_id": 296455, "sent_ids": [49518], "ref_id": 24010}, {"segmentation": [[195.01, 286.93, 212.79, 283.37, 280.34, 277.15, 280.34, 284.26, 285.68, 287.82, 288.34, 291.37, 301.68, 292.26, 306.12, 287.82, 309.68, 279.82, 314.12, 272.71, 392.34, 259.37, 406.57, 254.93, 413.68, 258.49, 427.9, 267.37, 431.46, 266.49, 438.57, 251.37, 438.57, 230.93, 437.68, 227.37, 422.57, 212.26, 406.57, 137.6, 401.23, 139.37, 387.9, 142.04, 363.9, 142.04, 164.79, 110.04, 161.23, 110.04, 90.12, 120.71, 86.57, 128.71, 78.57, 286.93, 86.57, 285.15, 100.79, 284.26, 154.12, 291.37, 173.68, 290.49, 189.68, 286.93]], "area": 51920.96839999999, "iscrowd": 0, "image_id": 256965, "bbox": [78.57, 110.04, 360.0, 182.22], "category_id": 8, "id": 399177, "split": "val", "sentences": [{"tokens": ["a", "truck", "with", "the", "side", "doors", "open", "parked", "beside", "pop", "up", "tent"], "raw": "a truck with the side doors open parked beside  pop up tent.", "sent_id": 49552, "sent": "a truck with the side doors open parked beside pop up tent"}, {"tokens": ["big", "white", "truck"], "raw": "big white truck", "sent_id": 49553, "sent": "big white truck"}], "file_name": "COCO_train2014_000000256965_399177.jpg", "ann_id": 399177, "sent_ids": [49552, 49553], "ref_id": 24023}, {"segmentation": [[46.97, 101.9, 58.34, 103.36, 68.25, 100.8, 76.32, 100.43, 84.03, 96.39, 84.03, 91.62, 86.23, 89.42, 84.4, 86.48, 80.73, 85.75, 73.75, 85.38, 73.75, 84.28, 71.55, 78.41, 68.98, 77.31, 68.98, 72.54, 68.98, 70.7, 63.48, 71.07, 69.35, 66.67, 67.52, 62.63, 68.98, 59.7, 75.96, 54.92, 85.86, 53.46, 93.57, 58.96, 95.41, 74.37, 110.08, 77.31, 123.3, 88.69, 129.53, 94.92, 140.54, 116.58, 140.91, 119.88, 142.74, 123.91, 145.68, 125.38, 146.78, 137.13, 143.11, 141.53, 142.38, 159.14, 138.34, 174.19, 146.41, 178.23, 154.85, 183.36, 163.66, 189.24, 159.26, 196.57, 170.63, 208.68, 172.1, 217.49, 158.52, 220.79, 146.41, 220.43, 149.35, 210.52, 148.62, 209.05, 143.85, 211.99, 141.64, 210.15, 140.91, 197.31, 126.96, 184.1, 101.28, 171.25, 105.68, 144.46, 110.82, 136.39, 103.85, 129.79, 96.87, 116.21, 92.84, 108.87, 89.17, 112.17, 82.93, 109.24, 72.29, 112.17, 56.87, 109.24, 52.84, 109.24, 46.6, 113.64, 41.83, 109.97, 42.93, 106.3, 47.7, 110.7, 51.0, 105.57, 45.5, 101.9]], "area": 6150.783100000001, "iscrowd": 0, "image_id": 401982, "bbox": [41.83, 53.46, 130.27, 167.33], "category_id": 1, "id": 494999, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "in", "a", "batting", "helmet", "about", "to", "run"], "raw": "a baseball player in a batting helmet about to run", "sent_id": 49558, "sent": "a baseball player in a batting helmet about to run"}, {"tokens": ["a", "ball", "player", "running"], "raw": "A ball player running.", "sent_id": 49559, "sent": "a ball player running"}], "file_name": "COCO_train2014_000000401982_494999.jpg", "ann_id": 494999, "sent_ids": [49558, 49559], "ref_id": 24026}, {"segmentation": [[343.44, 247.89, 380.7, 225.79, 368.7, 182.84, 366.81, 154.42, 373.75, 139.26, 378.17, 125.36, 395.23, 126.0, 416.07, 142.42, 414.81, 150.0, 417.96, 156.94, 414.81, 186.63, 429.96, 202.42, 440.7, 233.37, 450.17, 250.42, 459.02, 261.79, 448.28, 263.05, 426.81, 253.58, 426.81, 237.15, 417.33, 221.37, 416.07, 213.15, 403.44, 205.58, 395.23, 240.94, 355.44, 258.0, 351.02, 265.58, 345.96, 277.58, 339.65, 277.58]], "area": 6300.58405, "iscrowd": 0, "image_id": 119693, "bbox": [339.65, 125.36, 119.37, 152.22], "category_id": 1, "id": 557545, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "wearing", "red", "and", "white", "swinging", "a", "bat", "with", "a", "red", "helmet", "on", "his", "head"], "raw": "A BASEBALL PLAYER WEARING RED AND WHITE SWINGING A BAT WITH A RED HELMET ON HIS HEAD", "sent_id": 49607, "sent": "a baseball player wearing red and white swinging a bat with a red helmet on his head"}, {"tokens": ["a", "baseball", "player", "swinging", "the", "bat"], "raw": "A baseball player swinging the bat.", "sent_id": 49608, "sent": "a baseball player swinging the bat"}], "file_name": "COCO_train2014_000000119693_557545.jpg", "ann_id": 557545, "sent_ids": [49607, 49608], "ref_id": 24046}, {"segmentation": [[304.53, 365.46, 323.86, 343.03, 334.69, 305.14, 346.29, 277.29, 337.01, 239.4, 342.42, 220.07, 331.59, 198.41, 335.46, 189.9, 347.83, 189.13, 356.34, 193.0, 358.66, 210.01, 382.64, 205.37, 412.02, 216.97, 453.79, 225.48, 453.01, 240.17, 415.89, 231.67, 384.18, 227.03, 393.46, 265.69, 406.61, 282.71, 412.8, 317.51, 420.53, 329.11, 410.48, 343.03, 405.06, 341.48, 401.97, 322.92, 395.78, 308.23, 382.64, 297.4, 371.81, 297.4, 350.15, 324.47, 340.87, 355.41, 329.27, 370.87, 306.07, 375.51]], "area": 8776.4324, "iscrowd": 0, "image_id": 349686, "bbox": [304.53, 189.13, 149.26, 186.38], "category_id": 1, "id": 453334, "split": "val", "sentences": [{"tokens": ["a", "batter", "hitting", "a", "baseball"], "raw": "A batter hitting a baseball.", "sent_id": 49624, "sent": "a batter hitting a baseball"}, {"tokens": ["a", "baseball", "player", "swinging", "at", "bat"], "raw": "A baseball player swinging at bat.", "sent_id": 49625, "sent": "a baseball player swinging at bat"}], "file_name": "COCO_train2014_000000349686_453334.jpg", "ann_id": 453334, "sent_ids": [49624, 49625], "ref_id": 24051}, {"segmentation": [[392.15, 337.18, 433.97, 310.07, 435.8, 307.31, 446.83, 303.18, 458.32, 301.34, 463.83, 282.5, 470.73, 269.17, 479.46, 264.58, 487.73, 268.25, 493.7, 271.01, 498.76, 274.69, 499.22, 278.36, 496.0, 294.44, 493.24, 306.39, 506.11, 310.99, 506.11, 316.5, 509.79, 327.07, 510.71, 353.72, 511.62, 360.61, 503.35, 405.65, 498.76, 414.38, 490.49, 416.22, 488.65, 414.38, 487.27, 408.86, 472.57, 415.76, 467.05, 439.65, 462.46, 452.06, 457.86, 460.33, 458.32, 468.6, 453.73, 474.57, 456.02, 478.71, 455.56, 480.0, 437.18, 480.0, 437.18, 473.19, 450.05, 436.43, 452.35, 422.65, 456.48, 410.7, 447.75, 426.78, 439.02, 443.79, 434.89, 464.0, 432.59, 474.57, 431.67, 479.17, 414.67, 479.63, 413.29, 477.79, 415.13, 473.65, 419.72, 452.98, 424.32, 437.35, 432.13, 412.54, 435.8, 393.24, 433.51, 390.02, 433.05, 383.59, 437.18, 372.56, 436.26, 360.15, 441.78, 349.59, 440.4, 341.31, 441.78, 335.8, 441.78, 332.58, 437.64, 331.21, 409.61, 354.64, 393.07, 361.07, 386.64, 365.21, 383.88, 370.72, 377.45, 368.43, 376.99, 362.91, 375.61, 361.07, 380.66, 351.42, 384.34, 346.83, 387.1, 344.53, 388.02, 339.48]], "area": 12841.847700000006, "iscrowd": 0, "image_id": 546078, "bbox": [375.61, 264.58, 136.01, 215.42], "category_id": 1, "id": 2161438, "split": "val", "sentences": [{"tokens": ["girl", "with", "green", "jacket"], "raw": "Girl with green jacket.", "sent_id": 49652, "sent": "girl with green jacket"}, {"tokens": ["the", "girl", "exiting", "the", "bus", "in", "green", "jacket"], "raw": "The girl exiting the bus in green jacket", "sent_id": 49653, "sent": "the girl exiting the bus in green jacket"}], "file_name": "COCO_train2014_000000546078_2161438.jpg", "ann_id": 2161438, "sent_ids": [49652, 49653], "ref_id": 24062}, {"segmentation": [[317.22, 153.84, 319.03, 174.61, 322.19, 199.0, 319.93, 211.19, 335.74, 227.45, 338.9, 247.77, 337.09, 279.83, 318.58, 284.35, 313.61, 287.06, 313.16, 293.38, 320.39, 299.25, 335.74, 304.22, 349.74, 305.12, 359.22, 304.22, 365.54, 301.51, 367.35, 297.9, 368.25, 296.54, 369.16, 292.48, 366.0, 287.96, 362.84, 286.15, 360.58, 284.35, 346.58, 282.54, 344.32, 280.73, 347.93, 228.8, 352.45, 221.58, 361.48, 217.96, 371.87, 197.64, 370.96, 159.26, 369.16, 138.03, 318.58, 137.13, 317.68, 145.71]], "area": 5735.157700000002, "iscrowd": 0, "image_id": 122259, "bbox": [313.16, 137.13, 58.71, 167.99], "category_id": 46, "id": 663538, "split": "val", "sentences": [{"tokens": ["a", "wine", "glass", "to", "the", "back", "right", "of", "another", "glass"], "raw": "a wine glass to the back right of another glass", "sent_id": 49704, "sent": "a wine glass to the back right of another glass"}, {"tokens": ["glass", "on", "right", "closet", "to", "person"], "raw": "glass on right closet to person", "sent_id": 49705, "sent": "glass on right closet to person"}], "file_name": "COCO_train2014_000000122259_663538.jpg", "ann_id": 663538, "sent_ids": [49704, 49705], "ref_id": 24080}, {"segmentation": [[167.13, 377.03, 250.69, 333.26, 283.52, 285.51, 305.41, 285.51, 334.25, 256.66, 378.03, 231.79, 399.91, 202.94, 420.8, 184.04, 431.75, 177.08, 455.62, 167.13, 488.45, 152.21, 523.27, 131.31, 532.22, 114.4, 540.18, 102.46, 542.17, 89.53, 535.21, 71.63, 520.28, 56.7, 513.32, 47.75, 502.38, 50.74, 447.66, 77.59, 350.17, 130.32, 265.61, 194.98, 150.22, 270.59, 84.56, 300.43, 37.8, 322.32, 12.93, 345.2, 7.96, 371.06, 7.96, 376.04, 154.19, 375.04]], "area": 51520.70135000001, "iscrowd": 0, "image_id": 265235, "bbox": [7.96, 47.75, 534.21, 329.28], "category_id": 61, "id": 1928111, "split": "val", "sentences": [{"tokens": ["a", "cake", "made", "of", "cupcakes", "shaped", "like", "a", "baseball", "bat"], "raw": "A cake made of cupcakes shaped like a baseball bat.", "sent_id": 49710, "sent": "a cake made of cupcakes shaped like a baseball bat"}, {"tokens": ["a", "cupcake", "cake", "made", "into", "a", "baseball", "bat"], "raw": "A cupcake cake made into a baseball bat.", "sent_id": 49711, "sent": "a cupcake cake made into a baseball bat"}], "file_name": "COCO_train2014_000000265235_1928111.jpg", "ann_id": 1928111, "sent_ids": [49710, 49711], "ref_id": 24083}, {"segmentation": [[46.37, 285.9, 35.01, 308.33, 23.37, 320.54, 25.36, 310.03, 23.09, 296.4, 19.68, 286.75, 15.14, 274.25, 10.31, 265.45, 4.91, 249.83, 0.65, 242.45, 0.0, 216.89, 0.0, 169.75, 0.0, 128.86, 4.91, 122.89, 37.57, 89.38, 51.39, 76.83, 65.26, 71.02, 78.93, 67.65, 87.93, 60.34, 100.67, 59.41, 105.73, 56.22, 117.9, 40.67, 132.14, 21.37, 141.51, 16.88, 147.69, 16.69, 156.12, 17.81, 163.43, 23.06, 172.24, 31.68, 173.17, 45.17, 175.8, 57.72, 169.99, 68.77, 168.11, 87.13, 158.37, 92.19, 153.87, 94.25, 161.74, 121.61, 177.67, 150.09, 180.1, 155.14, 174.86, 165.26, 169.61, 167.51, 156.5, 165.26, 152.19, 159.27, 151.25, 160.2, 152.56, 173.13, 149.0, 180.06, 142.63, 181.0, 133.64, 182.12, 134.39, 186.81, 130.08, 186.62, 126.9, 183.25, 126.71, 179.69, 126.71, 177.44, 129.52, 163.2, 119.59, 158.7, 113.59, 147.84, 111.72, 148.77, 103.29, 153.08, 94.67, 154.21, 89.8, 156.27, 81.56, 159.27, 75.56, 167.51, 74.62, 169.76, 71.63, 183.81, 66.76, 187.93, 62.82, 189.8, 60.76, 198.42, 63.95, 207.04, 72.94, 226.53, 83.99, 240.95, 87.55, 246.57, 82.87, 249.95, 60.01, 261.37, 50.64, 275.43]], "area": 25404.838699999993, "iscrowd": 0, "image_id": 15190, "bbox": [0.0, 16.69, 180.1, 303.85], "category_id": 1, "id": 1724965, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "pink", "tank", "top"], "raw": "A woman in a pink tank top.", "sent_id": 49752, "sent": "a woman in a pink tank top"}, {"tokens": ["a", "woman", "in", "a", "pink", "tank", "top", "and", "khaki", "shorts"], "raw": "A woman in a pink tank top and khaki shorts.", "sent_id": 49753, "sent": "a woman in a pink tank top and khaki shorts"}], "file_name": "COCO_train2014_000000015190_1724965.jpg", "ann_id": 1724965, "sent_ids": [49752, 49753], "ref_id": 24103}, {"segmentation": [[8.56, 2.57, 30.82, 28.25, 61.64, 74.49, 68.49, 84.76, 101.03, 76.2, 116.44, 72.77, 133.56, 91.61, 138.7, 95.03, 123.29, 103.6, 104.45, 112.16, 83.9, 129.28, 73.63, 148.12, 39.38, 137.84, 22.26, 115.58, 35.96, 86.47, 20.55, 45.38, 5.14, 31.68, 3.42, 14.55], [152.4, 28.25, 167.81, 14.55, 203.77, 17.98, 220.89, 23.12, 212.33, 31.68, 188.36, 26.54, 184.93, 40.24, 167.81, 33.39, 148.97, 28.25]], "area": 7525.168199999999, "iscrowd": 0, "image_id": 581670, "bbox": [3.42, 2.57, 217.47, 145.55], "category_id": 1, "id": 558166, "split": "val", "sentences": [{"tokens": ["a", "hand", "holding", "a", "hamburg"], "raw": "A hand holding A hamburg", "sent_id": 49771, "sent": "a hand holding a hamburg"}, {"tokens": ["a", "man", "'", "s", "hand", "grabbing", "food"], "raw": "A man's hand grabbing food.", "sent_id": 49772, "sent": "a man ' s hand grabbing food"}], "file_name": "COCO_train2014_000000581670_558166.jpg", "ann_id": 558166, "sent_ids": [49771, 49772], "ref_id": 24109}, {"segmentation": [[314.19, 102.62, 250.0, 2.96, 335.3, 1.27, 417.23, 2.96, 424.83, 2.96, 425.68, 10.56, 428.21, 15.63, 429.9, 20.69, 429.9, 27.45]], "area": 10468.03575, "iscrowd": 0, "image_id": 63238, "bbox": [250.0, 1.27, 179.9, 101.35], "category_id": 54, "id": 311308, "split": "val", "sentences": [{"tokens": ["sandwich", "on", "white", "bread"], "raw": "sandwich on white bread", "sent_id": 49775, "sent": "sandwich on white bread"}], "file_name": "COCO_train2014_000000063238_311308.jpg", "ann_id": 311308, "sent_ids": [49775], "ref_id": 24111}, {"segmentation": [[42.42, 350.37, 0.0, 355.64, 0.0, 403.04, 0.0, 428.0, 333.27, 428.0, 343.22, 418.84, 364.29, 417.08, 380.09, 417.67, 384.77, 420.6, 397.06, 427.03, 408.76, 428.0, 450.31, 428.0, 515.27, 428.0, 524.64, 392.5, 529.32, 336.91, 510.59, 336.91, 508.25, 338.08, 498.3, 335.15, 498.3, 335.15, 483.09, 335.15, 193.4, 343.93, 153.02, 346.86, 35.98, 346.86]], "area": 44381.5448, "iscrowd": 0, "image_id": 513221, "bbox": [0.0, 335.15, 529.32, 92.85], "category_id": 67, "id": 1622694, "split": "val", "sentences": [{"tokens": ["the", "table", "cloth", "that", "is", "draped", "over", "the", "edge", "of", "the", "table", "in", "front", "of", "the", "cake", ".", "it", "had", "paw", "-", "prints", "on", "it", "and", "blue", "/", "green", "/", "orange", "stripes"], "raw": "the table cloth that is draped over the edge of the table in front of the cake. It had paw-prints on it and blue/green/orange stripes.", "sent_id": 49807, "sent": "the table cloth that is draped over the edge of the table in front of the cake . it had paw - prints on it and blue / green / orange stripes"}, {"tokens": ["table", "cloth", "in", "the", "front"], "raw": "table cloth in the front.", "sent_id": 49808, "sent": "table cloth in the front"}], "file_name": "COCO_train2014_000000513221_1622694.jpg", "ann_id": 1622694, "sent_ids": [49807, 49808], "ref_id": 24122}, {"segmentation": [[399.17, 245.78, 414.94, 277.31, 430.71, 295.44, 445.69, 312.0, 497.72, 331.71, 538.71, 326.19, 569.46, 292.29, 571.82, 270.22, 585.23, 252.87, 589.17, 200.93, 569.68, 153.61, 534.89, 117.43, 486.18, 113.25, 451.38, 123.69, 413.8, 160.57, 396.41, 200.24]], "area": 32220.715149999993, "iscrowd": 0, "image_id": 136894, "bbox": [396.41, 113.25, 192.76, 218.46], "category_id": 55, "id": 1051468, "split": "val", "sentences": [{"tokens": ["a", "big", "size", "mango", "in", "the", "plate"], "raw": "a big size mango in the plate", "sent_id": 49903, "sent": "a big size mango in the plate"}, {"tokens": ["a", "pear", "on", "top", "of", "a", "paper", "plate"], "raw": "A pear on top of a paper plate.", "sent_id": 49904, "sent": "a pear on top of a paper plate"}], "file_name": "COCO_train2014_000000136894_1051468.jpg", "ann_id": 1051468, "sent_ids": [49903, 49904], "ref_id": 24159}, {"segmentation": [[185.67, 271.12, 205.71, 267.96, 236.31, 264.79, 250.02, 259.52, 245.8, 255.3, 237.36, 253.19, 231.03, 253.19, 220.48, 257.41, 223.65, 247.91, 226.81, 225.76, 220.48, 204.66, 214.15, 183.56, 205.71, 167.74, 190.95, 157.19, 174.07, 155.08, 161.41, 155.08, 150.86, 159.3, 136.09, 165.63, 130.81, 171.96, 125.54, 185.67, 123.43, 202.55, 124.48, 214.15, 126.59, 228.92, 132.92, 245.8, 113.93, 264.79, 110.77, 274.29, 104.44, 292.22, 102.33, 298.55, 87.56, 318.59, 86.51, 327.03, 87.56, 338.64, 92.84, 346.02, 98.11, 347.08, 130.81, 334.42, 130.81, 341.8, 122.37, 372.4, 119.21, 402.99, 118.15, 429.36, 120.26, 450.46, 121.32, 475.78, 121.32, 480.0, 208.88, 480.0, 190.95, 453.63, 168.79, 426.2, 159.3, 320.7, 159.3, 286.95, 195.16, 272.18]], "area": 22650.810449999997, "iscrowd": 0, "image_id": 500057, "bbox": [86.51, 155.08, 163.51, 324.92], "category_id": 1, "id": 556903, "split": "val", "sentences": [{"tokens": ["one", "girl", "with", "blonde", "hair", "and", "brown", "long", "-", "sleeve", "shirt", "eating", "a", "lemon"], "raw": "One girl with blonde hair and brown long-sleeve shirt eating a lemon.", "sent_id": 49956, "sent": "one girl with blonde hair and brown long - sleeve shirt eating a lemon"}, {"tokens": ["a", "small", "child", "wearing", "a", "stripped", "dress", "eating"], "raw": "A small child wearing a stripped dress eating.", "sent_id": 49957, "sent": "a small child wearing a stripped dress eating"}], "file_name": "COCO_train2014_000000500057_556903.jpg", "ann_id": 556903, "sent_ids": [49956, 49957], "ref_id": 24179}, {"segmentation": [[508.59, 372.88, 499.98, 397.89, 516.65, 430.8, 529.16, 439.7, 528.05, 448.03, 533.05, 454.98, 535.27, 454.15, 538.05, 463.32, 547.5, 465.26, 565.56, 466.65, 566.67, 462.48, 551.11, 438.03, 526.1, 429.41, 510.54, 373.56], [413.24, 342.81, 424.54, 359.34, 432.47, 377.56, 433.48, 378.74, 448.84, 355.12, 454.57, 345.67, 466.38, 337.4, 471.27, 341.29, 478.36, 309.41, 453.53, 283.58, 446.29, 275.71, 445.66, 284.84, 441.25, 299.64, 433.07, 311.92, 423.62, 319.47, 412.92, 342.22], [448.49, 261.46, 467.07, 282.24, 476.51, 281.61, 478.4, 256.74, 481.24, 242.58, 498.86, 230.61, 504.53, 224.0, 496.66, 211.72, 493.83, 203.85, 488.79, 189.69, 492.25, 166.62, 499.49, 159.38, 495.4, 152.46, 486.9, 140.73, 475.57, 139.15, 457.94, 143.87, 451.96, 153.32, 448.18, 164.02, 448.81, 176.93, 457.62, 197.39, 453.22, 207.15, 443.77, 216.91, 442.2, 221.72, 436.53, 216.99, 436.22, 209.75, 430.24, 202.51, 419.85, 202.2, 421.42, 217.31, 433.7, 230.22, 443.14, 242.89, 447.87, 251.39, 448.49, 264.93]], "area": 10670.742199999997, "iscrowd": 0, "image_id": 100034, "bbox": [412.92, 139.15, 153.75, 327.5], "category_id": 1, "id": 493865, "split": "val", "sentences": [{"tokens": ["girl", "in", "the", "very", "back", "with", "the", "yellow", "and", "white", "shirt", "wearing", "a", "navy", "hat"], "raw": "Girl in the very back with the yellow and white shirt wearing a navy hat", "sent_id": 49966, "sent": "girl in the very back with the yellow and white shirt wearing a navy hat"}, {"tokens": ["two", "kids", "to", "the", "right"], "raw": "two kids to the right", "sent_id": 49967, "sent": "two kids to the right"}], "file_name": "COCO_train2014_000000100034_493865.jpg", "ann_id": 493865, "sent_ids": [49966, 49967], "ref_id": 24183}, {"segmentation": [[140.09, 426.04, 150.65, 372.31, 164.08, 361.75, 162.16, 340.64, 176.56, 283.07, 166.96, 276.35, 172.72, 257.16, 168.88, 240.85, 181.36, 220.7, 193.83, 195.75, 205.34, 193.83, 175.6, 153.53, 175.6, 125.7, 189.03, 89.24, 208.22, 68.13, 236.05, 62.37, 292.66, 87.32, 307.06, 106.51, 301.3, 122.82, 301.3, 154.49, 294.58, 184.23, 289.78, 196.71, 268.67, 205.34, 269.63, 213.98, 284.03, 239.89, 284.03, 279.23, 286.91, 319.53, 314.73, 301.3, 328.17, 292.66, 336.8, 290.74, 342.56, 300.34, 347.36, 307.06, 341.6, 337.76, 278.27, 355.03, 275.39, 424.12]], "area": 42938.88464999999, "iscrowd": 0, "image_id": 80472, "bbox": [140.09, 62.37, 207.27, 363.67], "category_id": 1, "id": 424378, "split": "val", "sentences": [{"tokens": ["the", "boy", "wearing", "the", "tie", "on", "his", "head"], "raw": "The boy wearing the tie on his head", "sent_id": 50056, "sent": "the boy wearing the tie on his head"}, {"tokens": ["a", "boy", "is", "blindfolded"], "raw": "A boy is blindfolded.", "sent_id": 50057, "sent": "a boy is blindfolded"}], "file_name": "COCO_train2014_000000080472_424378.jpg", "ann_id": 424378, "sent_ids": [50056, 50057], "ref_id": 24215}, {"segmentation": [[307.69, 438.98, 201.45, 440.99, 192.43, 370.83, 108.24, 331.74, 93.21, 286.64, 104.23, 268.6, 170.38, 233.52, 198.44, 199.45, 184.41, 174.39, 196.44, 125.28, 217.49, 107.24, 249.56, 105.24, 283.64, 137.31, 286.64, 167.38, 265.6, 246.55, 298.67, 262.59, 304.68, 280.63, 274.62, 274.62, 280.63, 299.67, 293.66, 331.74, 310.7, 333.75, 314.71, 360.81, 269.6, 331.74, 269.6, 286.64, 259.58, 288.65, 250.56, 302.68, 243.55, 293.66, 227.51, 308.69, 232.52, 327.73, 264.59, 400.9, 294.66, 428.96]], "area": 35689.25639999999, "iscrowd": 0, "image_id": 468219, "bbox": [93.21, 105.24, 221.5, 335.75], "category_id": 1, "id": 1707065, "split": "val", "sentences": [{"tokens": ["young", "man", "getting", "his", "tie", "tied"], "raw": "Young man getting his tie tied.", "sent_id": 50058, "sent": "young man getting his tie tied"}, {"tokens": ["a", "man", "in", "a", "suit", "getting", "his", "tie", "fitted", "for", "a", "special", "event"], "raw": "A man in a suit getting his tie fitted for a special event.", "sent_id": 50059, "sent": "a man in a suit getting his tie fitted for a special event"}], "file_name": "COCO_train2014_000000468219_1707065.jpg", "ann_id": 1707065, "sent_ids": [50058, 50059], "ref_id": 24216}, {"segmentation": [[247.0, 150.01, 257.87, 110.89, 270.91, 102.93, 276.7, 93.51, 286.12, 92.06, 336.1, 71.78, 357.83, 68.16, 394.04, 72.5, 412.88, 81.92, 449.82, 103.65, 465.75, 118.86, 486.04, 128.28, 504.87, 134.8, 510.66, 154.36, 510.66, 161.6, 528.77, 168.84, 534.57, 167.39, 567.16, 193.47, 577.3, 202.16, 596.14, 218.82, 621.49, 235.48, 639.6, 252.87, 622.94, 259.39, 603.38, 257.94, 613.52, 272.42, 636.7, 291.26, 638.15, 295.6, 603.38, 295.6, 593.96, 294.88, 577.3, 305.02, 555.57, 308.64, 531.67, 336.89, 507.77, 323.85, 501.25, 316.61, 496.9, 294.88, 489.66, 291.98, 475.9, 285.46, 467.93, 278.94, 452.72, 281.84, 427.36, 273.87, 400.56, 262.28, 381.73, 261.56, 339.72, 273.87, 324.51, 270.98, 296.26, 255.76, 275.25, 239.83, 270.91, 234.03, 278.87, 227.51, 290.46, 226.07, 301.33, 222.44, 309.3, 216.65, 331.75, 227.51, 337.55, 226.79, 342.62, 218.82, 332.47, 195.64, 332.47, 187.68, 301.33, 192.02, 285.39, 203.61, 282.49, 216.65, 278.15, 226.07, 266.56, 231.86, 255.69, 218.82, 258.59, 206.51, 265.84, 197.82, 268.01, 184.78, 278.15, 176.09, 307.85, 174.64, 299.15, 168.84, 296.98, 158.7, 283.22, 155.08, 283.94, 173.19, 262.21, 179.71, 253.52, 181.16, 245.55, 182.61, 228.89, 199.27, 204.99, 226.79, 189.05, 219.55, 190.5, 207.96, 200.64, 196.37, 228.89, 171.74, 249.18, 161.6, 249.18, 149.29]], "area": 57555.883050000004, "iscrowd": 0, "image_id": 149180, "bbox": [189.05, 68.16, 450.55, 268.73], "category_id": 18, "id": 3751, "split": "val", "sentences": [{"tokens": ["german", "shephard", "dog", "sleeping"], "raw": "German Shephard dog sleeping", "sent_id": 50098, "sent": "german shephard dog sleeping"}, {"tokens": ["a", "dog", "with", "a", "black", "face"], "raw": "A dog with a black face", "sent_id": 50099, "sent": "a dog with a black face"}], "file_name": "COCO_train2014_000000149180_3751.jpg", "ann_id": 3751, "sent_ids": [50098, 50099], "ref_id": 24229}, {"segmentation": [[157.92, 275.95, 144.62, 307.53, 167.9, 334.13, 136.31, 395.64, 182.86, 412.26, 171.22, 526.96, 197.82, 541.92, 207.79, 403.95, 231.06, 405.61, 252.68, 533.61, 295.9, 520.31, 290.91, 510.34, 272.62, 508.68, 252.68, 400.62, 265.97, 402.29, 251.01, 320.83, 272.62, 309.19, 262.65, 282.6, 162.91, 282.6]], "area": 19925.806699999994, "iscrowd": 0, "image_id": 29962, "bbox": [136.31, 275.95, 159.59, 265.97], "category_id": 1, "id": 2149760, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "skirt", "under", "an", "umbrella"], "raw": "A woman in a skirt under an umbrella", "sent_id": 50276, "sent": "a woman in a skirt under an umbrella"}, {"tokens": ["a", "girl", "in", "a", "skirt", "with", "a", "backpack", "on", "her", "back"], "raw": "A girl in a skirt with a backpack on her back.", "sent_id": 50277, "sent": "a girl in a skirt with a backpack on her back"}], "file_name": "COCO_train2014_000000029962_2149760.jpg", "ann_id": 2149760, "sent_ids": [50276, 50277], "ref_id": 24298}, {"segmentation": [[284.99, 416.15, 290.74, 409.43, 297.46, 403.68, 302.26, 389.28, 310.89, 330.75, 322.41, 301.01, 327.21, 293.33, 332.96, 285.65, 337.76, 277.02, 350.24, 255.91, 350.24, 254.95, 318.57, 214.65, 312.81, 215.61, 298.42, 227.12, 269.63, 230.96, 269.63, 216.57, 278.27, 224.24, 289.78, 212.73, 287.87, 205.05, 297.46, 185.86, 314.73, 161.87, 322.41, 161.87, 311.85, 148.44, 302.26, 139.8, 297.46, 135.96, 295.54, 128.29, 293.62, 119.65, 297.46, 103.34, 307.06, 98.54, 327.21, 94.7, 342.56, 120.61, 343.52, 137.88, 348.32, 137.88, 383.82, 141.72, 403.01, 152.28, 415.49, 165.71, 429.88, 189.7, 432.76, 195.46, 426.04, 209.85, 447.15, 244.39, 447.15, 244.39, 450.99, 244.39, 447.15, 244.39, 448.11, 241.51, 455.79, 246.31, 444.27, 251.11, 439.47, 250.15, 431.8, 251.11, 435.64, 255.91, 429.88, 259.74, 417.4, 260.7, 423.16, 264.54, 427.96, 264.54, 428.92, 265.5, 423.16, 274.14, 432.76, 277.02, 433.72, 274.14, 442.35, 271.26, 429.88, 286.61, 435.64, 285.65, 450.99, 291.41, 452.91, 279.9, 457.71, 274.14, 464.42, 278.94, 494.17, 324.03, 494.17, 361.46, 495.13, 368.17, 495.13, 368.17, 501.84, 376.81, 472.1, 342.27, 442.35, 319.24, 439.47, 310.6, 425.08, 319.24, 412.61, 318.28, 407.81, 304.84, 403.97, 300.05, 393.42, 305.8, 388.62, 312.52, 387.66, 313.48, 379.98, 310.6, 374.22, 308.68, 342.56, 329.79, 339.68, 344.19, 331.04, 376.81, 321.45, 395.04, 317.61, 417.11, 297.46, 419.03, 297.46, 419.03], [530.63, 387.37, 533.51, 380.65, 551.74, 395.04, 570.93, 410.39, 581.49, 415.19, 561.34, 417.11, 540.23, 417.11, 532.55, 399.84]], "area": 27285.12090000001, "iscrowd": 0, "image_id": 105714, "bbox": [269.63, 94.7, 311.86, 324.33], "category_id": 1, "id": 482561, "split": "val", "sentences": [{"tokens": ["man", "holding", "frisbee"], "raw": "Man holding frisbee", "sent_id": 50288, "sent": "man holding frisbee"}, {"tokens": ["the", "man", "with", "the", "frisbee"], "raw": "The man with the frisbee.", "sent_id": 50289, "sent": "the man with the frisbee"}], "file_name": "COCO_train2014_000000105714_482561.jpg", "ann_id": 482561, "sent_ids": [50288, 50289], "ref_id": 24304}, {"segmentation": [[235.15, 447.64, 252.4, 436.85, 262.11, 429.3, 270.74, 424.99, 279.37, 419.6, 288.0, 412.04, 299.87, 408.81, 300.94, 407.73, 309.57, 384.0, 330.07, 380.76, 378.61, 364.58, 420.67, 357.03, 436.85, 350.56, 446.56, 347.33, 441.17, 337.62, 440.09, 324.67, 436.85, 268.58, 412.04, 276.13, 404.49, 276.13, 398.02, 276.13, 392.63, 269.66, 380.76, 267.51, 372.13, 267.51, 362.43, 267.51, 354.88, 266.43, 345.17, 265.35, 345.17, 265.35, 330.07, 279.37, 322.52, 290.16, 304.18, 297.71, 275.06, 300.94, 223.28, 303.1, 184.45, 308.49, 166.11, 314.97, 140.22, 335.46, 133.75, 352.72, 133.75, 367.82, 134.83, 382.92, 140.22, 387.24, 160.72, 384.0, 167.19, 385.08, 177.98, 394.79, 183.37, 403.42, 198.47, 417.44, 211.42, 428.22, 221.12, 437.93, 232.99, 444.4, 237.3, 444.4]], "area": 30795.51414999999, "iscrowd": 0, "image_id": 238630, "bbox": [133.75, 265.35, 312.81, 182.29], "category_id": 65, "id": 315638, "split": "val", "sentences": [{"tokens": ["the", "bed", "that", "is", "whiter", "than", "the", "other", "one"], "raw": "The bed that is whiter than the other one.", "sent_id": 50318, "sent": "the bed that is whiter than the other one"}, {"tokens": ["a", "white", "coloured", "bedspread", "on", "a", "be", "in", "the", "room"], "raw": "a white coloured bedspread on a be in the room", "sent_id": 50319, "sent": "a white coloured bedspread on a be in the room"}], "file_name": "COCO_train2014_000000238630_315638.jpg", "ann_id": 315638, "sent_ids": [50318, 50319], "ref_id": 24317}, {"segmentation": [[399.36, 13.63, 391.43, 25.52, 386.48, 40.38, 384.5, 53.26, 384.5, 60.2, 386.48, 63.17, 391.43, 64.17, 396.39, 66.15, 389.45, 75.07, 375.58, 79.03, 356.75, 80.02, 351.79, 80.02, 349.81, 75.07, 334.95, 78.04, 306.21, 88.94, 295.31, 89.93, 287.38, 97.86, 278.46, 118.67, 278.46, 124.61, 307.2, 144.43, 332.97, 134.52, 350.8, 125.61, 350.8, 145.42, 345.85, 159.3, 344.86, 178.13, 332.97, 190.02, 325.04, 209.84, 325.04, 219.75, 325.04, 229.66, 336.93, 261.37, 334.95, 283.17, 291.35, 363.44, 282.43, 375.33, 268.55, 393.17, 258.64, 422.9, 258.64, 430.82, 258.64, 434.79, 327.02, 432.81, 316.12, 417.94, 334.95, 390.19, 349.81, 362.45, 376.57, 310.92, 389.45, 277.22, 411.25, 333.71, 411.25, 343.62, 387.47, 366.41, 370.62, 395.15, 362.7, 412.0, 356.75, 422.9, 362.7, 434.79, 412.24, 429.83, 446.93, 426.86, 430.08, 416.95, 419.18, 411.01, 421.16, 405.06, 431.07, 396.14, 478.64, 323.8, 443.95, 239.57, 443.95, 197.95, 439.99, 203.89, 456.84, 150.38, 485.58, 134.52, 525.21, 133.53, 541.07, 124.61, 543.05, 115.7, 544.04, 105.79, 544.04, 95.88, 544.04, 85.97, 538.1, 81.01, 529.18, 74.08, 518.28, 73.08, 509.36, 84.98, 514.31, 95.88, 508.37, 95.88, 496.48, 95.88, 485.58, 93.89, 474.67, 85.97, 461.79, 87.95, 448.91, 82.99, 444.95, 78.04, 445.94, 61.19, 448.91, 48.31, 448.91, 34.44, 443.95, 14.62, 439.0, 9.66, 434.05, 3.72, 407.29, 3.72]], "area": 53023.81085, "iscrowd": 0, "image_id": 222977, "bbox": [258.64, 3.72, 285.4, 431.07], "category_id": 1, "id": 484788, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "white", "photo", "of", "a", "man", "dressed", "in", "business", "attire", "on", "skis", "..", "posing"], "raw": "A BLACK AND WHITE PHOTO OF A MAN DRESSED IN BUSINESS ATTIRE ON SKIS..POSING", "sent_id": 50352, "sent": "a black and white photo of a man dressed in business attire on skis .. posing"}, {"tokens": ["the", "man", "is", "holding", "ski", "poles"], "raw": "The man is holding ski poles.", "sent_id": 50353, "sent": "the man is holding ski poles"}], "file_name": "COCO_train2014_000000222977_484788.jpg", "ann_id": 484788, "sent_ids": [50352, 50353], "ref_id": 24328}, {"segmentation": [[396.96, 31.18, 409.98, 10.85, 423.81, 0.0, 456.34, 2.71, 471.8, 18.98, 476.68, 54.77, 456.34, 203.63, 449.84, 236.17, 423.81, 241.87, 396.96, 236.17, 409.98, 213.39, 417.3, 164.59, 410.79, 77.55, 394.52, 75.92, 393.71, 33.62]], "area": 13621.986149999997, "iscrowd": 0, "image_id": 80590, "bbox": [393.71, 0.0, 82.97, 241.87], "category_id": 44, "id": 81270, "split": "val", "sentences": [{"tokens": ["a", "bottle", "wrapped", "with", "violet", "with", "other", "bottles"], "raw": "A bottle wrapped with violet with other bottles.", "sent_id": 50394, "sent": "a bottle wrapped with violet with other bottles"}, {"tokens": ["a", "bottle", "which", "is", "covered", "by", "lilac", "color", "wrap", "paper", "&", "muscat", "baileya", "2009", "printed", "on", "that"], "raw": "a bottle which is covered by lilac color wrap paper & muscat baileya 2009 printed on that.", "sent_id": 50395, "sent": "a bottle which is covered by lilac color wrap paper & muscat baileya 2009 printed on that"}], "file_name": "COCO_train2014_000000080590_81270.jpg", "ann_id": 81270, "sent_ids": [50394, 50395], "ref_id": 24347}, {"segmentation": [[499.1, 378.57, 499.89, 332.76, 167.35, 330.39, 167.35, 380.94, 498.31, 379.36], [149.18, 331.18, 122.33, 331.97, 121.54, 376.2, 150.76, 378.57]], "area": 17416.822500000006, "iscrowd": 0, "image_id": 189330, "bbox": [121.54, 330.39, 378.35, 50.55], "category_id": 15, "id": 1396781, "split": "val", "sentences": [{"tokens": ["the", "second", "red", "bench", "back", ",", "starting", "from", "the", "closest", "to", "the", "camera"], "raw": "The second red bench back,  starting from the closest to the camera.", "sent_id": 50512, "sent": "the second red bench back , starting from the closest to the camera"}, {"tokens": ["red", "park", "benches"], "raw": "Red park benches.", "sent_id": 50513, "sent": "red park benches"}], "file_name": "COCO_train2014_000000189330_1396781.jpg", "ann_id": 1396781, "sent_ids": [50512, 50513], "ref_id": 24393}, {"segmentation": [[501.79, 161.15, 621.2, 187.62, 610.61, 277.03, 602.96, 284.68, 598.84, 304.68, 495.32, 271.74, 493.55, 248.21, 497.08, 210.56, 499.43, 162.92]], "area": 13664.315550000003, "iscrowd": 0, "image_id": 456658, "bbox": [493.55, 161.15, 127.65, 143.53], "category_id": 72, "id": 1969607, "split": "val", "sentences": [{"tokens": ["a", "screen", "shows", "the", "truck"], "raw": "A screen shows the truck", "sent_id": 50582, "sent": "a screen shows the truck"}, {"tokens": ["a", "computer", "monitor", "sitting", "on", "the", "end", "of", "a", "desk"], "raw": "A computer monitor sitting on the end of a desk.", "sent_id": 50583, "sent": "a computer monitor sitting on the end of a desk"}], "file_name": "COCO_train2014_000000456658_1969607.jpg", "ann_id": 1969607, "sent_ids": [50582, 50583], "ref_id": 24421}, {"segmentation": [[292.93, 441.09, 297.45, 411.27, 276.67, 374.22, 246.84, 319.1, 223.35, 288.37, 210.69, 282.05, 183.58, 286.56, 179.97, 263.97, 198.04, 226.92, 208.89, 207.94, 196.23, 182.64, 201.66, 166.37, 228.77, 171.8, 245.03, 188.96, 269.44, 169.99, 281.18, 142.88, 281.18, 120.28, 288.41, 103.12, 301.06, 111.25, 287.5, 178.12, 267.62, 224.21, 311.91, 286.56, 341.73, 306.43, 372.45, 350.7, 377.87, 372.39, 355.28, 379.62, 331.78, 349.8, 298.35, 318.17, 301.06, 364.26, 328.17, 414.86, 299.26, 443.78]], "area": 20566.963350000005, "iscrowd": 0, "image_id": 290460, "bbox": [179.97, 103.12, 197.9, 340.66], "category_id": 1, "id": 476954, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "shirt", "going", "up", "a", "skateboard", "bowl"], "raw": "A man in a blue shirt going up a skateboard bowl.", "sent_id": 50593, "sent": "a man in a blue shirt going up a skateboard bowl"}, {"tokens": ["a", "man", "in", "a", "bright", "blue", "t", "-", "shirt", "and", "cool", "white", "sunglasses", "rides", "the", "skateboard", "up", "the", "ramp"], "raw": "A man in a bright blue t-shirt and cool white sunglasses rides the skateboard up the ramp.", "sent_id": 50594, "sent": "a man in a bright blue t - shirt and cool white sunglasses rides the skateboard up the ramp"}], "file_name": "COCO_train2014_000000290460_476954.jpg", "ann_id": 476954, "sent_ids": [50593, 50594], "ref_id": 24427}, {"segmentation": [[206.93, 432.56, 215.32, 433.26, 221.61, 465.4, 220.91, 480.09, 232.09, 512.24, 239.78, 522.02, 242.58, 548.59, 242.58, 551.38, 253.76, 551.38, 256.56, 515.73, 257.26, 512.94, 260.75, 517.83, 258.66, 538.1, 260.05, 551.38, 269.84, 551.38, 274.04, 533.21, 280.33, 517.13, 289.41, 517.83, 297.1, 515.73, 303.39, 536.0, 308.98, 526.22, 312.48, 512.94, 316.67, 499.66, 322.96, 452.82, 312.48, 426.96, 301.29, 421.37, 281.03, 419.27, 271.24, 409.49, 247.47, 387.12, 238.38, 381.53, 225.8, 378.73, 211.13, 384.32, 204.14, 394.11, 199.24, 404.59, 192.95, 426.96, 198.54, 433.26, 204.84, 433.96]], "area": 12964.607750000001, "iscrowd": 0, "image_id": 156823, "bbox": [192.95, 378.73, 130.01, 172.65], "category_id": 20, "id": 62553, "split": "val", "sentences": [{"tokens": ["sheep", "in", "middlr", "of", "picture"], "raw": "sheep in middlr of picture", "sent_id": 50607, "sent": "sheep in middlr of picture"}, {"tokens": ["the", "middled", "sized", "sheep", "to", "the", "right", "of", "the", "left", "most", "sheep"], "raw": "The middled sized sheep to the right of the left most sheep.", "sent_id": 50608, "sent": "the middled sized sheep to the right of the left most sheep"}], "file_name": "COCO_train2014_000000156823_62553.jpg", "ann_id": 62553, "sent_ids": [50607, 50608], "ref_id": 24432}, {"segmentation": [[1.44, 493.06, 20.13, 464.3, 51.78, 468.61, 112.18, 419.72, 125.12, 298.91, 172.58, 264.39, 168.27, 120.57, 197.03, 68.79, 215.73, 58.73, 281.89, 61.6, 316.4, 113.38, 316.4, 229.87, 343.73, 297.47, 434.34, 465.74, 401.26, 516.07, 382.56, 520.39, 365.3, 619.63, 174.02, 623.94, 179.78, 570.73, 184.09, 526.14, 159.64, 465.74, 67.6, 523.27, 27.33, 520.39]], "area": 120249.3314, "iscrowd": 0, "image_id": 313186, "bbox": [1.44, 58.73, 432.9, 565.21], "category_id": 1, "id": 436526, "split": "val", "sentences": [{"tokens": ["a", "young", "blond", "haired", "boy", "wearing", "a", "hoodie", "and", "holding", "a", "blue", "kite", "with", "a", "whale", "on", "it"], "raw": "A young blond haired boy wearing a hoodie and holding a blue kite with a whale on it.", "sent_id": 50619, "sent": "a young blond haired boy wearing a hoodie and holding a blue kite with a whale on it"}, {"tokens": ["a", "child", "with", "a", "kite", "in", "his", "hands"], "raw": "A child with a kite in his hands.", "sent_id": 50620, "sent": "a child with a kite in his hands"}], "file_name": "COCO_train2014_000000313186_436526.jpg", "ann_id": 436526, "sent_ids": [50619, 50620], "ref_id": 24437}, {"segmentation": [[223.62, 317.36, 184.09, 317.36, 142.31, 303.81, 111.81, 294.78, 74.54, 265.41, 75.67, 239.44, 110.68, 190.87, 163.76, 140.05, 198.78, 129.88, 251.86, 138.92, 293.65, 164.89, 311.72, 177.32, 304.94, 229.27, 294.78, 255.25, 272.19, 290.26, 230.4, 316.24]], "area": 32010.2417, "iscrowd": 0, "image_id": 513811, "bbox": [74.54, 129.88, 237.18, 187.48], "category_id": 59, "id": 1071175, "split": "val", "sentences": [{"tokens": ["smaller", "pizza"], "raw": "Smaller pizza", "sent_id": 50633, "sent": "smaller pizza"}, {"tokens": ["the", "smaller", "pizza"], "raw": "the smaller pizza", "sent_id": 50634, "sent": "the smaller pizza"}], "file_name": "COCO_train2014_000000513811_1071175.jpg", "ann_id": 1071175, "sent_ids": [50633, 50634], "ref_id": 24443}, {"segmentation": [[243.24, 48.11, 252.97, 32.97, 254.05, 27.57, 246.49, 25.41, 243.24, 26.49, 249.73, 12.43, 242.16, 11.35, 231.35, 10.27, 225.95, 13.51, 224.86, 21.08, 227.03, 34.05, 228.11, 41.62, 228.11, 49.19, 222.7, 75.14, 220.54, 94.59, 214.05, 116.22, 209.73, 138.92, 208.65, 156.22, 207.57, 177.84, 200.0, 192.97, 197.84, 217.84, 192.43, 236.22, 185.95, 261.08, 182.7, 277.3, 182.7, 297.84, 184.86, 311.89, 190.27, 323.78, 196.76, 346.49, 197.84, 357.3, 195.68, 374.59, 192.43, 390.81, 182.7, 432.97, 179.46, 442.7, 179.46, 449.19, 177.3, 454.59, 187.03, 463.24, 204.32, 461.08, 200.0, 451.35, 195.68, 443.78, 212.97, 388.65, 223.78, 368.11, 225.95, 355.14, 223.78, 337.84, 234.59, 352.97, 237.84, 365.95, 224.86, 381.08, 224.86, 402.7, 221.62, 426.49, 214.05, 430.81, 228.11, 443.78, 237.84, 452.43, 238.92, 444.86, 241.08, 428.65, 245.41, 397.3, 257.3, 364.86, 259.46, 351.89, 257.3, 333.51, 261.62, 327.03, 254.05, 300.0, 248.65, 263.24, 249.73, 228.65, 263.78, 208.11, 264.86, 203.78, 288.65, 207.03, 294.05, 198.38, 294.05, 182.16, 284.32, 171.35, 274.59, 169.19, 272.43, 176.76, 263.78, 173.51, 263.78, 170.27, 268.11, 151.89, 269.19, 133.51, 259.46, 125.95, 243.24, 127.03, 238.92, 143.24, 235.68, 150.81, 231.35, 132.43, 234.59, 114.05, 234.59, 90.27, 240.0, 57.84]], "area": 21187.196300000003, "iscrowd": 0, "image_id": 233841, "bbox": [177.3, 10.27, 116.75, 452.97], "category_id": 1, "id": 541928, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "black", "shorts", "and", "a", "green", "top", "reaching", "for", "a", "white", "frisbee"], "raw": "A girl in black shorts and a green top reaching for a white frisbee.", "sent_id": 50687, "sent": "a girl in black shorts and a green top reaching for a white frisbee"}, {"tokens": ["a", "teenage", "girl", "wearing", "green", "t", "-", "shirt", "jumping", "to", "catch", "a", "disc"], "raw": "A teenage girl wearing green t-shirt jumping to catch a disc.", "sent_id": 50688, "sent": "a teenage girl wearing green t - shirt jumping to catch a disc"}], "file_name": "COCO_train2014_000000233841_541928.jpg", "ann_id": 541928, "sent_ids": [50687, 50688], "ref_id": 24463}, {"segmentation": [[527.99, 140.92, 520.14, 161.66, 499.95, 191.93, 453.98, 246.32, 417.54, 293.97, 424.27, 305.18, 474.17, 237.35, 519.58, 181.84, 529.67, 162.78, 532.47, 144.84], [535.84, 148.15, 529.11, 163.29, 500.51, 208.7, 473.05, 247.38, 424.27, 311.29, 431.56, 315.78, 493.23, 230.0, 531.35, 173.38], [402.41, 344.37, 385.59, 369.04, 392.32, 369.59, 404.09, 353.9, 406.33, 349.98]], "area": 3365.300000000001, "iscrowd": 0, "image_id": 54282, "bbox": [385.59, 140.92, 150.25, 228.67], "category_id": 35, "id": 2202879, "split": "val", "sentences": [{"tokens": ["the", "skis", "sticking", "out", "behind", "the", "orange", "jacket"], "raw": "The skis sticking out behind the orange jacket.", "sent_id": 50695, "sent": "the skis sticking out behind the orange jacket"}, {"tokens": ["pair", "of", "gray", "skis", "close", "to", "smiling", "man"], "raw": "Pair of gray skis close to smiling man.", "sent_id": 50696, "sent": "pair of gray skis close to smiling man"}], "file_name": "COCO_train2014_000000054282_2202879.jpg", "ann_id": 2202879, "sent_ids": [50695, 50696], "ref_id": 24465}, {"segmentation": [[430.59, 190.59, 459.71, 187.94, 491.47, 199.41, 499.41, 229.41, 498.53, 239.12, 497.65, 338.82, 494.12, 366.18, 381.18, 370.59, 367.94, 353.82, 377.65, 345.0, 392.65, 337.94, 412.06, 321.18, 415.59, 286.76, 407.65, 283.24, 406.76, 264.71, 406.76, 237.35, 403.24, 223.24, 420.0, 197.65]], "area": 16490.830049999997, "iscrowd": 0, "image_id": 229002, "bbox": [367.94, 187.94, 131.47, 182.65], "category_id": 56, "id": 1056870, "split": "val", "sentences": [{"tokens": ["green", "broccoli", "on", "a", "plate", "of", "food"], "raw": "Green broccoli on a plate of food.", "sent_id": 50725, "sent": "green broccoli on a plate of food"}, {"tokens": ["brocolli", "on", "a", "plate"], "raw": "Brocolli on a plate", "sent_id": 50726, "sent": "brocolli on a plate"}], "file_name": "COCO_train2014_000000229002_1056870.jpg", "ann_id": 1056870, "sent_ids": [50725, 50726], "ref_id": 24477}, {"segmentation": [[0.74, 43.62, 18.48, 27.36, 40.66, 23.66, 65.8, 30.31, 79.85, 46.58, 84.28, 71.71, 76.15, 106.46, 65.8, 114.6, 53.97, 121.99, 48.06, 125.69, 36.23, 137.51, 34.01, 158.22, 47.32, 172.26, 55.45, 179.66, 65.8, 192.22, 68.76, 217.36, 68.02, 226.97, 88.72, 237.32, 115.33, 249.89, 147.87, 260.24, 168.57, 260.24, 175.96, 256.55, 184.09, 255.81, 179.66, 267.64, 173.0, 276.51, 150.08, 280.94, 123.47, 279.47, 99.81, 275.77, 69.5, 274.29, 43.62, 260.24, 93.89, 288.34, 107.2, 302.38, 116.07, 309.78, 101.29, 325.3, 74.67, 323.09, 1.48, 324.56, 0.74, 47.32]], "area": 23610.22655000001, "iscrowd": 0, "image_id": 177019, "bbox": [0.74, 23.66, 183.35, 301.64], "category_id": 1, "id": 210859, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "green", "on", "a", "motorcycle"], "raw": "A man in green on a motorcycle", "sent_id": 50844, "sent": "a man in green on a motorcycle"}], "file_name": "COCO_train2014_000000177019_210859.jpg", "ann_id": 210859, "sent_ids": [50844], "ref_id": 24524}, {"segmentation": [[320.0, 619.7, 425.0, 613.2, 425.0, 527.11, 397.97, 408.53, 402.84, 363.05, 420.71, 346.8, 425.0, 280.2, 422.34, 138.88, 389.85, 85.28, 365.48, 88.53, 342.74, 69.04, 341.12, 38.17, 310.25, 5.69, 294.01, 8.93, 276.14, 12.18, 276.14, 30.05, 269.64, 49.54, 269.64, 67.41, 269.47, 79.98, 283.24, 84.17, 285.04, 97.34, 265.28, 125.48, 256.9, 141.64, 253.31, 170.98, 235.95, 206.3, 216.19, 250.01, 203.02, 269.76, 211.4, 290.72, 223.37, 305.68, 237.74, 307.48, 246.72, 305.68, 253.31, 297.9, 244.33, 258.39, 273.66, 233.24, 280.85, 259.59, 285.04, 320.65, 289.83, 384.71, 295.22, 420.63, 301.2, 439.19, 310.18, 454.76, 321.56, 465.53, 328.74, 516.42, 313.78, 538.57, 291.03, 556.53, 300.01, 565.52, 319.16, 569.71, 327.55, 569.71, 327.55, 573.9, 319.76, 585.27, 330.54, 597.84, 324.55, 619.4]], "area": 76111.25440000002, "iscrowd": 0, "image_id": 62759, "bbox": [203.02, 5.69, 221.98, 614.01], "category_id": 1, "id": 491306, "split": "val", "sentences": [{"tokens": ["man", "in", "ski", "glasses", "and", "orange", "hat"], "raw": "man in ski glasses and orange hat", "sent_id": 50866, "sent": "man in ski glasses and orange hat"}, {"tokens": ["a", "man", "in", "black"], "raw": "A man in black", "sent_id": 50867, "sent": "a man in black"}], "file_name": "COCO_train2014_000000062759_491306.jpg", "ann_id": 491306, "sent_ids": [50866, 50867], "ref_id": 24534}, {"segmentation": [[371.86, 81.49, 382.0, 55.27, 350.41, 52.29, 358.16, 21.9, 377.82, 12.96, 395.7, 11.17, 404.64, 14.15, 413.58, 37.4, 426.69, 75.53, 422.52, 111.89, 420.14, 134.53, 416.56, 151.22, 415.96, 170.88, 426.69, 203.66, 431.46, 227.5, 432.05, 237.63, 430.86, 238.82, 393.91, 234.05, 411.79, 219.16, 414.18, 216.18, 414.18, 216.18, 390.93, 164.93, 384.98, 200.68, 381.4, 209.02, 376.04, 192.93, 369.48, 156.58, 375.44, 138.11, 383.78, 122.61, 387.95, 105.33]], "area": 9178.226649999997, "iscrowd": 0, "image_id": 337621, "bbox": [350.41, 11.17, 81.64, 227.65], "category_id": 1, "id": 532353, "split": "val", "sentences": [{"tokens": ["a", "person", "with", "yellow", "boots"], "raw": "A person with yellow boots.", "sent_id": 50918, "sent": "a person with yellow boots"}, {"tokens": ["skier", "wearing", "a", "bright", "purple", "and", "yellow", "-", "green", "suit", "along", "with", "a", "fuzzy", "wig"], "raw": "Skier wearing a bright purple and yellow-green suit along with a fuzzy wig.", "sent_id": 50919, "sent": "skier wearing a bright purple and yellow - green suit along with a fuzzy wig"}], "file_name": "COCO_train2014_000000337621_532353.jpg", "ann_id": 532353, "sent_ids": [50918, 50919], "ref_id": 24551}, {"segmentation": [[72.64, 129.04, 40.87, 104.61, 53.09, 89.13, 53.09, 76.1, 38.43, 68.77, 44.13, 55.74, 51.46, 45.96, 48.2, 28.04, 57.16, 12.57, 69.38, 8.5, 77.52, 10.12, 81.6, 11.75, 88.11, 16.64, 91.37, 22.34, 85.67, 43.52, 77.52, 52.48, 79.97, 63.07, 87.3, 68.77, 104.4, 72.03, 131.28, 85.06, 123.14, 96.46, 113.36, 102.16, 90.55, 102.16, 80.78, 101.35, 92.18, 131.49, 103.59, 159.99, 96.26, 200.72, 82.41, 198.28, 74.26, 162.44, 79.15, 148.59, 71.82, 132.3]], "area": 6795.953449999997, "iscrowd": 0, "image_id": 55412, "bbox": [38.43, 8.5, 92.85, 192.22], "category_id": 1, "id": 1751558, "split": "val", "sentences": [{"tokens": ["a", "person", "wearing", "a", "red", "helmet", "and", "riding", "a", "blue", "scooter"], "raw": "A person wearing a red helmet and riding a blue scooter.", "sent_id": 50928, "sent": "a person wearing a red helmet and riding a blue scooter"}, {"tokens": ["man", "wearing", "a", "red", "helmet"], "raw": "Man wearing a red helmet.", "sent_id": 50929, "sent": "man wearing a red helmet"}], "file_name": "COCO_train2014_000000055412_1751558.jpg", "ann_id": 1751558, "sent_ids": [50928, 50929], "ref_id": 24554}, {"segmentation": [[0.0, 136.22, 24.5, 120.36, 108.11, 120.36, 110.99, 120.36, 105.23, 154.95, 119.64, 218.38, 157.12, 366.85, 152.79, 395.68, 152.79, 417.3, 162.88, 547.03, 165.77, 572.97, 46.13, 585.95, 47.57, 496.58, 2.88, 495.14, 0.0, 493.69]], "area": 60881.302550000015, "iscrowd": 0, "image_id": 399276, "bbox": [0.0, 120.36, 165.77, 465.59], "category_id": 3, "id": 354072, "split": "val", "sentences": [{"tokens": ["a", "blue", "car", "behind", "a", "parking", "meter"], "raw": "A blue car behind a parking meter.", "sent_id": 50963, "sent": "a blue car behind a parking meter"}, {"tokens": ["the", "blues", "car"], "raw": "The blues car.", "sent_id": 50964, "sent": "the blues car"}], "file_name": "COCO_train2014_000000399276_354072.jpg", "ann_id": 354072, "sent_ids": [50963, 50964], "ref_id": 24570}, {"segmentation": [[491.43, 153.89, 475.52, 170.8, 454.63, 171.8, 439.7, 177.77, 438.71, 182.74, 409.86, 190.7, 382.01, 225.52, 397.92, 250.39, 404.89, 256.36, 383.99, 273.27, 387.97, 303.11, 420.8, 338.92, 431.75, 345.89, 428.76, 374.74, 591.91, 375.73, 599.87, 360.81, 630.71, 349.87, 640.0, 322.01, 640.0, 274.26, 611.81, 256.36, 610.81, 246.41, 606.83, 205.62, 596.88, 192.69, 580.97, 185.72, 567.04, 186.72, 545.15, 192.69, 532.22, 175.78, 522.27, 164.83, 512.32, 159.86]], "area": 43135.9703, "iscrowd": 0, "image_id": 265235, "bbox": [382.01, 153.89, 257.99, 221.84], "category_id": 61, "id": 1928506, "split": "val", "sentences": [{"tokens": ["the", "brown", "mit", "cake"], "raw": "The brown mit cake.", "sent_id": 51179, "sent": "the brown mit cake"}, {"tokens": ["a", "baseball", "mitt", "made", "out", "of", "cake", "frosting"], "raw": "A baseball mitt made out of cake frosting", "sent_id": 51180, "sent": "a baseball mitt made out of cake frosting"}], "file_name": "COCO_train2014_000000265235_1928506.jpg", "ann_id": 1928506, "sent_ids": [51179, 51180], "ref_id": 24658}, {"segmentation": [[80.81, 1.9, 95.5, 40.47, 87.24, 154.33, 92.75, 164.43, 87.24, 208.51, 69.79, 232.39, 81.73, 228.71, 72.54, 248.91, 96.42, 231.47, 85.4, 261.77, 103.77, 248.0, 95.5, 275.55, 122.13, 250.75, 112.95, 274.63, 140.5, 222.28, 147.84, 169.02, 154.27, 190.15, 151.52, 257.18, 158.86, 259.93, 157.94, 268.2, 150.6, 278.3, 184.57, 275.55, 210.29, 272.79, 209.37, 260.85, 201.1, 235.14, 186.41, 205.76, 178.15, 177.29, 178.15, 160.76, 187.33, 138.72, 201.1, 113.01, 203.86, 93.73, 244.26, 101.99, 264.46, 95.56, 269.06, 130.46, 278.24, 146.99, 289.26, 160.76, 295.69, 156.17, 300.28, 112.09, 325.07, 91.89, 333.34, 98.32, 339.76, 132.29, 336.09, 167.19, 337.01, 190.15, 359.97, 193.82, 364.56, 139.64, 367.31, 113.01, 383.84, 79.95, 383.84, 64.34, 401.29, 22.1, 406.8, 0.98]], "area": 49611.32170000001, "iscrowd": 0, "image_id": 228734, "bbox": [69.79, 0.98, 337.01, 277.32], "category_id": 19, "id": 60065, "split": "val", "sentences": [{"tokens": ["horse", "standing", "on", "the", "beach"], "raw": "horse standing on the beach", "sent_id": 51204, "sent": "horse standing on the beach"}, {"tokens": ["horse", "which", "is", "standing"], "raw": "horse which is standing", "sent_id": 51205, "sent": "horse which is standing"}], "file_name": "COCO_train2014_000000228734_60065.jpg", "ann_id": 60065, "sent_ids": [51204, 51205], "ref_id": 24669}, {"segmentation": [[373.71, 433.06, 375.78, 355.42, 394.42, 306.77, 416.15, 285.03, 436.86, 279.85, 502.08, 274.68, 533.13, 274.68, 573.51, 246.73, 607.67, 252.94, 638.73, 277.78, 640.0, 288.13, 637.69, 436.17, 374.75, 435.13]], "area": 42295.80605000001, "iscrowd": 0, "image_id": 333498, "bbox": [373.71, 246.73, 266.29, 189.44], "category_id": 33, "id": 1184891, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "purple", "piece", "of", "luggage", "outside", "of", "a", "train"], "raw": "A black and purple piece of luggage outside of a train.", "sent_id": 51391, "sent": "a black and purple piece of luggage outside of a train"}, {"tokens": ["gray", "luggage"], "raw": "gray luggage", "sent_id": 51392, "sent": "gray luggage"}], "file_name": "COCO_train2014_000000333498_1184891.jpg", "ann_id": 1184891, "sent_ids": [51391, 51392], "ref_id": 24745}, {"segmentation": [[213.48, 11.24, 215.73, 8.99, 250.56, 25.84, 253.93, 53.93, 256.18, 96.63, 253.93, 98.88, 249.44, 106.74, 256.18, 121.35, 266.29, 155.06, 265.17, 168.54, 261.8, 177.53, 259.55, 187.64, 247.19, 243.82, 239.33, 262.92, 174.16, 319.1, 143.82, 322.47, 139.33, 320.22, 135.96, 313.48, 120.22, 307.87, 108.99, 310.11, 108.99, 303.37, 110.11, 300.0, 161.8, 287.64, 176.4, 289.89, 206.74, 258.43, 186.52, 223.6, 167.42, 219.1, 133.71, 214.61, 125.84, 215.73, 105.62, 226.97, 104.49, 228.09, 108.99, 206.74, 114.61, 194.38, 114.61, 187.64, 84.27, 164.04, 92.13, 133.71, 92.13, 115.73, 106.74, 97.75, 120.22, 82.02, 149.44, 77.53, 156.18, 67.42, 173.03, 31.46, 186.52, 14.61, 215.73, 1.12]], "area": 32871.05485000001, "iscrowd": 0, "image_id": 358921, "bbox": [84.27, 1.12, 182.02, 321.35], "category_id": 1, "id": 195816, "split": "val", "sentences": [{"tokens": ["a", "smiling", "woman", "holding", "a", "tray", "of", "desserts", "on", "her", "lap"], "raw": "A smiling woman holding a tray of desserts on her lap", "sent_id": 51401, "sent": "a smiling woman holding a tray of desserts on her lap"}, {"tokens": ["a", "lady", "in", "a", "black", "sweater"], "raw": "a lady in a black sweater", "sent_id": 51402, "sent": "a lady in a black sweater"}], "file_name": "COCO_train2014_000000358921_195816.jpg", "ann_id": 195816, "sent_ids": [51401, 51402], "ref_id": 24749}, {"segmentation": [[380.74, 144.14, 385.15, 136.76, 392.58, 131.45, 399.3, 128.62, 400.37, 124.37, 404.97, 118.0, 412.04, 116.59, 418.06, 121.89, 427.62, 121.89, 446.37, 141.71, 450.62, 170.03, 449.05, 185.93, 466.03, 204.69, 481.61, 252.47, 492.93, 278.66, 492.93, 295.65, 488.33, 302.37, 500.01, 295.29, 506.03, 291.4, 523.01, 277.6, 539.65, 275.47, 547.08, 274.77, 549.91, 290.34, 521.6, 323.96, 469.93, 337.41, 464.26, 330.33, 448.34, 329.27, 437.72, 326.08, 398.08, 334.93, 378.97, 330.33, 365.88, 315.82, 348.89, 328.92, 317.04, 316.88, 271.74, 242.21, 274.21, 233.71, 295.8, 217.08, 305.0, 214.6, 324.11, 202.21, 332.96, 194.43, 339.63, 181.54, 349.62, 180.18, 347.35, 169.28, 367.33, 162.92]], "area": 32508.034349999984, "iscrowd": 0, "image_id": 205202, "bbox": [271.74, 116.59, 278.17, 220.82], "category_id": 1, "id": 523460, "split": "val", "sentences": [{"tokens": ["girl", "in", "gray", "hoodie", "leaning", "on", "table"], "raw": "GIRL IN GRAY HOODIE LEANING ON TABLE", "sent_id": 51409, "sent": "girl in gray hoodie leaning on table"}, {"tokens": ["girl", "looking", "at", "laptop", "screen"], "raw": "Girl looking at laptop screen.", "sent_id": 51410, "sent": "girl looking at laptop screen"}], "file_name": "COCO_train2014_000000205202_523460.jpg", "ann_id": 523460, "sent_ids": [51409, 51410], "ref_id": 24753}, {"segmentation": [[416.36, 473.53, 454.11, 435.78, 497.26, 403.42, 515.6, 355.96, 515.6, 330.07, 502.65, 311.73, 511.28, 300.94, 500.49, 258.88, 496.18, 236.22, 484.31, 160.72, 471.37, 136.99, 458.43, 125.12, 475.69, 112.18, 481.08, 96.0, 486.47, 74.43, 486.47, 74.43, 482.16, 61.48, 473.53, 57.17, 463.82, 31.28, 454.11, 17.26, 433.62, 8.63, 409.89, 10.79, 398.02, 10.79, 385.08, 20.49, 379.69, 32.36, 378.61, 51.78, 376.45, 59.33, 363.51, 69.03, 366.74, 76.58, 369.98, 85.21, 369.98, 93.84, 376.45, 102.47, 377.53, 111.1, 386.16, 116.49, 398.02, 116.49, 401.26, 129.44, 387.24, 129.44, 354.88, 140.22, 324.67, 140.22, 321.44, 118.65, 328.99, 91.69, 331.15, 71.19, 331.15, 59.33, 345.17, 24.81, 345.17, 14.02, 334.38, 25.89, 334.38, 33.44, 323.6, 39.91, 322.52, 42.07, 312.81, 52.85, 305.26, 44.22, 300.94, 52.85, 303.1, 62.56, 300.94, 74.43, 283.69, 129.44, 283.69, 165.03, 309.57, 174.74, 336.54, 180.13, 353.8, 181.21, 368.9, 176.9, 377.53, 179.06, 373.21, 216.81, 374.29, 241.62, 384.0, 269.66, 390.47, 275.06, 378.61, 311.73, 366.74, 322.52, 348.4, 340.85, 337.62, 362.43, 311.73, 380.76, 309.57, 387.24, 307.42, 406.65, 321.44, 413.12, 340.85, 408.81, 338.7, 402.34, 347.33, 390.47, 355.96, 372.13, 380.76, 359.19, 392.63, 353.8, 376.45, 394.79, 355.96, 444.4, 347.33, 472.45], [339.62, 5.22, 338.38, 0.57, 332.49, 0.26, 333.11, 8.94], [329.09, 12.96, 326.92, 14.51, 326.92, 16.68, 325.06, 19.78, 321.34, 21.02, 320.41, 21.33, 319.79, 23.81, 320.72, 27.21, 321.34, 30.31, 320.1, 31.55, 317.63, 32.48, 317.63, 32.48, 315.15, 35.58, 312.67, 35.27, 310.19, 32.48, 304.31, 37.74, 307.09, 30.93, 307.4, 27.21, 308.95, 24.73, 311.74, 24.73, 312.05, 20.71, 318.24, 16.68, 319.17, 19.16, 320.1, 11.72, 323.2, 10.18, 328.47, 10.18]], "area": 60505.2079, "iscrowd": 0, "image_id": 8856, "bbox": [283.69, 0.26, 231.91, 473.27], "category_id": 1, "id": 196687, "split": "val", "sentences": [{"tokens": ["female", "playing", "wii", "in", "tan", "sweater"], "raw": "Female playing WII in tan sweater", "sent_id": 51464, "sent": "female playing wii in tan sweater"}, {"tokens": ["a", "women", "with", "a", "light", "tan", "shirt", "and", "dark", "jeans", "playing", "the", "wii"], "raw": "A women with a light tan shirt and dark jeans playing the Wii.", "sent_id": 51465, "sent": "a women with a light tan shirt and dark jeans playing the wii"}], "file_name": "COCO_train2014_000000008856_196687.jpg", "ann_id": 196687, "sent_ids": [51464, 51465], "ref_id": 24779}, {"segmentation": [[33.75, 238.83, 71.83, 254.41, 121.17, 258.73, 134.15, 378.17, 37.22, 379.9, 0.87, 361.72]], "area": 14161.82965, "iscrowd": 0, "image_id": 223831, "bbox": [0.87, 238.83, 133.28, 141.07], "category_id": 63, "id": 1603773, "split": "val", "sentences": [{"tokens": ["a", "small", "bench", "covered", "with", "a", "green", "cloth"], "raw": "A small bench covered with a green cloth", "sent_id": 51494, "sent": "a small bench covered with a green cloth"}, {"tokens": ["a", "green", ",", "unoccupied", "couch"], "raw": "A green, unoccupied couch.", "sent_id": 51495, "sent": "a green , unoccupied couch"}], "file_name": "COCO_train2014_000000223831_1603773.jpg", "ann_id": 1603773, "sent_ids": [51494, 51495], "ref_id": 24792}, {"segmentation": [[42.05, 341.62, 33.15, 283.4, 40.43, 263.99, 57.41, 196.08, 33.96, 196.08, 26.68, 180.71, 32.34, 169.39, 46.09, 164.54, 55.79, 165.35, 63.88, 162.92, 97.84, 65.9, 68.73, 61.85, 60.64, 58.62, 59.02, 50.53, 60.64, 38.41, 74.39, 33.56, 81.66, 33.56, 88.94, 27.9, 93.79, 24.66, 93.79, 41.64, 100.26, 49.73, 102.69, 49.73, 113.2, 10.92, 97.03, 4.45, 308.87, 31.13, 310.49, 52.96, 422.88, 60.24, 424.49, 69.13, 402.66, 73.17, 425.3, 157.26, 461.69, 158.88, 454.41, 170.2, 444.71, 173.44, 456.03, 179.1, 485.14, 179.1, 501.31, 170.2, 504.54, 129.77, 507.77, 57.81, 468.16, 22.24, 460.88, 14.15, 463.3, 2.02, 562.76, 1.21, 562.76, 8.49, 510.2, 12.53, 549.82, 172.63, 565.18, 172.63, 561.14, 186.37, 568.42, 202.54, 587.01, 352.94, 40.43, 354.55]], "area": 151052.25385, "iscrowd": 0, "image_id": 502153, "bbox": [26.68, 1.21, 560.33, 353.34], "category_id": 8, "id": 396801, "split": "val", "sentences": [{"tokens": ["the", "back", "view", "of", "a", "chevrolet", "truck", ",", "including", "racks", "in", "the", "truck", "bed"], "raw": "The back view of a Chevrolet truck, including racks in the truck bed", "sent_id": 51591, "sent": "the back view of a chevrolet truck , including racks in the truck bed"}, {"tokens": ["a", "blue", "truck"], "raw": "A blue truck.", "sent_id": 51592, "sent": "a blue truck"}], "file_name": "COCO_train2014_000000502153_396801.jpg", "ann_id": 396801, "sent_ids": [51591, 51592], "ref_id": 24828}, {"segmentation": [[76.58, 274.88, 153.17, 314.79, 69.03, 343.91, 56.09, 272.72], [26.97, 273.8, 20.49, 269.48, 3.24, 281.35, 1.08, 475.51, 71.19, 472.27]], "area": 12909.8059, "iscrowd": 0, "image_id": 392098, "bbox": [1.08, 269.48, 152.09, 206.03], "category_id": 65, "id": 1611645, "split": "val", "sentences": [{"tokens": ["there", "is", "bed", "with", "grey", "colored", "bed", "sheet", "on", "it"], "raw": "There is bed with grey colored bed sheet on it", "sent_id": 51637, "sent": "there is bed with grey colored bed sheet on it"}, {"tokens": ["the", "bed", "with", "a", "gray", "blanket"], "raw": "the bed with a gray blanket", "sent_id": 51638, "sent": "the bed with a gray blanket"}], "file_name": "COCO_train2014_000000392098_1611645.jpg", "ann_id": 1611645, "sent_ids": [51637, 51638], "ref_id": 24844}, {"segmentation": [[135.59, 278.28, 139.2, 357.15, 147.89, 367.28, 160.91, 337.62, 155.85, 320.97, 144.99, 306.5, 158.74, 276.84], [145.94, 398.03, 140.44, 423.98, 140.44, 441.28, 151.45, 500.25, 179.75, 506.54, 174.25, 463.29, 172.68, 408.25], [198.63, 469.58, 200.2, 486.88, 211.99, 486.1, 215.93, 479.02]], "area": 4615.0054500000015, "iscrowd": 0, "image_id": 29962, "bbox": [135.59, 276.84, 80.34, 229.7], "category_id": 1, "id": 2158699, "split": "val", "sentences": [{"tokens": ["the", "pants", "of", "the", "male"], "raw": "the pants of the male", "sent_id": 51672, "sent": "the pants of the male"}, {"tokens": ["someone", "in", "black", "holding", "an", "umbrella"], "raw": "someone in black holding an umbrella", "sent_id": 51673, "sent": "someone in black holding an umbrella"}], "file_name": "COCO_train2014_000000029962_2158699.jpg", "ann_id": 2158699, "sent_ids": [51672, 51673], "ref_id": 24857}, {"segmentation": [[371.9, 221.88, 375.05, 220.7, 389.21, 228.96, 395.89, 230.92, 403.75, 230.92, 403.36, 236.03, 406.9, 238.39, 413.19, 231.71, 422.63, 227.78, 428.13, 226.6, 428.53, 236.03, 433.64, 239.57, 443.08, 251.37, 450.94, 279.68, 452.91, 285.19, 452.51, 288.33, 455.66, 295.02, 457.63, 316.65, 458.41, 356.75, 448.58, 370.91, 454.48, 375.63, 468.24, 374.84, 463.52, 366.59, 469.03, 364.62, 470.6, 357.54, 467.46, 325.69, 470.21, 297.77, 477.68, 313.89, 485.55, 355.18, 485.94, 378.38, 482.01, 392.15, 480.04, 398.44, 486.73, 401.98, 503.24, 399.22, 500.88, 392.54, 498.52, 385.85, 502.06, 375.63, 497.34, 363.44, 492.62, 341.42, 489.08, 315.07, 491.05, 301.7, 491.44, 283.61, 486.33, 276.14, 487.51, 257.27, 481.61, 249.4, 480.04, 234.07, 481.22, 223.84, 483.19, 193.17, 479.25, 180.59, 474.54, 173.51, 461.56, 158.57, 449.37, 151.1, 421.45, 134.98, 410.44, 127.11, 384.49, 101.55, 373.87, 90.54, 364.43, 86.61, 324.72, 85.04, 294.83, 82.28, 273.2, 78.35, 205.96, 65.77, 190.23, 64.98, 186.69, 59.48, 181.98, 60.26, 176.86, 55.54, 179.22, 47.68, 181.58, 39.03, 177.26, 37.85, 163.89, 55.54, 159.56, 58.69, 155.63, 54.36, 151.7, 57.9, 151.3, 62.62, 145.8, 71.27, 138.33, 77.96, 132.43, 89.75, 127.71, 94.08, 127.71, 100.37, 130.07, 103.52, 134.79, 107.45, 145.01, 103.52, 147.76, 101.16, 161.53, 99.98, 178.04, 92.51, 186.3, 90.15, 214.22, 99.19, 281.46, 123.18, 309.77, 135.76, 318.03, 145.59, 327.08, 155.42, 320.39, 168.79, 320.39, 179.8, 328.26, 198.68, 332.58, 206.54, 336.91, 221.09, 340.05, 237.61, 343.2, 272.21, 343.98, 283.22, 346.34, 287.94, 345.16, 305.64, 344.38, 316.65, 343.2, 337.09, 337.69, 346.53, 327.86, 355.18, 341.62, 359.9, 350.67, 355.18, 348.7, 348.89, 352.24, 344.17, 353.42, 332.37, 354.21, 307.99, 356.96, 288.33, 359.71, 279.68, 358.93, 260.02, 365.22, 288.33, 367.58, 295.02, 373.48, 344.96, 371.9, 361.08, 363.65, 372.48, 360.5, 376.81, 373.08, 381.13, 384.49, 378.78, 380.55, 371.3, 384.49, 359.11, 385.27, 350.46, 380.16, 316.65, 379.37, 283.61, 378.59, 271.42, 374.66, 245.47, 373.87, 227.38]], "area": 33541.477950000015, "iscrowd": 0, "image_id": 534107, "bbox": [127.71, 37.85, 375.53, 364.13], "category_id": 25, "id": 599916, "split": "val", "sentences": [{"tokens": ["picture", "of", "a", "giraffe"], "raw": "Picture of a Giraffe", "sent_id": 51676, "sent": "picture of a giraffe"}, {"tokens": ["a", "giraffe", "bending", "down", "to", "lick", "at", "a", "termite", "mound"], "raw": "A giraffe bending down to lick at a termite mound.", "sent_id": 51677, "sent": "a giraffe bending down to lick at a termite mound"}], "file_name": "COCO_train2014_000000534107_599916.jpg", "ann_id": 599916, "sent_ids": [51676, 51677], "ref_id": 24859}, {"segmentation": [[53.57, 34.02, 83.76, 323.29, 452.89, 251.22, 398.35, 24.28]], "area": 93864.8106, "iscrowd": 0, "image_id": 89773, "bbox": [53.57, 24.28, 399.32, 299.01], "category_id": 72, "id": 1969179, "split": "val", "sentences": [{"tokens": ["a", "picture", "featuring", "a", "girl", "and", "three", "panda", "bears"], "raw": "A picture featuring a girl and three panda bears.", "sent_id": 51682, "sent": "a picture featuring a girl and three panda bears"}, {"tokens": ["a", "laptop", "cover"], "raw": "A laptop cover.", "sent_id": 51683, "sent": "a laptop cover"}], "file_name": "COCO_train2014_000000089773_1969179.jpg", "ann_id": 1969179, "sent_ids": [51682, 51683], "ref_id": 24862}, {"segmentation": [[216.26, 154.15, 245.45, 138.44, 253.68, 127.96, 263.41, 118.98, 270.89, 94.29, 281.37, 79.32, 303.07, 68.84, 326.27, 72.59, 337.49, 87.55, 342.73, 101.02, 316.54, 110.75, 312.05, 142.93, 318.78, 159.39, 345.72, 173.61, 347.97, 181.09, 337.49, 205.04, 342.73, 239.46, 345.72, 275.38, 344.22, 314.29, 349.46, 333.0, 260.41, 333.0, 231.98, 330.76, 238.71, 301.57, 249.19, 288.1, 261.91, 243.2, 258.17, 227.49, 258.92, 217.76, 248.44, 203.54, 241.71, 193.07, 220.75, 169.12, 209.53, 158.64, 217.76, 153.4]], "area": 22689.122450000006, "iscrowd": 0, "image_id": 44637, "bbox": [209.53, 68.84, 139.93, 264.16], "category_id": 1, "id": 466469, "split": "val", "sentences": [{"tokens": ["a", "young", "brunette", "woman", "hugging", "a", "red", "haired", "woman"], "raw": "A young brunette woman hugging a red haired woman.", "sent_id": 51704, "sent": "a young brunette woman hugging a red haired woman"}, {"tokens": ["a", "woman", "in", "a", "coat", "trimmed", "with", "fur"], "raw": "A woman in a coat trimmed with fur.", "sent_id": 51705, "sent": "a woman in a coat trimmed with fur"}], "file_name": "COCO_train2014_000000044637_466469.jpg", "ann_id": 466469, "sent_ids": [51704, 51705], "ref_id": 24870}, {"segmentation": [[432.3, 145.79, 437.36, 165.17, 451.69, 179.49, 466.85, 187.08, 483.71, 202.25, 498.88, 243.54, 487.92, 278.09, 471.91, 314.33, 458.43, 333.71, 499.72, 367.42, 500.0, 191.29, 480.34, 167.7, 466.01, 151.69, 448.31, 146.63, 446.63, 153.37]], "area": 4429.677050000001, "iscrowd": 0, "image_id": 311706, "bbox": [432.3, 145.79, 67.7, 221.63], "category_id": 1, "id": 1252412, "split": "val", "sentences": [{"tokens": ["a", "hand", "holding", "a", "mobile", "phone", "near", "by", "the", "two", "man", "walking", "near"], "raw": "A HAND HOLDING A MOBILE PHONE NEAR BY THE TWO MAN WALKING NEAR", "sent_id": 51770, "sent": "a hand holding a mobile phone near by the two man walking near"}, {"tokens": ["a", "hand", "holding", "a", "cellphone"], "raw": "a hand holding a cellphone", "sent_id": 51771, "sent": "a hand holding a cellphone"}], "file_name": "COCO_train2014_000000311706_1252412.jpg", "ann_id": 1252412, "sent_ids": [51770, 51771], "ref_id": 24898}, {"segmentation": [[351.2, 381.97, 357.91, 375.25, 352.16, 347.42, 354.07, 328.23, 348.32, 302.32, 350.24, 274.5, 349.28, 262.98, 354.07, 255.3, 350.24, 231.32, 351.2, 213.08, 356.95, 215.0, 367.51, 210.21, 366.55, 207.33, 359.83, 200.61, 359.83, 192.93, 363.67, 184.3, 369.43, 181.42, 379.02, 182.38, 384.78, 191.97, 383.82, 198.69, 383.82, 211.17, 381.9, 215.0, 394.38, 211.17, 403.01, 207.33, 410.69, 212.12, 412.61, 221.72, 429.88, 277.37, 436.6, 310.96, 431.8, 320.55, 439.47, 332.07, 430.84, 344.54, 403.97, 362.77, 396.29, 374.29, 388.62, 373.33, 377.1, 382.92, 365.59, 382.92, 381.9, 371.41, 380.94, 327.27, 369.43, 288.89, 363.67, 334.95, 364.63, 369.49, 367.51, 381.01]], "area": 11425.044050000002, "iscrowd": 0, "image_id": 159957, "bbox": [348.32, 181.42, 91.15, 201.5], "category_id": 1, "id": 493522, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "bikini", "holding", "a", "beach", "towel"], "raw": "A woman in a bikini holding a beach towel.", "sent_id": 51782, "sent": "a woman in a bikini holding a beach towel"}, {"tokens": ["a", "woman", "wearing", "a", "black", "2", "piece", "bikini", "holding", "a", "orange", "and", "white", "striped", "towel"], "raw": "A woman wearing a black 2 piece bikini holding a orange and white striped towel.", "sent_id": 51783, "sent": "a woman wearing a black 2 piece bikini holding a orange and white striped towel"}], "file_name": "COCO_train2014_000000159957_493522.jpg", "ann_id": 493522, "sent_ids": [51782, 51783], "ref_id": 24904}, {"segmentation": [[611.07, 504.79, 580.02, 504.79, 574.37, 480.8, 554.62, 442.7, 529.21, 434.23, 505.22, 373.55, 493.93, 404.59, 495.34, 444.11, 474.18, 434.23, 458.65, 468.1, 460.06, 504.79, 434.66, 503.38, 431.84, 494.91, 431.84, 487.86, 430.43, 476.57, 445.95, 446.93, 451.6, 401.77, 469.94, 363.67, 474.18, 304.4, 481.23, 246.54, 482.64, 232.42, 499.58, 229.6, 484.05, 209.84, 484.05, 164.68, 498.17, 159.04, 513.69, 156.22, 524.98, 156.22, 533.45, 159.04, 540.5, 177.38, 540.5, 199.96, 533.45, 218.31, 543.33, 219.72, 553.2, 222.54, 561.67, 242.3, 551.79, 280.4, 550.38, 307.22, 550.38, 326.98, 551.79, 349.56, 567.32, 406.0, 582.84, 459.63, 592.72, 483.62, 611.07, 492.09, 618.12, 499.15, 616.71, 510.44]], "area": 24474.06510000001, "iscrowd": 0, "image_id": 100034, "bbox": [430.43, 156.22, 187.69, 354.22], "category_id": 1, "id": 533786, "split": "val", "sentences": [{"tokens": ["child", "on", "the", "right", "wearing", "a", "blue", "shirt"], "raw": "Child on the right wearing a blue shirt", "sent_id": 51790, "sent": "child on the right wearing a blue shirt"}, {"tokens": ["a", "child", "holding", "a", "tennis", "racket", "with", "a", "blue", "t", "-", "shirt", "and", "denim", "shorts", "on", ".", "l"], "raw": "A child holding a tennis racket with a blue t-shirt and denim shorts on.l", "sent_id": 51791, "sent": "a child holding a tennis racket with a blue t - shirt and denim shorts on . l"}], "file_name": "COCO_train2014_000000100034_533786.jpg", "ann_id": 533786, "sent_ids": [51790, 51791], "ref_id": 24908}, {"segmentation": [[54.78, 170.22, 37.92, 155.9, 52.25, 58.15, 69.94, 39.61, 77.53, 36.24, 241.01, 29.49, 255.34, 32.02, 270.51, 41.29, 273.88, 142.42, 261.24, 161.8, 251.97, 167.7, 59.83, 173.6]], "area": 30490.627749999996, "iscrowd": 0, "image_id": 174892, "bbox": [37.92, 29.49, 235.96, 144.11], "category_id": 51, "id": 1540492, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "bananas", ",", "honey", "and", "blueberries"], "raw": "A bowl of bananas, honey and blueberries.", "sent_id": 51854, "sent": "a bowl of bananas , honey and blueberries"}, {"tokens": ["a", "blue", "pot", "containing", "bananas", ",", "honey", "and", "blackcurrants"], "raw": "A blue pot containing bananas, honey and blackcurrants", "sent_id": 51855, "sent": "a blue pot containing bananas , honey and blackcurrants"}], "file_name": "COCO_train2014_000000174892_1540492.jpg", "ann_id": 1540492, "sent_ids": [51854, 51855], "ref_id": 24937}, {"segmentation": [[147.89, 263.27, 149.76, 255.79, 167.05, 249.24, 167.52, 233.35, 162.85, 220.27, 154.9, 200.17, 150.23, 196.9, 153.5, 188.95, 166.58, 183.81, 182.48, 189.42, 196.03, 196.9, 194.16, 212.79, 202.11, 205.78, 210.05, 207.18, 208.18, 214.66, 205.38, 225.87, 207.72, 235.22, 225.94, 245.51, 242.77, 286.64, 246.98, 312.81, 242.77, 313.28, 241.37, 318.42, 237.63, 307.67, 235.76, 318.42, 230.15, 311.41, 224.08, 299.72, 218.0, 289.91, 208.65, 280.56, 184.35, 261.4, 182.01, 266.54, 181.07, 291.78, 171.73, 291.78, 157.7, 285.7, 153.03, 278.22, 146.95, 274.95, 142.75, 267.01, 148.82, 259.06]], "area": 6092.925549999998, "iscrowd": 0, "image_id": 37122, "bbox": [142.75, 183.81, 104.23, 134.61], "category_id": 16, "id": 36453, "split": "val", "sentences": [{"tokens": ["a", "pigeon", "flying", "second", "position", "with", "another", "one"], "raw": "A PIGEON FLYING SECOND POSITION WITH ANOTHER ONE", "sent_id": 51901, "sent": "a pigeon flying second position with another one"}, {"tokens": ["a", "bird", "with", "a", "white", "wing"], "raw": "A bird with a white wing.", "sent_id": 51902, "sent": "a bird with a white wing"}], "file_name": "COCO_train2014_000000037122_36453.jpg", "ann_id": 36453, "sent_ids": [51901, 51902], "ref_id": 24955}, {"segmentation": [[497.89, 273.47, 485.52, 299.58, 485.52, 348.37, 472.47, 349.75, 467.66, 339.44, 469.72, 297.52, 461.47, 262.47, 459.41, 225.37, 468.34, 204.75, 483.46, 193.76, 515.07, 202.69, 522.63, 202.69, 531.56, 186.2, 548.74, 184.14, 558.36, 185.51, 566.61, 195.13, 579.66, 186.89, 589.97, 177.95, 596.16, 174.52, 602.34, 175.89, 600.97, 186.89, 590.66, 196.51, 588.6, 198.57, 592.72, 217.81, 591.35, 234.3, 596.84, 253.54, 590.66, 263.85, 581.04, 265.22, 570.04, 239.11, 570.04, 239.11, 562.49, 263.85, 554.93, 306.45, 561.11, 342.19, 559.05, 347.68, 553.55, 350.43, 547.37, 325.69, 542.56, 274.84, 536.37, 281.72, 537.75, 311.95, 539.81, 346.31, 532.25, 347.0, 526.75, 277.59, 526.75, 270.03, 496.52, 269.35]], "area": 12999.282199999996, "iscrowd": 0, "image_id": 370461, "bbox": [459.41, 174.52, 142.93, 175.91], "category_id": 24, "id": 2175344, "split": "val", "sentences": [{"tokens": ["a", "zebra", "behind", "another", "zebra"], "raw": "a zebra behind another zebra", "sent_id": 51919, "sent": "a zebra behind another zebra"}], "file_name": "COCO_train2014_000000370461_2175344.jpg", "ann_id": 2175344, "sent_ids": [51919], "ref_id": 24961}, {"segmentation": [[9.41, 386.64, 19.29, 408.85, 34.91, 437.64, 64.53, 449.98, 99.9, 431.06, 146.78, 415.43, 166.52, 412.14, 183.8, 412.14, 259.47, 447.51, 247.95, 473.01, 6.95, 472.19]], "area": 11218.30375, "iscrowd": 0, "image_id": 532711, "bbox": [6.95, 386.64, 252.52, 86.37], "category_id": 1, "id": 2009007, "split": "val", "sentences": [{"tokens": ["a", "person", "off", "the", "screen", "in", "a", "white", "shirt", "next", "to", "a", "pizza"], "raw": "A person off the screen in a white shirt next to a pizza.", "sent_id": 52027, "sent": "a person off the screen in a white shirt next to a pizza"}, {"tokens": ["the", "right", "shoulder", "of", "someone", "wearing", "a", "white", "shirt", "and", "a", "vest", "to", "the", "left", "of", "a", "pizza"], "raw": "The right shoulder of someone wearing a white shirt and a vest to the left of a pizza", "sent_id": 52028, "sent": "the right shoulder of someone wearing a white shirt and a vest to the left of a pizza"}], "file_name": "COCO_train2014_000000532711_2009007.jpg", "ann_id": 2009007, "sent_ids": [52027, 52028], "ref_id": 25003}, {"segmentation": [[380.89, 299.7, 374.88, 271.64, 370.87, 251.59, 367.86, 225.53, 370.87, 207.49, 368.87, 193.45, 345.81, 200.47, 332.78, 191.45, 334.79, 188.44, 345.81, 187.44, 352.83, 185.44, 362.85, 173.41, 369.87, 162.38, 375.88, 146.34, 374.88, 131.31, 382.9, 121.28, 393.92, 125.29, 399.94, 133.31, 398.94, 139.33, 408.96, 150.35, 414.97, 160.38, 416.98, 170.4, 417.98, 180.42, 416.98, 186.44, 416.98, 202.48, 420.99, 226.53, 422.99, 239.56, 425.0, 254.6, 428.0, 279.66, 427.0, 292.69, 421.99, 306.72, 413.97, 298.7, 411.97, 286.67, 409.96, 276.65, 407.96, 263.62, 404.95, 251.59, 401.94, 242.57, 393.92, 233.55, 389.92, 246.58, 392.92, 259.61, 395.93, 271.64, 396.93, 287.68, 397.93, 296.7, 386.91, 305.72, 382.9, 299.7]], "area": 7754.94285, "iscrowd": 0, "image_id": 32575, "bbox": [332.78, 121.28, 95.22, 185.44], "category_id": 1, "id": 487926, "split": "val", "sentences": [{"tokens": ["a", "skier", "wearing", "green", "pants", "and", "blue", "jacket"], "raw": "A skier wearing green pants and blue jacket.", "sent_id": 52052, "sent": "a skier wearing green pants and blue jacket"}, {"tokens": ["the", "skier", "wearing", "green", "pants", "and", "a", "blue", "shirt"], "raw": "The skier wearing green pants and a blue shirt.", "sent_id": 52053, "sent": "the skier wearing green pants and a blue shirt"}], "file_name": "COCO_train2014_000000032575_487926.jpg", "ann_id": 487926, "sent_ids": [52052, 52053], "ref_id": 25013}, {"segmentation": [[310.54, 228.82, 310.54, 216.77, 322.58, 196.13, 324.3, 187.53, 353.55, 176.34, 374.19, 176.34, 400.86, 179.78, 400.86, 187.53, 427.53, 172.9, 442.15, 168.6, 463.66, 172.04, 472.26, 178.92, 478.28, 186.67, 486.02, 207.31, 492.04, 223.66, 500.0, 246.02, 500.0, 264.09, 484.3, 271.83, 481.72, 288.17, 481.72, 304.52, 457.63, 323.44, 450.75, 351.83, 463.66, 367.31, 450.75, 395.7, 389.68, 396.56, 361.29, 383.66, 357.85, 381.08, 360.43, 369.03, 368.17, 364.73, 382.8, 359.57, 391.4, 351.83, 374.19, 289.03, 363.87, 276.99, 331.18, 268.39, 308.82, 234.84, 308.82, 220.22]], "area": 27313.556649999995, "iscrowd": 0, "image_id": 296760, "bbox": [308.82, 168.6, 191.18, 227.96], "category_id": 18, "id": 18296, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "white", "dog", "lying", "beside", "a", "black", "dog"], "raw": "A black and white dog lying beside a black dog.", "sent_id": 52054, "sent": "a black and white dog lying beside a black dog"}, {"tokens": ["a", "black", "and", "white", "dog", "lying", "on", "a", "bed", "with", "two", "other", "dogs"], "raw": "A black and white dog lying on a bed with two other dogs.", "sent_id": 52055, "sent": "a black and white dog lying on a bed with two other dogs"}], "file_name": "COCO_train2014_000000296760_18296.jpg", "ann_id": 18296, "sent_ids": [52054, 52055], "ref_id": 25014}, {"segmentation": [[381.63, 49.51, 378.29, 81.78, 378.29, 91.79, 356.04, 115.16, 339.35, 124.06, 329.33, 161.89, 328.22, 177.46, 328.22, 191.93, 328.22, 208.61, 329.33, 224.19, 330.45, 245.33, 336.01, 249.78, 336.01, 250.89, 339.35, 277.6, 347.14, 319.88, 347.14, 333.23, 358.26, 408.89, 378.29, 410.0, 379.4, 427.8, 381.63, 433.36, 402.77, 430.02, 407.22, 426.69, 417.23, 423.35, 442.82, 424.46, 449.5, 436.7, 502.9, 441.15, 505.13, 420.01, 504.01, 379.96, 506.24, 334.34, 487.32, 239.77, 482.87, 227.53, 490.66, 196.38, 491.77, 190.81, 490.66, 158.55, 486.21, 134.07, 463.96, 87.34, 457.28, 78.44, 443.93, 45.06, 423.91, 31.71, 393.86, 36.16, 381.63, 51.74]], "area": 54844.08935, "iscrowd": 0, "image_id": 558804, "bbox": [328.22, 31.71, 178.02, 409.44], "category_id": 1, "id": 533357, "split": "val", "sentences": [{"tokens": ["red", "sox", "player", "with", "both", "arms", "crossed", "in", "front", "of", "him", "and", "a", "bat", "pointing", "away", "from", "his", "body"], "raw": "Red Sox player with both arms crossed in front of him and a bat pointing away from his body.", "sent_id": 52123, "sent": "red sox player with both arms crossed in front of him and a bat pointing away from his body"}, {"tokens": ["the", "player", "to", "the", "right", "of", "another", "player"], "raw": "The player to the right of another player.", "sent_id": 52124, "sent": "the player to the right of another player"}], "file_name": "COCO_train2014_000000558804_533357.jpg", "ann_id": 533357, "sent_ids": [52123, 52124], "ref_id": 25043}, {"segmentation": [[169.31, 346.98, 175.8, 368.61, 173.63, 377.58, 169.0, 381.9, 168.69, 376.34, 166.22, 363.67, 163.74, 363.67, 163.43, 370.78, 158.49, 369.23, 157.56, 355.32, 159.42, 354.7, 156.33, 342.34, 146.13, 318.54, 143.96, 304.64, 126.66, 275.27, 110.89, 287.33, 96.37, 303.4, 130.36, 334.31, 142.73, 340.8, 145.82, 347.6, 152.31, 355.32, 152.0, 359.65, 149.22, 363.67, 146.44, 367.07, 143.96, 367.69, 140.56, 367.38, 136.24, 363.67, 132.84, 360.89, 123.87, 344.81, 99.77, 327.51, 126.66, 369.23, 108.11, 400.76, 102.86, 409.41, 89.57, 426.72, 84.93, 434.44, 83.7, 438.77, 93.89, 453.61, 104.4, 457.01, 105.64, 456.08, 104.4, 460.41, 83.08, 459.79, 62.37, 448.04, 61.13, 444.95, 64.84, 437.53, 68.55, 435.68, 71.02, 427.03, 63.92, 383.45, 69.17, 378.81, 63.3, 368.92, 47.53, 377.58, 20.65, 336.47, 14.46, 312.05, 20.03, 285.16, 33.63, 274.66, 37.64, 266.93, 71.02, 235.4, 85.86, 228.61, 112.13, 227.68, 107.18, 225.21, 121.71, 214.39, 135.31, 211.3, 145.82, 214.7, 156.02, 223.66, 157.56, 230.77, 171.16, 242.82, 169.62, 246.22, 157.87, 246.53, 152.62, 249.0, 147.05, 252.4, 151.69, 270.33, 152.62, 285.16, 166.83, 319.47, 169.62, 343.89]], "area": 19333.30234999999, "iscrowd": 0, "image_id": 233841, "bbox": [14.46, 211.3, 161.34, 249.11], "category_id": 1, "id": 519541, "split": "val", "sentences": [{"tokens": ["man", "in", "purple"], "raw": "man in purple", "sent_id": 52142, "sent": "man in purple"}, {"tokens": ["a", "man", "with", "a", "red", "shirt", "and", "black", "shorts", "and", "a", "hat", "is", "reaching", "down", "to", "pick", "up", "a", "white", "frisbee", "next", "to", "two", "women", "in", "green", "shirts"], "raw": "A man with a red shirt and black shorts and a hat is reaching down to pick up a white frisbee next to two women in green shirts.", "sent_id": 52143, "sent": "a man with a red shirt and black shorts and a hat is reaching down to pick up a white frisbee next to two women in green shirts"}], "file_name": "COCO_train2014_000000233841_519541.jpg", "ann_id": 519541, "sent_ids": [52142, 52143], "ref_id": 25049}, {"segmentation": [[116.29, 211.28, 128.4, 240.55, 136.47, 272.84, 165.74, 279.91, 214.18, 303.12, 225.28, 297.06, 299.96, 272.84, 306.02, 260.73, 329.23, 217.33, 307.02, 179.99, 291.89, 158.8, 212.16, 134.58, 169.77, 152.75, 153.63, 158.8, 114.27, 209.26]], "area": 24699.888649999994, "iscrowd": 0, "image_id": 29962, "bbox": [114.27, 134.58, 214.96, 168.54], "category_id": 28, "id": 2191583, "split": "val", "sentences": [{"tokens": ["a", "pair", "of", "black", "umbrellas", "being", "held", "by", "a", "couple", ",", "shielding", "their", "faces"], "raw": "a pair of black umbrellas being held by a couple, shielding their faces", "sent_id": 52164, "sent": "a pair of black umbrellas being held by a couple , shielding their faces"}, {"tokens": ["the", "umbrella", "closest", "to", "the", "camera"], "raw": "the umbrella closest to the camera", "sent_id": 52165, "sent": "the umbrella closest to the camera"}], "file_name": "COCO_train2014_000000029962_2191583.jpg", "ann_id": 2191583, "sent_ids": [52164, 52165], "ref_id": 25060}, {"segmentation": [[66.48, 381.2, 77.65, 395.18, 174.77, 404.26, 238.34, 404.26, 251.62, 394.48, 266.29, 364.44, 268.38, 344.88, 241.14, 331.6, 245.33, 325.31, 246.73, 319.03, 248.12, 302.96, 191.53, 296.67, 142.63, 293.18, 128.66, 301.56, 109.09, 303.66, 100.01, 317.63, 72.07, 363.74, 66.48, 378.41]], "area": 17634.733299999993, "iscrowd": 0, "image_id": 423890, "bbox": [66.48, 293.18, 201.9, 111.08], "category_id": 59, "id": 1077585, "split": "val", "sentences": [{"tokens": ["pizza", "with", "mozzarella", "slices"], "raw": "Pizza with mozzarella slices.", "sent_id": 52174, "sent": "pizza with mozzarella slices"}, {"tokens": ["the", "pizza", "with", "the", "white", "cheese", "on", "it"], "raw": "The pizza with the white cheese on it.", "sent_id": 52175, "sent": "the pizza with the white cheese on it"}], "file_name": "COCO_train2014_000000423890_1077585.jpg", "ann_id": 1077585, "sent_ids": [52174, 52175], "ref_id": 25065}, {"segmentation": [[387.23, 308.22, 334.57, 274.77, 341.69, 242.04, 356.63, 237.77, 357.34, 217.84, 360.19, 207.17, 351.65, 180.84, 351.65, 172.3, 346.67, 156.64, 340.97, 145.97, 321.05, 137.57, 314.64, 124.76, 298.99, 126.18, 288.31, 134.72, 276.22, 144.69, 270.52, 156.78, 261.98, 168.17, 256.29, 179.56, 250.6, 200.91, 254.87, 218.7, 256.29, 231.51, 257.71, 246.45, 263.41, 262.11, 266.25, 270.65, 236.36, 276.03, 215.73, 281.02, 209.32, 286.71, 198.65, 292.4, 195.09, 303.08, 194.38, 315.89, 193.66, 328.7, 185.12, 338.66, 178.72, 353.6, 169.47, 372.51, 174.45, 391.73, 176.58, 400.98, 175.87, 412.37, 177.3, 420.91, 182.99, 425.18, 190.11, 430.16, 197.22, 433.0, 215.01, 435.85, 205.05, 470.72, 192.95, 472.86, 192.95, 480.0, 354.5, 480.0, 351.65, 470.01, 345.96, 469.3, 344.53, 455.78, 345.24, 448.66, 347.38, 437.27, 357.34, 430.16, 359.48, 428.73, 361.61, 408.81, 363.04, 386.75, 364.46, 378.92, 365.88, 358.99, 369.44, 347.61, 373.0, 336.93, 377.27, 324.12, 381.54, 317.72, 384.39, 310.6]], "area": 47479.13665, "iscrowd": 0, "image_id": 323030, "bbox": [169.47, 124.76, 217.76, 355.24], "category_id": 1, "id": 507717, "split": "val", "sentences": [{"tokens": ["woman", "who", "is", "a", "tennis", "player"], "raw": "Woman who is a tennis player.", "sent_id": 52208, "sent": "woman who is a tennis player"}, {"tokens": ["a", "girl", "with", "blonde", "hair"], "raw": "A girl with blonde hair.", "sent_id": 52209, "sent": "a girl with blonde hair"}], "file_name": "COCO_train2014_000000323030_507717.jpg", "ann_id": 507717, "sent_ids": [52208, 52209], "ref_id": 25077}, {"segmentation": [[231.25, 421.24, 228.37, 404.93, 228.37, 390.54, 228.37, 370.39, 228.37, 352.16, 228.37, 341.6, 223.58, 320.49, 223.58, 292.66, 223.58, 280.19, 212.06, 265.8, 203.42, 235.09, 195.75, 212.06, 189.99, 189.99, 180.4, 164.08, 180.4, 137.22, 181.36, 107.47, 182.31, 98.83, 206.3, 91.16, 215.9, 83.48, 205.34, 80.6, 203.42, 60.45, 207.26, 42.22, 213.98, 28.79, 231.25, 24.95, 242.77, 24.95, 259.08, 31.67, 263.88, 46.06, 268.67, 55.65, 265.8, 72.93, 258.12, 79.64, 261.96, 83.48, 276.35, 88.28, 285.95, 93.08, 295.54, 112.27, 301.3, 131.46, 307.06, 148.73, 303.22, 159.29, 284.99, 143.93, 289.78, 169.84, 300.34, 183.27, 301.3, 209.18, 308.02, 218.78, 317.61, 250.44, 308.02, 279.23, 308.02, 302.26, 309.93, 325.29, 315.69, 348.32, 319.53, 364.63, 325.29, 374.22, 319.53, 380.94, 313.77, 379.98, 313.77, 393.42, 321.45, 412.61, 322.41, 421.24, 295.54, 419.32, 296.5, 394.38, 292.66, 378.06, 281.15, 378.06, 281.15, 342.56, 274.43, 318.57, 267.71, 294.58, 261.0, 319.53, 264.84, 342.56, 264.84, 368.47, 259.08, 387.66, 259.08, 397.25, 265.8, 419.32, 264.84, 422.2, 235.09, 422.2]], "area": 34165.073, "iscrowd": 0, "image_id": 549599, "bbox": [180.4, 24.95, 144.89, 397.25], "category_id": 1, "id": 477989, "split": "val", "sentences": [{"tokens": ["woman", "in", "blue", "outfit", "with", "glasses", ",", "holding", "her", "phone"], "raw": "woman in blue outfit with glasses, holding her phone", "sent_id": 52224, "sent": "woman in blue outfit with glasses , holding her phone"}, {"tokens": ["a", "woman", "with", "glasses", "and", "blue", "tennis", "shoes", "sits", "on", "a", "bench", "with", "other", "women"], "raw": "A woman with glasses and blue tennis shoes sits on a bench with other women.", "sent_id": 52225, "sent": "a woman with glasses and blue tennis shoes sits on a bench with other women"}], "file_name": "COCO_train2014_000000549599_477989.jpg", "ann_id": 477989, "sent_ids": [52224, 52225], "ref_id": 25083}, {"segmentation": [[150.79, 71.9, 152.33, 40.21, 150.79, 12.39, 147.69, 0.8, 197.15, 1.58, 197.92, 25.53, 194.06, 41.76, 180.92, 44.08, 179.38, 47.17, 168.56, 45.62, 162.38, 42.53, 161.6, 62.63, 150.79, 73.44], [205.65, 1.58, 211.83, 11.62, 218.79, 16.26, 224.97, 24.76, 224.97, 30.17, 232.7, 34.03, 232.7, 47.17, 241.2, 46.4, 244.29, 58.76, 237.34, 58.76, 255.88, 71.13, 253.56, 82.72, 253.56, 92.76, 246.61, 95.85, 249.7, 99.72, 255.11, 98.95, 258.97, 115.17, 267.47, 105.9, 259.75, 92.76, 286.02, 80.4, 290.66, 73.44, 286.79, 57.22, 286.02, 34.81, 286.02, 0.03, 207.97, 0.8], [300.7, 171.59, 289.89, 152.27, 289.11, 149.95, 282.16, 124.45, 279.07, 100.49, 263.61, 98.95, 263.61, 93.54, 289.11, 97.4, 289.89, 99.72, 295.29, 136.04, 303.8, 163.09, 308.43, 170.81, 303.02, 172.36]], "area": 7833.05235, "iscrowd": 0, "image_id": 447349, "bbox": [147.69, 0.03, 160.74, 172.33], "category_id": 62, "id": 1583195, "split": "val", "sentences": [{"tokens": ["chair"], "raw": "chair", "sent_id": 52287, "sent": "chair"}, {"tokens": ["a", "christmas", "tree"], "raw": "A Christmas tree.", "sent_id": 52288, "sent": "a christmas tree"}], "file_name": "COCO_train2014_000000447349_1583195.jpg", "ann_id": 1583195, "sent_ids": [52287, 52288], "ref_id": 25111}, {"segmentation": [[106.26, 129.93, 117.08, 124.15, 119.97, 121.27, 125.74, 121.27, 128.63, 118.38, 128.63, 88.07, 128.63, 76.52, 130.07, 64.25, 137.29, 56.31, 154.61, 50.54, 174.82, 58.48, 177.7, 72.19, 179.15, 88.79, 189.97, 114.77, 190.69, 129.2, 200.8, 127.04, 209.46, 134.98, 218.12, 154.46, 218.12, 172.51, 218.84, 195.6, 218.12, 207.87, 212.35, 196.32, 208.02, 187.66, 202.96, 173.23, 196.47, 197.04, 189.97, 204.98, 187.81, 213.64, 191.42, 227.36, 190.69, 244.68, 189.97, 251.89, 184.2, 256.22, 183.48, 269.21, 189.25, 280.76, 194.3, 285.81, 193.58, 287.22, 194.3, 313.2, 192.14, 323.19, 181.31, 326.08, 180.59, 332.57, 189.25, 337.63, 181.31, 361.44, 177.7, 378.04, 176.26, 389.59, 178.43, 398.97, 179.15, 412.68, 179.15, 418.46, 176.98, 420.55, 169.04, 418.38, 165.44, 411.88, 163.99, 422.71, 160.38, 429.21, 151.72, 430.65, 145.95, 425.6, 140.18, 420.55, 138.73, 414.05, 142.34, 398.17, 140.18, 394.56, 135.85, 394.56, 132.24, 375.08, 128.63, 350.54, 125.74, 362.81, 118.52, 366.42, 107.7, 346.21, 106.98, 341.16, 101.2, 282.7, 97.6, 259.61, 101.93, 237.96, 102.65, 229.29, 96.15, 224.96, 93.27, 223.52, 91.1, 216.3, 86.77, 207.64, 82.44, 206.2, 82.44, 199.71, 81.0, 197.54, 79.55, 197.54, 73.06, 173.0, 70.89, 161.46, 74.5, 151.35, 78.83, 150.63, 93.99, 139.08, 93.99, 136.92, 104.09, 128.98]], "area": 30331.58125, "iscrowd": 0, "image_id": 198785, "bbox": [70.89, 50.54, 147.95, 380.11], "category_id": 1, "id": 2166596, "split": "val", "sentences": [{"tokens": ["woman", "with", "long", "hair", "on", "the", "left"], "raw": "Woman with long hair on the left.", "sent_id": 52321, "sent": "woman with long hair on the left"}, {"tokens": ["the", "woman", "wearing", "the", "plaid", "shirt"], "raw": "the woman wearing the plaid shirt", "sent_id": 52322, "sent": "the woman wearing the plaid shirt"}], "file_name": "COCO_train2014_000000198785_2166596.jpg", "ann_id": 2166596, "sent_ids": [52321, 52322], "ref_id": 25123}, {"segmentation": [[313.89, 218.97, 449.8, 278.29, 519.91, 74.43, 381.84, 26.97, 309.57, 214.65, 320.36, 221.12]], "area": 31352.103199999998, "iscrowd": 0, "image_id": 183788, "bbox": [309.57, 26.97, 210.34, 251.32], "category_id": 84, "id": 1146211, "split": "val", "sentences": [{"tokens": ["a", "dark", "blue", "passport", "-", "sized", "book"], "raw": "A dark blue passport-sized book.", "sent_id": 52347, "sent": "a dark blue passport - sized book"}, {"tokens": ["a", "blue", "covered", "book", "near", "diary", "in", "a", "table"], "raw": "A BLUE COVERED BOOK NEAR DIARY IN A TABLE", "sent_id": 52348, "sent": "a blue covered book near diary in a table"}], "file_name": "COCO_train2014_000000183788_1146211.jpg", "ann_id": 1146211, "sent_ids": [52347, 52348], "ref_id": 25133}, {"segmentation": [[422.7, 267.74, 435.61, 270.32, 434.75, 244.49, 437.33, 235.88, 444.22, 234.16, 454.55, 237.6, 457.13, 238.47, 460.57, 241.05, 466.6, 250.52, 460.57, 258.27, 456.27, 263.43, 455.41, 274.62, 456.27, 278.07, 457.99, 278.93, 461.44, 281.51, 470.04, 282.37, 471.77, 282.37, 475.21, 274.62, 475.21, 270.32, 470.04, 267.74, 470.04, 261.71, 478.65, 250.52, 482.1, 245.35, 485.54, 237.6, 494.15, 222.11, 497.59, 210.06, 497.59, 201.45, 495.87, 191.12, 506.2, 183.37, 509.65, 183.37, 501.04, 179.06, 488.12, 176.48, 485.54, 175.62, 482.96, 171.32, 478.65, 166.15, 469.18, 161.85, 468.32, 161.85, 464.02, 159.26, 460.57, 156.68, 457.99, 151.52, 457.13, 148.93, 454.55, 144.63, 450.24, 144.63, 450.24, 145.49, 451.1, 149.79, 451.1, 151.52, 446.8, 149.79, 442.5, 148.07, 441.64, 142.05, 443.36, 139.46, 443.36, 136.02, 440.77, 131.72, 438.19, 129.99, 435.61, 128.27, 434.75, 127.41, 427.86, 127.41, 427.86, 127.41, 426.14, 134.3, 429.58, 146.35, 427.86, 154.96, 418.39, 161.85, 413.23, 170.46, 406.34, 174.76, 394.29, 180.79, 390.84, 187.67, 384.82, 196.28, 384.82, 196.28, 382.23, 204.03, 381.37, 211.78, 382.23, 218.67, 382.23, 223.83, 384.82, 229.86, 387.4, 231.58, 389.98, 230.72, 394.29, 227.27, 393.43, 225.55, 392.56, 220.39, 391.7, 212.64, 392.56, 205.75, 395.15, 204.89, 398.59, 216.94, 399.45, 219.53, 405.48, 227.27, 408.06, 221.25, 406.34, 216.08, 402.9, 210.06, 408.92, 210.06, 413.23, 213.5, 423.56, 219.53, 426.14, 221.25, 424.42, 229.86, 423.56, 234.16, 423.56, 238.47, 423.56, 244.49, 423.56, 255.68, 423.56, 258.27]], "area": 8784.113700000005, "iscrowd": 0, "image_id": 88671, "bbox": [381.37, 127.41, 128.28, 154.96], "category_id": 18, "id": 13452, "split": "val", "sentences": [{"tokens": ["small", "white", "dog", "with", "black", "scarf", "standing", "in", "between", "two", "people"], "raw": "Small white dog with black scarf standing in between two people.", "sent_id": 52455, "sent": "small white dog with black scarf standing in between two people"}, {"tokens": ["the", "little", "dog", "has", "a", "bandanna", "around", "its", "neck"], "raw": "The little dog has a bandanna around its neck.", "sent_id": 52456, "sent": "the little dog has a bandanna around its neck"}], "file_name": "COCO_train2014_000000088671_13452.jpg", "ann_id": 13452, "sent_ids": [52455, 52456], "ref_id": 25174}, {"segmentation": [[248.58, 379.88, 276.05, 316.7, 256.82, 294.73, 277.42, 298.85, 302.15, 300.22, 313.13, 301.6, 330.99, 291.98, 321.37, 318.08, 369.44, 342.8, 365.32, 403.23, 365.32, 443.06, 346.09, 449.92, 358.45, 489.75, 341.97, 488.38, 332.36, 449.92, 322.75, 452.67, 307.64, 430.7, 270.56, 419.71]], "area": 13684.362599999991, "iscrowd": 0, "image_id": 156823, "bbox": [248.58, 291.98, 120.86, 197.77], "category_id": 20, "id": 63000, "split": "val", "sentences": [{"tokens": ["an", "adult", "sheep", "in", "the", "background", "of", "the", "two", "lambs"], "raw": "An adult sheep in the background of the two lambs.", "sent_id": 52504, "sent": "an adult sheep in the background of the two lambs"}, {"tokens": ["a", "mother", "sheep", "looking", "at", "the", "camera"], "raw": "A mother sheep looking at the camera", "sent_id": 52505, "sent": "a mother sheep looking at the camera"}], "file_name": "COCO_train2014_000000156823_63000.jpg", "ann_id": 63000, "sent_ids": [52504, 52505], "ref_id": 25195}, {"segmentation": [[325.75, 216.81, 325.75, 244.85, 357.03, 280.45, 399.1, 303.1, 451.96, 310.65, 503.73, 311.73, 535.01, 298.79, 561.98, 296.63, 586.79, 280.45, 595.42, 243.78, 594.34, 224.36, 607.28, 213.57, 610.52, 209.26, 602.97, 192.0, 594.34, 185.53, 583.55, 177.98, 566.29, 163.96, 560.9, 157.48, 549.03, 126.2, 535.01, 104.63, 508.04, 92.76, 497.26, 86.29, 480.0, 78.74, 472.45, 75.51, 457.35, 73.35, 436.85, 77.66, 428.22, 84.13, 408.81, 88.45, 393.71, 92.76, 378.61, 105.71, 364.58, 124.04, 349.48, 135.91, 347.33, 143.46, 337.62, 149.93, 321.44, 160.72, 322.52, 183.37]], "area": 50337.72780000001, "iscrowd": 0, "image_id": 513811, "bbox": [321.44, 73.35, 289.08, 238.38], "category_id": 59, "id": 1073607, "split": "val", "sentences": [{"tokens": ["the", "larger", "pizza"], "raw": "The larger pizza", "sent_id": 52546, "sent": "the larger pizza"}, {"tokens": ["the", "bigger", "pizza", "on", "the", "right"], "raw": "The bigger pizza on the right.", "sent_id": 52547, "sent": "the bigger pizza on the right"}], "file_name": "COCO_train2014_000000513811_1073607.jpg", "ann_id": 1073607, "sent_ids": [52546, 52547], "ref_id": 25211}, {"segmentation": [[0.0, 175.73, 11.83, 172.18, 16.56, 188.73, 42.57, 185.18, 127.69, 225.38, 157.25, 241.93, 245.92, 239.57, 301.48, 241.93, 316.85, 262.03, 286.11, 273.85, 269.56, 262.03, 224.64, 276.22, 140.69, 275.04, 134.78, 290.41, 91.04, 299.86, 56.75, 400.36, 33.11, 428.73, 70.94, 480.0, 2.37, 480.0, 0.0, 180.45]], "area": 30041.2269, "iscrowd": 0, "image_id": 27149, "bbox": [0.0, 172.18, 316.85, 307.82], "category_id": 1, "id": 1755007, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "white", "shirt", "playing", "the", "wii"], "raw": "A person in a white shirt playing the wii.", "sent_id": 52606, "sent": "a person in a white shirt playing the wii"}, {"tokens": ["person", "closest", "to", "front"], "raw": "person closest to front", "sent_id": 52607, "sent": "person closest to front"}], "file_name": "COCO_train2014_000000027149_1755007.jpg", "ann_id": 1755007, "sent_ids": [52606, 52607], "ref_id": 25235}, {"segmentation": [[206.61, 269.69, 199.27, 243.98, 202.02, 239.39, 220.39, 209.09, 229.57, 180.62, 221.08, 169.21, 221.08, 169.21, 215.49, 186.0, 207.89, 183.2, 203.1, 175.61, 201.1, 174.01, 200.7, 174.01, 198.7, 168.01, 202.3, 164.01, 207.89, 158.42, 211.09, 148.83, 219.08, 143.23, 235.87, 138.43, 252.66, 136.83, 256.66, 137.23, 266.65, 138.03, 273.44, 143.63, 275.04, 150.02, 278.64, 158.02, 283.44, 162.42, 315.81, 151.62, 290.23, 181.2, 287.43, 187.6, 317.41, 188.0, 350.99, 193.59, 390.56, 201.99, 428.93, 232.76, 448.51, 262.34, 484.49, 280.73, 455.71, 284.73, 429.33, 283.53, 402.15, 278.33, 394.55, 278.33, 386.96, 278.33, 356.98, 275.13, 331.0, 275.93, 311.42, 285.52, 286.23, 274.73, 275.84, 287.52, 267.45, 287.92, 251.06, 284.73, 238.27, 283.13, 224.68, 276.73, 207.49, 265.14]], "area": 23272.2618, "iscrowd": 0, "image_id": 228734, "bbox": [198.7, 136.83, 285.79, 151.09], "category_id": 19, "id": 59290, "split": "val", "sentences": [{"tokens": ["a", "small", "horse", "lays", "on", "the", "beach", "with", "the", "ocean", "in", "the", "background"], "raw": "A small horse lays on the beach with the ocean in the background.", "sent_id": 52712, "sent": "a small horse lays on the beach with the ocean in the background"}, {"tokens": ["a", "gray", "horse", "laying", "on", "the", "sand", "on", "the", "beach"], "raw": "A gray horse laying on the sand on the beach.", "sent_id": 52713, "sent": "a gray horse laying on the sand on the beach"}], "file_name": "COCO_train2014_000000228734_59290.jpg", "ann_id": 59290, "sent_ids": [52712, 52713], "ref_id": 25275}, {"segmentation": [[260.31, 258.34, 230.43, 309.44, 211.14, 371.14, 190.9, 372.1, 188.97, 348.0, 209.22, 301.72, 236.21, 214.95, 243.92, 165.78, 224.64, 164.82, 211.14, 163.85, 212.11, 137.82, 219.82, 124.32, 234.28, 116.61, 247.78, 128.18, 254.53, 121.43, 261.28, 92.51, 267.06, 87.69, 283.45, 94.44, 292.13, 124.32, 298.88, 130.11, 321.05, 127.22, 350.94, 165.78, 321.05, 181.21, 311.41, 186.99, 312.38, 238.09, 298.88, 339.32, 293.09, 394.28, 283.45, 383.67, 267.06, 382.71, 269.96, 352.82]], "area": 21169.936799999992, "iscrowd": 0, "image_id": 41357, "bbox": [188.97, 87.69, 161.97, 306.59], "category_id": 1, "id": 491763, "split": "val", "sentences": [{"tokens": ["a", "skier", "with", "the", "number", "377", "on", "their", "chest"], "raw": "A skier with the number 377 on their chest.", "sent_id": 52740, "sent": "a skier with the number 377 on their chest"}, {"tokens": ["a", "person", "downhill", "skiing", "wearing", "a", "vest", "that", "says", "377", "on", "it", "and", "a", "blue", "jacket"], "raw": "A person downhill skiing wearing a vest that says 377 on it and a blue jacket.", "sent_id": 52741, "sent": "a person downhill skiing wearing a vest that says 377 on it and a blue jacket"}], "file_name": "COCO_train2014_000000041357_491763.jpg", "ann_id": 491763, "sent_ids": [52740, 52741], "ref_id": 25287}, {"segmentation": [[221.91, 255.46, 207.48, 244.63, 209.06, 232.03, 216.93, 186.36, 224.81, 174.81, 246.33, 163.26, 245.81, 161.69, 239.51, 158.54, 244.23, 125.52, 253.16, 108.19, 264.18, 104.0, 273.63, 105.04, 284.13, 109.77, 288.33, 119.22, 294.1, 126.57, 298.3, 147.04, 296.73, 160.69, 301.98, 166.46, 311.95, 170.66, 316.15, 173.29, 327.7, 192.19, 337.67, 212.66, 340.3, 250.4, 338.2, 257.23, 314.58, 261.43, 317.73, 270.85, 266.28, 272.92, 258.41, 259.27, 253.16, 257.7, 254.21, 265.05, 249.48, 269.25, 240.56, 267.15, 232.16, 256.65]], "area": 14562.6962, "iscrowd": 0, "image_id": 72396, "bbox": [207.48, 104.0, 132.82, 168.92], "category_id": 1, "id": 497255, "split": "val", "sentences": [{"tokens": ["the", "speaker", "behind", "the", "laptop"], "raw": "the speaker behind the laptop.", "sent_id": 52785, "sent": "the speaker behind the laptop"}, {"tokens": ["a", "women", "in", "blue", "giving", "a", "presentation"], "raw": "A women in blue giving a presentation.", "sent_id": 52786, "sent": "a women in blue giving a presentation"}], "file_name": "COCO_train2014_000000072396_497255.jpg", "ann_id": 497255, "sent_ids": [52785, 52786], "ref_id": 25306}, {"segmentation": [[476.76, 238.38, 530.7, 254.56, 555.51, 275.06, 571.69, 323.6, 550.11, 360.27, 550.11, 360.27, 540.4, 389.39, 540.4, 389.39, 540.4, 389.39, 544.72, 436.85, 544.72, 440.09, 531.78, 458.43, 484.31, 474.61, 403.42, 461.66, 369.98, 436.85, 344.09, 408.81, 344.09, 371.06, 364.58, 338.7, 368.9, 320.36, 375.37, 309.57, 371.06, 286.92, 377.53, 255.64, 402.34, 240.54, 432.54, 236.22, 459.51, 236.22]], "area": 41301.81845000001, "iscrowd": 0, "image_id": 47928, "bbox": [344.09, 236.22, 227.6, 238.39], "category_id": 54, "id": 1555051, "split": "val", "sentences": [{"tokens": ["a", "burger", "that", "is", "not", "next", "to", "the", "white", "bowl"], "raw": "A burger that is not next to the white bowl.", "sent_id": 52858, "sent": "a burger that is not next to the white bowl"}, {"tokens": ["the", "first", "burger", ",", "immediately", "next", "to", "the", "metal", "knife", "handle"], "raw": "The first burger, immediately next to the metal knife handle.", "sent_id": 52859, "sent": "the first burger , immediately next to the metal knife handle"}], "file_name": "COCO_train2014_000000047928_1555051.jpg", "ann_id": 1555051, "sent_ids": [52858, 52859], "ref_id": 25337}, {"segmentation": [[98.99, 387.81, 102.26, 318.19, 113.14, 265.98, 126.19, 240.96, 137.07, 226.81, 154.47, 214.85, 180.58, 206.15, 194.72, 189.83, 196.9, 174.6, 197.99, 133.26, 207.78, 113.68, 221.92, 103.89, 234.97, 102.8, 249.11, 101.71, 269.78, 109.33, 291.54, 127.82, 298.07, 138.7, 295.89, 149.58, 293.72, 152.84, 295.89, 163.72, 295.89, 171.33, 295.89, 178.95, 291.54, 192.0, 289.36, 196.35, 289.36, 208.32, 285.01, 215.94, 277.4, 217.02, 277.4, 223.55, 273.05, 233.34, 271.96, 238.78, 277.4, 255.1, 294.8, 294.26, 314.39, 316.02, 329.61, 325.81, 390.53, 334.51, 413.38, 334.51, 430.78, 329.07, 437.31, 326.9, 450.36, 327.98, 466.68, 334.51, 475.39, 345.39, 475.39, 357.35, 474.3, 357.35, 462.33, 348.65, 461.24, 345.39, 462.33, 358.44, 464.51, 362.79, 462.33, 370.41, 451.45, 363.88, 447.1, 359.53, 428.61, 358.44, 413.38, 356.27, 402.5, 356.27, 397.06, 356.27, 385.09, 367.15, 389.45, 373.67, 401.41, 369.32, 405.76, 374.76, 412.29, 383.46, 431.87, 399.78, 431.87, 407.4, 426.43, 411.75, 423.17, 407.4, 415.55, 412.83, 406.85, 412.83, 402.5, 410.66, 393.8, 415.01, 387.27, 411.75, 377.48, 405.22, 362.25, 404.13, 345.93, 406.31, 333.97, 401.96, 318.74, 399.78, 302.42, 411.75, 286.1, 417.19, 306.77, 426.98, 311.12, 431.33, 270.87, 468.31, 261.08, 470.49, 251.29, 452.0, 248.03, 428.06, 250.2, 425.89, 265.43, 422.63, 269.78, 409.57, 270.87, 387.81, 269.78, 360.62, 267.61, 348.65, 254.55, 339.95, 220.83, 347.56, 139.24, 372.58]], "area": 50423.32979999998, "iscrowd": 0, "image_id": 205202, "bbox": [98.99, 101.71, 376.4, 368.78], "category_id": 1, "id": 445530, "split": "val", "sentences": [{"tokens": ["a", "young", "man", "types", "on", "a", "laptop", "while", "two", "youngsters", "watch"], "raw": "A young man types on a laptop while two youngsters watch", "sent_id": 52930, "sent": "a young man types on a laptop while two youngsters watch"}, {"tokens": ["the", "man", "in", "black", "who", "is", "typing", "on", "the", "laptop"], "raw": "The man in black who is typing on the laptop.", "sent_id": 52931, "sent": "the man in black who is typing on the laptop"}], "file_name": "COCO_train2014_000000205202_445530.jpg", "ann_id": 445530, "sent_ids": [52930, 52931], "ref_id": 25362}, {"segmentation": [[203.96, 255.74, 218.49, 247.53, 242.48, 234.9, 257.0, 223.54, 258.27, 221.01, 301.84, 195.75, 346.67, 233.64, 286.05, 281.0, 203.33, 281.0, 196.38, 274.05, 191.96, 267.11, 191.96, 260.79, 200.8, 258.27, 207.12, 255.11]], "area": 7100.9762500000015, "iscrowd": 0, "image_id": 227891, "bbox": [191.96, 195.75, 154.71, 85.25], "category_id": 76, "id": 1116719, "split": "val", "sentences": [{"tokens": ["keyboard"], "raw": "Keyboard", "sent_id": 53034, "sent": "keyboard"}, {"tokens": ["an", "apple", "wireless", "keyboard"], "raw": "An Apple wireless keyboard", "sent_id": 53035, "sent": "an apple wireless keyboard"}], "file_name": "COCO_train2014_000000227891_1116719.jpg", "ann_id": 1116719, "sent_ids": [53034, 53035], "ref_id": 25399}, {"segmentation": [[293.11, 415.81, 246.5, 437.56, 212.33, 454.65, 171.16, 468.63, 161.06, 453.87, 161.06, 448.43, 171.16, 451.54, 178.15, 461.64, 252.72, 422.8, 287.67, 405.71], [374.67, 398.72, 378.56, 396.39, 386.32, 395.61, 389.43, 395.61, 389.43, 403.38, 330.4, 434.45, 243.4, 477.17, 236.41, 475.62, 230.97, 465.52, 234.08, 462.41, 243.4, 468.63, 342.82, 415.81, 347.49, 412.7, 350.59, 414.25, 359.14, 415.81, 374.67, 403.38]], "area": 2921.2129499999983, "iscrowd": 0, "image_id": 335524, "bbox": [161.06, 395.61, 228.37, 81.56], "category_id": 35, "id": 612410, "split": "val", "sentences": [{"tokens": ["a", "pair", "of", "skis", "being", "worn", "by", "a", "woman", "in", "a", "pink", "jacket"], "raw": "A pair of skis being worn by a woman in a pink jacket.", "sent_id": 53105, "sent": "a pair of skis being worn by a woman in a pink jacket"}, {"tokens": ["skis", "worn", "by", "women", "in", "middle", "wearing", "a", "pink", "coat"], "raw": "Skis worn by women in middle wearing a pink coat.", "sent_id": 53106, "sent": "skis worn by women in middle wearing a pink coat"}], "file_name": "COCO_train2014_000000335524_612410.jpg", "ann_id": 612410, "sent_ids": [53105, 53106], "ref_id": 25426}, {"segmentation": [[355.03, 299.12, 358.52, 258.58, 366.91, 237.62, 372.5, 236.22, 373.2, 215.25, 371.8, 206.87, 367.61, 186.6, 370.4, 180.31, 364.11, 163.54, 348.74, 153.05, 348.74, 138.38, 330.57, 136.28, 311.7, 140.47, 313.8, 150.26, 324.98, 157.95, 327.77, 162.84, 322.18, 167.03, 327.07, 174.72, 325.68, 186.6, 325.68, 211.06, 322.88, 234.12, 330.57, 241.81, 333.36, 250.9, 331.27, 266.97, 330.57, 283.74, 326.38, 292.83, 324.28, 298.42]], "area": 5965.048500000001, "iscrowd": 0, "image_id": 141121, "bbox": [311.7, 136.28, 61.5, 162.84], "category_id": 1, "id": 451494, "split": "val", "sentences": [{"tokens": ["smallest", "boy", "in", "the", "image"], "raw": "smallest boy in the image", "sent_id": 53120, "sent": "smallest boy in the image"}, {"tokens": ["a", "child", "standing", "in", "the", "snow"], "raw": "a child standing in the snow", "sent_id": 53121, "sent": "a child standing in the snow"}], "file_name": "COCO_train2014_000000141121_451494.jpg", "ann_id": 451494, "sent_ids": [53120, 53121], "ref_id": 25433}, {"segmentation": [[275.86, 52.66, 290.09, 52.66, 299.31, 50.15, 306.0, 56.01, 295.12, 61.88, 289.26, 69.41, 289.26, 69.41, 295.96, 73.6, 295.12, 83.65, 301.82, 85.32, 313.54, 76.11, 333.64, 79.46, 337.82, 97.88, 328.61, 117.98, 303.49, 126.35, 295.12, 107.93, 280.88, 112.12, 275.02, 55.18], [192.09, 98.73, 195.36, 103.09, 192.36, 107.72, 191.27, 106.63, 189.91, 110.17, 190.18, 114.26, 192.09, 115.07, 193.18, 113.44, 196.99, 119.7, 191.54, 127.88, 189.91, 131.96, 189.64, 136.59, 186.91, 137.41, 186.91, 139.32, 188.0, 153.49, 191.82, 151.31, 192.9, 148.31, 193.72, 147.76, 195.9, 149.4, 196.99, 148.31, 201.9, 154.85, 209.52, 155.94, 220.42, 154.57, 223.96, 155.12, 225.87, 159.21, 225.05, 160.02, 225.05, 161.39, 227.23, 161.39, 229.96, 163.56, 237.04, 171.74, 239.49, 169.83, 240.31, 169.01, 236.22, 161.39, 237.31, 158.93, 237.58, 157.3, 235.68, 158.12, 235.95, 154.57, 233.5, 154.85, 233.22, 152.94, 229.14, 150.76, 223.96, 150.76, 216.88, 138.77, 219.6, 134.42, 217.15, 127.06, 210.61, 121.07, 206.53, 121.61, 203.26, 117.25, 204.89, 111.26, 202.71, 106.35, 203.8, 104.99, 202.44, 100.36, 199.72, 100.36, 192.09, 89.19, 192.09, 100.36]], "area": 4022.3452000000007, "iscrowd": 0, "image_id": 68430, "bbox": [186.91, 50.15, 150.91, 121.59], "category_id": 2, "id": 124795, "split": "val", "sentences": [{"tokens": ["the", "handle", "bars", "and", "seat", "of", "one", "bicycle", "and", "the", "back", "half", "of", "another"], "raw": "the handle bars and seat of one bicycle and the back half of another", "sent_id": 53162, "sent": "the handle bars and seat of one bicycle and the back half of another"}], "file_name": "COCO_train2014_000000068430_124795.jpg", "ann_id": 124795, "sent_ids": [53162], "ref_id": 25450}, {"segmentation": [[81.98, 459.79, 124.55, 475.32, 177.58, 479.34, 229.0, 478.54, 250.69, 478.54, 280.42, 492.19, 283.63, 506.66, 281.22, 511.48, 247.48, 525.14, 238.64, 614.32, 223.37, 615.92, 230.6, 524.33, 214.53, 528.35, 179.18, 525.14, 148.65, 523.53, 110.09, 519.51, 85.18, 514.69, 73.13, 509.87, 70.72, 575.75, 57.86, 587.0, 51.44, 583.79, 49.83, 503.44, 33.76, 497.02, 24.92, 488.98, 21.71, 475.32, 34.56, 465.68, 61.88, 461.66, 79.56, 460.86]], "area": 14396.209449999998, "iscrowd": 0, "image_id": 91933, "bbox": [21.71, 459.79, 261.92, 156.13], "category_id": 15, "id": 576818, "split": "val", "sentences": [{"tokens": ["bench", "facing", "the", "mountains"], "raw": "bench facing the mountains", "sent_id": 53179, "sent": "bench facing the mountains"}], "file_name": "COCO_train2014_000000091933_576818.jpg", "ann_id": 576818, "sent_ids": [53179], "ref_id": 25459}, {"segmentation": [[321.81, 69.51, 340.42, 74.98, 339.32, 84.83, 344.8, 101.25, 344.8, 113.29, 343.7, 127.52, 348.08, 130.8, 363.41, 137.37, 372.16, 145.03, 373.26, 153.79, 375.45, 169.11, 378.73, 191.01, 379.82, 197.57, 380.92, 209.61, 379.82, 216.18, 363.41, 223.84, 363.41, 247.93, 363.41, 268.72, 362.31, 280.76, 332.76, 280.76, 291.16, 284.05, 272.55, 280.76, 275.84, 259.97, 282.41, 243.55, 283.5, 224.94, 269.27, 210.71, 270.36, 170.21, 275.84, 138.47, 302.11, 120.95, 306.49, 104.53, 306.49, 89.21, 314.15, 71.7]], "area": 16600.8073, "iscrowd": 0, "image_id": 222676, "bbox": [269.27, 69.51, 111.65, 214.54], "category_id": 1, "id": 459930, "split": "val", "sentences": [{"tokens": ["a", "man", "holding", "a", "tennis", "racket", "across", "his", "chest"], "raw": "A man holding a tennis racket across his chest.", "sent_id": 53198, "sent": "a man holding a tennis racket across his chest"}, {"tokens": ["a", "man", "between", "other", "two", "holding", "a", "badminton", "racket", "on", "his", "chest"], "raw": "A man between other two holding a badminton racket on his chest.", "sent_id": 53199, "sent": "a man between other two holding a badminton racket on his chest"}], "file_name": "COCO_train2014_000000222676_459930.jpg", "ann_id": 459930, "sent_ids": [53198, 53199], "ref_id": 25469}, {"segmentation": [[332.51, 432.74, 276.71, 273.72, 232.07, 116.1, 240.44, 89.6, 299.03, 92.39, 360.4, 135.63, 406.43, 188.64, 437.12, 294.65, 445.49, 381.13, 441.31, 429.95, 423.17, 487.14, 407.83, 491.33, 375.75, 487.14]], "area": 50615.165550000005, "iscrowd": 0, "image_id": 564823, "bbox": [232.07, 89.6, 213.42, 401.73], "category_id": 54, "id": 2218756, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "bread", "on", "a", "plate"], "raw": "A piece of bread on a plate.", "sent_id": 53206, "sent": "a piece of bread on a plate"}, {"tokens": ["the", "top", "piece", "of", "bread", "for", "a", "sandwich"], "raw": "the top piece of bread for a sandwich", "sent_id": 53207, "sent": "the top piece of bread for a sandwich"}], "file_name": "COCO_train2014_000000564823_2218756.jpg", "ann_id": 2218756, "sent_ids": [53206, 53207], "ref_id": 25472}, {"segmentation": [[309.93, 334.15, 314.78, 354.49, 420.35, 352.55, 527.85, 353.52, 528.82, 342.86, 526.89, 329.3, 391.29, 336.08, 393.23, 323.49, 394.2, 302.18, 412.6, 311.87, 489.11, 304.12, 526.89, 296.37, 528.82, 287.66, 492.99, 207.27, 484.27, 174.34, 515.26, 168.53, 536.57, 165.62, 532.7, 147.22, 517.2, 140.44, 485.24, 140.44, 482.33, 132.69, 396.13, 213.08, 402.91, 178.21, 431.0, 176.27, 402.91, 175.31, 402.91, 127.85, 431.0, 129.78, 431.0, 126.88, 402.91, 122.04, 402.91, 89.11, 401.94, 39.71, 395.16, 124.94, 363.2, 119.13, 363.2, 122.04, 400.01, 125.91, 394.2, 175.31, 341.89, 173.37, 342.86, 177.24, 396.13, 181.12, 377.73, 328.33, 376.76, 336.08, 328.33, 334.15, 316.71, 338.02]], "area": 23131.694700000022, "iscrowd": 0, "image_id": 321066, "bbox": [309.93, 39.71, 226.64, 314.78], "category_id": 9, "id": 180760, "split": "val", "sentences": [{"tokens": ["a", "sailboat"], "raw": "A sailboat.", "sent_id": 53220, "sent": "a sailboat"}, {"tokens": ["a", "green", "sailboat"], "raw": "a green sailboat", "sent_id": 53221, "sent": "a green sailboat"}], "file_name": "COCO_train2014_000000321066_180760.jpg", "ann_id": 180760, "sent_ids": [53220, 53221], "ref_id": 25478}, {"segmentation": [[100.86, 431.24, 158.77, 359.24, 235.81, 420.17, 190.49, 476.56, 182.94, 483.61, 164.81, 483.11]], "area": 9032.98, "iscrowd": 0, "image_id": 411653, "bbox": [100.86, 359.24, 134.95, 124.37], "category_id": 84, "id": 2143511, "split": "val", "sentences": [{"tokens": ["children", "'", "s", "book", "or", "a", "picture", "featuring", "a", "large", "pig", "and", "several", "baby", "pigs"], "raw": "Children's book or a picture featuring a large pig and several baby pigs.", "sent_id": 53244, "sent": "children ' s book or a picture featuring a large pig and several baby pigs"}, {"tokens": ["a", "pink", "pig", "cartoon"], "raw": "A pink pig cartoon.", "sent_id": 53245, "sent": "a pink pig cartoon"}], "file_name": "COCO_train2014_000000411653_2143511.jpg", "ann_id": 2143511, "sent_ids": [53244, 53245], "ref_id": 25487}, {"segmentation": [[113.57, 144.6, 146.02, 135.68, 150.08, 131.62, 165.49, 134.06, 202.81, 142.98, 200.38, 147.04, 343.96, 172.18, 348.83, 186.79, 352.89, 204.63, 368.3, 204.63, 381.28, 204.63, 382.9, 210.31, 356.94, 216.8, 332.61, 220.86, 318.0, 220.86, 295.29, 216.8, 241.75, 223.29, 223.09, 222.48, 219.84, 228.97, 184.15, 237.08, 143.59, 234.65, 137.1, 220.86, 116.01, 216.8]], "area": 17470.3306, "iscrowd": 0, "image_id": 6068, "bbox": [113.57, 131.62, 269.33, 105.46], "category_id": 7, "id": 170527, "split": "val", "sentences": [{"tokens": ["a", "lone", "train", "car", ",", "soon", "to", "be", "bypassed", "by", "a", "locomotive", "in", "motion", "on", "the", "opposite", "track"], "raw": "A lone train car, soon to be bypassed by a locomotive in motion on the opposite track.", "sent_id": 53252, "sent": "a lone train car , soon to be bypassed by a locomotive in motion on the opposite track"}, {"tokens": ["a", "gray", "and", "undetached", "train", "cart", "on", "the", "tracks"], "raw": "A gray and undetached train cart on the tracks.", "sent_id": 53253, "sent": "a gray and undetached train cart on the tracks"}], "file_name": "COCO_train2014_000000006068_170527.jpg", "ann_id": 170527, "sent_ids": [53252, 53253], "ref_id": 25490}, {"segmentation": [[328.34, 527.39, 353.59, 491.3, 372.84, 468.45, 384.86, 434.78, 384.86, 422.75, 394.49, 395.09, 408.92, 368.63, 425.76, 348.18, 442.59, 332.55, 431.77, 352.99, 425.76, 362.61, 420.95, 374.64, 418.54, 380.66, 431.77, 384.26, 448.61, 356.6, 460.64, 343.37, 463.04, 332.55, 470.26, 344.57, 465.45, 359.01, 464.24, 371.03, 464.24, 384.26, 465.45, 395.09, 466.65, 398.7, 471.46, 401.1, 478.68, 399.9, 488.3, 383.06, 491.91, 372.24, 493.11, 372.24, 503.93, 381.86, 524.38, 374.64, 524.38, 374.64, 531.59, 359.01, 550.84, 326.53, 555.65, 314.51, 552.04, 290.45, 537.61, 282.03, 530.39, 276.02, 538.81, 256.78, 543.62, 243.55, 548.43, 230.32, 548.43, 220.7, 560.46, 208.67, 570.08, 197.84, 577.3, 183.41, 582.11, 171.39, 592.93, 155.75, 596.54, 143.72, 601.35, 129.29, 601.35, 117.26, 598.95, 113.66, 592.93, 111.25, 582.11, 112.45, 580.91, 113.66, 566.47, 116.06, 561.66, 118.47, 552.04, 122.07, 547.23, 125.68, 538.81, 129.29, 529.19, 132.9, 523.18, 135.3, 513.55, 136.51, 511.15, 137.71, 503.93, 132.9, 490.7, 126.89, 473.86, 119.67, 463.04, 118.47, 459.43, 117.26, 457.03, 107.64, 454.62, 89.6, 453.42, 77.57, 453.42, 59.53, 452.22, 51.11, 443.8, 34.28, 437.78, 33.07, 426.96, 33.07, 425.76, 36.68, 418.54, 42.7, 416.14, 46.3, 407.72, 57.13, 406.51, 63.14, 404.11, 72.76, 399.3, 82.39, 394.49, 87.2, 392.08, 98.02, 389.68, 107.64, 389.68, 113.66, 387.27, 124.48, 386.07, 129.29, 374.04, 135.3, 363.22, 140.11, 360.81, 143.72, 352.39, 159.36, 349.99, 166.57, 356.0, 171.39, 358.41, 179.8, 360.81, 185.82, 360.81, 191.83, 362.01, 206.26, 356.0, 211.07, 353.59, 212.28, 352.39, 220.7, 352.39, 223.1, 352.39, 225.51, 348.78, 236.33, 348.78, 239.94, 349.99, 250.76, 331.95, 259.18, 330.74, 259.18, 323.53, 259.18, 312.7, 262.79, 310.3, 262.79, 301.88, 262.79, 295.86, 262.79, 287.45, 262.79, 342.77, 263.99, 342.77, 271.21, 337.96, 279.63, 335.55, 280.83, 330.74, 286.84, 323.53, 291.66, 310.3, 291.66, 298.27, 285.64, 298.27, 285.64, 282.64, 284.44, 279.03, 284.44, 276.62, 284.44, 273.01, 284.44, 264.59, 289.25, 258.58, 291.66, 257.38, 291.66, 248.96, 295.26, 234.53, 301.28, 233.32, 302.48, 229.72, 304.89, 221.3, 310.9, 211.68, 313.3, 202.05, 315.71, 198.45, 316.91, 198.45, 316.91, 190.03, 387.87, 191.23, 398.7, 191.23, 410.72, 191.23, 426.36, 191.23, 448.01, 191.23, 473.26, 190.03, 488.9, 188.82, 517.76, 190.03, 526.18, 190.03, 528.59, 321.12, 527.39]], "area": 96199.91385000004, "iscrowd": 0, "image_id": 365205, "bbox": [188.82, 33.07, 412.53, 495.52], "category_id": 17, "id": 46996, "split": "val", "sentences": [{"tokens": ["a", "cat", "that", "looked", "shocked", "with", "big", "green", "eyes"], "raw": "a cat that looked shocked with big green eyes", "sent_id": 53260, "sent": "a cat that looked shocked with big green eyes"}, {"tokens": ["a", "mirror", "image", "of", "a", "cat", "seeing", "the", "mirror"], "raw": "A mirror image of a cat seeing the mirror", "sent_id": 53261, "sent": "a mirror image of a cat seeing the mirror"}], "file_name": "COCO_train2014_000000365205_46996.jpg", "ann_id": 46996, "sent_ids": [53260, 53261], "ref_id": 25494}, {"segmentation": [[374.53, 314.21, 347.62, 294.83, 329.33, 225.96, 333.63, 162.46, 349.78, 105.42, 376.68, 65.6, 389.6, 10.71, 416.5, 3.17, 501.52, 3.17, 507.98, 47.3, 500.45, 171.07, 487.53, 215.19, 464.93, 250.71, 464.93, 303.44, 462.78, 308.83]], "area": 43278.52755, "iscrowd": 0, "image_id": 31187, "bbox": [329.33, 3.17, 178.65, 311.04], "category_id": 1, "id": 477804, "split": "val", "sentences": [{"tokens": ["little", "girl", "in", "light", "green", "shirt"], "raw": "little girl in light green shirt", "sent_id": 53314, "sent": "little girl in light green shirt"}, {"tokens": ["little", "girl", "in", "a", "green", "dress", "waiting", "for", "the", "cake", "to", "be", "cut"], "raw": "Little Girl in a green dress waiting for the cake to be cut.", "sent_id": 53315, "sent": "little girl in a green dress waiting for the cake to be cut"}], "file_name": "COCO_train2014_000000031187_477804.jpg", "ann_id": 477804, "sent_ids": [53314, 53315], "ref_id": 25515}, {"segmentation": [[306.68, 332.99, 300.05, 339.62, 289.79, 339.62, 281.94, 334.8, 277.11, 326.95, 272.89, 316.09, 266.85, 308.85, 263.84, 297.38, 263.84, 284.1, 263.84, 275.66, 263.84, 264.19, 267.46, 257.55, 272.29, 253.93, 272.89, 246.09, 269.87, 232.81, 271.68, 220.14, 285.56, 215.31, 295.82, 224.36, 297.63, 231.6, 297.63, 240.05, 299.44, 247.29, 308.49, 254.53, 315.74, 261.78, 322.37, 271.43, 326.0, 285.91, 329.62, 297.98, 334.44, 305.23, 340.48, 310.05, 350.74, 313.07, 364.62, 317.9, 374.88, 325.14, 376.69, 332.99, 371.26, 337.81, 361.6, 337.21, 338.67, 336.0, 325.39, 336.0]], "area": 6728.577850000001, "iscrowd": 0, "image_id": 363752, "bbox": [263.84, 215.31, 112.85, 124.31], "category_id": 1, "id": 499085, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "sitting", "in", "the", "dugout"], "raw": "A baseball player sitting in the dugout", "sent_id": 53325, "sent": "a baseball player sitting in the dugout"}, {"tokens": ["a", "man", "in", "a", "white", "baseball", "uniform", "waiting", "in", "the", "dug", "out"], "raw": "A man in a white baseball uniform waiting in the dug out.", "sent_id": 53326, "sent": "a man in a white baseball uniform waiting in the dug out"}], "file_name": "COCO_train2014_000000363752_499085.jpg", "ann_id": 499085, "sent_ids": [53325, 53326], "ref_id": 25519}, {"segmentation": [[20.5, 359.3, 130.7, 358.45, 147.79, 329.4, 151.2, 38.1, 134.97, 16.74, 93.11, 10.76, 18.79, 17.6, 6.83, 42.37, 1.71, 332.82]], "area": 49161.19195, "iscrowd": 0, "image_id": 118413, "bbox": [1.71, 10.76, 149.49, 348.54], "category_id": 77, "id": 327856, "split": "val", "sentences": [{"tokens": ["a", "part", "of", "a", "cellphone", "to", "the", "far", "left"], "raw": "A part of a cellphone to the far left", "sent_id": 53348, "sent": "a part of a cellphone to the far left"}], "file_name": "COCO_train2014_000000118413_327856.jpg", "ann_id": 327856, "sent_ids": [53348], "ref_id": 25527}, {"segmentation": [[37.17, 324.12, 20.01, 317.45, 8.58, 298.39, 0.0, 279.33, 1.91, 178.31, 22.87, 149.72, 51.46, 134.47, 68.62, 132.56, 77.19, 125.89, 103.88, 114.45, 122.94, 107.78, 149.62, 106.83, 171.54, 108.74, 208.71, 115.41, 247.79, 121.13, 288.77, 123.98, 307.83, 130.66, 320.21, 155.43, 337.37, 182.12, 354.52, 212.62, 365.96, 230.72, 386.93, 224.05, 391.69, 231.68, 381.21, 255.5, 366.91, 279.33, 353.57, 303.15, 346.9, 319.35, 331.65, 324.12, 314.5, 341.27, 301.15, 355.57, 289.72, 356.52, 270.66, 351.76, 249.69, 351.76, 214.43, 355.57, 185.84, 357.47, 156.3, 363.19, 127.7, 374.63, 95.3, 371.77, 72.43, 366.05, 57.18, 353.66, 50.51, 341.27, 57.18, 323.17, 42.89, 326.98, 40.03, 325.07]], "area": 79218.24940000002, "iscrowd": 0, "image_id": 111040, "bbox": [0.0, 106.83, 391.69, 267.8], "category_id": 17, "id": 53055, "split": "val", "sentences": [{"tokens": ["a", "black", "cat", "is", "sleeping", "near", "another", "cat", "on", "top", "of", "a", "bed"], "raw": "a black cat is sleeping near another cat on top of a bed", "sent_id": 53397, "sent": "a black cat is sleeping near another cat on top of a bed"}, {"tokens": ["black", "cat", "curled", "up", "on", "cushion"], "raw": "black cat curled up on cushion", "sent_id": 53398, "sent": "black cat curled up on cushion"}], "file_name": "COCO_train2014_000000111040_53055.jpg", "ann_id": 53055, "sent_ids": [53397, 53398], "ref_id": 25547}, {"segmentation": [[230.11, 499.06, 195.6, 491.87, 191.28, 468.85, 178.34, 470.29, 156.76, 461.66, 146.7, 447.28, 119.37, 484.67, 97.8, 486.11, 92.04, 476.04, 104.99, 464.54, 123.69, 418.52, 142.38, 414.2, 148.13, 419.96, 152.45, 395.51, 143.82, 392.63, 149.57, 371.06, 156.76, 366.74, 169.71, 366.74, 165.39, 337.98, 178.34, 329.35, 198.47, 332.22, 208.54, 349.48, 207.1, 366.74, 215.73, 388.31, 217.17, 421.39, 232.99, 432.9, 235.87, 450.16, 215.73, 478.92, 228.67, 493.3]], "area": 11475.687399999999, "iscrowd": 0, "image_id": 285478, "bbox": [92.04, 329.35, 143.83, 169.71], "category_id": 1, "id": 1229296, "split": "val", "sentences": [{"tokens": ["a", "catcher", "about", "to", "catch", "a", "baseball"], "raw": "A catcher about to catch a baseball.", "sent_id": 53407, "sent": "a catcher about to catch a baseball"}, {"tokens": ["player", "crouching", "waiting", "for", "the", "pitch"], "raw": "player crouching waiting for the pitch", "sent_id": 53408, "sent": "player crouching waiting for the pitch"}], "file_name": "COCO_train2014_000000285478_1229296.jpg", "ann_id": 1229296, "sent_ids": [53407, 53408], "ref_id": 25549}, {"segmentation": [[180.99, 130.77, 169.88, 134.27, 169.26, 134.47, 159.6, 136.94, 159.19, 137.14, 151.99, 140.85, 146.44, 144.14, 146.23, 144.34, 135.13, 153.39, 126.69, 162.23, 123.2, 169.64, 113.12, 169.64, 109.42, 163.67, 104.07, 150.92, 95.64, 138.38, 86.18, 130.77, 72.81, 124.47, 61.71, 117.89, 57.8, 119.74, 60.27, 126.32, 66.44, 129.2, 83.71, 139.69, 91.73, 146.06, 98.11, 150.17, 100.16, 153.46, 106.33, 169.92, 104.69, 174.85, 101.6, 180.61, 103.87, 186.37, 105.1, 188.01, 116.21, 192.54, 124.43, 188.22, 127.72, 179.58, 125.87, 173.41, 132.04, 161.69, 139.86, 154.08, 153.63, 143.59, 165.77, 139.07, 182.63, 130.84]], "area": 1195.8581499999998, "iscrowd": 0, "image_id": 334259, "bbox": [57.8, 117.89, 124.83, 74.65], "category_id": 16, "id": 41670, "split": "val", "sentences": [{"tokens": ["a", "bird", "that", "has", "its", "wings", "completely", "spread", "out"], "raw": "A bird that has its wings completely spread out.", "sent_id": 53478, "sent": "a bird that has its wings completely spread out"}, {"tokens": ["a", "bird", "in", "flight", "with", "it", "'", "s", "wings", "up"], "raw": "A bird in flight with it's wings up", "sent_id": 53479, "sent": "a bird in flight with it ' s wings up"}], "file_name": "COCO_train2014_000000334259_41670.jpg", "ann_id": 41670, "sent_ids": [53478, 53479], "ref_id": 25582}, {"segmentation": [[350.07, 204.13, 328.59, 170.84, 324.3, 132.18, 343.62, 87.08, 366.17, 64.53, 404.83, 46.28, 453.15, 50.57, 503.62, 68.83, 546.58, 103.19, 565.91, 122.52, 580.94, 146.14, 585.23, 175.14, 590.6, 194.47, 585.23, 233.12, 565.91, 250.31, 555.17, 265.34, 539.06, 273.93, 502.55, 282.52, 464.97, 285.74, 428.46, 273.93, 391.95, 256.75, 371.54, 243.86, 356.51, 224.53, 355.44, 207.35]], "area": 47413.15215000001, "iscrowd": 0, "image_id": 244836, "bbox": [324.3, 46.28, 266.3, 239.46], "category_id": 51, "id": 1039003, "split": "val", "sentences": [{"tokens": ["a", "right", "bowl"], "raw": "a right bowl", "sent_id": 53504, "sent": "a right bowl"}, {"tokens": ["a", "slightly", "smaller", "bowl", "of", "food"], "raw": "A slightly smaller bowl of food.", "sent_id": 53505, "sent": "a slightly smaller bowl of food"}], "file_name": "COCO_train2014_000000244836_1039003.jpg", "ann_id": 1039003, "sent_ids": [53504, 53505], "ref_id": 25593}, {"segmentation": [[150.34, 94.6, 150.34, 67.75, 161.07, 35.54, 190.07, 24.8, 233.02, 4.4, 422.01, 3.33, 546.58, 3.33, 566.98, 54.87, 559.46, 88.16, 536.91, 123.59, 475.7, 205.2, 443.49, 206.28, 386.58, 196.61, 340.4, 197.69, 283.49, 205.2, 231.95, 201.98, 211.54, 190.17]], "area": 71061.46035, "iscrowd": 0, "image_id": 424503, "bbox": [150.34, 3.33, 416.64, 202.95], "category_id": 54, "id": 308925, "split": "val", "sentences": [{"tokens": ["the", "top", "sandiwc"], "raw": "The top sandiwc", "sent_id": 53535, "sent": "the top sandiwc"}, {"tokens": ["the", "sandwich", "behind", "the", "pickle"], "raw": "The sandwich behind the pickle", "sent_id": 53536, "sent": "the sandwich behind the pickle"}], "file_name": "COCO_train2014_000000424503_308925.jpg", "ann_id": 308925, "sent_ids": [53535, 53536], "ref_id": 25607}, {"segmentation": [[462.49, 272.84, 573.4, 252.87, 575.62, 265.07, 539.02, 276.16, 540.13, 320.53, 453.62, 312.76, 421.45, 320.53, 417.02, 276.16, 469.15, 268.4], [527.93, 358.24, 544.56, 370.44, 611.11, 339.38, 628.85, 349.36, 638.84, 388.18, 634.4, 419.24, 552.33, 414.8, 527.93, 363.78]], "area": 12399.263350000001, "iscrowd": 0, "image_id": 235582, "bbox": [417.02, 252.87, 221.82, 166.37], "category_id": 67, "id": 1965586, "split": "val", "sentences": [{"tokens": ["table", "top", "between", "the", "woman", "in", "glasses", "and", "the", "seated", "man"], "raw": "Table top between the woman in glasses and the seated man.", "sent_id": 53563, "sent": "table top between the woman in glasses and the seated man"}, {"tokens": ["wooden", "table", "with", "a", "cake"], "raw": "Wooden table with a cake", "sent_id": 53564, "sent": "wooden table with a cake"}], "file_name": "COCO_train2014_000000235582_1965586.jpg", "ann_id": 1965586, "sent_ids": [53563, 53564], "ref_id": 25615}, {"segmentation": [[83.23, 250.51, 106.67, 248.08, 135.76, 226.26, 142.22, 213.33, 162.42, 209.29, 172.93, 210.91, 187.47, 209.29, 197.17, 203.64, 216.57, 191.52, 225.45, 181.82, 225.45, 174.55, 205.25, 162.42, 189.9, 155.15, 164.85, 138.18, 155.15, 137.37, 108.28, 135.76, 101.82, 137.37, 88.08, 128.48, 71.11, 120.4, 58.99, 121.21, 56.57, 126.06, 44.44, 126.06, 33.13, 123.64, 19.39, 131.72, 3.23, 143.03, 1.62, 152.73, 4.85, 157.58, 16.16, 164.04, 21.82, 167.27, 18.59, 176.97, 19.39, 196.36, 24.24, 216.57, 34.75, 231.92, 36.36, 242.42, 40.4, 265.05, 40.4, 281.21, 61.41, 282.02, 66.26, 266.67, 61.41, 246.46, 72.73, 249.7, 81.62, 252.12, 91.31, 250.51]], "area": 19267.258000000005, "iscrowd": 0, "image_id": 296760, "bbox": [1.62, 120.4, 223.83, 161.62], "category_id": 18, "id": 8070, "split": "val", "sentences": [{"tokens": ["tan", "and", "white", "dog", "on", "the", "edge", "of", "a", "bed"], "raw": "tan and white dog on the edge of a bed", "sent_id": 53639, "sent": "tan and white dog on the edge of a bed"}, {"tokens": ["a", "tan", "dog"], "raw": "A tan dog.", "sent_id": 53640, "sent": "a tan dog"}], "file_name": "COCO_train2014_000000296760_8070.jpg", "ann_id": 8070, "sent_ids": [53639, 53640], "ref_id": 25643}, {"segmentation": [[232.71, 292.86, 258.07, 294.35, 259.56, 288.38, 241.66, 278.68, 238.67, 269.73, 242.4, 252.58, 252.85, 245.12, 252.85, 239.15, 258.07, 233.18, 258.81, 207.08, 258.81, 192.16, 258.07, 180.97, 262.54, 184.7, 267.02, 186.19, 270.75, 177.24, 264.78, 169.78, 261.8, 168.29, 265.53, 166.05, 273.73, 171.27, 278.21, 175.75, 278.21, 174.26, 281.19, 175.75, 281.19, 169.78, 282.68, 166.05, 279.7, 160.83, 269.26, 155.61, 257.32, 149.64, 249.86, 119.06, 257.32, 117.57, 253.59, 112.35, 256.58, 108.62, 259.56, 108.62, 257.32, 104.89, 260.31, 101.16, 254.34, 87.73, 240.17, 86.24, 234.95, 91.46, 233.45, 99.67, 234.2, 101.91, 225.99, 106.38, 225.99, 110.86, 219.28, 128.76, 220.77, 149.64, 223.01, 162.32, 223.76, 170.53, 222.27, 185.45, 228.23, 195.89, 235.69, 201.86, 237.18, 210.06, 231.96, 218.27, 232.71, 224.98, 223.01, 244.37, 217.04, 253.32, 214.06, 257.8, 207.35, 280.92, 209.58, 291.36, 223.01, 294.35]], "area": 6865.12935, "iscrowd": 0, "image_id": 32575, "bbox": [207.35, 86.24, 75.33, 208.11], "category_id": 1, "id": 460087, "split": "val", "sentences": [{"tokens": ["a", "skier", "in", "a", "yellow", "jacket"], "raw": "a skier in a yellow jacket", "sent_id": 53655, "sent": "a skier in a yellow jacket"}, {"tokens": ["a", "skier", "in", "yellow", ",", "blue", ",", "orange", ",", "and", "pink", "clothing"], "raw": "A skier in yellow, blue, orange, and pink clothing.", "sent_id": 53656, "sent": "a skier in yellow , blue , orange , and pink clothing"}], "file_name": "COCO_train2014_000000032575_460087.jpg", "ann_id": 460087, "sent_ids": [53655, 53656], "ref_id": 25648}, {"segmentation": [[318.2, 471.37, 381.84, 435.78, 374.29, 436.85, 401.26, 426.07, 508.04, 413.12, 577.08, 416.36, 612.67, 423.91, 636.4, 430.38, 637.48, 433.62, 640.0, 472.45]], "area": 14517.859649999999, "iscrowd": 0, "image_id": 298014, "bbox": [318.2, 413.12, 321.8, 59.33], "category_id": 3, "id": 356638, "split": "val", "sentences": [{"tokens": ["the", "top", "of", "a", "moving", "car"], "raw": "The top of a moving car.", "sent_id": 53697, "sent": "the top of a moving car"}, {"tokens": ["black", "car", "going", "through", "an", "intersection"], "raw": "Black car going through an intersection", "sent_id": 53698, "sent": "black car going through an intersection"}], "file_name": "COCO_train2014_000000298014_356638.jpg", "ann_id": 356638, "sent_ids": [53697, 53698], "ref_id": 25666}, {"segmentation": [[136.63, 465.98, 159.64, 474.61, 163.96, 448.72, 153.89, 417.08, 148.13, 371.06, 185.53, 286.2, 186.97, 257.44, 186.97, 234.43, 186.97, 194.16, 169.71, 159.64, 142.38, 153.89, 133.75, 142.38, 143.82, 123.69, 143.82, 107.87, 135.19, 97.8, 109.3, 96.36, 96.36, 100.67, 87.73, 122.25, 87.73, 138.07, 106.43, 148.13, 97.8, 158.2, 80.54, 163.96, 76.22, 188.4, 74.79, 224.36, 66.16, 270.38, 61.84, 310.65, 67.6, 332.22, 76.22, 320.72, 77.66, 303.46, 92.04, 232.99, 93.48, 202.79, 96.36, 192.72, 103.55, 209.98, 103.55, 247.37, 96.36, 279.01, 94.92, 303.46, 89.17, 342.29, 79.1, 369.62, 66.16, 424.27, 63.28, 442.97, 57.53, 438.65, 48.9, 450.16, 58.97, 478.92, 74.79, 484.67, 113.62, 365.3, 129.44, 447.28]], "area": 29390.813699999995, "iscrowd": 0, "image_id": 243354, "bbox": [48.9, 96.36, 138.07, 388.31], "category_id": 1, "id": 464027, "split": "val", "sentences": [{"tokens": ["a", "boy", "wearing", "a", "white", "shirt", "and", "blue", "jeans", "standing", "on", "a", "skateboard"], "raw": "A boy wearing a white shirt and blue jeans standing on a skateboard.", "sent_id": 53701, "sent": "a boy wearing a white shirt and blue jeans standing on a skateboard"}, {"tokens": ["a", "person", "wearing", "a", "white", "shirt", "who", "is", "riding", "a", "skateboard"], "raw": "A person wearing a white shirt who is riding a skateboard.", "sent_id": 53702, "sent": "a person wearing a white shirt who is riding a skateboard"}], "file_name": "COCO_train2014_000000243354_464027.jpg", "ann_id": 464027, "sent_ids": [53701, 53702], "ref_id": 25668}, {"segmentation": [[87.07, 168.34, 162.54, 161.09, 168.34, 119.0, 181.41, 126.26, 191.56, 165.44, 214.78, 168.34, 216.24, 155.28, 235.1, 177.05, 297.51, 172.7, 296.05, 179.95, 251.07, 191.56, 246.71, 217.69, 258.32, 287.35, 175.6, 201.72]], "area": 8696.0406, "iscrowd": 0, "image_id": 116040, "bbox": [87.07, 119.0, 210.44, 168.35], "category_id": 5, "id": 160106, "split": "val", "sentences": [{"tokens": ["a", "white", "red", "and", "blue", "airplane", "in", "the", "sky", "next", "to", "2", "other", "planes"], "raw": "A white red and blue airplane in the sky next to 2 other planes", "sent_id": 53737, "sent": "a white red and blue airplane in the sky next to 2 other planes"}], "file_name": "COCO_train2014_000000116040_160106.jpg", "ann_id": 160106, "sent_ids": [53737], "ref_id": 25680}, {"segmentation": [[320.56, 406.52, 316.52, 376.18, 322.58, 355.96, 323.6, 333.71, 340.79, 316.52, 369.1, 314.49, 416.63, 314.49, 456.07, 321.57, 469.21, 326.63, 501.57, 329.66, 513.71, 343.82, 523.82, 375.17, 521.8, 389.33, 525.84, 408.54, 520.79, 425.73, 506.63, 432.81, 469.21, 432.81, 448.99, 430.79, 422.7, 426.74, 399.44, 427.75, 382.25, 427.75, 364.04, 426.74, 342.81, 420.67, 324.61, 411.57]], "area": 21240.054200000002, "iscrowd": 0, "image_id": 423890, "bbox": [316.52, 314.49, 209.32, 118.32], "category_id": 59, "id": 1076655, "split": "val", "sentences": [{"tokens": ["the", "pizza", "on", "the", "left", "without", "mozzarella", "cheese"], "raw": "The pizza on the left without mozzarella cheese.", "sent_id": 53738, "sent": "the pizza on the left without mozzarella cheese"}, {"tokens": ["pizza", "on", "the", "right", "with", "spinach"], "raw": "Pizza on the right with spinach.", "sent_id": 53739, "sent": "pizza on the right with spinach"}], "file_name": "COCO_train2014_000000423890_1076655.jpg", "ann_id": 1076655, "sent_ids": [53738, 53739], "ref_id": 25681}, {"segmentation": [[292.44, 327.55, 304.88, 322.97, 309.47, 316.42, 313.4, 296.12, 319.95, 296.12, 334.35, 317.73, 339.59, 344.58, 346.79, 351.78, 352.69, 391.73, 359.24, 407.44, 359.24, 424.47, 364.48, 423.16, 372.99, 409.41, 372.33, 402.2, 370.37, 397.62, 380.19, 352.44, 399.84, 347.2, 402.46, 346.54, 404.42, 357.67, 391.98, 386.49, 397.22, 393.69, 401.8, 387.8, 414.9, 348.51, 417.52, 339.34, 418.83, 332.14, 422.76, 324.93, 431.27, 352.44, 433.89, 373.39, 431.92, 393.04, 438.47, 392.38, 441.09, 379.94, 441.09, 351.78, 441.75, 341.96, 439.13, 330.83, 439.13, 317.73, 446.33, 305.29, 424.07, 277.13, 405.08, 312.49, 399.84, 309.22, 393.94, 304.63, 388.7, 282.37, 376.26, 267.31, 365.79, 267.96, 361.2, 269.92, 321.26, 252.24, 314.71, 252.24, 312.74, 245.04, 308.81, 245.7, 301.61, 254.21, 289.17, 248.97, 287.86, 248.97, 285.89, 260.1, 287.2, 275.16, 280.66, 279.75, 285.24, 290.22, 279.35, 298.74, 276.07, 322.31]], "area": 12511.664999999999, "iscrowd": 0, "image_id": 154257, "bbox": [276.07, 245.04, 170.26, 179.43], "category_id": 19, "id": 275053, "split": "val", "sentences": [{"tokens": ["the", "horse", "on", "the", "left", "closest", "to", "the", "water"], "raw": "The horse on the left closest to the water", "sent_id": 53748, "sent": "the horse on the left closest to the water"}, {"tokens": ["a", "dark", "brown", "horse", "walking", "on", "the", "beach"], "raw": "a dark brown horse walking on the beach.", "sent_id": 53749, "sent": "a dark brown horse walking on the beach"}], "file_name": "COCO_train2014_000000154257_275053.jpg", "ann_id": 275053, "sent_ids": [53748, 53749], "ref_id": 25686}, {"segmentation": [[640.0, 221.25, 603.74, 214.3, 581.9, 214.3, 562.05, 206.36, 545.17, 205.37, 541.2, 156.73, 509.44, 124.97, 480.66, 106.11, 438.97, 81.3, 393.31, 84.28, 375.45, 97.18, 363.54, 121.99, 359.57, 135.89, 353.61, 167.65, 369.49, 211.32, 392.32, 248.05, 400.26, 258.97, 410.19, 270.88, 481.65, 237.13, 526.32, 247.06, 556.09, 263.93, 581.9, 290.73, 602.74, 320.51, 615.65, 416.78, 608.7, 434.65, 587.86, 452.52, 579.91, 474.35, 640.0, 479.32, 638.56, 226.52], [430.38, 276.13, 378.61, 349.48, 381.84, 400.18, 381.84, 416.36, 381.84, 431.46, 386.16, 447.64, 387.24, 461.66, 392.63, 469.21, 558.74, 472.45, 582.47, 436.85, 587.87, 401.26, 593.26, 364.58, 567.37, 302.02, 533.93, 275.06, 512.36, 263.19, 487.55, 253.48, 458.43, 255.64, 433.62, 271.82]], "area": 77465.74369999998, "iscrowd": 0, "image_id": 323030, "bbox": [353.61, 81.3, 286.39, 398.02], "category_id": 1, "id": 1716113, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "baseball", "cap", "and", "sunglasses"], "raw": "A man wearing a baseball cap and sunglasses.", "sent_id": 53812, "sent": "a man wearing a baseball cap and sunglasses"}, {"tokens": ["male", "tennis", "player"], "raw": "Male tennis player", "sent_id": 53813, "sent": "male tennis player"}], "file_name": "COCO_train2014_000000323030_1716113.jpg", "ann_id": 1716113, "sent_ids": [53812, 53813], "ref_id": 25710}, {"segmentation": [[68.29, 226.98, 68.29, 198.13, 74.06, 178.89, 81.75, 175.05, 76.94, 161.58, 76.94, 158.7, 88.49, 149.08, 95.22, 147.16, 103.87, 147.16, 106.76, 152.93, 106.76, 160.62, 93.29, 162.54, 98.1, 171.2, 101.95, 171.2, 123.11, 175.05, 132.73, 177.93, 128.88, 188.51, 128.88, 188.51, 125.03, 215.44, 123.11, 220.25, 107.72, 220.25, 105.8, 222.18, 100.03, 226.02, 102.91, 246.22, 113.49, 256.8, 119.26, 269.3, 140.42, 271.23, 153.89, 269.3, 178.89, 256.8, 192.36, 254.88, 203.9, 253.91, 208.71, 246.22, 220.25, 247.18, 230.83, 246.22, 233.72, 244.3, 244.3, 242.37, 254.88, 240.45, 265.46, 237.56, 272.19, 237.56, 277.0, 236.6, 280.84, 236.6, 277.0, 226.98, 281.81, 220.25, 282.77, 206.79, 282.77, 199.09, 286.62, 195.24, 288.54, 196.21, 292.39, 165.43, 305.85, 152.93, 337.59, 149.08, 356.83, 163.51, 361.64, 167.35, 362.6, 185.63, 361.64, 201.98, 364.52, 207.75, 363.56, 228.91, 355.87, 234.68, 353.94, 235.64, 352.98, 249.11, 354.9, 252.95, 380.87, 257.76, 406.84, 262.57, 428.0, 253.91, 450.12, 235.64, 491.48, 175.05, 486.67, 172.16, 505.91, 174.09, 508.79, 181.78, 520.33, 170.24, 536.68, 157.73, 543.42, 150.04, 554.0, 158.7, 558.8, 162.54, 550.15, 162.54, 540.53, 167.35, 566.5, 162.54, 565.54, 166.39, 563.61, 173.12, 545.34, 181.78, 565.54, 176.01, 568.42, 182.74, 562.65, 185.63, 542.45, 194.28, 538.61, 196.21, 556.88, 195.24, 563.61, 201.02, 555.92, 204.86, 538.61, 205.82, 534.76, 205.82, 518.41, 214.48, 534.76, 284.69, 532.84, 323.16, 534.76, 335.67, 534.76, 345.29, 539.57, 362.6, 541.49, 377.99, 543.42, 390.49, 542.45, 419.34, 524.18, 422.23, 525.14, 421.27, 520.33, 423.19, 510.71, 399.15, 511.68, 376.06, 505.91, 328.93, 501.1, 308.74, 494.36, 264.49, 495.33, 252.95, 467.43, 275.07, 451.08, 295.27, 442.43, 317.39, 423.19, 327.01, 418.38, 327.01, 417.42, 327.97, 422.23, 367.41, 426.08, 403.96, 420.31, 423.19, 384.72, 423.19, 380.87, 384.72, 384.72, 361.64, 389.53, 337.59, 383.76, 334.71, 381.83, 365.48, 377.02, 386.64, 380.87, 406.84, 380.87, 422.23, 173.12, 422.23, 184.67, 343.36, 141.38, 344.32, 120.22, 347.21, 103.87, 331.82, 95.22, 326.05, 83.68, 329.9, 74.06, 313.55, 62.52, 295.27, 64.44, 272.19, 61.56, 269.3, 62.52, 249.11, 60.59, 242.37]], "area": 76103.05485000006, "iscrowd": 0, "image_id": 422354, "bbox": [60.59, 147.16, 507.83, 276.03], "category_id": 1, "id": 509905, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "a", "pink", "cloth", "and", "a", "plastic", "cup", "in", "his", "right", "hand"], "raw": "The man with a pink cloth and a plastic cup in his right hand.", "sent_id": 54051, "sent": "the man with a pink cloth and a plastic cup in his right hand"}, {"tokens": ["a", "man", "wearing", "a", "pink", "scarf"], "raw": "A man wearing a pink scarf.", "sent_id": 54052, "sent": "a man wearing a pink scarf"}], "file_name": "COCO_train2014_000000422354_509905.jpg", "ann_id": 509905, "sent_ids": [54051, 54052], "ref_id": 25793}, {"segmentation": [[530.45, 144.98, 506.0, 151.23, 493.49, 153.51, 493.49, 138.72, 475.87, 139.29, 474.73, 150.09, 457.11, 132.47, 454.26, 65.38, 527.04, 45.48, 610.61, 47.19, 620.84, 137.59, 579.34, 141.0, 583.89, 154.64, 564.56, 158.62, 554.33, 143.27]], "area": 15182.951200000003, "iscrowd": 0, "image_id": 396825, "bbox": [454.26, 45.48, 166.58, 113.14], "category_id": 6, "id": 166048, "split": "val", "sentences": [{"tokens": ["a", "bus", "was", "going", "on", "the", "road"], "raw": "a bus was going on the road", "sent_id": 54061, "sent": "a bus was going on the road"}, {"tokens": ["bus", "with", "the", "number", "3501"], "raw": "Bus with the number 3501", "sent_id": 54062, "sent": "bus with the number 3501"}], "file_name": "COCO_train2014_000000396825_166048.jpg", "ann_id": 166048, "sent_ids": [54061, 54062], "ref_id": 25796}, {"segmentation": [[208.46, 439.71, 201.94, 418.0, 194.34, 397.37, 188.91, 375.66, 179.14, 356.11, 174.8, 334.4, 169.37, 309.43, 170.46, 262.74, 174.8, 247.54, 163.94, 225.83, 140.06, 185.66, 124.86, 166.11, 119.43, 144.4, 149.83, 132.46, 212.8, 135.71, 242.11, 127.03, 234.51, 95.54, 243.2, 82.51, 254.06, 73.83, 268.17, 69.49, 280.11, 67.31, 301.83, 84.69, 308.34, 104.23, 307.26, 122.69, 319.2, 136.8, 328.97, 161.77, 330.06, 185.66, 332.23, 221.49, 324.63, 252.97, 331.14, 260.57, 336.57, 276.86, 340.91, 301.83, 342.0, 322.46, 342.0, 343.09, 343.09, 363.71, 344.17, 383.26, 343.09, 393.03, 342.0, 403.89, 342.0, 409.31, 349.6, 425.6, 356.11, 437.54, 353.94, 447.31, 338.74, 451.66, 324.63, 445.14, 315.94, 435.37, 307.26, 416.91, 305.09, 398.46, 300.74, 369.14, 292.06, 331.14, 287.71, 318.11, 255.14, 309.43, 247.54, 328.97, 247.54, 356.11, 252.97, 375.66, 256.23, 396.29, 256.23, 412.57, 255.14, 427.77, 255.14, 439.71, 250.8, 442.97, 220.4, 446.23, 210.63, 441.89]], "area": 49899.849650000004, "iscrowd": 0, "image_id": 558804, "bbox": [119.43, 67.31, 236.68, 384.35], "category_id": 1, "id": 543177, "split": "val", "sentences": [{"tokens": ["baseball", "player", "on", "left", "side", ",", "holding", "bat", "by", "his", "leg"], "raw": "baseball player on left side, holding bat by his leg", "sent_id": 54133, "sent": "baseball player on left side , holding bat by his leg"}, {"tokens": ["red", "sox", "baseball", "player", "posing", "for", "picture", "with", "right", "hand", "on", "end", "of", "bat", "that", "is", "to", "his", "right", "side"], "raw": "Red Sox baseball player posing for picture with right hand on end of bat that is to his right side", "sent_id": 54134, "sent": "red sox baseball player posing for picture with right hand on end of bat that is to his right side"}], "file_name": "COCO_train2014_000000558804_543177.jpg", "ann_id": 543177, "sent_ids": [54133, 54134], "ref_id": 25830}, {"segmentation": [[283.19, 293.85, 356.06, 276.77, 409.57, 263.68, 418.11, 272.22, 354.35, 319.47, 231.38, 339.97, 193.81, 345.09, 186.97, 330.86, 190.39, 316.63, 198.36, 313.21], [409.57, 292.15, 461.94, 254.57, 489.84, 253.43, 500.09, 252.86, 451.13, 290.44, 415.26, 314.35, 404.45, 309.22, 406.72, 297.27], [521.72, 251.73, 545.06, 256.28, 545.63, 264.25, 524.0, 293.28, 471.05, 297.84, 490.98, 279.05, 509.2, 260.83], [271.8, 258.56, 348.09, 238.06, 448.28, 211.87, 483.58, 206.18, 461.94, 234.08, 334.42, 270.51, 201.21, 305.24, 188.11, 300.12, 184.13, 291.01, 181.28, 283.61, 205.76, 270.51, 221.13, 264.82, 229.67, 262.54, 251.3, 262.54], [485.29, 206.18, 501.8, 201.06, 521.15, 200.49, 497.81, 214.72, 471.62, 230.66, 464.22, 230.66, 469.35, 218.71], [537.09, 187.39, 575.23, 183.98, 575.23, 195.93, 547.91, 212.44, 496.1, 234.08, 502.36, 219.28, 516.03, 207.89]], "area": 21780.088700000008, "iscrowd": 0, "image_id": 276874, "bbox": [181.28, 183.98, 393.95, 161.11], "category_id": 35, "id": 2202401, "split": "val", "sentences": [{"tokens": ["a", "green", "and", "white", "ski", "with", "an", "x", "on", "it"], "raw": "A green and white ski with an x on it.", "sent_id": 54252, "sent": "a green and white ski with an x on it"}, {"tokens": ["ski", "that", "says", "oslo", "and", "the", "one", "underneath"], "raw": "ski that says oslo and the one underneath", "sent_id": 54253, "sent": "ski that says oslo and the one underneath"}], "file_name": "COCO_train2014_000000276874_2202401.jpg", "ann_id": 2202401, "sent_ids": [54252, 54253], "ref_id": 25877}, {"segmentation": [[55.91, 494.62, 55.91, 480.65, 59.14, 462.37, 61.29, 455.91, 59.14, 449.46, 62.37, 444.09, 63.44, 435.48, 53.44, 433.96, 44.43, 391.31, 70.26, 391.31, 63.65, 385.3, 59.45, 385.91, 60.65, 378.1, 65.46, 372.69, 70.26, 377.5, 69.06, 380.5, 74.47, 385.91, 82.28, 386.51, 89.48, 387.11, 94.89, 387.11, 102.7, 379.3, 115.31, 377.5, 115.91, 383.5, 126.13, 382.3, 126.73, 371.49, 127.93, 367.88, 136.34, 373.29, 133.94, 395.52, 128.53, 405.13, 135.74, 418.94, 132.13, 430.36, 128.53, 430.96, 130.33, 439.97, 142.95, 439.37, 136.94, 445.97, 127.93, 452.58, 123.72, 473.01, 123.12, 460.39, 124.92, 443.57, 125.53, 425.55, 125.53, 413.54, 123.72, 400.92, 115.31, 386.51, 100.3, 391.91, 103.9, 405.73, 103.3, 421.95, 103.3, 434.56, 103.9, 448.38, 100.9, 464.0, 100.9, 471.8, 94.29, 477.21, 91.89, 488.62, 91.89, 488.62, 90.08, 499.44, 57.05, 499.44], [104.5, 471.2, 108.11, 471.2, 110.51, 483.22, 118.92, 482.02, 115.91, 486.82, 109.91, 486.82, 105.1, 483.22]], "area": 6301.43955, "iscrowd": 0, "image_id": 423776, "bbox": [44.43, 367.88, 98.52, 131.56], "category_id": 2, "id": 127694, "split": "val", "sentences": [{"tokens": ["the", "bike", "of", "the", "girl", "in", "front", "wearing", "white", "t", "-", "shirt"], "raw": "the bike of the girl in front wearing white t-shirt", "sent_id": 54280, "sent": "the bike of the girl in front wearing white t - shirt"}, {"tokens": ["the", "bicycle", "with", "the", "basket", "the", "woman", "'", "s", "riding", "on"], "raw": "The bicycle with the basket the woman's riding on.", "sent_id": 54281, "sent": "the bicycle with the basket the woman ' s riding on"}], "file_name": "COCO_train2014_000000423776_127694.jpg", "ann_id": 127694, "sent_ids": [54280, 54281], "ref_id": 25886}, {"segmentation": [[168.97, 171.3, 177.29, 244.21, 144.99, 251.55, 1.14, 260.35, 0.0, 155.64, 0.0, 68.55, 0.65, 0.0, 156.74, 0.0, 159.67, 48.0, 165.54, 134.6]], "area": 42180.37595000001, "iscrowd": 0, "image_id": 183788, "bbox": [0.0, 0.0, 177.29, 260.35], "category_id": 84, "id": 1147781, "split": "val", "sentences": [{"tokens": ["drawings", "of", "saints", "in", "a", "sketch", "book"], "raw": "drawings of saints in a sketch book", "sent_id": 54368, "sent": "drawings of saints in a sketch book"}, {"tokens": ["white", "paper", "wrapped", "around", "a", "book", "with", "line", "drawing"], "raw": "White paper wrapped around a book with line drawing", "sent_id": 54369, "sent": "white paper wrapped around a book with line drawing"}], "file_name": "COCO_train2014_000000183788_1147781.jpg", "ann_id": 1147781, "sent_ids": [54368, 54369], "ref_id": 25923}, {"segmentation": [[248.22, 198.2, 160.45, 153.84, 126.47, 134.02, 124.58, 117.03, 168.94, 110.43, 209.53, 106.65, 350.16, 173.66, 432.27, 134.97, 453.03, 146.29, 417.17, 181.21, 403.96, 187.82, 388.85, 191.6, 369.98, 187.82, 294.47, 180.27, 332.22, 201.03, 260.49, 204.81], [369.03, 237.84, 412.45, 223.69, 447.37, 206.7, 458.7, 219.91, 475.69, 243.51, 396.4, 250.11]], "area": 16669.495300000002, "iscrowd": 0, "image_id": 183022, "bbox": [124.58, 106.65, 351.11, 143.46], "category_id": 5, "id": 159427, "split": "val", "sentences": [{"tokens": ["space", "shuttle", "being", "taxied", "by", "a", "jumbo", "jet"], "raw": "space shuttle being taxied by a jumbo jet", "sent_id": 54376, "sent": "space shuttle being taxied by a jumbo jet"}, {"tokens": ["ship", "on", "top", "of", "airplane"], "raw": "Ship on top of airplane.", "sent_id": 54377, "sent": "ship on top of airplane"}], "file_name": "COCO_train2014_000000183022_159427.jpg", "ann_id": 159427, "sent_ids": [54376, 54377], "ref_id": 25926}, {"segmentation": [[164.77, 99.53, 164.77, 47.29, 442.07, 57.34, 439.06, 73.41, 439.06, 82.45, 439.06, 94.51, 417.96, 99.53, 398.87, 100.54, 365.71, 99.53, 352.65, 96.52, 344.61, 90.49, 328.54, 90.49, 334.57, 123.65, 305.43, 123.65, 305.43, 103.55, 306.44, 90.49, 296.39, 90.49, 284.33, 95.51, 267.25, 99.53, 246.15, 98.53, 230.08, 98.53, 206.97, 94.51, 197.93, 90.49, 193.91, 84.46, 181.85, 84.46, 182.86, 101.54, 183.86, 104.56, 166.78, 101.54]], "area": 12881.23955, "iscrowd": 0, "image_id": 197525, "bbox": [164.77, 47.29, 277.3, 76.36], "category_id": 67, "id": 121880, "split": "val", "sentences": [{"tokens": ["an", "empty", "table", "with", "seven", "chairs"], "raw": "An empty table with seven chairs.", "sent_id": 54429, "sent": "an empty table with seven chairs"}, {"tokens": ["a", "table", "partially", "cover", "with", "a", "red", "cloth", ",", "a", "white", "plate", ",", "and", "other", "various", "items"], "raw": "A table partially cover with a red cloth, a white plate, and other various items.", "sent_id": 54430, "sent": "a table partially cover with a red cloth , a white plate , and other various items"}], "file_name": "COCO_train2014_000000197525_121880.jpg", "ann_id": 121880, "sent_ids": [54429, 54430], "ref_id": 25946}, {"segmentation": [[475.88, 0.62, 447.04, 27.4, 426.44, 161.3, 426.44, 174.7, 430.56, 172.64, 510.9, 71.69, 525.32, 49.03, 551.07, 45.94, 550.04, 26.37, 540.77, 0.62], [539.74, 112.89, 516.05, 207.66, 463.52, 195.3, 520.17, 131.43]], "area": 12808.518649999998, "iscrowd": 0, "image_id": 226046, "bbox": [426.44, 0.62, 124.63, 207.04], "category_id": 44, "id": 88236, "split": "val", "sentences": [{"tokens": ["the", "bottle"], "raw": "The bottle.", "sent_id": 54680, "sent": "the bottle"}], "file_name": "COCO_train2014_000000226046_88236.jpg", "ann_id": 88236, "sent_ids": [54680], "ref_id": 26040}, {"segmentation": [[638.93, 64.58, 632.48, 77.47, 629.26, 84.99, 631.41, 91.43, 606.71, 147.27, 586.31, 175.19, 572.35, 194.52, 568.05, 215.99, 564.83, 229.95, 558.39, 256.8, 548.72, 287.94, 542.28, 306.19, 549.8, 326.6, 573.42, 343.78, 598.12, 343.78, 618.52, 337.33, 620.67, 316.93, 624.97, 305.12, 638.93, 270.76]], "area": 14733.101049999988, "iscrowd": 0, "image_id": 447374, "bbox": [542.28, 64.58, 96.65, 279.2], "category_id": 44, "id": 78641, "split": "val", "sentences": [{"tokens": ["bottle", "of", "wine", "below", "the", "sushi", "tray"], "raw": "bottle of wine below the sushi tray", "sent_id": 54769, "sent": "bottle of wine below the sushi tray"}, {"tokens": ["bottle", "of", "liquid", "in", "front", "of", "sushi"], "raw": "Bottle of liquid in front of sushi.", "sent_id": 54770, "sent": "bottle of liquid in front of sushi"}], "file_name": "COCO_train2014_000000447374_78641.jpg", "ann_id": 78641, "sent_ids": [54769, 54770], "ref_id": 26072}, {"segmentation": [[106.66, 88.16, 102.3, 84.67, 66.53, 80.31, 60.85, 80.31, 66.09, 70.27, 69.14, 53.26, 80.05, 33.19, 99.68, 17.92, 117.13, 13.56, 142.43, 2.65, 156.39, 3.96, 183.44, 0.04, 192.6, 0.04, 205.25, 7.02, 225.76, 11.38, 256.3, 30.14, 265.46, 38.43, 260.22, 38.86, 240.16, 60.24, 239.28, 63.73, 220.52, 66.35, 181.26, 80.31, 178.64, 82.92, 176.46, 81.62, 148.98, 80.74, 152.03, 67.65, 152.03, 64.6, 152.03, 58.93, 149.41, 53.26, 143.74, 48.02, 140.69, 44.1, 132.84, 41.48, 128.04, 41.48, 115.39, 47.59, 110.59, 52.82, 107.53, 59.37, 109.72, 70.71, 111.9, 73.76, 113.64, 78.13, 116.26, 84.23, 114.51, 85.11]], "area": 10482.651500000002, "iscrowd": 0, "image_id": 184224, "bbox": [60.85, 0.04, 204.61, 88.12], "category_id": 28, "id": 285530, "split": "val", "sentences": [{"tokens": ["a", "unbrella", "held", "my", "a", "woman"], "raw": "a unbrella held my a woman", "sent_id": 54875, "sent": "a unbrella held my a woman"}, {"tokens": ["plaid", "style", "umbrella", "being", "held", "by", "a", "gray", "haired", "woman"], "raw": "Plaid style umbrella being held by a gray haired woman.", "sent_id": 54876, "sent": "plaid style umbrella being held by a gray haired woman"}], "file_name": "COCO_train2014_000000184224_285530.jpg", "ann_id": 285530, "sent_ids": [54875, 54876], "ref_id": 26106}, {"segmentation": [[92.32, 169.26, 92.32, 130.79, 116.37, 91.36, 233.7, 87.52, 282.74, 84.63, 339.48, 154.84, 365.45, 197.15, 373.14, 205.81, 399.11, 212.54, 404.88, 219.27, 384.68, 227.93, 387.57, 239.47, 393.34, 246.2, 387.57, 275.05, 388.53, 305.82, 390.45, 319.29, 381.8, 328.91, 368.34, 329.87, 356.8, 323.14, 355.83, 306.79, 337.56, 274.09, 336.6, 243.31, 317.36, 198.11, 309.67, 199.07, 294.28, 228.89, 285.63, 253.89, 307.75, 291.4, 299.09, 297.17, 295.25, 290.44, 288.51, 279.86, 281.78, 297.17, 281.78, 305.82, 290.44, 318.33, 277.93, 322.17, 263.51, 290.44, 267.36, 246.2, 261.59, 205.81, 252.93, 207.73, 230.81, 208.69, 207.73, 212.54, 187.53, 203.88, 168.3, 254.85, 190.42, 308.71, 206.77, 325.06, 183.69, 329.87, 183.69, 322.17, 174.07, 318.33, 144.26, 251.97, 149.07, 213.5, 139.45, 201.96, 121.18, 262.55, 116.37, 307.75, 127.91, 338.52, 109.64, 341.41, 102.9, 336.6, 107.71, 327.94, 103.86, 317.36, 95.21, 248.12, 103.86, 221.19, 91.36, 168.3]], "area": 42799.63785, "iscrowd": 0, "image_id": 413297, "bbox": [91.36, 84.63, 313.52, 256.78], "category_id": 24, "id": 588472, "split": "val", "sentences": [{"tokens": ["a", "black", "and", "white", "zebra", "eating", "grass", "in", "a", "field"], "raw": "A black and white zebra eating grass in a field", "sent_id": 54881, "sent": "a black and white zebra eating grass in a field"}, {"tokens": ["one", "zebra", "closest", "to", "the", "camera"], "raw": "One zebra closest to the camera.", "sent_id": 54882, "sent": "one zebra closest to the camera"}], "file_name": "COCO_train2014_000000413297_588472.jpg", "ann_id": 588472, "sent_ids": [54881, 54882], "ref_id": 26109}, {"segmentation": [[126.2, 304.18, 121.35, 278.29, 121.35, 222.47, 121.35, 211.15, 115.69, 206.29, 116.49, 172.31, 111.64, 156.94, 111.64, 174.74, 113.26, 182.02, 105.17, 170.7, 105.17, 135.91, 109.21, 127.01, 118.11, 118.92, 117.3, 114.07, 128.63, 110.83, 131.87, 108.4, 131.87, 101.93, 135.91, 95.46, 142.38, 94.65, 155.33, 101.93, 155.33, 110.02, 156.94, 115.69, 156.94, 122.97, 165.03, 125.39, 176.36, 158.56, 178.79, 165.84, 170.7, 180.4, 165.03, 183.64, 164.22, 204.67, 165.84, 222.47, 169.08, 279.91, 159.37, 305.8, 151.28, 306.61, 146.43, 302.56, 147.24, 283.96, 148.85, 246.74, 142.38, 228.13, 140.76, 252.4, 140.76, 300.94, 127.82, 303.37]], "area": 9633.41065, "iscrowd": 0, "image_id": 411289, "bbox": [105.17, 94.65, 73.62, 211.96], "category_id": 1, "id": 200394, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "dark", "athletic", "pants", "and", "sweatshirt", "getting", "supplies", "ready", "for", "fishing"], "raw": "A man in dark athletic pants and sweatshirt getting supplies ready for fishing.", "sent_id": 54883, "sent": "a man in dark athletic pants and sweatshirt getting supplies ready for fishing"}, {"tokens": ["a", "man", "with", "black", "pants", "whose", "back", "side", "can", "only", "be", "seen"], "raw": "a man with black pants whose back side can only be seen", "sent_id": 54884, "sent": "a man with black pants whose back side can only be seen"}], "file_name": "COCO_train2014_000000411289_200394.jpg", "ann_id": 200394, "sent_ids": [54883, 54884], "ref_id": 26110}, {"segmentation": [[427.0, 631.2, 418.17, 587.86, 358.17, 577.86, 353.17, 502.86, 338.17, 499.53, 301.5, 579.53, 223.17, 511.2, 224.83, 551.2, 199.83, 541.2, 196.5, 554.53, 194.83, 556.2, 184.83, 581.2, 178.17, 640.0]], "area": 19801.213550000004, "iscrowd": 0, "image_id": 101573, "bbox": [178.17, 499.53, 248.83, 140.47], "category_id": 84, "id": 1984530, "split": "val", "sentences": [{"tokens": ["an", "open", "book", "resting", "on", "the", "ground"], "raw": "an open book resting on the ground", "sent_id": 54893, "sent": "an open book resting on the ground"}, {"tokens": ["an", "open", "book", "sitting", "on", "the", "ground", "in", "front", "of", "a", "young", "lady", "wearing", "sandals", "and", "blue", "jeans"], "raw": "An open book sitting on the ground in front of a young lady wearing sandals and blue jeans.", "sent_id": 54894, "sent": "an open book sitting on the ground in front of a young lady wearing sandals and blue jeans"}], "file_name": "COCO_train2014_000000101573_1984530.jpg", "ann_id": 1984530, "sent_ids": [54893, 54894], "ref_id": 26113}, {"segmentation": [[377.34, 437.97, 377.34, 422.55, 523.18, 441.52, 556.38, 456.94, 551.63, 574.32, 547.43, 636.14, 447.37, 615.98, 480.48, 597.27, 491.21, 458.89]], "area": 15023.423649999997, "iscrowd": 0, "image_id": 538196, "bbox": [377.34, 422.55, 179.04, 213.59], "category_id": 72, "id": 1969943, "split": "val", "sentences": [{"tokens": ["a", "television", "screen", "with", "an", "image", "of", "a", "man", "on", "it"], "raw": "a television screen with an image of a man on it", "sent_id": 54975, "sent": "a television screen with an image of a man on it"}, {"tokens": ["video", "displays", "in", "a", "hall"], "raw": "video displays in a hall", "sent_id": 54976, "sent": "video displays in a hall"}], "file_name": "COCO_train2014_000000538196_1969943.jpg", "ann_id": 1969943, "sent_ids": [54975, 54976], "ref_id": 26142}, {"segmentation": [[0.0, 147.33, 37.08, 127.29, 84.19, 135.3, 103.23, 167.38, 114.26, 214.48, 110.25, 224.5, 108.24, 254.57, 97.22, 294.66, 109.24, 324.73, 114.26, 333.75, 193.43, 375.84, 195.44, 415.93, 199.45, 438.98, 0.0, 436.98]], "area": 39504.49255, "iscrowd": 0, "image_id": 468219, "bbox": [0.0, 127.29, 199.45, 311.69], "category_id": 1, "id": 533680, "split": "val", "sentences": [{"tokens": ["a", "man", "without", "his", "face", "showing", "facing", "two", "men", "putting", "on", "a", "tie"], "raw": "A man without his face showing facing two men putting on a tie.", "sent_id": 55028, "sent": "a man without his face showing facing two men putting on a tie"}, {"tokens": ["the", "back", "of", "a", "man", "to", "the", "left", "of", "two", "other", "men"], "raw": "The back of a man to the left of two other men", "sent_id": 55029, "sent": "the back of a man to the left of two other men"}], "file_name": "COCO_train2014_000000468219_533680.jpg", "ann_id": 533680, "sent_ids": [55028, 55029], "ref_id": 26160}, {"segmentation": [[30.34, 493.72, 98.24, 346.37, 65.01, 252.46, 78.01, 129.66, 99.68, 84.88, 145.91, 11.2, 186.37, 68.98, 180.59, 180.23, 156.03, 291.47, 184.92, 415.71, 167.58, 509.62, 199.37, 538.51, 102.57, 541.4, 102.57, 511.06, 59.23, 495.17]], "area": 48794.480149999996, "iscrowd": 0, "image_id": 62759, "bbox": [30.34, 11.2, 169.03, 530.2], "category_id": 1, "id": 498475, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "green", "jacket"], "raw": "a woman in a green jacket", "sent_id": 55103, "sent": "a woman in a green jacket"}, {"tokens": ["a", "woman", "wearing", "green", "gloves", "and", "eye", "glass", "standing", "near", "a", "man"], "raw": "A woman wearing green gloves and eye glass standing near a man", "sent_id": 55104, "sent": "a woman wearing green gloves and eye glass standing near a man"}], "file_name": "COCO_train2014_000000062759_498475.jpg", "ann_id": 498475, "sent_ids": [55103, 55104], "ref_id": 26186}, {"segmentation": [[99.44, 397.98, 91.23, 361.84, 92.87, 319.94, 113.41, 290.37, 119.98, 286.26, 122.45, 262.44, 133.13, 247.65, 156.13, 247.65, 162.7, 257.51, 165.98, 271.47, 165.16, 282.15, 160.23, 303.51, 197.2, 315.01, 210.35, 315.01, 228.42, 304.33, 247.31, 306.8, 242.38, 349.52, 218.56, 330.62, 171.74, 322.41, 156.95, 321.59, 143.8, 342.94, 182.41, 325.69, 188.17, 332.26, 194.74, 349.52, 161.06, 397.16, 179.13, 402.91, 179.13, 414.41, 174.2, 417.7, 126.55, 417.7, 114.23, 411.95]], "area": 12995.527049999997, "iscrowd": 0, "image_id": 572998, "bbox": [91.23, 247.65, 156.08, 170.05], "category_id": 1, "id": 2206918, "split": "val", "sentences": [{"tokens": ["the", "catcher", "behind", "home", "plate", "extends", "his", "mitt", "in", "anticipation", "of", "the", "pitch"], "raw": "The catcher behind home plate extends his mitt in anticipation of the pitch.", "sent_id": 55183, "sent": "the catcher behind home plate extends his mitt in anticipation of the pitch"}, {"tokens": ["this", "is", "the", "baseball", "catcher", "in", "a", "yellow", "shirt"], "raw": "This is the baseball catcher in a yellow shirt.", "sent_id": 55184, "sent": "this is the baseball catcher in a yellow shirt"}], "file_name": "COCO_train2014_000000572998_2206918.jpg", "ann_id": 2206918, "sent_ids": [55183, 55184], "ref_id": 26215}, {"segmentation": [[227.03, 161.62, 242.16, 203.78, 436.76, 203.78, 473.51, 215.68, 491.89, 230.81, 534.05, 230.81, 558.92, 226.49, 577.3, 209.19, 605.41, 174.59, 609.73, 158.38, 596.76, 94.59, 574.05, 68.65, 553.51, 60.0, 516.76, 53.51, 288.65, 49.19, 259.46, 55.68, 240.0, 69.73, 228.11, 101.08, 224.86, 136.76, 224.86, 154.05]], "area": 57340.47565, "iscrowd": 0, "image_id": 41730, "bbox": [224.86, 49.19, 384.87, 181.62], "category_id": 51, "id": 716580, "split": "val", "sentences": [{"tokens": ["the", "bento", "box", "with", "rice", "in", "it"], "raw": "The bento box with rice in it.", "sent_id": 55211, "sent": "the bento box with rice in it"}, {"tokens": ["a", "bowl", "of", "rice", "and", "seaweed", "next", "to", "another", "bowl", "of", "broccolli", "and", "sweet", "potato"], "raw": "A bowl of rice and seaweed next to another bowl of broccolli  and sweet potato", "sent_id": 55212, "sent": "a bowl of rice and seaweed next to another bowl of broccolli and sweet potato"}], "file_name": "COCO_train2014_000000041730_716580.jpg", "ann_id": 716580, "sent_ids": [55211, 55212], "ref_id": 26224}, {"segmentation": [[207.48, 151.05, 220.82, 176.25, 252.69, 199.96, 291.23, 205.15, 320.87, 194.03, 329.02, 164.39, 323.09, 134.0, 307.53, 113.99, 291.97, 100.65, 276.4, 91.02, 255.65, 89.54, 248.98, 89.54, 226.01, 92.5, 212.67, 102.88, 206.0, 114.73, 203.78, 134.0, 204.52, 148.08]], "area": 11065.544, "iscrowd": 0, "image_id": 269723, "bbox": [203.78, 89.54, 125.24, 115.61], "category_id": 85, "id": 336931, "split": "val", "sentences": [{"tokens": ["a", "clock", "showing", "the", "time", "4", ":", "16"], "raw": "A clock showing the time 4:16.", "sent_id": 55225, "sent": "a clock showing the time 4 : 16"}, {"tokens": ["a", "fully", "visible", "clock", "face"], "raw": "A fully visible clock face.", "sent_id": 55226, "sent": "a fully visible clock face"}], "file_name": "COCO_train2014_000000269723_336931.jpg", "ann_id": 336931, "sent_ids": [55225, 55226], "ref_id": 26230}, {"segmentation": [[65.91, 460.1, 346.94, 465.08, 368.08, 432.75, 366.84, 278.55, 340.73, 249.95, 207.67, 267.36, 72.12, 251.19, 41.04, 262.38, 39.79, 431.5]], "area": 65819.53994999999, "iscrowd": 0, "image_id": 510027, "bbox": [39.79, 249.95, 328.29, 215.13], "category_id": 51, "id": 1899469, "split": "val", "sentences": [{"tokens": ["the", "container", "with", "carrots"], "raw": "The container with carrots", "sent_id": 55258, "sent": "the container with carrots"}, {"tokens": ["a", "portion", "of", "food", "with", "carrots", "and", "cheese", "slices"], "raw": "A portion of food with carrots and cheese slices.", "sent_id": 55259, "sent": "a portion of food with carrots and cheese slices"}], "file_name": "COCO_train2014_000000510027_1899469.jpg", "ann_id": 1899469, "sent_ids": [55258, 55259], "ref_id": 26245}, {"segmentation": [[285.25, 325.2, 296.7, 328.38, 345.67, 334.74, 367.3, 337.92, 367.93, 342.38, 356.48, 342.38, 332.95, 340.47, 282.71, 331.56, 273.8, 323.93, 275.71, 319.48], [466.52, 309.3, 461.43, 295.95, 465.88, 282.59, 472.88, 276.23, 479.24, 276.86, 486.87, 283.22, 491.32, 293.4, 491.32, 304.21]], "area": 1324.9044000000006, "iscrowd": 0, "image_id": 186198, "bbox": [273.8, 276.23, 217.52, 66.15], "category_id": 35, "id": 612553, "split": "val", "sentences": [{"tokens": ["white", "skiis", "on", "a", "snowcoved", "mountainside"], "raw": "White skiis on a snowcoved mountainside", "sent_id": 55291, "sent": "white skiis on a snowcoved mountainside"}], "file_name": "COCO_train2014_000000186198_612553.jpg", "ann_id": 612553, "sent_ids": [55291], "ref_id": 26259}, {"segmentation": [[162.79, 295.36, 163.85, 238.19, 163.85, 219.13, 187.14, 197.96, 188.2, 172.55, 193.49, 158.78, 229.49, 156.67, 246.43, 169.37, 233.73, 202.19, 227.37, 213.84, 250.67, 247.72, 251.72, 286.89, 249.61, 300.65, 239.02, 303.83, 273.96, 326.06, 291.96, 333.47, 285.6, 356.77, 284.55, 379.0, 260.19, 386.41, 232.67, 357.82, 211.49, 336.65, 192.44, 319.71, 188.2, 311.24, 201.96, 304.89, 196.67, 289.01]], "area": 14572.5139, "iscrowd": 0, "image_id": 74945, "bbox": [162.79, 156.67, 129.17, 229.74], "category_id": 1, "id": 1221391, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "beige", "dress", "holding", "umbrella", "at", "a", "picnic"], "raw": "A woman wearing beige dress holding umbrella at a picnic.", "sent_id": 55399, "sent": "a woman wearing beige dress holding umbrella at a picnic"}, {"tokens": ["woman", "wearing", "glasses", "and", "white", "dress"], "raw": "woman wearing glasses and white dress", "sent_id": 55400, "sent": "woman wearing glasses and white dress"}], "file_name": "COCO_train2014_000000074945_1221391.jpg", "ann_id": 1221391, "sent_ids": [55399, 55400], "ref_id": 26306}, {"segmentation": [[105.18, 9.67, 125.65, 75.62, 133.61, 105.75, 125.65, 123.37, 130.2, 131.33, 128.49, 135.88, 126.22, 138.72, 101.77, 147.25, 93.81, 154.64, 88.12, 163.74, 77.89, 165.44, 63.68, 166.58, 54.01, 178.52, 43.78, 183.64, 27.29, 180.23, 16.49, 170.56, 10.8, 164.31, 14.78, 8.53]], "area": 17125.34385, "iscrowd": 0, "image_id": 396825, "bbox": [10.8, 8.53, 122.81, 175.11], "category_id": 6, "id": 168799, "split": "val", "sentences": [{"tokens": ["the", "front", "of", "a", "beat", "-", "up", "red", "and", "yellow", "bus"], "raw": "The front of a beat-up red and yellow bus.", "sent_id": 55444, "sent": "the front of a beat - up red and yellow bus"}, {"tokens": ["the", "red", "front", "of", "a", "bus"], "raw": "The red front of a bus.", "sent_id": 55445, "sent": "the red front of a bus"}], "file_name": "COCO_train2014_000000396825_168799.jpg", "ann_id": 168799, "sent_ids": [55444, 55445], "ref_id": 26323}, {"segmentation": [[6.47, 88.45, 631.01, 96.0, 637.48, 350.56, 570.61, 355.96, 51.78, 358.11, 21.57, 354.88, 3.24, 354.88, 3.24, 306.34]], "area": 166457.22065, "iscrowd": 0, "image_id": 27679, "bbox": [3.24, 88.45, 634.24, 269.66], "category_id": 79, "id": 1126266, "split": "val", "sentences": [{"tokens": ["inside", "of", "the", "oven"], "raw": "Inside of the oven.", "sent_id": 55491, "sent": "inside of the oven"}, {"tokens": ["apple", "pie", "inside", "of", "an", "oven"], "raw": "Apple pie inside of an oven.", "sent_id": 55492, "sent": "apple pie inside of an oven"}], "file_name": "COCO_train2014_000000027679_1126266.jpg", "ann_id": 1126266, "sent_ids": [55491, 55492], "ref_id": 26343}, {"segmentation": [[171.51, 120.81, 290.16, 64.72, 363.51, 24.81, 403.42, 9.71, 420.67, 9.71, 484.31, 47.46, 638.56, 132.67, 635.33, 141.3, 586.79, 140.22, 395.87, 134.83, 220.04, 130.52, 175.82, 120.81]], "area": 32078.96784999999, "iscrowd": 0, "image_id": 258538, "bbox": [171.51, 9.71, 467.05, 131.59], "category_id": 28, "id": 282693, "split": "val", "sentences": [{"tokens": ["an", "umbrella", "in", "white", "over", "a", "table", "in", "an", "outdoor", "cafe", "area"], "raw": "An umbrella in white over a table in an outdoor cafe area.", "sent_id": 55570, "sent": "an umbrella in white over a table in an outdoor cafe area"}, {"tokens": ["white", "bungalow", "top", "with", "wooden", "chairs", "in", "it"], "raw": "White bungalow top with wooden chairs in it", "sent_id": 55571, "sent": "white bungalow top with wooden chairs in it"}], "file_name": "COCO_train2014_000000258538_282693.jpg", "ann_id": 282693, "sent_ids": [55570, 55571], "ref_id": 26371}, {"segmentation": [[516.13, 123.98, 472.45, 175.75, 445.75, 187.08, 428.76, 194.36, 413.39, 198.4, 410.97, 200.83, 418.25, 205.69, 432.0, 208.92, 440.09, 216.2, 444.94, 227.53, 457.89, 227.53, 471.64, 220.25, 488.63, 211.35, 492.67, 192.74, 502.38, 166.85, 512.09, 208.11, 516.13, 221.87, 524.22, 223.48, 577.62, 216.2, 588.94, 196.79, 592.99, 191.93, 588.94, 191.12]], "area": 8355.37785, "iscrowd": 0, "image_id": 84162, "bbox": [410.97, 123.98, 182.02, 103.55], "category_id": 9, "id": 182041, "split": "val", "sentences": [{"tokens": ["gray", "naval", "boat", "parked", "on", "far", "right"], "raw": "gray naval boat parked on far right", "sent_id": 55597, "sent": "gray naval boat parked on far right"}, {"tokens": ["the", "grey", "ship", "furthest", "right"], "raw": "The grey ship furthest right", "sent_id": 55598, "sent": "the grey ship furthest right"}], "file_name": "COCO_train2014_000000084162_182041.jpg", "ann_id": 182041, "sent_ids": [55597, 55598], "ref_id": 26380}, {"segmentation": [[457.81, 213.54, 440.09, 218.85, 417.93, 240.56, 419.71, 245.44, 394.89, 254.3, 385.15, 273.79, 389.58, 292.85, 412.62, 310.57, 418.82, 311.01, 444.08, 306.14, 453.38, 287.97, 472.88, 316.77, 498.58, 318.54, 513.2, 312.34, 526.49, 287.09, 539.34, 314.11, 565.92, 315.0, 584.53, 307.47, 592.06, 293.73, 597.82, 279.55, 592.51, 263.6, 576.56, 250.31, 551.3, 244.11, 541.11, 225.06, 529.59, 217.52, 531.36, 198.03, 516.74, 181.63, 502.12, 177.2, 483.95, 178.53, 470.22, 185.62, 461.8, 198.03, 456.04, 208.66]], "area": 18113.687699999995, "iscrowd": 0, "image_id": 183435, "bbox": [385.15, 177.2, 212.67, 141.34], "category_id": 55, "id": 1912957, "split": "val", "sentences": [{"tokens": ["a", "group", "of", "six", "oranges", "on", "a", "wooden", "table", "surrounded", "by", "several", "other", "fruits", "and", "vegetables"], "raw": "A group of six oranges on a wooden table surrounded by several other fruits and vegetables.", "sent_id": 55658, "sent": "a group of six oranges on a wooden table surrounded by several other fruits and vegetables"}, {"tokens": ["stack", "of", "oranges"], "raw": "stack of oranges", "sent_id": 55659, "sent": "stack of oranges"}], "file_name": "COCO_train2014_000000183435_1912957.jpg", "ann_id": 1912957, "sent_ids": [55658, 55659], "ref_id": 26402}, {"segmentation": [[457.22, 179.87, 543.78, 196.67, 549.67, 205.92, 557.23, 235.33, 558.07, 254.66, 469.82, 258.03, 470.66, 276.52, 481.59, 309.29, 545.46, 350.48, 564.8, 364.76, 579.92, 379.05, 590.85, 392.5, 526.97, 447.13, 426.12, 365.61, 414.36, 444.61, 397.55, 460.58, 368.13, 479.07, 341.24, 459.74, 331.99, 399.23, 350.48, 283.24, 363.93, 258.03, 282.4, 246.26, 277.36, 240.38, 278.2, 207.6, 279.04, 181.55, 367.29, 178.18, 368.13, 165.58, 355.52, 121.87, 362.25, 66.4, 344.6, 45.39, 331.99, 10.94, 347.12, 1.69, 395.02, 4.21, 409.31, 1.69, 409.31, 15.14, 425.28, 24.38, 460.58, 27.74, 468.98, 15.98, 497.56, 3.37, 511.85, 7.57, 524.45, 14.3, 535.38, 28.58, 531.18, 43.71, 526.13, 53.8, 518.57, 63.04, 509.33, 72.29, 491.68, 79.85, 492.52, 101.7, 490.84, 136.16, 479.91, 154.65, 462.26, 179.87]], "area": 76544.19944999999, "iscrowd": 0, "image_id": 15809, "bbox": [277.36, 1.69, 313.49, 477.38], "category_id": 88, "id": 1160905, "split": "val", "sentences": [{"tokens": ["blue", "yarn", "bear", "on", "the", "right"], "raw": "blue Yarn bear on the right", "sent_id": 55672, "sent": "blue yarn bear on the right"}, {"tokens": ["a", "knit", "bear", "figure", "to", "the", "right", "of", "a", "duplicate"], "raw": "A knit bear figure to the right of a duplicate.", "sent_id": 55673, "sent": "a knit bear figure to the right of a duplicate"}], "file_name": "COCO_train2014_000000015809_1160905.jpg", "ann_id": 1160905, "sent_ids": [55672, 55673], "ref_id": 26406}, {"segmentation": [[326.53, 301.3, 251.93, 317.59, 252.79, 340.74, 289.37, 349.6, 389.69, 371.32, 407.39, 375.0, 441.4, 375.0, 489.42, 343.58, 487.13, 340.72, 486.27, 328.72, 489.42, 325.29, 487.42, 322.15, 423.97, 313.6, 424.54, 316.45, 424.54, 319.6, 422.83, 324.17, 418.54, 328.46, 405.11, 330.46, 334.8, 315.6, 333.37, 310.45, 333.37, 305.88, 333.94, 303.02, 334.23, 301.31, 329.94, 299.31]], "area": 10333.543900000002, "iscrowd": 0, "image_id": 537337, "bbox": [251.93, 299.31, 237.49, 75.69], "category_id": 84, "id": 1144886, "split": "val", "sentences": [{"tokens": ["the", "book", "under", "th", "phone"], "raw": "the book under th phone", "sent_id": 55702, "sent": "the book under th phone"}, {"tokens": ["a", "book", "holding", "a", "charging", "mobile", "near", "the", "cat"], "raw": "A BOOK HOLDING A CHARGING MOBILE NEAR THE CAT", "sent_id": 55703, "sent": "a book holding a charging mobile near the cat"}], "file_name": "COCO_train2014_000000537337_1144886.jpg", "ann_id": 1144886, "sent_ids": [55702, 55703], "ref_id": 26417}, {"segmentation": [[173.55, 292.39, 183.46, 300.65, 189.66, 318.82, 192.14, 328.32, 198.33, 347.73, 198.75, 354.76, 192.96, 359.3, 188.01, 370.86, 190.9, 401.43, 190.49, 415.06, 194.62, 427.03, 186.77, 439.01, 182.23, 443.55, 163.64, 444.79, 151.66, 447.68, 125.64, 443.55, 122.75, 434.88, 122.34, 426.62, 119.86, 422.08, 115.73, 422.49, 121.93, 372.93, 122.75, 346.08, 123.99, 331.63, 122.75, 329.15, 123.16, 324.19, 121.51, 340.3, 120.27, 347.73, 112.43, 356.82, 95.08, 355.58, 92.19, 345.67, 94.25, 337.0, 101.27, 330.8, 107.47, 327.91, 115.73, 318.0, 125.23, 306.43, 130.19, 299.41, 125.23, 292.8, 119.03, 281.65, 117.8, 275.04, 117.8, 271.74, 114.49, 261.41, 114.9, 254.39, 119.45, 248.61, 130.19, 245.72, 131.42, 245.72, 130.6, 239.11, 137.62, 233.33, 143.82, 232.5, 151.66, 235.39, 160.75, 237.05, 166.94, 241.18, 170.66, 247.79, 182.23, 252.33, 191.72, 262.24, 189.66, 273.39, 180.16, 278.76, 177.68, 287.43]], "area": 14660.044800000001, "iscrowd": 0, "image_id": 264821, "bbox": [92.19, 232.5, 106.56, 215.18], "category_id": 88, "id": 1159292, "split": "val", "sentences": [{"tokens": ["a", "teddy", "bear", "wearing", "a", "black", "dress"], "raw": "A teddy bear wearing a black dress.", "sent_id": 55704, "sent": "a teddy bear wearing a black dress"}], "file_name": "COCO_train2014_000000264821_1159292.jpg", "ann_id": 1159292, "sent_ids": [55704], "ref_id": 26418}, {"segmentation": [[298.26, 94.79, 281.36, 64.6, 265.66, 47.7, 258.42, 46.49, 243.92, 51.32, 243.92, 65.81, 230.64, 70.64, 223.4, 75.47, 210.11, 69.43, 201.66, 75.47, 194.42, 81.51, 172.68, 81.51, 126.79, 117.74, 88.15, 152.75, 56.75, 190.19, 44.68, 220.38, 62.79, 279.55, 113.51, 320.6, 149.74, 345.96, 202.87, 349.58, 236.68, 323.02, 257.21, 248.15, 320.0, 169.66, 373.13, 117.74, 350.19, 81.51, 342.94, 79.09, 321.21, 89.96, 310.34, 93.58, 298.26, 97.21]], "area": 55141.1004, "iscrowd": 0, "image_id": 319192, "bbox": [44.68, 46.49, 328.45, 303.09], "category_id": 58, "id": 1069717, "split": "val", "sentences": [{"tokens": ["a", "hot", "dog", "on", "the", "left", "side", "of", "a", "plate"], "raw": "A hot dog on the left side of a plate.", "sent_id": 55707, "sent": "a hot dog on the left side of a plate"}, {"tokens": ["a", "hot", "dog", "with", "ketchup", "next", "to", "a", "stove"], "raw": "A hot dog with ketchup next to a stove.", "sent_id": 55708, "sent": "a hot dog with ketchup next to a stove"}], "file_name": "COCO_train2014_000000319192_1069717.jpg", "ann_id": 1069717, "sent_ids": [55707, 55708], "ref_id": 26419}, {"segmentation": [[132.47, 320.78, 136.36, 389.61, 150.65, 407.79, 222.08, 401.3, 222.08, 310.39, 188.31, 312.99, 176.62, 300.0, 157.14, 305.19, 155.84, 318.18]], "area": 8101.094350000003, "iscrowd": 0, "image_id": 215436, "bbox": [132.47, 300.0, 89.61, 107.79], "category_id": 31, "id": 1834174, "split": "val", "sentences": [{"tokens": ["the", "zara", "shopping", "bag"], "raw": "the zara shopping bag", "sent_id": 55723, "sent": "the zara shopping bag"}, {"tokens": ["zara", "bag", "that", "the", "man", "is", "holding"], "raw": "zara bag that the man is holding.", "sent_id": 55724, "sent": "zara bag that the man is holding"}], "file_name": "COCO_train2014_000000215436_1834174.jpg", "ann_id": 1834174, "sent_ids": [55723, 55724], "ref_id": 26426}, {"segmentation": [[354.07, 407.81, 315.69, 366.55, 302.26, 349.28, 299.38, 308.02, 296.5, 275.39, 295.54, 254.28, 298.42, 230.29, 304.18, 217.82, 316.65, 196.71, 338.72, 172.72, 359.83, 159.29, 387.66, 136.26, 411.65, 130.5, 443.31, 121.86, 471.14, 121.86, 502.8, 122.82, 521.04, 126.66, 551.74, 134.34, 634.26, 182.31, 640.0, 192.87, 640.0, 199.59, 640.0, 331.04, 587.24, 403.97, 544.07, 421.24]], "area": 86519.92010000002, "iscrowd": 0, "image_id": 223165, "bbox": [295.54, 121.86, 344.46, 299.38], "category_id": 60, "id": 1079906, "split": "val", "sentences": [{"tokens": ["the", "chocolate", "covered", "yeast", "donut", "with", "nut", "topping"], "raw": "The chocolate covered yeast donut with nut topping.", "sent_id": 55752, "sent": "the chocolate covered yeast donut with nut topping"}, {"tokens": ["the", "donut", "with", "the", "chocolate", "and", "nuts", "on", "it"], "raw": "The donut with the chocolate and nuts on it", "sent_id": 55753, "sent": "the donut with the chocolate and nuts on it"}], "file_name": "COCO_train2014_000000223165_1079906.jpg", "ann_id": 1079906, "sent_ids": [55752, 55753], "ref_id": 26435}, {"segmentation": [[297.72, 72.46, 284.32, 30.34, 195.29, 2.58, 637.56, 3.54, 637.56, 195.0, 548.53, 205.53, 461.42, 169.15, 451.85, 137.56, 457.59, 87.78, 436.53, 58.1, 397.28, 55.23, 376.22, 64.8, 364.73, 82.99, 300.59, 89.69]], "area": 47414.22944999999, "iscrowd": 0, "image_id": 568725, "bbox": [195.29, 2.58, 442.27, 202.95], "category_id": 3, "id": 1347383, "split": "val", "sentences": [{"tokens": ["yellow", "section", "of", "a", "car", "and", "the", "wheel", "to", "the", "right", "of", "it"], "raw": "Yellow section of a car and the wheel to the right of it.", "sent_id": 55758, "sent": "yellow section of a car and the wheel to the right of it"}, {"tokens": ["the", "yellow", "car"], "raw": "The yellow car.", "sent_id": 55759, "sent": "the yellow car"}], "file_name": "COCO_train2014_000000568725_1347383.jpg", "ann_id": 1347383, "sent_ids": [55758, 55759], "ref_id": 26438}, {"segmentation": [[258.29, 389.04, 356.89, 390.12, 374.04, 356.89, 391.19, 295.8, 389.04, 219.71, 381.54, 188.63, 377.26, 180.05, 369.75, 195.06, 368.68, 188.63, 357.96, 188.63, 360.11, 176.84, 363.32, 171.48, 363.32, 160.76, 355.82, 147.9, 346.17, 140.4, 326.88, 140.4, 296.87, 135.04, 290.44, 135.04, 281.87, 139.33, 295.8, 152.19, 300.09, 168.26, 286.16, 175.77, 278.65, 169.34, 278.65, 161.83, 266.87, 165.05, 261.51, 156.48, 246.5, 192.91, 225.07, 228.28, 214.35, 293.66, 231.5, 342.96]], "area": 34992.85850000001, "iscrowd": 0, "image_id": 543838, "bbox": [214.35, 135.04, 176.84, 255.08], "category_id": 86, "id": 1156222, "split": "val", "sentences": [{"tokens": ["a", "flower", "vase", "between", "two", "others"], "raw": "A flower vase between two others.", "sent_id": 55767, "sent": "a flower vase between two others"}, {"tokens": ["flower", "bottle", "in", "middle", "like", "a", "mango", "shape"], "raw": "flower bottle in middle like a mango shape", "sent_id": 55768, "sent": "flower bottle in middle like a mango shape"}], "file_name": "COCO_train2014_000000543838_1156222.jpg", "ann_id": 1156222, "sent_ids": [55767, 55768], "ref_id": 26442}, {"segmentation": [[71.68, 416.96, 70.3, 348.04, 68.92, 299.8, 67.54, 263.96, 86.84, 237.77, 107.51, 223.99, 99.24, 196.42, 84.08, 179.88, 84.08, 145.42, 113.03, 119.23, 140.59, 119.23, 154.38, 150.93, 157.14, 196.42, 157.14, 223.99, 169.54, 240.53, 151.62, 250.18, 153.0, 284.64, 157.14, 297.04, 157.14, 316.34, 153.0, 327.36, 148.86, 335.64, 148.86, 338.39, 188.84, 348.04, 227.43, 348.04, 241.22, 345.28, 260.51, 363.2, 255.0, 365.96, 238.46, 381.12, 221.92, 374.23, 204.0, 367.34, 188.84, 378.36, 206.76, 393.53, 245.35, 425.23, 242.59, 439.01, 242.59, 480.36, 242.59, 518.96, 235.7, 552.04, 228.81, 563.07, 213.65, 546.53, 221.92, 564.45, 227.43, 593.39, 228.81, 605.8, 201.24, 600.28, 175.05, 576.85, 184.7, 524.47, 183.32, 481.74, 177.81, 462.45, 135.08, 450.04, 97.86, 432.12]], "area": 40352.7736, "iscrowd": 0, "image_id": 220504, "bbox": [67.54, 119.23, 192.97, 486.57], "category_id": 1, "id": 222454, "split": "val", "sentences": [{"tokens": ["the", "woman", "on", "the", "motorcycle", "behind", "the", "man", "and", "holding", "a", "baby"], "raw": "The woman on the motorcycle behind the man and holding a baby", "sent_id": 55934, "sent": "the woman on the motorcycle behind the man and holding a baby"}, {"tokens": ["a", "woman", "on", "the", "back", "of", "a", "motorcycle"], "raw": "A woman on the back of a motorcycle.", "sent_id": 55935, "sent": "a woman on the back of a motorcycle"}], "file_name": "COCO_train2014_000000220504_222454.jpg", "ann_id": 222454, "sent_ids": [55934, 55935], "ref_id": 26501}, {"segmentation": [[517.53, 297.36, 484.67, 290.51, 466.87, 276.82, 461.4, 186.46, 447.7, 159.08, 466.87, 124.85, 512.05, 108.42, 570.93, 112.53, 606.52, 161.81, 595.57, 200.15, 561.34, 239.85, 532.59, 289.14]], "area": 20497.181500000002, "iscrowd": 0, "image_id": 253834, "bbox": [447.7, 108.42, 158.82, 188.94], "category_id": 47, "id": 679830, "split": "val", "sentences": [{"tokens": ["coffee", "in", "a", "white", "cup"], "raw": "coffee in a white cup", "sent_id": 55978, "sent": "coffee in a white cup"}, {"tokens": ["to", "go", "coffee", "cup"], "raw": "to go coffee cup", "sent_id": 55979, "sent": "to go coffee cup"}], "file_name": "COCO_train2014_000000253834_679830.jpg", "ann_id": 679830, "sent_ids": [55978, 55979], "ref_id": 26520}, {"segmentation": [[402.81, 31.88, 414.61, 9.13, 428.09, 2.39, 447.47, 3.23, 465.17, 7.44, 475.28, 19.24, 484.55, 39.47, 487.08, 60.53, 481.18, 75.7, 472.75, 85.81, 471.91, 92.56, 478.65, 96.77, 499.72, 88.34, 499.72, 251.83, 327.81, 244.24, 326.12, 226.54, 331.18, 169.24, 350.56, 126.26, 378.37, 108.57, 401.97, 102.67, 407.02, 103.51, 396.07, 70.65, 397.75, 41.15]], "area": 31136.491250000003, "iscrowd": 0, "image_id": 122259, "bbox": [326.12, 2.39, 173.6, 249.44], "category_id": 1, "id": 437752, "split": "val", "sentences": [{"tokens": ["man", "wearing", "a", "brown", "striped", "sweater", "sitting", "on", "the", "right", "laughing"], "raw": "Man wearing a brown striped sweater sitting on the right laughing", "sent_id": 56020, "sent": "man wearing a brown striped sweater sitting on the right laughing"}, {"tokens": ["a", "man", "in", "a", "striped", "sweater"], "raw": "A man in a striped sweater.", "sent_id": 56021, "sent": "a man in a striped sweater"}], "file_name": "COCO_train2014_000000122259_437752.jpg", "ann_id": 437752, "sent_ids": [56020, 56021], "ref_id": 26536}, {"segmentation": [[63.04, 231.91, 88.83, 212.81, 103.16, 206.12, 133.72, 203.26, 239.74, 213.76, 289.41, 224.27, 344.81, 227.14, 431.73, 230.0, 473.76, 230.96, 561.63, 166.96, 582.65, 171.74, 553.04, 238.6, 565.45, 246.24, 550.17, 263.43, 503.37, 262.48, 428.87, 267.25, 429.82, 277.76, 387.79, 282.54, 354.36, 283.49, 327.62, 281.58, 320.93, 295.91, 295.14, 296.86, 264.58, 292.09, 267.44, 281.58, 248.34, 280.63, 236.88, 281.58, 233.06, 281.58, 215.87, 280.63, 207.27, 266.3, 163.33, 262.48, 134.68, 262.48, 124.17, 262.48, 121.3, 280.63, 109.84, 279.67, 108.89, 268.21, 103.16, 258.66, 79.28, 251.97, 69.73, 250.06, 64.0, 244.33, 61.13, 231.91]], "area": 28865.250749999996, "iscrowd": 0, "image_id": 55092, "bbox": [61.13, 166.96, 521.52, 129.9], "category_id": 5, "id": 156972, "split": "val", "sentences": [{"tokens": ["a", "large", "british", "airways", "jet", "next", "to", "water"], "raw": "A Large British Airways Jet next to water.", "sent_id": 56046, "sent": "a large british airways jet next to water"}, {"tokens": ["british", "airways", "airplane", "sitting", "by", "a", "smaller", "gray", "plane"], "raw": "British Airways airplane sitting by a smaller gray plane.", "sent_id": 56047, "sent": "british airways airplane sitting by a smaller gray plane"}], "file_name": "COCO_train2014_000000055092_156972.jpg", "ann_id": 156972, "sent_ids": [56046, 56047], "ref_id": 26544}, {"segmentation": [[433.83, 474.73, 440.27, 447.89, 445.64, 447.89, 446.71, 432.86, 466.04, 412.45, 462.82, 407.08, 453.15, 404.94, 449.93, 388.83, 470.34, 382.39, 482.15, 360.91, 471.41, 343.73, 471.41, 332.99, 460.67, 342.65, 448.86, 345.88, 446.71, 360.91, 446.71, 390.98, 437.05, 411.38, 425.23, 425.34, 413.42, 442.52, 403.76, 456.48, 386.58, 472.59], [471.41, 312.59, 458.52, 312.59, 458.52, 283.59, 462.82, 277.15, 454.23, 271.78, 459.6, 254.6, 474.63, 239.57, 496.11, 237.42, 515.44, 244.94, 528.32, 266.41, 504.7, 266.41, 488.59, 275.0, 476.78, 287.89, 474.63, 306.14]], "area": 6216.4582500000015, "iscrowd": 0, "image_id": 401455, "bbox": [386.58, 237.42, 141.74, 237.31], "category_id": 1, "id": 225341, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "red", "and", "black", "coat", "sitting", "and", "watching", "people", "work", "on", "a", "project"], "raw": "A woman wearing a red and black coat sitting and watching people work on a project.", "sent_id": 56086, "sent": "a woman wearing a red and black coat sitting and watching people work on a project"}, {"tokens": ["a", "woman", "in", "a", "red", "and", "grey", "coat"], "raw": "a woman in a red and grey coat", "sent_id": 56087, "sent": "a woman in a red and grey coat"}], "file_name": "COCO_train2014_000000401455_225341.jpg", "ann_id": 225341, "sent_ids": [56086, 56087], "ref_id": 26558}, {"segmentation": [[621.62, 274.59, 640.0, 295.14, 637.84, 403.24, 633.51, 467.03, 605.41, 467.03, 548.11, 472.43, 518.92, 470.27, 436.76, 468.11, 539.46, 427.03]], "area": 14961.006550000002, "iscrowd": 0, "image_id": 196156, "bbox": [436.76, 274.59, 203.24, 197.84], "category_id": 67, "id": 1091489, "split": "val", "sentences": [{"tokens": ["this", "is", "a", "pretty", "colored", "flower", "tablecloth"], "raw": "This is a pretty colored flower tablecloth.", "sent_id": 56097, "sent": "this is a pretty colored flower tablecloth"}], "file_name": "COCO_train2014_000000196156_1091489.jpg", "ann_id": 1091489, "sent_ids": [56097], "ref_id": 26564}, {"segmentation": [[2.87, 216.48, 40.21, 250.95, 146.48, 263.4, 175.2, 267.23, 197.22, 267.23, 210.63, 266.27, 224.03, 265.31, 220.2, 358.18, 160.84, 360.09, 132.12, 360.09, 111.06, 360.09, 93.83, 362.97, 77.55, 368.71, 69.89, 370.63, 40.21, 378.28, 38.3, 378.28, 19.15, 374.45, 17.23, 373.5, 18.19, 392.65, 9.57, 406.05, 0.96, 412.75], [235.52, 261.48, 228.82, 325.63, 228.82, 340.95, 231.69, 360.09, 234.56, 363.92, 252.75, 363.92, 264.24, 362.97, 275.73, 360.09, 283.39, 357.22, 290.09, 354.35, 298.71, 351.48, 311.15, 339.99, 319.77, 308.39, 323.6, 291.16, 323.6, 271.06, 321.69, 258.61, 314.03, 250.95, 299.67, 242.33, 279.56, 239.46, 264.24, 244.25, 244.14, 252.87]], "area": 34197.649249999995, "iscrowd": 0, "image_id": 90569, "bbox": [0.96, 216.48, 322.64, 196.27], "category_id": 1, "id": 475144, "split": "val", "sentences": [{"tokens": ["the", "arm", "of", "the", "person", "on", "the", "left", "that", "is", "wearing", "a", "bracelet", "on", "their", "wrist"], "raw": "The arm of the person on the left that is wearing a bracelet on their wrist", "sent_id": 56119, "sent": "the arm of the person on the left that is wearing a bracelet on their wrist"}, {"tokens": ["the", "hand", "on", "the", "left", "holding", "the", "wine", "glass"], "raw": "The hand on the left holding the wine glass.", "sent_id": 56120, "sent": "the hand on the left holding the wine glass"}], "file_name": "COCO_train2014_000000090569_475144.jpg", "ann_id": 475144, "sent_ids": [56119, 56120], "ref_id": 26575}, {"segmentation": [[317.66, 161.92, 358.0, 145.95, 395.82, 140.91, 396.66, 137.55, 389.94, 131.66, 389.94, 127.46, 389.94, 125.78, 393.3, 122.42, 396.66, 121.58, 398.34, 121.58, 402.54, 128.3, 401.7, 136.71, 400.86, 139.23, 411.79, 140.07, 417.67, 145.11, 437.0, 148.47, 439.52, 163.6, 431.12, 164.44, 443.73, 219.91, 451.29, 214.03, 458.85, 230.84, 469.78, 251.01, 477.34, 292.19, 473.14, 309.84, 443.73, 316.56, 426.92, 320.76, 415.99, 321.6, 378.17, 320.76, 369.77, 325.81, 324.38, 330.01, 315.14, 303.11, 301.69, 303.95, 297.49, 326.65, 281.52, 335.89, 271.43, 335.89, 265.55, 323.28, 268.91, 287.15, 254.63, 284.62, 257.99, 320.76, 247.06, 328.33, 226.05, 334.21, 213.44, 338.41, 203.36, 316.56, 203.36, 311.52, 199.16, 303.11, 185.71, 315.72, 165.54, 311.52, 152.93, 301.43, 139.48, 302.27, 127.72, 295.55, 107.55, 295.55, 98.3, 298.07, 84.01, 269.5, 88.22, 244.28, 91.58, 236.72, 104.19, 227.47, 114.27, 220.75, 120.15, 192.17, 121.83, 179.57, 117.63, 178.73, 116.79, 161.08, 117.63, 150.15, 120.15, 149.31, 126.04, 161.08, 132.76, 161.92, 129.4, 150.15, 139.48, 142.59, 198.32, 139.23, 242.86, 135.86, 273.11, 140.07, 290.76, 145.11, 296.65, 156.04, 292.45, 161.08, 292.45, 166.96, 310.94, 168.64]], "area": 60575.525000000016, "iscrowd": 0, "image_id": 395425, "bbox": [84.01, 121.58, 393.33, 216.83], "category_id": 8, "id": 398679, "split": "val", "sentences": [{"tokens": ["3", "farm", "tractors"], "raw": "3 farm tractors", "sent_id": 56225, "sent": "3 farm tractors"}, {"tokens": ["farm", "equipment", "being", "transported"], "raw": "Farm equipment being transported.", "sent_id": 56226, "sent": "farm equipment being transported"}], "file_name": "COCO_train2014_000000395425_398679.jpg", "ann_id": 398679, "sent_ids": [56225, 56226], "ref_id": 26611}, {"segmentation": [[0.9, 274.96, 18.09, 270.92, 59.54, 265.19, 95.93, 246.65, 146.48, 242.95, 154.57, 244.29, 176.47, 247.33, 179.84, 251.37, 178.16, 297.54, 175.46, 299.22, 174.11, 303.27, 173.44, 309.67, 75.1, 313.55, 67.35, 313.55, 63.48, 318.19, 58.84, 322.06, 48.77, 325.16, 40.26, 322.06, 35.61, 315.87, 34.06, 313.55, 24.77, 313.55, 17.03, 312.77, 13.16, 312.0, 6.19, 312.0, 0.77, 311.23], [186.58, 311.23, 202.84, 312.0, 202.06, 314.32, 188.13, 314.32, 187.35, 312.0]], "area": 10370.452600000004, "iscrowd": 0, "image_id": 388935, "bbox": [0.77, 242.95, 202.07, 82.21], "category_id": 3, "id": 133281, "split": "val", "sentences": [{"tokens": ["the", "grey", "car"], "raw": "The grey car.", "sent_id": 56227, "sent": "the grey car"}, {"tokens": ["a", "silver", "mercedes", "benz", "next", "to", "a", "red", "sightseeing", "bus"], "raw": "A silver mercedes benz next to a red sightseeing bus.", "sent_id": 56228, "sent": "a silver mercedes benz next to a red sightseeing bus"}], "file_name": "COCO_train2014_000000388935_133281.jpg", "ann_id": 133281, "sent_ids": [56227, 56228], "ref_id": 26612}, {"segmentation": [[152.65, 333.99, 103.25, 292.52, 94.71, 287.64, 89.23, 280.93, 88.01, 283.98, 88.01, 287.64, 75.81, 290.69, 42.27, 304.72, 18.48, 319.35, 43.49, 332.16, 57.51, 339.48, 85.57, 339.48, 102.03, 338.87, 153.26, 335.21]], "area": 4235.703, "iscrowd": 0, "image_id": 184224, "bbox": [18.48, 280.93, 134.78, 58.55], "category_id": 28, "id": 285610, "split": "val", "sentences": [{"tokens": ["an", "umbrella", "over", "a", "dog"], "raw": "An umbrella over a dog", "sent_id": 56248, "sent": "an umbrella over a dog"}, {"tokens": ["the", "umbrella", "covering", "the", "dog"], "raw": "the umbrella covering the dog.", "sent_id": 56249, "sent": "the umbrella covering the dog"}], "file_name": "COCO_train2014_000000184224_285610.jpg", "ann_id": 285610, "sent_ids": [56248, 56249], "ref_id": 26619}, {"segmentation": [[252.24, 87.9, 266.98, 81.2, 297.79, 77.85, 335.3, 77.85, 349.37, 79.19, 379.51, 71.16, 407.65, 77.85, 462.57, 118.05, 493.39, 158.24, 498.08, 161.59, 504.77, 158.91, 513.48, 164.94, 513.48, 171.63, 516.83, 181.01, 514.15, 185.03, 518.84, 205.13, 513.48, 225.22, 518.84, 252.02, 508.79, 266.08, 491.38, 260.72, 490.04, 250.01, 475.3, 227.23, 469.94, 222.54, 468.6, 200.44, 448.51, 166.94, 436.45, 161.59, 429.75, 164.27, 415.01, 167.61, 408.99, 180.34, 406.31, 240.63, 423.72, 271.44, 420.37, 272.78, 415.68, 272.11, 407.65, 263.4, 401.62, 259.38, 400.28, 243.31, 394.92, 223.88, 404.97, 218.52, 400.95, 216.51, 392.24, 212.49, 377.5, 209.81, 379.51, 178.33, 379.51, 170.96, 354.73, 174.98, 318.56, 123.4, 295.11, 96.61, 285.73, 83.88, 269.66, 83.88, 259.61, 85.89], [240.85, 205.13, 252.24, 201.11, 259.61, 225.22, 249.56, 260.05, 262.96, 292.21, 258.94, 297.56, 246.21, 294.89, 244.87, 280.82, 239.51, 270.1, 238.84, 229.24, 235.5, 216.51]], "area": 20958.827299999994, "iscrowd": 0, "image_id": 413297, "bbox": [235.5, 71.16, 283.34, 226.4], "category_id": 24, "id": 1822262, "split": "val", "sentences": [{"tokens": ["a", "zebra", "behind", "another", "zebra"], "raw": "A zebra behind another zebra.", "sent_id": 56261, "sent": "a zebra behind another zebra"}, {"tokens": ["one", "of", "the", "zebras", "(", "the", "one", "in", "the", "distance", ")", "is", "red"], "raw": "ONE OF THE ZEBRAS (THE ONE IN THE DISTANCE) IS RED.", "sent_id": 56262, "sent": "one of the zebras ( the one in the distance ) is red"}], "file_name": "COCO_train2014_000000413297_1822262.jpg", "ann_id": 1822262, "sent_ids": [56261, 56262], "ref_id": 26626}, {"segmentation": [[138.07, 481.56, 139.51, 432.66, 168.27, 429.78, 184.09, 401.02, 263.19, 373.69, 302.02, 306.1, 343.73, 222.68, 327.91, 212.61, 289.08, 212.61, 238.74, 193.92, 217.17, 156.52, 186.97, 83.18, 250.25, 15.58, 297.71, 8.39, 346.61, 29.96, 359.55, 64.48, 427.0, 126.32, 427.0, 626.82, 214.29, 623.94, 283.33, 507.45]], "area": 108956.55635000001, "iscrowd": 0, "image_id": 133486, "bbox": [138.07, 8.39, 288.93, 618.43], "category_id": 1, "id": 436835, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "over", "a", "counter", "making", "food"], "raw": "A man standing over a counter making food.", "sent_id": 56270, "sent": "a man standing over a counter making food"}, {"tokens": ["a", "man", "cooking"], "raw": "a man cooking", "sent_id": 56271, "sent": "a man cooking"}], "file_name": "COCO_train2014_000000133486_436835.jpg", "ann_id": 436835, "sent_ids": [56270, 56271], "ref_id": 26629}, {"segmentation": [[414.95, 277.61, 432.53, 288.43, 445.72, 256.3, 454.85, 264.08, 455.53, 294.85, 471.76, 278.96, 477.85, 281.32, 481.23, 289.44, 473.11, 313.79, 505.57, 337.8, 524.51, 352.0, 531.61, 374.99, 539.05, 384.8, 546.83, 404.08, 517.75, 383.11, 489.68, 356.4, 477.51, 349.63, 459.59, 334.42, 433.55, 311.76, 426.45, 303.64, 426.45, 298.91, 415.62, 280.31, 396.01, 264.76, 417.99, 279.3]], "area": 4600.91465, "iscrowd": 0, "image_id": 223459, "bbox": [396.01, 256.3, 150.82, 147.78], "category_id": 5, "id": 160041, "split": "val", "sentences": [{"tokens": ["the", "number", "one", "jet", "in", "the", "blue", "angles"], "raw": "The number one jet in the Blue Angles.", "sent_id": 56278, "sent": "the number one jet in the blue angles"}], "file_name": "COCO_train2014_000000223459_160041.jpg", "ann_id": 160041, "sent_ids": [56278], "ref_id": 26632}, {"segmentation": [[301.94, 136.88, 294.72, 148.44, 290.38, 168.67, 294.72, 177.34, 297.61, 184.56, 303.39, 190.34, 300.5, 196.12, 290.38, 196.12, 280.27, 209.12, 249.93, 255.35, 244.15, 268.35, 244.15, 326.14, 264.38, 379.59, 264.38, 398.37, 273.05, 398.37, 274.49, 396.93, 293.27, 415.71, 293.27, 425.82, 301.94, 430.16, 312.05, 435.94, 307.72, 450.38, 294.72, 461.94, 297.61, 483.61, 300.5, 498.06, 307.72, 524.06, 310.61, 548.62, 310.61, 574.63, 312.05, 591.96, 317.83, 599.19, 326.5, 607.86, 348.17, 620.86, 359.73, 620.86, 359.73, 600.63, 359.73, 578.96, 368.4, 558.74, 377.07, 535.62, 379.95, 515.4, 381.4, 483.61, 381.4, 483.61, 375.62, 450.38, 375.62, 435.94, 374.18, 411.38, 374.18, 396.93, 377.07, 369.48, 391.51, 350.7, 408.85, 333.36, 413.18, 326.14, 430.52, 298.69, 442.08, 282.8, 442.08, 274.13, 442.08, 268.35, 430.52, 253.91, 418.96, 235.12, 394.4, 213.45, 375.62, 204.79, 362.62, 203.34, 346.73, 190.34, 353.95, 168.67, 355.4, 148.44, 345.28, 136.88, 340.95, 132.55, 329.39, 132.55, 314.94, 132.55, 307.72, 132.55, 300.5, 134.0, 294.72, 144.11]], "area": 48882.93950000001, "iscrowd": 0, "image_id": 124786, "bbox": [244.15, 132.55, 197.93, 488.31], "category_id": 1, "id": 514454, "split": "val", "sentences": [{"tokens": ["guy", "wearing", "black", "jacket", "standing", "next", "to", "a", "woman"], "raw": "Guy wearing black jacket standing next to a woman.", "sent_id": 56602, "sent": "guy wearing black jacket standing next to a woman"}, {"tokens": ["a", "man", "standing", "next", "to", "a", "women", "and", "a", "gold", "fire", "hydrant"], "raw": "A man standing next to a women and a gold fire hydrant", "sent_id": 56603, "sent": "a man standing next to a women and a gold fire hydrant"}], "file_name": "COCO_train2014_000000124786_514454.jpg", "ann_id": 514454, "sent_ids": [56602, 56603], "ref_id": 26750}, {"segmentation": [[634.25, 402.11, 602.47, 396.58, 578.98, 393.82, 588.65, 370.33, 592.8, 335.78, 592.8, 316.44, 590.04, 294.33, 601.09, 294.33, 601.09, 232.15, 620.44, 295.71, 625.96, 304.0, 639.78, 306.76], [585.89, 183.78, 559.64, 178.25, 530.62, 179.64, 507.13, 203.13, 491.93, 254.25, 491.93, 216.95, 507.13, 187.93, 523.71, 174.11, 537.53, 171.35, 566.55, 167.2]], "area": 6527.017550000001, "iscrowd": 0, "image_id": 55385, "bbox": [491.93, 167.2, 147.85, 234.91], "category_id": 27, "id": 2073510, "split": "val", "sentences": [{"tokens": ["the", "black", "tote", "bag", "belonging", "to", "the", "man", "on", "the", "far", "right"], "raw": "The black tote bag belonging to the man on the far right", "sent_id": 56610, "sent": "the black tote bag belonging to the man on the far right"}, {"tokens": ["the", "black", "bag", "that", "the", "guy", "furthest", "to", "the", "right", "with", "the", "watch", "on", "is", "carrying"], "raw": "The black bag that the guy furthest to the right with the watch on is carrying", "sent_id": 56611, "sent": "the black bag that the guy furthest to the right with the watch on is carrying"}], "file_name": "COCO_train2014_000000055385_2073510.jpg", "ann_id": 2073510, "sent_ids": [56610, 56611], "ref_id": 26753}, {"segmentation": [[372.01, 379.41, 378.64, 354.02, 388.57, 344.08, 394.09, 326.42, 416.17, 288.89, 423.9, 270.12, 422.79, 227.07, 434.94, 181.81, 438.25, 158.63, 438.25, 124.41, 432.73, 101.23, 432.73, 76.94, 464.74, 67.01, 476.88, 72.53, 494.55, 76.94, 487.92, 86.88, 485.71, 99.02, 492.34, 113.37, 524.35, 91.29, 525.45, 86.88, 534.29, 101.23, 529.87, 119.99, 516.62, 121.1, 495.65, 142.07, 493.44, 172.98, 494.55, 208.31, 505.58, 230.38, 495.65, 243.63, 527.66, 330.84, 546.43, 382.72, 535.39, 392.66, 504.48, 383.82, 503.38, 348.5, 471.36, 282.27, 463.64, 274.54, 413.96, 348.5, 406.23, 363.95, 399.61, 390.45, 370.91, 389.34]], "area": 21968.019299999996, "iscrowd": 0, "image_id": 339283, "bbox": [370.91, 67.01, 175.52, 325.65], "category_id": 1, "id": 2150289, "split": "val", "sentences": [{"tokens": ["this", "is", "a", "boy", "wearing", "white", "pants", "and", "holding", "a", "baseball", "bat"], "raw": "This is a boy wearing white pants and holding a baseball bat.", "sent_id": 56614, "sent": "this is a boy wearing white pants and holding a baseball bat"}, {"tokens": ["a", "kid", "hitting", "a", "baseball", "with", "his", "bat"], "raw": "a kid hitting a baseball with his bat", "sent_id": 56615, "sent": "a kid hitting a baseball with his bat"}], "file_name": "COCO_train2014_000000339283_2150289.jpg", "ann_id": 2150289, "sent_ids": [56614, 56615], "ref_id": 26754}, {"segmentation": [[323.1, 171.51, 307.61, 248.96, 343.01, 295.43, 340.8, 349.65, 333.05, 348.55, 320.88, 348.55, 312.03, 359.61, 312.03, 370.68, 320.88, 380.63, 338.59, 385.06, 354.08, 386.17, 367.36, 383.95, 372.89, 378.42, 377.31, 371.78, 377.31, 362.93, 370.68, 358.5, 362.93, 350.76, 355.18, 348.55, 350.76, 348.55, 347.44, 347.44, 354.08, 299.86, 358.5, 293.22, 390.59, 265.56, 397.23, 253.39, 387.27, 175.93, 357.4, 174.83, 338.59, 173.72]], "area": 10816.82785, "iscrowd": 0, "image_id": 563525, "bbox": [307.61, 171.51, 89.62, 214.66], "category_id": 46, "id": 2182856, "split": "val", "sentences": [{"tokens": ["a", "wine", "glass", "that", "is", "not", "being", "poured", "into"], "raw": "A wine glass that is not being poured into.", "sent_id": 56681, "sent": "a wine glass that is not being poured into"}, {"tokens": ["the", "empty", "wine", "glass"], "raw": "the empty wine glass", "sent_id": 56682, "sent": "the empty wine glass"}], "file_name": "COCO_train2014_000000563525_2182856.jpg", "ann_id": 2182856, "sent_ids": [56681, 56682], "ref_id": 26784}, {"segmentation": [[497.4, 197.57, 494.42, 173.17, 484.31, 157.7, 472.4, 124.97, 480.14, 108.9, 487.28, 99.38, 503.94, 101.76, 508.11, 114.26, 515.25, 146.39, 526.56, 154.72, 534.29, 218.99, 538.46, 245.77, 537.27, 257.67, 524.18, 270.76, 517.03, 259.46, 517.03, 241.6], [485.15, 294.39, 485.15, 320.86, 476.33, 345.36, 506.71, 349.28, 515.53, 337.52, 508.68, 308.12], [565.53, 276.75, 598.86, 296.35, 611.6, 309.09, 611.6, 335.55, 591.02, 322.81, 555.72, 297.33, 547.88, 288.51]], "area": 8014.312449999999, "iscrowd": 0, "image_id": 90573, "bbox": [472.4, 99.38, 139.2, 249.9], "category_id": 1, "id": 565146, "split": "val", "sentences": [{"tokens": ["group", "of", "three", "children", "on", "a", "soccer", "field"], "raw": "Group of three children on a soccer field", "sent_id": 56793, "sent": "group of three children on a soccer field"}], "file_name": "COCO_train2014_000000090573_565146.jpg", "ann_id": 565146, "sent_ids": [56793], "ref_id": 26832}, {"segmentation": [[260.27, 236.45, 283.47, 220.98, 295.85, 204.48, 319.05, 195.72, 459.28, 180.77, 467.52, 185.92, 471.65, 174.58, 487.63, 183.86, 480.41, 191.6, 479.9, 199.33, 487.63, 201.91, 478.35, 212.73, 479.9, 228.72, 472.68, 243.67, 461.85, 239.54, 460.31, 223.04, 448.45, 212.73, 436.08, 211.19, 345.34, 241.09, 341.22, 249.85, 348.43, 268.41, 341.22, 295.22, 357.71, 357.09, 357.2, 371.52, 329.87, 392.14, 320.08, 392.14, 323.69, 381.83, 344.82, 361.21, 335.03, 338.01, 319.05, 312.75, 316.47, 365.34, 316.98, 368.43, 315.44, 384.93, 315.44, 396.78, 306.16, 395.24, 302.03, 363.27, 299.97, 306.56, 298.94, 304.5, 291.21, 305.02, 279.35, 309.14, 260.79, 346.26, 255.63, 371.01, 257.18, 401.94, 248.93, 410.7, 250.48, 392.66, 245.84, 356.57, 252.54, 316.87, 259.76, 273.05, 254.6, 265.83, 268.01, 253.46, 262.34, 245.73], [232.95, 306.56, 218.0, 390.08, 227.8, 381.32, 230.89, 358.63, 235.01, 344.71, 239.14, 307.59]], "area": 18783.914450000004, "iscrowd": 0, "image_id": 77380, "bbox": [218.0, 174.58, 269.63, 236.12], "category_id": 25, "id": 1823313, "split": "val", "sentences": [{"tokens": ["middle", "giraffe"], "raw": "Middle giraffe.", "sent_id": 56825, "sent": "middle giraffe"}, {"tokens": ["the", "giraffe", "in", "the", "middle"], "raw": "the giraffe in the middle", "sent_id": 56826, "sent": "the giraffe in the middle"}], "file_name": "COCO_train2014_000000077380_1823313.jpg", "ann_id": 1823313, "sent_ids": [56825, 56826], "ref_id": 26843}, {"segmentation": [[1.44, 323.69, 21.57, 306.43, 28.76, 292.05, 46.02, 263.29, 71.91, 248.9, 84.85, 244.59, 94.92, 208.64, 104.99, 191.38, 132.31, 166.93, 159.64, 159.74, 181.21, 155.42, 212.85, 164.05, 224.36, 168.37, 235.87, 200.01, 254.56, 234.52, 257.44, 279.11, 257.44, 303.56, 256.0, 317.94, 263.19, 371.15, 245.93, 394.16, 243.06, 420.05, 254.56, 454.57, 243.06, 477.58, 12.94, 517.85]], "area": 71396.585, "iscrowd": 0, "image_id": 311273, "bbox": [1.44, 155.42, 261.75, 362.43], "category_id": 1, "id": 468446, "split": "val", "sentences": [{"tokens": ["a", "little", "girl", "smiling", "as", "a", "woman", "cuts", "a", "cake"], "raw": "A little girl smiling as a woman cuts a cake.", "sent_id": 56887, "sent": "a little girl smiling as a woman cuts a cake"}, {"tokens": ["a", "little", "girl", "wearing", "a", "maroon", "shirt", ",", "visibly", "happy", "to", "get", "a", "piece", "of", "the", "cake"], "raw": "A little girl wearing a maroon shirt, visibly happy to get a piece of the cake.", "sent_id": 56888, "sent": "a little girl wearing a maroon shirt , visibly happy to get a piece of the cake"}], "file_name": "COCO_train2014_000000311273_468446.jpg", "ann_id": 468446, "sent_ids": [56887, 56888], "ref_id": 26867}, {"segmentation": [[245.6, 600.63, 251.38, 589.07, 251.38, 570.29, 252.82, 550.07, 270.68, 552.86, 269.66, 530.45, 276.38, 515.84, 287.49, 498.06, 303.39, 479.28, 303.39, 472.05, 307.72, 448.94, 307.72, 434.49, 309.16, 412.82, 310.61, 394.04, 310.61, 376.7, 322.17, 360.81, 325.06, 399.82, 325.06, 408.49, 323.61, 420.05, 329.39, 430.16, 333.72, 433.05, 353.95, 427.27, 355.4, 420.05, 353.95, 382.48, 343.84, 349.26, 333.72, 327.58, 329.39, 314.58, 339.5, 313.14, 351.06, 305.91, 362.93, 293.22, 367.95, 280.72, 372.59, 239.96, 348.17, 213.45, 339.5, 206.23, 337.3, 181.43, 288.75, 180.29, 273.05, 190.34, 257.16, 199.01, 239.82, 213.45, 225.37, 225.01, 210.93, 233.68, 202.26, 259.68, 202.26, 275.58, 203.7, 285.69, 203.7, 300.14, 203.7, 304.47, 202.26, 327.58, 202.26, 340.59, 193.59, 324.7, 200.81, 290.02, 193.59, 277.02, 189.26, 269.8, 182.03, 274.13, 173.36, 284.24, 170.47, 307.36, 170.47, 321.81, 177.7, 339.14, 202.26, 370.93, 206.59, 370.93, 218.15, 408.49, 210.93, 412.82, 206.59, 414.27, 195.03, 440.27, 195.03, 454.72, 191.46, 490.84, 185.18, 513.0, 171.92, 577.52, 171.92, 586.19, 174.81, 589.07, 182.03, 593.41, 189.26, 580.41, 203.7, 567.4, 218.15, 537.07, 222.48, 516.84, 228.26, 508.17, 232.6, 499.5, 244.15, 498.06, 242.71, 529.84, 236.93, 548.62, 229.71, 560.18, 223.93, 594.85, 244.15, 602.08]], "area": 48858.654550000014, "iscrowd": 0, "image_id": 490610, "bbox": [170.47, 180.29, 202.12, 421.79], "category_id": 1, "id": 211520, "split": "val", "sentences": [{"tokens": ["a", "little", "boy", "wearing", "a", "big", "hat"], "raw": "A little boy wearing a big hat.", "sent_id": 56911, "sent": "a little boy wearing a big hat"}, {"tokens": ["a", "little", "boy", "with", "a", "beach", "hat", "and", "blue", "floral", "shorts"], "raw": "A little boy with a beach hat and blue floral shorts.", "sent_id": 56912, "sent": "a little boy with a beach hat and blue floral shorts"}], "file_name": "COCO_train2014_000000490610_211520.jpg", "ann_id": 211520, "sent_ids": [56911, 56912], "ref_id": 26876}, {"segmentation": [[391.54, 121.58, 363.78, 112.96, 319.74, 92.86, 312.08, 92.86, 294.85, 92.86, 289.11, 93.82, 283.36, 95.73, 272.83, 92.86, 246.03, 86.16, 219.22, 78.5, 209.65, 76.58, 199.12, 73.71, 180.93, 65.1, 173.27, 70.84, 165.61, 71.8, 151.25, 75.63, 141.68, 90.94, 134.02, 94.77, 132.11, 108.18, 132.11, 134.02, 136.89, 151.25, 144.55, 192.42, 142.64, 226.88, 141.68, 292.93, 143.6, 291.98, 150.3, 297.72, 166.57, 290.06, 167.53, 290.06, 156.04, 255.6, 157.0, 243.16, 157.96, 239.33, 158.91, 245.07, 163.7, 222.09, 176.14, 231.67, 175.19, 249.86, 179.02, 261.34, 181.89, 280.49, 190.5, 299.64, 193.38, 295.81, 203.91, 296.76, 208.69, 286.23, 197.2, 266.13, 188.59, 252.73, 190.5, 230.71, 201.99, 234.54, 254.64, 239.33, 254.64, 239.33, 253.69, 235.5, 251.77, 224.97, 253.69, 214.44, 251.77, 204.86, 252.73, 182.84, 285.28, 154.13, 298.68, 155.08, 341.76, 169.44, 394.41, 189.55, 402.07, 190.5, 434.62, 199.12, 461.42, 205.82, 476.74, 213.48, 492.05, 211.56, 498.76, 201.99, 498.76, 192.42, 494.93, 185.72, 483.44, 164.66, 473.87, 145.51, 458.55, 123.49, 461.42, 115.83, 493.97, 112.0, 468.12, 110.09, 453.76, 112.96, 447.06, 113.92, 430.79, 108.18, 423.13, 115.83, 409.73, 117.75, 397.28, 125.41]], "area": 37344.008549999984, "iscrowd": 0, "image_id": 178492, "bbox": [132.11, 65.1, 366.65, 234.54], "category_id": 21, "id": 72008, "split": "val", "sentences": [{"tokens": ["a", "large", "brown", "and", "white", "cow", "behind", "the", "white", "calve"], "raw": "a large brown and white cow behind the white calve", "sent_id": 56919, "sent": "a large brown and white cow behind the white calve"}, {"tokens": ["black", "and", "white", "cows", "stand", "on", "in", "an", "open", "field"], "raw": "Black and white cows stand on in an open field.", "sent_id": 56920, "sent": "black and white cows stand on in an open field"}], "file_name": "COCO_train2014_000000178492_72008.jpg", "ann_id": 72008, "sent_ids": [56919, 56920], "ref_id": 26879}, {"segmentation": [[171.08, 260.08, 169.61, 253.47, 165.2, 228.51, 159.33, 213.09, 166.67, 195.47, 171.81, 182.25, 181.36, 180.78, 196.77, 180.78, 205.59, 179.31, 206.32, 174.17, 196.77, 169.77, 184.29, 166.83, 163.73, 159.49, 161.53, 158.02, 169.61, 150.68, 171.08, 133.79, 149.78, 130.85, 149.78, 135.26, 126.29, 155.82, 127.76, 174.17, 127.76, 183.72, 127.02, 210.15, 131.43, 218.96, 132.16, 219.7, 124.82, 229.97, 108.67, 238.79, 91.78, 251.27, 91.05, 270.36, 93.98, 274.03, 105.73, 271.83, 136.57, 249.8, 146.85, 243.92, 146.85, 258.61, 149.05, 279.9, 164.47, 279.9, 174.75, 279.9, 176.22, 270.36]], "area": 6594.041549999999, "iscrowd": 0, "image_id": 417753, "bbox": [91.05, 130.85, 115.27, 149.05], "category_id": 1, "id": 521936, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "sweater", "and", "black", "pants", "with", "a", "stripe", "hitting", "a", "ball", "to", "another", "person"], "raw": "A man in a white sweater and black pants with a stripe hitting a ball to another person.", "sent_id": 56934, "sent": "a man in a white sweater and black pants with a stripe hitting a ball to another person"}, {"tokens": ["man", "with", "bat"], "raw": "man with bat", "sent_id": 56935, "sent": "man with bat"}], "file_name": "COCO_train2014_000000417753_521936.jpg", "ann_id": 521936, "sent_ids": [56934, 56935], "ref_id": 26887}, {"segmentation": [[74.83, 10.31, 52.77, 28.54, 39.33, 39.09, 32.62, 44.85, 26.86, 63.08, 22.07, 76.51, 20.15, 77.47, 17.27, 78.43, 7.67, 69.79, 4.8, 65.0, 0.96, 65.0, 0.96, 419.0, 76.75, 419.96, 96.9, 419.96, 86.34, 405.57, 127.6, 367.2, 146.78, 341.3, 191.87, 287.57, 240.8, 242.48, 254.23, 193.55, 248.48, 184.92, 242.72, 183.0, 242.72, 183.0, 234.09, 196.43, 218.74, 198.35, 205.3, 203.15, 197.63, 201.23, 191.87, 189.72, 197.63, 172.45, 197.63, 163.81, 192.83, 160.93, 185.16, 168.61, 177.48, 174.37, 176.52, 164.77, 180.36, 159.02, 197.63, 143.67, 199.55, 112.97, 200.51, 68.83, 166.93, 35.26, 149.66, 21.83, 113.21, 10.31]], "area": 71046.78005, "iscrowd": 0, "image_id": 460362, "bbox": [0.96, 10.31, 253.27, 409.65], "category_id": 1, "id": 503265, "split": "val", "sentences": [{"tokens": ["guy", "clicking", "picture", "of", "pizza", "with", "dslr", "camera"], "raw": "guy clicking picture of pizza with dslr camera", "sent_id": 56970, "sent": "guy clicking picture of pizza with dslr camera"}, {"tokens": ["a", "man", "taking", "the", "photography", "of", "the", "pizza"], "raw": "A man taking the photography of the pizza", "sent_id": 56971, "sent": "a man taking the photography of the pizza"}], "file_name": "COCO_train2014_000000460362_503265.jpg", "ann_id": 503265, "sent_ids": [56970, 56971], "ref_id": 26900}, {"segmentation": [[269.03, 285.88, 195.31, 302.16, 191.48, 319.39, 206.8, 328.0, 202.97, 336.62, 197.22, 340.45, 170.42, 333.75, 174.25, 308.86, 101.48, 291.62, 70.85, 276.31, 67.02, 263.86, 114.89, 211.2, 155.1, 176.74, 167.54, 170.03, 292.96, 157.59, 369.56, 169.08, 434.66, 161.42, 419.34, 154.72, 431.79, 153.76, 460.51, 159.5, 466.25, 157.59, 506.46, 81.0, 513.17, 82.91, 494.98, 162.37, 503.59, 157.59, 506.46, 167.16, 591.67, 160.46, 586.89, 168.12, 500.72, 180.57, 458.59, 225.56, 447.11, 220.78, 438.49, 215.03, 434.66, 186.31, 423.17, 210.24, 404.02, 195.88, 392.53, 185.35, 382.96, 199.71, 365.73, 202.59, 362.85, 189.18, 307.33, 199.71, 306.37, 210.24, 300.62, 200.67, 295.84, 211.2, 280.52, 212.16, 276.69, 197.8, 208.71, 210.24, 215.41, 272.48]], "area": 29814.816049999987, "iscrowd": 0, "image_id": 368479, "bbox": [67.02, 81.0, 524.65, 259.45], "category_id": 5, "id": 159374, "split": "val", "sentences": [{"tokens": ["a", "large", "airplane", "being", "boarded"], "raw": "A LARGE AIRPLANE BEING BOARDED.", "sent_id": 57056, "sent": "a large airplane being boarded"}, {"tokens": ["large", "white", "plane", "that", "is", "unloading"], "raw": "Large white plane that is unloading.", "sent_id": 57057, "sent": "large white plane that is unloading"}], "file_name": "COCO_train2014_000000368479_159374.jpg", "ann_id": 159374, "sent_ids": [57056, 57057], "ref_id": 26935}, {"segmentation": [[606.56, 293.68, 524.1, 251.87, 523.72, 243.44, 495.34, 228.86, 502.62, 196.64, 509.53, 189.74, 535.99, 186.67, 553.25, 188.97, 559.39, 167.11, 562.84, 160.21, 568.98, 159.06, 638.78, 176.32]], "area": 11412.618499999997, "iscrowd": 0, "image_id": 88647, "bbox": [495.34, 159.06, 143.44, 134.62], "category_id": 63, "id": 1604389, "split": "val", "sentences": [{"tokens": ["a", "black", "pillow", "on", "a", "two", "-", "seater", "beige", "sofa", "leaned", "up", "against", "the", "wall", "beneath", "a", "window"], "raw": "A black pillow on a two-seater beige sofa leaned up against the wall beneath a window.", "sent_id": 57141, "sent": "a black pillow on a two - seater beige sofa leaned up against the wall beneath a window"}, {"tokens": ["a", "slick", "off", "white", "leather", "love", "seat", "by", "a", "window", "in", "a", "living", "room"], "raw": "a slick off white leather love seat by a window in a living room", "sent_id": 57142, "sent": "a slick off white leather love seat by a window in a living room"}], "file_name": "COCO_train2014_000000088647_1604389.jpg", "ann_id": 1604389, "sent_ids": [57141, 57142], "ref_id": 26965}, {"segmentation": [[115.39, 247.12, 115.39, 242.81, 139.33, 218.88, 153.69, 256.69, 154.64, 270.09, 158.47, 281.1, 152.73, 291.15, 152.25, 300.25, 153.69, 305.03, 149.86, 307.43, 142.2, 304.56, 124.49, 272.01], [160.39, 204.52, 161.82, 214.57, 165.18, 223.18, 164.7, 243.77, 166.61, 264.35, 170.44, 276.32, 174.27, 281.1, 174.27, 282.54, 191.02, 270.09, 207.78, 251.9, 191.02, 229.89, 177.62, 216.0, 171.88, 216.0, 167.09, 210.74, 165.18, 206.91]], "area": 3928.7467500000007, "iscrowd": 0, "image_id": 215436, "bbox": [115.39, 204.52, 92.39, 102.91], "category_id": 31, "id": 2077369, "split": "val", "sentences": [{"tokens": ["a", "yellow", "messenger", "bag", "being", "held", "by", "a", "man"], "raw": "A yellow messenger bag being held by a man", "sent_id": 57144, "sent": "a yellow messenger bag being held by a man"}, {"tokens": ["a", "yellow", "bag", "pinned", "beneath", "the", "forearm", "of", "a", "man", "sitting", "on", "a", "yellow", "fire", "hydrant", ".\\"], "raw": "A yellow bag pinned beneath the forearm of a man sitting on a yellow fire hydrant.\\", "sent_id": 57145, "sent": "a yellow bag pinned beneath the forearm of a man sitting on a yellow fire hydrant .\\"}], "file_name": "COCO_train2014_000000215436_2077369.jpg", "ann_id": 2077369, "sent_ids": [57144, 57145], "ref_id": 26966}, {"segmentation": [[229.71, 130.74, 222.48, 132.19, 213.81, 145.19, 215.26, 179.86, 215.26, 187.09, 210.93, 192.87, 200.81, 195.76, 179.14, 211.65, 160.36, 226.09, 151.69, 237.65, 144.47, 247.77, 138.69, 257.88, 208.04, 312.78, 203.7, 360.45, 195.03, 435.58, 208.04, 438.47, 199.37, 489.03, 208.04, 536.7, 180.59, 572.82, 203.7, 575.71, 228.26, 551.15, 228.26, 512.14, 231.15, 478.92, 223.93, 460.14, 231.15, 438.47, 245.6, 425.46, 249.93, 442.8, 236.93, 470.25, 229.71, 522.26, 245.6, 549.71, 257.16, 541.04, 258.6, 532.37, 251.38, 513.59, 254.27, 489.03, 271.6, 454.36, 271.6, 434.13, 271.6, 431.24, 287.49, 424.02, 294.72, 421.13, 287.49, 382.12, 287.49, 347.45, 286.05, 327.22, 293.27, 315.67, 338.06, 260.77, 339.5, 244.88, 323.61, 221.76, 316.39, 214.54, 301.94, 200.09, 293.27, 197.2, 278.83, 197.2, 268.71, 194.31, 264.38, 181.31, 265.82, 171.2, 267.27, 150.97, 264.38, 130.74, 249.93, 123.52, 232.6, 123.52, 221.04, 129.3]], "area": 37926.2557, "iscrowd": 0, "image_id": 138496, "bbox": [138.69, 123.52, 200.81, 452.19], "category_id": 1, "id": 445891, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "on", "a", "sandy", "beach"], "raw": "A man in a white shirt on a sandy beach.", "sent_id": 57151, "sent": "a man in a white shirt on a sandy beach"}, {"tokens": ["a", "man", "in", "a", "hite", "shirt"], "raw": "A man in a hite shirt.", "sent_id": 57152, "sent": "a man in a hite shirt"}], "file_name": "COCO_train2014_000000138496_445891.jpg", "ann_id": 445891, "sent_ids": [57151, 57152], "ref_id": 26969}, {"segmentation": [[71.23, 375.85, 67.48, 347.74, 69.35, 333.37, 61.23, 338.99, 49.36, 343.99, 43.12, 342.74, 39.37, 340.24, 46.24, 330.87, 47.49, 320.88, 54.36, 319.01, 64.98, 303.39, 73.1, 292.15, 73.1, 286.53, 69.98, 274.03, 64.98, 265.29, 64.98, 257.79, 64.98, 248.43, 69.98, 237.18, 77.47, 232.81, 83.72, 230.94, 90.59, 227.19, 99.96, 225.31, 108.08, 228.44, 119.95, 233.43, 124.94, 232.81, 130.56, 234.06, 132.44, 238.43, 131.19, 243.43, 129.94, 245.93, 122.44, 247.8, 115.57, 249.67, 113.07, 255.3, 113.07, 260.92, 117.45, 265.29, 118.7, 273.41, 119.95, 282.78, 125.57, 288.4, 125.57, 292.15, 132.44, 299.02, 127.44, 304.64, 104.95, 327.13, 94.96, 334.62, 90.59, 341.49, 93.71, 350.24, 97.46, 355.86, 106.83, 357.73, 117.45, 354.61, 119.95, 340.87, 124.94, 340.24, 118.07, 403.33, 112.45, 414.57, 118.7, 422.69, 104.95, 423.32, 94.96, 423.94, 89.96, 420.19, 88.09, 418.32, 76.22, 418.32, 64.98, 413.32, 64.98, 403.95, 73.72, 396.46, 78.1, 385.84, 82.47, 382.72]], "area": 9711.592999999997, "iscrowd": 0, "image_id": 264821, "bbox": [39.37, 225.31, 93.07, 198.63], "category_id": 88, "id": 1160599, "split": "val", "sentences": [{"tokens": ["a", "teddy", "bear", "wearing", "a", "purple", "jacket", "stands", "next", "to", "a", "bear", "in", "a", "dress"], "raw": "A teddy bear wearing a purple jacket stands next to a bear in a dress.", "sent_id": 57159, "sent": "a teddy bear wearing a purple jacket stands next to a bear in a dress"}], "file_name": "COCO_train2014_000000264821_1160599.jpg", "ann_id": 1160599, "sent_ids": [57159], "ref_id": 26971}, {"segmentation": [[458.75, 343.88, 461.47, 266.05, 438.84, 170.11, 424.35, 120.34, 430.7, 93.19, 412.59, 95.91, 420.74, 33.46, 466.89, 28.93, 494.04, 39.79, 525.72, 65.14, 570.07, 85.05, 588.16, 134.82, 578.21, 200.88, 584.54, 285.05, 575.49, 281.43, 566.44, 209.93, 559.21, 257.9, 552.86, 368.31, 542.0, 368.31, 539.3, 241.61, 542.0, 175.55, 525.72, 218.98, 526.62, 253.38, 503.09, 372.84, 484.08, 368.31, 504.9, 233.47, 503.99, 180.97, 493.13, 199.07, 486.8, 274.19, 482.27, 360.16, 473.22, 367.4, 450.61, 366.5]], "area": 35252.725249999996, "iscrowd": 0, "image_id": 3178, "bbox": [412.59, 28.93, 175.57, 343.91], "category_id": 25, "id": 597590, "split": "val", "sentences": [{"tokens": ["baby", "giraffe", "to", "the", "right", "of", "its", "mother"], "raw": "Baby giraffe to the right of its mother.", "sent_id": 57217, "sent": "baby giraffe to the right of its mother"}, {"tokens": ["giraffe", "to", "the", "right", "of", "two", "other", "giraffes"], "raw": "Giraffe to the right of two other giraffes.", "sent_id": 57218, "sent": "giraffe to the right of two other giraffes"}], "file_name": "COCO_train2014_000000003178_597590.jpg", "ann_id": 597590, "sent_ids": [57217, 57218], "ref_id": 26993}, {"segmentation": [[313.25, 225.81, 321.68, 278.24, 315.05, 283.66, 324.09, 290.29, 334.34, 339.7, 327.11, 344.52, 340.96, 346.33, 349.4, 349.34, 366.88, 346.93, 371.7, 355.37, 375.31, 352.35, 372.9, 345.73, 389.77, 337.89, 404.84, 377.06, 412.07, 375.25, 400.02, 341.51, 419.3, 327.05, 421.71, 321.02, 419.9, 310.78, 413.88, 313.79, 383.75, 301.74, 377.12, 241.48, 372.9, 217.38, 315.05, 220.39, 315.05, 233.04]], "area": 8756.7464, "iscrowd": 0, "image_id": 36574, "bbox": [313.25, 217.38, 108.46, 159.68], "category_id": 62, "id": 373204, "split": "val", "sentences": [{"tokens": ["the", "wooden", "chair", "on", "the", "left", "in", "the", "row", "of", "three"], "raw": "the wooden chair on the left in the row of three", "sent_id": 57273, "sent": "the wooden chair on the left in the row of three"}, {"tokens": ["the", "wooden", "chair", "closest", "to", "the", "table"], "raw": "The wooden chair closest to the table.", "sent_id": 57274, "sent": "the wooden chair closest to the table"}], "file_name": "COCO_train2014_000000036574_373204.jpg", "ann_id": 373204, "sent_ids": [57273, 57274], "ref_id": 27012}, {"segmentation": [[2.16, 172.97, 0.0, 311.35, 91.89, 406.49, 144.86, 472.43, 408.65, 470.27, 496.22, 377.3, 318.92, 220.54, 230.27, 29.19, 3.24, 172.97]], "area": 129981.7601, "iscrowd": 0, "image_id": 187939, "bbox": [0.0, 29.19, 496.22, 443.24], "category_id": 73, "id": 1102941, "split": "val", "sentences": [{"tokens": ["a", "silver", "laptop"], "raw": "A silver laptop.", "sent_id": 57283, "sent": "a silver laptop"}, {"tokens": ["silver", "laptop", "computer"], "raw": "silver laptop computer", "sent_id": 57284, "sent": "silver laptop computer"}], "file_name": "COCO_train2014_000000187939_1102941.jpg", "ann_id": 1102941, "sent_ids": [57283, 57284], "ref_id": 27015}, {"segmentation": [[323.41, 287.71, 293.19, 282.29, 281.51, 275.74, 282.36, 244.1, 290.63, 244.38, 292.05, 238.4, 289.2, 233.55, 293.48, 231.56, 293.19, 226.42, 306.59, 227.57, 312.01, 227.57, 311.72, 216.16, 313.43, 204.48, 310.3, 201.34, 312.86, 197.92, 318.56, 201.34, 318.56, 207.33, 317.99, 230.7, 327.11, 228.71, 326.83, 223.0, 332.53, 224.14, 333.67, 207.9, 331.11, 202.77, 335.67, 201.34, 340.23, 203.05, 337.38, 207.33, 337.95, 225.85, 341.65, 229.85, 350.2, 228.71, 357.04, 212.46, 356.47, 233.27, 367.3, 234.98, 385.26, 237.83, 384.98, 240.68, 384.12, 246.95, 411.49, 246.95, 411.49, 251.51, 425.74, 252.65, 427.45, 254.64, 430.87, 256.35, 429.73, 261.2, 436.0, 262.05, 435.43, 266.33, 433.43, 269.18, 442.84, 269.47, 436.0, 279.16, 446.83, 287.99, 435.71, 291.13, 441.7, 295.4, 433.15, 298.54, 432.58, 301.68, 359.61, 299.68, 356.47, 295.97, 372.72, 283.43, 362.74, 285.43, 325.69, 286.85]], "area": 8863.140300000003, "iscrowd": 0, "image_id": 381214, "bbox": [281.51, 197.92, 165.32, 103.76], "category_id": 9, "id": 179510, "split": "val", "sentences": [{"tokens": ["white", "boat", "attached", "to", "a", "doc"], "raw": "White boat attached to a doc.", "sent_id": 57316, "sent": "white boat attached to a doc"}, {"tokens": ["the", "big", "boat"], "raw": "The big boat.", "sent_id": 57317, "sent": "the big boat"}], "file_name": "COCO_train2014_000000381214_179510.jpg", "ann_id": 179510, "sent_ids": [57316, 57317], "ref_id": 27027}, {"segmentation": [[306.13, 1.48, 305.06, 15.44, 263.18, 31.55, 263.18, 76.65, 274.99, 109.94, 286.81, 112.08, 285.73, 146.45, 279.29, 179.74, 280.36, 214.1, 306.13, 224.84, 350.16, 225.91, 366.27, 218.39, 393.11, 226.98, 396.34, 242.02, 408.15, 240.94, 414.59, 201.21, 421.03, 175.44, 421.03, 175.44, 419.96, 159.33, 421.03, 158.26, 425.33, 141.08, 429.62, 87.39, 443.58, 97.05, 471.5, 83.09, 471.5, 83.09, 468.28, 54.1, 433.92, 9.0, 422.11, 0.41, 382.38, 3.63, 315.8, 3.63]], "area": 35041.70725, "iscrowd": 0, "image_id": 229825, "bbox": [263.18, 0.41, 208.32, 241.61], "category_id": 1, "id": 446300, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "blue", "button", "up", "shirt"], "raw": "a woman in a blue button up shirt", "sent_id": 57332, "sent": "a woman in a blue button up shirt"}, {"tokens": ["a", "woman", "wearing", "light", "blue", "shirt"], "raw": "A WOMAN WEARING LIGHT BLUE SHIRT", "sent_id": 57333, "sent": "a woman wearing light blue shirt"}], "file_name": "COCO_train2014_000000229825_446300.jpg", "ann_id": 446300, "sent_ids": [57332, 57333], "ref_id": 27035}, {"segmentation": [[242.05, 114.15, 254.43, 79.77, 317.69, 67.39, 352.07, 108.65, 328.69, 177.41, 368.58, 239.3, 389.2, 258.55, 445.59, 283.31, 489.6, 299.81, 541.86, 328.69, 528.11, 352.07, 479.97, 334.19, 427.71, 314.94, 386.45, 317.69, 387.83, 319.07, 445.59, 328.69, 470.35, 349.32, 462.09, 369.95, 429.09, 371.33, 402.96, 371.33, 400.21, 376.83, 468.97, 391.96, 484.1, 412.58, 492.35, 437.34, 490.98, 463.47, 488.22, 515.73, 484.1, 532.23, 463.47, 543.24, 404.33, 561.11, 404.33, 576.24, 378.2, 601.0, 297.06, 602.37, 324.57, 567.99, 336.94, 484.1, 276.43, 490.98, 248.93, 441.47, 254.43, 437.34, 294.31, 419.46, 292.93, 374.08, 258.55, 349.32, 220.04, 327.32, 239.3, 321.82, 225.55, 291.56, 203.54, 297.06, 200.79, 265.43, 206.29, 226.92, 225.55, 198.04, 253.05, 167.78]], "area": 84663.52125000002, "iscrowd": 0, "image_id": 220504, "bbox": [200.79, 67.39, 341.07, 534.98], "category_id": 1, "id": 213947, "split": "val", "sentences": [{"tokens": ["an", "elderly", "man", "in", "a", "blue", "cap"], "raw": "an elderly man in a blue cap", "sent_id": 57343, "sent": "an elderly man in a blue cap"}, {"tokens": ["a", "man", "wearing", "a", "blue", "hat", "riding", "a", "motorcycle"], "raw": "A man wearing a blue hat riding a motorcycle.", "sent_id": 57344, "sent": "a man wearing a blue hat riding a motorcycle"}], "file_name": "COCO_train2014_000000220504_213947.jpg", "ann_id": 213947, "sent_ids": [57343, 57344], "ref_id": 27040}, {"segmentation": [[638.87, 223.92, 594.09, 250.43, 538.33, 247.69, 530.11, 266.88, 528.28, 276.02, 531.94, 282.42, 522.8, 288.82, 521.88, 311.67, 535.59, 321.72, 570.32, 330.86, 573.98, 330.86, 575.81, 341.83, 584.03, 359.19, 611.45, 368.33, 637.04, 347.31]], "area": 11050.414449999997, "iscrowd": 0, "image_id": 466949, "bbox": [521.88, 223.92, 116.99, 144.41], "category_id": 3, "id": 132398, "split": "val", "sentences": [{"tokens": ["a", "silver", "colored", "sedan"], "raw": "a silver colored sedan", "sent_id": 57460, "sent": "a silver colored sedan"}, {"tokens": ["a", "car", "parked", "in", "front", "of", "school", "bus"], "raw": "A car parked in front of school bus.", "sent_id": 57461, "sent": "a car parked in front of school bus"}], "file_name": "COCO_train2014_000000466949_132398.jpg", "ann_id": 132398, "sent_ids": [57460, 57461], "ref_id": 27087}, {"segmentation": [[171.25, 100.25, 182.16, 76.38, 212.18, 60.0, 235.37, 69.55, 253.79, 85.93, 256.52, 129.58, 246.97, 152.77, 272.2, 182.79, 294.72, 193.7, 331.0, 205.3, 330.87, 214.85, 331.0, 345.14, 331.0, 481.56, 330.19, 500.0, 134.41, 500.0, 135.78, 493.16, 128.96, 485.66, 116.0, 482.93, 109.86, 462.46, 128.96, 356.73, 130.32, 331.49, 143.28, 252.37, 152.83, 215.53, 168.52, 205.3, 191.03, 194.38, 192.4, 174.6, 171.93, 136.4, 171.25, 122.76, 173.3, 112.53]], "area": 70400.5303, "iscrowd": 0, "image_id": 443741, "bbox": [109.86, 60.0, 221.14, 440.0], "category_id": 1, "id": 1231856, "split": "val", "sentences": [{"tokens": ["a", "man", "who", "wears", "glasses", "with", "a", "dark", "suit", "coat", ",", "white", "shirt", ",", "dark", "brown", "tie", "and", "khaki", "pants"], "raw": "A man who wears glasses with a dark suit coat, white shirt, dark brown tie and khaki pants", "sent_id": 57570, "sent": "a man who wears glasses with a dark suit coat , white shirt , dark brown tie and khaki pants"}, {"tokens": ["a", "man", "wearing", "a", "blue", "suit", "jacket", "and", "glasses", "smiling"], "raw": "A man wearing a blue suit jacket and glasses smiling.", "sent_id": 57571, "sent": "a man wearing a blue suit jacket and glasses smiling"}], "file_name": "COCO_train2014_000000443741_1231856.jpg", "ann_id": 1231856, "sent_ids": [57570, 57571], "ref_id": 27128}, {"segmentation": [[172.5, 399.16, 170.26, 388.68, 173.25, 381.94, 174.75, 378.2, 171.75, 374.45, 172.88, 365.47, 176.62, 361.73, 182.61, 357.24, 184.11, 359.11, 198.7, 340.39, 199.83, 325.79, 200.57, 319.81, 207.31, 313.82, 216.29, 310.45, 227.52, 307.83, 233.51, 306.33, 242.12, 304.46, 265.7, 299.22, 277.68, 295.48, 285.91, 293.23, 292.28, 293.23, 296.39, 293.6, 299.39, 294.73, 302.38, 299.97, 303.13, 320.93, 299.39, 340.02, 306.5, 358.36, 306.5, 367.34, 302.01, 365.84, 302.01, 363.22, 300.89, 360.98, 300.89, 369.59, 295.65, 371.46, 294.9, 367.34, 296.39, 359.86, 294.52, 351.99, 291.15, 347.88, 288.91, 342.26, 287.79, 347.88, 290.03, 350.87, 285.54, 363.97, 283.67, 379.32, 274.69, 380.07, 275.43, 375.2, 277.68, 370.34, 278.43, 363.97, 279.55, 349.37, 279.55, 343.01, 273.56, 347.88, 265.7, 352.74, 252.23, 356.11, 240.25, 354.24, 245.12, 365.1, 248.11, 380.44, 246.99, 389.42, 242.5, 391.67, 243.99, 383.81, 243.99, 377.82, 242.87, 371.83, 239.88, 366.22, 238.38, 362.85, 234.26, 361.73, 237.26, 380.07, 235.01, 382.31, 233.14, 379.69, 232.76, 372.96, 229.77, 366.22, 228.65, 362.1, 226.03, 359.48, 211.05, 366.97, 207.69, 373.33, 203.19, 373.7, 199.45, 380.44, 196.83, 386.8, 189.72, 392.04, 180.74, 400.28, 173.63, 400.28]], "area": 7281.815499999998, "iscrowd": 0, "image_id": 83561, "bbox": [170.26, 293.23, 136.24, 107.05], "category_id": 21, "id": 1820314, "split": "val", "sentences": [{"tokens": ["a", "skinny", "brown", "cow", "eating", "to", "the", "left", "of", "a", "lighter", "colored", "smaller", "one"], "raw": "A skinny brown cow eating to the left of a lighter colored smaller one.", "sent_id": 57572, "sent": "a skinny brown cow eating to the left of a lighter colored smaller one"}, {"tokens": ["a", "starving", "dark", "brown", "cow"], "raw": "a starving dark brown cow", "sent_id": 57573, "sent": "a starving dark brown cow"}], "file_name": "COCO_train2014_000000083561_1820314.jpg", "ann_id": 1820314, "sent_ids": [57572, 57573], "ref_id": 27129}, {"segmentation": [[109.04, 195.92, 115.61, 209.05, 117.58, 216.94, 121.52, 221.53, 132.69, 224.16, 136.63, 224.82, 142.54, 230.07, 149.11, 236.64, 155.68, 243.87, 160.28, 252.41, 162.25, 263.58, 166.85, 261.6, 172.1, 239.27, 172.1, 237.3, 168.82, 230.07, 160.28, 226.13, 156.34, 224.16, 151.74, 221.53, 139.26, 211.68, 127.44, 204.46, 126.12, 191.97, 137.29, 171.61, 140.57, 149.93, 141.23, 133.51, 141.23, 128.91, 142.54, 121.69, 147.14, 111.18, 145.17, 103.95, 140.57, 98.7, 138.6, 96.73, 142.54, 88.84, 147.14, 83.59, 150.43, 80.3, 151.74, 72.42, 143.86, 70.45, 141.23, 69.79, 142.54, 63.23, 142.54, 55.34, 130.72, 54.03, 127.44, 57.31, 126.12, 63.23, 120.87, 71.76, 114.3, 78.99, 95.91, 90.16, 95.25, 98.04, 100.5, 106.58, 102.47, 109.21, 102.47, 121.69, 99.85, 132.2, 99.19, 136.8, 99.19, 153.22, 99.19, 157.16, 90.65, 167.01, 80.14, 174.24, 69.63, 184.75, 68.97, 185.41, 67.66, 187.38, 78.17, 211.68, 86.71, 217.59, 87.37, 218.25, 91.31, 230.73, 91.31, 237.3, 87.37, 245.18, 86.05, 253.06, 105.76, 241.9, 111.01, 239.27, 112.98, 234.67, 100.5, 217.59, 99.19, 212.99, 95.91, 206.43, 93.28, 197.89, 103.79, 195.92, 104.44, 195.92, 105.76, 193.95]], "area": 8096.122899999997, "iscrowd": 0, "image_id": 34680, "bbox": [67.66, 54.03, 104.44, 209.55], "category_id": 1, "id": 496274, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "blue", "tshirt", "&", "catch", "the", "plate"], "raw": "a man wearing a blue tshirt & catch the plate", "sent_id": 57599, "sent": "a man wearing a blue tshirt & catch the plate"}, {"tokens": ["a", "jumping", "boy", "in", "a", "blue", "shirt", "and", "khakis"], "raw": "A jumping boy in a blue shirt and khakis.", "sent_id": 57600, "sent": "a jumping boy in a blue shirt and khakis"}], "file_name": "COCO_train2014_000000034680_496274.jpg", "ann_id": 496274, "sent_ids": [57599, 57600], "ref_id": 27141}, {"segmentation": [[430.66, 369.63, 458.98, 311.04, 474.61, 279.79, 490.23, 260.25, 491.21, 230.96, 492.19, 208.5, 469.73, 204.59, 435.55, 233.89, 394.53, 229.0, 377.93, 231.93, 369.14, 230.96, 360.35, 255.37, 357.42, 255.37, 336.91, 259.28, 325.2, 256.35, 318.36, 260.25, 294.92, 297.36, 289.06, 318.85, 291.99, 365.72, 301.76, 363.77, 316.41, 343.26, 356.45, 362.79, 375.98, 365.72, 382.81, 370.61]], "area": 21372.1642, "iscrowd": 0, "image_id": 533568, "bbox": [289.06, 204.59, 203.13, 166.02], "category_id": 63, "id": 1951789, "split": "val", "sentences": [{"tokens": ["brown", "arm", "chair"], "raw": "brown arm chair", "sent_id": 57672, "sent": "brown arm chair"}, {"tokens": ["brown", "chair", "in", "living", "room"], "raw": "Brown chair in living room.", "sent_id": 57673, "sent": "brown chair in living room"}], "file_name": "COCO_train2014_000000533568_1951789.jpg", "ann_id": 1951789, "sent_ids": [57672, 57673], "ref_id": 27167}, {"segmentation": [[6.47, 221.2, 7.55, 185.6, 11.87, 158.63, 20.49, 128.43, 31.28, 111.17, 44.22, 98.23, 78.74, 90.68, 100.31, 98.23, 114.34, 115.49, 131.6, 138.14, 131.6, 168.34, 136.99, 193.15, 135.91, 210.41, 124.04, 222.27, 105.71, 244.93, 104.63, 251.4, 122.97, 257.87, 143.46, 275.13, 153.17, 296.7, 172.58, 318.27, 186.61, 345.24, 203.87, 377.6, 190.92, 394.86, 170.43, 408.88, 161.8, 411.04, 171.51, 474.68, 5.39, 470.36, 12.94, 214.72]], "area": 52552.702150000005, "iscrowd": 0, "image_id": 551524, "bbox": [5.39, 90.68, 198.48, 384.0], "category_id": 1, "id": 492532, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "red", "shirt"], "raw": "A woman in a red shirt.", "sent_id": 57703, "sent": "a woman in a red shirt"}, {"tokens": ["a", "women", "with", "long", "hair", "and", "a", "marron", "shirt"], "raw": "A women with long hair and a marron shirt", "sent_id": 57704, "sent": "a women with long hair and a marron shirt"}], "file_name": "COCO_train2014_000000551524_492532.jpg", "ann_id": 492532, "sent_ids": [57703, 57704], "ref_id": 27180}, {"segmentation": [[410.72, 145.82, 422.18, 165.88, 422.18, 199.31, 395.43, 261.39, 395.43, 300.56, 378.24, 382.7, 364.87, 420.91, 317.11, 421.86, 316.16, 391.3, 298.01, 420.91, 272.22, 421.86, 269.35, 346.4, 294.19, 241.34, 311.38, 206.0, 286.55, 214.59, 270.31, 208.86, 261.71, 179.25, 240.7, 174.48, 232.1, 155.37, 213.0, 146.78, 234.97, 131.49, 303.74, 147.73, 331.44, 132.45, 363.91, 136.27, 360.09, 115.26, 379.2, 78.96, 404.03, 71.32, 425.04, 87.56, 429.82, 99.97, 424.09, 126.72, 413.58, 139.13]], "area": 38871.80770000002, "iscrowd": 0, "image_id": 355717, "bbox": [213.0, 71.32, 216.82, 350.54], "category_id": 1, "id": 474999, "split": "val", "sentences": [{"tokens": ["man", "playing", "tennis"], "raw": "man playing tennis", "sent_id": 57719, "sent": "man playing tennis"}, {"tokens": ["the", "man", "holding", "a", "black", "ball", "bat", ",", "wearing", "white", "shorts", "and", "a", "white", "shirt", "with", "a", "yellow", "and", "blue", "stripe", "running", "diagonal", "down", "it"], "raw": "The man holding a black ball bat, wearing white shorts and a white shirt with a yellow and blue stripe running diagonal down it.", "sent_id": 57720, "sent": "the man holding a black ball bat , wearing white shorts and a white shirt with a yellow and blue stripe running diagonal down it"}], "file_name": "COCO_train2014_000000355717_474999.jpg", "ann_id": 474999, "sent_ids": [57719, 57720], "ref_id": 27187}, {"segmentation": [[3.24, 31.28, 176.9, 40.99, 194.16, 32.36, 222.2, 17.26, 243.78, 24.81, 248.09, 28.04, 279.37, 36.67, 307.42, 37.75, 326.83, 30.2, 351.64, 30.2, 427.15, 37.75, 423.91, 198.47, 413.12, 196.31, 420.67, 168.27, 416.36, 153.17, 405.57, 140.22, 386.16, 133.75, 369.98, 145.62, 365.66, 157.48, 365.66, 168.27, 368.9, 182.29, 368.9, 189.84, 363.51, 192.0, 358.11, 196.31, 322.52, 198.47, 323.6, 184.45, 326.83, 168.27, 319.28, 149.93, 316.04, 149.93, 299.87, 127.28, 281.53, 132.67, 277.21, 149.93, 289.08, 153.17, 285.84, 166.11, 283.69, 184.45, 281.53, 187.69, 276.13, 195.24, 272.9, 197.39, 264.27, 200.63, 190.92, 199.55, 184.45, 185.53, 181.21, 173.66, 173.66, 167.19, 170.43, 159.64, 173.66, 147.78, 174.74, 140.22, 174.74, 130.52, 166.11, 121.89, 155.33, 117.57, 141.3, 125.12, 141.3, 139.15, 141.3, 146.7, 140.22, 153.17, 131.6, 155.33, 98.16, 139.15, 88.45, 128.36, 66.88, 116.49, 63.64, 114.34, 64.72, 103.55, 65.8, 92.76, 61.48, 76.58, 57.17, 65.8, 44.22, 59.33, 31.28, 58.25, 21.57, 63.64, 10.79, 71.19, 9.71, 84.13, 16.18, 92.76, 16.18, 97.08, 8.63, 108.94, 6.47, 113.26, 3.24, 35.6]], "area": 48932.87769999999, "iscrowd": 0, "image_id": 411238, "bbox": [3.24, 17.26, 423.91, 183.37], "category_id": 6, "id": 168566, "split": "val", "sentences": [{"tokens": ["a", "red", "and", "yellow", "bus", "with", "an", "ad", "on", "the", "side"], "raw": "A red and yellow bus with an ad on the side", "sent_id": 57739, "sent": "a red and yellow bus with an ad on the side"}, {"tokens": ["the", "large", "colorful", "bus", "that", "has", "a", "large", "ice", "cream", "on", "the", "side", "of", "it"], "raw": "The large colorful bus that has a large ice cream on the side of it.", "sent_id": 57740, "sent": "the large colorful bus that has a large ice cream on the side of it"}], "file_name": "COCO_train2014_000000411238_168566.jpg", "ann_id": 168566, "sent_ids": [57739, 57740], "ref_id": 27194}, {"segmentation": [[425.71, 436.13, 407.01, 454.83, 360.99, 417.44, 385.44, 348.4, 388.31, 197.39, 385.44, 118.29, 379.69, 101.03, 299.15, 119.73, 306.34, 237.66, 322.16, 270.74, 302.02, 269.3, 296.27, 211.78, 267.51, 136.99, 238.74, 111.1, 214.29, 108.22, 199.91, 109.66, 199.91, 132.67, 103.55, 95.28, 92.04, 60.76, 71.91, 3.24, 355.24, 4.67, 427.0, 0.0, 427.0, 3.24, 427.0, 299.51, 427.0, 428.94]], "area": 54370.876849999986, "iscrowd": 0, "image_id": 563110, "bbox": [71.91, 0.0, 355.09, 454.83], "category_id": 22, "id": 584609, "split": "val", "sentences": [{"tokens": ["an", "adult", "elephant", "which", "is", "partly", "not", "in", "the", "picture"], "raw": "An adult elephant which is partly not in the picture.", "sent_id": 57776, "sent": "an adult elephant which is partly not in the picture"}, {"tokens": ["the", "bigger", "elephant"], "raw": "the bigger elephant", "sent_id": 57777, "sent": "the bigger elephant"}], "file_name": "COCO_train2014_000000563110_584609.jpg", "ann_id": 584609, "sent_ids": [57776, 57777], "ref_id": 27209}, {"segmentation": [[320.56, 393.07, 270.0, 404.19, 279.1, 423.4, 239.66, 434.53, 192.13, 414.3, 192.13, 371.83, 246.74, 340.48, 310.45, 333.4, 296.29, 284.87, 235.62, 293.97, 188.09, 288.91, 172.92, 282.84, 183.03, 238.35, 233.6, 243.4, 259.89, 245.43, 286.18, 227.22, 297.3, 214.08, 315.51, 191.83, 322.58, 178.69, 323.6, 160.48, 315.51, 146.33, 308.43, 103.85, 355.96, 82.62, 399.44, 121.04, 400.45, 145.31, 392.36, 166.55, 392.36, 189.81, 406.52, 193.85, 411.57, 203.97, 384.27, 220.15, 366.07, 235.31, 357.98, 253.52, 339.78, 286.89, 337.75, 301.04, 337.75, 340.48, 336.74, 367.79, 329.66, 378.91, 325.62, 385.99]], "area": 32219.4084, "iscrowd": 0, "image_id": 440689, "bbox": [172.92, 82.62, 238.65, 351.91], "category_id": 1, "id": 185675, "split": "val", "sentences": [{"tokens": ["person", "on", "scooter", "wearing", "black", "helmet", ",", "and", "has", "black", "backpack"], "raw": "person on scooter wearing black helmet, and has black backpack", "sent_id": 57828, "sent": "person on scooter wearing black helmet , and has black backpack"}, {"tokens": ["man", "on", "moped", "wearing", "stiped", "shirt", "and", "black", "helmet", "carrying", "a", "backpack"], "raw": "Man on moped wearing stiped shirt and black helmet carrying a backpack", "sent_id": 57829, "sent": "man on moped wearing stiped shirt and black helmet carrying a backpack"}], "file_name": "COCO_train2014_000000440689_185675.jpg", "ann_id": 185675, "sent_ids": [57828, 57829], "ref_id": 27226}, {"segmentation": [[1.61, 178.06, 33.02, 186.92, 61.21, 190.14, 90.2, 197.39, 107.92, 199.0, 115.17, 199.0, 117.58, 202.23, 118.39, 217.53, 118.39, 217.53, 120.81, 228.0, 117.58, 245.72, 112.75, 252.16, 119.19, 259.41, 117.58, 277.93, 118.39, 290.82, 103.09, 295.65, 78.93, 298.06, 53.96, 299.68, 24.97, 300.48, 11.28, 301.29, 0.0, 296.45, 0.81, 244.1, 2.42, 196.59, 0.0, 174.04], [169.13, 196.59, 186.85, 194.98, 195.7, 215.92, 196.51, 228.0, 190.87, 239.27, 179.6, 243.3, 172.35, 249.74, 169.13, 248.13, 170.74, 229.61, 169.13, 211.89, 165.91, 197.39], [223.89, 177.26, 231.95, 174.04, 240.81, 180.48, 241.61, 180.48, 240.0, 167.59, 233.56, 159.54, 229.53, 150.68, 224.7, 143.43, 227.92, 137.8, 241.61, 127.33, 244.03, 132.96, 245.64, 139.41, 249.66, 144.24, 259.33, 138.6, 261.74, 144.24, 257.72, 153.9, 256.11, 177.26, 252.08, 197.39, 242.42, 211.89, 241.61, 217.53, 234.36, 227.19, 228.72, 211.89, 227.11, 194.17, 225.5, 187.73, 223.09, 175.65]], "area": 15778.236800000002, "iscrowd": 0, "image_id": 411289, "bbox": [0.0, 127.33, 261.74, 173.96], "category_id": 9, "id": 177593, "split": "val", "sentences": [{"tokens": ["the", "boat", "on", "the", "left"], "raw": "The boat on the left.", "sent_id": 57858, "sent": "the boat on the left"}, {"tokens": ["the", "boat", "on", "the", "let"], "raw": "The boat on the let.", "sent_id": 57859, "sent": "the boat on the let"}], "file_name": "COCO_train2014_000000411289_177593.jpg", "ann_id": 177593, "sent_ids": [57858, 57859], "ref_id": 27237}, {"segmentation": [[230.31, 164.23, 313.18, 150.24, 320.72, 188.99, 328.25, 190.06, 320.72, 149.17, 449.87, 124.41, 527.35, 113.65, 527.35, 127.64, 512.29, 134.1, 528.43, 141.63, 517.67, 171.77, 493.99, 175.0, 469.24, 218.04, 455.25, 268.63, 433.72, 312.75, 463.86, 314.91, 459.55, 324.59, 435.87, 328.9, 406.82, 403.16, 394.98, 453.74, 305.65, 422.53, 265.83, 369.79, 260.45, 347.19, 251.84, 342.89, 230.31, 325.67, 226.01, 292.3, 220.63, 271.86, 223.86, 227.73, 217.4, 186.83, 227.09, 171.77]], "area": 62189.412500000006, "iscrowd": 0, "image_id": 291493, "bbox": [217.4, 113.65, 311.03, 340.09], "category_id": 54, "id": 310339, "split": "val", "sentences": [{"tokens": ["a", "half", "of", "a", "sandwich", "that", "has", "a", "piece", "of", "mushroom", "hanging", "out", "of", "the", "end"], "raw": "a half of a sandwich that has a piece of mushroom hanging out of the end", "sent_id": 57937, "sent": "a half of a sandwich that has a piece of mushroom hanging out of the end"}, {"tokens": ["a", "piece", "of", "sandwich", "closest", "to", "you"], "raw": "a piece of sandwich closest to you", "sent_id": 57938, "sent": "a piece of sandwich closest to you"}], "file_name": "COCO_train2014_000000291493_310339.jpg", "ann_id": 310339, "sent_ids": [57937, 57938], "ref_id": 27266}, {"segmentation": [[150.59, 593.55, 139.65, 546.98, 131.42, 516.85, 131.42, 452.46, 123.21, 397.68, 119.1, 433.29, 104.03, 433.29, 91.7, 414.12, 93.07, 260.7, 102.66, 233.31, 132.79, 205.92, 136.9, 190.85, 121.83, 163.45, 138.27, 137.43, 165.67, 136.05, 183.47, 144.28, 183.47, 168.93, 190.32, 194.96, 191.7, 212.77, 213.6, 212.77, 245.11, 314.12, 258.8, 375.76, 246.48, 390.83, 225.94, 351.11, 225.94, 397.68, 221.83, 427.81, 221.83, 440.13, 199.91, 460.68, 227.31, 479.86, 219.08, 540.13, 199.91, 551.09, 223.19, 560.67, 209.5, 585.33, 172.51, 560.67, 187.58, 483.97, 175.26, 419.6, 175.26, 533.29, 171.15, 563.42, 177.99, 599.03, 182.11, 620.94, 161.55, 616.83, 147.86, 597.66]], "area": 46700.74655, "iscrowd": 0, "image_id": 124786, "bbox": [91.7, 136.05, 167.1, 484.89], "category_id": 1, "id": 477643, "split": "val", "sentences": [{"tokens": ["a", "woman", "standing", "next", "to", "a", "golden", "fire", "hydrant"], "raw": "A woman standing next to a golden fire hydrant.", "sent_id": 57970, "sent": "a woman standing next to a golden fire hydrant"}, {"tokens": ["a", "woman", "next", "to", "a", "fire", "hydrant"], "raw": "A woman next to a fire hydrant.", "sent_id": 57971, "sent": "a woman next to a fire hydrant"}], "file_name": "COCO_train2014_000000124786_477643.jpg", "ann_id": 477643, "sent_ids": [57970, 57971], "ref_id": 27278}, {"segmentation": [[16.2, 397.5, 29.54, 403.22, 32.4, 349.85, 44.79, 390.83, 54.32, 389.88, 50.51, 346.04, 56.23, 299.34, 69.57, 306.01, 89.58, 307.92, 95.3, 219.29, 63.85, 241.21, 23.83, 250.74, 19.06, 277.42, 21.92, 322.21, 20.97, 351.76]], "area": 7263.428650000002, "iscrowd": 0, "image_id": 418989, "bbox": [16.2, 219.29, 79.1, 183.93], "category_id": 25, "id": 600810, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "whose", "head", "is", "not", "visible"], "raw": "The giraffe whose head is not visible.", "sent_id": 57991, "sent": "the giraffe whose head is not visible"}, {"tokens": ["the", "back", "of", "a", "giraffe", "standing", "behind", "another", "giraffe"], "raw": "The back of a giraffe standing behind another giraffe.", "sent_id": 57992, "sent": "the back of a giraffe standing behind another giraffe"}], "file_name": "COCO_train2014_000000418989_600810.jpg", "ann_id": 600810, "sent_ids": [57991, 57992], "ref_id": 27286}, {"segmentation": [[239.83, 148.05, 245.36, 124.06, 251.82, 118.53, 266.58, 112.07, 272.11, 89.94, 394.79, 93.63, 408.63, 111.15, 441.84, 136.98, 437.22, 158.19, 439.07, 178.49, 439.07, 194.17, 439.07, 211.69, 438.15, 234.75, 377.27, 247.67, 361.59, 252.28, 329.3, 241.21, 310.85, 235.68, 280.41, 232.91, 255.51, 233.83, 261.97, 215.38, 272.11, 195.09, 278.57, 172.95, 267.5, 156.35, 254.59, 152.66]], "area": 25211.786900000006, "iscrowd": 0, "image_id": 331419, "bbox": [239.83, 89.94, 202.01, 162.34], "category_id": 18, "id": 16785, "split": "val", "sentences": [{"tokens": ["the", "poodle", "behind", "the", "the", "other", "dog", "next", "to", "the", "dark", "brown", "dog"], "raw": "The poodle behind the the other dog next to the dark brown dog.", "sent_id": 57999, "sent": "the poodle behind the the other dog next to the dark brown dog"}, {"tokens": ["a", "dog", "back", "and", "in", "between", "two", "other", "dogs", "looking", "out", "side"], "raw": "A dog back and in between two other dogs looking out side", "sent_id": 58000, "sent": "a dog back and in between two other dogs looking out side"}], "file_name": "COCO_train2014_000000331419_16785.jpg", "ann_id": 16785, "sent_ids": [57999, 58000], "ref_id": 27288}, {"segmentation": [[2.13, 289.11, 3.19, 273.17, 24.45, 251.91, 79.72, 250.85, 78.66, 234.91, 90.35, 229.59, 85.03, 254.04, 104.17, 242.35, 131.8, 261.48, 132.87, 271.04, 122.24, 290.18, 115.86, 324.19, 87.16, 322.07, 51.02, 319.94, 46.77, 336.95, 27.64, 356.08, 20.2, 392.22, 3.19, 400.72, 2.13, 379.46]], "area": 10843.288350000003, "iscrowd": 0, "image_id": 484369, "bbox": [2.13, 229.59, 130.74, 171.13], "category_id": 64, "id": 1608005, "split": "val", "sentences": [{"tokens": ["wooden", "flower", "container"], "raw": "Wooden flower container.", "sent_id": 58015, "sent": "wooden flower container"}], "file_name": "COCO_train2014_000000484369_1608005.jpg", "ann_id": 1608005, "sent_ids": [58015], "ref_id": 27296}, {"segmentation": [[123.1, 143.18, 154.7, 150.31, 186.61, 156.81, 211.08, 160.84, 232.76, 164.87, 256.61, 168.89, 260.95, 173.54, 258.78, 181.28, 254.13, 185.31, 250.42, 187.17, 249.49, 228.99, 238.65, 229.61, 237.1, 186.86, 225.64, 185.31, 167.4, 203.9, 167.4, 236.11, 153.77, 238.59, 147.58, 235.8, 149.74, 178.19, 76.64, 169.82, 20.88, 163.01, 22.43, 230.23, 25.53, 242.31, 31.41, 250.98, 38.85, 256.87, 32.34, 262.44, 17.79, 263.68, 9.42, 264.3, 1.06, 262.13, 0.0, 178.19, 1.06, 161.46, 1.37, 105.7, 1.06, 99.2, 0.0, 59.86, 19.64, 59.55, 20.26, 138.54, 50.0, 139.47, 58.36, 134.51, 98.63, 134.2, 107.0, 135.44, 107.31, 137.92, 100.18, 140.4, 113.19, 140.4, 121.87, 141.63]], "area": 13325.373150000003, "iscrowd": 0, "image_id": 357362, "bbox": [0.0, 59.55, 260.95, 204.75], "category_id": 15, "id": 1396116, "split": "val", "sentences": [{"tokens": ["the", "railing", "that", "the", "people", "are", "standing", "on"], "raw": "The railing that the people are standing on.", "sent_id": 58030, "sent": "the railing that the people are standing on"}, {"tokens": ["the", "section", "of", "rail", "closest", "in", "the", "image"], "raw": "The section of rail closest in the image.", "sent_id": 58031, "sent": "the section of rail closest in the image"}], "file_name": "COCO_train2014_000000357362_1396116.jpg", "ann_id": 1396116, "sent_ids": [58030, 58031], "ref_id": 27303}, {"segmentation": [[123.28, 349.97, 113.28, 324.98, 117.45, 290.83, 125.78, 273.34, 139.94, 250.01, 173.26, 224.19, 207.41, 205.03, 244.9, 197.53, 257.39, 189.2, 257.39, 184.21, 275.72, 169.21, 274.05, 162.55, 264.89, 150.89, 257.39, 142.56, 260.72, 136.73, 271.55, 136.73, 285.71, 144.22, 289.88, 140.06, 299.87, 135.06, 314.03, 130.06, 331.52, 135.89, 340.69, 143.39, 354.85, 134.23, 367.34, 132.56, 380.67, 135.89, 374.84, 144.22, 366.51, 153.39, 357.35, 157.55, 371.51, 173.38, 381.5, 196.7, 397.33, 223.36, 399.0, 234.19, 404.83, 241.68, 394.0, 275.83, 384.84, 284.16, 397.33, 289.99, 407.33, 304.99, 409.82, 311.65, 407.33, 319.15, 394.0, 309.15, 377.34, 297.49, 366.51, 295.83, 364.01, 294.16, 373.17, 309.15, 384.0, 320.81, 388.17, 322.48, 376.51, 325.81, 368.18, 322.48, 361.51, 316.65, 350.68, 305.82, 342.35, 316.65, 336.52, 323.31, 288.21, 336.64, 263.22, 334.98, 217.41, 342.47, 168.26, 343.31]], "area": 41042.631, "iscrowd": 0, "image_id": 389154, "bbox": [113.28, 130.06, 296.54, 219.91], "category_id": 20, "id": 64833, "split": "val", "sentences": [{"tokens": ["large", "sheep", "with", "lots", "of", "wool"], "raw": "Large sheep with lots of wool.", "sent_id": 58034, "sent": "large sheep with lots of wool"}, {"tokens": ["the", "big", "sheep"], "raw": "The big sheep", "sent_id": 58035, "sent": "the big sheep"}], "file_name": "COCO_train2014_000000389154_64833.jpg", "ann_id": 64833, "sent_ids": [58034, 58035], "ref_id": 27304}, {"segmentation": [[228.11, 471.89, 211.89, 455.68, 196.76, 445.95, 182.7, 431.89, 168.65, 415.68, 149.19, 403.78, 128.65, 388.65, 117.84, 380.0, 100.54, 380.0, 92.97, 380.0, 91.89, 363.78, 97.3, 340.0, 105.95, 324.86, 109.19, 314.05, 114.59, 310.81, 123.24, 311.89, 131.89, 312.97, 144.86, 309.73, 155.68, 300.0, 163.24, 291.35, 166.49, 257.84, 165.41, 230.81, 165.41, 200.54, 167.57, 181.08, 174.05, 163.78, 178.38, 151.89, 178.38, 141.08, 170.81, 127.03, 161.08, 114.05, 150.27, 101.08, 147.03, 101.08, 144.86, 104.32, 144.86, 117.3, 144.86, 125.95, 144.86, 136.76, 144.86, 138.92, 138.38, 137.84, 138.38, 137.84, 136.22, 154.05, 135.14, 168.11, 138.38, 182.16, 142.7, 194.05, 143.78, 203.78, 145.95, 218.92, 145.95, 232.97, 145.95, 252.43, 140.54, 260.0, 135.14, 250.27, 128.65, 231.89, 129.73, 203.78, 129.73, 178.92, 130.81, 163.78, 122.16, 149.73, 109.19, 130.27, 109.19, 119.46, 105.95, 83.78, 105.95, 68.65, 109.19, 62.16, 114.59, 62.16, 121.08, 66.49, 128.65, 66.49, 130.81, 66.49, 128.65, 57.84, 118.92, 42.7, 107.03, 34.05, 98.38, 14.59, 89.73, 10.27, 76.76, 7.03, 34.59, 10.27, 20.54, 23.24, 10.81, 30.81, 1.08, 44.86, 1.08, 53.51, 2.16, 475.14]], "area": 64228.362550000005, "iscrowd": 0, "image_id": 71229, "bbox": [1.08, 7.03, 227.03, 468.11], "category_id": 1, "id": 444537, "split": "val", "sentences": [{"tokens": ["the", "girl", "in", "the", "dress"], "raw": "the girl in the dress", "sent_id": 58125, "sent": "the girl in the dress"}, {"tokens": ["woman", "in", "dress", "brushing", "her", "blonde", "hair"], "raw": "Woman in dress brushing her blonde hair.", "sent_id": 58126, "sent": "woman in dress brushing her blonde hair"}], "file_name": "COCO_train2014_000000071229_444537.jpg", "ann_id": 444537, "sent_ids": [58125, 58126], "ref_id": 27335}, {"segmentation": [[263.86, 296.99, 278.55, 261.31, 287.47, 244.0, 299.54, 224.59, 314.75, 217.77, 331.54, 215.15, 340.46, 213.05, 348.85, 214.62, 353.57, 205.7, 365.12, 196.78, 380.86, 198.88, 391.87, 212.0, 393.45, 220.92, 395.02, 228.79, 392.92, 232.98, 396.59, 240.85, 400.27, 264.99, 398.69, 288.6, 398.69, 299.61, 400.79, 305.38, 401.32, 317.45, 394.5, 328.47, 381.9, 328.47, 374.04, 320.6, 377.18, 307.48, 372.99, 293.32, 371.41, 280.73, 368.26, 290.69, 365.12, 296.46, 362.49, 302.24, 357.25, 308.53, 349.38, 313.25, 360.39, 378.83, 361.44, 426.57, 258.62, 426.05, 254.94, 387.23, 257.57, 355.75, 257.04, 340.01, 256.52, 325.84, 259.67, 310.63, 262.29, 304.33]], "area": 23521.508, "iscrowd": 0, "image_id": 525180, "bbox": [254.94, 196.78, 146.38, 229.79], "category_id": 1, "id": 2157927, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "blue", "-", "green", "towel", "tucked", "into", "his", "apron"], "raw": "The man with the blue-green towel tucked into his apron.", "sent_id": 58140, "sent": "the man with the blue - green towel tucked into his apron"}, {"tokens": ["a", "man", "with", "a", "green", "cloth", "tucked", "into", "his", "waist", "band", "who", "is", "facing", "away", "from", "the", "camera", "and", "has", "tattoos"], "raw": "A man with a green cloth tucked into his waist band who is facing away from the camera and has tattoos.", "sent_id": 58141, "sent": "a man with a green cloth tucked into his waist band who is facing away from the camera and has tattoos"}], "file_name": "COCO_train2014_000000525180_2157927.jpg", "ann_id": 2157927, "sent_ids": [58140, 58141], "ref_id": 27342}, {"segmentation": [[146.14, 362.58, 147.09, 333.92, 158.56, 313.86, 170.02, 306.22, 212.04, 311.95, 228.28, 318.64, 256.94, 291.9, 278.91, 280.43, 289.41, 264.2, 290.37, 256.56, 303.74, 240.32, 303.74, 226.95, 304.7, 215.48, 296.1, 210.71, 303.74, 201.16, 311.38, 194.47, 312.34, 176.32, 320.93, 153.4, 341.95, 138.12, 389.7, 129.52, 429.82, 164.86, 447.97, 251.78, 448.92, 299.54, 447.01, 332.97, 433.64, 385.5, 423.13, 403.65, 405.94, 426.0, 212.04, 426.0, 212.04, 417.98, 223.51, 412.25, 219.69, 399.83, 216.82, 398.87, 200.58, 425.62, 159.51, 425.62, 150.91, 382.64, 180.52, 374.99, 213.96, 369.26, 216.82, 357.8, 219.69, 352.07, 211.09, 357.8, 195.81, 367.35, 189.12, 367.35, 166.2, 372.13, 169.06, 366.4, 181.48, 356.85, 170.02, 354.94, 158.56, 358.76, 149.96, 363.53]], "area": 56157.12569999999, "iscrowd": 0, "image_id": 155268, "bbox": [146.14, 129.52, 302.78, 296.48], "category_id": 1, "id": 447989, "split": "val", "sentences": [{"tokens": ["woman", "sits", "in", "a", "hall"], "raw": "woman sits in a hall", "sent_id": 58161, "sent": "woman sits in a hall"}, {"tokens": ["the", "person", "sitting", "on", "the", "floor"], "raw": "The person sitting on the floor.", "sent_id": 58162, "sent": "the person sitting on the floor"}], "file_name": "COCO_train2014_000000155268_447989.jpg", "ann_id": 447989, "sent_ids": [58161, 58162], "ref_id": 27349}, {"segmentation": [[292.71, 144.6, 289.2, 128.21, 286.86, 122.35, 289.79, 120.01, 281.0, 103.62, 269.88, 91.32, 250.56, 86.64, 252.32, 81.96, 257.0, 74.35, 257.0, 57.95, 253.49, 53.27, 253.49, 43.32, 249.39, 38.05, 244.7, 36.88, 238.85, 30.44, 230.07, 29.27, 222.46, 31.02, 219.53, 33.95, 211.33, 39.8, 211.92, 50.34, 208.41, 57.37, 208.99, 66.74, 211.92, 69.66, 213.09, 70.83, 214.85, 77.86, 216.6, 80.2, 219.53, 86.64, 223.04, 88.4, 213.09, 91.32, 207.82, 90.74, 200.21, 93.08, 190.26, 98.35, 177.96, 113.57, 173.28, 124.7, 172.69, 129.38, 163.91, 132.31, 154.54, 131.72, 153.96, 131.72, 146.35, 137.58, 164.5, 137.58, 184.4, 138.16, 192.6, 139.92, 191.43, 139.92, 183.23, 142.26, 182.06, 144.6, 172.11, 146.36, 162.74, 146.36, 149.86, 146.36, 143.42, 146.94, 151.03, 151.04, 158.64, 152.21, 163.33, 153.97, 170.94, 156.9, 186.74, 149.29, 189.67, 151.04, 199.04, 151.63, 192.01, 165.09, 193.18, 167.43, 187.92, 176.8, 186.16, 182.66, 185.57, 186.17, 182.65, 208.42, 183.82, 220.13, 194.94, 264.62, 199.62, 283.94, 224.8, 284.53, 216.02, 271.65, 220.12, 257.59, 225.97, 247.64, 240.61, 234.18, 240.02, 206.07, 242.36, 190.85, 279.25, 190.85, 279.83, 189.68, 277.49, 182.07, 275.15, 172.7, 272.81, 168.61, 270.46, 158.65, 269.88, 147.53, 269.88, 145.19, 274.56, 155.73, 279.25, 166.85, 281.0, 162.75, 285.1, 153.38, 290.96, 148.11]], "area": 16433.5698, "iscrowd": 0, "image_id": 56677, "bbox": [143.42, 29.27, 149.29, 255.26], "category_id": 1, "id": 1733214, "split": "val", "sentences": [{"tokens": ["this", "is", "a", "woman", "wearing", "a", "green", "shirt", "and", "black", "pants"], "raw": "This is a woman wearing a green shirt and black pants.", "sent_id": 58174, "sent": "this is a woman wearing a green shirt and black pants"}, {"tokens": ["a", "lday", "wearing", "goggles", ",", "blue", "tsheir", ",", "black", "trouser", "standing", "with", "old", "lady", "and", "2", "kids"], "raw": "a lday wearing goggles, blue tsheir, black trouser standing with old lady and 2 kids", "sent_id": 58175, "sent": "a lday wearing goggles , blue tsheir , black trouser standing with old lady and 2 kids"}], "file_name": "COCO_train2014_000000056677_1733214.jpg", "ann_id": 1733214, "sent_ids": [58174, 58175], "ref_id": 27353}, {"segmentation": [[388.12, 235.13, 498.74, 262.78, 490.84, 268.71, 473.06, 276.61, 472.4, 291.75, 477.01, 301.63, 475.03, 308.21, 479.64, 308.21, 484.91, 314.79, 490.18, 307.55, 492.81, 302.28, 505.32, 283.85, 510.59, 285.17, 518.49, 286.48, 528.36, 288.46, 523.76, 292.41, 530.34, 292.41, 536.92, 314.14, 550.09, 328.62, 563.26, 333.89, 554.04, 346.4, 557.99, 355.62, 576.43, 354.3, 573.79, 337.84, 577.75, 328.62, 598.16, 312.16, 613.3, 285.82, 613.96, 267.39, 597.5, 250.93, 611.32, 243.03, 617.25, 243.69, 616.59, 238.42, 610.67, 230.52, 638.98, 226.57, 638.98, 223.28, 613.96, 225.25, 610.67, 225.91, 602.76, 219.98, 604.74, 164.68, 599.47, 166.0, 596.18, 219.98, 587.62, 225.25, 544.17, 217.35, 544.82, 222.62, 581.7, 228.54, 563.92, 245.0, 554.04, 242.37, 558.65, 249.61, 536.27, 247.64, 538.24, 258.17]], "area": 10198.963249999992, "iscrowd": 0, "image_id": 69579, "bbox": [388.12, 164.68, 250.86, 190.94], "category_id": 5, "id": 162342, "split": "val", "sentences": [{"tokens": ["a", "white", "airplane", "facing", "a", "building"], "raw": "a white airplane facing a building.", "sent_id": 58188, "sent": "a white airplane facing a building"}, {"tokens": ["pure", "white", "plane", "parked", "on", "a", "runway"], "raw": "Pure white plane parked on a runway", "sent_id": 58189, "sent": "pure white plane parked on a runway"}], "file_name": "COCO_train2014_000000069579_162342.jpg", "ann_id": 162342, "sent_ids": [58188, 58189], "ref_id": 27359}, {"segmentation": [[553.58, 81.48, 554.57, 62.9, 556.89, 55.6, 569.5, 34.37, 583.77, 27.73, 587.09, 23.09, 585.1, 10.81, 593.72, 3.18, 601.35, 2.85, 607.66, 5.5, 615.29, 12.14, 616.28, 21.43, 611.97, 28.06, 630.88, 40.67, 639.84, 76.5, 635.19, 111.67, 630.55, 115.65, 624.25, 119.3, 621.59, 152.15, 627.23, 183.67, 626.9, 197.27, 623.91, 201.91, 617.61, 206.56, 609.32, 203.24, 604.01, 186.65, 604.01, 175.7, 604.01, 169.73, 596.38, 134.89, 593.72, 124.61, 586.09, 132.57, 582.44, 147.17, 572.16, 178.36, 569.17, 196.27, 563.86, 202.58, 558.22, 203.57, 552.58, 201.91, 549.26, 192.95, 551.25, 183.67, 555.9, 168.74, 555.9, 140.53, 555.9, 134.56, 559.22, 124.28, 552.91, 105.37, 552.58, 97.07]], "area": 11547.842899999994, "iscrowd": 0, "image_id": 270248, "bbox": [549.26, 2.85, 90.58, 203.71], "category_id": 1, "id": 2205086, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "in", "an", "orange", "shirt"], "raw": "A baseball player in an orange shirt.", "sent_id": 58261, "sent": "a baseball player in an orange shirt"}, {"tokens": ["the", "player", "on", "the", "right", "is", "wearing", "an", "orange", "shirt", "and", "cap"], "raw": "The player on the right is wearing an orange shirt and cap.", "sent_id": 58262, "sent": "the player on the right is wearing an orange shirt and cap"}], "file_name": "COCO_train2014_000000270248_2205086.jpg", "ann_id": 2205086, "sent_ids": [58261, 58262], "ref_id": 27383}, {"segmentation": [[228.74, 295.11, 253.63, 205.04, 240.59, 196.74, 245.33, 177.78, 285.63, 156.44, 322.37, 167.11, 343.7, 168.3, 365.04, 175.41, 388.74, 233.48, 367.41, 239.41, 376.89, 251.26, 369.78, 266.67, 362.67, 269.04, 365.04, 301.04, 353.19, 317.63, 322.37, 334.22, 258.37, 330.67]], "area": 20785.380500000003, "iscrowd": 0, "image_id": 47928, "bbox": [228.74, 156.44, 160.0, 177.78], "category_id": 54, "id": 2218372, "split": "val", "sentences": [{"tokens": ["burger", "in", "the", "middle"], "raw": "burger in the middle", "sent_id": 58330, "sent": "burger in the middle"}, {"tokens": ["the", "one", "in", "the", "middle"], "raw": "the one in the middle", "sent_id": 58331, "sent": "the one in the middle"}], "file_name": "COCO_train2014_000000047928_2218372.jpg", "ann_id": 2218372, "sent_ids": [58330, 58331], "ref_id": 27404}, {"segmentation": [[206.76, 625.04, 180.74, 529.17, 205.39, 493.56, 232.79, 452.46, 239.63, 394.93, 225.94, 390.83, 202.64, 392.2, 168.41, 357.95, 150.59, 342.88, 128.69, 326.46, 127.31, 311.39, 135.54, 296.31, 172.51, 329.19, 208.12, 360.7, 245.11, 315.5, 261.55, 279.87, 245.11, 248.38, 261.55, 211.4, 256.07, 179.89, 254.71, 123.73, 241.0, 78.53, 230.04, 47.03, 262.92, 49.76, 271.13, 68.95, 276.61, 147.01, 284.84, 197.7, 309.49, 212.77, 314.97, 248.38, 317.7, 277.14, 341.0, 408.64, 349.21, 442.88, 342.36, 489.45, 327.29, 529.17, 332.77, 556.57, 305.37, 563.42, 317.7, 614.1, 317.7, 629.16, 293.05, 630.52, 283.47, 615.46, 277.99, 592.18, 273.88, 546.98, 258.8, 546.98, 234.15, 540.13, 214.98, 552.46, 241.0, 631.9, 205.39, 630.52]], "area": 46911.81665, "iscrowd": 0, "image_id": 75841, "bbox": [127.31, 47.03, 221.9, 584.87], "category_id": 1, "id": 442787, "split": "val", "sentences": [{"tokens": ["the", "boy", "that", "is", "serving", "a", "ball"], "raw": "The boy that is serving a ball", "sent_id": 58386, "sent": "the boy that is serving a ball"}, {"tokens": ["a", "boy", "in", "blue", "shorts", "serving", "a", "tennis", "ball"], "raw": "A boy in blue shorts serving a tennis ball", "sent_id": 58387, "sent": "a boy in blue shorts serving a tennis ball"}], "file_name": "COCO_train2014_000000075841_442787.jpg", "ann_id": 442787, "sent_ids": [58386, 58387], "ref_id": 27426}, {"segmentation": [[252.35, 139.99, 251.1, 163.76, 243.91, 165.32, 238.9, 175.02, 241.09, 185.03, 246.41, 192.85, 263.92, 201.92, 269.87, 200.36, 281.44, 200.36, 288.63, 206.3, 296.45, 210.68, 297.7, 227.57, 299.27, 235.7, 307.4, 236.95, 316.78, 239.45, 329.3, 241.33, 333.05, 243.21, 344.31, 242.89, 344.31, 238.83, 335.24, 232.88, 331.49, 228.19, 330.55, 223.19, 330.55, 220.37, 378.09, 216.93, 398.11, 216.31, 402.8, 208.8, 431.26, 208.17, 426.57, 214.12, 448.15, 212.87, 461.6, 212.87, 461.92, 200.36, 461.6, 189.41, 457.85, 183.15, 440.33, 175.65, 426.88, 171.89, 420.32, 170.02, 420.32, 141.87, 416.56, 140.3, 398.11, 140.3, 356.51, 136.24, 329.92, 134.98, 305.21, 134.05, 287.7, 134.05, 278.94, 132.79, 269.87, 132.79, 261.42, 132.79, 249.85, 136.86, 251.73, 138.11]], "area": 15456.4988, "iscrowd": 0, "image_id": 88647, "bbox": [238.9, 132.79, 223.02, 110.42], "category_id": 63, "id": 98676, "split": "val", "sentences": [{"tokens": ["a", "large", "couch", "with", "a", "table", "in", "front", "of", "it"], "raw": "A large couch with a table in front of it.", "sent_id": 58475, "sent": "a large couch with a table in front of it"}, {"tokens": ["tan", "leather", "couch", "with", "laptop", "on", "coffee", "table"], "raw": "Tan leather couch with laptop on coffee table.", "sent_id": 58476, "sent": "tan leather couch with laptop on coffee table"}], "file_name": "COCO_train2014_000000088647_98676.jpg", "ann_id": 98676, "sent_ids": [58475, 58476], "ref_id": 27457}, {"segmentation": [[267.53, 167.78, 283.68, 170.09, 291.75, 171.24, 294.05, 175.86, 295.21, 188.54, 288.29, 204.68, 280.22, 210.45, 285.98, 216.22, 292.9, 248.5, 300.97, 294.63, 296.36, 311.93, 294.05, 326.92, 289.44, 358.05, 295.21, 401.87, 269.84, 412.25, 262.92, 363.82, 256.0, 396.11, 250.23, 418.02, 238.7, 446.85, 231.78, 448.0, 224.86, 426.09, 237.55, 368.43, 230.63, 323.46, 230.63, 306.16, 236.4, 248.5, 245.62, 223.14, 258.31, 210.45, 260.61, 195.46, 257.15, 180.47], [274.45, 446.85, 274.45, 428.4, 297.51, 408.79, 306.74, 430.7, 315.96, 436.47, 321.73, 442.23, 319.42, 444.54]], "area": 14121.306100000002, "iscrowd": 0, "image_id": 201634, "bbox": [224.86, 167.78, 96.87, 280.22], "category_id": 1, "id": 493241, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "a", "light", "colored", "tee", "shirt", "standing", "next", "to", "two", "other", "boys", "and", "looking", "off", "into", "the", "distance"], "raw": "A boy in a light colored tee shirt standing next to two other boys and looking off into the distance.", "sent_id": 58500, "sent": "a boy in a light colored tee shirt standing next to two other boys and looking off into the distance"}, {"tokens": ["a", "young", "male", "standing", "with", "a", "skateboard", "and", "a", "grey", "shirt"], "raw": "A young male standing with a skateboard and a grey shirt", "sent_id": 58501, "sent": "a young male standing with a skateboard and a grey shirt"}], "file_name": "COCO_train2014_000000201634_493241.jpg", "ann_id": 493241, "sent_ids": [58500, 58501], "ref_id": 27468}, {"segmentation": [[413.93, 186.32, 405.24, 169.38, 397.86, 151.14, 394.39, 132.47, 400.47, 135.94, 400.47, 146.37, 409.15, 159.83, 413.06, 146.8, 406.98, 135.08, 406.55, 128.56, 412.63, 93.38, 418.71, 73.41, 422.61, 55.17, 421.31, 40.83, 416.1, 25.2, 409.59, 11.74, 402.64, 4.79, 398.29, 0.44, 182.88, 0.88, 168.12, 0.44, 158.56, 21.29, 156.83, 33.45, 159.0, 46.04, 161.17, 47.78, 177.24, 52.12, 191.57, 57.34, 208.51, 69.5, 232.83, 86.87, 254.98, 99.03, 268.01, 103.37, 277.13, 105.11, 278.86, 94.69, 281.03, 87.74, 291.02, 90.34, 303.18, 93.82, 311.43, 95.12, 324.9, 98.59, 330.98, 106.41, 342.27, 122.05, 350.52, 136.38, 369.63, 169.82, 377.45, 201.52, 385.7, 224.11, 388.74, 254.94, 387.0, 287.51, 387.44, 310.1, 387.0, 348.75, 378.32, 362.21, 374.41, 372.63, 376.14, 373.07, 378.75, 371.77, 373.97, 378.28, 409.59, 375.24, 407.41, 370.9, 405.68, 368.73, 407.85, 366.12, 407.85, 363.08, 403.07, 358.74, 403.94, 355.26, 408.72, 352.66, 410.45, 344.41, 410.45, 337.02, 408.28, 329.64, 406.11, 296.2, 404.37, 267.1, 406.11, 245.39, 409.15, 224.11, 409.59, 213.25, 414.8, 195.01], [201.99, 165.04, 207.64, 149.41, 210.24, 140.72, 211.55, 135.94, 235.87, 145.06, 242.82, 148.1, 241.95, 186.32, 244.12, 224.97, 243.25, 259.72, 244.99, 311.83, 245.42, 328.77, 249.33, 342.23, 248.46, 355.26, 249.76, 364.38, 255.84, 369.59, 256.28, 375.24, 253.24, 377.85, 236.74, 379.58, 223.27, 379.58, 226.75, 369.59, 229.35, 361.78, 231.52, 356.13, 231.52, 353.53, 230.22, 343.97, 228.92, 333.55, 229.35, 325.3, 228.05, 295.33, 226.31, 274.48, 225.01, 265.8, 221.54, 312.27, 221.1, 339.63, 219.8, 350.49, 215.46, 355.7, 210.68, 357.43, 208.51, 370.9, 212.85, 376.98, 210.68, 379.15, 201.99, 380.89, 183.32, 382.19, 182.01, 379.15, 188.09, 364.82, 196.78, 351.79, 200.69, 339.19, 202.86, 332.25, 207.2, 284.04, 208.94, 245.82, 207.2, 237.13, 205.47, 225.41, 205.47, 215.85, 205.47, 195.01, 201.99, 171.12]], "area": 40367.424800000015, "iscrowd": 0, "image_id": 3178, "bbox": [156.83, 0.44, 265.78, 381.75], "category_id": 25, "id": 594602, "split": "val", "sentences": [{"tokens": ["the", "mother", "giraffe", "in", "the", "middle"], "raw": "The mother giraffe in the middle", "sent_id": 58536, "sent": "the mother giraffe in the middle"}, {"tokens": ["a", "tan", "and", "white", "giraffe", "with", "a", "small", "giraffe", "under", "it"], "raw": "A tan and white giraffe with a small giraffe under it.", "sent_id": 58537, "sent": "a tan and white giraffe with a small giraffe under it"}], "file_name": "COCO_train2014_000000003178_594602.jpg", "ann_id": 594602, "sent_ids": [58536, 58537], "ref_id": 27479}, {"segmentation": [[298.66, 156.51, 371.95, 180.32, 396.68, 193.15, 412.26, 194.07, 421.42, 205.06, 404.93, 214.22, 396.68, 213.31, 390.27, 242.62, 384.77, 257.28, 382.94, 266.44, 371.95, 313.16, 372.86, 347.06, 383.86, 385.54, 365.54, 375.46, 357.29, 353.47, 357.29, 338.82, 354.54, 290.26, 349.96, 290.26, 356.37, 335.15, 356.37, 338.82, 339.88, 342.48, 338.97, 343.4, 342.63, 366.3, 343.55, 370.88, 326.14, 372.71, 321.56, 364.47, 319.73, 347.06, 310.57, 342.48, 309.65, 341.56, 305.99, 287.51, 299.57, 284.76, 304.15, 342.48, 300.49, 349.81, 284.0, 350.72, 277.59, 347.98, 272.09, 315.91, 269.34, 294.84, 265.68, 271.02, 264.76, 238.96, 255.6, 205.98, 255.6, 184.91, 286.75, 156.51]], "area": 21954.995099999996, "iscrowd": 0, "image_id": 178492, "bbox": [255.6, 156.51, 165.82, 229.03], "category_id": 21, "id": 72904, "split": "val", "sentences": [{"tokens": ["the", "calf", "in", "front"], "raw": "the calf in front", "sent_id": 58627, "sent": "the calf in front"}, {"tokens": ["white", "calf", "standing", "to", "the", "right", "of", "a", "black", "and", "white", "cow"], "raw": "White calf standing to the right of a black and white cow.", "sent_id": 58628, "sent": "white calf standing to the right of a black and white cow"}], "file_name": "COCO_train2014_000000178492_72904.jpg", "ann_id": 72904, "sent_ids": [58627, 58628], "ref_id": 27516}, {"segmentation": [[297.61, 273.96, 298.43, 232.71, 483.62, 222.06, 482.25, 219.33, 474.88, 216.6, 473.24, 217.14, 281.49, 227.25, 281.22, 262.76, 280.13, 267.4, 287.77, 275.87]], "area": 1872.2170500000018, "iscrowd": 0, "image_id": 147303, "bbox": [280.13, 216.6, 203.49, 59.27], "category_id": 6, "id": 248573, "split": "val", "sentences": [{"tokens": ["almost", "hidden", "bus", "that", "is", "the", "third", "one", "in", "counting", "from", "the", "bottom", "up"], "raw": "almost hidden bus that is the third one in counting from the bottom up", "sent_id": 58644, "sent": "almost hidden bus that is the third one in counting from the bottom up"}, {"tokens": ["red", "white", "orange", "and", "blue", "bus", "that", "is", "the", "second", "from", "the", "building"], "raw": "Red white orange and blue bus that is the second from the building", "sent_id": 58645, "sent": "red white orange and blue bus that is the second from the building"}], "file_name": "COCO_train2014_000000147303_248573.jpg", "ann_id": 248573, "sent_ids": [58644, 58645], "ref_id": 27523}, {"segmentation": [[108.93, 112.15, 113.89, 81.69, 127.35, 50.52, 133.72, 32.1, 137.97, 1.63, 221.57, 0.0, 222.28, 14.38, 220.15, 22.89, 224.41, 32.8, 230.07, 83.1, 239.28, 103.65, 249.91, 110.03, 272.58, 167.41, 267.62, 176.62, 273.29, 192.92, 275.41, 199.29, 268.33, 196.46, 256.29, 187.96, 249.2, 174.5, 213.07, 128.45, 199.61, 117.11, 176.94, 91.61, 159.94, 74.6, 139.39, 88.77]], "area": 12706.60925, "iscrowd": 0, "image_id": 500440, "bbox": [108.93, 0.0, 166.48, 199.29], "category_id": 1, "id": 1710641, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "white", "shirt", "behind", "a", "table"], "raw": "A man with a white shirt behind a table.", "sent_id": 58727, "sent": "a man with a white shirt behind a table"}, {"tokens": ["a", "man", "in", "a", "white", "shirt"], "raw": "A man in a white shirt.", "sent_id": 58728, "sent": "a man in a white shirt"}], "file_name": "COCO_train2014_000000500440_1710641.jpg", "ann_id": 1710641, "sent_ids": [58727, 58728], "ref_id": 27556}, {"segmentation": [[188.25, 265.88, 183.0, 301.88, 309.75, 296.63, 306.0, 328.88, 312.75, 329.63, 316.5, 296.63, 347.25, 295.13, 350.25, 328.13, 357.0, 328.88, 360.0, 328.88, 354.75, 288.38, 359.25, 255.38, 354.0, 232.13, 345.0, 223.88, 327.75, 223.13, 317.25, 232.13, 310.5, 193.13, 166.5, 194.63, 175.5, 226.88, 180.75, 235.88, 213.75, 253.88, 228.75, 256.13, 246.75, 256.13, 261.0, 265.88, 252.75, 278.63, 244.5, 290.63, 234.0, 291.38, 227.25, 290.63, 216.0, 277.88, 205.5, 269.63, 201.0, 265.88], [155.25, 301.88, 156.75, 295.88, 149.25, 291.38, 135.0, 289.88, 129.0, 284.63, 118.5, 284.63, 94.5, 286.88, 80.25, 286.88, 78.0, 283.88, 76.5, 265.13, 73.5, 250.13, 60.0, 249.37, 66.75, 262.13, 67.5, 271.88, 65.25, 278.63, 6.0, 288.38, 3.0, 288.38, 1.5, 304.13], [0.75, 247.13, 11.25, 238.87, 24.0, 235.88, 28.5, 229.13, 33.75, 217.88, 42.75, 210.38, 54.0, 197.63, 0.75, 195.37]], "area": 20230.496249999997, "iscrowd": 0, "image_id": 175142, "bbox": [0.75, 193.13, 359.25, 136.5], "category_id": 15, "id": 577560, "split": "val", "sentences": [{"tokens": ["the", "bench", "that", "the", "gentleman", "wearing", "a", "light", "blue", "hat", "is", "sitting", "on"], "raw": "The bench that the gentleman wearing a light blue hat is sitting on.", "sent_id": 58771, "sent": "the bench that the gentleman wearing a light blue hat is sitting on"}], "file_name": "COCO_train2014_000000175142_577560.jpg", "ann_id": 577560, "sent_ids": [58771], "ref_id": 27574}, {"segmentation": [[332.63, 112.56, 384.85, 111.16, 450.98, 80.88, 499.8, 79.03, 500.42, 70.38, 398.45, 49.37, 334.18, 41.33, 281.65, 43.8, 241.48, 68.52, 284.74, 69.14, 311.93, 80.26, 331.09, 95.71]], "area": 9483.706400000003, "iscrowd": 0, "image_id": 183435, "bbox": [241.48, 41.33, 258.94, 71.23], "category_id": 56, "id": 1915118, "split": "val", "sentences": [{"tokens": ["the", "bag", "of", "vegetables", "behind", "all", "of", "the", "other", "fruits", "and", "vegetables"], "raw": "The bag of vegetables behind all of the other fruits and vegetables.", "sent_id": 58827, "sent": "the bag of vegetables behind all of the other fruits and vegetables"}, {"tokens": ["the", "farthest", "away", "greens"], "raw": "The farthest away greens", "sent_id": 58828, "sent": "the farthest away greens"}], "file_name": "COCO_train2014_000000183435_1915118.jpg", "ann_id": 1915118, "sent_ids": [58827, 58828], "ref_id": 27597}, {"segmentation": [[139.78, 180.51, 148.55, 176.12, 144.16, 160.77, 155.13, 168.45, 161.71, 160.77, 171.58, 170.64, 171.58, 207.93, 162.81, 215.61, 151.84, 209.03, 144.16, 181.61], [131.0, 223.85, 122.23, 303.91, 93.71, 364.23, 67.39, 394.94, 57.52, 407.0, 57.52, 453.07, 61.91, 523.26, 66.29, 581.38, 60.81, 628.14, 86.04, 632.52, 81.65, 591.94, 86.04, 537.11, 98.1, 520.66, 99.2, 566.72, 94.81, 636.91, 114.55, 640.0, 113.45, 483.37, 128.81, 447.17, 129.91, 536.01, 139.78, 622.65, 147.45, 636.91, 162.81, 638.01, 154.03, 613.88, 144.16, 540.4, 151.84, 468.01, 140.87, 419.76, 148.55, 381.37, 139.78, 372.6, 148.55, 337.5, 144.16, 268.41, 132.1, 235.51]], "area": 22702.670049999997, "iscrowd": 0, "image_id": 96586, "bbox": [57.52, 160.77, 114.06, 479.23], "category_id": 25, "id": 1823544, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "to", "the", "left", "of", "two", "other", "giraffes"], "raw": "A giraffe to the left of two other giraffes.", "sent_id": 58833, "sent": "a giraffe to the left of two other giraffes"}, {"tokens": ["the", "darkest", "giraffe", "on", "the", "far", "left"], "raw": "The darkest giraffe on the far left.", "sent_id": 58834, "sent": "the darkest giraffe on the far left"}], "file_name": "COCO_train2014_000000096586_1823544.jpg", "ann_id": 1823544, "sent_ids": [58833, 58834], "ref_id": 27599}, {"segmentation": [[233.2, 459.75, 174.53, 378.96, 139.91, 351.07, 107.21, 352.03, 101.44, 391.46, 121.64, 426.09, 194.73, 487.64, 233.2, 468.4]], "area": 9157.916449999999, "iscrowd": 0, "image_id": 142431, "bbox": [101.44, 351.07, 131.76, 136.57], "category_id": 75, "id": 2227554, "split": "val", "sentences": [{"tokens": ["keyboard", "for", "xbox", "controller"], "raw": "keyboard for xbox controller", "sent_id": 58969, "sent": "keyboard for xbox controller"}, {"tokens": ["a", "small", "keyboard", "peripheral", "for", "an", "xbox", "360", "controller"], "raw": "A small keyboard peripheral for an Xbox 360 controller.", "sent_id": 58970, "sent": "a small keyboard peripheral for an xbox 360 controller"}], "file_name": "COCO_train2014_000000142431_2227554.jpg", "ann_id": 2227554, "sent_ids": [58969, 58970], "ref_id": 27650}, {"segmentation": [[97.36, 474.91, 60.0, 472.64, 1.13, 442.08, 0.0, 378.68, 187.92, 322.08, 198.11, 350.38, 180.0, 369.62, 177.74, 384.34, 195.85, 390.0, 216.23, 383.21, 238.87, 374.15, 258.11, 363.96, 262.64, 359.43, 259.25, 350.38, 250.19, 348.11, 263.77, 336.79, 269.43, 327.74, 266.04, 314.15, 266.04, 306.23, 275.09, 311.89, 284.15, 314.15, 303.4, 308.49, 314.72, 306.23, 321.51, 298.3, 327.17, 293.77, 332.83, 286.98, 336.23, 281.32, 337.36, 283.58, 345.28, 292.64, 348.68, 297.17, 335.09, 310.75, 331.7, 322.08, 339.62, 333.4, 358.87, 330.0, 367.92, 327.74, 371.32, 326.6, 376.98, 326.6, 375.85, 323.21, 383.77, 339.06, 403.02, 351.51, 408.68, 342.45, 406.42, 320.94, 407.55, 315.28, 422.26, 305.09, 422.26, 301.7, 421.13, 288.11, 410.94, 280.19, 400.75, 279.06, 414.34, 274.53, 433.58, 280.19, 452.83, 284.72, 537.74, 296.04, 537.74, 306.23, 218.49, 474.91]], "area": 49213.97310000002, "iscrowd": 0, "image_id": 356916, "bbox": [0.0, 274.53, 537.74, 200.38], "category_id": 67, "id": 123497, "split": "val", "sentences": [{"tokens": ["table", "with", "flowers", "on", "it"], "raw": "table with flowers on it", "sent_id": 59068, "sent": "table with flowers on it"}, {"tokens": ["the", "white", "table", "the", "man", "is", "standing", "next", "to"], "raw": "The white table the man is standing next to", "sent_id": 59069, "sent": "the white table the man is standing next to"}], "file_name": "COCO_train2014_000000356916_123497.jpg", "ann_id": 123497, "sent_ids": [59068, 59069], "ref_id": 27681}, {"segmentation": [[1.07, 30.49, 6.95, 13.91, 4.81, 0.53, 84.5, 0.53, 84.5, 6.95, 105.36, 25.14, 157.78, 47.6, 157.24, 234.79, 1.07, 234.79, 0.0, 33.69]], "area": 34454.1651, "iscrowd": 0, "image_id": 205223, "bbox": [0.0, 0.53, 157.78, 234.26], "category_id": 1, "id": 466217, "split": "val", "sentences": [{"tokens": ["black", "tie", "with", "a", "white", "floral", "pinned", "to", "his", "suit"], "raw": "Black tie with a white floral pinned to his suit.", "sent_id": 59152, "sent": "black tie with a white floral pinned to his suit"}, {"tokens": ["tux", "on", "the", "left", "with", "the", "white", "flower"], "raw": "Tux on the left with the white flower.", "sent_id": 59153, "sent": "tux on the left with the white flower"}], "file_name": "COCO_train2014_000000205223_466217.jpg", "ann_id": 466217, "sent_ids": [59152, 59153], "ref_id": 27718}, {"segmentation": [[277.72, 242.03, 292.18, 253.59, 301.42, 272.09, 320.5, 299.83, 324.55, 314.28, 312.41, 324.11, 319.34, 337.41, 313.56, 336.83, 306.05, 337.41, 296.8, 343.19, 289.29, 342.03, 272.52, 333.36, 252.29, 331.63, 235.53, 335.09, 221.08, 341.45, 211.25, 327.58, 200.27, 281.91, 201.42, 265.73, 212.98, 249.54, 207.78, 236.25, 211.25, 211.97, 221.08, 197.52, 235.53, 183.07, 248.24, 182.49, 269.05, 195.21, 279.46, 211.97, 281.19, 228.74, 275.99, 237.98, 279.46, 243.19]], "area": 13048.242, "iscrowd": 0, "image_id": 220037, "bbox": [200.27, 182.49, 124.28, 160.7], "category_id": 1, "id": 507650, "split": "val", "sentences": [{"tokens": ["seated", "woman", "in", "glasses"], "raw": "Seated woman in glasses.", "sent_id": 59172, "sent": "seated woman in glasses"}, {"tokens": ["a", "woman", "with", "a", "black", "and", "white", "blouse", "and", "glasses", "sitting", "at", "a", "table"], "raw": "A woman with a black and white blouse and glasses sitting at a table.", "sent_id": 59173, "sent": "a woman with a black and white blouse and glasses sitting at a table"}], "file_name": "COCO_train2014_000000220037_507650.jpg", "ann_id": 507650, "sent_ids": [59172, 59173], "ref_id": 27726}, {"segmentation": [[85.48, 294.79, 52.6, 300.27, 48.22, 287.12, 56.99, 261.92, 98.63, 270.68, 92.05, 256.44, 89.86, 241.1, 89.86, 196.16, 111.78, 183.01, 106.3, 141.37, 104.11, 112.88, 110.68, 98.63, 128.22, 65.75, 157.81, 62.47, 183.01, 69.04, 201.64, 88.77, 209.32, 111.78, 210.41, 131.51, 207.12, 163.29, 247.67, 169.86, 270.68, 226.85, 270.68, 246.58, 279.45, 284.93, 246.58, 290.41, 230.14, 291.51, 215.89, 277.26, 212.6, 229.04, 161.1, 234.52, 162.19, 273.97, 164.38, 287.12, 117.26, 287.12]], "area": 28581.010499999997, "iscrowd": 0, "image_id": 159768, "bbox": [48.22, 62.47, 231.23, 237.8], "category_id": 1, "id": 457418, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "red", "dress"], "raw": "A woman in a red dress.", "sent_id": 59201, "sent": "a woman in a red dress"}, {"tokens": ["a", "women", "wearing", "red", "colour", "dress"], "raw": "a women wearing red colour dress", "sent_id": 59202, "sent": "a women wearing red colour dress"}], "file_name": "COCO_train2014_000000159768_457418.jpg", "ann_id": 457418, "sent_ids": [59201, 59202], "ref_id": 27737}, {"segmentation": [[423.91, 326.83, 473.53, 325.75, 523.15, 330.07, 627.78, 348.4, 636.4, 360.27, 638.56, 468.13, 638.56, 478.92, 504.81, 475.69, 121.89, 475.69, 93.84, 477.84, 85.21, 478.92, 84.13, 463.82, 116.49, 431.46, 161.8, 410.97, 193.08, 404.49, 208.18, 406.65, 223.28, 386.16, 291.24, 378.61, 333.3, 366.74, 322.52, 351.64, 321.44, 334.38, 321.44, 331.15, 332.22, 324.67, 373.21, 323.6, 426.07, 323.6]], "area": 63019.14394999999, "iscrowd": 0, "image_id": 516106, "bbox": [84.13, 323.6, 554.43, 155.32], "category_id": 67, "id": 392778, "split": "val", "sentences": [{"tokens": ["bowl", "on", "soup", "on", "a", "brown", "table", "and", "black", "lunch", "tray"], "raw": "Bowl on soup on a brown table and black lunch tray", "sent_id": 59207, "sent": "bowl on soup on a brown table and black lunch tray"}], "file_name": "COCO_train2014_000000516106_392778.jpg", "ann_id": 392778, "sent_ids": [59207], "ref_id": 27740}, {"segmentation": [[312.17, 183.72, 336.69, 170.87, 333.19, 160.36, 325.6, 155.69, 318.59, 133.5, 317.43, 115.98, 327.94, 89.71, 341.37, 80.95, 369.98, 87.37, 384.57, 118.9, 399.17, 134.08, 407.93, 163.28, 403.26, 177.88, 433.04, 198.31, 448.8, 225.17, 469.24, 266.05, 430.12, 289.4, 418.44, 293.49, 427.78, 323.27, 430.7, 341.95, 427.78, 413.19, 419.61, 425.45, 417.86, 425.45, 309.29, 426.11, 312.29, 359.41, 337.77, 363.16, 374.49, 327.18, 363.25, 322.69, 360.25, 312.95, 366.25, 297.21, 367.0, 286.72, 346.76, 281.47, 325.78, 283.72, 310.04, 299.46, 305.54, 306.95, 310.04, 315.19, 301.8, 313.7, 300.3, 326.44, 297.3, 316.69, 300.3, 302.45, 310.79, 283.72, 317.53, 267.23, 307.04, 241.0, 314.54, 226.02, 305.54, 195.29]], "area": 33517.069399999986, "iscrowd": 0, "image_id": 435029, "bbox": [297.3, 80.95, 171.94, 345.16], "category_id": 1, "id": 475453, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "green", "shirt", "is", "holding", "a", "frisbee"], "raw": "A woman in a green shirt is holding a frisbee", "sent_id": 59227, "sent": "a woman in a green shirt is holding a frisbee"}, {"tokens": ["a", "woman", "in", "a", "green", "t", "-", "shirt", "holding", "a", "white", "frisbee"], "raw": "A woman in a green t-shirt holding a white frisbee.", "sent_id": 59228, "sent": "a woman in a green t - shirt holding a white frisbee"}], "file_name": "COCO_train2014_000000435029_475453.jpg", "ann_id": 475453, "sent_ids": [59227, 59228], "ref_id": 27749}, {"segmentation": [[186.48, 430.84, 201.49, 405.12, 167.19, 335.46, 171.48, 325.81, 155.4, 324.74, 158.62, 315.09, 175.77, 297.95, 158.62, 260.43, 154.33, 237.93, 137.18, 233.64, 152.19, 193.99, 130.75, 136.11, 146.83, 87.88, 173.62, 77.17, 231.5, 103.96, 252.93, 159.69, 256.15, 168.26, 287.23, 203.63, 304.38, 239.0, 333.31, 294.73, 334.39, 336.53, 310.81, 370.83, 279.73, 334.39, 222.92, 346.17, 260.43, 396.55, 264.72, 409.41, 230.43, 447.99, 197.2, 459.78, 171.48, 447.99, 184.34, 427.63], [322.6, 386.9, 334.39, 405.12, 303.3, 413.7, 304.38, 429.77, 339.74, 442.63, 374.04, 446.92, 386.9, 428.7, 355.82, 347.25, 336.53, 378.33, 318.31, 389.04]], "area": 46142.2304, "iscrowd": 0, "image_id": 151729, "bbox": [130.75, 77.17, 256.15, 382.61], "category_id": 1, "id": 427795, "split": "val", "sentences": [{"tokens": ["the", "nonblurry", "kid"], "raw": "the nonblurry kid", "sent_id": 59259, "sent": "the nonblurry kid"}, {"tokens": ["a", "little", "girl", "in", "polka", "dotted", "pants", "avoiding", "another", "child"], "raw": "A little girl in polka dotted pants avoiding another child.", "sent_id": 59260, "sent": "a little girl in polka dotted pants avoiding another child"}], "file_name": "COCO_train2014_000000151729_427795.jpg", "ann_id": 427795, "sent_ids": [59259, 59260], "ref_id": 27760}, {"segmentation": [[494.61, 158.7, 487.59, 144.03, 484.41, 130.01, 486.96, 113.43, 515.65, 0.58, 640.0, 0.58, 640.0, 41.38, 556.45, 176.55, 537.33, 176.55, 525.85, 172.09, 511.82, 165.07, 496.52, 160.61]], "area": 19122.749250000004, "iscrowd": 0, "image_id": 522741, "bbox": [484.41, 0.58, 155.59, 175.97], "category_id": 47, "id": 2099097, "split": "val", "sentences": [{"tokens": ["tall", "glass", "of", "lemondae"], "raw": "Tall glass of lemondae.", "sent_id": 59271, "sent": "tall glass of lemondae"}, {"tokens": ["a", "tall", "glass", "of", "lemonade", "with", "condensation", "on", "the", "outside"], "raw": "A tall glass of lemonade with condensation on the outside.", "sent_id": 59272, "sent": "a tall glass of lemonade with condensation on the outside"}], "file_name": "COCO_train2014_000000522741_2099097.jpg", "ann_id": 2099097, "sent_ids": [59271, 59272], "ref_id": 27764}, {"segmentation": [[407.33, 309.11, 405.66, 303.28, 403.99, 295.79, 415.66, 270.8, 432.31, 262.47, 436.48, 259.97, 450.64, 255.8, 467.3, 252.47, 480.63, 252.47, 510.61, 249.97, 524.78, 248.31, 539.77, 246.64, 549.76, 240.81, 536.44, 235.81, 527.27, 221.65, 533.1, 213.32, 547.27, 215.82, 548.1, 216.65, 558.09, 227.48, 565.59, 224.98, 585.58, 218.32, 597.24, 204.99, 603.07, 202.49, 606.41, 218.32, 599.74, 224.98, 594.75, 234.98, 591.41, 239.98, 591.41, 240.81, 591.41, 249.14, 589.75, 260.8, 591.41, 264.97, 578.92, 294.12, 552.26, 295.79, 408.99, 315.78, 409.82, 309.11, 409.82, 309.11]], "area": 10880.158699999994, "iscrowd": 0, "image_id": 389154, "bbox": [403.99, 202.49, 202.42, 113.29], "category_id": 20, "id": 61829, "split": "val", "sentences": [{"tokens": ["a", "young", "lamb", "resting", "in", "the", "grass", "next", "to", "an", "older", "sheep"], "raw": "A young lamb resting in the grass next to an older sheep.", "sent_id": 59279, "sent": "a young lamb resting in the grass next to an older sheep"}], "file_name": "COCO_train2014_000000389154_61829.jpg", "ann_id": 61829, "sent_ids": [59279], "ref_id": 27767}, {"segmentation": [[169.35, 200.45, 186.61, 195.06, 186.61, 172.4, 198.47, 149.75, 216.81, 124.94, 236.22, 122.79, 249.17, 128.18, 252.4, 140.04, 256.72, 147.6, 269.66, 151.91, 276.13, 171.33, 278.29, 187.51, 266.43, 203.69, 275.06, 228.49, 264.27, 251.15, 257.8, 265.17, 258.88, 279.19, 230.83, 288.9, 181.21, 296.45, 165.03, 292.13, 168.27, 258.7]], "area": 14232.985749999998, "iscrowd": 0, "image_id": 71229, "bbox": [165.03, 122.79, 113.26, 173.66], "category_id": 1, "id": 1235740, "split": "val", "sentences": [{"tokens": ["a", "woman", "'", "s", "reflection", "in", "the", "mirror"], "raw": "A woman's reflection in the mirror.", "sent_id": 59389, "sent": "a woman ' s reflection in the mirror"}, {"tokens": ["the", "reflection", "of", "the", "red", "haired", "girl", "combing", "her", "hair"], "raw": "The reflection of the red haired girl combing her hair.", "sent_id": 59390, "sent": "the reflection of the red haired girl combing her hair"}], "file_name": "COCO_train2014_000000071229_1235740.jpg", "ann_id": 1235740, "sent_ids": [59389, 59390], "ref_id": 27807}, {"segmentation": [[522.0, 349.67, 524.0, 332.67, 517.0, 308.67, 515.0, 273.67, 516.0, 251.67, 507.0, 254.67, 508.0, 230.67, 515.0, 210.67, 531.0, 202.67, 519.0, 186.67, 530.0, 178.67, 543.0, 178.67, 550.0, 204.67, 576.0, 220.67, 574.0, 254.67, 566.0, 268.67, 574.0, 306.67, 572.0, 343.67, 586.0, 376.67, 562.0, 380.67, 542.0, 314.67, 532.0, 383.67, 521.0, 374.67, 520.0, 356.67]], "area": 9438.000000000002, "iscrowd": 0, "image_id": 525180, "bbox": [507.0, 178.67, 79.0, 205.0], "category_id": 1, "id": 525780, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "apron", "and", "a", "grey", "shirt", "standing", "up", ",", "with", "his", "body", "facing", "the", "door"], "raw": "A man wearing a black apron and a grey shirt standing up, with his body facing the door.", "sent_id": 59391, "sent": "a man wearing a black apron and a grey shirt standing up , with his body facing the door"}, {"tokens": ["black", "man", "in", "restaurant", "kitchen", "with", "his", "back", "turned", ",", "wearing", "grey", "shirt", "and", "black", "pants"], "raw": "Black man in restaurant kitchen with his back turned, wearing grey shirt and black pants.", "sent_id": 59392, "sent": "black man in restaurant kitchen with his back turned , wearing grey shirt and black pants"}], "file_name": "COCO_train2014_000000525180_525780.jpg", "ann_id": 525780, "sent_ids": [59391, 59392], "ref_id": 27808}, {"segmentation": [[171.2, 53.91, 177.7, 66.91, 182.03, 74.49, 189.62, 80.99, 184.2, 84.24, 179.86, 90.74, 177.7, 107.0, 172.28, 121.08, 171.2, 143.84, 171.2, 150.34, 151.69, 156.84, 150.61, 169.84, 147.36, 172.01, 147.36, 181.76, 156.03, 198.01, 163.61, 196.93, 171.2, 178.51, 176.61, 176.34, 177.7, 177.43, 178.78, 183.93, 189.62, 205.6, 189.62, 215.35, 192.87, 232.69, 196.12, 242.44, 204.79, 265.19, 215.62, 285.78, 225.37, 291.2, 225.37, 307.45, 217.79, 311.78, 203.7, 319.37, 198.28, 329.12, 215.62, 334.54, 230.79, 334.54, 227.54, 335.62, 204.79, 354.04, 198.28, 357.29, 199.37, 368.13, 210.2, 370.29, 275.21, 360.54, 275.21, 344.29, 268.71, 317.2, 250.29, 290.11, 239.46, 263.02, 237.29, 225.1, 241.63, 215.35, 253.54, 214.27, 263.3, 203.43, 263.3, 186.09, 263.3, 181.76, 274.13, 144.92, 255.71, 112.42, 243.79, 84.24, 221.04, 63.66, 214.54, 50.65, 204.79, 37.65, 193.95, 20.32, 182.03, 19.23, 172.28, 25.73, 169.03, 31.15, 166.86, 40.9]], "area": 21753.648099999995, "iscrowd": 0, "image_id": 430555, "bbox": [147.36, 19.23, 127.85, 351.06], "category_id": 1, "id": 459433, "split": "val", "sentences": [{"tokens": ["a", "man", "dressed", "in", "blue", "on", "his", "skis", "helping", "his", "daughter", "learned", "to", "ski"], "raw": "A man dressed in blue on his skis helping his daughter learned to ski.", "sent_id": 59399, "sent": "a man dressed in blue on his skis helping his daughter learned to ski"}, {"tokens": ["the", "man", "in", "a", "blue", "jacket"], "raw": "The man in a blue jacket.", "sent_id": 59400, "sent": "the man in a blue jacket"}], "file_name": "COCO_train2014_000000430555_459433.jpg", "ann_id": 459433, "sent_ids": [59399, 59400], "ref_id": 27812}, {"segmentation": [[261.17, 632.35, 302.78, 577.82, 341.52, 541.94, 377.4, 531.9, 417.58, 513.24, 434.8, 506.07, 443.41, 497.46, 463.5, 487.41, 470.67, 474.5, 476.41, 470.19, 477.85, 632.35, 269.78, 633.78], [477.85, 312.35, 453.45, 270.73, 463.5, 247.77, 460.63, 227.68, 449.15, 194.68, 452.02, 147.32, 476.41, 118.62, 474.98, 306.61]], "area": 23397.276800000007, "iscrowd": 0, "image_id": 237976, "bbox": [261.17, 118.62, 216.68, 515.16], "category_id": 1, "id": 1260357, "split": "val", "sentences": [{"tokens": ["a", "girl", "with", "the", "camera", "on", "her", "hand", "to", "take", "selfie"], "raw": "a girl with the camera on her hand to take selfie", "sent_id": 59580, "sent": "a girl with the camera on her hand to take selfie"}, {"tokens": ["girl", "getting", "ready", "to", "take", "a", "shelfi", "in", "the", "bathroom"], "raw": "GIRL GETTING READY TO TAKE A SHELFI IN THE BATHROOM", "sent_id": 59581, "sent": "girl getting ready to take a shelfi in the bathroom"}], "file_name": "COCO_train2014_000000237976_1260357.jpg", "ann_id": 1260357, "sent_ids": [59580, 59581], "ref_id": 27873}, {"segmentation": [[304.0, 125.64, 372.42, 17.95, 364.57, 1.12, 98.72, 0.0, 62.82, 39.26, 69.55, 57.21, 234.45, 114.42]], "area": 26807.3727, "iscrowd": 0, "image_id": 178763, "bbox": [62.82, 0.0, 309.6, 125.64], "category_id": 51, "id": 2109782, "split": "val", "sentences": [{"tokens": ["a", "lunch", "tray", "that", "holds", "a", "smaller", "pink", "container"], "raw": "A lunch tray that holds a smaller pink container.", "sent_id": 59589, "sent": "a lunch tray that holds a smaller pink container"}, {"tokens": ["a", "container", "of", "food", "that", "has", "a", "smaller", "container", "with", "an", "orange", "lid", "in", "it"], "raw": "A container of food that has a smaller container with an orange lid in it.", "sent_id": 59590, "sent": "a container of food that has a smaller container with an orange lid in it"}], "file_name": "COCO_train2014_000000178763_2109782.jpg", "ann_id": 2109782, "sent_ids": [59589, 59590], "ref_id": 27877}, {"segmentation": [[376.6, 154.06, 432.76, 161.72, 460.83, 164.27, 476.15, 173.63, 463.39, 160.02, 454.88, 141.3, 445.52, 131.94, 429.35, 119.18, 391.07, 64.73, 410.64, 39.2, 449.77, 17.93, 469.34, 28.99, 514.44, 57.92, 548.47, 134.49, 559.53, 157.47, 560.38, 188.1, 561.23, 212.77, 564.63, 225.53, 547.62, 262.97, 516.14, 271.48, 480.4, 273.18, 462.54, 280.84, 483.81, 310.61, 478.7, 332.74, 471.04, 347.2, 444.67, 357.41, 418.29, 364.22, 415.74, 344.65, 428.5, 323.38, 429.35, 319.12, 408.08, 277.43, 437.01, 271.48, 450.62, 259.57, 457.43, 241.7, 458.28, 217.87]], "area": 32165.420550000003, "iscrowd": 0, "image_id": 364169, "bbox": [376.6, 17.93, 188.03, 346.29], "category_id": 1, "id": 489711, "split": "val", "sentences": [{"tokens": ["little", "girl", "on", "a", "bench", "playing", "on", "her", "laptop"], "raw": "Little girl on a bench playing on her laptop", "sent_id": 59626, "sent": "little girl on a bench playing on her laptop"}, {"tokens": ["young", "girl", "wearing", "a", "black", "vest", "sitting", "on", "a", "wooden", "box", "typing", "on", "a", "green", "laptop"], "raw": "Young girl wearing a black vest sitting on a wooden box typing on a green laptop", "sent_id": 59627, "sent": "young girl wearing a black vest sitting on a wooden box typing on a green laptop"}], "file_name": "COCO_train2014_000000364169_489711.jpg", "ann_id": 489711, "sent_ids": [59626, 59627], "ref_id": 27889}, {"segmentation": [[258.38, 267.57, 269.19, 278.38, 276.76, 295.68, 278.92, 304.32, 281.08, 308.65, 284.32, 309.73, 294.05, 315.14, 303.78, 315.14, 307.03, 312.97, 301.62, 296.76, 302.7, 275.14, 307.03, 256.76, 322.16, 214.59, 318.92, 190.81, 314.59, 177.84, 297.3, 161.62, 284.32, 155.14, 273.51, 146.49, 261.62, 146.49, 242.16, 148.65, 222.7, 152.97, 215.14, 156.22, 197.84, 146.49, 182.7, 151.89, 179.46, 167.03, 176.22, 178.92, 175.14, 184.32, 175.14, 194.05, 187.03, 211.35, 202.16, 221.08, 210.81, 224.32, 211.89, 227.57, 220.54, 248.11, 222.7, 269.73, 222.7, 276.22, 232.43, 274.05, 238.92, 267.57, 249.73, 263.24, 256.22, 264.32]], "area": 15054.707099999996, "iscrowd": 0, "image_id": 40433, "bbox": [175.14, 146.49, 147.02, 168.65], "category_id": 22, "id": 583334, "split": "val", "sentences": [{"tokens": ["smaller", "gray", "elephant", "in", "sunlight"], "raw": "Smaller gray elephant in sunlight.", "sent_id": 59628, "sent": "smaller gray elephant in sunlight"}, {"tokens": ["an", "elephant", "out", "from", "under", "the", "shade", "with", "two", "short", "husks", "showing"], "raw": "An elephant out from under the shade with two short husks showing.", "sent_id": 59629, "sent": "an elephant out from under the shade with two short husks showing"}], "file_name": "COCO_train2014_000000040433_583334.jpg", "ann_id": 583334, "sent_ids": [59628, 59629], "ref_id": 27890}, {"segmentation": [[400.09, 147.98, 401.99, 160.01, 404.52, 169.5, 410.22, 176.47, 403.26, 180.9, 396.29, 179.0, 395.03, 172.03, 395.03, 169.5, 391.86, 155.57], [389.33, 136.58, 398.19, 128.35, 393.13, 96.7, 393.76, 88.47, 400.72, 72.64, 400.72, 52.38, 394.39, 29.59, 390.59, 24.53, 380.46, 22.0, 380.46, 17.57, 383.0, 14.4, 383.63, 0.0, 358.31, 0.0, 359.57, 3.01, 342.48, 13.77, 331.09, 22.63, 336.15, 30.86, 345.65, 34.66, 350.71, 39.72, 356.41, 53.65, 355.77, 77.07, 355.14, 84.67, 352.61, 106.2, 351.34, 125.19, 348.18, 145.45, 352.61, 176.47, 356.41, 171.4, 358.31, 167.6, 360.21, 153.68, 364.0, 143.55, 365.27, 135.32, 367.8, 125.82, 371.6, 126.45, 381.73, 126.45, 388.06, 138.48]], "area": 6448.8368500000015, "iscrowd": 0, "image_id": 524966, "bbox": [331.09, 0.0, 79.13, 180.9], "category_id": 1, "id": 549087, "split": "val", "sentences": [{"tokens": ["a", "youth", "male", "soccer", "player", "with", "a", "black", "and", "white", "uniform", "and", "blue", "cleats", "on"], "raw": "A youth male soccer player with a black and white uniform and blue cleats on.", "sent_id": 59834, "sent": "a youth male soccer player with a black and white uniform and blue cleats on"}, {"tokens": ["a", "soccer", "player", "with", "the", "sun", "in", "his", "eyes"], "raw": "a soccer player with the sun in his eyes", "sent_id": 59835, "sent": "a soccer player with the sun in his eyes"}], "file_name": "COCO_train2014_000000524966_549087.jpg", "ann_id": 549087, "sent_ids": [59834, 59835], "ref_id": 27976}, {"segmentation": [[209.22, 367.56, 216.97, 377.89, 216.97, 388.22, 224.72, 394.68, 232.47, 405.01, 245.38, 410.17, 258.3, 406.3, 269.92, 411.47, 280.25, 446.34, 286.71, 461.83, 276.38, 508.33, 263.46, 516.08, 242.8, 510.91, 237.63, 500.58, 231.17, 513.49, 229.88, 554.82, 228.59, 561.28, 160.14, 554.82, 160.14, 490.25, 152.39, 487.66, 148.52, 481.21, 148.52, 467.0, 153.69, 460.54, 160.14, 460.54, 160.14, 437.3, 157.56, 436.0, 152.39, 433.42, 144.65, 429.55, 144.65, 420.51, 164.02, 421.8, 183.39, 417.92, 187.26, 412.76, 171.77, 397.26, 170.48, 386.93, 176.93, 376.6, 188.56, 364.97]], "area": 17611.85165, "iscrowd": 0, "image_id": 458751, "bbox": [144.65, 364.97, 142.06, 196.31], "category_id": 11, "id": 417845, "split": "val", "sentences": [{"tokens": ["a", "red", "and", "gray", "fire", "hydrant", "filtered", "in", "a", "coloring", "book", "style"], "raw": "A red and gray fire hydrant filtered in a coloring book style", "sent_id": 59868, "sent": "a red and gray fire hydrant filtered in a coloring book style"}, {"tokens": ["a", "person", "standing", "on", "a", "red", "fire", "hydrent"], "raw": "A person standing on a red fire hydrent.", "sent_id": 59869, "sent": "a person standing on a red fire hydrent"}], "file_name": "COCO_train2014_000000458751_417845.jpg", "ann_id": 417845, "sent_ids": [59868, 59869], "ref_id": 27993}, {"segmentation": [[291.89, 381.08, 341.62, 398.38, 385.95, 404.86, 438.92, 399.46, 484.32, 374.59, 499.46, 364.86, 516.76, 358.38, 563.24, 321.62, 579.46, 285.95, 584.86, 247.03, 572.97, 200.54, 568.65, 188.65, 565.41, 163.78, 551.35, 145.41, 541.62, 138.92, 529.73, 133.51, 522.16, 131.35, 516.76, 124.86, 503.78, 118.38, 465.95, 96.76, 459.46, 95.68, 452.97, 76.22, 440.0, 63.24, 423.78, 57.84, 405.41, 55.68, 382.7, 64.32, 374.05, 71.89, 344.86, 68.65, 323.24, 68.65, 308.11, 70.81, 290.81, 68.65, 264.86, 79.46, 254.05, 90.27, 236.76, 97.84, 217.3, 110.81, 192.43, 134.59, 180.54, 175.68, 179.46, 204.86, 188.11, 238.38, 203.24, 266.49, 205.41, 274.05, 206.49, 285.95, 217.3, 317.3, 262.7, 352.97, 298.38, 383.24]], "area": 105788.46470000007, "iscrowd": 0, "image_id": 450914, "bbox": [179.46, 55.68, 405.4, 349.18], "category_id": 51, "id": 710942, "split": "val", "sentences": [{"tokens": ["bowl", "of", "bananas", "and", "oranges"], "raw": "bowl of bananas and oranges", "sent_id": 59894, "sent": "bowl of bananas and oranges"}, {"tokens": ["bowl", "with", "many", "fruits"], "raw": "bowl with many fruits", "sent_id": 59895, "sent": "bowl with many fruits"}, {"tokens": ["a", "bowl", "of", "mixed", "fruit", "with", "oranges", ",", "bananas", "and", "apples"], "raw": "A bowl of mixed fruit with oranges, bananas and apples.", "sent_id": 59896, "sent": "a bowl of mixed fruit with oranges , bananas and apples"}], "file_name": "COCO_train2014_000000450914_710942.jpg", "ann_id": 710942, "sent_ids": [59894, 59895, 59896], "ref_id": 28004}, {"segmentation": [[21.4, 126.0, 54.18, 137.24, 62.61, 155.04, 86.96, 147.55, 102.89, 147.55, 122.56, 153.17, 135.67, 158.79, 140.35, 158.79, 154.41, 124.13, 138.48, 70.74, 132.86, 48.26, 71.04, 31.4, 38.26, 49.19, 10.16, 103.52, 8.28, 123.19, 27.95, 130.69]], "area": 12943.389249999997, "iscrowd": 0, "image_id": 533220, "bbox": [8.28, 31.4, 146.13, 127.39], "category_id": 64, "id": 1956363, "split": "val", "sentences": [{"tokens": ["a", "green", "plant", "on", "the", "left", "back", "side", "of", "a", "patio", "with", "tables"], "raw": "a green plant on the left back side of a patio with tables.", "sent_id": 60039, "sent": "a green plant on the left back side of a patio with tables"}, {"tokens": ["a", "green", "bush", "to", "the", "left", "of", "two", "other", "bushes"], "raw": "A green bush to the left of two other bushes", "sent_id": 60040, "sent": "a green bush to the left of two other bushes"}], "file_name": "COCO_train2014_000000533220_1956363.jpg", "ann_id": 1956363, "sent_ids": [60039, 60040], "ref_id": 28056}, {"segmentation": [[54.07, 314.75, 70.4, 323.94, 90.8, 323.94, 105.09, 323.94, 145.9, 307.61, 180.59, 295.37, 235.68, 275.98, 235.68, 285.17, 235.68, 294.35, 243.84, 295.37, 257.11, 280.06, 265.27, 279.04, 273.43, 279.04, 284.66, 279.04, 296.9, 279.04, 313.22, 279.04, 314.24, 268.84, 333.63, 268.84, 330.57, 263.74, 321.39, 247.42, 325.47, 239.25, 331.59, 236.19, 331.59, 247.42, 339.75, 252.52, 337.71, 260.68, 334.65, 261.7, 334.65, 266.8, 336.69, 272.92, 347.91, 265.78, 359.14, 263.74, 366.28, 259.66, 379.54, 259.66, 371.38, 265.78, 363.22, 273.94, 358.11, 285.17, 368.32, 288.23, 376.48, 290.27, 367.3, 297.41, 354.03, 299.45, 349.95, 305.57, 353.01, 310.67, 367.3, 310.67, 367.3, 310.67, 376.48, 308.63, 385.66, 311.69, 388.72, 315.77, 396.89, 317.81, 408.11, 329.04, 399.95, 341.28, 399.95, 349.44, 399.95, 355.56, 407.09, 364.75, 421.37, 364.75, 423.41, 371.89, 406.07, 371.89, 403.01, 367.81, 398.93, 374.95, 400.97, 383.11, 409.13, 385.15, 404.03, 391.27, 406.07, 397.4, 417.29, 397.4, 429.53, 403.52, 428.51, 411.68, 422.39, 419.84, 419.33, 426.98, 417.29, 428.0, 427.49, 430.04, 433.61, 418.82, 433.61, 404.54, 436.68, 379.03, 440.76, 319.85, 444.84, 293.33, 432.59, 250.48, 434.64, 230.07, 442.8, 205.58, 450.96, 167.83, 470.34, 148.45, 496.87, 143.35, 522.38, 143.35, 547.89, 146.41, 571.35, 138.25, 615.22, 124.98, 629.51, 124.98, 590.74, 108.66, 560.13, 100.5, 523.4, 94.38, 477.49, 103.56, 438.72, 109.68, 421.37, 109.68, 386.68, 109.68, 364.24, 109.68, 345.87, 112.74, 322.41, 98.46, 294.86, 100.5, 287.72, 102.54, 264.25, 96.42, 250.99, 101.52, 239.76, 113.76, 236.7, 120.9, 231.6, 141.31, 220.38, 154.57, 210.18, 168.85, 207.11, 182.12, 207.11, 197.42, 207.11, 209.67, 193.85, 227.01, 177.53, 245.37, 149.98, 263.74, 121.41, 282.1, 95.91, 290.27, 70.4, 307.61]], "area": 57374.83055, "iscrowd": 0, "image_id": 343847, "bbox": [54.07, 94.38, 575.44, 335.66], "category_id": 22, "id": 583377, "split": "val", "sentences": [{"tokens": ["an", "elephant", "reaching", "out", "its", "trunk", "in", "thick", "brush"], "raw": "an elephant reaching out its trunk in thick brush", "sent_id": 60121, "sent": "an elephant reaching out its trunk in thick brush"}, {"tokens": ["elephant", "with", "outstretched", "trunk"], "raw": "elephant with outstretched trunk", "sent_id": 60122, "sent": "elephant with outstretched trunk"}], "file_name": "COCO_train2014_000000343847_583377.jpg", "ann_id": 583377, "sent_ids": [60121, 60122], "ref_id": 28090}, {"segmentation": [[368.73, 54.14, 362.7, 81.26, 370.74, 78.25, 381.79, 73.23, 392.84, 68.2, 405.9, 67.2, 415.95, 79.25, 410.92, 99.35, 398.87, 115.42, 386.81, 134.51, 372.75, 145.57, 352.65, 166.66, 332.56, 164.65, 312.46, 167.67, 300.41, 157.62, 301.41, 144.56, 291.36, 134.51, 275.29, 130.49, 287.35, 107.39, 293.37, 102.36, 285.34, 96.33, 270.27, 88.3, 259.21, 80.26, 260.22, 73.23, 279.31, 70.21, 324.52, 77.25, 347.63, 18.97, 364.71, 19.98, 370.74, 29.02, 377.77, 29.02, 371.74, 41.08]], "area": 11727.705449999998, "iscrowd": 0, "image_id": 233746, "bbox": [259.21, 18.97, 156.74, 148.7], "category_id": 56, "id": 1055624, "split": "val", "sentences": [{"tokens": ["broccoli", "stalk", "that", "is", "pointing", "up", "and", "is", "touching", "a", "sliced", "carrot"], "raw": "broccoli stalk that is pointing up and is touching a sliced carrot", "sent_id": 60168, "sent": "broccoli stalk that is pointing up and is touching a sliced carrot"}], "file_name": "COCO_train2014_000000233746_1055624.jpg", "ann_id": 1055624, "sent_ids": [60168], "ref_id": 28106}, {"segmentation": [[321.94, 236.48, 303.76, 238.82, 293.2, 253.49, 292.02, 275.2, 299.06, 288.1, 320.18, 304.53, 353.04, 301.01, 361.25, 292.21, 380.02, 296.32, 422.26, 288.1, 436.93, 265.22, 446.9, 230.02, 455.12, 218.29, 467.44, 247.62, 455.12, 257.01, 446.9, 280.48, 456.29, 300.42, 483.28, 312.16, 510.85, 298.66, 518.48, 276.37, 513.2, 258.77, 495.6, 242.34, 480.34, 237.06, 473.3, 235.89, 456.29, 197.76, 448.08, 196.58, 460.98, 180.16, 458.64, 177.22, 445.73, 192.48, 440.45, 200.69, 427.54, 221.22, 418.74, 240.58, 412.88, 245.28, 407.01, 245.28, 394.1, 225.33, 385.3, 211.25, 365.94, 204.8, 334.26, 200.69, 316.08, 200.69, 313.73, 200.69, 307.86, 214.77, 319.6, 220.64, 321.94, 224.74, 319.6, 230.61, 309.62, 235.89, 307.86, 238.24]], "area": 15699.183350000003, "iscrowd": 0, "image_id": 562176, "bbox": [292.02, 177.22, 226.46, 134.94], "category_id": 2, "id": 126495, "split": "val", "sentences": [{"tokens": ["the", "bottom", "half", "of", "a", "man", "in", "red", "shorts", "on", "a", "bike"], "raw": "the bottom half of a man in red shorts on a bike.", "sent_id": 60397, "sent": "the bottom half of a man in red shorts on a bike"}, {"tokens": ["a", "silver", "bike", "being", "riden", "by", "a", "man", "in", "rust", "colored", "shorts"], "raw": "A silver bike being riden by a man in rust colored shorts.", "sent_id": 60398, "sent": "a silver bike being riden by a man in rust colored shorts"}], "file_name": "COCO_train2014_000000562176_126495.jpg", "ann_id": 126495, "sent_ids": [60397, 60398], "ref_id": 28189}, {"segmentation": [[266.07, 631.37, 408.45, 440.09, 451.6, 424.27, 478.92, 435.78, 480.0, 629.93, 384.0, 631.37, 385.44, 611.24, 358.11, 631.37]], "area": 27489.710450000006, "iscrowd": 0, "image_id": 28154, "bbox": [266.07, 424.27, 213.93, 207.1], "category_id": 1, "id": 1725639, "split": "val", "sentences": [{"tokens": ["the", "legs", "of", "a", "person", "sitting", "on", "the", "couch"], "raw": "The legs of a person sitting on the couch.", "sent_id": 60413, "sent": "the legs of a person sitting on the couch"}, {"tokens": ["the", "legs", "of", "the", "person", "who", "isn", "'", "t", "in", "the", "shot"], "raw": "the legs of the person who isn't in the shot.", "sent_id": 60414, "sent": "the legs of the person who isn ' t in the shot"}], "file_name": "COCO_train2014_000000028154_1725639.jpg", "ann_id": 1725639, "sent_ids": [60413, 60414], "ref_id": 28196}, {"segmentation": [[95.57, 364.43, 93.91, 353.63, 106.38, 352.79, 120.51, 351.13, 124.66, 343.65, 124.66, 329.52, 126.32, 322.04, 114.69, 294.62, 109.7, 268.85, 109.7, 245.58, 118.01, 236.44, 133.8, 233.12, 213.59, 217.33, 216.91, 201.54, 214.42, 194.06, 222.73, 192.4, 231.87, 189.9, 239.35, 184.08, 241.01, 175.77, 240.18, 169.13, 229.38, 169.96, 221.9, 175.77, 211.09, 178.27, 203.61, 177.44, 196.14, 180.76, 157.91, 192.4, 151.26, 187.41, 146.27, 186.58, 136.3, 186.58, 130.48, 194.06, 129.65, 194.89, 113.86, 196.55, 114.69, 188.24, 100.56, 175.77, 91.42, 172.45, 91.42, 165.8, 100.56, 161.65, 98.07, 159.15, 103.89, 147.52, 103.89, 133.39, 100.56, 123.42, 91.42, 115.1, 79.78, 119.26, 72.3, 120.92, 57.34, 123.42, 46.54, 126.74, 37.4, 147.52, 33.24, 153.33, 24.93, 171.62, 24.93, 181.59, 16.62, 204.03, 17.45, 229.79, 29.92, 248.08, 34.91, 269.69, 35.74, 296.28, 38.23, 328.69, 39.06, 351.13, 44.05, 360.27, 46.54, 365.26, 46.54, 365.26]], "area": 23817.61205, "iscrowd": 0, "image_id": 241392, "bbox": [16.62, 115.1, 224.39, 250.16], "category_id": 1, "id": 1723585, "split": "val", "sentences": [{"tokens": ["the", "person", "holding", "their", "hand", "out", "on", "the", "right"], "raw": "The person holding their hand out on the right", "sent_id": 60429, "sent": "the person holding their hand out on the right"}, {"tokens": ["a", "woman", "wearing", "black", "sweater"], "raw": "a woman wearing black sweater", "sent_id": 60430, "sent": "a woman wearing black sweater"}], "file_name": "COCO_train2014_000000241392_1723585.jpg", "ann_id": 1723585, "sent_ids": [60429, 60430], "ref_id": 28203}, {"segmentation": [[371.43, 350.37, 365.69, 336.97, 374.31, 328.36, 385.79, 326.44, 400.15, 323.57, 404.94, 324.53, 408.77, 324.53, 411.64, 322.61, 419.3, 308.25, 411.64, 305.38, 410.68, 300.59, 415.47, 290.06, 425.04, 280.49, 430.79, 270.92, 440.36, 262.3, 437.49, 254.64, 438.44, 247.94, 439.4, 244.11, 445.15, 237.41, 451.85, 223.05, 466.21, 220.18, 474.82, 220.18, 481.52, 226.88, 482.48, 238.37, 481.52, 246.98, 481.52, 252.73, 495.88, 256.56, 501.63, 264.22, 504.5, 289.11, 501.63, 295.81, 495.88, 295.81, 492.05, 299.64, 491.1, 321.65, 491.1, 340.8, 489.18, 347.5, 487.27, 347.5, 475.78, 338.89, 465.25, 336.01, 455.68, 336.97, 447.06, 341.76, 441.32, 350.37, 439.4, 357.07, 443.23, 372.39, 446.1, 380.05, 417.38, 377.18, 411.64, 369.52, 402.07, 368.56, 392.49, 375.26, 385.79, 374.31, 379.09, 372.39, 376.22, 362.82, 382.92, 351.33]], "area": 10674.0704, "iscrowd": 0, "image_id": 536244, "bbox": [365.69, 220.18, 138.81, 159.87], "category_id": 1, "id": 490659, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "on", "a", "road", "taking", "a", "picture"], "raw": "a man sitting on a road taking a picture", "sent_id": 60559, "sent": "a man sitting on a road taking a picture"}, {"tokens": ["a", "man", "in", "a", "white", "shirt", "with", "jeans", "taking", "a", "pic", "of", "a", "greyhound"], "raw": "a man in a white shirt with jeans taking a pic of a greyhound", "sent_id": 60560, "sent": "a man in a white shirt with jeans taking a pic of a greyhound"}], "file_name": "COCO_train2014_000000536244_490659.jpg", "ann_id": 490659, "sent_ids": [60559, 60560], "ref_id": 28251}, {"segmentation": [[257.52, 108.11, 246.64, 141.99, 241.62, 166.67, 224.06, 211.42, 230.33, 213.09, 372.53, 208.07, 381.73, 199.29, 384.24, 176.29, 377.97, 159.98, 366.68, 149.94, 359.15, 141.99, 357.06, 127.77, 358.73, 111.88, 361.66, 97.24]], "area": 13794.786500000002, "iscrowd": 0, "image_id": 428149, "bbox": [224.06, 97.24, 160.18, 115.85], "category_id": 1, "id": 1727366, "split": "val", "sentences": [{"tokens": ["arm", "holding", "cell", "phone", "to", "ear"], "raw": "arm holding cell phone to ear", "sent_id": 60603, "sent": "arm holding cell phone to ear"}, {"tokens": ["a", "bue", "shirt"], "raw": "A bue shirt.", "sent_id": 60604, "sent": "a bue shirt"}], "file_name": "COCO_train2014_000000428149_1727366.jpg", "ann_id": 1727366, "sent_ids": [60603, 60604], "ref_id": 28267}, {"segmentation": [[250.26, 162.95, 244.54, 160.09, 234.06, 160.09, 228.34, 163.9, 224.53, 167.71, 223.58, 170.57, 224.53, 178.19, 223.58, 177.24, 214.05, 192.48, 211.2, 199.15, 195.0, 207.72, 188.33, 217.25, 189.28, 231.54, 186.43, 242.97, 182.61, 256.31, 188.33, 275.37, 199.76, 295.37, 238.82, 315.38, 251.21, 313.47, 266.45, 295.37, 295.99, 277.27, 307.42, 267.74, 310.28, 255.36, 315.99, 249.64, 355.05, 283.94, 377.92, 280.13, 356.96, 253.45, 327.43, 222.97, 318.85, 218.2, 266.45, 233.45, 255.02, 238.21, 249.3, 229.64, 240.73, 210.58, 251.21, 196.29, 258.83, 185.81]], "area": 12926.978250000002, "iscrowd": 0, "image_id": 74156, "bbox": [182.61, 160.09, 195.31, 155.29], "category_id": 1, "id": 472045, "split": "val", "sentences": [{"tokens": ["the", "man", "wearing", "a", "black", "shirt", "and", "jeans"], "raw": "the man wearing a black shirt and jeans", "sent_id": 60611, "sent": "the man wearing a black shirt and jeans"}, {"tokens": ["a", "man", "sitting", "with", "blue", "jacket", "and", "blue", "jean"], "raw": "a man sitting with blue jacket and blue jean", "sent_id": 60612, "sent": "a man sitting with blue jacket and blue jean"}], "file_name": "COCO_train2014_000000074156_472045.jpg", "ann_id": 472045, "sent_ids": [60611, 60612], "ref_id": 28270}, {"segmentation": [[315.74, 493.15, 362.05, 478.67, 388.82, 477.95, 417.04, 456.24, 415.59, 441.05, 406.19, 418.62, 390.99, 389.67, 374.35, 375.2, 343.96, 376.65, 309.95, 396.19, 273.05, 430.92, 241.94, 446.84, 199.97, 472.89, 177.54, 484.46, 165.96, 484.46, 162.34, 503.28, 170.3, 530.05, 175.37, 542.35, 207.93, 545.24, 219.51, 540.18, 199.25, 521.36, 197.8, 499.66, 207.93, 494.59, 220.23, 504.0, 230.36, 509.79, 236.15, 503.28, 244.83, 496.76, 259.3, 498.93, 273.77, 504.0, 301.99, 501.1]], "area": 18765.855799999998, "iscrowd": 0, "image_id": 142431, "bbox": [162.34, 375.2, 254.7, 170.04], "category_id": 75, "id": 1973246, "split": "val", "sentences": [{"tokens": ["cracked", "clay", "in", "a", "gentleman", "'", "s", "left", "hand"], "raw": "Cracked clay in a gentleman's left hand", "sent_id": 60630, "sent": "cracked clay in a gentleman ' s left hand"}, {"tokens": ["it", "appears", "to", "be", "a", "wiimote", ",", "with", "a", "boy", "'", "s", "fingers", "holding", "it", "up", ".", "additionally", ",", "half", "of", "an", "xbox", "360", "controller"], "raw": "It appears to be a WiiMote, with a boy's fingers holding it up. Additionally, half of an xbox 360 controller.", "sent_id": 60631, "sent": "it appears to be a wiimote , with a boy ' s fingers holding it up . additionally , half of an xbox 360 controller"}], "file_name": "COCO_train2014_000000142431_1973246.jpg", "ann_id": 1973246, "sent_ids": [60630, 60631], "ref_id": 28275}, {"segmentation": [[164.44, 17.31, 170.0, 8.04, 165.05, 1.24, 275.71, 0.62, 291.78, 14.22, 317.13, 24.73, 315.89, 233.67, 160.11, 233.67, 162.58, 17.93]], "area": 35454.47194999999, "iscrowd": 0, "image_id": 205223, "bbox": [160.11, 0.62, 157.02, 233.05], "category_id": 1, "id": 2161944, "split": "val", "sentences": [{"tokens": ["the", "second", "suit"], "raw": "The second suit.", "sent_id": 60714, "sent": "the second suit"}], "file_name": "COCO_train2014_000000205223_2161944.jpg", "ann_id": 2161944, "sent_ids": [60714], "ref_id": 28309}, {"segmentation": [[124.74, 115.39, 4.8, 117.31, 10.56, 132.66, 95.96, 149.93, 76.76, 184.47, 67.17, 184.47, 71.01, 191.19, 76.76, 191.19, 59.49, 196.95, 71.01, 209.42, 103.63, 211.34, 110.35, 203.66, 158.33, 156.65, 191.91, 162.4, 190.95, 174.88, 202.47, 176.8, 212.06, 165.28, 224.53, 155.69, 247.56, 120.18, 228.37, 113.47, 227.41, 120.18, 223.58, 120.18, 215.9, 107.71, 199.59, 108.67, 180.4, 123.06, 177.52, 124.98, 185.19, 87.56, 198.63, 81.8, 150.65, 70.29, 147.77, 80.84, 152.57, 83.72, 146.81, 90.44, 140.09, 87.56, 142.01, 92.36, 142.97, 95.24, 129.54, 107.71]], "area": 13313.633649999996, "iscrowd": 0, "image_id": 171478, "bbox": [4.8, 70.29, 242.76, 141.05], "category_id": 5, "id": 162381, "split": "val", "sentences": [{"tokens": ["plane", "in", "the", "front"], "raw": "plane in the front", "sent_id": 60842, "sent": "plane in the front"}], "file_name": "COCO_train2014_000000171478_162381.jpg", "ann_id": 162381, "sent_ids": [60842], "ref_id": 28362}, {"segmentation": [[180.4, 370.39, 111.31, 322.41, 86.36, 284.03, 68.13, 238.93, 67.17, 174.64, 81.56, 113.23, 105.55, 77.72, 144.89, 45.1, 210.14, 23.03, 267.71, 36.46, 315.69, 59.49, 348.32, 88.28, 383.82, 136.26, 400.13, 188.07, 403.01, 233.17, 373.27, 308.98, 344.48, 351.2, 303.22, 369.43, 270.59, 380.94, 198.63, 377.1]], "area": 92562.51460000001, "iscrowd": 0, "image_id": 79111, "bbox": [67.17, 23.03, 335.84, 357.91], "category_id": 51, "id": 1037875, "split": "val", "sentences": [{"tokens": ["wooden", "bowls", "holding", "apples", "and", "five", "wooden", "spoons"], "raw": "Wooden bowls holding apples and five wooden spoons.", "sent_id": 60899, "sent": "wooden bowls holding apples and five wooden spoons"}, {"tokens": ["bowl", "with", "spoons", "and", "apples"], "raw": "bowl with spoons and apples", "sent_id": 60900, "sent": "bowl with spoons and apples"}], "file_name": "COCO_train2014_000000079111_1037875.jpg", "ann_id": 1037875, "sent_ids": [60899, 60900], "ref_id": 28384}, {"segmentation": [[267.58, 295.4, 267.58, 277.0, 269.06, 262.28, 274.21, 240.94, 280.83, 235.05, 294.08, 229.9, 309.54, 229.9, 327.94, 231.37, 341.19, 236.52, 364.0, 249.77, 375.04, 267.43, 375.04, 274.79, 373.57, 289.51, 372.1, 299.08, 348.55, 332.2, 347.81, 338.83, 327.94, 405.8, 320.58, 405.8, 328.67, 374.15, 328.67, 369.0, 326.47, 360.17, 322.05, 356.49, 320.58, 382.25, 313.95, 378.57, 320.58, 351.34, 280.1, 335.15, 283.04, 330.73, 283.78, 313.8, 281.57, 307.18, 274.21, 297.61]], "area": 10695.418800000003, "iscrowd": 0, "image_id": 442356, "bbox": [267.58, 229.9, 107.46, 175.9], "category_id": 62, "id": 374370, "split": "val", "sentences": [{"tokens": ["a", "chair", "containing", "white", "color", "seat"], "raw": "A CHAIR CONTAINING WHITE COLOR SEAT", "sent_id": 60923, "sent": "a chair containing white color seat"}], "file_name": "COCO_train2014_000000442356_374370.jpg", "ann_id": 374370, "sent_ids": [60923], "ref_id": 28393}, {"segmentation": [[176.24, 291.55, 188.32, 289.53, 194.37, 285.51, 205.44, 280.47, 217.53, 281.48, 246.73, 284.5, 268.89, 283.49, 290.04, 280.47, 300.11, 276.44, 328.31, 270.4, 345.43, 269.39, 352.48, 269.39, 382.69, 275.44, 397.79, 282.48, 404.84, 284.5, 410.89, 294.57, 412.9, 302.63, 396.79, 323.77, 355.5, 327.8, 330.32, 327.8, 306.15, 324.78, 286.01, 318.74, 251.77, 317.73, 230.62, 316.73, 189.33, 314.71, 174.22, 308.67, 169.19, 305.65, 169.19, 297.59]], "area": 9811.64765, "iscrowd": 0, "image_id": 199958, "bbox": [169.19, 269.39, 243.71, 58.41], "category_id": 57, "id": 1063718, "split": "val", "sentences": [{"tokens": ["carrot", "sitting", "on", "cutting", "board"], "raw": "Carrot sitting on cutting board.", "sent_id": 60948, "sent": "carrot sitting on cutting board"}, {"tokens": ["the", "carrot", "between", "the", "bottom", "carrot", "and", "the", "green", "onion"], "raw": "The carrot between the bottom carrot and the green onion", "sent_id": 60949, "sent": "the carrot between the bottom carrot and the green onion"}], "file_name": "COCO_train2014_000000199958_1063718.jpg", "ann_id": 1063718, "sent_ids": [60948, 60949], "ref_id": 28402}, {"segmentation": [[61.66, 167.37, 7.93, 241.37, 95.14, 238.72, 141.82, 244.89, 180.58, 165.61, 65.19, 166.49]], "area": 9446.699349999999, "iscrowd": 0, "image_id": 562474, "bbox": [7.93, 165.61, 172.65, 79.28], "category_id": 84, "id": 1647979, "split": "val", "sentences": [{"tokens": ["a", "book", "titled", "kakarhu"], "raw": "A book titled KAKARHU", "sent_id": 61014, "sent": "a book titled kakarhu"}, {"tokens": ["a", "story", "book", "with", "a", "bear", "on", "the", "cover", "on", "a", "table"], "raw": "A story book with a bear on the cover on a table", "sent_id": 61015, "sent": "a story book with a bear on the cover on a table"}], "file_name": "COCO_train2014_000000562474_1647979.jpg", "ann_id": 1647979, "sent_ids": [61014, 61015], "ref_id": 28427}, {"segmentation": [[581.45, 403.72, 420.51, 366.09, 376.38, 314.17, 372.49, 245.38, 462.04, 214.24, 460.74, 167.51, 503.57, 132.47, 546.4, 125.98, 608.7, 151.94, 640.0, 125.98, 639.85, 403.72]], "area": 56365.0654, "iscrowd": 0, "image_id": 197289, "bbox": [372.49, 125.98, 267.51, 277.74], "category_id": 56, "id": 1055396, "split": "val", "sentences": [{"tokens": ["green", "broccoli", "next", "to", "other", "assorted", "foods"], "raw": "Green broccoli next to other assorted foods", "sent_id": 61037, "sent": "green broccoli next to other assorted foods"}, {"tokens": ["it", "is", "the", "broccoli", "next", "to", "the", "beans", "and", "the", "slider", "with", "a", "tomato", "and", "a", "slice", "of", "the", "cheese", "on", "it"], "raw": "It is the broccoli next to the beans and the slider with a tomato and a slice of the cheese on it.", "sent_id": 61038, "sent": "it is the broccoli next to the beans and the slider with a tomato and a slice of the cheese on it"}], "file_name": "COCO_train2014_000000197289_1055396.jpg", "ann_id": 1055396, "sent_ids": [61037, 61038], "ref_id": 28437}, {"segmentation": [[229.75, 38.83, 428.22, 77.66, 576.0, 117.57, 600.81, 142.38, 606.2, 222.2, 587.87, 227.6, 588.94, 280.45, 579.24, 331.15, 555.51, 341.93, 532.85, 358.11, 505.89, 362.43, 490.79, 349.48, 267.51, 374.29, 253.48, 380.76, 213.57, 413.12, 176.9, 403.42, 169.35, 368.9, 166.11, 362.43, 131.6, 359.19, 132.67, 307.42, 131.6, 266.43, 144.54, 197.39, 170.43, 129.44, 183.37, 85.21, 203.87, 66.88]], "area": 129495.92345, "iscrowd": 0, "image_id": 412220, "bbox": [131.6, 38.83, 474.6, 374.29], "category_id": 6, "id": 163018, "split": "val", "sentences": [{"tokens": ["the", "front", "bus", "in", "the", "right", "hand", "picture"], "raw": "the front bus in the right hand picture", "sent_id": 61059, "sent": "the front bus in the right hand picture"}, {"tokens": ["fully", "visible", "double", "decker", "bus"], "raw": "fully visible double decker bus", "sent_id": 61060, "sent": "fully visible double decker bus"}, {"tokens": ["a", "red", "double", "-", "decker", "with", "a", "wrigley", "'", "s", "ad"], "raw": "A red double-decker with a Wrigley's ad.", "sent_id": 61061, "sent": "a red double - decker with a wrigley ' s ad"}], "file_name": "COCO_train2014_000000412220_163018.jpg", "ann_id": 163018, "sent_ids": [61059, 61060, 61061], "ref_id": 28446}, {"segmentation": [[11.56, 240.5, 6.7, 257.15, 3.92, 269.65, 6.0, 286.3, 13.64, 316.84, 21.97, 316.84, 38.62, 312.68, 21.27, 298.79, 18.5, 244.66, 12.25, 239.8], [193.39, 228.0, 205.19, 246.05, 201.03, 250.91, 192.7, 230.09]], "area": 1165.9567499999991, "iscrowd": 0, "image_id": 342996, "bbox": [3.92, 228.0, 201.27, 88.84], "category_id": 62, "id": 1931441, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "that", "a", "woman", "is", "sitting", "in"], "raw": "A wooden chair that a woman is sitting in.", "sent_id": 61064, "sent": "a wooden chair that a woman is sitting in"}], "file_name": "COCO_train2014_000000342996_1931441.jpg", "ann_id": 1931441, "sent_ids": [61064], "ref_id": 28448}, {"segmentation": [[332.02, 191.07, 330.92, 197.65, 336.41, 202.59, 332.02, 220.13, 321.06, 223.43, 315.02, 232.2, 315.57, 243.17, 327.64, 240.43, 341.35, 230.01, 367.12, 213.56, 381.93, 214.65, 396.19, 205.88, 409.34, 205.33, 416.47, 205.33, 416.47, 197.1, 415.92, 170.78, 418.12, 165.84, 435.12, 162.01, 444.44, 158.72, 467.48, 166.39, 486.67, 176.82, 500.38, 187.78, 506.96, 194.91, 492.15, 197.1, 498.19, 205.33, 500.38, 214.1, 502.02, 229.46, 504.77, 240.98, 531.09, 238.23, 552.48, 236.04, 579.89, 240.43, 593.6, 234.94, 592.51, 214.65, 589.76, 196.01, 580.44, 172.43, 557.96, 151.04, 532.18, 134.59, 519.02, 128.56, 491.06, 117.59, 471.31, 109.91, 458.7, 107.17, 425.25, 104.98, 418.67, 91.27, 429.64, 75.91, 427.99, 74.82, 413.19, 77.01, 412.09, 69.33, 400.02, 68.79, 396.19, 66.59, 387.41, 67.14, 383.57, 64.39, 378.09, 62.2, 366.57, 62.75, 356.7, 65.49, 341.9, 69.33, 333.12, 66.59, 328.19, 77.01, 320.51, 84.14, 319.96, 92.91, 319.96, 98.4, 311.74, 106.62, 295.83, 119.23, 291.44, 128.01, 290.89, 136.78, 298.57, 148.85, 305.7, 157.07, 318.31, 152.69, 322.15, 158.72, 327.64, 177.91, 333.12, 190.52]], "area": 28495.89385, "iscrowd": 0, "image_id": 213005, "bbox": [290.89, 62.2, 302.71, 180.97], "category_id": 20, "id": 61846, "split": "val", "sentences": [{"tokens": ["sheep", "laying", "in", "grass"], "raw": "sheep laying in grass", "sent_id": 61224, "sent": "sheep laying in grass"}, {"tokens": ["a", "mother", "sheep", "with", "three", "of", "her", "kids"], "raw": "A MOTHER SHEEP WITH THREE OF HER KIDS", "sent_id": 61225, "sent": "a mother sheep with three of her kids"}], "file_name": "COCO_train2014_000000213005_61846.jpg", "ann_id": 61846, "sent_ids": [61224, 61225], "ref_id": 28505}, {"segmentation": [[237.22, 115.99, 196.06, 63.61, 180.34, 50.14, 172.11, 26.94, 201.3, 21.7, 242.45, 21.7, 261.16, 17.96, 283.61, 26.19, 309.8, 29.18, 327.76, 29.93, 351.71, 39.66, 368.92, 51.63, 378.65, 60.61, 398.1, 71.09, 413.82, 89.05, 425.79, 110.75, 437.76, 136.94, 443.0, 155.65, 446.74, 186.33, 441.51, 214.77, 436.27, 215.51, 431.78, 242.45, 426.54, 247.69, 410.08, 265.65, 279.12, 329.26, 216.26, 327.76, 197.56, 322.52, 187.08, 318.78, 177.35, 318.03, 169.87, 308.31, 151.16, 303.07, 125.72, 288.1, 104.76, 274.63, 79.32, 240.96, 66.6, 203.54, 63.61, 183.34, 62.86, 167.62, 67.35, 163.13, 72.59, 163.13, 139.19, 151.91, 160.89, 146.67, 207.28, 134.7, 232.73, 128.71, 239.46, 124.22, 237.22, 117.49]], "area": 79038.05559999999, "iscrowd": 0, "image_id": 161031, "bbox": [62.86, 17.96, 383.88, 311.3], "category_id": 59, "id": 1073919, "split": "val", "sentences": [{"tokens": ["partially", "eaten", "pepperoni", "pizza", "in", "pizza", "box"], "raw": "Partially eaten pepperoni pizza in pizza box.", "sent_id": 61263, "sent": "partially eaten pepperoni pizza in pizza box"}, {"tokens": ["a", "pack", "of", "pizza", "quarter", "eaten"], "raw": "A pack of pizza quarter eaten.", "sent_id": 61264, "sent": "a pack of pizza quarter eaten"}], "file_name": "COCO_train2014_000000161031_1073919.jpg", "ann_id": 1073919, "sent_ids": [61263, 61264], "ref_id": 28520}, {"segmentation": [[0.0, 41.29, 30.34, 107.02, 43.82, 172.75, 41.29, 272.19, 33.71, 267.98, 109.55, 370.79, 3.37, 369.1, 1.69, 51.4]], "area": 13964.725650000002, "iscrowd": 0, "image_id": 376941, "bbox": [0.0, 41.29, 109.55, 329.5], "category_id": 1, "id": 452538, "split": "val", "sentences": [{"tokens": ["the", "arm", "of", "a", "person", "'", "s", "blue", "jacket"], "raw": "The arm of a person's blue jacket.", "sent_id": 61289, "sent": "the arm of a person ' s blue jacket"}], "file_name": "COCO_train2014_000000376941_452538.jpg", "ann_id": 452538, "sent_ids": [61289], "ref_id": 28529}, {"segmentation": [[72.79, 522.65, 71.6, 468.95, 91.88, 466.56, 116.94, 429.57, 105.01, 396.16, 109.78, 346.04, 131.26, 235.07, 159.9, 176.6, 188.53, 156.32, 239.84, 155.12, 275.64, 188.53, 304.28, 235.07, 298.31, 269.68, 293.54, 276.84, 291.16, 292.35, 281.61, 319.79, 278.03, 326.95, 297.12, 342.47, 343.66, 356.78, 365.14, 365.14, 390.2, 405.71, 410.48, 441.51, 412.87, 511.91, 361.56, 474.92, 361.56, 515.49]], "area": 78895.07365, "iscrowd": 0, "image_id": 509746, "bbox": [71.6, 155.12, 341.27, 367.53], "category_id": 1, "id": 433435, "split": "val", "sentences": [{"tokens": ["the", "little", "girl", "with", "a", "black", "dress"], "raw": "The little girl with a black dress.", "sent_id": 61296, "sent": "the little girl with a black dress"}, {"tokens": ["female", "wearing", "dress", "and", "makeup"], "raw": "Female wearing dress and makeup.", "sent_id": 61297, "sent": "female wearing dress and makeup"}], "file_name": "COCO_train2014_000000509746_433435.jpg", "ann_id": 433435, "sent_ids": [61296, 61297], "ref_id": 28533}, {"segmentation": [[105.38, 441.83, 232.06, 391.39, 235.43, 381.3, 285.87, 462.01, 293.72, 484.44, 338.57, 484.44, 349.78, 479.95, 360.99, 468.74, 369.96, 460.89, 334.08, 450.8, 328.48, 423.9, 256.73, 288.25, 242.15, 257.98, 235.43, 198.56, 237.67, 155.96, 262.33, 118.96, 248.88, 78.61, 218.61, 67.4, 224.22, 51.7, 224.22, 44.97, 221.97, 33.76, 200.67, 18.07, 176.01, 14.7, 160.31, 23.67, 151.35, 31.52, 145.74, 32.64, 128.92, 33.76, 107.62, 32.64, 103.14, 39.37, 100.9, 43.85, 102.02, 55.06, 117.71, 68.52, 131.17, 68.52, 155.83, 73.0, 131.17, 76.36, 117.71, 76.36, 106.5, 87.57, 90.81, 78.61, 86.32, 58.43, 77.35, 47.22, 53.81, 36.01, 44.84, 44.97, 43.72, 58.43, 60.54, 76.36, 59.42, 102.15, 53.81, 131.3, 75.11, 136.9, 94.17, 138.02, 106.5, 138.02, 116.59, 138.02, 124.44, 171.66, 134.53, 197.44, 136.77, 222.1, 128.92, 266.95, 149.1, 287.13, 164.8, 299.46, 174.89, 331.97, 179.37, 347.66, 181.61, 360.0, 86.32, 399.23, 50.45, 405.96, 61.66, 421.66, 75.11, 466.5, 97.53, 478.83, 104.26, 478.83, 110.99, 475.47, 110.99, 467.62, 110.99, 458.65]], "area": 60294.06449999999, "iscrowd": 0, "image_id": 363752, "bbox": [43.72, 14.7, 326.24, 469.74], "category_id": 1, "id": 453520, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "swinging", "a", "bat"], "raw": "A baseball player swinging a bat", "sent_id": 61426, "sent": "a baseball player swinging a bat"}, {"tokens": ["a", "baseball", "player", "with", "760", "next", "to", "him"], "raw": "a baseball player with 760 next to him", "sent_id": 61427, "sent": "a baseball player with 760 next to him"}], "file_name": "COCO_train2014_000000363752_453520.jpg", "ann_id": 453520, "sent_ids": [61426, 61427], "ref_id": 28585}, {"segmentation": [[254.05, 367.03, 280.0, 344.32, 289.73, 315.14, 298.38, 291.35, 295.14, 275.14, 299.46, 265.41, 294.05, 252.43, 284.32, 251.35, 282.16, 228.65, 278.92, 217.84, 263.78, 199.46, 242.16, 196.22, 225.95, 197.3, 204.32, 177.84, 183.78, 190.81, 158.92, 195.14, 141.62, 198.38, 114.59, 203.78, 101.62, 217.84, 92.97, 226.49, 78.92, 234.05, 54.05, 250.27, 54.05, 271.89, 46.49, 282.7, 40.0, 300.0, 55.14, 356.22, 65.95, 369.19, 87.57, 376.76, 113.51, 376.76, 134.05, 380.0, 171.89, 373.51, 190.27, 363.78, 216.22, 355.14, 240.0, 352.97]], "area": 38545.994399999996, "iscrowd": 0, "image_id": 9822, "bbox": [40.0, 177.84, 259.46, 202.16], "category_id": 60, "id": 1080534, "split": "val", "sentences": [{"tokens": ["the", "doughnut", "in", "the", "bottom", "left", "corner"], "raw": "The doughnut in the bottom left corner.", "sent_id": 61436, "sent": "the doughnut in the bottom left corner"}], "file_name": "COCO_train2014_000000009822_1080534.jpg", "ann_id": 1080534, "sent_ids": [61436], "ref_id": 28589}, {"segmentation": [[193.91, 592.75, 122.4, 262.68, 147.16, 247.55, 182.91, 261.3, 209.04, 314.94, 222.8, 308.06, 233.8, 320.44, 228.3, 330.07, 220.04, 334.19, 218.67, 352.07, 261.3, 530.86, 280.56, 521.23, 287.43, 532.23, 288.81, 547.36, 280.56, 556.99, 272.31, 558.36, 275.06, 569.37, 265.43, 583.12, 264.05, 590.0]], "area": 27032.91385, "iscrowd": 0, "image_id": 313873, "bbox": [122.4, 247.55, 166.41, 345.2], "category_id": 41, "id": 638357, "split": "val", "sentences": [{"tokens": ["a", "skateboard", "with", "four", "wheels", "that", "is", "mainly", "green", "in", "color"], "raw": "A skateboard with four wheels that is mainly green in color.", "sent_id": 61451, "sent": "a skateboard with four wheels that is mainly green in color"}, {"tokens": ["a", "skateboard", "with", "a", "green", "bottom"], "raw": "A skateboard with a green bottom.", "sent_id": 61452, "sent": "a skateboard with a green bottom"}], "file_name": "COCO_train2014_000000313873_638357.jpg", "ann_id": 638357, "sent_ids": [61451, 61452], "ref_id": 28594}, {"segmentation": [[383.76, 108.65, 375.97, 100.86, 357.55, 90.94, 346.92, 83.14, 334.88, 79.6, 307.96, 80.31, 305.83, 78.19, 293.08, 62.6, 287.41, 56.22, 273.24, 50.56, 231.44, 47.01, 236.4, 68.27, 242.07, 78.19, 237.82, 99.44, 226.48, 104.4, 217.98, 104.4, 208.06, 90.23, 194.6, 89.52, 183.27, 89.52, 179.02, 107.23, 186.1, 117.15, 200.27, 117.15, 208.77, 117.15, 215.15, 141.24, 210.9, 163.2, 192.48, 192.25, 166.21, 185.15, 140.5, 188.43, 119.0, 201.51, 113.39, 215.07, 88.62, 266.95, 85.81, 312.29, 102.64, 368.85, 131.15, 396.89, 154.06, 408.58, 181.63, 410.91, 202.67, 407.17, 230.71, 384.27, 242.86, 362.3, 257.82, 352.49, 264.83, 331.92, 266.23, 289.85, 260.62, 269.76, 250.81, 245.92, 251.74, 229.09, 262.03, 220.68, 282.13, 214.13, 295.21, 204.32, 305.03, 250.12, 298.02, 273.03, 303.63, 290.32, 328.4, 337.06, 352.24, 354.82, 391.97, 361.37, 421.41, 361.37, 433.57, 361.37, 442.91, 364.64, 430.76, 407.64, 425.15, 418.39, 419.08, 421.2, 424.69, 428.67, 441.98, 428.67, 436.37, 423.07, 433.57, 413.72, 439.18, 390.81, 448.52, 364.64, 453.66, 357.16, 475.17, 358.56, 489.19, 365.57, 496.2, 360.9, 504.15, 356.69, 520.5, 353.89, 540.14, 373.52, 559.77, 379.6, 590.15, 379.6, 622.87, 368.85, 640.0, 354.82, 637.82, 246.38, 640.0, 138.88, 636.42, 135.14, 621.93, 133.74, 583.14, 137.95, 551.82, 143.09, 516.3, 143.55, 456.47, 148.7, 443.85, 142.15, 428.89, 134.21, 388.7, 118.31]], "area": 125155.81535, "iscrowd": 0, "image_id": 234819, "bbox": [85.81, 47.01, 554.19, 381.66], "category_id": 4, "id": 152270, "split": "val", "sentences": [{"tokens": ["a", "motor", "bike", "parked", "amongst", "other", "motor", "bikes", "with", "its", "front", "wheel", "facing", "the", "right"], "raw": "A motor bike parked amongst other motor bikes with its front wheel facing the right.", "sent_id": 61461, "sent": "a motor bike parked amongst other motor bikes with its front wheel facing the right"}, {"tokens": ["a", "red", "honda", "motorcycle", "on", "the", "grass", "in", "front", "of", "a", "couple", "of", "motorcycles", "and", "a", "few", "cars"], "raw": "A red Honda motorcycle on the grass in front of a couple of motorcycles and a few cars.", "sent_id": 61462, "sent": "a red honda motorcycle on the grass in front of a couple of motorcycles and a few cars"}], "file_name": "COCO_train2014_000000234819_152270.jpg", "ann_id": 152270, "sent_ids": [61461, 61462], "ref_id": 28597}, {"segmentation": [[466.0, 111.77, 464.03, 120.31, 334.68, 148.54, 297.91, 171.52, 291.34, 176.12, 285.43, 201.07, 289.37, 211.57, 278.87, 211.57, 270.33, 182.68, 293.31, 160.36, 279.52, 158.39, 280.18, 136.72, 270.99, 136.07, 263.11, 130.81, 274.27, 108.49, 306.44, 105.86, 340.59, 111.12, 384.58, 107.83, 418.07, 108.49, 435.79, 111.77, 467.97, 107.83]], "area": 7118.5513, "iscrowd": 0, "image_id": 421298, "bbox": [263.11, 105.86, 204.86, 105.71], "category_id": 54, "id": 1554420, "split": "val", "sentences": [{"tokens": ["half", "of", "a", "sandwich", "in", "back", "of", "another", "half"], "raw": "Half of a sandwich in back of another half", "sent_id": 61469, "sent": "half of a sandwich in back of another half"}], "file_name": "COCO_train2014_000000421298_1554420.jpg", "ann_id": 1554420, "sent_ids": [61469], "ref_id": 28601}, {"segmentation": [[2.22, 151.76, 36.6, 146.22, 47.69, 140.67, 52.13, 140.67, 56.56, 152.87, 62.11, 157.31, 56.56, 166.18, 55.45, 169.51, 46.58, 170.62, 14.42, 182.82, 34.38, 193.91, 29.95, 206.11, 21.07, 212.76, 8.87, 210.54, 2.22, 205.0, 2.22, 205.0, 7.76, 243.82, 27.73, 292.62, 33.27, 303.71, 22.18, 388.0, 22.18, 415.72, 16.64, 417.94, 16.64, 419.05, 4.44, 420.16, 1.11, 234.94, 1.11, 172.83], [3.33, 80.78, 9.98, 69.69, 6.65, 53.05, 0.0, 46.4]], "area": 6477.210399999999, "iscrowd": 0, "image_id": 524966, "bbox": [0.0, 46.4, 62.11, 373.76], "category_id": 1, "id": 2158142, "split": "val", "sentences": [{"tokens": ["a", "man", "playing", "soccer", "in", "a", "red", "shirt"], "raw": "A man playing soccer in a red shirt", "sent_id": 61502, "sent": "a man playing soccer in a red shirt"}, {"tokens": ["partiall", "visible", "soccer", "player", "in", "red", "sleaved", "uniform"], "raw": "partiall visible soccer player in red sleaved uniform", "sent_id": 61503, "sent": "partiall visible soccer player in red sleaved uniform"}], "file_name": "COCO_train2014_000000524966_2158142.jpg", "ann_id": 2158142, "sent_ids": [61502, 61503], "ref_id": 28611}, {"segmentation": [[319.57, 31.62, 312.55, 43.46, 323.52, 42.59, 321.32, 51.36, 326.15, 57.5, 323.08, 65.84, 320.45, 96.1, 318.25, 103.56, 322.2, 112.77, 320.45, 126.8, 320.45, 128.56, 305.53, 132.94, 296.32, 132.94, 287.55, 139.96, 287.99, 139.96, 295.0, 144.79, 279.65, 152.24, 268.69, 154.0, 256.41, 164.08, 258.16, 170.23, 258.6, 173.3, 269.13, 172.27, 291.94, 162.18, 301.15, 193.76, 305.53, 186.3, 321.76, 170.07, 332.73, 141.12, 336.67, 125.33, 338.43, 118.76, 340.19, 74.45, 337.99, 40.68, 355.1, 28.4, 349.83, 18.75, 341.06, 13.49, 326.15, 17.43, 319.57, 21.82, 318.69, 31.47], [307.29, 258.11, 289.3, 314.25, 254.65, 316.01, 254.21, 319.95, 286.23, 333.99, 302.9, 332.67, 291.5, 324.34, 294.57, 312.94, 298.95, 308.55, 305.97, 308.11, 310.8, 259.86], [346.76, 248.9, 356.41, 239.25, 377.03, 311.18, 371.33, 312.06, 362.55, 281.35, 356.85, 272.58, 347.64, 249.34], [359.92, 332.24, 348.96, 338.37, 348.52, 344.08, 360.36, 346.71, 361.67, 335.3]], "area": 6285.413950000002, "iscrowd": 0, "image_id": 97936, "bbox": [254.21, 13.49, 122.82, 333.22], "category_id": 1, "id": 211171, "split": "val", "sentences": [{"tokens": ["the", "woman", "holding", "the", "buckle", "of", "a", "dog"], "raw": "The woman holding the buckle of a dog.", "sent_id": 61575, "sent": "the woman holding the buckle of a dog"}, {"tokens": ["woman", "in", "a", "grey", "bucket", "hat", "walking", "a", "dog"], "raw": "Woman in a grey bucket hat walking a dog.", "sent_id": 61576, "sent": "woman in a grey bucket hat walking a dog"}], "file_name": "COCO_train2014_000000097936_211171.jpg", "ann_id": 211171, "sent_ids": [61575, 61576], "ref_id": 28635}, {"segmentation": [[320.02, 171.11, 308.13, 170.2, 296.25, 164.71, 279.79, 162.88, 269.73, 165.63, 254.19, 174.77, 245.96, 182.09, 238.64, 194.89, 239.56, 204.94, 238.64, 213.17, 239.56, 223.23, 242.3, 236.03, 217.61, 247.92, 227.67, 246.09, 215.79, 262.55, 213.96, 275.35, 213.96, 282.66, 213.04, 288.15, 231.33, 288.15, 232.24, 288.15, 234.99, 284.49, 236.82, 277.18, 237.73, 272.61, 237.73, 274.43, 237.73, 284.49, 237.73, 291.81, 235.9, 300.04, 235.9, 306.44, 235.9, 314.67, 242.3, 324.72, 248.7, 330.21, 257.85, 330.21, 256.02, 321.07, 254.19, 315.58, 250.53, 311.01, 246.87, 314.67, 246.87, 304.61, 247.79, 294.55, 252.36, 279.01, 249.62, 299.12, 256.93, 307.35, 258.76, 311.92, 270.65, 314.67, 269.73, 311.01, 256.93, 300.04, 256.02, 291.81, 260.59, 275.35, 262.42, 258.89, 264.25, 249.75, 266.07, 245.18, 279.79, 230.55, 294.42, 229.63, 289.85, 245.18, 283.45, 259.81, 281.62, 271.69, 280.7, 278.09, 298.08, 309.18, 301.73, 327.47, 304.48, 335.7, 311.79, 343.01, 312.71, 343.01, 315.45, 338.44, 314.54, 325.64, 312.71, 317.41, 310.88, 311.92, 305.39, 301.87, 300.82, 295.46, 298.08, 284.49, 299.91, 274.43, 300.82, 268.95, 304.48, 257.06, 307.22, 250.66, 312.71, 237.86, 326.42, 246.09, 330.99, 223.23, 330.99, 214.09, 330.99, 201.29, 327.34, 194.89, 326.42, 183.91, 323.68, 174.77, 321.85, 172.03], [378.54, 169.28, 387.68, 161.06, 396.83, 157.4, 405.97, 155.57, 409.63, 144.6, 419.69, 139.11, 427.91, 136.37, 433.4, 135.45, 439.8, 125.4, 448.03, 140.03, 453.52, 137.28, 458.09, 127.22, 458.09, 143.68, 459.0, 151.0, 463.57, 161.97, 464.49, 169.28, 462.66, 170.2, 472.72, 176.6, 471.8, 185.74, 469.06, 191.23, 471.8, 197.63, 469.97, 201.29, 469.97, 206.77, 464.49, 210.43, 450.77, 211.34, 450.77, 204.03, 444.37, 200.37, 439.8, 195.8, 437.97, 192.14, 433.4, 192.14, 427.91, 192.14, 421.51, 203.12, 407.8, 220.49, 402.31, 230.55, 397.74, 237.86, 392.25, 248.83, 385.85, 257.98, 383.11, 257.98, 379.45, 274.43, 384.94, 307.35, 384.94, 332.95, 392.25, 343.93, 383.11, 344.84, 376.71, 340.27, 375.8, 330.21, 376.71, 314.67, 370.31, 297.29, 359.34, 315.58, 341.97, 329.3, 332.82, 339.35, 322.76, 343.01, 322.76, 335.7, 327.34, 329.3, 336.48, 326.55, 346.54, 311.92, 354.77, 297.29, 358.42, 280.84, 359.34, 266.21, 347.45, 258.89, 341.05, 255.23, 348.37, 217.75, 348.37, 209.52, 349.28, 196.72, 350.19, 187.57, 350.19, 181.17, 356.6, 172.03, 360.25, 168.37, 373.05, 168.37, 377.63, 164.71]], "area": 21556.370300000006, "iscrowd": 0, "image_id": 287659, "bbox": [213.04, 125.4, 259.68, 219.44], "category_id": 19, "id": 55515, "split": "val", "sentences": [{"tokens": ["horse", "in", "lead"], "raw": "horse in lead", "sent_id": 61577, "sent": "horse in lead"}, {"tokens": ["the", "horse", "in", "front"], "raw": "The horse in front.", "sent_id": 61578, "sent": "the horse in front"}], "file_name": "COCO_train2014_000000287659_55515.jpg", "ann_id": 55515, "sent_ids": [61577, 61578], "ref_id": 28636}, {"segmentation": [[39.25, 255.63, 76.59, 231.69, 122.55, 216.37, 388.7, 213.5, 466.25, 204.88, 513.17, 181.91, 560.08, 112.97, 588.8, 105.31, 566.78, 213.5, 635.71, 208.71, 532.31, 247.01, 355.2, 292.01, 305.41, 291.05, 256.58, 278.6, 110.1, 279.56, 111.06, 296.79, 103.4, 298.71, 81.38, 285.3, 39.25, 261.37]], "area": 37557.54049999999, "iscrowd": 0, "image_id": 126537, "bbox": [39.25, 105.31, 596.46, 193.4], "category_id": 5, "id": 156730, "split": "val", "sentences": [{"tokens": ["sunexpress", "airplane", "on", "a", "runway"], "raw": "SunExpress airplane on a runway.", "sent_id": 61620, "sent": "sunexpress airplane on a runway"}, {"tokens": ["an", "aircraft", "on", "the", "runaway"], "raw": "An aircraft on the runaway", "sent_id": 61621, "sent": "an aircraft on the runaway"}], "file_name": "COCO_train2014_000000126537_156730.jpg", "ann_id": 156730, "sent_ids": [61620, 61621], "ref_id": 28658}, {"segmentation": [[11.59, 337.2, 22.21, 333.34, 34.77, 324.65, 36.7, 314.99, 38.63, 301.47, 41.53, 281.18, 46.36, 273.46, 52.15, 265.73, 73.4, 250.28, 85.96, 241.59, 101.41, 233.86, 123.62, 230.96, 146.8, 230.0, 189.3, 230.0, 210.54, 230.0, 245.31, 230.0, 255.94, 237.72, 276.22, 251.24, 290.7, 259.94, 310.99, 273.46, 322.58, 286.01, 334.16, 314.99, 332.23, 334.3, 332.23, 361.35, 333.2, 383.56, 329.34, 396.11, 320.64, 400.94, 314.85, 392.25, 313.88, 375.83, 315.81, 345.89, 316.78, 330.44, 307.12, 334.3, 290.7, 343.96, 277.18, 343.0, 272.35, 350.72, 263.66, 356.52, 260.76, 362.31, 237.59, 367.14, 223.1, 371.97, 208.61, 377.76, 187.36, 379.7, 191.23, 366.17, 198.95, 360.38, 202.82, 358.45, 187.36, 354.58, 180.6, 354.58, 169.01, 358.45, 167.08, 364.24, 166.12, 381.63, 167.08, 391.28, 163.22, 405.77, 145.84, 406.74, 127.48, 399.01, 115.9, 392.25, 108.17, 379.7, 95.61, 369.07, 82.09, 366.17, 66.64, 368.11, 58.91, 360.38, 59.88, 354.58, 62.78, 344.93, 63.74, 325.61, 55.05, 320.78, 47.32, 338.17, 31.87, 346.86, 12.56, 350.72, 9.66, 350.72]], "area": 36906.529200000004, "iscrowd": 0, "image_id": 5862, "bbox": [9.66, 230.0, 324.5, 176.74], "category_id": 18, "id": 13297, "split": "val", "sentences": [{"tokens": ["a", "white", "dog", "with", "a", "blue", "collar", "on", "a", "bed"], "raw": "A white dog with a blue collar on a bed.", "sent_id": 61634, "sent": "a white dog with a blue collar on a bed"}, {"tokens": ["white", "dog", "laying", "on", "couch"], "raw": "white dog laying on couch", "sent_id": 61635, "sent": "white dog laying on couch"}], "file_name": "COCO_train2014_000000005862_13297.jpg", "ann_id": 13297, "sent_ids": [61634, 61635], "ref_id": 28663}, {"segmentation": [[35.58, 224.56, 141.37, 233.22, 163.49, 212.06, 179.84, 210.13, 192.34, 209.17, 203.88, 213.02, 215.42, 213.02, 229.85, 215.9, 237.54, 220.71, 243.31, 226.48, 251.97, 234.18, 268.32, 241.87, 291.4, 244.76, 292.36, 285.15, 283.7, 293.8, 278.9, 307.27, 268.32, 309.19, 251.01, 307.27, 246.2, 297.65, 234.66, 303.42, 225.04, 304.38, 215.42, 299.57, 210.61, 289.96, 193.3, 290.92, 158.68, 287.07, 148.1, 305.34, 136.56, 305.34, 111.56, 299.57, 98.09, 298.61, 86.55, 298.61, 78.86, 293.8, 71.17, 288.99, 68.28, 281.3, 58.66, 271.68, 49.05, 264.95, 40.39, 254.37, 37.51, 246.68, 28.85, 238.02]], "area": 17609.378049999992, "iscrowd": 0, "image_id": 307082, "bbox": [28.85, 209.17, 263.51, 100.02], "category_id": 8, "id": 399352, "split": "val", "sentences": [{"tokens": ["car", "number", "five", "that", "is", "in", "the", "snow"], "raw": "car number five that is in the snow", "sent_id": 61674, "sent": "car number five that is in the snow"}], "file_name": "COCO_train2014_000000307082_399352.jpg", "ann_id": 399352, "sent_ids": [61674], "ref_id": 28675}, {"segmentation": [[412.88, 234.09, 425.0, 219.7, 429.55, 207.58, 432.58, 188.64, 432.58, 177.27, 429.55, 168.94, 437.12, 151.52, 439.39, 146.97, 421.21, 133.33, 420.45, 115.15, 403.03, 108.33, 384.09, 104.55, 353.79, 118.94, 350.0, 124.24, 348.48, 128.79, 343.94, 154.55, 343.94, 160.61, 340.91, 175.76, 339.39, 190.15, 331.06, 209.09, 329.55, 215.15, 328.79, 219.7, 325.0, 230.3]], "area": 10678.979449999999, "iscrowd": 0, "image_id": 283624, "bbox": [325.0, 104.55, 114.39, 129.54], "category_id": 18, "id": 13058, "split": "val", "sentences": [{"tokens": ["a", "dog", "in", "a", "party", "hat"], "raw": "A dog in a party hat.", "sent_id": 61697, "sent": "a dog in a party hat"}, {"tokens": ["a", "small", "dog", "with", "a", "hat", "on", "its", "head"], "raw": "A small dog with a hat on its head.", "sent_id": 61698, "sent": "a small dog with a hat on its head"}], "file_name": "COCO_train2014_000000283624_13058.jpg", "ann_id": 13058, "sent_ids": [61697, 61698], "ref_id": 28685}, {"segmentation": [[420.67, 183.19, 421.75, 204.76, 501.57, 216.63, 537.17, 229.57, 528.54, 255.46, 545.8, 275.96, 537.17, 283.51, 549.03, 315.87, 530.7, 349.3, 510.2, 362.25, 476.76, 354.7, 467.06, 348.22, 460.58, 360.09, 456.27, 384.9, 429.3, 411.87, 405.57, 416.18, 355.96, 392.45, 351.64, 357.93, 337.62, 334.2, 307.42, 346.07, 295.55, 352.54, 166.11, 302.92, 162.88, 320.18, 147.78, 325.57, 127.28, 313.71, 115.42, 287.82, 111.1, 267.33, 118.65, 245.75, 125.12, 218.79, 127.28, 213.39, 152.09, 214.47, 153.17, 178.88, 167.19, 148.67, 142.38, 155.15, 116.49, 155.15, 120.81, 142.2, 140.22, 136.81, 392.63, 46.2, 406.65, 47.28, 435.78, 55.91, 433.62, 72.09, 400.18, 80.72, 297.71, 107.69, 302.02, 129.26, 305.26, 167.01, 343.01, 174.56, 382.92, 176.72, 419.6, 181.03]], "area": 83824.80470000002, "iscrowd": 0, "image_id": 7852, "bbox": [111.1, 46.2, 437.93, 369.98], "category_id": 8, "id": 398249, "split": "val", "sentences": [{"tokens": ["the", "old", "school", "fire", "truck", "with", "a", "blue", "engine", "top"], "raw": "The old school fire truck with a blue engine top.", "sent_id": 61733, "sent": "the old school fire truck with a blue engine top"}, {"tokens": ["an", "antique", "fire", "truck", "with", "a", "ladder", "on", "top", "of", "it"], "raw": "An antique fire truck with a ladder on top of it.", "sent_id": 61734, "sent": "an antique fire truck with a ladder on top of it"}], "file_name": "COCO_train2014_000000007852_398249.jpg", "ann_id": 398249, "sent_ids": [61733, 61734], "ref_id": 28700}, {"segmentation": [[142.1, 295.69, 141.23, 286.09, 151.7, 273.88, 150.82, 247.71, 159.54, 218.92, 205.78, 198.87, 235.44, 181.41, 268.59, 163.97, 298.25, 133.44, 309.59, 128.21, 319.18, 135.18, 332.26, 158.74, 330.52, 161.35, 307.84, 156.99, 263.35, 207.59, 246.78, 218.92, 252.89, 240.73, 241.55, 259.05, 252.02, 327.09, 258.99, 343.66, 249.4, 339.31, 228.46, 265.16, 217.99, 278.24, 195.32, 332.33, 194.44, 310.52, 211.01, 263.42, 188.33, 260.8, 174.38, 299.18, 163.91, 297.43, 165.66, 279.99, 149.95, 297.43]], "area": 11198.511700000003, "iscrowd": 0, "image_id": 285000, "bbox": [141.23, 128.21, 191.03, 215.45], "category_id": 25, "id": 598597, "split": "val", "sentences": [{"tokens": ["a", "large", "giraffe", "runs", "at", "the", "the", "back", "of", "the", "pack"], "raw": "A large giraffe runs at the the back of the pack.", "sent_id": 61796, "sent": "a large giraffe runs at the the back of the pack"}], "file_name": "COCO_train2014_000000285000_598597.jpg", "ann_id": 598597, "sent_ids": [61796], "ref_id": 28724}, {"segmentation": [[7.46, 322.37, 17.42, 312.42, 7.46, 287.54, 26.13, 262.66, 24.88, 258.92, 26.13, 242.75, 27.37, 231.55, 49.77, 219.11, 77.14, 214.13, 100.78, 221.6, 119.44, 246.48, 121.93, 266.39, 105.75, 270.12, 99.53, 265.14, 89.58, 277.58, 89.58, 296.25, 93.31, 309.93, 77.14, 342.28, 82.11, 372.14, 89.58, 425.64, 33.59, 470.43, 3.73, 470.43, 1.24, 322.37]], "area": 19483.508499999996, "iscrowd": 0, "image_id": 485173, "bbox": [1.24, 214.13, 120.69, 256.3], "category_id": 20, "id": 2174778, "split": "val", "sentences": [{"tokens": ["all", "brown", "goat", "next", "to", "the", "white", "goats"], "raw": "All brown goat next to the white goats.", "sent_id": 61833, "sent": "all brown goat next to the white goats"}, {"tokens": ["a", "brown", "goat"], "raw": "A brown goat.", "sent_id": 61834, "sent": "a brown goat"}], "file_name": "COCO_train2014_000000485173_2174778.jpg", "ann_id": 2174778, "sent_ids": [61833, 61834], "ref_id": 28737}, {"segmentation": [[222.59, 20.04, 226.32, 85.95, 246.22, 108.33, 272.33, 177.97, 268.6, 190.4, 313.37, 296.1, 339.48, 289.89, 334.51, 311.03, 332.02, 332.17, 343.21, 343.36, 317.1, 449.06, 309.64, 471.44, 640.0, 471.44, 640.0, 94.65, 640.0, 48.64, 624.25, 8.85, 330.78, 2.63]], "area": 163810.141, "iscrowd": 0, "image_id": 500440, "bbox": [222.59, 2.63, 417.41, 468.81], "category_id": 73, "id": 1970770, "split": "val", "sentences": [{"tokens": ["an", "open", "laptop", "sits", "to", "the", "right", "of", "a", "glass", "of", "beer"], "raw": "An open laptop sits to the right of a glass of beer.", "sent_id": 61844, "sent": "an open laptop sits to the right of a glass of beer"}, {"tokens": ["white", "laptop", "with", "green", "keyboard", "open", "and", "turned", "on", "with", "email", "page", "showing"], "raw": "White laptop with green keyboard open and turned on with email page showing", "sent_id": 61845, "sent": "white laptop with green keyboard open and turned on with email page showing"}], "file_name": "COCO_train2014_000000500440_1970770.jpg", "ann_id": 1970770, "sent_ids": [61844, 61845], "ref_id": 28743}, {"segmentation": [[219.22, 175.98, 230.71, 137.69, 239.33, 122.38, 289.11, 105.14, 322.61, 104.19, 355.16, 109.93, 370.48, 122.38, 386.75, 148.22, 389.62, 160.67, 387.71, 176.94, 395.37, 182.69, 402.07, 185.56, 402.07, 191.3, 402.07, 194.17, 406.85, 203.75, 410.68, 207.58, 414.51, 215.23, 410.68, 224.81, 408.77, 230.55, 405.9, 237.25, 406.85, 248.74, 408.77, 263.1, 407.81, 285.12, 380.05, 295.65, 371.43, 299.48, 371.43, 308.09, 400.15, 351.17, 426.0, 421.05, 257.51, 419.14, 260.39, 383.72, 255.6, 341.6, 255.6, 303.31, 269.0, 277.46, 276.66, 262.14, 267.09, 248.74, 230.71, 228.64, 218.27, 204.7, 218.27, 177.9]], "area": 46890.258850000006, "iscrowd": 0, "image_id": 218734, "bbox": [218.27, 104.19, 207.73, 316.86], "category_id": 1, "id": 442450, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "leaning", "on", "a", "display", "of", "bananas"], "raw": "A young boy leaning on a display of bananas.", "sent_id": 61850, "sent": "a young boy leaning on a display of bananas"}, {"tokens": ["black", "boy", "standing", "beside", "a", "bunch", "of", "banannas", "at", "the", "market"], "raw": "Black boy standing beside a bunch of banannas at the market", "sent_id": 61851, "sent": "black boy standing beside a bunch of banannas at the market"}], "file_name": "COCO_train2014_000000218734_442450.jpg", "ann_id": 442450, "sent_ids": [61850, 61851], "ref_id": 28746}, {"segmentation": [[176.21, 418.35, 148.17, 366.55, 150.31, 345.87, 152.45, 301.65, 168.14, 273.12, 171.7, 268.13, 171.7, 248.16, 179.55, 199.66, 183.11, 190.39, 245.16, 171.14, 250.15, 153.31, 253.72, 146.89, 250.87, 146.17, 245.87, 140.47, 242.31, 126.2, 238.03, 129.06, 233.04, 122.64, 229.47, 105.52, 230.18, 96.25, 228.76, 84.84, 225.91, 74.14, 221.63, 68.43, 204.51, 54.88, 204.51, 51.32, 223.77, 43.47, 233.04, 39.19, 243.74, 35.63, 245.16, 27.78, 235.18, 25.64, 232.32, 16.37, 260.85, 5.67, 285.81, 14.23, 303.64, 21.36, 311.49, 40.62, 319.33, 49.18, 325.04, 89.12, 325.04, 111.23, 320.05, 120.5, 313.63, 121.21, 312.2, 135.48, 307.92, 146.17, 314.34, 164.0, 329.32, 176.84, 350.0, 186.11, 357.13, 188.97, 356.42, 201.8, 366.41, 203.94, 369.26, 229.62, 378.53, 256.72, 394.93, 270.98, 375.68, 276.69, 357.85, 294.52, 341.44, 310.92, 339.3, 323.05, 327.89, 333.75, 302.22, 367.98, 288.67, 340.88, 279.4, 327.33, 279.4, 314.49, 279.4, 304.5, 274.4, 300.94, 262.28, 287.39, 248.01, 286.67, 240.88, 293.81, 240.17, 306.64, 239.46, 317.34, 233.75, 327.33, 238.03, 337.31, 235.89, 353.0, 247.3, 360.85, 250.87, 368.69, 269.41, 377.96, 281.53, 400.07, 281.53, 413.62, 275.12, 411.48, 268.7, 409.35, 272.98, 425.04, 182.4, 425.75]], "area": 52153.42675000001, "iscrowd": 0, "image_id": 535666, "bbox": [148.17, 5.67, 246.76, 420.08], "category_id": 1, "id": 198423, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "shirt", ",", "black", "tie", ",", "and", "black", "jacket", "with", "a", "burgundy", "flower", "in", "the", "buttonhole"], "raw": "A man wearing a black shirt, black tie, and black jacket with a burgundy flower in the buttonhole.", "sent_id": 61921, "sent": "a man wearing a black shirt , black tie , and black jacket with a burgundy flower in the buttonhole"}, {"tokens": ["a", "man", "in", "a", "dark", "suit", ",", "shirt", "and", "tie", "with", "dark", "hair", "looking", "suprised", "next", "to", "a", "woman", "in", "white"], "raw": "A man in a dark suit, shirt and tie with dark hair looking suprised next to a woman in white", "sent_id": 61922, "sent": "a man in a dark suit , shirt and tie with dark hair looking suprised next to a woman in white"}], "file_name": "COCO_train2014_000000535666_198423.jpg", "ann_id": 198423, "sent_ids": [61921, 61922], "ref_id": 28775}, {"segmentation": [[640.0, 37.42, 600.68, 49.9, 577.65, 70.05, 572.85, 86.36, 578.61, 94.04, 580.53, 102.67, 573.81, 107.47, 574.77, 118.98, 564.22, 135.3, 565.18, 140.09, 572.85, 145.85, 572.85, 153.53, 579.57, 160.24, 570.93, 167.92, 576.69, 175.6, 579.57, 175.6, 581.49, 184.23, 591.08, 192.87, 570.93, 206.3, 566.13, 221.66, 556.54, 235.09, 554.62, 241.81, 541.19, 247.56, 533.51, 263.88, 518.16, 280.19, 506.64, 293.62, 500.89, 299.38, 484.57, 306.1, 475.94, 312.81, 462.5, 326.25, 449.07, 333.92, 450.99, 355.99, 450.99, 358.87, 476.9, 352.16, 493.21, 353.11, 506.64, 355.99, 519.12, 360.79, 533.51, 360.79, 547.9, 368.47, 558.46, 372.31, 571.89, 378.06, 570.93, 399.17, 585.33, 405.89, 604.52, 400.13, 618.91, 403.97, 631.38, 414.53, 635.22, 417.4, 639.06, 419.32, 640.0, 47.02]], "area": 33056.428400000004, "iscrowd": 0, "image_id": 517492, "bbox": [449.07, 37.42, 190.93, 381.9], "category_id": 1, "id": 437357, "split": "val", "sentences": [{"tokens": ["a", "asian", "woman", "wholding", "her", "hand", "to", "her", "face"], "raw": "A asian woman wholding her hand to her face.", "sent_id": 62003, "sent": "a asian woman wholding her hand to her face"}, {"tokens": ["an", "asian", "man", "in", "glasses", "sitting", "at", "a", "table"], "raw": "An asian man in glasses sitting at a table.", "sent_id": 62004, "sent": "an asian man in glasses sitting at a table"}], "file_name": "COCO_train2014_000000517492_437357.jpg", "ann_id": 437357, "sent_ids": [62003, 62004], "ref_id": 28806}, {"segmentation": [[183.68, 152.93, 183.08, 140.87, 189.11, 134.23, 203.59, 131.22, 223.5, 128.8, 243.4, 133.03, 266.93, 140.87, 292.26, 148.11, 285.63, 163.19, 279.6, 166.2, 276.58, 171.63, 272.36, 177.67, 263.91, 203.0, 253.05, 222.31, 253.05, 260.91, 256.07, 269.36, 256.07, 274.79, 251.85, 279.01, 248.23, 279.61, 240.99, 282.03, 237.97, 282.03, 228.32, 282.03, 228.32, 273.58, 229.53, 256.69, 228.32, 246.44, 220.48, 249.45, 218.67, 260.91, 218.67, 264.53, 218.07, 264.53, 216.26, 264.53, 212.03, 262.72, 209.02, 259.1, 200.57, 255.48, 183.08, 267.55, 178.25, 280.22, 171.01, 297.71, 162.57, 300.12, 156.54, 304.95, 145.07, 303.14, 137.83, 296.5, 137.83, 286.85, 138.44, 279.61, 146.88, 273.58, 151.11, 268.76, 155.93, 257.9, 160.15, 246.44, 164.98, 237.39, 169.81, 227.73, 171.01, 213.26, 171.01, 198.18, 172.22, 184.3, 180.06, 167.41, 183.08, 154.14]], "area": 13799.895899999996, "iscrowd": 0, "image_id": 490507, "bbox": [137.83, 128.8, 154.43, 176.15], "category_id": 17, "id": 46407, "split": "val", "sentences": [{"tokens": ["a", "cat", "to", "the", "left", "of", "two", "other", "cats"], "raw": "A cat to the left of two other cats.", "sent_id": 62009, "sent": "a cat to the left of two other cats"}], "file_name": "COCO_train2014_000000490507_46407.jpg", "ann_id": 46407, "sent_ids": [62009], "ref_id": 28808}, {"segmentation": [[411.13, 372.82, 422.76, 391.25, 420.82, 414.52, 426.64, 422.28, 430.52, 403.85, 433.43, 372.82, 433.43, 372.82, 434.4, 342.77, 427.61, 334.04, 427.61, 327.25, 420.82, 327.25, 415.97, 311.74, 403.37, 304.95, 377.19, 278.77, 377.19, 278.77, 376.22, 280.71, 374.28, 269.07, 355.86, 267.13, 355.86, 267.13, 344.22, 275.86, 344.22, 275.86, 340.34, 284.59, 331.62, 290.41, 341.31, 300.1, 353.92, 298.16, 358.77, 303.98, 366.05, 306.35, 366.05, 313.39, 365.41, 327.46, 363.49, 343.45, 363.49, 360.09, 369.88, 383.12, 374.36, 383.96, 373.72, 348.77, 378.84, 345.57, 387.8, 359.01, 387.8, 359.01, 390.36, 359.01, 387.16, 380.12, 384.6, 389.72, 384.6, 389.72, 387.8, 405.07, 387.16, 432.58, 387.16, 432.58, 392.28, 432.58, 398.67, 412.11, 401.23, 401.87, 399.95, 391.0]], "area": 6814.014799999999, "iscrowd": 0, "image_id": 258679, "bbox": [331.62, 267.13, 102.78, 165.45], "category_id": 18, "id": 8266, "split": "val", "sentences": [{"tokens": ["a", "big", "dog", "near", "by", "the", "man"], "raw": "A big dog near by the man", "sent_id": 62014, "sent": "a big dog near by the man"}, {"tokens": ["a", "white", "color", "tall", "dog"], "raw": "A white color tall dog", "sent_id": 62015, "sent": "a white color tall dog"}], "file_name": "COCO_train2014_000000258679_8266.jpg", "ann_id": 8266, "sent_ids": [62014, 62015], "ref_id": 28810}, {"segmentation": [[86.29, 347.33, 105.71, 333.3, 139.15, 343.01, 142.38, 335.46, 126.2, 318.2, 155.33, 310.65, 155.33, 304.18, 139.15, 298.79, 179.06, 229.75, 194.16, 170.43, 230.83, 168.27, 244.85, 167.19, 250.25, 162.88, 259.96, 155.33, 256.72, 141.3, 250.25, 136.99, 241.62, 136.99, 234.07, 152.09, 194.16, 155.33, 187.69, 139.15, 196.31, 135.91, 192.0, 103.55, 202.79, 65.8, 241.62, 38.83, 267.51, 38.83, 306.34, 43.15, 349.48, 80.9, 360.27, 96.0, 437.93, 136.99, 483.24, 206.02, 517.75, 255.64, 537.17, 249.17, 553.35, 257.8, 530.7, 293.39, 499.42, 300.94, 436.85, 300.94, 358.11, 319.28, 337.62, 350.56, 312.81, 357.03, 323.6, 367.82, 339.78, 368.9, 348.4, 351.64, 361.35, 351.64, 371.06, 380.76, 319.28, 392.63, 266.43, 381.84, 244.85, 409.89, 209.26, 404.49, 168.27, 386.16, 210.34, 354.88, 245.93, 327.91, 208.18, 335.46, 117.57, 364.58, 110.02, 373.21, 85.21, 354.88]], "area": 85544.94870000001, "iscrowd": 0, "image_id": 176179, "bbox": [85.21, 38.83, 468.14, 371.06], "category_id": 22, "id": 581088, "split": "val", "sentences": [{"tokens": ["an", "elephant", "lying", "in", "the", "river", "water", "with", "her", "caretaker", "standing", "on", "it", "forelimb"], "raw": "An elephant lying in the river water with her caretaker standing on it forelimb", "sent_id": 62039, "sent": "an elephant lying in the river water with her caretaker standing on it forelimb"}, {"tokens": ["the", "large", "elephant"], "raw": "The large elephant.", "sent_id": 62040, "sent": "the large elephant"}], "file_name": "COCO_train2014_000000176179_581088.jpg", "ann_id": 581088, "sent_ids": [62039, 62040], "ref_id": 28821}, {"segmentation": [[193.3, 56.23, 198.58, 21.09, 228.45, 0.0, 278.53, 4.39, 285.56, 12.3, 324.22, 50.96, 299.62, 90.5, 287.32, 100.17, 300.5, 182.76, 239.87, 99.29, 230.21, 53.6], [202.97, 152.01, 187.15, 220.54, 208.24, 236.36, 227.57, 188.03]], "area": 12243.653549999999, "iscrowd": 0, "image_id": 347908, "bbox": [187.15, 0.0, 137.07, 236.36], "category_id": 1, "id": 1209095, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "blue", "jeans", "standing", "behind", "the", "fence"], "raw": "A man in blue jeans standing behind the fence.", "sent_id": 62194, "sent": "a man in blue jeans standing behind the fence"}, {"tokens": ["man", "standing", "behind", "fence"], "raw": "man standing behind fence", "sent_id": 62195, "sent": "man standing behind fence"}], "file_name": "COCO_train2014_000000347908_1209095.jpg", "ann_id": 1209095, "sent_ids": [62194, 62195], "ref_id": 28878}, {"segmentation": [[405.0, 295.46, 410.24, 257.05, 400.64, 249.2, 404.13, 241.34, 409.36, 235.23, 422.46, 231.74, 437.3, 228.25, 456.5, 222.14, 466.1, 219.52, 467.84, 231.74, 465.23, 236.1, 439.91, 240.47, 421.22, 249.81, 425.59, 271.63], [571.35, 337.09, 574.84, 326.62, 580.95, 322.26, 587.94, 289.96, 584.45, 270.76, 582.7, 260.28, 590.56, 257.66, 602.78, 251.55, 603.65, 244.57, 612.38, 243.7, 615.0, 249.81, 606.27, 264.65, 600.16, 272.5, 604.52, 295.2, 590.56, 311.78, 588.81, 335.35, 585.32, 341.46]], "area": 2891.7410999999934, "iscrowd": 0, "image_id": 342996, "bbox": [400.64, 219.52, 214.36, 121.94], "category_id": 62, "id": 104473, "split": "val", "sentences": [{"tokens": ["a", "chair", "where", "a", "man", "is", "sitting"], "raw": "A CHAIR  WHERE A MAN IS SITTING", "sent_id": 62382, "sent": "a chair where a man is sitting"}, {"tokens": ["a", "chair", "with", "a", "man", "in", "a", "black", "suit", "sitting", "on", "it"], "raw": "A chair with a man in a black suit sitting on it.", "sent_id": 62383, "sent": "a chair with a man in a black suit sitting on it"}], "file_name": "COCO_train2014_000000342996_104473.jpg", "ann_id": 104473, "sent_ids": [62382, 62383], "ref_id": 28953}, {"segmentation": [[270.25, 182.13, 270.6, 182.13, 301.93, 179.72, 350.14, 179.03, 378.03, 180.07, 392.84, 186.95, 419.36, 222.42, 419.36, 222.42, 419.36, 222.42, 442.77, 228.27, 468.94, 237.23, 469.63, 256.51, 471.86, 299.84, 356.2, 306.91, 338.85, 283.78, 290.01, 273.5, 290.01, 273.5, 270.1, 273.5, 247.61, 258.08, 256.6, 213.1, 269.45, 180.33]], "area": 20763.104299999995, "iscrowd": 0, "image_id": 228519, "bbox": [247.61, 179.03, 224.25, 127.88], "category_id": 8, "id": 1797781, "split": "val", "sentences": [{"tokens": ["a", "black", "land", "rover", "that", "is", "pulling", "a", "boat"], "raw": "A black Land Rover that is pulling a boat.", "sent_id": 62414, "sent": "a black land rover that is pulling a boat"}, {"tokens": ["a", "black", "jeep", "with", "a", "boat", "on", "back", "parked"], "raw": "A black jeep with a boat on back parked.", "sent_id": 62415, "sent": "a black jeep with a boat on back parked"}], "file_name": "COCO_train2014_000000228519_1797781.jpg", "ann_id": 1797781, "sent_ids": [62414, 62415], "ref_id": 28965}, {"segmentation": [[156.76, 549.39, 162.52, 484.67, 149.57, 404.13, 159.64, 385.44, 166.83, 360.99, 126.56, 385.44, 128.0, 405.57, 116.49, 412.76, 110.74, 368.18, 123.69, 333.66, 138.07, 303.46, 129.44, 266.07, 151.01, 220.04, 186.97, 197.03, 188.4, 179.78, 174.02, 161.08, 174.02, 146.7, 175.46, 123.69, 192.72, 100.67, 225.8, 97.8, 250.25, 125.12, 251.69, 145.26, 264.63, 155.33, 244.49, 182.65, 247.37, 212.85, 287.64, 243.06, 289.08, 319.28, 276.13, 356.67, 270.38, 430.02, 263.19, 432.9, 253.12, 454.47, 232.99, 522.07, 238.74, 550.83, 251.69, 581.03, 218.61, 579.6, 214.29, 547.96, 215.73, 465.98, 205.66, 454.47, 192.72, 473.17, 186.97, 480.36, 181.21, 568.09, 163.96, 570.97, 149.57, 559.46]], "area": 48170.67435000001, "iscrowd": 0, "image_id": 421643, "bbox": [110.74, 97.8, 178.34, 483.23], "category_id": 1, "id": 197053, "split": "val", "sentences": [{"tokens": ["all", "of", "the", "boy", "wearing", "a", "blue", "shirt", ",", "black", "shorts", "and", "dirty", "shoes"], "raw": "All of the boy wearing a blue shirt, black shorts and dirty shoes.", "sent_id": 62436, "sent": "all of the boy wearing a blue shirt , black shorts and dirty shoes"}, {"tokens": ["a", "young", "boy", "inside", "a", "house", "holding", "a", "wii", "controller", "in", "both", "hands"], "raw": "A young boy inside a house holding a Wii controller in both hands.", "sent_id": 62437, "sent": "a young boy inside a house holding a wii controller in both hands"}], "file_name": "COCO_train2014_000000421643_197053.jpg", "ann_id": 197053, "sent_ids": [62436, 62437], "ref_id": 28974}, {"segmentation": [[367.94, 599.8, 358.16, 553.18, 349.89, 549.42, 346.13, 538.9, 353.65, 528.37, 379.97, 530.63, 392.0, 523.11, 396.51, 502.81, 395.76, 471.22, 395.76, 409.47, 387.49, 400.45, 385.23, 387.67, 388.99, 377.89, 400.27, 372.63, 417.57, 373.38, 447.64, 372.63, 523.59, 376.39, 567.41, 376.93, 587.36, 381.78, 598.14, 392.56, 599.22, 409.27, 582.51, 420.06, 580.35, 448.09, 573.88, 501.45, 569.57, 532.7, 576.58, 546.18, 595.45, 553.19, 594.37, 570.96, 593.29, 575.28, 586.82, 573.66, 585.2, 573.64, 579.81, 597.9, 487.62, 597.36, 395.97, 597.36, 369.56, 596.82]], "area": 44406.01529999999, "iscrowd": 0, "image_id": 95185, "bbox": [346.13, 372.63, 253.09, 227.17], "category_id": 62, "id": 2189977, "split": "val", "sentences": [{"tokens": ["a", "wood", "rocking", "chair", "painted", "red"], "raw": "A wood rocking chair painted red.", "sent_id": 62442, "sent": "a wood rocking chair painted red"}, {"tokens": ["the", "red", "chair", "to", "the", "front"], "raw": "The red chair to the front.", "sent_id": 62443, "sent": "the red chair to the front"}], "file_name": "COCO_train2014_000000095185_2189977.jpg", "ann_id": 2189977, "sent_ids": [62442, 62443], "ref_id": 28976}, {"segmentation": [[473.7, 417.92, 471.57, 404.4, 489.36, 391.59, 495.05, 371.66, 509.29, 346.04, 517.83, 326.83, 517.83, 316.86, 517.83, 308.32, 506.44, 314.73, 501.46, 314.73, 497.9, 308.32, 496.48, 308.32, 495.77, 306.19, 489.36, 289.82, 492.21, 276.3, 504.31, 269.89, 518.54, 275.59, 522.81, 279.86, 523.52, 279.86, 534.91, 269.89, 569.07, 271.32, 575.47, 270.61, 608.92, 284.13, 613.9, 284.13, 626.0, 290.53, 630.27, 299.07, 627.42, 301.21, 621.73, 301.21, 611.05, 301.21, 603.22, 295.51, 601.8, 290.53, 586.14, 284.13, 611.05, 305.48, 623.15, 324.69, 625.29, 343.91, 603.94, 360.27, 601.8, 372.37, 586.86, 372.37, 580.45, 385.89, 598.95, 411.51, 621.73, 443.54, 617.46, 447.09, 591.84, 445.67, 600.38, 438.55, 592.55, 423.61, 564.8, 397.28, 553.41, 388.74, 547.72, 417.2, 546.29, 434.28, 547.72, 446.38, 514.27, 449.94, 506.44, 442.11, 514.27, 440.69, 531.35, 426.46, 539.18, 407.95, 535.62, 358.14, 542.73, 353.87, 556.97, 346.75, 556.26, 341.06, 542.02, 338.21, 532.06, 354.58, 527.79, 353.16, 490.07, 405.82, 483.67, 422.19, 472.99, 418.63]], "area": 14336.94195, "iscrowd": 0, "image_id": 233841, "bbox": [471.57, 269.89, 158.7, 180.05], "category_id": 1, "id": 545948, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "green", "shirt", "with", "the", "black", "sunglasses", "is", "picking", "up", "a", "yellow", "frisbee"], "raw": "The man in the green shirt with the black sunglasses is picking up a yellow Frisbee.", "sent_id": 62479, "sent": "the man in the green shirt with the black sunglasses is picking up a yellow frisbee"}, {"tokens": ["a", "man", "in", "a", "green", "shirt", "bending", "over", "in", "a", "grassy", "area", "to", "pick", "up", "a", "frisbee"], "raw": "A man in a green shirt bending over in a grassy area to pick up a frisbee.", "sent_id": 62480, "sent": "a man in a green shirt bending over in a grassy area to pick up a frisbee"}], "file_name": "COCO_train2014_000000233841_545948.jpg", "ann_id": 545948, "sent_ids": [62479, 62480], "ref_id": 28993}, {"segmentation": [[109.73, 354.11, 101.55, 354.54, 100.69, 349.38, 96.39, 336.47, 103.7, 326.15, 116.61, 314.53, 122.2, 313.24, 121.77, 323.14, 111.88, 351.1], [280.96, 390.25, 280.1, 365.73, 274.51, 359.28, 269.77, 355.83, 269.34, 345.94, 271.07, 335.61, 271.07, 330.45, 280.53, 342.93, 296.88, 352.82, 300.32, 383.37]], "area": 1549.7742000000003, "iscrowd": 0, "image_id": 571719, "bbox": [96.39, 313.24, 203.93, 77.01], "category_id": 62, "id": 382642, "split": "val", "sentences": [{"tokens": ["a", "plastic", "chair", "supporting", "a", "woman", "in", "a", "gray", "shirt"], "raw": "A plastic chair supporting a woman in a gray shirt", "sent_id": 62518, "sent": "a plastic chair supporting a woman in a gray shirt"}, {"tokens": ["the", "chair", "the", "woman", "in", "the", "gray", "shirt", "is", "sitting", "on"], "raw": "The chair the woman in the gray shirt is sitting on .", "sent_id": 62519, "sent": "the chair the woman in the gray shirt is sitting on"}], "file_name": "COCO_train2014_000000571719_382642.jpg", "ann_id": 382642, "sent_ids": [62518, 62519], "ref_id": 29006}, {"segmentation": [[178.15, 195.38, 172.87, 196.75, 169.94, 196.75, 165.06, 196.17, 159.48, 194.37, 152.82, 190.05, 149.22, 187.35, 148.32, 183.93, 150.3, 181.77, 151.56, 181.05, 157.86, 179.07, 165.42, 178.35, 171.0, 178.35, 176.94, 178.89, 184.14, 178.35, 190.62, 175.83, 192.96, 175.47, 193.32, 174.39, 192.96, 173.67, 192.6, 172.59, 194.4, 170.43, 194.94, 170.07, 193.5, 167.73, 195.66, 167.37, 196.92, 168.09, 198.36, 168.45, 198.9, 164.85, 201.6, 165.57, 205.56, 167.19, 206.64, 167.55, 210.42, 167.55, 214.74, 167.19, 220.14, 166.83, 223.74, 168.09, 226.44, 169.53, 228.24, 171.33, 227.7, 171.69, 225.72, 172.59, 224.1, 172.95, 224.1, 174.39, 228.42, 175.65, 233.1, 177.99, 235.8, 177.99, 239.4, 177.45, 243.36, 176.73, 251.28, 177.99, 257.58, 180.69, 258.48, 183.39, 257.76, 186.45, 254.88, 188.25, 249.66, 191.85, 248.4, 193.47, 246.78, 195.63, 247.14, 197.25, 251.1, 199.77, 253.44, 203.55, 255.78, 208.23, 257.04, 210.93, 258.66, 212.19, 263.88, 211.65, 268.74, 212.73, 271.26, 213.09, 284.4, 213.09, 297.54, 212.37, 308.88, 209.67, 322.92, 210.03, 343.07, 207.69, 349.19, 208.05, 353.87, 205.71, 362.51, 204.81, 363.59, 204.81, 372.59, 204.45, 377.99, 201.21, 379.61, 200.13, 383.21, 201.03, 384.83, 200.85, 385.91, 198.51, 386.63, 197.61, 400.31, 195.09, 417.77, 192.75, 420.83, 193.11, 422.81, 192.75, 442.43, 188.79, 452.69, 188.79, 460.97, 189.33, 468.89, 192.03, 475.37, 194.73, 487.43, 197.79, 495.53, 201.93, 502.37, 206.07, 508.49, 211.83, 516.05, 218.85, 519.83, 223.89, 522.53, 227.84, 525.41, 235.04, 527.39, 239.36, 528.83, 244.94, 526.13, 249.98, 522.89, 252.5, 520.19, 259.34, 520.19, 273.56, 520.91, 285.44, 520.01, 299.48, 518.75, 318.92, 518.03, 332.06, 518.39, 341.06, 515.33, 344.3, 501.11, 350.78, 490.49, 351.86, 480.41, 354.2, 479.51, 356.9, 474.11, 362.3, 469.25, 364.46, 466.55, 363.02, 463.13, 356.18, 454.31, 351.86, 448.19, 348.98, 445.85, 350.96, 445.31, 352.76, 441.35, 350.42, 439.19, 351.5, 438.65, 350.96, 434.51, 348.26, 432.53, 346.46, 422.99, 349.7, 414.89, 354.02, 399.77, 357.26, 383.57, 360.86, 373.13, 361.58, 365.03, 363.38, 356.03, 362.3, 349.19, 360.32, 339.48, 357.98, 331.2, 357.08, 329.04, 357.08, 326.7, 356.54, 321.3, 356.9, 317.16, 356.9, 309.6, 358.34, 305.46, 362.3, 303.66, 370.4, 302.4, 377.06, 301.5, 380.48, 298.26, 387.68, 297.0, 394.52, 296.46, 399.92, 293.4, 405.68, 290.52, 416.66, 290.16, 422.06, 288.9, 427.46, 286.56, 430.87, 280.98, 435.55, 279.9, 436.09, 276.12, 437.17, 270.72, 436.99, 266.76, 440.59, 264.24, 441.49, 261.54, 441.31, 259.56, 439.15, 259.02, 404.42, 256.32, 388.4, 252.18, 372.2, 244.8, 362.66, 238.68, 363.2, 235.8, 365.18, 229.32, 363.92, 225.36, 362.48, 220.32, 360.68, 216.18, 356.36, 212.76, 351.86, 207.72, 343.58, 203.04, 330.44, 196.02, 311.9, 192.96, 302.36, 189.9, 291.56, 184.14, 280.58, 181.8, 269.78, 181.8, 262.22, 181.26, 257.9, 181.26, 257.72, 181.08, 252.14, 178.92, 246.02, 176.58, 240.44, 174.78, 232.52, 173.88, 229.46, 173.52, 223.53, 173.52, 219.93, 173.7, 216.69, 173.52, 215.25, 174.42, 210.75, 177.3, 205.89, 180.72, 202.65, 181.8, 201.39, 181.08, 198.15, 180.0, 196.35, 179.28, 196.17]], "area": 57050.61105000004, "iscrowd": 0, "image_id": 436797, "bbox": [148.32, 164.85, 380.51, 276.64], "category_id": 20, "id": 61274, "split": "val", "sentences": [{"tokens": ["a", "big", "female", "sheep", "and", "her", "baby", "lamb"], "raw": "A big female sheep and her baby lamb", "sent_id": 62530, "sent": "a big female sheep and her baby lamb"}, {"tokens": ["adult", "sheep"], "raw": "adult sheep", "sent_id": 62531, "sent": "adult sheep"}], "file_name": "COCO_train2014_000000436797_61274.jpg", "ann_id": 61274, "sent_ids": [62530, 62531], "ref_id": 29011}, {"segmentation": [[117.77, 255.14, 126.82, 239.45, 142.51, 230.41, 165.43, 218.95, 182.92, 211.1, 206.45, 216.53, 229.97, 218.34, 243.85, 206.28, 249.88, 198.44, 249.88, 194.82, 245.05, 186.37, 237.21, 175.51, 239.02, 168.88, 255.91, 164.05, 266.77, 165.86, 276.42, 167.07, 300.55, 162.85, 310.81, 165.26, 313.22, 178.53, 326.49, 188.78, 333.73, 194.82, 337.95, 201.45, 339.16, 206.28, 337.95, 213.52, 330.11, 220.15, 320.46, 224.98, 312.62, 231.61, 310.2, 241.87, 315.03, 252.73, 317.44, 259.36, 325.28, 263.58, 354.84, 274.44, 369.92, 276.25, 384.4, 279.27, 389.83, 283.49, 388.02, 290.73, 372.94, 294.95, 359.06, 297.36, 348.81, 294.95, 315.03, 289.52, 288.49, 286.51, 267.98, 284.09, 250.48, 281.08, 236.01, 279.27, 200.42, 273.24, 176.89, 268.41, 156.38, 266.0, 126.22, 264.19, 117.77, 261.17, 119.58, 254.54]], "area": 16976.500300000003, "iscrowd": 0, "image_id": 213005, "bbox": [117.77, 162.85, 272.06, 134.51], "category_id": 20, "id": 62102, "split": "val", "sentences": [{"tokens": ["one", "of", "three", "lambs", "sitting", "near", "their", "mom", ".", "it", "has", "two", "visible", "light", "teal", "spots", "on", "its", "back"], "raw": "One of three lambs sitting near their mom. It has two visible light teal spots on its back.", "sent_id": 62550, "sent": "one of three lambs sitting near their mom . it has two visible light teal spots on its back"}, {"tokens": ["the", "baby", "sheep", "that", "is", "to", "the", "left", "of", "his", "mom"], "raw": "The baby sheep that is to the left of his mom", "sent_id": 62551, "sent": "the baby sheep that is to the left of his mom"}], "file_name": "COCO_train2014_000000213005_62102.jpg", "ann_id": 62102, "sent_ids": [62550, 62551], "ref_id": 29019}, {"segmentation": [[2.16, 463.65, 25.93, 436.64, 108.05, 385.86, 180.45, 358.84, 242.04, 341.55, 263.65, 342.63, 272.3, 361.0, 264.73, 392.34, 267.97, 415.03, 248.52, 422.59, 259.33, 477.7, 225.83, 476.62, 211.79, 436.64, 205.3, 435.56, 212.87, 476.62, 186.93, 475.54, 183.69, 435.56, 156.68, 444.21, 164.24, 476.62, 148.03, 476.62, 140.47, 451.77, 109.13, 466.9, 114.54, 477.7, 75.64, 473.38, 68.07, 466.9, 7.56, 462.57]], "area": 21143.829699999995, "iscrowd": 0, "image_id": 205202, "bbox": [2.16, 341.55, 270.14, 136.15], "category_id": 62, "id": 385295, "split": "val", "sentences": [{"tokens": ["an", "empty", "brown", "wooden", "chair", "pushed", "up", "under", "a", "table", "next", "to", "three", "kids"], "raw": "An empty brown wooden chair pushed up under a table next to three kids.", "sent_id": 62593, "sent": "an empty brown wooden chair pushed up under a table next to three kids"}, {"tokens": ["a", "chair", "that", "is", "unoccupied"], "raw": "A chair that is unoccupied.", "sent_id": 62594, "sent": "a chair that is unoccupied"}], "file_name": "COCO_train2014_000000205202_385295.jpg", "ann_id": 385295, "sent_ids": [62593, 62594], "ref_id": 29033}, {"segmentation": [[534.34, 148.24, 572.2, 144.11, 575.6, 152.36, 580.45, 150.91, 587.0, 150.91, 594.53, 203.81, 596.71, 215.71, 601.08, 247.98, 601.32, 264.0, 598.17, 252.11, 591.61, 237.55, 582.88, 225.9, 577.54, 220.56, 565.4, 211.58, 561.28, 208.18, 555.94, 206.97, 552.54, 205.03, 551.33, 200.66, 551.33, 195.8, 549.87, 197.5, 550.84, 188.77, 551.33, 184.64, 547.2, 184.64, 545.75, 182.46, 544.05, 179.54, 542.83, 187.55, 540.65, 190.47, 535.55, 191.92, 535.07, 189.74, 535.07, 183.67, 536.28, 178.09, 536.52, 167.65, 537.01, 162.07, 535.55, 154.3, 534.1, 149.21], [605.56, 297.98, 596.38, 314.3, 589.78, 327.5, 586.21, 336.84, 586.21, 343.44, 584.83, 350.86, 580.98, 356.64, 583.46, 363.51, 580.43, 387.98, 578.51, 411.08, 576.04, 423.17, 576.86, 425.65, 581.26, 425.65, 591.16, 420.15, 601.06, 416.58, 608.2, 414.65, 611.78, 413.0, 612.05, 409.43, 611.5, 395.96, 612.88, 382.21, 613.43, 372.86, 612.05, 369.01, 607.93, 356.09, 606.83, 336.57]], "area": 6513.0388, "iscrowd": 0, "image_id": 390496, "bbox": [534.1, 144.11, 79.33, 281.54], "category_id": 1, "id": 1718017, "split": "val", "sentences": [{"tokens": ["a", "person", "is", "boarding", "a", "small", "airplane", "in", "front", "of", "a", "man", "who", "is", "waiting", "to", "board"], "raw": "A person is boarding a small airplane in front of a man who is waiting to board.", "sent_id": 62599, "sent": "a person is boarding a small airplane in front of a man who is waiting to board"}, {"tokens": ["a", "man", "in", "a", "yellow", "shirt", "inside", "the", "a", "plane"], "raw": "A man in a yellow shirt inside the a plane.", "sent_id": 62600, "sent": "a man in a yellow shirt inside the a plane"}], "file_name": "COCO_train2014_000000390496_1718017.jpg", "ann_id": 1718017, "sent_ids": [62599, 62600], "ref_id": 29035}, {"segmentation": [[170.4, 323.57, 176.14, 283.36, 171.36, 264.22, 180.93, 240.28, 160.83, 208.69, 167.53, 204.86, 189.55, 209.65, 199.12, 201.99, 200.08, 182.84, 206.78, 176.14, 213.48, 184.76, 217.31, 193.38, 317.82, 198.16, 366.65, 216.35, 440.36, 223.05, 585.87, 202.95, 640.0, 210.61, 638.52, 420.26, 593.53, 420.26, 569.6, 359.95, 544.71, 376.22, 477.69, 381.96, 446.1, 375.26, 435.57, 373.35, 449.93, 418.34, 418.34, 420.26, 396.32, 374.31, 381.01, 420.26, 347.5, 417.38, 348.46, 365.69, 333.14, 359.95, 316.87, 315.91, 280.49, 302.51, 262.3, 287.19, 251.77, 285.28, 247.94, 302.51, 227.84, 318.78, 204.86, 340.8, 200.08, 358.03, 181.89, 357.07, 168.49, 339.84, 169.44, 327.4]], "area": 75323.17665000001, "iscrowd": 0, "image_id": 366956, "bbox": [160.83, 176.14, 479.17, 244.12], "category_id": 24, "id": 589864, "split": "val", "sentences": [{"tokens": ["a", "zebra", "with", "its", "head", "lowered"], "raw": "A zebra with its head lowered.", "sent_id": 62713, "sent": "a zebra with its head lowered"}, {"tokens": ["the", "zebra", "who", "is", "looking", "at", "the", "ground"], "raw": "The zebra who is looking at the ground.", "sent_id": 62714, "sent": "the zebra who is looking at the ground"}], "file_name": "COCO_train2014_000000366956_589864.jpg", "ann_id": 589864, "sent_ids": [62713, 62714], "ref_id": 29080}, {"segmentation": [[1.74, 0.87, 500.0, 2.61, 500.0, 330.65, 0.87, 328.04]], "area": 163375.9216, "iscrowd": 0, "image_id": 226966, "bbox": [0.87, 0.87, 499.13, 329.78], "category_id": 67, "id": 2194340, "split": "val", "sentences": [{"tokens": ["an", "open", "sandwich"], "raw": "An open sandwich", "sent_id": 62768, "sent": "an open sandwich"}, {"tokens": ["open", "sandwich", "on", "a", "blue", "plate"], "raw": "open sandwich on a blue plate", "sent_id": 62769, "sent": "open sandwich on a blue plate"}], "file_name": "COCO_train2014_000000226966_2194340.jpg", "ann_id": 2194340, "sent_ids": [62768, 62769], "ref_id": 29100}, {"segmentation": [[486.36, 416.47, 517.0, 376.26, 533.27, 361.9, 536.14, 296.79, 528.48, 269.99, 529.44, 251.8, 497.85, 250.84, 488.27, 242.22, 481.57, 218.29, 477.74, 202.97, 467.21, 187.65, 476.78, 166.59, 482.53, 129.25, 463.38, 130.21, 475.83, 107.23, 550.5, 80.42, 597.42, 90.95, 623.27, 113.93, 629.01, 178.08, 628.05, 197.22, 638.59, 204.88, 639.54, 422.21, 481.57, 421.26, 482.53, 418.38]], "area": 43863.738450000004, "iscrowd": 0, "image_id": 80472, "bbox": [463.38, 80.42, 176.16, 341.79], "category_id": 1, "id": 432846, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "brown", "hair", "in", "a", "dark", "green", "shirt"], "raw": "A man with brown hair in a dark green shirt.", "sent_id": 62808, "sent": "a man with brown hair in a dark green shirt"}, {"tokens": ["a", "man", "wearing", "a", "brown", "shirt", "and", "making", "a", "funny", "face"], "raw": "A man wearing a brown shirt and making a funny face.", "sent_id": 62809, "sent": "a man wearing a brown shirt and making a funny face"}], "file_name": "COCO_train2014_000000080472_432846.jpg", "ann_id": 432846, "sent_ids": [62808, 62809], "ref_id": 29113}, {"segmentation": [[81.61, 421.89, 118.84, 360.33, 137.45, 337.42, 151.77, 325.97, 171.81, 323.1, 191.86, 325.97, 201.88, 330.26, 204.74, 344.58, 194.72, 377.51, 160.36, 457.69, 143.18, 483.46, 110.25, 526.41, 91.63, 542.16, 75.88, 543.59, 58.7, 537.87, 57.27, 507.8, 58.7, 472.01, 60.13, 463.42, 57.27, 454.82, 65.86, 446.23, 70.16, 440.51]], "area": 17377.601099999993, "iscrowd": 0, "image_id": 50410, "bbox": [57.27, 323.1, 147.47, 220.49], "category_id": 42, "id": 653028, "split": "val", "sentences": [{"tokens": ["white", "surfboard", "laying", "in", "the", "sand", "with", "black", "straps", "on", "it"], "raw": "White surfboard laying in the sand with black straps on it.", "sent_id": 62871, "sent": "white surfboard laying in the sand with black straps on it"}, {"tokens": ["a", "white", "surfboard", "with", "a", "greenish", "-", "yellow", "striped", "design", "at", "the", "end"], "raw": "A white surfboard with a greenish-yellow striped design at the end.", "sent_id": 62872, "sent": "a white surfboard with a greenish - yellow striped design at the end"}], "file_name": "COCO_train2014_000000050410_653028.jpg", "ann_id": 653028, "sent_ids": [62871, 62872], "ref_id": 29137}, {"segmentation": [[281.67, 349.78, 283.35, 298.49, 266.54, 257.29, 248.04, 253.08, 265.7, 212.72, 257.29, 200.11, 267.38, 175.73, 278.31, 163.12, 287.56, 159.75, 282.51, 144.62, 290.08, 127.8, 290.08, 118.55, 304.37, 116.03, 321.19, 132.85, 324.55, 141.26, 320.35, 163.12, 341.37, 176.57, 347.25, 214.41, 334.64, 233.74, 325.39, 304.37, 346.41, 341.37, 282.51, 361.55]], "area": 13941.4504, "iscrowd": 0, "image_id": 311706, "bbox": [248.04, 116.03, 99.21, 245.52], "category_id": 1, "id": 201062, "split": "val", "sentences": [{"tokens": ["man", "in", "green", "long", "sleeved", "shirt", "with", "light", "blue", "denim", "pants"], "raw": "Man in green long sleeved shirt with light blue denim pants.", "sent_id": 62895, "sent": "man in green long sleeved shirt with light blue denim pants"}, {"tokens": ["a", "man", "with", "a", "beard", "playing", "the", "wii"], "raw": "A man with a beard playing the wii.", "sent_id": 62896, "sent": "a man with a beard playing the wii"}], "file_name": "COCO_train2014_000000311706_201062.jpg", "ann_id": 201062, "sent_ids": [62895, 62896], "ref_id": 29149}, {"segmentation": [[271.82, 388.69, 149.63, 389.57, 143.43, 373.64, 108.02, 383.38, 87.65, 377.18, 85.0, 363.9, 112.44, 320.51, 123.07, 319.63, 112.44, 305.46, 124.84, 281.56, 156.71, 268.27, 179.73, 270.93, 185.93, 297.49, 188.59, 290.41, 212.49, 297.49, 277.13, 325.82, 285.1, 336.45, 270.93, 347.96, 235.51, 347.96, 221.35, 346.19, 227.55, 370.09, 247.02, 361.24, 272.7, 374.52, 280.67, 385.15]], "area": 15311.930399999996, "iscrowd": 0, "image_id": 56677, "bbox": [85.0, 268.27, 200.1, 121.3], "category_id": 1, "id": 514574, "split": "val", "sentences": [{"tokens": ["a", "child", "looks", "up", "at", "an", "older", "female", "while", "sitting", "on", "a", "chair"], "raw": "A child looks up at an older female while sitting on a chair.", "sent_id": 62920, "sent": "a child looks up at an older female while sitting on a chair"}, {"tokens": ["a", "child", "sitting", "on", "a", "chair", "with", "a", "blue", "shirt", "on"], "raw": "A child sitting on a chair with a blue shirt on", "sent_id": 62921, "sent": "a child sitting on a chair with a blue shirt on"}], "file_name": "COCO_train2014_000000056677_514574.jpg", "ann_id": 514574, "sent_ids": [62920, 62921], "ref_id": 29159}, {"segmentation": [[241.86, 226.26, 232.95, 149.35, 216.23, 59.07, 212.89, 142.67, 157.16, 167.19, 173.88, 205.08], [284.22, 207.31, 297.59, 198.4, 338.83, 61.3, 358.9, 57.96, 348.86, 16.72, 248.55, 28.98]], "area": 16197.749849999997, "iscrowd": 0, "image_id": 10870, "bbox": [157.16, 16.72, 201.74, 209.54], "category_id": 73, "id": 2134523, "split": "val", "sentences": [{"tokens": ["the", "laptop", "behind", "the", "beer", "bottle"], "raw": "The laptop behind the beer bottle.", "sent_id": 62981, "sent": "the laptop behind the beer bottle"}, {"tokens": ["a", "laptop", "with", "a", "blank", "screen"], "raw": "A laptop with a blank screen.", "sent_id": 62982, "sent": "a laptop with a blank screen"}], "file_name": "COCO_train2014_000000010870_2134523.jpg", "ann_id": 2134523, "sent_ids": [62981, 62982], "ref_id": 29181}, {"segmentation": [[597.51, 1.11, 601.93, 80.77, 596.4, 163.76, 590.87, 142.74, 567.63, 152.7, 568.74, 189.21, 566.52, 222.41, 566.52, 279.94, 593.08, 305.39, 611.89, 318.67, 619.64, 344.12, 604.15, 419.36, 640.0, 420.47, 640.0, 4.43]], "area": 20191.086700000007, "iscrowd": 0, "image_id": 218734, "bbox": [566.52, 1.11, 73.48, 419.36], "category_id": 1, "id": 2157065, "split": "val", "sentences": [{"tokens": ["an", "arm", "with", "bracelets", "on", "it"], "raw": "An arm with bracelets on it.", "sent_id": 63116, "sent": "an arm with bracelets on it"}, {"tokens": ["a", "womans", "arm"], "raw": "a womans arm", "sent_id": 63117, "sent": "a womans arm"}], "file_name": "COCO_train2014_000000218734_2157065.jpg", "ann_id": 2157065, "sent_ids": [63116, 63117], "ref_id": 29237}, {"segmentation": [[53.48, 419.27, 59.21, 395.39, 98.37, 355.28, 187.19, 309.44, 213.93, 274.1, 252.13, 263.6, 331.4, 260.73, 410.67, 239.72, 440.28, 213.93, 467.02, 204.38, 455.56, 193.88, 464.16, 187.19, 504.27, 200.56, 531.01, 216.8, 560.62, 235.9, 551.07, 250.22, 517.64, 242.58, 490.9, 253.09, 459.38, 261.69, 387.75, 309.44, 306.57, 339.04, 290.34, 358.15, 307.53, 385.84, 295.11, 420.22]], "area": 40801.1527, "iscrowd": 0, "image_id": 298956, "bbox": [53.48, 187.19, 507.14, 233.03], "category_id": 25, "id": 598470, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "with", "a", "lowered", "head", "watching", "the", "higher", "giraffe", "eat"], "raw": "a giraffe with a lowered head watching the higher giraffe eat", "sent_id": 63190, "sent": "a giraffe with a lowered head watching the higher giraffe eat"}, {"tokens": ["the", "shorter", "giraffe", "with", "it", "'", "s", "eyes", "closed", "standing", "in", "front", "of", "a", "taller", "giraffe"], "raw": "The shorter giraffe  with it's eyes closed standing in front of a taller giraffe.", "sent_id": 63191, "sent": "the shorter giraffe with it ' s eyes closed standing in front of a taller giraffe"}], "file_name": "COCO_train2014_000000298956_598470.jpg", "ann_id": 598470, "sent_ids": [63190, 63191], "ref_id": 29267}, {"segmentation": [[79.21, 385.79, 104.37, 321.49, 136.05, 280.49, 199.42, 236.69, 212.47, 236.69, 232.04, 252.54, 249.74, 255.33, 253.47, 263.72, 218.06, 288.88, 202.22, 303.79, 175.19, 310.31, 164.94, 331.75, 177.99, 324.29, 198.49, 322.43, 218.99, 301.93, 232.04, 302.86, 249.74, 282.36, 287.02, 294.47, 299.13, 295.4, 327.09, 285.15, 329.88, 268.38, 363.43, 262.79, 374.61, 281.42, 420.27, 307.52, 433.32, 294.47, 497.62, 275.83, 583.35, 255.33, 633.67, 273.04, 638.33, 274.9, 640.0, 420.27, 18.64, 420.27, 35.41, 403.5, 84.8, 383.93]], "area": 79619.90549999998, "iscrowd": 0, "image_id": 61460, "bbox": [18.64, 236.69, 621.36, 183.58], "category_id": 1, "id": 485194, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "brons", "shirt", "and", "stipped", "skirt", "standing", "next", "to", "luggage"], "raw": "A person in a brons shirt and stipped skirt standing next to luggage.", "sent_id": 63204, "sent": "a person in a brons shirt and stipped skirt standing next to luggage"}], "file_name": "COCO_train2014_000000061460_485194.jpg", "ann_id": 485194, "sent_ids": [63204], "ref_id": 29272}, {"segmentation": [[231.64, 156.95, 223.38, 165.49, 225.3, 177.62, 226.41, 183.95, 230.54, 191.12, 227.23, 195.25, 223.38, 203.24, 220.62, 215.64, 222.0, 221.43, 228.89, 234.38, 234.95, 236.59, 239.36, 237.14, 242.66, 242.37, 245.42, 250.36, 242.39, 253.67, 247.35, 261.66, 250.93, 264.42, 253.69, 262.49, 250.66, 271.86, 252.03, 277.92, 256.44, 282.6, 259.75, 282.6, 264.16, 277.92, 264.16, 290.87, 267.74, 309.33, 270.77, 315.4, 271.05, 316.22, 275.46, 333.03, 287.86, 359.48, 291.16, 370.78, 291.99, 375.19, 292.27, 379.6, 288.96, 387.59, 283.17, 393.1, 284.55, 394.76, 302.46, 395.31, 306.04, 390.9, 309.35, 390.35, 317.62, 384.01, 308.25, 368.85, 300.81, 350.67, 300.26, 338.54, 293.37, 323.39, 290.34, 319.8, 292.82, 309.88, 295.3, 307.4, 296.4, 292.52, 299.71, 314.57, 302.46, 320.91, 307.42, 325.59, 315.41, 329.17, 324.23, 333.58, 331.67, 338.27, 334.43, 342.95, 337.18, 359.76, 338.83, 365.82, 343.52, 369.4, 349.58, 368.03, 355.92, 353.42, 352.34, 344.88, 350.68, 340.47, 352.89, 336.89, 350.96, 328.9, 348.2, 324.21, 339.66, 325.04, 332.22, 313.74, 320.92, 311.54, 320.65, 274.34, 320.65, 267.45, 316.51, 243.47, 307.7, 228.32, 298.88, 214.54, 288.13, 197.46, 277.39, 188.64, 261.13, 183.95, 255.89, 182.02, 258.65, 178.72, 249.55, 169.9, 250.93, 163.29, 245.42, 159.15, 243.22, 157.22, 232.19, 156.67]], "area": 12252.942749999998, "iscrowd": 0, "image_id": 97632, "bbox": [220.62, 156.67, 135.3, 238.64], "category_id": 1, "id": 491061, "split": "val", "sentences": [{"tokens": ["a", "tennis", "player", "with", "blue", "t", "-", "shirt", "&", "shorts", "in", "the", "court"], "raw": "A tennis player with blue T-shirt & shorts in the court", "sent_id": 63214, "sent": "a tennis player with blue t - shirt & shorts in the court"}, {"tokens": ["a", "man", "in", "blue", "and", "white", "playing", "tennis"], "raw": "A man in blue and white playing tennis.", "sent_id": 63215, "sent": "a man in blue and white playing tennis"}], "file_name": "COCO_train2014_000000097632_491061.jpg", "ann_id": 491061, "sent_ids": [63214, 63215], "ref_id": 29277}, {"segmentation": [[87.5, 434.38, 78.75, 283.13, 1.25, 289.38, 1.25, 363.13, 2.5, 424.38, 22.5, 383.13, 46.25, 384.38, 51.25, 370.63, 42.5, 360.63, 65.0, 353.13, 66.25, 473.13, 86.25, 473.13]], "area": 9621.875, "iscrowd": 0, "image_id": 553021, "bbox": [1.25, 283.13, 86.25, 190.0], "category_id": 62, "id": 1938282, "split": "val", "sentences": [{"tokens": ["the", "wooden", "chair", "to", "the", "left", "of", "the", "other", "chair"], "raw": "The wooden chair to the left of the other chair.", "sent_id": 63226, "sent": "the wooden chair to the left of the other chair"}, {"tokens": ["the", "head", "of", "a", "chair", "in", "front", "of", "the", "back", "porch", "door"], "raw": "The head of a chair in front of the back porch door", "sent_id": 63227, "sent": "the head of a chair in front of the back porch door"}], "file_name": "COCO_train2014_000000553021_1938282.jpg", "ann_id": 1938282, "sent_ids": [63226, 63227], "ref_id": 29281}, {"segmentation": [[151.46, 308.72, 152.65, 305.14, 150.27, 303.55, 130.79, 303.55, 126.81, 298.38, 129.99, 281.29, 143.11, 247.9, 149.08, 236.37, 149.87, 220.86, 149.47, 216.49, 156.63, 212.12, 156.23, 206.55, 157.82, 185.48, 156.23, 178.72, 155.04, 172.76, 157.03, 164.01, 158.62, 158.84, 159.01, 154.07, 159.01, 148.11, 171.74, 156.06, 185.65, 164.01, 198.37, 167.19, 221.83, 166.0, 229.78, 164.81, 246.87, 166.79, 251.65, 164.01, 249.66, 160.04, 240.51, 157.25, 247.27, 154.07, 244.49, 151.69, 238.92, 150.89, 239.32, 146.12, 231.77, 149.7, 227.79, 153.67, 194.0, 151.69, 186.84, 146.52, 177.3, 138.57, 168.16, 131.41, 170.15, 128.63, 186.84, 133.0, 197.18, 137.37, 199.17, 136.18, 196.39, 132.6, 194.79, 128.23, 196.78, 125.45, 197.18, 123.06, 195.59, 118.69, 193.6, 118.69, 186.84, 123.46, 183.27, 123.86, 173.72, 119.48, 171.34, 117.89, 170.15, 105.97, 173.72, 103.58, 174.92, 99.61, 176.9, 96.03, 176.51, 87.68, 176.51, 80.92, 177.3, 72.18, 172.53, 63.83, 162.99, 59.06, 155.04, 58.26, 149.47, 60.65, 146.29, 65.42, 143.91, 69.39, 143.11, 75.36, 142.32, 79.73, 141.12, 84.9, 135.96, 94.04, 132.38, 101.99, 129.2, 115.51, 124.83, 129.82, 122.04, 143.34, 118.07, 152.88, 111.31, 163.61, 110.12, 185.88, 109.72, 202.57, 111.31, 224.04, 117.27, 222.45, 120.85, 223.25, 123.63, 235.97, 117.67, 259.82, 112.5, 270.56, 111.31, 292.82, 110.12, 306.73, 102.96, 323.43, 104.15, 331.38, 113.69, 333.77, 127.21, 338.94, 137.55, 340.92, 141.92, 338.94, 141.12, 336.55, 132.78, 327.41, 122.44, 319.46, 122.44, 314.29, 129.6, 311.5, 138.74, 310.71, 145.1, 310.31, 150.27, 309.52, 153.05, 308.72]], "area": 11063.73345, "iscrowd": 0, "image_id": 176179, "bbox": [102.96, 58.26, 148.69, 282.66], "category_id": 1, "id": 480943, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "cloth", "washing", "an", "elephant"], "raw": "A man in a red cloth washing an elephant.", "sent_id": 63294, "sent": "a man in a red cloth washing an elephant"}, {"tokens": ["a", "man", "in", "red", "shorts", "scrubbing", "an", "elephant", "'", "s", "trunk"], "raw": "A man in red shorts scrubbing an elephant's trunk.", "sent_id": 63295, "sent": "a man in red shorts scrubbing an elephant ' s trunk"}], "file_name": "COCO_train2014_000000176179_480943.jpg", "ann_id": 480943, "sent_ids": [63294, 63295], "ref_id": 29312}, {"segmentation": [[391.81, 458.79, 436.54, 460.15, 475.17, 461.5, 502.96, 462.86, 538.87, 464.89, 559.2, 464.89, 580.21, 465.57, 595.12, 466.92, 600.54, 464.21, 599.87, 458.79, 591.06, 456.08, 570.73, 456.08, 544.3, 454.72, 542.26, 460.15, 521.25, 460.82, 504.99, 458.79, 492.11, 458.11, 467.04, 456.76, 452.13, 454.72, 447.39, 450.66, 425.02, 449.98, 403.34, 447.95, 393.85, 446.59, 380.29, 442.53, 368.77, 440.49, 366.74, 443.88, 370.81, 449.98, 381.65, 457.44, 391.82, 458.79], [437.22, 407.96, 420.28, 410.67, 397.91, 411.35, 386.39, 411.35, 374.2, 410.0, 368.1, 410.0, 368.1, 414.06, 376.23, 421.52, 385.04, 424.23, 411.47, 420.16, 439.25, 418.13, 475.85, 413.39, 487.37, 413.39, 484.66, 410.0, 469.75, 411.35, 451.45, 412.03, 443.32, 412.03, 438.58, 410.0, 437.22, 407.96], [517.87, 397.12, 521.25, 407.29, 521.93, 410.0, 538.87, 410.0, 551.07, 408.64, 557.17, 404.58, 550.39, 399.83, 541.58, 398.48, 526.68, 398.48, 520.58, 398.48]], "area": 3108.409399999999, "iscrowd": 0, "image_id": 430555, "bbox": [366.74, 397.12, 233.8, 69.8], "category_id": 35, "id": 608516, "split": "val", "sentences": [{"tokens": ["the", "smaller", "white", "skis"], "raw": "the smaller white skis", "sent_id": 63312, "sent": "the smaller white skis"}], "file_name": "COCO_train2014_000000430555_608516.jpg", "ann_id": 608516, "sent_ids": [63312], "ref_id": 29319}, {"segmentation": [[0.0, 268.04, 84.84, 260.44, 125.29, 259.45, 173.63, 246.63, 168.69, 101.61, 155.87, 96.68, 2.96, 55.24, 1.97, 56.23]], "area": 31044.031549999996, "iscrowd": 0, "image_id": 44960, "bbox": [0.0, 55.24, 173.63, 212.8], "category_id": 6, "id": 166332, "split": "val", "sentences": [{"tokens": ["the", "bus", "that", "is", "almost", "out", "of", "view"], "raw": "The bus that is almost out of view.", "sent_id": 63351, "sent": "the bus that is almost out of view"}], "file_name": "COCO_train2014_000000044960_166332.jpg", "ann_id": 166332, "sent_ids": [63351], "ref_id": 29335}, {"segmentation": [[318.2, 134.83, 412.04, 129.44, 412.04, 129.44, 414.2, 127.28, 416.36, 141.3, 424.99, 115.42, 511.28, 102.47, 558.74, 96.0, 560.9, 85.21, 573.84, 86.29, 605.12, 90.61, 605.12, 96.0, 619.15, 104.63, 621.3, 125.12, 640.0, 173.66, 640.0, 257.8, 604.04, 276.13, 586.79, 276.13, 587.87, 267.51, 563.06, 266.43, 547.96, 283.69, 544.72, 267.51, 531.78, 253.48, 539.33, 225.44, 516.67, 229.75, 497.26, 212.49, 484.31, 202.79, 477.84, 213.57, 420.67, 202.79, 424.99, 193.08, 423.91, 177.98, 371.06, 177.98, 348.4, 168.27, 319.28, 170.43, 305.26, 163.96, 302.02, 134.83]], "area": 34236.63854999999, "iscrowd": 0, "image_id": 7852, "bbox": [302.02, 85.21, 337.98, 198.48], "category_id": 8, "id": 395111, "split": "val", "sentences": [{"tokens": ["firetruck", "in", "the", "right", "hand", "picture"], "raw": "firetruck in the right hand picture", "sent_id": 63368, "sent": "firetruck in the right hand picture"}, {"tokens": ["the", "red", "fire", "truck", "furthest", "to", "the", "right"], "raw": "The red fire truck furthest to the right.", "sent_id": 63369, "sent": "the red fire truck furthest to the right"}], "file_name": "COCO_train2014_000000007852_395111.jpg", "ann_id": 395111, "sent_ids": [63368, 63369], "ref_id": 29343}, {"segmentation": [[306.4, 485.51, 293.51, 489.8, 284.92, 491.23, 286.35, 448.28, 283.49, 406.76, 276.33, 403.9, 276.33, 386.72, 279.19, 355.22, 279.19, 340.9, 286.35, 323.72, 296.38, 299.38, 293.51, 266.45, 289.22, 240.68, 302.1, 224.93, 296.38, 219.2, 293.51, 206.31, 292.08, 196.29, 293.51, 181.97, 309.26, 164.79, 325.01, 163.36, 333.6, 177.68, 337.9, 189.13, 340.76, 203.45, 335.03, 213.47, 342.19, 223.49, 360.81, 227.79, 376.55, 232.08, 390.87, 244.97, 412.35, 275.04, 423.8, 295.08, 416.64, 299.38, 430.96, 325.15, 439.55, 375.26, 428.1, 391.01, 419.51, 386.72, 419.51, 372.4, 413.78, 376.69, 412.35, 362.38, 415.21, 345.19, 399.46, 316.56, 395.17, 312.26, 386.58, 315.13, 385.15, 303.67, 379.42, 310.83, 390.87, 406.76, 395.17, 435.4, 405.19, 482.64, 386.58, 479.78, 386.58, 485.51, 388.01, 519.87, 395.17, 547.07, 413.78, 552.8, 409.49, 575.71, 379.42, 565.69, 365.1, 537.05, 366.53, 509.85, 356.51, 488.37, 350.78, 478.35, 340.76, 458.3, 342.19, 481.21, 340.76, 494.1, 342.19, 506.98, 340.76, 537.05, 333.6, 562.82, 320.72, 577.14, 306.4, 567.12, 316.42, 542.78, 316.42, 519.87, 307.83, 484.08]], "area": 36927.18970000001, "iscrowd": 0, "image_id": 483766, "bbox": [276.33, 163.36, 163.22, 413.78], "category_id": 1, "id": 449847, "split": "val", "sentences": [{"tokens": ["a", "boy", "with", "a", "beige", "shirt"], "raw": "A boy with a beige shirt.", "sent_id": 63387, "sent": "a boy with a beige shirt"}, {"tokens": ["a", "boy", "in", "a", "tan", "tshirt", "that", "says", "dickies"], "raw": "a boy in a tan tshirt that says dickies", "sent_id": 63388, "sent": "a boy in a tan tshirt that says dickies"}], "file_name": "COCO_train2014_000000483766_449847.jpg", "ann_id": 449847, "sent_ids": [63387, 63388], "ref_id": 29352}, {"segmentation": [[384.79, 423.2, 342.21, 425.61, 340.61, 436.86, 342.21, 447.31, 343.02, 453.73, 346.23, 456.15, 345.43, 463.38, 335.78, 523.63, 343.02, 527.65, 347.03, 524.44, 352.66, 481.86, 356.67, 495.51, 359.89, 516.4, 362.3, 530.06, 365.51, 540.51, 370.33, 544.52, 370.33, 563.0, 370.33, 579.07, 370.33, 591.93, 371.14, 601.57, 377.56, 614.42, 379.97, 619.24, 381.58, 631.3, 381.58, 637.72, 425.77, 638.53, 424.16, 487.48, 406.49, 456.95, 399.26, 437.67, 392.03, 424.01]], "area": 12984.402750000003, "iscrowd": 0, "image_id": 568962, "bbox": [335.78, 423.2, 89.99, 215.33], "category_id": 15, "id": 1392702, "split": "val", "sentences": [{"tokens": ["the", "bench", "with", "no", "one", "sitting", "on", "it"], "raw": "The bench with no one sitting on it", "sent_id": 63435, "sent": "the bench with no one sitting on it"}, {"tokens": ["unoccupied", "bench"], "raw": "Unoccupied bench.", "sent_id": 63436, "sent": "unoccupied bench"}], "file_name": "COCO_train2014_000000568962_1392702.jpg", "ann_id": 1392702, "sent_ids": [63435, 63436], "ref_id": 29370}, {"segmentation": [[245.96, 157.36, 310.88, 162.84, 340.14, 166.5, 372.14, 197.59, 352.02, 235.08, 356.6, 272.56, 332.82, 265.25, 329.16, 250.62, 318.19, 258.85, 320.02, 268.91, 302.65, 257.02, 301.73, 241.48, 295.33, 227.76, 295.33, 227.76, 278.88, 241.48, 298.08, 286.28, 278.88, 281.71, 265.16, 235.99, 234.99, 245.13, 227.67, 263.42, 206.64, 261.59, 219.44, 221.36]], "area": 12425.404149999995, "iscrowd": 0, "image_id": 349408, "bbox": [206.64, 157.36, 165.5, 128.92], "category_id": 21, "id": 75367, "split": "val", "sentences": [{"tokens": ["calf", "is", "trying", "to"], "raw": "calf is trying to", "sent_id": 63520, "sent": "calf is trying to"}, {"tokens": ["brown", "calf", "sucking", "milk", "from", "mother", "cow"], "raw": "brown calf sucking milk from mother cow", "sent_id": 63521, "sent": "brown calf sucking milk from mother cow"}], "file_name": "COCO_train2014_000000349408_75367.jpg", "ann_id": 75367, "sent_ids": [63520, 63521], "ref_id": 29403}, {"segmentation": [[273.02, 177.43, 286.26, 173.74, 287.27, 163.01, 290.62, 157.81, 299.01, 156.47, 308.06, 159.99, 312.59, 167.87, 311.92, 174.08, 319.47, 178.1, 325.17, 188.66, 331.37, 199.23, 348.64, 235.64, 353.67, 239.66, 362.9, 242.18, 366.92, 246.37, 362.73, 246.37, 359.04, 246.2, 357.03, 246.71, 358.7, 249.22, 359.21, 250.9, 356.52, 251.4, 352.83, 249.89, 346.29, 244.53, 336.57, 228.43, 326.17, 209.99, 321.81, 210.99, 318.12, 207.13, 314.27, 200.26, 306.72, 217.53, 305.21, 224.41, 307.22, 241.92, 305.88, 250.3, 261.28, 254.16, 261.78, 229.17, 261.28, 216.6, 257.93, 220.62, 253.4, 236.72, 248.7, 253.15, 246.69, 257.68, 242.5, 263.84, 236.97, 264.34, 234.45, 263.67, 238.31, 260.82, 230.26, 260.15, 224.05, 260.31, 224.05, 257.63, 232.27, 255.96, 240.49, 252.43, 244.01, 243.55, 243.51, 234.49, 248.37, 217.32, 251.39, 210.78, 250.88, 209.77, 255.41, 199.37, 261.45, 191.16, 268.99, 178.8]], "area": 5574.115, "iscrowd": 0, "image_id": 476651, "bbox": [224.05, 156.47, 142.87, 107.87], "category_id": 1, "id": 445747, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "t", "-", "shirt", "with", "both", "of", "his", "hands", "on", "a", "tennis", "net"], "raw": "A man in a white t-shirt with both of his hands on a tennis net.", "sent_id": 63560, "sent": "a man in a white t - shirt with both of his hands on a tennis net"}, {"tokens": ["man", "without", "racket"], "raw": "man without racket", "sent_id": 63561, "sent": "man without racket"}], "file_name": "COCO_train2014_000000476651_445747.jpg", "ann_id": 445747, "sent_ids": [63560, 63561], "ref_id": 29418}, {"segmentation": [[202.95, 3.83, 267.09, 20.1, 290.06, 36.38, 301.55, 90.94, 263.26, 77.54, 221.14, 87.11, 198.16, 128.28, 198.16, 154.13, 187.63, 188.59, 184.76, 278.58, 194.33, 309.21, 175.19, 368.56, 174.23, 396.32, 164.66, 403.98, 82.33, 417.38, 0.96, 414.51, 0.0, 3.83, 191.46, 0.0]], "area": 84834.3028, "iscrowd": 0, "image_id": 568725, "bbox": [0.0, 0.0, 301.55, 417.38], "category_id": 3, "id": 242699, "split": "val", "sentences": [{"tokens": ["a", "red", "box", "behind", "the", "teddy", "bear"], "raw": "A red box behind the teddy bear", "sent_id": 63584, "sent": "a red box behind the teddy bear"}, {"tokens": ["the", "front", "of", "the", "red", "truck", "that", "the", "bear", "is", "leaning", "up", "against"], "raw": "The front of the red truck that the bear is leaning up against", "sent_id": 63585, "sent": "the front of the red truck that the bear is leaning up against"}], "file_name": "COCO_train2014_000000568725_242699.jpg", "ann_id": 242699, "sent_ids": [63584, 63585], "ref_id": 29425}, {"segmentation": [[412.89, 231.62, 381.68, 200.4, 339.38, 182.28, 311.18, 179.26, 261.84, 189.33, 222.56, 217.52, 229.61, 242.7, 212.49, 288.02, 222.56, 298.09, 239.68, 288.02, 293.05, 277.95, 296.08, 283.99, 300.1, 283.99, 310.17, 266.87, 335.35, 259.82, 412.89, 238.67, 412.89, 231.62]], "area": 13857.713199999997, "iscrowd": 0, "image_id": 9185, "bbox": [212.49, 179.26, 200.4, 118.83], "category_id": 53, "id": 1048000, "split": "val", "sentences": [{"tokens": ["an", "apple", "in", "the", "center", "of", "oranges"], "raw": "An apple in the center of oranges.", "sent_id": 63686, "sent": "an apple in the center of oranges"}, {"tokens": ["the", "apple", "in", "the", "middle"], "raw": "The apple in the middle.", "sent_id": 63687, "sent": "the apple in the middle"}], "file_name": "COCO_train2014_000000009185_1048000.jpg", "ann_id": 1048000, "sent_ids": [63686, 63687], "ref_id": 29463}, {"segmentation": [[54.41, 419.65, 78.75, 330.88, 123.13, 276.47, 117.4, 254.99, 111.68, 169.09, 88.77, 180.54, 71.59, 180.54, 105.95, 120.41, 126.0, 156.2, 140.31, 210.61, 170.38, 300.81, 193.29, 355.22, 186.13, 402.46, 170.38, 461.17, 204.74, 598.62, 187.56, 600.05, 170.38, 539.91, 160.36, 419.65, 141.74, 431.1, 121.7, 524.17, 131.72, 594.32, 131.72, 620.09, 114.54, 620.09, 101.66, 531.32, 100.22, 565.69, 98.79, 590.03, 81.61, 502.69, 75.88, 602.91, 57.27, 614.37, 70.16, 519.87]], "area": 33204.28355000001, "iscrowd": 0, "image_id": 466790, "bbox": [54.41, 120.41, 150.33, 499.68], "category_id": 25, "id": 596147, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "looking", "to", "the", "left"], "raw": "A giraffe looking to the left.", "sent_id": 63688, "sent": "a giraffe looking to the left"}, {"tokens": ["giraffe", "with", "its", "back", "to", "the", "camera", "looking", "left"], "raw": "Giraffe with its back to the camera looking left", "sent_id": 63689, "sent": "giraffe with its back to the camera looking left"}], "file_name": "COCO_train2014_000000466790_596147.jpg", "ann_id": 596147, "sent_ids": [63688, 63689], "ref_id": 29464}, {"segmentation": [[4.26, 176.49, 52.95, 178.93, 71.82, 176.49, 67.55, 187.45, 63.9, 207.53, 69.99, 225.18, 79.12, 238.57, 90.68, 249.53, 100.42, 252.57, 111.37, 255.0, 128.42, 255.0, 133.89, 254.4, 143.02, 250.74, 151.54, 246.48, 161.28, 237.96, 163.71, 228.23, 165.54, 225.79, 211.79, 225.79, 231.27, 228.23, 223.36, 229.44, 232.49, 241.01, 248.31, 244.05, 259.87, 237.35, 266.57, 223.97, 269.61, 216.66, 270.22, 205.71, 265.96, 197.19, 264.74, 189.28, 260.48, 182.58, 256.83, 172.84, 258.05, 158.24, 251.96, 152.76, 232.49, 122.33, 214.23, 91.29, 199.01, 76.68, 138.15, 31.04, 124.15, 40.78, 104.07, 30.43, 78.51, 31.04, 49.91, 31.65, 34.08, 37.73, 19.48, 41.99, 3.65, 48.69, 0.0, 50.51, 1.83, 177.1]], "area": 42904.25749999999, "iscrowd": 0, "image_id": 385066, "bbox": [0.0, 30.43, 270.22, 224.57], "category_id": 3, "id": 131864, "split": "val", "sentences": [{"tokens": ["red", "color", "car"], "raw": "red color car", "sent_id": 63696, "sent": "red color car"}, {"tokens": ["a", "red", "color", "car", "is", "on", "the", "road"], "raw": "A red color car is on the road.", "sent_id": 63697, "sent": "a red color car is on the road"}], "file_name": "COCO_train2014_000000385066_131864.jpg", "ann_id": 131864, "sent_ids": [63696, 63697], "ref_id": 29466}, {"segmentation": [[468.1, 557.0, 477.91, 536.71, 487.72, 521.79, 497.52, 519.23, 504.35, 508.99, 510.32, 500.47, 516.28, 493.64, 516.71, 489.38, 523.53, 474.88, 523.96, 465.08, 523.96, 455.27, 520.98, 447.59, 514.58, 441.63, 505.63, 434.8, 497.1, 427.98, 498.8, 422.86, 535.05, 427.13, 538.03, 427.13, 544.0, 432.25, 545.71, 436.51, 549.97, 451.43, 555.09, 457.83, 572.14, 458.25, 586.64, 456.12, 589.62, 453.14, 590.48, 448.87, 595.17, 445.46, 622.03, 462.52, 640.0, 480.43, 640.0, 540.97, 640.0, 557.0]], "area": 14820.239549999998, "iscrowd": 0, "image_id": 535358, "bbox": [468.1, 422.86, 171.9, 134.14], "category_id": 3, "id": 1776061, "split": "val", "sentences": [{"tokens": ["the", "car", "behind", "the", "horse"], "raw": "The car behind the horse", "sent_id": 63756, "sent": "the car behind the horse"}, {"tokens": ["the", "silver", "car", "behind", "the", "white", "horse"], "raw": "The silver car behind the white horse.", "sent_id": 63757, "sent": "the silver car behind the white horse"}], "file_name": "COCO_train2014_000000535358_1776061.jpg", "ann_id": 1776061, "sent_ids": [63756, 63757], "ref_id": 29487}, {"segmentation": [[50.34, 450.16, 51.78, 425.71, 50.34, 414.2, 54.65, 372.49, 61.84, 376.81, 90.61, 388.31, 145.26, 424.27, 152.45, 421.39, 159.64, 418.52, 174.02, 408.45, 197.03, 399.82, 198.47, 399.82, 215.73, 447.28, 232.99, 444.4, 248.81, 430.02, 258.88, 458.79, 140.94, 513.44, 113.62, 487.55, 106.43, 481.8, 90.61, 471.73, 80.54, 467.42, 74.79, 460.22, 58.97, 451.6]], "area": 14629.479000000008, "iscrowd": 0, "image_id": 158195, "bbox": [50.34, 372.49, 208.54, 140.95], "category_id": 73, "id": 1101144, "split": "val", "sentences": [{"tokens": ["laptop", "the", "person", "with", "black", "suit", "is", "operating"], "raw": "laptop the person with black suit is operating", "sent_id": 63984, "sent": "laptop the person with black suit is operating"}, {"tokens": ["a", "laptop", "that", "the", "man", "is", "using"], "raw": "A laptop that the man is using.", "sent_id": 63985, "sent": "a laptop that the man is using"}], "file_name": "COCO_train2014_000000158195_1101144.jpg", "ann_id": 1101144, "sent_ids": [63984, 63985], "ref_id": 29574}, {"segmentation": [[481.68, 238.52, 465.14, 262.85, 451.52, 288.15, 459.3, 324.15, 472.92, 369.89, 461.25, 388.38, 417.46, 393.24, 402.86, 392.27, 416.48, 377.67, 432.05, 353.35, 430.11, 328.05, 420.38, 288.15, 425.24, 253.12, 432.05, 234.63, 430.11, 226.84, 422.32, 220.03, 420.38, 198.62, 430.11, 182.08, 434.0, 167.49, 438.87, 142.19, 444.7, 125.64, 432.05, 117.86, 420.38, 100.34, 419.4, 78.93, 441.78, 71.15, 456.38, 60.45, 473.9, 47.8, 481.68, 43.9, 517.69, 55.58, 514.77, 62.39, 514.77, 88.67, 540.07, 98.4, 541.04, 107.15, 541.04, 124.67, 576.07, 141.21, 601.37, 126.62, 612.08, 127.59, 616.94, 139.27, 602.35, 157.75, 571.21, 159.7, 532.28, 162.62, 543.96, 182.08, 548.83, 209.33, 550.77, 228.79, 557.58, 254.09, 565.37, 279.39, 575.1, 295.93, 596.51, 331.94, 600.4, 339.72, 623.75, 370.86, 618.89, 381.57, 608.18, 387.41, 592.61, 377.67, 577.04, 361.13, 563.42, 332.91, 541.04, 293.01, 515.74, 253.12, 488.49, 243.39]], "area": 33001.31135000001, "iscrowd": 0, "image_id": 333546, "bbox": [402.86, 43.9, 220.89, 349.34], "category_id": 1, "id": 424576, "split": "val", "sentences": [{"tokens": ["right", "duplicate", "image", "of", "tennis", "player"], "raw": "right duplicate image of tennis player", "sent_id": 64074, "sent": "right duplicate image of tennis player"}, {"tokens": ["lady", "who", "is", "playing", "in", "the", "right", "side", "of", "the", "image"], "raw": "lady who is playing in the right side of the image", "sent_id": 64075, "sent": "lady who is playing in the right side of the image"}], "file_name": "COCO_train2014_000000333546_424576.jpg", "ann_id": 424576, "sent_ids": [64074, 64075], "ref_id": 29609}, {"segmentation": [[85.77, 186.09, 128.06, 181.25, 271.86, 175.82, 295.42, 175.82, 312.34, 182.46, 324.42, 196.36, 328.65, 223.55, 330.46, 262.82, 323.21, 280.95, 297.84, 296.65, 109.33, 304.51, 80.33, 299.68, 62.81, 281.55, 58.58, 262.82, 60.99, 203.0, 66.43, 191.52]], "area": 31447.681599999996, "iscrowd": 0, "image_id": 520100, "bbox": [58.58, 175.82, 271.88, 128.69], "category_id": 51, "id": 1041281, "split": "val", "sentences": [{"tokens": ["avocado", "chunks", "and", "several", "carrots"], "raw": "Avocado chunks and several carrots.", "sent_id": 64121, "sent": "avocado chunks and several carrots"}, {"tokens": ["a", "lunch", "box", "with", "carrot", "on", "middle", "and", "other", "vegetables", "on", "side"], "raw": "A lunch box with carrot on middle and other vegetables on side", "sent_id": 64122, "sent": "a lunch box with carrot on middle and other vegetables on side"}], "file_name": "COCO_train2014_000000520100_1041281.jpg", "ann_id": 1041281, "sent_ids": [64121, 64122], "ref_id": 29630}, {"segmentation": [[319.47, 321.39, 347.35, 338.55, 353.07, 335.69, 360.93, 344.27, 366.65, 316.39, 375.23, 322.11, 377.38, 352.13, 398.82, 334.26, 409.54, 344.98, 399.54, 367.14, 426.7, 390.02, 433.14, 390.02, 454.58, 415.04, 449.58, 427.19, 462.45, 454.36, 442.43, 450.07, 421.7, 423.62, 395.96, 396.45, 389.53, 398.6, 370.23, 376.44, 363.08, 367.86]], "area": 4805.407900000002, "iscrowd": 0, "image_id": 223459, "bbox": [319.47, 316.39, 142.98, 137.97], "category_id": 5, "id": 162388, "split": "val", "sentences": [{"tokens": ["a", "jet", "third", "from", "the", "right", "in", "a", "group", "of", "identical", "jets"], "raw": "A jet third from the right in a group of identical jets.", "sent_id": 64125, "sent": "a jet third from the right in a group of identical jets"}], "file_name": "COCO_train2014_000000223459_162388.jpg", "ann_id": 162388, "sent_ids": [64125], "ref_id": 29632}, {"segmentation": [[474.98, 102.38, 573.81, 63.04, 640.0, 8.34, 636.18, 125.41, 496.09, 118.69, 474.02, 107.18]], "area": 9208.783249999999, "iscrowd": 0, "image_id": 159957, "bbox": [474.02, 8.34, 165.98, 117.07], "category_id": 28, "id": 282720, "split": "val", "sentences": [{"tokens": ["the", "rightmost", "sun", "blocker"], "raw": "the rightmost sun blocker", "sent_id": 64164, "sent": "the rightmost sun blocker"}, {"tokens": ["a", "hat", "which", "is", "at", "the", "right", "side", "of", "the", "other", "two", "hats"], "raw": "A hat which is at the right side of the other two hats.", "sent_id": 64165, "sent": "a hat which is at the right side of the other two hats"}], "file_name": "COCO_train2014_000000159957_282720.jpg", "ann_id": 282720, "sent_ids": [64164, 64165], "ref_id": 29648}, {"segmentation": [[435.9, 205.46, 432.29, 188.0, 432.29, 168.73, 428.07, 167.53, 425.66, 145.85, 429.28, 124.78, 426.27, 107.32, 438.91, 91.67, 459.98, 88.65, 497.31, 103.71, 513.57, 106.72, 531.63, 129.6, 546.08, 163.31, 550.89, 161.51, 550.29, 175.95, 555.11, 212.08, 550.29, 222.92, 531.63, 213.28, 521.39, 175.95, 518.38, 181.98, 523.8, 203.65, 534.64, 221.71, 524.4, 221.11, 515.97, 201.84, 504.53, 162.11, 495.5, 159.7, 490.69, 184.99, 488.88, 209.07, 494.3, 218.1, 485.27, 226.53, 478.65, 217.5, 481.05, 203.05, 483.46, 186.79, 481.05, 156.69, 459.98, 148.86, 446.74, 167.53, 445.53, 189.2, 456.37, 209.67, 443.73, 212.08]], "area": 9829.070899999999, "iscrowd": 0, "image_id": 309338, "bbox": [425.66, 88.65, 129.45, 137.88], "category_id": 24, "id": 589835, "split": "val", "sentences": [{"tokens": ["the", "zebra", "drinking", "out", "of", "the", "water", "by", "the", "twig", "visible", "in", "the", "picture"], "raw": "The zebra drinking out of the water by the twig visible in the picture.", "sent_id": 64182, "sent": "the zebra drinking out of the water by the twig visible in the picture"}, {"tokens": ["the", "zebra", "furthest", "to", "the", "right"], "raw": "The zebra furthest to the right", "sent_id": 64183, "sent": "the zebra furthest to the right"}], "file_name": "COCO_train2014_000000309338_589835.jpg", "ann_id": 589835, "sent_ids": [64182, 64183], "ref_id": 29656}, {"segmentation": [[243.54, 34.24, 370.85, 0.37, 435.74, 0.0, 599.78, 140.34, 640.0, 178.7, 639.77, 220.32, 640.0, 300.71, 640.0, 359.07, 418.6, 359.47, 416.15, 295.82, 440.23, 287.25, 492.87, 289.69, 498.58, 281.94, 507.15, 274.19, 534.08, 269.29, 551.63, 318.26, 552.45, 301.53, 566.32, 279.9, 581.83, 259.09, 583.87, 250.93, 570.81, 239.5, 581.01, 206.45, 581.83, 185.23, 576.93, 176.66, 572.03, 159.93, 568.77, 150.54, 559.38, 131.77, 551.22, 119.12, 541.02, 106.06, 538.57, 90.56, 531.23, 84.84, 526.74, 86.48, 505.93, 68.93, 485.93, 54.65, 465.53, 55.87, 439.0, 58.73, 425.54, 46.08, 419.01, 50.56, 414.11, 48.12, 385.14, 54.65, 374.94, 82.39, 356.57, 128.51, 353.31, 139.12, 343.11, 159.93, 339.43, 184.41, 336.99, 204.82, 322.29, 199.92, 329.64, 189.31, 323.93, 161.15, 319.44, 126.06, 314.13, 105.65, 303.52, 95.86, 258.23, 70.56, 245.99, 56.69, 243.94, 35.06]], "area": 43747.30765, "iscrowd": 0, "image_id": 246641, "bbox": [243.54, 0.0, 396.46, 359.47], "category_id": 67, "id": 1966344, "split": "val", "sentences": [{"tokens": ["right", "half", "of", "the", "table", "top", "undersandwhiches", "that", "have", "multiple", "children", "pictures", "under", "the", "glass", "of", "the", "top"], "raw": "Right Half of the Table Top undersandwhiches that have multiple children pictures under the glass of the top.", "sent_id": 64344, "sent": "right half of the table top undersandwhiches that have multiple children pictures under the glass of the top"}, {"tokens": ["this", "is", "a", "table", "with", "pictures", "of", "people", "on", "it"], "raw": "this is a table with pictures of people on it", "sent_id": 64345, "sent": "this is a table with pictures of people on it"}], "file_name": "COCO_train2014_000000246641_1966344.jpg", "ann_id": 1966344, "sent_ids": [64344, 64345], "ref_id": 29720}, {"segmentation": [[432.67, 95.39, 470.79, 144.95, 498.43, 184.98, 539.41, 200.23, 598.5, 193.56, 594.68, 202.13, 530.83, 212.62, 417.42, 221.19, 409.8, 209.76, 400.27, 164.96, 384.07, 170.68, 373.58, 173.54, 362.15, 156.39, 367.87, 135.42, 367.87, 109.69, 375.49, 98.25, 363.1, 75.38, 368.82, 58.23, 381.21, 65.85, 392.64, 70.62, 405.03, 64.9, 410.75, 61.09, 424.09, 41.07, 431.72, 57.27, 430.77, 77.29, 427.91, 87.77]], "area": 14890.656900000004, "iscrowd": 0, "image_id": 366956, "bbox": [362.15, 41.07, 236.35, 180.12], "category_id": 24, "id": 591138, "split": "val", "sentences": [{"tokens": ["a", "zebra", "stares", "to", "the", "right", "of", "its", "companion"], "raw": "A zebra stares to the right of its companion.", "sent_id": 64352, "sent": "a zebra stares to the right of its companion"}, {"tokens": ["a", "zebra", "behind", "the", "other"], "raw": "a zebra behind the other", "sent_id": 64353, "sent": "a zebra behind the other"}], "file_name": "COCO_train2014_000000366956_591138.jpg", "ann_id": 591138, "sent_ids": [64352, 64353], "ref_id": 29723}, {"segmentation": [[2.89, 328.93, 1.92, 235.64, 241.41, 235.64, 237.56, 240.45, 233.72, 243.33, 226.02, 269.3, 247.18, 280.84, 213.52, 289.5, 202.94, 304.89, 206.79, 309.7, 249.11, 301.04, 251.03, 306.81, 285.65, 314.51, 287.58, 326.05, 207.75, 330.86, 213.52, 381.83, 223.14, 387.6, 209.67, 395.3, 181.78, 391.45, 176.01, 332.78, 32.7, 331.82, 32.7, 376.06, 23.08, 378.95, 21.16, 328.93, 0.96, 332.78], [347.21, 331.82, 382.8, 307.78, 399.15, 308.74, 402.03, 303.93, 390.49, 298.16, 385.68, 277.96, 379.91, 272.19, 377.99, 237.56, 424.15, 238.53, 425.11, 304.89, 427.04, 319.32, 413.57, 327.97, 390.49, 327.01, 392.41, 389.53, 374.14, 394.34, 373.18, 368.37, 374.14, 327.01, 359.71, 331.82]], "area": 30398.79745, "iscrowd": 0, "image_id": 189915, "bbox": [0.96, 235.64, 426.08, 159.66], "category_id": 15, "id": 576229, "split": "val", "sentences": [{"tokens": ["a", "bench", "with", "a", "woman", "in", "a", "blue", "sweater", "sitting", "on", "it"], "raw": "a bench with a woman in a blue sweater sitting on it", "sent_id": 64378, "sent": "a bench with a woman in a blue sweater sitting on it"}, {"tokens": ["black", "park", "bench", "woman", "holding", "book", "sitting", "on"], "raw": "black park bench woman holding book sitting on", "sent_id": 64379, "sent": "black park bench woman holding book sitting on"}], "file_name": "COCO_train2014_000000189915_576229.jpg", "ann_id": 576229, "sent_ids": [64378, 64379], "ref_id": 29735}, {"segmentation": [[257.51, 335.22, 283.53, 351.58, 301.38, 370.91, 322.94, 386.53, 337.81, 408.09, 357.88, 424.45, 369.04, 422.96, 387.63, 438.58, 406.96, 445.27, 412.91, 437.09, 411.42, 424.45, 389.11, 405.12, 378.7, 394.71, 362.35, 382.07, 344.5, 361.99, 331.86, 353.07, 323.68, 346.38, 302.12, 291.35, 295.43, 278.71, 290.97, 247.49, 299.89, 198.41, 311.04, 184.29, 320.71, 178.28, 309.55, 143.33, 293.94, 121.03, 286.5, 99.35, 275.35, 90.42, 260.48, 89.68, 250.07, 96.37, 223.3, 96.37, 218.84, 107.52, 213.64, 116.45, 220.33, 123.88, 222.56, 151.39, 157.13, 176.67, 125.9, 202.7, 106.57, 228.72, 127.39, 250.28, 137.05, 238.39, 140.03, 225.0, 148.95, 224.26, 138.54, 222.03, 161.59, 210.13, 172.0, 213.11, 180.18, 210.13, 208.43, 261.44, 208.43, 271.85, 206.2, 281.51, 196.54, 294.15, 172.74, 334.3, 155.64, 380.4, 143.75, 436.91, 150.44, 461.45, 128.13, 480.0, 171.26, 477.12, 180.18, 477.12, 176.46, 451.1, 181.67, 418.38, 191.33, 392.36, 205.46, 364.85, 227.77, 346.26, 246.35, 334.36]], "area": 38473.65630000002, "iscrowd": 0, "image_id": 449914, "bbox": [106.57, 89.68, 306.34, 390.32], "category_id": 1, "id": 427516, "split": "val", "sentences": [{"tokens": ["a", "giants", "pitcher", "strides", "forward", "to", "deliver", "the", "cocked", "-", "and", "-", "ready", "pitch", "from", "behind", "his", "head"], "raw": "A Giants pitcher strides forward to deliver the cocked-and-ready pitch from behind his head.", "sent_id": 64395, "sent": "a giants pitcher strides forward to deliver the cocked - and - ready pitch from behind his head"}, {"tokens": ["a", "pitcher", "for", "the", "giants", "professional", "base", "ball", "team", "wearing", "an", "orange", "and", "black", "jersey"], "raw": "A pitcher for the Giants professional base ball team wearing an orange and black jersey.", "sent_id": 64396, "sent": "a pitcher for the giants professional base ball team wearing an orange and black jersey"}], "file_name": "COCO_train2014_000000449914_427516.jpg", "ann_id": 427516, "sent_ids": [64395, 64396], "ref_id": 29741}, {"segmentation": [[242.45, 621.36, 224.43, 604.4, 215.41, 593.27, 207.99, 577.37, 209.05, 533.37, 208.52, 505.28, 210.11, 488.32, 238.74, 476.65, 242.45, 475.59, 251.46, 492.56, 260.47, 509.52, 284.85, 545.03, 286.97, 542.38, 296.52, 560.94, 303.94, 571.54, 301.82, 576.31, 295.46, 577.37, 291.21, 592.21, 283.79, 603.34, 282.73, 603.34, 285.91, 609.17, 284.32, 613.94, 279.55, 615.53, 272.13, 615.0, 270.01, 609.7]], "area": 9002.026350000002, "iscrowd": 0, "image_id": 202076, "bbox": [207.99, 475.59, 95.95, 145.77], "category_id": 33, "id": 1185691, "split": "val", "sentences": [{"tokens": ["the", "red", "luggage"], "raw": "the red luggage", "sent_id": 64443, "sent": "the red luggage"}, {"tokens": ["red", "suitcase"], "raw": "red suitcase", "sent_id": 64444, "sent": "red suitcase"}], "file_name": "COCO_train2014_000000202076_1185691.jpg", "ann_id": 1185691, "sent_ids": [64443, 64444], "ref_id": 29759}, {"segmentation": [[257.72, 144.0, 250.98, 172.85, 250.98, 190.16, 258.68, 228.63, 259.64, 255.55, 263.49, 260.36, 269.26, 261.32, 274.06, 281.52, 281.76, 295.94, 292.33, 302.67, 297.14, 309.4, 305.8, 339.21, 305.8, 389.22, 316.37, 391.14, 330.8, 387.29, 340.42, 384.41, 342.34, 368.06, 342.34, 351.71, 363.49, 313.25, 389.46, 313.25, 397.15, 363.25, 424.08, 352.68, 419.27, 328.64, 419.27, 314.21, 422.15, 293.06, 432.73, 288.25, 428.88, 345.94, 428.88, 352.68, 471.2, 328.64, 461.58, 309.4, 461.58, 297.86, 467.35, 275.75, 470.23, 262.28, 475.04, 247.86, 480.81, 252.67, 480.81, 260.36, 498.12, 286.32, 502.93, 240.17, 480.81, 203.62, 467.35, 180.55, 451.96, 158.43, 424.08, 151.7, 340.42, 169.01, 311.57, 153.62, 301.95, 144.97, 289.45, 131.5, 284.64, 126.69, 277.91, 118.04, 270.22, 117.08, 262.52, 127.66, 262.52, 136.31]], "area": 39742.2599, "iscrowd": 0, "image_id": 62263, "bbox": [250.98, 117.08, 251.95, 274.06], "category_id": 24, "id": 590610, "split": "val", "sentences": [{"tokens": ["a", "small", "baby", "zebra", "with", "black", "and", "white", "stripe"], "raw": "A small baby zebra with black and white stripe.", "sent_id": 64461, "sent": "a small baby zebra with black and white stripe"}, {"tokens": ["a", "zebra", "looking", "at", "the", "camera", "through", "the", "legs", "of", "an", "elephant"], "raw": "A zebra looking at the camera through the legs of an elephant", "sent_id": 64462, "sent": "a zebra looking at the camera through the legs of an elephant"}], "file_name": "COCO_train2014_000000062263_590610.jpg", "ann_id": 590610, "sent_ids": [64461, 64462], "ref_id": 29766}, {"segmentation": [[188.52, 165.5, 201.22, 165.5, 216.21, 167.13, 226.63, 169.08, 229.56, 169.41, 235.42, 175.59, 236.73, 179.18, 238.68, 172.99, 238.68, 169.73, 248.78, 171.36, 259.53, 171.36, 264.09, 175.92, 269.3, 178.85, 267.02, 173.64, 266.37, 170.71, 269.62, 171.03, 279.4, 170.71, 294.05, 169.08, 311.32, 167.78, 317.51, 157.35, 328.25, 150.19, 346.49, 141.39, 355.61, 138.79, 354.96, 135.2, 352.03, 131.95, 353.33, 128.04, 356.92, 129.34, 358.87, 132.27, 365.06, 133.9, 367.34, 130.97, 373.2, 132.92, 381.67, 138.46, 384.28, 141.72, 386.23, 142.04, 384.28, 145.63, 387.21, 150.51, 392.75, 158.33, 396.66, 162.24, 396.33, 167.45, 403.82, 182.43, 407.73, 193.83, 409.03, 201.65, 404.15, 208.82, 399.59, 210.45, 394.05, 210.45, 388.84, 209.14, 385.91, 205.23, 386.23, 202.95, 374.83, 193.83, 364.74, 188.3, 362.13, 188.62, 357.57, 196.44, 352.03, 202.95, 344.54, 209.14, 336.72, 216.64, 334.44, 223.15, 328.25, 234.22, 321.74, 240.09, 313.92, 252.79, 307.41, 265.82, 305.13, 281.78, 302.85, 288.29, 298.29, 295.79, 296.66, 299.04, 295.68, 300.67, 295.03, 295.13, 295.03, 294.16, 291.12, 298.07, 289.82, 301.65, 284.28, 305.56, 278.74, 306.86, 276.79, 306.86, 278.42, 299.04, 283.63, 290.9, 284.93, 281.45, 284.93, 278.85, 286.89, 270.05, 290.8, 258.65, 290.8, 252.79, 291.77, 248.88, 290.8, 247.25, 283.96, 246.93, 265.06, 252.14, 236.4, 253.12, 223.05, 247.25, 214.58, 243.02, 208.71, 254.74, 204.48, 267.12, 199.27, 277.55, 197.97, 290.9, 199.92, 303.6, 199.59, 304.91, 192.1, 305.56, 190.8, 304.58, 186.89, 293.18, 180.7, 286.34, 180.7, 278.85, 182.0, 273.64, 182.98, 269.73, 184.28, 262.56, 185.26, 254.74, 185.91, 252.46, 184.61, 249.86, 180.38, 255.72, 176.14, 260.28, 178.42, 262.89, 179.4, 267.12, 179.07, 272.99, 179.07, 275.92, 178.1, 276.89, 173.54, 274.61, 170.93, 272.01, 167.02, 281.13, 163.76, 289.6, 161.16, 296.11, 155.95, 299.04, 154.32, 297.41, 153.34, 289.6, 154.97, 285.04, 154.97, 283.08, 152.69, 280.48, 151.71, 278.85, 151.39, 270.71, 152.04, 264.84, 155.95, 260.28, 157.58, 257.35, 153.67, 249.53, 153.67, 238.78, 153.99, 227.38, 154.32, 213.38, 152.69, 203.93, 154.32, 196.44, 155.95, 185.37, 159.86, 180.81, 166.7, 175.27, 174.19, 171.03, 182.33, 167.13]], "area": 21512.96764999998, "iscrowd": 0, "image_id": 314725, "bbox": [151.39, 128.04, 257.64, 178.82], "category_id": 24, "id": 591017, "split": "val", "sentences": [{"tokens": ["a", "zebra", "with", "two", "birds", "perched", "on", "its", "side"], "raw": "A zebra with two birds perched on its side.", "sent_id": 64531, "sent": "a zebra with two birds perched on its side"}, {"tokens": ["a", "zebra", "with", "a", "bunch", "of", "birds", "hanging", "out", "on", "it", "'", "s", "back"], "raw": "A zebra with a bunch of birds hanging out on it's back.", "sent_id": 64532, "sent": "a zebra with a bunch of birds hanging out on it ' s back"}], "file_name": "COCO_train2014_000000314725_591017.jpg", "ann_id": 591017, "sent_ids": [64531, 64532], "ref_id": 29789}, {"segmentation": [[483.56, 183.0, 431.44, 170.8, 417.02, 153.05, 380.42, 150.84, 358.24, 146.4, 369.33, 158.6, 358.24, 169.69, 342.71, 177.45, 340.49, 177.45, 344.93, 194.09, 369.33, 198.53, 369.33, 230.69, 371.55, 242.89, 371.55, 249.55, 375.98, 268.4, 393.73, 271.73, 408.15, 273.95, 413.69, 277.27, 405.93, 288.36, 394.84, 293.91, 397.05, 303.89, 410.36, 309.44, 424.78, 306.11, 430.33, 305.0, 436.98, 289.47, 443.64, 287.25, 443.64, 308.33, 461.38, 308.33, 480.24, 320.53, 493.55, 322.75, 510.18, 312.76, 516.84, 291.69, 516.84, 289.47, 523.49, 296.13, 534.58, 297.24, 535.69, 289.47, 534.58, 279.49, 564.53, 275.05, 572.29, 270.62, 573.4, 262.85, 564.53, 261.75, 562.31, 261.75, 549.0, 268.4, 535.69, 269.51, 530.15, 269.51, 523.49, 255.09, 526.82, 236.24, 526.82, 219.6, 517.95, 197.42, 510.18, 190.76, 496.87, 185.22, 479.13, 180.78]], "area": 21466.23220000001, "iscrowd": 0, "image_id": 490507, "bbox": [340.49, 146.4, 232.91, 176.35], "category_id": 17, "id": 2066756, "split": "val", "sentences": [{"tokens": ["small", "orange", "kitten", "on", "the", "right"], "raw": "Small orange kitten on the right", "sent_id": 64533, "sent": "small orange kitten on the right"}, {"tokens": ["curious", "kitten", "closest", "to", "grabbing", "little", "bear", "looking", "for", "help"], "raw": "Curious kitten closest to grabbing little bear looking for help.", "sent_id": 64534, "sent": "curious kitten closest to grabbing little bear looking for help"}], "file_name": "COCO_train2014_000000490507_2066756.jpg", "ann_id": 2066756, "sent_ids": [64533, 64534], "ref_id": 29790}, {"segmentation": [[136.71, 309.52, 143.83, 293.86, 136.71, 254.72, 134.57, 233.37, 138.13, 206.33, 138.13, 178.58, 145.96, 173.59, 152.37, 173.59, 145.25, 172.17, 141.69, 166.48, 139.56, 162.21, 136.71, 167.19, 125.32, 165.77, 125.32, 171.46, 124.61, 180.71, 126.75, 186.4, 130.3, 186.4, 130.3, 207.75, 127.46, 237.64, 127.46, 238.35, 118.21, 254.01, 89.03, 267.53, 84.76, 288.88, 88.32, 307.38, 91.88, 327.31, 100.42, 347.95, 100.42, 397.05, 103.97, 397.05, 104.69, 381.39, 111.09, 352.22, 123.19, 321.62, 133.86, 306.67]], "area": 5038.779100000002, "iscrowd": 0, "image_id": 226527, "bbox": [84.76, 162.21, 67.61, 234.84], "category_id": 25, "id": 595347, "split": "val", "sentences": [{"tokens": ["a", "mother", "giraffe", "nursing", "her", "young"], "raw": "A mother giraffe nursing her young", "sent_id": 64625, "sent": "a mother giraffe nursing her young"}], "file_name": "COCO_train2014_000000226527_595347.jpg", "ann_id": 595347, "sent_ids": [64625], "ref_id": 29830}, {"segmentation": [[411.65, 328.84, 400.31, 277.37, 407.28, 272.14, 404.67, 244.22, 393.33, 278.24, 402.05, 229.39, 418.62, 212.82, 453.52, 197.99, 483.18, 180.54, 531.16, 157.87, 563.43, 129.08, 576.52, 125.59, 597.45, 158.74, 590.47, 163.09, 566.05, 156.12, 522.43, 201.48, 502.37, 218.92, 502.37, 237.25, 491.9, 260.8, 503.24, 343.66, 495.39, 341.05, 477.07, 279.11, 465.73, 309.65, 443.05, 342.8, 436.94, 336.69, 465.73, 293.08, 465.73, 261.67, 437.81, 259.05, 418.62, 283.48, 419.5, 341.93, 413.39, 341.93]], "area": 12312.9606, "iscrowd": 0, "image_id": 285000, "bbox": [393.33, 125.59, 204.12, 218.07], "category_id": 25, "id": 597581, "split": "val", "sentences": [{"tokens": ["giraffe", "walking", "while", "another", "giraffe", "follows", "it"], "raw": "Giraffe walking while another giraffe follows it.", "sent_id": 64626, "sent": "giraffe walking while another giraffe follows it"}, {"tokens": ["a", "walking", "giraff", "on", "the", "right", "side", "of", "the", "picture"], "raw": "A walking giraff on the right side of the picture.", "sent_id": 64627, "sent": "a walking giraff on the right side of the picture"}], "file_name": "COCO_train2014_000000285000_597581.jpg", "ann_id": 597581, "sent_ids": [64626, 64627], "ref_id": 29831}, {"segmentation": [[292.27, 255.86, 296.51, 290.31, 296.51, 315.76, 284.85, 320.0, 282.2, 336.96, 280.61, 345.97, 274.25, 349.68, 275.84, 376.18, 275.84, 401.1, 273.72, 427.6, 279.55, 446.15, 254.11, 450.4, 250.93, 461.0, 247.75, 480.61, 249.34, 497.04, 272.66, 515.06, 280.61, 524.61, 276.37, 530.44, 266.83, 533.09, 252.52, 529.91, 252.52, 541.04, 259.41, 556.94, 249.34, 561.18, 227.6, 563.3, 219.12, 552.17, 210.64, 540.51, 210.64, 527.26, 215.94, 512.41, 213.82, 497.57, 206.93, 468.95, 194.74, 465.24, 193.68, 444.03, 186.26, 358.69, 185.2, 341.73, 191.56, 322.65, 175.13, 308.87, 165.59, 276.0, 166.65, 242.08, 162.41, 230.94, 87.13, 210.27, 81.3, 200.73, 75.47, 204.97, 44.73, 192.25, 18.22, 182.18, 18.22, 180.06, 34.13, 179.53, 30.95, 171.05, 30.95, 163.09, 36.78, 164.15, 44.73, 174.76, 52.68, 172.64, 86.6, 176.88, 100.39, 178.47, 106.75, 176.88, 144.91, 179.0, 171.42, 169.99, 191.56, 174.23, 206.4, 166.81, 205.34, 160.97, 201.6, 157.84, 197.06, 144.2, 198.81, 131.26, 202.65, 116.57, 213.14, 106.08, 218.04, 106.08, 221.89, 111.68, 228.18, 107.13, 244.27, 112.72, 250.22, 130.21, 249.17, 152.24, 240.77, 168.33, 233.78, 174.62, 233.78, 179.87, 246.37, 182.67, 262.11, 195.61, 265.95, 199.1, 267.35, 197.36, 269.8, 201.9, 269.1, 208.55, 271.2, 210.3, 275.39, 213.44, 277.14, 217.64, 280.99, 219.74, 280.99, 224.63, 291.48, 252.26, 292.88, 264.15]], "area": 41084.68400000001, "iscrowd": 0, "image_id": 483766, "bbox": [18.22, 106.08, 278.29, 457.22], "category_id": 1, "id": 1719270, "split": "val", "sentences": [{"tokens": ["the", "boy", "wearing", "the", "blue", "striped", "hoodie", "sweatshirt"], "raw": "the boy wearing the blue striped hoodie sweatshirt", "sent_id": 64724, "sent": "the boy wearing the blue striped hoodie sweatshirt"}, {"tokens": ["a", "boy", "standing", "on", "a", "skateboard"], "raw": "A boy standing on a skateboard.", "sent_id": 64725, "sent": "a boy standing on a skateboard"}], "file_name": "COCO_train2014_000000483766_1719270.jpg", "ann_id": 1719270, "sent_ids": [64724, 64725], "ref_id": 29868}, {"segmentation": [[297.74, 355.46, 349.96, 368.28, 458.06, 377.45, 524.94, 367.37, 599.15, 366.45, 629.38, 366.45, 632.13, 335.3, 640.0, 318.81, 640.0, 251.94, 619.3, 204.3, 575.33, 174.98, 537.77, 158.49, 503.87, 152.99, 485.55, 142.0, 469.97, 141.08, 456.23, 131.01, 432.41, 122.76, 426.92, 100.77, 417.75, 89.78, 401.26, 100.77, 359.12, 108.1, 335.3, 113.6, 311.48, 97.11, 299.57, 99.86, 301.41, 112.68, 306.9, 131.92, 306.9, 140.17, 336.22, 185.97, 354.54, 210.71, 360.04, 223.54, 370.12, 227.2, 388.44, 219.87, 391.19, 225.37, 377.45, 251.94, 368.28, 271.17, 363.7, 284.92, 354.54, 301.41, 349.96, 314.23, 348.13, 317.9, 332.55, 319.73, 323.39, 330.72]], "area": 66855.4377, "iscrowd": 0, "image_id": 111040, "bbox": [297.74, 89.78, 342.26, 287.67], "category_id": 17, "id": 48167, "split": "val", "sentences": [{"tokens": ["sleeping", "grey", "cat", "with", "black", "stripes"], "raw": "Sleeping grey cat with black stripes.", "sent_id": 64801, "sent": "sleeping grey cat with black stripes"}, {"tokens": ["a", "multi", "-", "colored", "cat", "sleeping", "next", "to", "a", "black", "cat"], "raw": "A multi-colored cat sleeping next to a black cat.", "sent_id": 64802, "sent": "a multi - colored cat sleeping next to a black cat"}], "file_name": "COCO_train2014_000000111040_48167.jpg", "ann_id": 48167, "sent_ids": [64801, 64802], "ref_id": 29899}, {"segmentation": [[3.22, 93.06, 64.43, 82.33, 144.97, 80.18, 182.55, 80.18, 191.14, 82.33, 193.29, 109.17, 191.14, 112.39, 135.3, 126.35, 138.52, 155.35, 140.67, 246.62, 154.63, 288.5, 109.53, 279.91, 83.76, 273.47, 65.5, 262.73, 10.74, 204.74, 0.0, 197.23, 2.15, 90.92]], "area": 25847.0792, "iscrowd": 0, "image_id": 577416, "bbox": [0.0, 80.18, 193.29, 208.32], "category_id": 1, "id": 1715289, "split": "val", "sentences": [{"tokens": ["the", "brown", "cushion", "on", "the", "left", "side", "of", "the", "picture"], "raw": "The brown cushion on the left side of the picture.", "sent_id": 64817, "sent": "the brown cushion on the left side of the picture"}], "file_name": "COCO_train2014_000000577416_1715289.jpg", "ann_id": 1715289, "sent_ids": [64817], "ref_id": 29905}, {"segmentation": [[182.86, 151.84, 149.35, 154.72, 141.7, 150.89, 144.57, 126.95, 139.78, 110.68, 146.48, 97.27, 120.63, 72.38, 149.35, 92.48, 163.72, 84.83, 188.61, 87.7, 196.27, 90.57, 202.97, 69.51, 203.93, 88.66, 216.37, 85.78, 213.5, 99.19, 296.79, 97.27, 358.07, 108.76, 384.87, 127.91, 381.04, 259.07, 366.68, 251.41, 364.77, 260.03, 360.94, 247.58, 359.02, 227.48, 369.56, 198.76, 358.07, 180.57, 331.26, 162.37, 266.16, 156.63, 245.09, 160.46, 221.16, 219.82, 220.2, 225.56, 209.67, 209.29]], "area": 18874.332450000005, "iscrowd": 0, "image_id": 349408, "bbox": [120.63, 69.51, 264.24, 190.52], "category_id": 21, "id": 74805, "split": "val", "sentences": [{"tokens": ["the", "large", "black", "cow"], "raw": "The large black cow", "sent_id": 64843, "sent": "the large black cow"}, {"tokens": ["a", "larger", "bull", "with", "a", "smaller", "brown", "one", "in", "front", "of", "it"], "raw": "A larger bull with a smaller brown one in front of it.", "sent_id": 64844, "sent": "a larger bull with a smaller brown one in front of it"}], "file_name": "COCO_train2014_000000349408_74805.jpg", "ann_id": 74805, "sent_ids": [64843, 64844], "ref_id": 29914}, {"segmentation": [[35.28, 425.14, 33.56, 412.23, 49.05, 393.3, 64.55, 356.29, 49.92, 374.36, 43.89, 391.58, 21.52, 396.74, 10.33, 380.39, 20.65, 382.97, 27.54, 388.13, 31.84, 389.85, 40.45, 382.11, 46.47, 368.34, 56.8, 348.55, 72.29, 333.92, 92.95, 326.17, 142.86, 326.17, 197.08, 333.92, 194.5, 329.61, 200.52, 321.01, 214.29, 325.31, 219.45, 326.17, 220.32, 333.92, 226.34, 339.94, 228.92, 349.41, 238.39, 364.9, 224.62, 368.34, 207.41, 360.59, 186.75, 360.59, 179.01, 375.22, 178.15, 376.95, 183.31, 386.41, 190.19, 400.18, 196.22, 406.21, 201.38, 425.14, 195.36, 426.0, 193.64, 426.0, 191.05, 419.98, 166.96, 396.74, 163.52, 388.13, 163.52, 379.53, 150.61, 384.69, 148.88, 398.46, 148.88, 422.56, 135.98, 426.0, 136.84, 417.39, 136.84, 408.79, 137.7, 394.16, 135.98, 387.27, 129.95, 372.64, 119.62, 368.34, 92.08, 359.73, 102.41, 374.36, 102.41, 382.11, 97.25, 400.18, 88.64, 415.67, 91.22, 423.42, 90.36, 423.42, 74.87, 417.39, 80.04, 412.23, 78.32, 380.39, 74.01, 395.88, 62.82, 404.48, 51.64, 415.67, 51.64, 421.7, 49.05, 423.42, 36.15, 426.0]], "area": 11047.792849999994, "iscrowd": 0, "image_id": 277284, "bbox": [10.33, 321.01, 228.06, 104.99], "category_id": 18, "id": 12482, "split": "val", "sentences": [{"tokens": ["a", "dog", "wearing", "a", "blue", "and", "orange", "shirt"], "raw": "A dog wearing a blue and orange shirt.", "sent_id": 64849, "sent": "a dog wearing a blue and orange shirt"}, {"tokens": ["a", "dog", "waring", "a", "blue", "and", "orange", "shirt"], "raw": "A dog waring a blue and orange shirt.", "sent_id": 64850, "sent": "a dog waring a blue and orange shirt"}], "file_name": "COCO_train2014_000000277284_12482.jpg", "ann_id": 12482, "sent_ids": [64849, 64850], "ref_id": 29917}, {"segmentation": [[397.25, 230.96, 361.75, 212.73, 353.11, 176.26, 356.95, 126.37, 359.83, 122.53, 359.83, 100.46, 359.83, 80.31, 371.35, 46.72, 389.58, 26.57, 420.28, 16.98, 467.3, 16.98, 531.59, 48.64, 550.78, 91.82, 550.78, 137.88, 550.78, 182.98, 551.74, 198.33, 549.82, 203.13, 534.47, 212.73, 520.08, 233.84, 547.9, 269.34, 619.87, 276.06, 638.1, 275.1, 640.0, 415.19, 634.26, 418.07, 619.87, 418.07, 591.08, 418.07, 570.93, 419.99, 543.11, 419.99, 515.28, 419.03, 501.84, 419.03, 491.29, 419.99, 377.1, 419.03, 308.02, 417.11, 259.08, 419.99, 263.88, 409.43, 293.62, 372.01, 319.53, 340.35, 343.52, 309.64, 348.32, 298.13, 368.47, 285.65, 400.13, 284.69, 405.89, 276.06]], "area": 89737.48425000001, "iscrowd": 0, "image_id": 511967, "bbox": [259.08, 16.98, 380.92, 403.01], "category_id": 1, "id": 443762, "split": "val", "sentences": [{"tokens": ["the", "man", "who", "is", "putting", "the", "tie", "around", "his", "neck"], "raw": "The man who is putting the tie around his neck.", "sent_id": 64932, "sent": "the man who is putting the tie around his neck"}, {"tokens": ["a", "man", "putting", "a", "tie", "on", "his", "own", "neck"], "raw": "A man putting a tie on his own neck.", "sent_id": 64933, "sent": "a man putting a tie on his own neck"}], "file_name": "COCO_train2014_000000511967_443762.jpg", "ann_id": 443762, "sent_ids": [64932, 64933], "ref_id": 29946}, {"segmentation": [[240.18, 289.08, 227.24, 225.8, 261.75, 194.16, 303.46, 194.16, 309.21, 244.49, 287.64, 299.15, 333.66, 306.34, 373.93, 405.57, 296.27, 442.97, 376.81, 500.49, 375.37, 570.97, 373.93, 568.09, 375.37, 619.87, 212.85, 614.11, 218.61, 460.22, 234.43, 408.45, 146.7, 414.2, 197.03, 339.42, 244.49, 286.2]], "area": 53836.19875, "iscrowd": 0, "image_id": 354391, "bbox": [146.7, 194.16, 230.11, 425.71], "category_id": 1, "id": 506796, "split": "val", "sentences": [{"tokens": ["a", "little", "girl"], "raw": "A little girl", "sent_id": 64970, "sent": "a little girl"}, {"tokens": ["a", "child", "sitting", "on", "his", "dad", "'", "s", "lap"], "raw": "A child sitting on his dad's lap", "sent_id": 64971, "sent": "a child sitting on his dad ' s lap"}], "file_name": "COCO_train2014_000000354391_506796.jpg", "ann_id": 506796, "sent_ids": [64970, 64971], "ref_id": 29964}, {"segmentation": [[290.45, 339.21, 255.89, 291.51, 228.63, 244.3, 228.15, 242.35, 233.99, 239.92, 255.89, 237.48, 293.37, 234.08, 325.98, 231.64, 356.16, 231.16, 390.23, 234.08, 425.76, 238.46, 469.56, 248.68, 518.72, 263.77, 583.94, 291.02, 600.49, 301.73, 633.1, 329.48, 640.0, 339.21, 639.92, 383.99, 640.0, 473.06, 637.0, 480.0, 438.41, 479.87, 243.98, 479.87, 49.55, 479.87, 42.25, 473.06, 36.41, 471.11, 16.46, 469.17, 0.0, 472.09, 0.0, 333.04, 13.53, 323.31, 41.28, 306.28, 58.31, 294.11, 70.0, 284.37, 87.48, 278.63, 120.1, 269.38, 130.8, 276.2, 149.79, 285.93, 202.84, 307.35, 274.39, 338.5, 281.2, 338.5, 284.61, 334.6, 288.99, 338.98]], "area": 131737.21579999998, "iscrowd": 0, "image_id": 443136, "bbox": [0.0, 231.16, 640.0, 248.84], "category_id": 59, "id": 1571667, "split": "val", "sentences": [{"tokens": ["a", "very", "large", "pizza", "the", "size", "of", "a", "table"], "raw": "A very large pizza the size of a table", "sent_id": 65008, "sent": "a very large pizza the size of a table"}, {"tokens": ["a", "huge", "pepperoni", "and", "cheese", "pizza"], "raw": "a huge pepperoni and cheese pizza", "sent_id": 65009, "sent": "a huge pepperoni and cheese pizza"}], "file_name": "COCO_train2014_000000443136_1571667.jpg", "ann_id": 1571667, "sent_ids": [65008, 65009], "ref_id": 29979}, {"segmentation": [[402.9, 195.71, 409.06, 201.1, 411.37, 204.18, 401.35, 218.83, 390.56, 224.99, 385.94, 232.7, 385.17, 261.99, 380.54, 322.87, 387.48, 334.43, 386.71, 360.64, 379.77, 386.07, 375.15, 399.17, 374.38, 416.13, 372.84, 425.38, 373.61, 446.96, 380.54, 463.91, 368.21, 463.91, 367.44, 454.67, 367.44, 442.33, 365.13, 412.28, 366.67, 398.4, 368.98, 374.51, 367.44, 373.74, 362.82, 380.68, 357.42, 396.86, 359.74, 409.19, 358.19, 416.9, 355.47, 428.18, 353.22, 444.59, 353.54, 456.5, 352.89, 462.94, 349.35, 465.51, 344.53, 463.9, 344.85, 461.97, 342.6, 455.53, 344.2, 451.03, 343.88, 438.48, 343.56, 407.26, 343.88, 400.83, 346.78, 395.68, 349.03, 384.41, 347.1, 375.4, 344.53, 372.51, 343.24, 391.49, 340.34, 398.25, 341.95, 418.2, 340.67, 432.36, 340.34, 443.95, 338.09, 463.58, 330.69, 461.97, 332.94, 448.13, 334.23, 436.87, 334.55, 434.62, 336.48, 418.2, 333.26, 409.19, 334.55, 403.4, 332.3, 386.67, 327.79, 375.08, 326.51, 360.28, 327.79, 348.05, 330.37, 333.57, 336.16, 327.13, 344.85, 321.66, 349.68, 318.44, 355.79, 309.11, 359.01, 303.32, 361.9, 299.78, 368.02, 284.65, 367.37, 282.08, 369.31, 278.22, 369.63, 269.85, 371.88, 259.23, 371.88, 227.37, 366.09, 229.3, 367.37, 225.12, 368.34, 220.94, 372.85, 218.04, 372.88, 210.61, 366.64, 204.67, 377.14, 202.54, 385.51, 202.24, 392.51, 200.26, 402.56, 195.99]], "area": 8135.529800000001, "iscrowd": 0, "image_id": 466790, "bbox": [326.51, 195.71, 84.86, 269.8], "category_id": 25, "id": 598347, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "standing", "in", "the", "background", "looking", "up", "at", "the", "trees"], "raw": "a giraffe standing in the background looking up at the trees", "sent_id": 65013, "sent": "a giraffe standing in the background looking up at the trees"}, {"tokens": ["the", "giraffe", "to", "the", "right", "eating", "leaves", "from", "the", "tree"], "raw": "The giraffe to the right eating leaves from the tree", "sent_id": 65014, "sent": "the giraffe to the right eating leaves from the tree"}], "file_name": "COCO_train2014_000000466790_598347.jpg", "ann_id": 598347, "sent_ids": [65013, 65014], "ref_id": 29982}, {"segmentation": [[16.18, 422.83, 12.94, 399.1, 22.65, 399.1, 62.56, 404.49, 98.16, 392.63, 104.63, 376.45, 138.07, 379.69, 165.03, 371.06, 183.37, 363.51, 212.49, 361.35, 224.36, 339.78, 298.79, 341.93, 303.1, 390.47, 295.55, 403.42, 298.79, 473.53, 273.98, 474.61, 259.96, 418.52, 151.01, 472.45, 110.02, 471.37, 3.24, 472.45, 71.19, 423.91, 18.34, 422.83]], "area": 24284.923350000005, "iscrowd": 0, "image_id": 297019, "bbox": [3.24, 339.78, 299.86, 134.83], "category_id": 67, "id": 1621932, "split": "val", "sentences": [{"tokens": ["the", "brown", "coffee", "table"], "raw": "The brown coffee table", "sent_id": 65027, "sent": "the brown coffee table"}, {"tokens": ["a", "dark", "brown", "wooden", "table", "top"], "raw": "A dark brown wooden table top.", "sent_id": 65028, "sent": "a dark brown wooden table top"}], "file_name": "COCO_train2014_000000297019_1621932.jpg", "ann_id": 1621932, "sent_ids": [65027, 65028], "ref_id": 29987}, {"segmentation": [[6.43, 16.38, 125.8, 13.62, 147.84, 60.45, 146.92, 76.98, 137.74, 82.49, 134.99, 95.35, 112.03, 93.51, 112.03, 86.17, 85.4, 89.84, 83.56, 99.02, 72.54, 106.37, 60.61, 107.29, 56.02, 99.02, 0.0, 102.69]], "area": 11265.100149999998, "iscrowd": 0, "image_id": 435681, "bbox": [0.0, 13.62, 147.84, 93.67], "category_id": 3, "id": 132524, "split": "val", "sentences": [{"tokens": ["car"], "raw": "CAR", "sent_id": 65074, "sent": "car"}, {"tokens": ["blue", "van", "behind", "woman"], "raw": "Blue van behind woman.", "sent_id": 65075, "sent": "blue van behind woman"}], "file_name": "COCO_train2014_000000435681_132524.jpg", "ann_id": 132524, "sent_ids": [65074, 65075], "ref_id": 30010}, {"segmentation": [[344.09, 209.26, 524.22, 63.64, 623.46, 131.6, 443.33, 291.24]], "area": 28651.34730000001, "iscrowd": 0, "image_id": 187939, "bbox": [344.09, 63.64, 279.37, 227.6], "category_id": 76, "id": 1634486, "split": "val", "sentences": [{"tokens": ["a", "black", "laptop", "set", "next", "to", "a", "white", "one"], "raw": "A black laptop set next to a white one.", "sent_id": 65102, "sent": "a black laptop set next to a white one"}, {"tokens": ["a", "black", "laptop"], "raw": "A black laptop", "sent_id": 65103, "sent": "a black laptop"}], "file_name": "COCO_train2014_000000187939_1634486.jpg", "ann_id": 1634486, "sent_ids": [65102, 65103], "ref_id": 30023}, {"segmentation": [[177.58, 240.94, 195.15, 190.82, 200.36, 174.88, 206.21, 164.79, 207.19, 163.49, 212.07, 156.33, 213.05, 151.45, 211.75, 145.59, 207.84, 141.68, 207.84, 137.78, 212.4, 110.12, 221.51, 100.68, 226.39, 97.43, 229.64, 95.15, 239.41, 91.24, 247.22, 90.59, 250.47, 90.59, 256.33, 90.92, 262.51, 88.64, 280.74, 87.34, 290.5, 92.54, 305.8, 100.35, 313.28, 105.56, 314.26, 108.82, 311.98, 115.65, 308.72, 121.18, 303.19, 127.69, 291.15, 132.25, 281.71, 136.15, 281.39, 153.4, 282.69, 154.7, 291.48, 165.12, 292.13, 172.93, 293.43, 179.11, 297.33, 194.4, 300.26, 201.89, 302.22, 203.52, 304.82, 206.77, 301.57, 213.28, 343.87, 230.2, 348.1, 232.48, 361.77, 235.41, 370.56, 235.73, 386.18, 238.34, 379.34, 247.12, 385.85, 265.02, 385.85, 266.0, 380.65, 270.23, 371.86, 276.09, 366.65, 287.8, 364.7, 292.03, 341.92, 292.03, 323.04, 280.64, 317.84, 280.32, 300.91, 283.25, 299.29, 293.34, 291.48, 305.7, 292.45, 310.26, 296.68, 320.35, 299.29, 333.04, 300.91, 333.69, 304.49, 334.99, 299.61, 359.07, 306.77, 374.69, 308.4, 383.48, 308.72, 389.66, 308.72, 396.5, 309.05, 398.45, 309.7, 403.66, 306.45, 426.11, 243.64, 420.58, 238.43, 412.44, 230.62, 401.71, 228.34, 387.39, 224.11, 375.35, 221.83, 369.49, 218.91, 368.51, 208.17, 362.33, 209.14, 359.4, 216.3, 336.62, 217.6, 330.44, 202.96, 305.7, 197.43, 299.52, 191.57, 293.66, 184.41, 290.73, 181.16, 289.11, 178.55, 286.83, 181.16, 275.44, 181.48, 268.28, 173.67, 259.17, 175.3, 244.2]], "area": 36278.42410000002, "iscrowd": 0, "image_id": 502134, "bbox": [173.67, 87.34, 212.51, 338.77], "category_id": 1, "id": 222517, "split": "val", "sentences": [{"tokens": ["a", "man", "on", "a", "motorcycle", "wearing", "a", "santa", "costume"], "raw": "A man on a motorcycle wearing a Santa costume.", "sent_id": 65127, "sent": "a man on a motorcycle wearing a santa costume"}, {"tokens": ["a", "man", "wearing", "a", "santa", "claus", "outfit", "driving", "a", "motorcycle"], "raw": "A man wearing a Santa Claus outfit driving a motorcycle.", "sent_id": 65128, "sent": "a man wearing a santa claus outfit driving a motorcycle"}], "file_name": "COCO_train2014_000000502134_222517.jpg", "ann_id": 222517, "sent_ids": [65127, 65128], "ref_id": 30034}, {"segmentation": [[307.17, 230.11, 350.02, 285.89, 347.59, 300.44, 338.7, 294.78, 328.19, 284.27, 319.3, 274.57, 306.37, 264.06, 301.52, 270.53, 267.57, 306.1, 250.59, 320.65, 227.96, 323.07, 87.3, 318.22, 61.43, 306.1, 59.01, 290.74, 74.37, 281.04, 105.89, 276.19, 116.4, 275.38, 174.6, 259.21, 184.3, 253.55, 190.77, 254.36, 211.79, 294.78, 237.66, 302.86, 260.29, 293.97, 269.99, 280.23, 272.42, 265.68, 271.61, 254.36, 265.14, 240.62, 253.01, 207.48, 258.67, 189.69, 279.69, 179.99, 287.77, 183.23, 303.13, 205.86, 307.98, 228.49]], "area": 13636.807000000004, "iscrowd": 0, "image_id": 177019, "bbox": [59.01, 179.99, 291.01, 143.08], "category_id": 4, "id": 1790704, "split": "val", "sentences": [{"tokens": ["area", "under", "motorcycle"], "raw": "Area under motorcycle", "sent_id": 65129, "sent": "area under motorcycle"}], "file_name": "COCO_train2014_000000177019_1790704.jpg", "ann_id": 1790704, "sent_ids": [65129], "ref_id": 30035}, {"segmentation": [[354.38, 422.16, 362.13, 389.24, 349.54, 379.56, 341.79, 363.1, 344.7, 354.38, 341.79, 347.6, 353.41, 343.73, 354.38, 335.98, 365.03, 332.11, 369.87, 325.33, 380.52, 327.27, 387.3, 319.52, 388.27, 312.75, 396.98, 305.97, 393.11, 304.03, 391.17, 304.03, 388.27, 302.1, 385.37, 286.6, 383.43, 289.51, 377.62, 290.48, 373.75, 290.48, 372.78, 285.63, 368.9, 281.76, 369.87, 277.89, 371.81, 274.02, 371.81, 274.02, 372.78, 266.27, 361.16, 244.0, 364.06, 226.57, 356.32, 218.83, 371.81, 185.9, 389.24, 177.19, 404.73, 168.48, 423.13, 165.57, 449.27, 174.29, 469.6, 180.1, 472.51, 203.33, 482.19, 204.3, 495.75, 213.02, 503.49, 238.19, 517.05, 262.4, 531.57, 281.76, 546.1, 286.6, 543.19, 307.9, 550.94, 315.65, 551.9, 327.27, 573.21, 347.6, 571.27, 418.29]], "area": 41735.77125000001, "iscrowd": 0, "image_id": 376241, "bbox": [341.79, 165.57, 231.42, 256.59], "category_id": 1, "id": 556074, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "a", "grey", "shirt", "brushing", "her", "teeth", "with", "two", "other", "people"], "raw": "A girl in a grey shirt brushing her teeth with two other people.", "sent_id": 65134, "sent": "a girl in a grey shirt brushing her teeth with two other people"}, {"tokens": ["a", "woman", "in", "a", "grey", "t", "shirt", "brushing", "her", "teeth"], "raw": "A woman in a grey t shirt brushing her teeth", "sent_id": 65135, "sent": "a woman in a grey t shirt brushing her teeth"}], "file_name": "COCO_train2014_000000376241_556074.jpg", "ann_id": 556074, "sent_ids": [65134, 65135], "ref_id": 30038}, {"segmentation": [[0.96, 126.19, 19.11, 142.43, 16.24, 179.68, 16.24, 209.29, 21.97, 228.4, 8.6, 252.28, 3.82, 258.97, 3.82, 331.57, 19.11, 342.07, 63.05, 351.63, 80.24, 373.6, 89.79, 394.61, 86.93, 418.49, 0.0, 422.32]], "area": 8358.886250000001, "iscrowd": 0, "image_id": 187577, "bbox": [0.0, 126.19, 89.79, 296.13], "category_id": 1, "id": 495554, "split": "val", "sentences": [{"tokens": ["someone", "'", "s", "left", "side", "and", "only", "showing", "ear", "and", "shoulder"], "raw": "Someone's left side and only showing ear and shoulder.", "sent_id": 65250, "sent": "someone ' s left side and only showing ear and shoulder"}, {"tokens": ["a", "kid", "whose", "face", "is", "not", "seen"], "raw": "a kid whose face is not seen", "sent_id": 65251, "sent": "a kid whose face is not seen"}], "file_name": "COCO_train2014_000000187577_495554.jpg", "ann_id": 495554, "sent_ids": [65250, 65251], "ref_id": 30085}, {"segmentation": [[158.17, 424.0, 172.46, 407.8, 203.9, 387.79, 240.11, 374.45, 295.37, 363.02, 370.64, 352.54, 440.2, 355.4, 486.89, 365.88, 473.55, 374.45, 470.69, 377.31, 472.59, 383.03, 496.41, 382.08, 523.09, 374.45, 578.36, 398.27, 600.27, 417.33, 601.22, 421.14]], "area": 21601.40215, "iscrowd": 0, "image_id": 327209, "bbox": [158.17, 352.54, 443.05, 71.46], "category_id": 67, "id": 1617635, "split": "val", "sentences": [{"tokens": ["a", "black", "table", "with", "kids", "around", "it"], "raw": "A black table with kids around it.", "sent_id": 65367, "sent": "a black table with kids around it"}, {"tokens": ["a", "table", "that", "has", "three", "people", "around", "it"], "raw": "A table that has three people around it.", "sent_id": 65368, "sent": "a table that has three people around it"}], "file_name": "COCO_train2014_000000327209_1617635.jpg", "ann_id": 1617635, "sent_ids": [65367, 65368], "ref_id": 30133}, {"segmentation": [[401.93, 179.69, 408.73, 193.61, 410.9, 197.63, 410.28, 205.98, 425.74, 206.29, 431.93, 212.47, 442.44, 227.32, 447.08, 242.47, 460.38, 252.37, 467.18, 264.43, 468.73, 269.38, 468.11, 297.21, 472.75, 314.84, 471.2, 330.61, 466.56, 349.16, 461.93, 360.3, 459.76, 371.43, 446.46, 373.59, 439.66, 370.19, 437.19, 352.87, 438.11, 339.27, 435.95, 324.73, 437.8, 303.09, 434.4, 295.97, 431.0, 301.85, 420.8, 306.18, 409.97, 305.56, 385.23, 306.49, 373.17, 312.36, 354.31, 330.3, 328.64, 336.79, 310.7, 346.07, 302.97, 346.07, 291.53, 339.27, 285.65, 332.46, 276.07, 327.52, 257.82, 301.54, 263.08, 291.64, 270.5, 290.1, 289.98, 301.54, 308.85, 308.65, 327.09, 304.01, 355.54, 291.64, 356.47, 282.06, 361.42, 279.58, 379.67, 278.04, 375.03, 273.4, 378.43, 266.9, 377.81, 257.01, 378.12, 227.63, 385.54, 214.02, 382.76, 208.45, 379.67, 200.72, 379.36, 186.19, 388.94, 175.98, 397.91, 176.29]], "area": 14534.710300000004, "iscrowd": 0, "image_id": 74156, "bbox": [257.82, 175.98, 214.93, 197.61], "category_id": 1, "id": 454795, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "multicolored", "shirt", "and", "brown", "boots", "is", "sitting", "on", "the", "ground", "with", "something", "white", "behind", "him"], "raw": "A man with a multicolored shirt and brown boots is sitting on the ground with something white behind him", "sent_id": 65379, "sent": "a man with a multicolored shirt and brown boots is sitting on the ground with something white behind him"}, {"tokens": ["a", "man", "with", "two", "other", "men", "in", "the", "back", "of", "a", "truck", "with", "hiking", "gear"], "raw": "A man with two other men in the back of a truck with hiking gear.", "sent_id": 65380, "sent": "a man with two other men in the back of a truck with hiking gear"}], "file_name": "COCO_train2014_000000074156_454795.jpg", "ann_id": 454795, "sent_ids": [65379, 65380], "ref_id": 30136}, {"segmentation": [[169.29, 63.62, 222.52, 71.02, 230.66, 79.15, 217.35, 95.41, 218.83, 124.25, 224.0, 138.29, 170.03, 136.08, 158.2, 114.64, 154.51, 93.93, 167.81, 85.06], [176.69, 150.86, 227.7, 153.08, 229.18, 171.56, 217.35, 163.43, 210.69, 160.47, 196.65, 157.52, 184.82, 165.65, 177.42, 164.91], [228.44, 205.57, 224.0, 222.58, 232.87, 226.27, 241.75, 224.79, 240.27, 208.53], [130.85, 116.85, 129.37, 133.86, 144.89, 158.99, 148.59, 152.34, 145.63, 141.99], [108.67, 181.17, 135.28, 184.13, 136.02, 192.26, 115.32, 204.83, 112.36, 225.53, 107.93, 224.79, 98.32, 197.44, 110.15, 193.0], [116.8, 146.43, 119.76, 155.3, 99.06, 155.3, 116.06, 146.43]], "area": 6070.580150000002, "iscrowd": 0, "image_id": 15190, "bbox": [98.32, 63.62, 143.43, 162.65], "category_id": 22, "id": 1409608, "split": "val", "sentences": [{"tokens": ["elephant", "in", "the", "background", "that", "you", "can", "only", "see", "his", "back", "directly", "behind", "the", "woman", "in", "the", "tank", "top"], "raw": "Elephant in the background that you can only see his back directly behind the woman in the tank top", "sent_id": 65406, "sent": "elephant in the background that you can only see his back directly behind the woman in the tank top"}, {"tokens": ["the", "elephant", "to", "the", "far", "left", "in", "front", "of", "the", "people"], "raw": "The elephant to the far left in front of the people.", "sent_id": 65407, "sent": "the elephant to the far left in front of the people"}], "file_name": "COCO_train2014_000000015190_1409608.jpg", "ann_id": 1409608, "sent_ids": [65406, 65407], "ref_id": 30146}, {"segmentation": [[549.03, 362.43, 527.46, 363.51, 504.81, 360.27, 491.87, 341.93, 462.74, 303.1, 461.66, 263.19, 461.66, 239.46, 476.76, 217.89, 495.1, 199.55, 516.67, 171.51, 539.33, 166.11, 567.37, 188.76, 597.57, 231.91, 607.28, 279.37, 600.81, 307.42, 592.18, 325.75, 582.47, 338.7, 584.63, 357.03, 558.74, 357.03]], "area": 21193.666699999998, "iscrowd": 0, "image_id": 444036, "bbox": [461.66, 166.11, 145.62, 197.4], "category_id": 51, "id": 709808, "split": "val", "sentences": [{"tokens": ["a", "silver", "bread", "bowl", "with", "a", "white", "napkin", "and", "roll", "inside"], "raw": "A silver bread bowl with a white napkin and roll inside.", "sent_id": 65438, "sent": "a silver bread bowl with a white napkin and roll inside"}, {"tokens": ["a", "silver", "bowl", "containing", "a", "cloth", "white", "napkin", "and", "a", "bread", "roll"], "raw": "A silver bowl containing a cloth white napkin and a bread roll.", "sent_id": 65439, "sent": "a silver bowl containing a cloth white napkin and a bread roll"}], "file_name": "COCO_train2014_000000444036_709808.jpg", "ann_id": 709808, "sent_ids": [65438, 65439], "ref_id": 30158}, {"segmentation": [[377.65, 442.32, 392.19, 457.54, 412.81, 476.48, 414.17, 470.73, 404.36, 445.03, 403.01, 435.22, 406.05, 435.56, 412.81, 442.32, 414.84, 440.29, 406.73, 427.11, 397.26, 415.27, 395.57, 414.93, 392.53, 418.99, 389.82, 420.34, 388.13, 418.31, 387.79, 415.95, 367.5, 395.66, 364.12, 391.94, 366.83, 382.13, 368.85, 375.37, 357.36, 363.53, 343.49, 375.71, 342.48, 377.74, 340.11, 355.76, 343.49, 357.45, 341.8, 345.61, 321.17, 324.98, 317.12, 324.64, 328.61, 340.54, 329.29, 346.29, 325.91, 365.9, 319.82, 361.84, 315.43, 361.5, 303.59, 357.45, 293.45, 351.02, 284.65, 346.29, 287.36, 357.11, 296.49, 372.66, 330.98, 400.39, 347.55, 417.64, 356.0, 421.02, 362.77, 425.08]], "area": 4845.500650000001, "iscrowd": 0, "image_id": 223459, "bbox": [284.65, 324.64, 130.19, 151.84], "category_id": 5, "id": 162571, "split": "val", "sentences": [{"tokens": ["plane", "to", "far", "left"], "raw": "plane to far left", "sent_id": 65450, "sent": "plane to far left"}, {"tokens": ["the", "jet", "that", "is", "under", "all", "the", "other", "jets"], "raw": "The jet that is under all the other jets.", "sent_id": 65451, "sent": "the jet that is under all the other jets"}], "file_name": "COCO_train2014_000000223459_162571.jpg", "ann_id": 162571, "sent_ids": [65450, 65451], "ref_id": 30160}, {"segmentation": [[94.45, 68.55, 94.45, 73.88, 90.18, 76.54, 92.85, 80.81, 102.97, 85.07, 111.49, 87.2, 116.82, 85.07, 117.29, 100.16, 121.81, 103.1, 127.31, 100.75, 130.45, 104.48, 133.59, 118.61, 132.8, 121.56, 117.88, 133.14, 109.75, 142.0, 76.07, 135.15, 74.64, 92.9, 74.36, 80.62, 71.79, 44.65, 76.07, 42.66, 82.35, 46.08, 86.35, 52.65, 88.63, 56.93, 87.49, 57.21, 92.91, 62.92], [78.51, 161.44, 106.54, 173.06, 122.26, 169.64, 122.94, 199.73, 112.01, 209.3, 113.37, 216.13, 103.12, 218.19, 103.12, 218.87, 81.24, 217.5, 75.77, 160.76]], "area": 5353.85865, "iscrowd": 0, "image_id": 569037, "bbox": [71.79, 42.66, 61.8, 176.21], "category_id": 1, "id": 557694, "split": "val", "sentences": [{"tokens": ["backside", "of", "a", "man"], "raw": "BACKSIDE OF A MAN", "sent_id": 65509, "sent": "backside of a man"}, {"tokens": ["the", "person", "in", "the", "background", "wearing", "a", "white", "hate"], "raw": "The person in the background wearing a white hate.", "sent_id": 65510, "sent": "the person in the background wearing a white hate"}], "file_name": "COCO_train2014_000000569037_557694.jpg", "ann_id": 557694, "sent_ids": [65509, 65510], "ref_id": 30185}, {"segmentation": [[240.72, 558.99, 219.1, 494.13, 196.04, 440.79, 162.88, 393.23, 129.73, 342.77, 135.5, 230.34, 100.9, 228.9, 98.02, 179.89, 136.94, 99.17, 172.97, 90.52, 172.97, 60.25, 172.97, 35.75, 177.3, 17.01, 216.22, 9.8, 232.07, 31.42, 229.19, 64.58, 223.42, 93.41, 219.1, 100.61, 259.46, 125.12, 272.43, 189.98, 258.02, 231.78, 263.78, 302.41, 253.69, 377.37, 279.64, 419.17, 288.29, 456.65, 285.41, 494.13, 272.43, 508.54, 259.46, 505.66, 272.43, 543.14, 266.67, 566.2, 256.58, 576.29]], "area": 56095.65149999999, "iscrowd": 0, "image_id": 580695, "bbox": [98.02, 9.8, 190.27, 566.49], "category_id": 1, "id": 456832, "split": "val", "sentences": [{"tokens": ["a", "young", "girl", "wearing", "a", "red", "and", "black", "uniform"], "raw": "A young girl wearing a red and black uniform.", "sent_id": 65564, "sent": "a young girl wearing a red and black uniform"}, {"tokens": ["a", "young", "asian", "girl", "in", "a", "red", "soccer", "jersey", "preparing", "to", "kick"], "raw": "A young asian girl in a red soccer jersey preparing to kick.", "sent_id": 65565, "sent": "a young asian girl in a red soccer jersey preparing to kick"}], "file_name": "COCO_train2014_000000580695_456832.jpg", "ann_id": 456832, "sent_ids": [65564, 65565], "ref_id": 30204}, {"segmentation": [[183.04, 344.29, 174.32, 337.51, 162.7, 335.57, 159.8, 328.8, 154.95, 320.08, 152.05, 314.27, 156.89, 307.49, 159.8, 304.58, 160.77, 272.62, 162.7, 261.0, 166.58, 248.41, 176.26, 239.7, 204.35, 230.01, 218.87, 231.95, 363.18, 247.44, 447.43, 259.07, 522.97, 269.72, 524.91, 269.72, 524.91, 284.25, 451.31, 293.93, 355.43, 317.17, 274.08, 334.61, 231.46, 340.42, 219.84, 341.39, 203.38, 342.35]], "area": 25466.249699999997, "iscrowd": 0, "image_id": 204216, "bbox": [152.05, 230.01, 372.86, 114.28], "category_id": 7, "id": 366839, "split": "val", "sentences": [{"tokens": ["the", "train", "that", "is", "on", "the", "tracks"], "raw": "The train that is on the tracks.", "sent_id": 65711, "sent": "the train that is on the tracks"}, {"tokens": ["the", "yellow", "grey", "and", "blue", "train"], "raw": "the yellow grey and blue train.", "sent_id": 65712, "sent": "the yellow grey and blue train"}], "file_name": "COCO_train2014_000000204216_366839.jpg", "ann_id": 366839, "sent_ids": [65711, 65712], "ref_id": 30260}, {"segmentation": [[21.38, 333.65, 103.85, 342.82, 183.27, 337.73, 188.36, 334.67, 189.38, 344.85, 197.53, 346.89, 201.6, 341.8, 199.56, 324.49, 216.87, 288.85, 216.87, 307.18, 225.02, 307.18, 230.11, 297.0, 228.07, 273.58, 229.09, 218.6, 217.89, 191.11, 171.05, 188.05, 127.27, 177.87, 61.09, 186.02, 42.76, 195.18, 33.6, 222.67, 28.51, 236.93, 28.51, 248.13, 26.47, 321.43, 22.4, 320.42]], "area": 29512.79925, "iscrowd": 0, "image_id": 14484, "bbox": [21.38, 177.87, 208.73, 169.02], "category_id": 3, "id": 2170316, "split": "val", "sentences": [{"tokens": ["a", "yellow", "volkswagen", "van"], "raw": "A yellow Volkswagen van.", "sent_id": 65737, "sent": "a yellow volkswagen van"}, {"tokens": ["a", "yellow", "vw", "bus", "with", "license", "plate", "lpl", "3iip"], "raw": "A yellow VW bus with license plate LPL 3IIP", "sent_id": 65738, "sent": "a yellow vw bus with license plate lpl 3iip"}], "file_name": "COCO_train2014_000000014484_2170316.jpg", "ann_id": 2170316, "sent_ids": [65737, 65738], "ref_id": 30270}, {"segmentation": [[257.69, 155.82, 278.36, 137.8, 286.84, 131.97, 290.02, 122.43, 297.44, 120.84, 305.92, 108.11, 312.28, 91.15, 323.94, 84.26, 332.96, 83.73, 345.15, 87.97, 349.92, 94.86, 359.99, 107.05, 362.64, 119.25, 354.69, 122.43, 348.33, 128.26, 344.09, 137.27, 344.09, 142.04, 342.5, 143.1, 334.55, 143.63, 331.9, 148.4, 331.37, 152.64, 340.91, 167.48, 349.39, 186.57, 349.39, 202.47, 349.39, 208.83, 357.87, 211.48, 362.64, 217.31, 358.93, 219.96, 358.93, 227.38, 351.51, 229.5, 353.1, 277.21, 348.33, 305.3, 348.33, 334.46, 344.62, 371.03, 340.91, 393.29, 339.32, 437.82, 340.91, 445.77, 344.62, 459.02, 371.12, 472.28, 366.35, 484.47, 357.34, 494.01, 342.5, 498.78, 318.64, 492.42, 291.61, 492.42, 286.84, 482.88, 294.79, 460.61, 292.14, 442.06, 285.25, 410.79, 285.25, 373.15, 282.6, 330.22, 282.6, 323.32, 279.95, 311.66, 267.23, 304.77, 266.7, 281.98, 267.23, 259.72, 281.89, 274.26, 317.67, 316.0, 328.82, 312.69, 327.17, 293.28, 320.56, 278.0, 312.3, 267.26, 302.39, 250.74, 294.54, 246.2, 285.04, 232.98, 280.91, 229.68, 280.5, 222.24, 270.18, 214.81, 266.05, 194.57, 259.85, 179.29, 257.79, 163.59]], "area": 25549.42530000001, "iscrowd": 0, "image_id": 316557, "bbox": [257.69, 83.73, 113.43, 415.05], "category_id": 1, "id": 440453, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "glasses", "staring", "down", "at", "an", "object", "in", "his", "hands", "while", "wearing", "skis"], "raw": "A man with glasses staring down at an object in his hands while wearing skis.", "sent_id": 65762, "sent": "a man with glasses staring down at an object in his hands while wearing skis"}, {"tokens": ["the", "person", "that", "is", "wearing", "glasses"], "raw": "The person that is wearing glasses.", "sent_id": 65763, "sent": "the person that is wearing glasses"}], "file_name": "COCO_train2014_000000316557_440453.jpg", "ann_id": 440453, "sent_ids": [65762, 65763], "ref_id": 30279}, {"segmentation": [[91.41, 188.86, 109.84, 176.97, 114.0, 172.81, 114.0, 167.46, 121.13, 157.35, 128.86, 154.98, 138.96, 162.11, 156.2, 151.41, 172.84, 151.41, 192.45, 162.11, 204.93, 156.76, 214.44, 162.7, 211.47, 175.19, 209.69, 187.07, 207.91, 203.71, 201.96, 209.06, 212.07, 219.17, 216.23, 259.58, 221.58, 282.17, 223.36, 300.0, 231.09, 305.94, 241.78, 316.64, 213.85, 314.86, 207.91, 317.23, 202.56, 323.77, 202.56, 343.98, 193.64, 345.17, 187.7, 349.33, 164.52, 348.14, 163.92, 354.08, 143.12, 359.43, 129.45, 363.0, 124.7, 362.4, 99.73, 317.23, 99.14, 266.12, 88.16, 261.43, 83.59, 214.13]], "area": 22719.693799999994, "iscrowd": 0, "image_id": 54572, "bbox": [83.59, 151.41, 158.19, 211.59], "category_id": 23, "id": 1821692, "split": "val", "sentences": [{"tokens": ["polar", "bear", "cub", "on", "the", "left", "and", "leaning", "to", "the", "left"], "raw": "Polar bear cub on the left and leaning to the left.", "sent_id": 65785, "sent": "polar bear cub on the left and leaning to the left"}, {"tokens": ["the", "polar", "cub", "on", "the", "left"], "raw": "the polar cub on the left", "sent_id": 65786, "sent": "the polar cub on the left"}], "file_name": "COCO_train2014_000000054572_1821692.jpg", "ann_id": 1821692, "sent_ids": [65785, 65786], "ref_id": 30289}, {"segmentation": [[347.52, 349.7, 295.23, 338.81, 264.73, 319.2, 208.08, 279.98, 142.71, 252.74, 119.84, 239.67, 100.23, 228.78, 86.06, 214.61, 76.26, 200.45, 86.06, 192.83, 105.67, 187.38, 131.82, 197.18, 173.22, 220.06, 303.95, 290.87, 368.22, 327.91, 379.12, 337.72, 379.12, 352.97, 370.4, 359.51]], "area": 12809.181799999995, "iscrowd": 0, "image_id": 364803, "bbox": [76.26, 187.38, 302.86, 172.13], "category_id": 57, "id": 1066117, "split": "val", "sentences": [{"tokens": ["carrot"], "raw": "carrot", "sent_id": 65801, "sent": "carrot"}, {"tokens": ["the", "carrot", "on", "top", "touching", "the", "green", "zucchini"], "raw": "The carrot on top touching the green zucchini.", "sent_id": 65802, "sent": "the carrot on top touching the green zucchini"}], "file_name": "COCO_train2014_000000364803_1066117.jpg", "ann_id": 1066117, "sent_ids": [65801, 65802], "ref_id": 30294}, {"segmentation": [[520.67, 212.58, 504.24, 192.04, 503.21, 181.77, 518.62, 7.19, 518.62, 5.13, 640.0, 2.05, 626.45, 101.67, 617.21, 183.83, 619.26, 213.61, 569.97, 220.8, 535.05, 215.66]], "area": 24644.78310000001, "iscrowd": 0, "image_id": 106100, "bbox": [503.21, 2.05, 136.79, 218.75], "category_id": 47, "id": 675791, "split": "val", "sentences": [{"tokens": ["a", "glass", "containing", "a", "yellow", "colored", "beverage"], "raw": "A glass containing a yellow colored beverage.", "sent_id": 65982, "sent": "a glass containing a yellow colored beverage"}, {"tokens": ["glass", "with", "yellow", "juice", "in", "it"], "raw": "Glass with yellow juice in it.", "sent_id": 65983, "sent": "glass with yellow juice in it"}], "file_name": "COCO_train2014_000000106100_675791.jpg", "ann_id": 675791, "sent_ids": [65982, 65983], "ref_id": 30362}, {"segmentation": [[31.76, 3.59, 141.18, 3.59, 168.53, 22.12, 198.53, 53.88, 211.76, 82.12, 211.76, 96.24, 254.12, 120.06, 272.65, 152.71, 275.29, 218.88, 262.94, 258.59, 215.29, 319.47, 149.12, 351.24, 76.76, 339.76, 63.53, 328.29, 58.24, 284.18, 64.41, 257.71, 15.88, 189.76, 2.65, 127.12, 4.41, 52.12, 28.24, 5.35]], "area": 69991.69155, "iscrowd": 0, "image_id": 103430, "bbox": [2.65, 3.59, 272.64, 347.65], "category_id": 58, "id": 1068177, "split": "val", "sentences": [{"tokens": ["the", "only", "bagel", "dog", "that", "is", "completely", "visible"], "raw": "The only bagel dog that is completely visible.", "sent_id": 66012, "sent": "the only bagel dog that is completely visible"}, {"tokens": ["a", "pig", "in", "a", "blanket", "to", "the", "left", "of", "all", "the", "other", "ones"], "raw": "A pig in a blanket to the left of all the other ones.", "sent_id": 66013, "sent": "a pig in a blanket to the left of all the other ones"}], "file_name": "COCO_train2014_000000103430_1068177.jpg", "ann_id": 1068177, "sent_ids": [66012, 66013], "ref_id": 30371}, {"segmentation": [[362.42, 49.88, 360.49, 50.84, 389.41, 2.65, 191.81, 2.65, 172.53, 73.01, 187.96, 77.83, 203.38, 78.8, 235.19, 118.32, 253.5, 83.62, 268.92, 69.16, 280.49, 100.97, 304.59, 76.87, 321.94, 55.66, 345.07, 54.7, 361.78, 54.78]], "area": 14457.885999999997, "iscrowd": 0, "image_id": 162760, "bbox": [172.53, 2.65, 216.88, 115.67], "category_id": 1, "id": 430060, "split": "val", "sentences": [{"tokens": ["a", "gray", "shirt", "on", "a", "man"], "raw": "A gray shirt on a man.", "sent_id": 66020, "sent": "a gray shirt on a man"}, {"tokens": ["an", "elbow", "of", "a", "person", "in", "a", "green", "shirt"], "raw": "An elbow of a person in a green shirt.", "sent_id": 66021, "sent": "an elbow of a person in a green shirt"}], "file_name": "COCO_train2014_000000162760_430060.jpg", "ann_id": 430060, "sent_ids": [66020, 66021], "ref_id": 30372}, {"segmentation": [[358.39, 286.28, 360.54, 341.17, 387.44, 376.68, 383.14, 474.62, 297.04, 474.62, 300.27, 364.84, 320.72, 341.17, 327.17, 288.43, 335.78, 283.05, 318.57, 263.68, 261.52, 270.13, 219.55, 234.62, 248.61, 201.26, 229.24, 179.73, 257.22, 161.43, 257.22, 134.53, 198.03, 135.61, 207.71, 72.11, 271.21, 108.7, 263.68, 47.35, 203.41, 0.0, 480.0, 2.15, 464.93, 51.66, 513.36, 37.67, 532.74, 76.41, 441.26, 125.92, 533.81, 148.52, 520.9, 202.33, 392.83, 186.19]], "area": 74344.6742, "iscrowd": 0, "image_id": 553021, "bbox": [198.03, 0.0, 335.78, 474.62], "category_id": 64, "id": 20184, "split": "val", "sentences": [{"tokens": ["a", "large", "vase", "with", "tall", "flowers"], "raw": "A large vase with tall flowers.", "sent_id": 66026, "sent": "a large vase with tall flowers"}, {"tokens": ["purple", "and", "white", "flowers", "and", "the", "glass", "bottle", "holding", "them"], "raw": "Purple and white flowers and the glass bottle holding them.", "sent_id": 66027, "sent": "purple and white flowers and the glass bottle holding them"}], "file_name": "COCO_train2014_000000553021_20184.jpg", "ann_id": 20184, "sent_ids": [66026, 66027], "ref_id": 30374}, {"segmentation": [[499.77, 65.21, 502.21, 57.09, 513.59, 48.15, 518.47, 40.02, 537.16, 29.46, 547.72, 22.14, 564.79, 29.46, 583.48, 32.71, 591.6, 48.15, 599.73, 77.4, 594.04, 96.09, 586.73, 113.16, 578.6, 131.85, 567.22, 141.6, 569.66, 152.98, 604.6, 196.86, 604.6, 203.36, 604.6, 220.43, 604.6, 244.81, 601.35, 270.81, 597.29, 285.44, 595.67, 303.32, 588.35, 330.95, 577.79, 344.76, 568.85, 354.51, 149.53, 355.33, 147.09, 352.89, 147.09, 352.89, 145.46, 352.89, 145.46, 340.7, 147.9, 339.07, 153.59, 336.64, 155.21, 330.95, 160.9, 324.45, 161.72, 324.45, 169.84, 326.07, 172.28, 335.82, 174.72, 343.14, 174.72, 343.95, 176.34, 351.26, 177.97, 354.51, 206.41, 352.89, 217.79, 352.89, 231.6, 348.83, 234.04, 347.2, 260.86, 336.64, 270.61, 335.82, 293.36, 335.82, 338.06, 341.51, 370.56, 339.07, 384.38, 338.26, 381.94, 338.26, 377.07, 330.14, 375.44, 325.26, 375.44, 313.88, 377.07, 304.13, 386.0, 298.44, 399.82, 295.19, 410.38, 301.69, 422.57, 304.13, 422.57, 304.13, 446.14, 308.19, 435.58, 295.19, 435.58, 282.19, 435.58, 278.94, 434.76, 276.5, 437.2, 249.68, 438.01, 234.24, 446.95, 220.43, 457.52, 211.49, 451.83, 201.74, 438.83, 198.49, 429.89, 198.49, 429.07, 188.74, 429.07, 185.49, 433.14, 178.17, 440.45, 180.61, 451.02, 184.67, 473.77, 183.05, 481.9, 174.92, 499.77, 166.79, 504.65, 164.36, 504.65, 152.98, 502.21, 149.73, 491.65, 145.67, 490.84, 131.85, 488.4, 113.16, 490.84, 100.16, 494.9, 96.09, 496.52, 83.91, 496.52, 73.34, 502.21, 69.28, 499.77, 69.28, 500.59, 63.59]], "area": 47161.021499999995, "iscrowd": 0, "image_id": 163985, "bbox": [145.46, 22.14, 459.14, 333.19], "category_id": 1, "id": 490563, "split": "val", "sentences": [{"tokens": ["boy", "with", "white", "shirt", "pulling", "boy", "on", "skis", "from", "boat"], "raw": "boy with white shirt pulling boy on skis from boat", "sent_id": 66074, "sent": "boy with white shirt pulling boy on skis from boat"}, {"tokens": ["man", "in", "white", "shirt", "and", "white", "pants"], "raw": "Man in white shirt and white pants.", "sent_id": 66075, "sent": "man in white shirt and white pants"}], "file_name": "COCO_train2014_000000163985_490563.jpg", "ann_id": 490563, "sent_ids": [66074, 66075], "ref_id": 30393}, {"segmentation": [[451.52, 255.86, 439.26, 273.7, 429.22, 289.31, 432.57, 306.03, 433.68, 313.83, 415.84, 313.83, 396.89, 293.77, 399.12, 278.16, 416.96, 259.21, 428.11, 235.79, 415.84, 227.99, 389.09, 211.27, 382.4, 184.51, 389.09, 162.21, 410.27, 137.69, 433.68, 122.08, 448.18, 112.04, 452.64, 102.01, 454.86, 93.09, 450.41, 87.52, 453.75, 71.91, 469.36, 85.29, 470.47, 102.01, 470.47, 105.35, 471.59, 112.04, 487.2, 103.13, 510.61, 108.7, 511.72, 108.7, 516.18, 114.27, 511.72, 133.23, 515.07, 143.26, 512.84, 144.38, 499.46, 141.03, 491.66, 147.72, 490.54, 156.64, 488.31, 164.44, 473.82, 168.9, 466.01, 164.44, 452.64, 171.13, 443.72, 182.28, 440.37, 190.08, 450.41, 204.58, 471.59, 212.38, 479.39, 224.65, 486.08, 234.68, 492.77, 249.17, 501.69, 255.86, 512.84, 260.32, 521.76, 267.01, 548.51, 264.78, 547.4, 274.81, 536.25, 284.85, 516.18, 302.69, 505.03, 300.46, 493.89, 283.73, 470.47, 261.44, 464.9, 255.86]], "area": 15541.893300000003, "iscrowd": 0, "image_id": 332133, "bbox": [382.4, 71.91, 166.11, 241.92], "category_id": 1, "id": 475722, "split": "val", "sentences": [{"tokens": ["the", "skateboarder", "who", "wears", "a", "hat"], "raw": "the skateboarder who wears a hat", "sent_id": 66085, "sent": "the skateboarder who wears a hat"}, {"tokens": ["skateboarder", "wearing", "a", "hat", "performing", "trick"], "raw": "skateboarder wearing a hat performing trick", "sent_id": 66086, "sent": "skateboarder wearing a hat performing trick"}], "file_name": "COCO_train2014_000000332133_475722.jpg", "ann_id": 475722, "sent_ids": [66085, 66086], "ref_id": 30397}, {"segmentation": [[109.64, 17.79, 107.71, 28.37, 104.83, 39.91, 99.06, 50.49, 93.29, 65.88, 89.44, 81.26, 86.55, 95.69, 82.71, 118.77, 76.94, 137.04, 78.86, 154.35, 86.55, 172.63, 96.17, 183.21, 110.6, 187.05, 110.6, 186.09, 111.56, 182.24, 116.37, 167.82, 118.29, 157.24, 120.21, 150.51, 127.91, 125.5, 131.75, 110.12, 134.64, 100.5, 141.37, 88.96, 149.07, 86.07, 160.61, 83.19, 171.18, 89.92, 178.88, 93.77, 188.5, 110.12, 189.46, 123.58, 205.81, 138.01, 207.73, 146.66, 205.81, 163.97, 200.04, 180.32, 193.3, 191.86, 184.65, 201.48, 198.11, 212.06, 205.81, 216.87, 213.5, 224.56, 218.31, 228.41, 229.85, 238.99, 234.66, 241.87, 240.43, 245.72, 241.39, 253.41, 242.35, 309.19, 244.27, 253.41, 248.12, 273.61, 252.93, 285.15, 255.82, 289.96, 258.7, 296.69, 259.66, 302.46, 263.51, 309.19, 267.36, 319.77, 272.16, 330.35, 276.01, 349.58, 278.9, 361.12, 278.9, 371.7, 281.78, 388.05, 284.67, 402.48, 287.55, 412.09, 293.32, 421.71, 291.4, 422.67, 273.13, 413.06, 258.7, 410.17, 238.5, 413.06, 217.35, 417.86, 185.61, 414.98, 152.91, 418.83, 118.29, 422.67, 93.29, 422.67, 76.94, 419.79, 58.66, 421.71, 34.62, 420.75, 19.23, 416.9, 14.43, 415.94, 4.81, 410.17, 5.77, 401.51, 6.73, 381.32, 8.66, 350.54, 7.69, 314.0, 8.66, 271.68, 6.73, 231.29, 4.81, 196.67, 7.69, 168.78, 8.66, 120.69, 7.69, 100.5, 4.81, 75.49, 0.96, 51.45, 1.92, 17.79, 1.92, 12.98, 10.58, 8.17, 25.97, 5.29, 46.16, 6.25, 67.32, 8.17, 81.75, 4.33, 101.94, 8.17, 104.83, 10.1, 108.67, 12.98, 111.56, 14.91]], "area": 79142.84844999998, "iscrowd": 0, "image_id": 246753, "bbox": [0.96, 4.33, 292.36, 418.34], "category_id": 1, "id": 200954, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "white", "tshirt"], "raw": "The man in the white tshirt.", "sent_id": 66103, "sent": "the man in the white tshirt"}, {"tokens": ["a", "man", "holding", "a", "camera", "taking", "a", "picture"], "raw": "A man holding a camera taking a picture.", "sent_id": 66104, "sent": "a man holding a camera taking a picture"}], "file_name": "COCO_train2014_000000246753_200954.jpg", "ann_id": 200954, "sent_ids": [66103, 66104], "ref_id": 30403}, {"segmentation": [[414.47, 354.44, 409.71, 331.58, 395.42, 297.28, 403.99, 286.8, 411.61, 268.69, 406.85, 257.26, 405.9, 240.11, 403.99, 207.71, 399.23, 198.18, 385.89, 182.94, 386.84, 169.6, 399.23, 158.17, 403.99, 147.69, 403.04, 122.91, 399.23, 117.2, 385.89, 103.86, 369.69, 96.23, 353.49, 96.23, 331.58, 105.76, 323.0, 117.2, 326.81, 134.35, 331.58, 155.31, 337.29, 173.41, 334.44, 181.99, 315.38, 186.75, 301.09, 192.47, 291.56, 202.0, 276.31, 219.15, 262.02, 227.72, 250.59, 237.25, 225.82, 243.92, 217.24, 262.02, 219.15, 274.41, 234.39, 278.22, 243.92, 282.98, 268.69, 279.17, 302.99, 278.22, 318.24, 281.08, 314.43, 300.13, 313.47, 327.77, 315.38, 347.78, 340.15, 350.63, 376.36, 353.49, 407.8, 352.54, 409.71, 352.54]], "area": 26166.44815, "iscrowd": 0, "image_id": 176342, "bbox": [217.24, 96.23, 197.23, 258.21], "category_id": 1, "id": 491634, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "cream", "color", "dress", "and", "cutting", "cake", "with", "a", "men"], "raw": "A woman wearing cream color dress and cutting cake with a men", "sent_id": 66151, "sent": "a woman wearing cream color dress and cutting cake with a men"}, {"tokens": ["a", "girl", "in", "a", "white", "head", "band", "and", "white", "dress"], "raw": "A girl in a white head band and white dress.", "sent_id": 66152, "sent": "a girl in a white head band and white dress"}], "file_name": "COCO_train2014_000000176342_491634.jpg", "ann_id": 491634, "sent_ids": [66151, 66152], "ref_id": 30422}, {"segmentation": [[205.47, 245.16, 210.89, 150.81, 218.62, 152.35, 391.85, 122.97, 447.54, 133.79, 444.44, 201.08, 442.9, 205.72, 443.67, 260.63, 443.67, 270.68, 401.91, 273.77, 383.35, 276.87, 353.19, 276.87, 338.49, 273.77, 328.44, 277.64, 311.42, 268.36, 248.78, 258.31, 230.99, 261.4, 222.49, 249.03]], "area": 31197.586549999996, "iscrowd": 0, "image_id": 257243, "bbox": [205.47, 122.97, 242.07, 154.67], "category_id": 6, "id": 166961, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "blue", "and", "orange", "double", "dekker", "bus", "on", "the", "road"], "raw": "A white and blue and orange double Dekker bus on the road.", "sent_id": 66215, "sent": "a white and blue and orange double dekker bus on the road"}, {"tokens": ["a", "white", "blue", "and", "orange", "double", "decker", "bus"], "raw": "A white blue and orange double decker bus", "sent_id": 66216, "sent": "a white blue and orange double decker bus"}], "file_name": "COCO_train2014_000000257243_166961.jpg", "ann_id": 166961, "sent_ids": [66215, 66216], "ref_id": 30446}, {"segmentation": [[350.13, 0.14, 452.02, 1.58, 452.02, 21.67, 423.32, 54.67, 403.23, 81.94, 361.61, 107.77, 353.0, 107.77, 374.53, 36.02, 374.53, 20.23, 342.96, 24.54, 321.43, 56.11, 302.78, 43.19, 295.61, 10.19, 304.22, 5.88]], "area": 8192.82755, "iscrowd": 0, "image_id": 35945, "bbox": [295.61, 0.14, 156.41, 107.63], "category_id": 1, "id": 1709691, "split": "val", "sentences": [{"tokens": ["man", "sitting", "with", "legs", "crossed"], "raw": "Man sitting with legs crossed", "sent_id": 66284, "sent": "man sitting with legs crossed"}, {"tokens": ["a", "man", "was", "sitting", "on", "chair"], "raw": "a man  was sitting on chair", "sent_id": 66285, "sent": "a man was sitting on chair"}], "file_name": "COCO_train2014_000000035945_1709691.jpg", "ann_id": 1709691, "sent_ids": [66284, 66285], "ref_id": 30473}, {"segmentation": [[106.49, 217.54, 127.96, 225.59, 149.44, 238.12, 177.18, 257.8, 184.34, 262.28, 249.66, 261.38, 298.88, 257.8, 332.89, 257.8, 361.52, 260.49, 392.84, 261.38, 439.37, 304.34, 488.59, 351.76, 493.06, 360.71, 511.86, 371.45, 534.23, 395.61, 468.01, 394.72, 366.89, 394.72, 263.09, 395.61, 170.92, 394.72, 80.54, 394.72, 15.21, 393.82, 0.0, 392.03, 0.0, 322.23, 0.89, 257.8, 0.0, 228.27, 48.32, 221.12, 91.28, 217.54, 103.8, 214.85]], "area": 68242.2033, "iscrowd": 0, "image_id": 264058, "bbox": [0.0, 214.85, 534.23, 180.76], "category_id": 65, "id": 315251, "split": "val", "sentences": [{"tokens": ["a", "bed", "in", "a", "large", "room", "near", "a", "chair"], "raw": "A bed in a large room near a chair.", "sent_id": 66319, "sent": "a bed in a large room near a chair"}, {"tokens": ["a", "colorful", "bed"], "raw": "a colorful bed", "sent_id": 66320, "sent": "a colorful bed"}], "file_name": "COCO_train2014_000000264058_315251.jpg", "ann_id": 315251, "sent_ids": [66319, 66320], "ref_id": 30488}, {"segmentation": [[116.11, 54.69, 92.12, 60.45, 69.09, 74.84, 50.86, 91.16, 46.06, 111.31, 46.06, 121.86, 53.73, 142.01, 49.9, 166.0, 51.82, 186.15, 63.33, 212.06, 77.72, 231.25, 90.2, 242.77, 91.16, 255.24, 80.6, 265.8, 75.8, 278.27, 76.76, 296.5, 71.97, 305.14, 120.9, 315.69, 171.76, 329.13, 178.48, 332.96, 176.56, 384.78, 173.68, 413.57, 171.76, 418.36, 207.26, 419.32, 207.26, 384.78, 207.26, 361.75, 211.1, 339.68, 210.14, 321.45, 203.42, 305.14, 189.03, 289.78, 171.76, 282.11, 159.29, 273.47, 146.81, 261.0, 136.26, 242.77, 132.42, 226.45, 140.09, 211.1, 137.22, 195.75, 120.9, 178.48, 118.02, 166.96, 123.78, 152.57, 125.7, 128.58, 131.46, 96.91, 131.46, 80.6, 124.74, 66.21, 121.86, 62.37]], "area": 23036.559000000012, "iscrowd": 0, "image_id": 502134, "bbox": [46.06, 54.69, 165.04, 364.63], "category_id": 1, "id": 228325, "split": "val", "sentences": [{"tokens": ["a", "lady", "wearing", "a", "mrs", ".", "claus", "suit", "sitting", "on", "the", "back", "of", "a", "motorcycle", "with", "a", "helmet", "on", ">"], "raw": "A lady wearing a Mrs. Claus suit sitting on the back of a motorcycle with a helmet on>", "sent_id": 66429, "sent": "a lady wearing a mrs . claus suit sitting on the back of a motorcycle with a helmet on >"}, {"tokens": ["a", "female", "in", "a", "santa", "claus", "costume", "riding", "as", "passenger", "behind", "a", "santa", "-", "clad", "man", "on", "a", "motorcycle"], "raw": "A female in a Santa Claus costume riding as passenger behind a Santa-clad man on a motorcycle", "sent_id": 66430, "sent": "a female in a santa claus costume riding as passenger behind a santa - clad man on a motorcycle"}], "file_name": "COCO_train2014_000000502134_228325.jpg", "ann_id": 228325, "sent_ids": [66429, 66430], "ref_id": 30530}, {"segmentation": [[196.99, 331.64, 147.12, 331.64, 53.61, 325.4, 62.34, 193.25, 69.82, 162.08, 152.1, 157.09, 206.96, 184.52, 199.48, 322.91]], "area": 23877.637399999996, "iscrowd": 0, "image_id": 125658, "bbox": [53.61, 157.09, 153.35, 174.55], "category_id": 6, "id": 2050175, "split": "val", "sentences": [{"tokens": ["red", "double", "decker", "bus", "with", "large", "plain", "white", "sign", "with", "no", "writing"], "raw": "red double decker bus with large plain white sign with no writing.", "sent_id": 66463, "sent": "red double decker bus with large plain white sign with no writing"}, {"tokens": ["the", "back", "of", "red", "bus", "parked"], "raw": "The back of red bus parked", "sent_id": 66464, "sent": "the back of red bus parked"}], "file_name": "COCO_train2014_000000125658_2050175.jpg", "ann_id": 2050175, "sent_ids": [66463, 66464], "ref_id": 30543}, {"segmentation": [[194.41, 458.79, 196.4, 472.7, 199.38, 498.53, 200.37, 529.33, 203.35, 554.17, 220.25, 570.07, 240.12, 566.1, 245.09, 559.14, 247.07, 547.22, 247.07, 537.28, 245.09, 517.41, 235.15, 502.51, 232.17, 480.65, 232.17, 470.71, 232.17, 447.86, 237.14, 430.97, 237.14, 417.05, 237.14, 409.11, 237.14, 401.16, 235.15, 391.22, 230.18, 379.3, 227.2, 371.35, 225.21, 362.41, 223.23, 354.46, 204.35, 218.33], [126.85, 198.46, 115.92, 198.46, 124.86, 188.52, 130.82, 180.57, 151.69, 174.61, 167.58, 171.63, 179.51, 170.64, 189.44, 178.59, 187.46, 180.57, 170.57, 195.48, 163.61, 204.42, 156.65, 214.36, 144.73, 225.29, 134.8, 221.31, 130.82, 207.4, 130.82, 202.43]], "area": 11721.990050000002, "iscrowd": 0, "image_id": 426877, "bbox": [115.92, 170.64, 131.15, 399.43], "category_id": 1, "id": 538007, "split": "val", "sentences": [{"tokens": ["the", "boy", "dressed", "in", "red"], "raw": "the boy dressed in red", "sent_id": 66471, "sent": "the boy dressed in red"}, {"tokens": ["a", "guy", "in", "a", "red", "outfit", "reaching", "for", "a", "frisbee"], "raw": "a guy in a red outfit reaching for a frisbee", "sent_id": 66472, "sent": "a guy in a red outfit reaching for a frisbee"}], "file_name": "COCO_train2014_000000426877_538007.jpg", "ann_id": 538007, "sent_ids": [66471, 66472], "ref_id": 30546}, {"segmentation": [[424.3, 268.26, 424.3, 268.26, 421.52, 280.59, 554.3, 288.94, 563.45, 164.5, 557.88, 164.5, 551.92, 270.65, 426.29, 265.88]], "area": 2676.0699500000032, "iscrowd": 0, "image_id": 94300, "bbox": [421.52, 164.5, 141.93, 124.44], "category_id": 84, "id": 1655220, "split": "val", "sentences": [{"tokens": ["the", "small", "portion", "of", "a", "book", "visible", "underneath", "\"", "tangerine", "bear", "\""], "raw": "The small portion of a book visible underneath \"Tangerine Bear\"", "sent_id": 66519, "sent": "the small portion of a book visible underneath \" tangerine bear \""}, {"tokens": ["the", "book", "under", "the", "red", "book"], "raw": "the book under the red book", "sent_id": 66520, "sent": "the book under the red book"}], "file_name": "COCO_train2014_000000094300_1655220.jpg", "ann_id": 1655220, "sent_ids": [66519, 66520], "ref_id": 30563}, {"segmentation": [[634.25, 309.84, 491.06, 328.45, 471.64, 326.02, 398.83, 326.02, 385.89, 292.04, 416.63, 286.38, 415.01, 277.48, 419.87, 275.06, 424.72, 262.92, 436.04, 261.3, 436.85, 243.51, 427.96, 236.22, 465.98, 232.99, 471.64, 211.15, 493.48, 211.15, 499.15, 161.8, 504.0, 199.01, 517.75, 231.37, 516.94, 232.99, 559.82, 233.8, 577.62, 231.37, 577.62, 216.81, 587.33, 216.0, 595.42, 227.33, 618.88, 224.9, 626.97, 239.46, 634.25, 232.99, 638.29, 308.22]], "area": 21388.428149999996, "iscrowd": 0, "image_id": 84162, "bbox": [385.89, 161.8, 252.4, 166.65], "category_id": 9, "id": 178927, "split": "val", "sentences": [{"tokens": ["this", "picture", "shows", "a", "ferry", "boat", "transporting", "people"], "raw": "This picture shows a ferry boat transporting people.", "sent_id": 66625, "sent": "this picture shows a ferry boat transporting people"}, {"tokens": ["a", "white", "tourist", "ship"], "raw": "a white tourist ship", "sent_id": 66626, "sent": "a white tourist ship"}], "file_name": "COCO_train2014_000000084162_178927.jpg", "ann_id": 178927, "sent_ids": [66625, 66626], "ref_id": 30606}, {"segmentation": [[252.18, 50.49, 255.94, 47.98, 264.7, 43.6, 275.35, 38.59, 287.24, 39.84, 294.75, 43.6, 301.01, 51.11, 304.14, 63.01, 304.14, 69.27, 306.02, 73.02, 299.14, 85.54, 296.0, 96.19, 284.74, 107.45, 286.61, 114.34, 292.87, 119.97, 297.88, 125.61, 301.01, 141.88, 301.64, 150.02, 299.76, 155.03, 298.51, 159.41, 296.63, 166.92, 294.13, 172.56, 285.36, 183.83, 285.36, 184.45, 279.1, 188.21, 275.35, 187.58, 274.09, 187.58, 270.34, 185.71, 267.83, 175.69, 265.96, 170.05, 264.7, 163.17, 264.7, 158.16, 259.7, 151.9, 255.31, 152.53, 241.54, 168.8, 232.78, 181.32, 224.64, 188.84, 218.38, 192.59, 212.75, 197.6, 212.12, 197.6, 203.98, 200.73, 191.46, 203.86, 192.71, 195.1, 192.71, 181.95, 192.71, 176.32, 192.71, 173.18, 193.34, 153.15, 193.96, 148.14, 195.22, 137.5, 195.22, 127.49, 197.72, 119.97, 202.1, 114.34, 211.49, 111.84, 225.27, 106.2, 237.16, 102.45, 241.54, 102.45, 249.68, 100.57, 252.81, 99.94, 254.06, 94.31, 250.93, 91.18, 248.43, 88.05, 246.55, 83.04, 244.05, 77.4, 244.05, 72.4, 244.05, 65.51, 244.67, 61.13, 247.8, 55.49, 248.43, 51.74, 250.31, 49.86, 252.18, 47.98]], "area": 10806.5016, "iscrowd": 0, "image_id": 100611, "bbox": [191.46, 38.59, 114.56, 165.27], "category_id": 1, "id": 532255, "split": "val", "sentences": [{"tokens": ["a", "lady", "sitting", "next", "to", "a", "toddler", "wiping", "her", "mouth"], "raw": "A lady sitting next to a toddler wiping her mouth.", "sent_id": 66635, "sent": "a lady sitting next to a toddler wiping her mouth"}, {"tokens": ["a", "woman", "with", "red", "hair", "wiping", "her", "chin"], "raw": "A woman with red hair wiping her chin.", "sent_id": 66636, "sent": "a woman with red hair wiping her chin"}], "file_name": "COCO_train2014_000000100611_532255.jpg", "ann_id": 532255, "sent_ids": [66635, 66636], "ref_id": 30610}, {"segmentation": [[318.1, 177.39, 311.46, 184.98, 307.19, 190.19, 305.77, 193.98, 305.77, 198.25, 318.1, 215.31, 326.63, 227.63, 322.84, 259.86, 317.15, 282.61, 316.2, 287.82, 318.1, 291.62, 328.05, 293.51, 383.98, 275.03, 405.78, 263.18, 411.47, 244.22, 406.73, 214.36, 395.82, 196.82, 378.29, 182.61, 363.12, 173.13, 347.48, 169.81, 329.94, 172.18, 322.36, 174.07]], "area": 8998.843600000002, "iscrowd": 0, "image_id": 263744, "bbox": [305.77, 169.81, 105.7, 123.7], "category_id": 53, "id": 1049535, "split": "val", "sentences": [{"tokens": ["an", "upside", "down", "apple", "beneath", "an", "orange"], "raw": "an upside down apple beneath an orange", "sent_id": 66778, "sent": "an upside down apple beneath an orange"}], "file_name": "COCO_train2014_000000263744_1049535.jpg", "ann_id": 1049535, "sent_ids": [66778], "ref_id": 30668}, {"segmentation": [[15.61, 118.93, 37.55, 120.68, 76.15, 135.6, 116.52, 142.62, 140.21, 116.3, 134.94, 104.89, 126.17, 99.62, 118.27, 99.62, 117.39, 84.71, 109.5, 61.89, 114.76, 45.22, 136.7, 28.55, 150.74, 33.82, 170.04, 50.49, 173.55, 75.93, 193.73, 75.06, 234.09, 90.85, 271.82, 133.84, 289.37, 168.94, 288.49, 190.0, 275.33, 190.88, 270.95, 193.51, 264.8, 178.59, 260.42, 160.17, 251.64, 161.04, 253.4, 190.0, 250.76, 193.51, 223.56, 186.49, 220.93, 175.96, 209.53, 177.72, 207.77, 182.1, 177.06, 174.21, 164.78, 173.33, 150.74, 168.06, 121.78, 162.8, 110.37, 167.19, 88.44, 160.17, 48.95, 140.86, 7.71, 147.88, 8.59, 133.84, 20.88, 124.19], [184.96, 184.74, 199.87, 240.89, 206.89, 211.94, 211.28, 184.74, 191.98, 179.47], [225.32, 192.63, 233.22, 215.45, 240.24, 240.01, 250.76, 211.94, 250.76, 197.9]], "area": 19867.54895, "iscrowd": 0, "image_id": 569037, "bbox": [7.71, 28.55, 281.66, 212.34], "category_id": 1, "id": 448735, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "shaved", "head", "and", "a", "gold", "watch"], "raw": "A man with a shaved head and a gold watch.", "sent_id": 66781, "sent": "a man with a shaved head and a gold watch"}, {"tokens": ["a", "man", "wearing", "an", "apron"], "raw": "A man wearing an apron.", "sent_id": 66782, "sent": "a man wearing an apron"}], "file_name": "COCO_train2014_000000569037_448735.jpg", "ann_id": 448735, "sent_ids": [66781, 66782], "ref_id": 30670}, {"segmentation": [[10.65, 62.93, 38.34, 42.7, 235.34, 39.5, 286.45, 44.83, 331.18, 81.03, 371.64, 161.96, 387.62, 226.92, 384.42, 271.65, 372.71, 290.81, 368.45, 299.33, 316.27, 300.4, 324.79, 262.06, 321.59, 248.22, 286.45, 176.87, 259.83, 125.76, 275.8, 131.08, 306.68, 134.28, 322.66, 110.85, 315.2, 91.68, 299.23, 82.1, 290.71, 83.16, 266.22, 93.81, 241.73, 99.14, 212.98, 111.91, 204.46, 132.15, 215.11, 161.96, 230.01, 173.68, 231.08, 202.43, 254.51, 258.87, 232.14, 278.04, 208.72, 290.81, 205.52, 281.23, 218.3, 270.58, 214.04, 233.31, 198.07, 194.98, 181.03, 165.16, 168.25, 173.68, 166.12, 151.32, 158.67, 139.6, 140.56, 116.17, 150.15, 82.1, 141.63, 62.93, 130.98, 55.48, 113.94, 55.48, 101.16, 64.0, 87.32, 76.77, 95.84, 114.04, 104.36, 135.34, 93.71, 154.51, 91.58, 167.29, 63.89, 176.87, 62.83, 231.18, 63.89, 236.51, 50.05, 261.0, 34.08, 262.06, 26.62, 255.67, 10.65, 259.93, 10.65, 274.84, 8.52, 317.44, 3.19, 316.37, 4.26, 59.74]], "area": 48679.39850000003, "iscrowd": 0, "image_id": 258505, "bbox": [3.19, 39.5, 384.43, 277.94], "category_id": 3, "id": 364816, "split": "val", "sentences": [{"tokens": ["a", "navy", "blue", "suv", "with", "dark", "windows", "and", "a", "silver", "grill"], "raw": "A navy blue SUV with dark windows and a silver grill.", "sent_id": 66806, "sent": "a navy blue suv with dark windows and a silver grill"}, {"tokens": ["the", "black", "suv", "behind", "the", "boys"], "raw": "the black suv behind the boys", "sent_id": 66807, "sent": "the black suv behind the boys"}], "file_name": "COCO_train2014_000000258505_364816.jpg", "ann_id": 364816, "sent_ids": [66806, 66807], "ref_id": 30679}, {"segmentation": [[10.84, 523.78, 131.24, 459.96, 179.41, 437.08, 195.06, 423.84, 190.24, 408.18, 178.2, 406.98, 170.98, 402.16, 160.14, 398.55, 154.12, 406.98, 137.27, 399.76, 134.86, 393.73, 126.43, 393.73, 122.82, 402.16, 131.24, 411.8, 26.49, 467.18, 12.04, 467.18, 2.41, 469.59, 2.41, 517.76]], "area": 8975.456449999994, "iscrowd": 0, "image_id": 275917, "bbox": [2.41, 393.73, 192.65, 130.05], "category_id": 41, "id": 644387, "split": "val", "sentences": [{"tokens": ["a", "skateboard", "laying", "upside", "down", "on", "the", "ground", "in", "front", "of", "the", "blue", "backpack"], "raw": "A skateboard laying upside down on the ground in front of the blue backpack.", "sent_id": 66969, "sent": "a skateboard laying upside down on the ground in front of the blue backpack"}, {"tokens": ["a", "skateboard", "laying", "next", "to", "a", "blue", "backpack"], "raw": "A skateboard laying next to a blue backpack", "sent_id": 66970, "sent": "a skateboard laying next to a blue backpack"}], "file_name": "COCO_train2014_000000275917_644387.jpg", "ann_id": 644387, "sent_ids": [66969, 66970], "ref_id": 30739}, {"segmentation": [[115.33, 144.35, 119.05, 155.51, 122.03, 172.63, 118.31, 189.74, 106.4, 209.09, 116.08, 233.64, 115.33, 254.48, 116.08, 267.13, 103.43, 293.17, 114.59, 296.89, 123.52, 290.94, 135.42, 277.54, 136.91, 263.41, 141.38, 241.83, 154.03, 218.76, 158.49, 245.55, 154.77, 261.92, 151.05, 279.03, 154.03, 290.94, 157.75, 302.1, 159.98, 302.84, 171.88, 296.89, 170.4, 276.8, 168.16, 265.64, 178.58, 255.97, 186.02, 243.32, 191.97, 227.69, 193.46, 209.83, 193.46, 191.23, 186.02, 162.95, 186.02, 162.95, 180.07, 155.51, 180.07, 133.19, 176.35, 113.1, 190.49, 105.66, 222.48, 101.94, 249.27, 98.96, 255.97, 100.45, 261.92, 93.75, 260.43, 85.57, 255.97, 81.85, 235.13, 81.85, 212.06, 81.85, 171.14, 70.69, 160.72, 61.76, 136.91, 47.62, 110.87, 40.18, 71.43, 46.13, 69.94, 46.88, 59.53, 58.04, 52.09, 64.74, 49.11, 73.66, 70.69, 78.87, 81.11, 93.01, 84.08, 94.5, 103.43, 100.45, 103.43, 116.82, 97.48, 126.49, 87.06, 134.68, 75.9, 146.58, 81.11, 167.42, 81.11, 171.14, 89.29, 171.88, 94.5, 167.42, 106.4, 155.51, 115.33, 151.79]], "area": 21098.32469999999, "iscrowd": 0, "image_id": 82484, "bbox": [49.11, 40.18, 212.81, 262.66], "category_id": 17, "id": 50440, "split": "val", "sentences": [{"tokens": ["a", "orange", "cat", "standing", "on", "it", "hind", "legs", "playing", "with", "another", "cat"], "raw": "A orange cat standing on it hind legs playing with another cat", "sent_id": 67055, "sent": "a orange cat standing on it hind legs playing with another cat"}, {"tokens": ["this", "is", "an", "orange", "cat", "standing", "up"], "raw": "this is an orange cat standing up", "sent_id": 67056, "sent": "this is an orange cat standing up"}], "file_name": "COCO_train2014_000000082484_50440.jpg", "ann_id": 50440, "sent_ids": [67055, 67056], "ref_id": 30773}, {"segmentation": [[336.02, 144.44, 345.41, 140.06, 347.91, 133.8, 353.54, 133.8, 355.42, 141.31, 359.18, 159.46, 359.18, 166.98, 356.68, 168.23, 386.72, 193.27, 408.01, 222.07, 411.14, 238.97, 404.88, 262.76, 390.48, 281.54, 377.96, 293.43, 367.94, 294.06, 362.94, 386.08, 361.06, 425.52, 355.42, 435.54, 354.8, 302.2, 355.42, 257.75, 352.29, 229.58, 358.55, 227.7, 364.19, 222.07, 364.81, 213.93, 349.79, 208.92, 351.67, 191.39, 347.91, 178.87, 338.52, 163.22, 332.26, 156.96, 332.26, 148.2, 342.9, 144.44]], "area": 7038.086099999999, "iscrowd": 0, "image_id": 316557, "bbox": [332.26, 133.8, 78.88, 301.74], "category_id": 1, "id": 481283, "split": "val", "sentences": [{"tokens": ["person", "in", "light", "colored", "jacket", "and", "wearing", "a", "cap", "at", "the", "end", "of", "the", "line"], "raw": "Person in light colored jacket and wearing a cap at the end of the line.", "sent_id": 67061, "sent": "person in light colored jacket and wearing a cap at the end of the line"}, {"tokens": ["the", "farthest", "person", "in", "the", "picture"], "raw": "the farthest person in the picture", "sent_id": 67062, "sent": "the farthest person in the picture"}], "file_name": "COCO_train2014_000000316557_481283.jpg", "ann_id": 481283, "sent_ids": [67061, 67062], "ref_id": 30775}, {"segmentation": [[186.09, 230.54, 178.18, 218.99, 171.49, 201.96, 176.36, 194.05, 204.33, 181.89, 220.15, 175.2, 255.42, 178.24, 277.31, 170.34, 287.65, 178.24, 297.38, 192.23, 299.2, 208.04, 299.2, 227.5, 300.42, 239.06, 309.54, 236.62, 308.33, 220.81, 310.76, 203.18, 308.33, 189.8, 308.33, 178.85, 334.48, 184.32, 342.99, 200.14, 355.76, 223.25, 362.45, 232.37, 370.96, 227.5, 370.36, 220.81, 352.72, 188.58, 339.95, 172.77, 325.96, 159.39, 329.61, 133.85, 339.95, 106.48, 346.03, 104.05, 364.88, 116.21, 375.83, 125.33, 387.99, 125.94, 392.25, 118.04, 385.56, 95.54, 380.69, 82.77, 368.53, 60.87, 366.71, 56.01, 361.23, 57.83, 354.54, 63.3, 333.26, 69.99, 295.55, 86.41, 265.76, 96.75, 237.17, 103.44, 200.69, 103.44, 173.93, 110.13, 161.16, 105.87, 141.09, 102.83, 124.67, 112.56, 120.41, 129.59, 119.19, 162.43, 125.88, 177.63, 133.18, 187.36, 137.44, 192.84, 144.74, 187.97, 145.95, 181.28, 134.4, 163.65, 135.01, 149.66, 143.52, 134.46, 152.64, 125.33, 156.9, 127.77, 152.64, 144.19, 153.25, 160.0, 153.86, 172.77, 148.39, 179.46, 148.99, 190.41, 137.44, 195.88, 133.18, 192.84, 127.71, 211.08, 127.1, 223.85, 126.49, 241.49, 138.66, 244.53, 147.17, 243.31, 139.26, 229.33, 140.48, 206.83, 148.99, 202.57, 155.07, 197.7, 167.24, 226.89, 171.49, 234.8, 186.7, 240.88, 190.96, 237.23, 182.44, 227.5]], "area": 22477.906549999996, "iscrowd": 0, "image_id": 454246, "bbox": [119.19, 56.01, 273.06, 188.52], "category_id": 19, "id": 54922, "split": "val", "sentences": [{"tokens": ["the", "brown", "horse", "with", "white", "hooves", "is", "next", "to", "the", "horse", "outside"], "raw": "The brown horse with white hooves is next to the horse outside.", "sent_id": 67134, "sent": "the brown horse with white hooves is next to the horse outside"}, {"tokens": ["two", "horses", "on", "a", "plot", "of", "dirt"], "raw": "Two horses on a plot of dirt", "sent_id": 67135, "sent": "two horses on a plot of dirt"}], "file_name": "COCO_train2014_000000454246_54922.jpg", "ann_id": 54922, "sent_ids": [67134, 67135], "ref_id": 30801}, {"segmentation": [[146.63, 288.2, 117.98, 288.2, 97.75, 260.39, 90.17, 251.97, 31.18, 262.08, 7.58, 245.22, 0.0, 206.46, 47.19, 187.92, 49.72, 164.33, 42.98, 144.94, 66.57, 106.18, 121.35, 92.7, 141.57, 87.64, 148.31, 49.72, 157.58, 29.49, 178.65, 8.43, 203.09, 0.0, 241.85, 26.12, 246.91, 41.29, 241.01, 75.84, 237.64, 104.49, 248.6, 126.4, 220.79, 131.46, 201.4, 147.47, 198.03, 178.65, 203.09, 193.82, 169.38, 198.03, 142.42, 208.15, 144.94, 244.38, 160.11, 262.92]], "area": 34314.578250000006, "iscrowd": 0, "image_id": 66669, "bbox": [0.0, 0.0, 248.6, 288.2], "category_id": 88, "id": 1161123, "split": "val", "sentences": [{"tokens": ["an", "orange", "cat", "stuffed", "animal"], "raw": "an orange cat stuffed animal", "sent_id": 67185, "sent": "an orange cat stuffed animal"}, {"tokens": ["the", "teddy", "bear", "that", "is", "as", "large", "as", "the", "baby"], "raw": "The teddy bear that is as large as the baby.", "sent_id": 67186, "sent": "the teddy bear that is as large as the baby"}], "file_name": "COCO_train2014_000000066669_1161123.jpg", "ann_id": 1161123, "sent_ids": [67185, 67186], "ref_id": 30821}, {"segmentation": [[125.12, 593.98, 143.82, 598.29, 169.71, 595.42, 184.09, 593.98, 202.79, 591.1, 207.1, 605.48, 238.74, 605.48, 260.31, 595.42, 258.88, 542.2, 268.94, 480.36, 258.88, 419.96, 264.63, 384.0, 276.13, 345.17, 270.38, 309.21, 271.82, 279.01, 300.58, 277.57, 314.97, 264.63, 313.53, 237.3, 306.34, 194.16, 289.08, 163.96, 270.38, 148.13, 248.81, 132.31, 244.49, 107.87, 237.3, 87.73, 212.85, 80.54, 191.28, 80.54, 186.97, 99.24, 189.84, 123.69, 197.03, 138.07, 171.15, 158.2, 143.82, 195.6, 133.75, 232.99, 129.44, 264.63, 112.18, 325.03, 92.04, 358.11, 96.36, 373.93, 103.55, 381.12, 120.81, 360.99, 123.69, 343.73, 129.44, 322.16, 133.75, 314.97, 139.51, 323.6, 133.75, 352.36, 140.94, 385.44, 149.57, 425.71, 156.76, 477.48, 156.76, 514.88, 158.2, 552.27, 142.38, 581.03, 126.56, 593.98]], "area": 64665.97124999997, "iscrowd": 0, "image_id": 221169, "bbox": [92.04, 80.54, 222.93, 524.94], "category_id": 1, "id": 1729360, "split": "val", "sentences": [{"tokens": ["the", "man", "standing", "with", "umbrella"], "raw": "The man standing with umbrella", "sent_id": 67228, "sent": "the man standing with umbrella"}, {"tokens": ["man", "in", "too", "-", "small", "black", "shirt", "and", "white", "sneakers"], "raw": "man in too-small black shirt and white sneakers", "sent_id": 67229, "sent": "man in too - small black shirt and white sneakers"}], "file_name": "COCO_train2014_000000221169_1729360.jpg", "ann_id": 1729360, "sent_ids": [67228, 67229], "ref_id": 30841}, {"segmentation": [[73.89, 548.34, 120.46, 505.89, 151.97, 478.49, 164.3, 444.25, 165.67, 431.92, 147.86, 416.85, 131.42, 433.29, 90.33, 444.25, 86.22, 429.17, 130.06, 396.31, 145.11, 378.51, 131.42, 344.26, 138.27, 329.19, 145.11, 325.08, 176.63, 345.63, 180.74, 319.6, 180.74, 271.66, 179.36, 247.01, 197.18, 251.11, 195.8, 279.87, 201.28, 349.74, 232.79, 412.75, 232.79, 468.9, 232.79, 522.33, 217.72, 536.02, 184.84, 563.42, 183.47, 586.7, 161.55, 574.37, 156.07, 549.71, 176.63, 538.75, 199.91, 516.85, 198.54, 485.34, 173.88, 509.99, 162.93, 508.62, 105.41, 538.75, 79.37, 568.9, 65.68, 568.9, 61.57, 559.3]], "area": 20642.872899999995, "iscrowd": 0, "image_id": 424165, "bbox": [61.57, 247.01, 171.22, 339.69], "category_id": 1, "id": 440735, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "black", "shorts", "on", "a", "tennis", "court", "is", "about", "to", "hit", "the", "ball"], "raw": "A man in a white shirt and black shorts on a tennis court is about to hit the ball", "sent_id": 67259, "sent": "a man in a white shirt and black shorts on a tennis court is about to hit the ball"}, {"tokens": ["a", "man", "is", "jumping", "up", "to", "serve", "a", "tennis", "ball"], "raw": "A man is jumping up to serve a tennis ball.", "sent_id": 67260, "sent": "a man is jumping up to serve a tennis ball"}], "file_name": "COCO_train2014_000000424165_440735.jpg", "ann_id": 440735, "sent_ids": [67259, 67260], "ref_id": 30851}, {"segmentation": [[382.25, 253.75, 382.25, 253.75, 407.02, 271.44, 428.25, 300.93, 433.56, 325.69, 426.48, 350.46, 419.41, 395.88, 399.95, 405.9, 376.94, 391.75, 373.41, 374.64, 365.74, 364.03, 353.35, 364.03, 340.38, 320.39, 336.84, 292.08, 327.41, 267.31, 335.66, 254.34, 355.12, 247.85, 378.12, 246.67, 382.25, 251.39]], "area": 10868.583849999999, "iscrowd": 0, "image_id": 547974, "bbox": [327.41, 246.67, 106.15, 159.23], "category_id": 22, "id": 1821220, "split": "val", "sentences": [{"tokens": ["butt", "of", "the", "farthest", "elephant"], "raw": "butt of the farthest elephant", "sent_id": 67271, "sent": "butt of the farthest elephant"}, {"tokens": ["the", "back", "end", "of", "the", "elephant", "in", "the", "front"], "raw": "The back end of the elephant in the front.", "sent_id": 67272, "sent": "the back end of the elephant in the front"}], "file_name": "COCO_train2014_000000547974_1821220.jpg", "ann_id": 1821220, "sent_ids": [67271, 67272], "ref_id": 30855}, {"segmentation": [[377.09, 162.28, 373.77, 172.23, 371.56, 199.88, 373.77, 207.62, 370.45, 223.1, 359.4, 250.75, 348.34, 272.86, 335.07, 288.35, 308.53, 289.45, 293.05, 290.56, 286.41, 304.93, 298.57, 314.89, 315.16, 306.04, 326.22, 307.14, 330.64, 317.1, 332.86, 338.11, 374.88, 381.24, 392.57, 398.93, 375.98, 405.56, 390.36, 414.41, 421.32, 408.88, 447.86, 401.14, 458.92, 415.52, 463.34, 436.53, 481.04, 447.59, 502.05, 433.21, 504.26, 419.94, 492.1, 395.61, 479.93, 350.27, 492.1, 327.05, 506.47, 306.04, 493.2, 273.97, 482.14, 210.94, 452.29, 196.56, 446.76, 157.86, 419.11, 140.16, 392.57, 133.53, 377.09, 146.8, 371.56, 166.7]], "area": 34666.14625, "iscrowd": 0, "image_id": 68786, "bbox": [286.41, 133.53, 220.06, 314.06], "category_id": 1, "id": 190362, "split": "val", "sentences": [{"tokens": ["a", "man", "smoking", "a", "cigaret"], "raw": "a man smoking a cigaret", "sent_id": 67306, "sent": "a man smoking a cigaret"}, {"tokens": ["man", "squatting", "smoking", "cigarette", "holding", "a", "towel"], "raw": "Man squatting smoking cigarette holding a towel.", "sent_id": 67307, "sent": "man squatting smoking cigarette holding a towel"}], "file_name": "COCO_train2014_000000068786_190362.jpg", "ann_id": 190362, "sent_ids": [67306, 67307], "ref_id": 30868}, {"segmentation": [[378.07, 299.15, 366.68, 277.8, 357.43, 242.22, 346.05, 204.5, 342.49, 195.96, 328.25, 195.96, 341.78, 184.57, 349.6, 164.65, 344.62, 139.74, 361.7, 114.12, 381.63, 107.72, 399.42, 109.85, 431.44, 105.58, 459.91, 127.64, 484.1, 129.07, 507.59, 129.07, 528.94, 139.74, 541.04, 169.63, 549.58, 195.25, 555.27, 220.16, 553.85, 256.45, 555.27, 268.55, 564.52, 283.49, 552.42, 282.07, 549.58, 265.7, 548.15, 235.1, 541.04, 242.93, 538.9, 268.55, 542.46, 314.09, 502.61, 311.96, 508.3, 261.43, 491.22, 250.05, 451.37, 240.08, 447.81, 269.26, 447.81, 301.28, 455.64, 309.82, 425.75, 311.25, 430.02, 292.74, 417.21, 239.37, 400.84, 295.59, 409.38, 306.98, 371.67, 309.11]], "area": 31400.000099999994, "iscrowd": 0, "image_id": 40433, "bbox": [328.25, 105.58, 236.27, 208.51], "category_id": 22, "id": 583467, "split": "val", "sentences": [{"tokens": ["an", "elephant", "which", "is", "standing", "on", "the", "right", "side", "of", "the", "two", "elephants"], "raw": "An elephant which is standing on the right side of the two elephants.", "sent_id": 67312, "sent": "an elephant which is standing on the right side of the two elephants"}, {"tokens": ["the", "bigger", "elephant", "on", "the", "right"], "raw": "The bigger elephant on the right.", "sent_id": 67313, "sent": "the bigger elephant on the right"}], "file_name": "COCO_train2014_000000040433_583467.jpg", "ann_id": 583467, "sent_ids": [67312, 67313], "ref_id": 30871}, {"segmentation": [[259.4, 41.25, 295.84, 7.79, 330.05, 5.56, 358.3, 15.97, 359.79, 22.66, 375.41, 0.35, 498.11, 20.43, 498.11, 131.23, 464.64, 154.29, 443.82, 173.62, 428.95, 167.67, 391.77, 167.67, 360.53, 155.77, 339.71, 146.11, 331.53, 135.69, 325.58, 129.75, 315.17, 129.0, 302.53, 129.0, 287.66, 123.05, 279.48, 108.92, 277.99, 106.69, 260.89, 100.0, 254.94, 80.67, 255.68, 62.82]], "area": 32209.582899999994, "iscrowd": 0, "image_id": 103430, "bbox": [254.94, 0.35, 243.17, 173.27], "category_id": 58, "id": 1068377, "split": "val", "sentences": [{"tokens": ["the", "top", "right", "food"], "raw": "The top right food.", "sent_id": 67372, "sent": "the top right food"}], "file_name": "COCO_train2014_000000103430_1068377.jpg", "ann_id": 1068377, "sent_ids": [67372], "ref_id": 30893}, {"segmentation": [[398.83, 9.21, 504.73, 11.96, 499.23, 38.09, 489.6, 60.09, 471.72, 79.35, 449.72, 98.6, 442.84, 141.23, 441.47, 181.12, 459.34, 189.37, 470.35, 204.5, 463.47, 211.37, 434.59, 221.0, 407.08, 215.5, 389.2, 201.75, 386.45, 196.24, 393.33, 185.24, 422.21, 179.74, 434.59, 97.22, 418.09, 79.35, 402.96, 51.84]], "area": 10494.471400000008, "iscrowd": 0, "image_id": 528151, "bbox": [386.45, 9.21, 118.28, 211.79], "category_id": 46, "id": 662211, "split": "val", "sentences": [{"tokens": ["liquor", "on", "a", "glass"], "raw": "LIQUOR ON A GLASS", "sent_id": 67450, "sent": "liquor on a glass"}, {"tokens": ["wine", "glass", "on", "the", "right", "hand", "side", "of", "the", "pizza"], "raw": "wine glass on the right hand side of the pizza", "sent_id": 67451, "sent": "wine glass on the right hand side of the pizza"}], "file_name": "COCO_train2014_000000528151_662211.jpg", "ann_id": 662211, "sent_ids": [67450, 67451], "ref_id": 30923}, {"segmentation": [[77.03, 408.5, 78.15, 395.06, 100.56, 364.8, 108.4, 346.87, 105.04, 321.1, 147.63, 267.31, 158.83, 258.34, 165.55, 248.26, 189.09, 247.14, 192.45, 265.07, 184.6, 279.63, 180.12, 289.72, 177.88, 293.08, 180.12, 299.81, 161.07, 313.25, 148.75, 330.06, 159.95, 352.47, 136.42, 400.66, 159.95, 407.38, 139.78, 419.71, 110.65, 409.62, 107.28, 404.02, 125.21, 364.8, 103.92, 382.73, 103.92, 398.42, 110.65, 410.74, 93.84, 416.35, 79.27, 408.5, 78.15, 399.54]], "area": 8236.101349999999, "iscrowd": 0, "image_id": 32707, "bbox": [77.03, 247.14, 115.42, 172.57], "category_id": 1, "id": 539319, "split": "val", "sentences": [{"tokens": ["skier", "in", "orange", "coat", "in", "the", "right", "hand", "picture"], "raw": "skier in orange coat in the right hand picture", "sent_id": 67460, "sent": "skier in orange coat in the right hand picture"}, {"tokens": ["skier", "with", "black", "pants", "and", "orange", "jacket", "facing", "another", "skier", "in", "a", "green", "ski", "suit"], "raw": "Skier with black pants and orange jacket facing another skier in a green ski suit", "sent_id": 67461, "sent": "skier with black pants and orange jacket facing another skier in a green ski suit"}], "file_name": "COCO_train2014_000000032707_539319.jpg", "ann_id": 539319, "sent_ids": [67460, 67461], "ref_id": 30927}, {"segmentation": [[119.5, 277.73, 0.0, 287.69, 0.0, 283.26, 0.0, 164.87, 118.39, 181.46, 118.39, 276.62]], "area": 12975.1764, "iscrowd": 0, "image_id": 22195, "bbox": [0.0, 164.87, 119.5, 122.82], "category_id": 7, "id": 2171674, "split": "val", "sentences": [{"tokens": ["the", "train", "cart", "in", "front", "of", "and", "to", "the", "side", "of", "the", "blue", "train"], "raw": "The train cart in front of and to the side of the blue train.", "sent_id": 67480, "sent": "the train cart in front of and to the side of the blue train"}, {"tokens": ["the", "brown", "train", "next", "to", "the", "blue", "train"], "raw": "The brown train next to the blue train.", "sent_id": 67481, "sent": "the brown train next to the blue train"}], "file_name": "COCO_train2014_000000022195_2171674.jpg", "ann_id": 2171674, "sent_ids": [67480, 67481], "ref_id": 30936}, {"segmentation": [[167.66, 273.57, 186.75, 249.93, 213.12, 216.28, 239.49, 190.82, 248.58, 171.73, 249.49, 151.73, 235.85, 147.18, 243.12, 140.82, 253.13, 140.82, 263.13, 132.63, 268.58, 117.17, 285.86, 120.81, 293.13, 132.63, 304.05, 151.73, 305.86, 167.18, 313.14, 183.55, 298.59, 185.37, 273.13, 173.55, 263.13, 185.37, 234.03, 248.11, 230.4, 277.2, 238.58, 304.48, 235.85, 347.22, 230.4, 384.5, 224.94, 438.14, 232.21, 466.33, 222.21, 462.69, 216.76, 377.22, 216.76, 351.76, 211.3, 395.41, 204.03, 421.78, 204.94, 449.96, 195.84, 448.14, 186.75, 439.96, 190.39, 387.22, 179.48, 384.5, 171.29, 421.78, 167.66, 426.32, 164.02, 376.31, 149.47, 328.12, 154.02, 300.84]], "area": 17355.7725, "iscrowd": 0, "image_id": 321766, "bbox": [149.47, 117.17, 163.67, 349.16], "category_id": 25, "id": 596091, "split": "val", "sentences": [{"tokens": ["two", "zibras", "standing", "on", "road"], "raw": "Two zibras standing on road.", "sent_id": 67636, "sent": "two zibras standing on road"}, {"tokens": ["a", "giraffe", "looking", "to", "the", "right"], "raw": "a giraffe looking to the right.", "sent_id": 67637, "sent": "a giraffe looking to the right"}], "file_name": "COCO_train2014_000000321766_596091.jpg", "ann_id": 596091, "sent_ids": [67636, 67637], "ref_id": 30994}, {"segmentation": [[342.37, 299.57, 377.95, 286.11, 379.88, 271.68, 380.84, 241.87, 378.91, 194.75, 378.91, 181.28, 402.0, 187.05, 392.38, 270.72, 397.19, 329.39, 403.92, 349.58, 399.11, 357.28, 391.42, 346.7, 387.57, 317.85, 368.34, 330.35, 365.45, 382.28, 361.6, 379.4, 361.6, 313.04, 341.41, 309.19, 341.41, 341.89, 335.64, 337.08, 333.71, 306.31], [293.32, 288.03, 301.02, 280.34, 301.02, 343.81, 293.32, 340.93, 297.17, 296.69]], "area": 4437.155749999998, "iscrowd": 0, "image_id": 252093, "bbox": [293.32, 181.28, 110.6, 201.0], "category_id": 62, "id": 380957, "split": "val", "sentences": [{"tokens": ["a", "brown", "chair", "that", "the", "woman", "is", "sitting", "on"], "raw": "A brown chair that the woman is sitting on.", "sent_id": 67661, "sent": "a brown chair that the woman is sitting on"}, {"tokens": ["the", "chair", "the", "woman", "in", "pink", "is", "sitting", "in"], "raw": "The chair the woman in pink is sitting in", "sent_id": 67662, "sent": "the chair the woman in pink is sitting in"}], "file_name": "COCO_train2014_000000252093_380957.jpg", "ann_id": 380957, "sent_ids": [67661, 67662], "ref_id": 31003}, {"segmentation": [[331.04, 286.64, 280.77, 279.05, 200.14, 78.91, 180.22, 125.39, 195.4, 156.69, 0.0, 237.31, 0.95, 1.13, 278.87, 0.0, 293.1, 1.13, 333.89, 264.82, 331.99, 281.9]], "area": 62124.48285000001, "iscrowd": 0, "image_id": 61460, "bbox": [0.0, 0.0, 333.89, 286.64], "category_id": 1, "id": 456376, "split": "val", "sentences": [{"tokens": ["a", "hand", ",", "blue", "suitcase", ",", "and", "faded", "jeans"], "raw": "A hand, blue suitcase, and faded jeans", "sent_id": 67757, "sent": "a hand , blue suitcase , and faded jeans"}, {"tokens": ["a", "person", "wearing", "jeans"], "raw": "A person wearing jeans", "sent_id": 67758, "sent": "a person wearing jeans"}], "file_name": "COCO_train2014_000000061460_456376.jpg", "ann_id": 456376, "sent_ids": [67757, 67758], "ref_id": 31041}, {"segmentation": [[10.2, 140.28, 1.46, 136.64, 2.91, 78.34, 41.54, 52.11, 88.91, 38.26, 123.16, 40.45, 151.58, 38.99, 173.44, 55.02, 182.19, 72.51, 222.27, 74.7, 239.03, 78.34, 238.3, 91.46, 215.71, 90.73, 209.15, 95.83, 187.29, 90.73, 181.46, 115.51, 180.73, 137.37, 168.34, 136.64, 155.95, 129.35, 147.21, 114.05, 132.63, 113.32, 131.9, 122.06, 107.85, 121.34, 91.82, 127.17, 125.34, 124.98, 134.09, 126.44, 122.43, 135.18, 72.87, 139.55, 65.59, 131.54, 40.08, 141.01, 18.95, 141.01, 8.74, 141.01]], "area": 16318.962049999996, "iscrowd": 0, "image_id": 149180, "bbox": [1.46, 38.26, 237.57, 102.75], "category_id": 18, "id": 15142, "split": "val", "sentences": [{"tokens": ["golden", "dog", "in", "back"], "raw": "golden dog in back", "sent_id": 67787, "sent": "golden dog in back"}, {"tokens": ["a", "smaller", "dog", "with", "eyes", "open"], "raw": "A smaller dog with eyes open", "sent_id": 67788, "sent": "a smaller dog with eyes open"}], "file_name": "COCO_train2014_000000149180_15142.jpg", "ann_id": 15142, "sent_ids": [67787, 67788], "ref_id": 31053}, {"segmentation": [[344.09, 365.66, 344.09, 328.99, 339.78, 298.79, 338.7, 283.69, 333.3, 272.9, 323.6, 264.27, 316.04, 259.96, 311.73, 257.8, 308.49, 251.33, 308.49, 243.78, 308.49, 230.83, 302.02, 222.2, 284.76, 215.73, 268.58, 218.97, 262.11, 221.12, 265.35, 232.99, 266.43, 242.7, 261.03, 255.64, 268.58, 265.35, 269.66, 266.43, 258.88, 283.69, 250.25, 308.49, 247.01, 330.07, 261.03, 341.93, 259.96, 355.96, 254.56, 367.82, 244.85, 377.53, 212.49, 402.34, 210.34, 416.36, 217.89, 432.54, 221.12, 441.17, 225.44, 445.48, 241.62, 431.46, 242.7, 422.83, 254.56, 414.2, 270.74, 401.26, 282.61, 391.55, 292.31, 378.61, 300.94, 371.06, 304.18, 368.9, 321.44, 360.27, 339.78, 362.43, 344.09, 368.9]], "area": 13746.48305, "iscrowd": 0, "image_id": 547974, "bbox": [210.34, 215.73, 133.75, 229.75], "category_id": 1, "id": 456918, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "dark", "shirt", "and", "pink", "pants"], "raw": "A woman in a dark shirt and pink pants", "sent_id": 67818, "sent": "a woman in a dark shirt and pink pants"}, {"tokens": ["the", "elephant", "rider", "with", "a", "flower", "in", "her", "hair"], "raw": "The elephant rider with a flower in her hair.", "sent_id": 67819, "sent": "the elephant rider with a flower in her hair"}], "file_name": "COCO_train2014_000000547974_456918.jpg", "ann_id": 456918, "sent_ids": [67818, 67819], "ref_id": 31066}, {"segmentation": [[448.5, 206.98, 449.27, 203.37, 448.24, 198.21, 447.46, 193.56, 448.75, 186.6, 450.82, 182.73, 450.3, 178.08, 451.85, 169.82, 456.75, 157.95, 463.98, 157.69, 467.08, 154.08, 468.37, 145.05, 467.59, 139.11, 463.46, 132.92, 463.21, 127.24, 459.33, 123.37, 453.91, 121.82, 448.5, 118.72, 441.01, 116.4, 433.53, 117.43, 433.53, 116.66, 433.53, 113.56, 435.33, 109.69, 436.37, 106.08, 435.33, 103.24, 435.59, 97.05, 432.75, 92.92, 428.37, 84.4, 418.04, 83.11, 411.08, 85.18, 406.69, 89.3, 403.33, 93.95, 402.56, 99.63, 401.01, 105.3, 400.75, 107.89, 401.78, 111.5, 403.07, 115.11, 404.37, 115.63, 406.43, 115.89, 408.24, 117.95, 407.98, 120.01, 407.2, 121.82, 401.27, 121.31, 391.46, 123.11, 384.24, 128.53, 381.14, 130.34, 373.91, 126.72, 365.91, 124.66, 352.24, 121.56, 345.27, 117.43, 342.69, 115.37, 341.91, 113.82, 338.82, 111.24, 335.98, 106.6, 334.69, 103.5, 332.11, 100.92, 329.27, 99.11, 326.43, 98.85, 325.65, 101.18, 323.07, 101.95, 321.27, 102.72, 319.98, 106.85, 321.01, 110.47, 322.56, 113.05, 325.65, 115.37, 327.72, 116.4, 331.33, 121.56, 333.4, 123.37, 336.49, 124.4, 339.85, 125.95, 351.2, 134.72, 357.91, 142.21, 369.78, 145.82, 374.17, 148.4, 376.49, 147.63, 381.91, 149.43, 384.24, 150.47, 388.62, 153.31, 389.4, 163.11, 390.95, 173.18, 390.17, 182.98, 392.75, 187.63, 392.24, 188.92, 389.91, 195.37, 390.43, 203.63, 389.14, 209.56, 387.59, 214.98, 385.78, 222.73, 386.04, 228.4, 387.33, 233.05, 389.66, 236.66, 390.43, 241.57, 389.91, 248.28, 388.11, 253.18, 383.46, 261.18, 381.91, 284.4, 380.36, 295.24, 380.11, 301.7, 378.82, 304.02, 378.3, 316.15, 380.11, 321.57, 385.01, 322.34, 388.37, 321.05, 392.75, 315.89, 397.14, 306.08, 399.72, 299.89, 400.75, 285.44, 406.43, 268.15, 408.24, 257.82, 411.08, 249.82, 415.46, 243.89, 417.78, 243.37, 419.08, 250.6, 420.88, 255.76, 422.95, 260.4, 423.46, 263.76, 421.66, 265.31, 418.82, 269.95, 415.98, 272.53, 414.95, 270.73, 411.85, 271.76, 407.2, 273.57, 405.66, 276.92, 405.4, 278.99, 405.66, 281.82, 406.95, 287.24, 410.3, 294.73, 411.08, 305.31, 412.88, 314.6, 418.04, 321.57, 422.69, 323.12, 426.04, 318.21, 427.85, 307.11, 428.11, 299.11, 426.3, 294.99, 427.08, 293.95, 427.85, 290.34, 433.01, 284.66, 436.62, 283.37, 442.04, 281.82, 444.62, 278.73, 443.08, 272.79, 450.3, 267.37, 452.37, 255.76, 453.91, 247.24, 452.88, 230.21, 452.62, 226.08, 452.88, 218.34, 450.82, 212.66, 448.75, 209.31]], "area": 13978.684100000006, "iscrowd": 0, "image_id": 482731, "bbox": [319.98, 83.11, 148.39, 240.01], "category_id": 1, "id": 556392, "split": "val", "sentences": [{"tokens": ["player", "in", "the", "jersey", "labeled", "49"], "raw": "Player in the jersey labeled 49.", "sent_id": 67826, "sent": "player in the jersey labeled 49"}, {"tokens": ["a", "player", "with", "no", "49"], "raw": "A player with no 49", "sent_id": 67827, "sent": "a player with no 49"}], "file_name": "COCO_train2014_000000482731_556392.jpg", "ann_id": 556392, "sent_ids": [67826, 67827], "ref_id": 31070}, {"segmentation": [[326.1, 470.44, 327.17, 432.77, 327.17, 422.01, 332.56, 388.65, 332.56, 378.96, 334.71, 371.43, 332.56, 345.6, 339.01, 314.39, 368.07, 305.78, 393.9, 305.78, 419.73, 311.16, 438.03, 314.39, 438.03, 317.61, 438.03, 327.3, 435.87, 349.9, 443.41, 377.88, 459.55, 409.09, 462.78, 446.76, 461.7, 458.6, 461.7, 462.91, 458.48, 472.59, 329.33, 468.29], [505.83, 469.36, 634.98, 471.52, 637.13, 346.67, 627.44, 317.61, 633.9, 301.47, 633.9, 275.64, 627.44, 233.67, 610.22, 217.52, 597.31, 201.38, 574.71, 189.54, 558.57, 200.3, 556.41, 209.99, 561.79, 263.8, 561.79, 269.18, 552.11, 269.18, 537.04, 258.42, 538.12, 239.05, 520.9, 233.67, 512.29, 234.74, 500.45, 245.51, 502.6, 254.12, 512.29, 263.8, 523.05, 265.96, 538.12, 272.41, 539.19, 277.79, 533.81, 285.33, 535.96, 291.78, 539.19, 301.47, 539.19, 307.93, 547.8, 317.61, 552.11, 324.07, 561.79, 344.52, 565.02, 372.5, 565.02, 382.19, 559.64, 396.18, 545.65, 422.01, 542.42, 430.62, 537.04, 432.77, 526.28, 420.93, 542.42, 406.94, 538.12, 391.87, 531.66, 380.04, 519.82, 372.5, 509.06, 375.73, 507.98, 389.72, 507.98, 413.4, 503.68, 465.06, 500.45, 469.36, 503.68, 472.59]], "area": 44683.72660000001, "iscrowd": 0, "image_id": 47294, "bbox": [326.1, 189.54, 311.03, 283.05], "category_id": 4, "id": 154514, "split": "val", "sentences": [{"tokens": ["a", "white", "motorcycle", "with", "the", "letters", "nypd"], "raw": "A white motorcycle with the letters NYPD.", "sent_id": 67981, "sent": "a white motorcycle with the letters nypd"}, {"tokens": ["nypd", "bike", "being", "ridden", "by", "black", "cop"], "raw": "NYPD bike being ridden by black cop", "sent_id": 67982, "sent": "nypd bike being ridden by black cop"}], "file_name": "COCO_train2014_000000047294_154514.jpg", "ann_id": 154514, "sent_ids": [67981, 67982], "ref_id": 31130}, {"segmentation": [[480.0, 320.83, 480.0, 387.32, 360.73, 447.17, 334.13, 482.08, 362.39, 502.03, 260.99, 533.61, 251.01, 630.03, 172.88, 631.69, 132.99, 611.74, 96.42, 536.94, 88.1, 513.66, 108.05, 498.7, 166.23, 540.26, 211.12, 407.27, 247.69, 377.35, 224.42, 349.09, 184.52, 332.47, 209.45, 294.23, 234.39, 304.21, 202.81, 314.18, 224.42, 335.79, 249.35, 339.12, 269.3, 329.14, 244.36, 309.19, 294.23, 310.86, 327.48, 295.9, 357.4, 294.23, 357.4, 211.12, 402.29, 194.49, 447.17, 212.78, 453.82, 259.32, 458.81, 300.88]], "area": 70283.05050000001, "iscrowd": 0, "image_id": 28154, "bbox": [88.1, 194.49, 391.9, 437.2], "category_id": 1, "id": 2166503, "split": "val", "sentences": [{"tokens": ["a", "girl", "wearing", "earrings", "and", "sitting", "in", "the", "middle", "of", "the", "couch", "is", "playing", "wii"], "raw": "A girl wearing earrings and sitting in the middle of the couch is playing Wii.", "sent_id": 67995, "sent": "a girl wearing earrings and sitting in the middle of the couch is playing wii"}, {"tokens": ["a", "woman", "sitting", "between", "two", "other", "people", "with", "a", "pink", "shirt", "playing", "a", "video", "game"], "raw": "A woman sitting between two other people with a pink shirt playing a video game.", "sent_id": 67996, "sent": "a woman sitting between two other people with a pink shirt playing a video game"}], "file_name": "COCO_train2014_000000028154_2166503.jpg", "ann_id": 2166503, "sent_ids": [67995, 67996], "ref_id": 31136}, {"segmentation": [[310.11, 101.97, 266.29, 26.97, 135.67, 5.06, 138.2, 69.94, 136.52, 132.3, 218.26, 168.54]], "area": 19726.541250000006, "iscrowd": 0, "image_id": 63238, "bbox": [135.67, 5.06, 174.44, 163.48], "category_id": 54, "id": 313171, "split": "val", "sentences": [{"tokens": ["dark", "brown", "sandwich", "to", "left", "of", "white", "sandwich", "in", "middle", "row", "of", "food", "platters"], "raw": "Dark brown sandwich to left of white sandwich in middle row of food platters.", "sent_id": 68022, "sent": "dark brown sandwich to left of white sandwich in middle row of food platters"}], "file_name": "COCO_train2014_000000063238_313171.jpg", "ann_id": 313171, "sent_ids": [68022], "ref_id": 31144}, {"segmentation": [[142.33, 188.31, 163.45, 185.87, 172.38, 186.68, 187.01, 162.31, 197.57, 155.0, 209.75, 155.0, 227.62, 161.5, 232.5, 169.62, 220.31, 174.5, 192.69, 187.49, 186.19, 206.18, 203.25, 222.43, 210.56, 228.11, 204.06, 241.92, 187.82, 245.98, 191.88, 262.23, 185.38, 267.92, 174.82, 280.1, 164.26, 284.98, 157.76, 306.91, 165.07, 321.53, 172.38, 351.59, 186.19, 370.27, 212.19, 346.71, 218.69, 367.02, 191.07, 408.45, 177.26, 412.51, 169.13, 406.83, 149.64, 389.77, 137.45, 375.14, 129.33, 359.71, 117.96, 386.52, 144.76, 401.95, 159.39, 416.57, 166.7, 440.13, 156.14, 461.25, 139.08, 475.06, 117.14, 503.49, 138.27, 506.74, 144.76, 513.24, 137.45, 535.99, 131.77, 541.67, 112.27, 542.49, 100.9, 540.86, 55.41, 518.93, 55.41, 495.37, 27.79, 480.75, 15.6, 458.82, 0.98, 402.76, 13.17, 336.15, 53.78, 276.04, 69.22, 254.92, 88.71, 244.36, 107.4, 250.04, 110.65, 232.17, 110.65, 216.74, 110.65, 206.18, 126.89, 194.81]], "area": 45197.5062, "iscrowd": 0, "image_id": 15190, "bbox": [0.98, 155.0, 231.52, 387.49], "category_id": 1, "id": 1744573, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "grey", "hat", "carrying", "a", "camera", "is", "looking", "at", "an", "elephant"], "raw": "A man in a grey hat carrying a camera is looking at an elephant.", "sent_id": 68023, "sent": "a man in a grey hat carrying a camera is looking at an elephant"}, {"tokens": ["man", "carrying", "a", "camera", "while", "wearing", "a", "grey", "hat"], "raw": "Man carrying a camera while wearing a grey hat.", "sent_id": 68024, "sent": "man carrying a camera while wearing a grey hat"}], "file_name": "COCO_train2014_000000015190_1744573.jpg", "ann_id": 1744573, "sent_ids": [68023, 68024], "ref_id": 31145}, {"segmentation": [[125.77, 421.47, 110.93, 372.26, 100.77, 351.95, 96.09, 327.73, 69.53, 302.73, 83.59, 284.77, 78.9, 259.77, 62.5, 251.96, 45.31, 259.77, 42.19, 283.99, 47.65, 295.7, 26.56, 312.11, 14.06, 330.86, 6.25, 368.35, 10.94, 397.25, 25.0, 383.97, 23.44, 373.04, 23.44, 359.76, 28.91, 359.76, 32.81, 383.19, 74.99, 355.07, 85.93, 373.82, 89.06, 392.57, 110.93, 418.34, 113.27, 426.16, 129.68, 426.16]], "area": 8364.551399999998, "iscrowd": 0, "image_id": 206062, "bbox": [6.25, 251.96, 123.43, 174.2], "category_id": 1, "id": 1709496, "split": "val", "sentences": [{"tokens": ["man", "wearing", "gray", "wetsuit", "carrying", "a", "yellow", "surfboard", "watching", "another", "man", "on", "waves"], "raw": "Man wearing gray wetsuit carrying a yellow surfboard watching another man on waves", "sent_id": 68044, "sent": "man wearing gray wetsuit carrying a yellow surfboard watching another man on waves"}, {"tokens": ["man", "holding", "a", "surf", "board", "in", "hand"], "raw": "man holding a surf board in hand", "sent_id": 68045, "sent": "man holding a surf board in hand"}], "file_name": "COCO_train2014_000000206062_1709496.jpg", "ann_id": 1709496, "sent_ids": [68044, 68045], "ref_id": 31153}, {"segmentation": [[533.68, 197.16, 583.23, 202.32, 615.23, 205.42, 631.74, 208.52, 632.77, 219.87, 637.94, 232.26, 640.0, 249.81, 635.87, 269.42, 635.87, 282.84, 637.94, 303.48, 637.94, 310.71, 637.94, 347.87, 637.94, 347.87, 640.0, 347.87, 640.0, 348.9, 597.68, 342.71, 580.13, 333.42, 570.84, 288.0, 562.58, 273.55, 548.13, 240.52, 541.94, 218.84, 535.74, 204.39, 535.74, 198.19, 533.68, 199.23, 533.68, 199.23]], "area": 10655.252150000004, "iscrowd": 0, "image_id": 469293, "bbox": [533.68, 197.16, 106.32, 151.74], "category_id": 62, "id": 101503, "split": "val", "sentences": [{"tokens": ["empty", "chair", "back"], "raw": "Empty chair back.", "sent_id": 68104, "sent": "empty chair back"}, {"tokens": ["a", "brown", "chair", "behind", "an", "old", "asian", "woman"], "raw": "A brown chair behind an old asian woman", "sent_id": 68105, "sent": "a brown chair behind an old asian woman"}], "file_name": "COCO_train2014_000000469293_101503.jpg", "ann_id": 101503, "sent_ids": [68104, 68105], "ref_id": 31175}, {"segmentation": [[416.07, 286.86, 434.49, 130.84, 454.0, 113.5, 458.33, 109.16, 452.91, 91.83, 443.16, 59.32, 450.74, 34.4, 482.17, 38.74, 503.84, 53.91, 503.84, 91.83, 490.84, 98.33, 519.01, 109.16, 567.77, 154.67, 574.27, 225.1, 547.18, 245.69, 545.01, 374.63, 529.84, 460.23, 480.0, 461.31, 487.58, 352.96, 481.08, 351.87, 438.83, 462.39, 405.24, 458.06, 425.82, 303.12]], "area": 45963.097749999986, "iscrowd": 0, "image_id": 131277, "bbox": [405.24, 34.4, 169.03, 427.99], "category_id": 1, "id": 528823, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "blue", "jacket"], "raw": "A man wearing a blue jacket.", "sent_id": 68117, "sent": "a man wearing a blue jacket"}, {"tokens": ["a", "man", "holding", "a", "remote", "standing", "next", "to", "a", "woman"], "raw": "A man holding a remote standing next to a woman.", "sent_id": 68118, "sent": "a man holding a remote standing next to a woman"}], "file_name": "COCO_train2014_000000131277_528823.jpg", "ann_id": 528823, "sent_ids": [68117, 68118], "ref_id": 31179}, {"segmentation": [[296.88, 317.59, 322.54, 305.68, 322.54, 312.09, 328.95, 311.18, 346.36, 291.02, 394.93, 295.6, 432.5, 279.11, 469.15, 269.03, 480.15, 249.79, 490.23, 243.37, 503.97, 256.2, 515.88, 242.46, 506.72, 225.05, 512.22, 215.88, 489.31, 188.39, 485.64, 196.64, 395.85, 205.8, 322.54, 214.05, 303.3, 236.96, 306.05, 255.28, 284.06, 322.17]], "area": 16430.233500000002, "iscrowd": 0, "image_id": 12824, "bbox": [284.06, 188.39, 231.82, 133.78], "category_id": 20, "id": 62042, "split": "val", "sentences": [{"tokens": ["sheep", "is", "running", "in", "the", "forest"], "raw": "Sheep is running in the forest", "sent_id": 68247, "sent": "sheep is running in the forest"}, {"tokens": ["sheep", "that", "isnt", "blurry"], "raw": "SHEEP THAT ISNT BLURRY", "sent_id": 68248, "sent": "sheep that isnt blurry"}], "file_name": "COCO_train2014_000000012824_62042.jpg", "ann_id": 62042, "sent_ids": [68247, 68248], "ref_id": 31231}, {"segmentation": [[16.33, 223.67, 228.57, 227.76, 226.94, 214.69, 202.45, 210.61, 259.59, 208.98, 262.04, 160.0, 269.39, 211.43, 294.69, 202.45, 292.24, 133.88, 307.76, 184.49, 323.27, 198.37, 363.27, 187.76, 396.73, 179.59, 431.84, 187.76, 480.0, 177.96, 483.27, 184.49, 442.45, 189.39, 442.45, 195.92, 448.98, 207.35, 493.88, 211.43, 520.0, 233.47, 535.51, 253.06, 487.35, 282.45, 458.78, 288.98, 462.04, 302.86, 465.31, 324.9, 441.63, 329.8, 437.55, 324.9, 437.55, 302.86, 442.45, 286.53, 366.53, 274.29, 327.35, 263.67, 308.57, 241.63, 291.43, 241.63, 269.39, 250.61, 245.71, 250.61, 226.12, 233.47]], "area": 22683.538699999994, "iscrowd": 0, "image_id": 277243, "bbox": [16.33, 133.88, 519.18, 195.92], "category_id": 5, "id": 160412, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "brown", "private", "airplane", "stopped", "on", "a", "runway"], "raw": "A white and brown private airplane stopped on a runway.", "sent_id": 68249, "sent": "a white and brown private airplane stopped on a runway"}, {"tokens": ["a", "white", "plane", "on", "the", "asphalt"], "raw": "A white plane on the asphalt", "sent_id": 68250, "sent": "a white plane on the asphalt"}], "file_name": "COCO_train2014_000000277243_160412.jpg", "ann_id": 160412, "sent_ids": [68249, 68250], "ref_id": 31232}, {"segmentation": [[422.98, 255.07, 423.48, 275.99, 412.03, 279.48, 409.04, 273.5, 386.13, 273.5, 386.13, 259.56, 386.13, 251.59, 388.12, 247.11, 374.18, 243.62, 377.66, 235.65, 367.7, 220.21, 360.23, 215.23, 357.24, 217.22, 353.26, 209.75, 348.28, 208.76, 341.8, 211.74, 335.83, 217.22, 336.82, 225.69, 329.35, 235.15, 328.36, 245.11, 318.39, 245.61, 314.91, 235.15, 317.9, 229.67, 327.86, 230.17, 336.32, 212.24, 343.3, 205.77, 363.22, 207.76, 380.15, 210.25, 384.63, 210.25, 416.51, 207.26, 423.98, 208.76, 427.47, 216.73, 432.45, 225.19, 435.43, 233.16, 435.93, 240.13, 426.47, 275.99]], "area": 3930.906250000001, "iscrowd": 0, "image_id": 397362, "bbox": [314.91, 205.77, 121.02, 73.71], "category_id": 63, "id": 114856, "split": "val", "sentences": [{"tokens": ["a", "leather", "love", "seat", "behind", "a", "table"], "raw": "A leather love seat behind a table", "sent_id": 68310, "sent": "a leather love seat behind a table"}, {"tokens": ["the", "couch", "sitting", "in", "front", "of", "the", "window"], "raw": "The couch sitting in front of the window", "sent_id": 68311, "sent": "the couch sitting in front of the window"}], "file_name": "COCO_train2014_000000397362_114856.jpg", "ann_id": 114856, "sent_ids": [68310, 68311], "ref_id": 31258}, {"segmentation": [[336.84, 149.82, 325.24, 195.22, 315.66, 197.23, 266.73, 191.43, 232.68, 185.38, 234.95, 180.08, 248.82, 161.67, 274.3, 127.37, 299.26, 91.31, 318.18, 68.61, 340.37, 70.63, 354.5, 70.63, 351.22, 85.26, 341.89, 128.38]], "area": 8507.527600000001, "iscrowd": 0, "image_id": 423343, "bbox": [232.68, 68.61, 121.82, 128.62], "category_id": 84, "id": 1139168, "split": "val", "sentences": [{"tokens": ["an", "advertisement", "on", "a", "sheet", "of", "paper", "next", "to", "a", "laptop"], "raw": "An advertisement on a sheet of paper next to a laptop.", "sent_id": 68312, "sent": "an advertisement on a sheet of paper next to a laptop"}, {"tokens": ["a", "magazine", "partially", "behind", "an", "open", "laptop"], "raw": "A magazine partially behind an open laptop.", "sent_id": 68313, "sent": "a magazine partially behind an open laptop"}], "file_name": "COCO_train2014_000000423343_1139168.jpg", "ann_id": 1139168, "sent_ids": [68312, 68313], "ref_id": 31259}, {"segmentation": [[208.95, 469.04, 127.12, 590.32, 119.82, 607.85, 86.21, 621.0, 59.91, 623.93, 40.91, 609.32, 5.84, 607.85, 4.38, 606.39, 1.46, 632.69, 333.15, 629.77, 333.15, 618.08, 296.62, 588.86, 277.63, 556.71, 255.71, 502.65]], "area": 21628.943049999998, "iscrowd": 0, "image_id": 309084, "bbox": [1.46, 469.04, 331.69, 163.65], "category_id": 65, "id": 315572, "split": "val", "sentences": [{"tokens": ["a", "large", "mattress", "with", "a", "blue", "flower", "on", "it"], "raw": "a large mattress with a blue flower on it", "sent_id": 68334, "sent": "a large mattress with a blue flower on it"}], "file_name": "COCO_train2014_000000309084_315572.jpg", "ann_id": 315572, "sent_ids": [68334], "ref_id": 31267}, {"segmentation": [[400.01, 336.18, 215.5, 486.89, 191.55, 522.1, 326.77, 524.92, 422.55, 424.92, 405.64, 409.42, 404.24, 396.75, 422.55, 389.71, 433.81, 386.89, 429.59, 382.66, 443.67, 382.66, 411.28, 336.18]], "area": 20549.257199999996, "iscrowd": 0, "image_id": 275917, "bbox": [191.55, 336.18, 252.12, 188.74], "category_id": 41, "id": 642651, "split": "val", "sentences": [{"tokens": ["the", "skateboard", "being", "held", "by", "the", "man", "in", "the", "white", "shirt"], "raw": "The skateboard being held by the man in the white shirt.", "sent_id": 68406, "sent": "the skateboard being held by the man in the white shirt"}, {"tokens": ["the", "skateboard", "being", "held"], "raw": "The skateboard being held", "sent_id": 68407, "sent": "the skateboard being held"}], "file_name": "COCO_train2014_000000275917_642651.jpg", "ann_id": 642651, "sent_ids": [68406, 68407], "ref_id": 31300}, {"segmentation": [[638.21, 164.23, 480.0, 134.1, 375.61, 144.86, 355.16, 154.55, 344.39, 169.61, 325.02, 262.17, 325.02, 292.3, 347.62, 311.68, 357.31, 339.66, 469.24, 329.97, 640.0, 294.46, 640.0, 165.31]], "area": 53326.88435000002, "iscrowd": 0, "image_id": 136736, "bbox": [325.02, 134.1, 314.98, 205.56], "category_id": 7, "id": 174962, "split": "val", "sentences": [{"tokens": ["a", "train", "with", "red", "and", "blue", "markings"], "raw": "a train with red and blue markings", "sent_id": 68449, "sent": "a train with red and blue markings"}, {"tokens": ["the", "train", "numbered", "8343"], "raw": "The train numbered 8343.", "sent_id": 68450, "sent": "the train numbered 8343"}], "file_name": "COCO_train2014_000000136736_174962.jpg", "ann_id": 174962, "sent_ids": [68449, 68450], "ref_id": 31315}, {"segmentation": [[415.14, 306.49, 415.14, 280.54, 424.86, 222.16, 424.86, 213.51, 416.22, 199.46, 409.73, 194.05, 397.84, 194.05, 381.62, 191.89, 369.73, 187.57, 351.35, 187.57, 343.78, 182.16, 337.3, 181.08, 332.97, 176.76, 326.49, 185.41, 316.7, 197.53, 309.03, 202.64, 309.03, 198.55, 310.56, 193.44, 306.98, 189.35, 304.94, 186.79, 293.69, 190.37, 280.9, 198.55, 276.81, 198.04, 277.32, 192.42, 290.11, 184.75, 294.71, 180.65, 294.71, 179.63, 284.99, 181.68, 281.92, 185.26, 281.92, 186.79, 278.86, 185.26, 277.32, 180.14, 280.39, 174.52, 281.41, 170.94, 285.5, 163.27, 300.85, 157.13, 303.4, 157.13, 317.21, 157.64, 320.28, 157.64, 325.9, 156.11, 327.44, 152.02, 333.57, 148.95, 341.76, 148.95, 343.8, 148.95, 357.61, 145.37, 379.09, 145.37, 386.25, 143.84, 392.89, 146.9, 397.5, 147.42, 437.9, 149.46, 447.61, 149.46, 450.17, 150.48, 459.37, 149.97, 461.93, 150.99, 463.47, 152.53, 463.47, 153.55, 468.07, 155.09, 471.14, 155.09, 473.18, 151.51, 475.23, 147.93, 473.18, 141.79, 475.23, 135.65, 477.78, 127.47, 482.9, 115.2, 505.4, 102.92, 520.23, 101.9, 525.34, 105.99, 538.13, 114.69, 548.35, 122.87, 552.45, 133.1, 550.4, 149.46, 544.78, 159.69, 543.24, 165.31, 543.24, 166.34, 542.73, 175.54, 547.84, 184.75, 558.07, 196.51, 567.28, 197.53, 551.35, 247.03, 538.38, 290.27, 529.73, 297.84, 524.32, 314.05, 513.51, 320.54, 496.22, 318.38, 502.7, 325.95, 517.84, 325.95, 528.65, 328.11, 522.16, 334.59, 504.86, 340.0, 490.81, 333.51, 487.57, 334.59, 483.24, 332.43, 478.92, 332.43, 468.11, 330.27, 463.78, 324.86, 464.86, 319.46, 470.27, 316.22, 459.46, 316.22]], "area": 30402.05660000001, "iscrowd": 0, "image_id": 551524, "bbox": [276.81, 101.9, 290.47, 238.1], "category_id": 1, "id": 470140, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "red", "color", "tshirt", "pouring", "wine", "in", "glass"], "raw": "A man wearing red color tshirt pouring wine in glass", "sent_id": 68463, "sent": "a man wearing red color tshirt pouring wine in glass"}, {"tokens": ["a", "man", "behind", "the", "counter", "pouring", "a", "drink", "into", "a", "glass"], "raw": "A man behind the counter pouring a drink into a glass.", "sent_id": 68464, "sent": "a man behind the counter pouring a drink into a glass"}], "file_name": "COCO_train2014_000000551524_470140.jpg", "ann_id": 470140, "sent_ids": [68463, 68464], "ref_id": 31320}, {"segmentation": [[237.44, 227.35, 197.69, 259.39, 192.01, 268.72, 196.88, 271.56, 270.7, 270.75, 291.39, 249.25, 295.04, 253.31, 302.34, 251.28, 308.02, 250.06, 327.49, 245.19, 330.73, 241.14, 323.43, 228.16, 321.81, 221.67, 382.24, 163.26, 376.16, 158.39, 289.76, 183.54, 277.6, 194.49, 274.76, 191.25, 268.27, 192.46, 263.8, 196.52, 263.8, 202.6, 260.56, 204.23, 257.72, 203.42, 255.34, 200.06, 251.11, 196.0, 247.72, 196.68, 245.52, 199.56, 244.67, 198.71, 243.49, 197.69, 240.27, 199.22, 239.25, 201.59, 241.96, 204.13, 245.69, 211.24, 242.81, 209.21, 240.1, 208.53, 235.87, 212.6, 237.56, 216.49, 238.24, 222.59, 237.39, 226.31]], "area": 8864.072650000007, "iscrowd": 0, "image_id": 532711, "bbox": [192.01, 158.39, 190.23, 113.17], "category_id": 67, "id": 1959975, "split": "val", "sentences": [{"tokens": ["table", "nearest", "woman", "in", "white"], "raw": "table nearest woman in white", "sent_id": 68501, "sent": "table nearest woman in white"}], "file_name": "COCO_train2014_000000532711_1959975.jpg", "ann_id": 1959975, "sent_ids": [68501], "ref_id": 31332}, {"segmentation": [[544.38, 338.09, 511.91, 297.98, 440.28, 304.66, 427.87, 306.57, 435.51, 327.58, 320.9, 338.09, 255.96, 307.53, 226.35, 292.25, 208.2, 279.83, 240.67, 264.55, 238.76, 249.27, 224.44, 248.31, 217.75, 205.34, 266.46, 134.66, 270.28, 127.02, 251.18, 122.25, 201.52, 194.83, 148.99, 216.8, 106.97, 290.34, 103.15, 327.58, 44.89, 342.87, 16.24, 364.83, 528.15, 366.74]], "area": 35986.79944999999, "iscrowd": 0, "image_id": 390565, "bbox": [16.24, 122.25, 528.14, 244.49], "category_id": 4, "id": 153235, "split": "val", "sentences": [{"tokens": ["the", "front", "bike", "in", "the", "right", "hand", "picture"], "raw": "the front bike in the right hand picture", "sent_id": 68504, "sent": "the front bike in the right hand picture"}, {"tokens": ["the", "orange", "motorcycle"], "raw": "The orange motorcycle", "sent_id": 68505, "sent": "the orange motorcycle"}], "file_name": "COCO_train2014_000000390565_153235.jpg", "ann_id": 153235, "sent_ids": [68504, 68505], "ref_id": 31333}, {"segmentation": [[94.71, 96.86, 71.03, 132.38, 72.11, 166.82, 43.05, 199.1, 58.12, 284.13, 89.33, 333.63, 97.94, 387.44, 99.01, 438.03, 115.16, 480.0, 151.75, 480.0, 137.76, 397.13, 140.99, 389.6, 176.5, 480.0, 210.94, 477.85, 204.48, 417.58, 187.26, 340.09, 177.58, 291.66, 167.89, 247.53, 150.67, 212.02, 129.15, 163.59, 142.06, 117.31, 120.54, 75.34]], "area": 35435.14655, "iscrowd": 0, "image_id": 77332, "bbox": [43.05, 75.34, 167.89, 404.66], "category_id": 1, "id": 207603, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "button", "up", "shirt", "and", "jeans"], "raw": "A man in a button up shirt and jeans.", "sent_id": 68615, "sent": "a man in a button up shirt and jeans"}, {"tokens": ["an", "older", "man", "wearing", "jeans", ",", "a", "black", "belt", "and", "a", "striped", "shirt"], "raw": "An older man wearing jeans, a black belt and a striped shirt.", "sent_id": 68616, "sent": "an older man wearing jeans , a black belt and a striped shirt"}], "file_name": "COCO_train2014_000000077332_207603.jpg", "ann_id": 207603, "sent_ids": [68615, 68616], "ref_id": 31375}, {"segmentation": [[204.94, 472.45, 218.97, 444.4, 247.01, 426.07, 272.9, 395.87, 298.79, 371.06, 326.83, 361.35, 347.33, 367.82, 384.0, 405.57, 416.36, 428.22, 454.11, 456.27, 480.0, 474.61]], "area": 16887.3486, "iscrowd": 0, "image_id": 547974, "bbox": [204.94, 361.35, 275.06, 113.26], "category_id": 22, "id": 583199, "split": "val", "sentences": [{"tokens": ["an", "elephant", "with", "a", "woman", "on", "top", "of", "it", "with", "a", "flower", "in", "her", "hair"], "raw": "An elephant with a woman on top of it with a flower in her hair.", "sent_id": 68648, "sent": "an elephant with a woman on top of it with a flower in her hair"}, {"tokens": ["the", "back", "of", "the", "elephant", "whose", "rider", "is", "wearing", "black"], "raw": "The back of the elephant whose rider is wearing black.", "sent_id": 68649, "sent": "the back of the elephant whose rider is wearing black"}], "file_name": "COCO_train2014_000000547974_583199.jpg", "ann_id": 583199, "sent_ids": [68648, 68649], "ref_id": 31388}, {"segmentation": [[503.29, 20.02, 512.39, 8.19, 525.13, 3.64, 539.7, 7.28, 556.99, 12.74, 567.0, 23.66, 571.55, 35.49, 577.01, 63.71, 569.73, 81.91, 574.28, 91.92, 583.38, 101.93, 624.34, 121.04, 640.0, 130.15, 640.0, 173.83, 637.99, 192.94, 635.26, 212.97, 627.07, 232.08, 623.43, 240.27, 617.97, 244.82, 601.58, 245.73, 587.02, 263.02, 587.02, 275.76, 587.02, 291.24, 581.56, 324.91, 571.55, 329.46, 568.82, 337.65, 505.11, 324.91, 503.29, 320.36, 498.74, 320.36, 480.54, 320.36, 411.37, 313.08, 397.72, 304.89, 396.81, 300.34, 435.03, 259.38, 438.67, 254.83, 449.6, 248.46, 452.33, 243.91, 458.7, 241.18, 474.17, 229.35, 481.45, 212.97, 489.64, 196.58, 486.91, 197.49, 480.54, 203.87, 471.44, 221.16, 463.25, 222.98, 451.42, 227.53, 442.31, 228.44, 435.94, 228.44, 425.93, 223.89, 425.02, 208.42, 420.47, 198.4, 418.65, 192.94, 416.83, 183.84, 418.65, 182.93, 420.47, 175.65, 425.93, 173.83, 432.3, 172.01, 437.76, 171.1, 443.22, 168.37, 446.87, 171.1, 450.51, 180.2, 452.33, 174.74, 471.44, 143.8, 473.26, 131.97, 477.81, 130.15, 474.17, 121.04, 479.63, 112.85, 507.84, 101.93, 505.11, 91.92, 500.56, 81.0, 497.83, 70.99, 496.01, 57.34, 497.83, 45.51, 502.38, 36.4, 502.38, 27.3], [599.76, 272.12, 602.49, 296.7, 587.93, 336.74, 595.21, 278.49]], "area": 45663.35585000001, "iscrowd": 0, "image_id": 342996, "bbox": [396.81, 3.64, 243.19, 334.01], "category_id": 1, "id": 227023, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "red", "tie", "gesturing", "at", "the", "woman", "in", "blue"], "raw": "The man in red tie gesturing at the woman in blue.", "sent_id": 68668, "sent": "the man in red tie gesturing at the woman in blue"}, {"tokens": ["a", "man"], "raw": "a man", "sent_id": 68669, "sent": "a man"}], "file_name": "COCO_train2014_000000342996_227023.jpg", "ann_id": 227023, "sent_ids": [68668, 68669], "ref_id": 31395}, {"segmentation": [[314.98, 145.22, 338.84, 141.13, 354.53, 126.81, 357.94, 97.49, 375.66, 82.49, 385.89, 79.08, 394.07, 78.4, 406.35, 81.12, 417.26, 93.4, 423.39, 104.31, 424.76, 113.85, 419.98, 124.76, 415.21, 132.94, 411.12, 137.72, 406.35, 142.49, 401.57, 153.4, 396.12, 155.44, 389.98, 158.85, 385.89, 164.99, 411.8, 197.04, 419.98, 207.95, 425.44, 209.31, 451.35, 207.95, 469.08, 204.54, 483.4, 206.58, 489.53, 213.4, 492.26, 219.54, 492.94, 224.49, 488.85, 227.9, 477.94, 228.58, 475.21, 228.58, 465.67, 229.26, 451.35, 242.9, 440.44, 246.99, 416.57, 240.17, 414.53, 232.67, 389.3, 238.81, 386.57, 252.45, 387.94, 264.04, 392.03, 272.22, 392.03, 281.77, 385.89, 289.95, 384.53, 296.77, 389.3, 313.81, 390.66, 322.68, 389.3, 327.45, 350.44, 329.5, 336.12, 322.68, 331.34, 318.59, 324.53, 310.4, 314.98, 306.31, 299.98, 303.59, 295.89, 302.9, 295.21, 298.13, 299.98, 278.36, 302.71, 259.95, 303.39, 242.9, 302.02, 216.99, 299.98, 201.99, 299.3, 182.9, 297.93, 165.85, 304.75, 149.49, 318.39, 142.67], [295.21, 332.9, 299.98, 339.72, 302.02, 344.5, 299.98, 349.27, 288.39, 347.91, 293.16, 330.18]], "area": 23332.407449999988, "iscrowd": 0, "image_id": 511930, "bbox": [288.39, 78.4, 204.55, 270.87], "category_id": 1, "id": 470071, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "black", "smock"], "raw": "A man wearing a black smock.", "sent_id": 68746, "sent": "a man wearing a black smock"}, {"tokens": ["man", "in", "black", "apron", "slicing", "meat", "off", "an", "animal", "'", "s", "leg"], "raw": "Man in black apron slicing meat off an animal's leg.", "sent_id": 68747, "sent": "man in black apron slicing meat off an animal ' s leg"}], "file_name": "COCO_train2014_000000511930_470071.jpg", "ann_id": 470071, "sent_ids": [68746, 68747], "ref_id": 31420}, {"segmentation": [[63.9, 2.62, 83.24, 75.77, 126.12, 114.45, 128.64, 150.6, 134.53, 167.42, 141.26, 169.1, 143.78, 169.1, 151.35, 169.1, 158.91, 167.42, 161.43, 165.74, 167.32, 163.21, 171.52, 160.69, 174.05, 158.17, 179.09, 153.13, 180.77, 150.6, 190.86, 140.51, 202.63, 123.7, 213.57, 95.11, 200.11, 53.07, 206.84, 34.57, 206.84, 16.07, 244.67, 14.39, 248.88, 18.6, 239.63, 69.89, 232.9, 75.77, 237.11, 89.22, 272.42, 122.86, 297.65, 137.15, 312.78, 129.58, 316.98, 121.17, 316.98, 105.2, 312.78, 95.95, 305.21, 90.06, 305.21, 68.2, 315.3, 1.78]], "area": 25582.98345, "iscrowd": 0, "image_id": 377017, "bbox": [63.9, 1.78, 253.08, 167.32], "category_id": 1, "id": 485321, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "brick", "in", "his", "hand"], "raw": "The man with the brick in his hand.", "sent_id": 68750, "sent": "the man with the brick in his hand"}, {"tokens": ["a", "man", "kneeling"], "raw": "a man kneeling", "sent_id": 68751, "sent": "a man kneeling"}], "file_name": "COCO_train2014_000000377017_485321.jpg", "ann_id": 485321, "sent_ids": [68750, 68751], "ref_id": 31422}, {"segmentation": [[288.85, 393.25, 295.74, 391.37, 286.97, 384.48, 281.34, 366.95, 276.33, 342.54, 278.21, 321.25, 277.58, 307.48, 261.31, 307.48, 241.9, 303.1, 239.4, 295.59, 242.53, 289.33, 257.55, 291.2, 278.21, 288.7, 278.21, 273.05, 281.97, 259.9, 276.96, 253.02, 268.82, 243.63, 271.32, 231.73, 281.97, 227.35, 291.98, 226.73, 302.0, 235.49, 307.01, 249.26, 310.14, 256.77, 316.4, 271.17, 312.01, 299.97, 315.14, 318.75, 305.75, 331.27, 304.5, 346.29, 312.64, 368.2, 318.27, 390.74, 324.53, 395.12, 332.67, 400.76, 326.41, 413.9, 308.26, 414.53, 293.23, 405.77, 283.84, 400.13, 290.73, 397.63]], "area": 6623.915749999999, "iscrowd": 0, "image_id": 32707, "bbox": [239.4, 226.73, 93.27, 187.8], "category_id": 1, "id": 1715003, "split": "val", "sentences": [{"tokens": ["a", "skier", "in", "a", "green", "outfit"], "raw": "A skier in a green outfit.", "sent_id": 68811, "sent": "a skier in a green outfit"}, {"tokens": ["someone", "in", "a", "green", "ski", "waiting", "to", "ski"], "raw": "Someone in a green ski waiting to ski.", "sent_id": 68812, "sent": "someone in a green ski waiting to ski"}], "file_name": "COCO_train2014_000000032707_1715003.jpg", "ann_id": 1715003, "sent_ids": [68811, 68812], "ref_id": 31446}, {"segmentation": [[278.1, 574.36, 196.05, 587.59, 176.2, 575.68, 172.23, 528.04, 200.02, 498.92, 206.64, 494.95, 225.16, 521.42, 227.81, 493.63, 243.69, 481.72, 245.01, 502.89, 254.28, 512.16, 268.84, 500.24, 271.48, 481.72, 295.3, 475.1, 296.63, 475.1, 301.92, 472.45, 316.48, 460.54, 356.18, 448.63, 386.62, 489.66, 410.44, 510.83, 415.73, 566.42, 417.06, 600.82, 403.82, 623.32, 361.47, 614.06, 342.95, 592.88, 309.86, 577.0]], "area": 25249.7867, "iscrowd": 0, "image_id": 69344, "bbox": [172.23, 448.63, 244.83, 174.69], "category_id": 61, "id": 1088521, "split": "val", "sentences": [{"tokens": ["a", "cake", "with", "candles", "in", "it"], "raw": "a cake with candles in it", "sent_id": 68813, "sent": "a cake with candles in it"}, {"tokens": ["a", "birthday", "cake", "with", "candles"], "raw": "A birthday cake with candles.", "sent_id": 68814, "sent": "a birthday cake with candles"}], "file_name": "COCO_train2014_000000069344_1088521.jpg", "ann_id": 1088521, "sent_ids": [68813, 68814], "ref_id": 31447}, {"segmentation": [[131.81, 287.5, 185.3, 284.64, 247.39, 277.0, 405.94, 252.16, 431.73, 243.57, 427.91, 208.22, 396.39, 205.36, 324.75, 189.12, 252.16, 179.57, 185.3, 168.11, 164.29, 163.33, 145.18, 163.33, 126.08, 173.84, 118.44, 176.7, 116.53, 192.94, 118.44, 256.94, 119.39, 273.17, 119.39, 282.73]], "area": 27271.346149999994, "iscrowd": 0, "image_id": 22195, "bbox": [116.53, 163.33, 315.2, 124.17], "category_id": 7, "id": 173586, "split": "val", "sentences": [{"tokens": ["blue", "train"], "raw": "blue train", "sent_id": 68820, "sent": "blue train"}, {"tokens": ["the", "train"], "raw": "the train", "sent_id": 68821, "sent": "the train"}], "file_name": "COCO_train2014_000000022195_173586.jpg", "ann_id": 173586, "sent_ids": [68820, 68821], "ref_id": 31450}, {"segmentation": [[120.22, 284.27, 131.46, 253.93, 115.73, 248.31, 124.72, 235.96, 137.08, 252.81, 149.44, 240.45, 152.81, 229.21, 148.31, 217.98, 175.28, 219.1, 187.64, 191.01, 206.74, 196.63, 207.87, 217.98, 197.75, 230.34, 204.49, 238.2, 206.74, 264.04, 203.37, 297.75, 213.48, 312.36, 210.11, 322.47, 193.26, 329.21, 208.99, 347.19, 204.49, 353.93, 170.79, 338.2, 157.3, 334.83, 147.19, 335.96, 141.57, 343.82, 130.34, 342.7, 122.47, 330.34, 120.22, 321.35, 113.48, 313.48, 112.36, 301.12, 115.73, 292.13]], "area": 10263.796150000004, "iscrowd": 0, "image_id": 141952, "bbox": [112.36, 191.01, 101.12, 162.92], "category_id": 1, "id": 524443, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "indian", "style", "in", "front", "of", "a", "pizza", "wearing", "a", "red", "jacket"], "raw": "A man sitting indian style in front of a pizza wearing a red jacket.", "sent_id": 68857, "sent": "a man sitting indian style in front of a pizza wearing a red jacket"}, {"tokens": ["a", "man", "in", "red", "shirt", "offering", "a", "piece", "of", "pizza", "to", "her", "lady", "love"], "raw": "A man in red shirt offering a piece of pizza to her lady love", "sent_id": 68858, "sent": "a man in red shirt offering a piece of pizza to her lady love"}], "file_name": "COCO_train2014_000000141952_524443.jpg", "ann_id": 524443, "sent_ids": [68857, 68858], "ref_id": 31462}, {"segmentation": [[177.53, 492.13, 210.11, 491.01, 222.47, 416.85, 230.34, 362.92, 224.72, 328.09, 224.72, 278.65, 224.72, 251.69, 222.47, 223.6, 217.98, 201.12, 207.87, 188.76, 187.64, 162.92, 175.28, 142.7, 153.93, 130.34, 140.45, 175.28, 141.57, 192.13, 144.94, 197.75, 133.71, 208.99, 132.58, 238.2, 133.71, 278.65, 164.04, 317.98, 168.54, 348.31, 178.65, 398.88, 178.65, 416.85, 178.65, 444.94, 170.79, 477.53]], "area": 21457.734799999995, "iscrowd": 0, "image_id": 522062, "bbox": [132.58, 130.34, 97.76, 361.79], "category_id": 1, "id": 515650, "split": "val", "sentences": [{"tokens": ["a", "man", "'", "s", "hand", "holding", "a", "wine", "glass", "in", "the", "foreground", "with", "a", "guy", "in", "a", "suit", "standing", "in", "background", "with", "a", "glass"], "raw": "A man's hand holding a wine glass in the foreground with a guy in a suit standing in background with a glass", "sent_id": 68925, "sent": "a man ' s hand holding a wine glass in the foreground with a guy in a suit standing in background with a glass"}, {"tokens": ["a", "man", "in", "a", "black", "tshirt", "with", "white", "writing"], "raw": "A man in a black tshirt with white writing.", "sent_id": 68926, "sent": "a man in a black tshirt with white writing"}], "file_name": "COCO_train2014_000000522062_515650.jpg", "ann_id": 515650, "sent_ids": [68925, 68926], "ref_id": 31487}, {"segmentation": [[385.11, 282.16, 378.37, 312.5, 380.06, 339.47, 368.26, 342.84, 344.66, 362.22, 336.24, 355.48, 300.0, 367.28, 267.13, 369.8, 241.01, 371.49, 235.11, 351.26, 238.48, 329.35, 254.49, 318.4, 259.55, 300.7, 285.67, 300.7, 291.57, 304.07, 296.63, 278.79, 303.37, 261.94, 314.33, 245.08, 321.91, 240.03, 303.37, 242.56, 293.26, 225.7, 298.31, 214.75, 317.7, 217.28, 323.6, 214.75, 330.34, 209.69, 334.55, 194.52, 340.45, 181.04, 342.13, 166.71, 358.99, 165.03, 375.0, 153.23, 383.43, 165.87, 393.54, 175.98, 392.7, 191.15, 398.6, 218.96, 408.71, 246.77, 400.28, 272.05]], "area": 19540.534449999996, "iscrowd": 0, "image_id": 66669, "bbox": [235.11, 153.23, 173.6, 218.26], "category_id": 88, "id": 1161670, "split": "val", "sentences": [{"tokens": ["the", "group", "of", "stuffed", "animals", "the", "child", "is", "facing"], "raw": "The group of stuffed animals the child is facing.", "sent_id": 68964, "sent": "the group of stuffed animals the child is facing"}, {"tokens": ["infant", "feed", "her", "teddy", "bear"], "raw": "Infant feed her teddy bear", "sent_id": 68965, "sent": "infant feed her teddy bear"}], "file_name": "COCO_train2014_000000066669_1161670.jpg", "ann_id": 1161670, "sent_ids": [68964, 68965], "ref_id": 31502}, {"segmentation": [[1.08, 120.81, 0.0, 198.47, 99.24, 181.21, 175.82, 118.65, 192.0, 51.78, 222.2, 4.31, 201.71, 2.16, 181.21, 17.26, 165.03, 0.0, 0.0, 4.31, 1.08, 118.65]], "area": 31680.472700000002, "iscrowd": 0, "image_id": 177314, "bbox": [0.0, 0.0, 222.2, 198.47], "category_id": 51, "id": 1039545, "split": "val", "sentences": [{"tokens": ["a", "dish", "of", "broccoli"], "raw": "A dish of broccoli.", "sent_id": 68996, "sent": "a dish of broccoli"}], "file_name": "COCO_train2014_000000177314_1039545.jpg", "ann_id": 1039545, "sent_ids": [68996], "ref_id": 31515}, {"segmentation": [[4.8, 358.58, 55.65, 361.46, 78.68, 262.62, 118.98, 246.31, 94.04, 379.69, 105.55, 413.27, 91.16, 401.76, 53.73, 419.03, 1.92, 416.15, 7.68, 362.42]], "area": 9151.019500000002, "iscrowd": 0, "image_id": 252093, "bbox": [1.92, 246.31, 117.06, 172.72], "category_id": 62, "id": 378472, "split": "val", "sentences": [{"tokens": ["unoccupied", "chair", "with", "visible", "seat"], "raw": "unoccupied chair with visible seat", "sent_id": 69001, "sent": "unoccupied chair with visible seat"}, {"tokens": ["an", "empty", "brown", "chair"], "raw": "An empty brown chair.", "sent_id": 69002, "sent": "an empty brown chair"}], "file_name": "COCO_train2014_000000252093_378472.jpg", "ann_id": 378472, "sent_ids": [69001, 69002], "ref_id": 31518}, {"segmentation": [[447.99, 403.41, 453.43, 404.09, 462.28, 392.52, 526.93, 403.41, 541.22, 414.98, 544.62, 412.26, 545.98, 399.33, 559.59, 388.44, 564.36, 391.16, 563.67, 287.72, 560.95, 272.07, 558.91, 267.99, 516.72, 270.03, 465.68, 267.99, 445.27, 267.99, 445.95, 293.17, 447.99, 355.77, 449.35, 399.33]], "area": 15199.993699999999, "iscrowd": 0, "image_id": 329543, "bbox": [445.27, 267.99, 119.09, 146.99], "category_id": 79, "id": 1122272, "split": "val", "sentences": [{"tokens": ["an", "old", "oven", "with", "the", "door", "open"], "raw": "an old oven with the door open", "sent_id": 69013, "sent": "an old oven with the door open"}, {"tokens": ["a", "stove", "to", "the", "right", "of", "a", "woman", "and", "under", "an", "imperial", "sign"], "raw": "A stove to the right of a woman and under an Imperial sign.", "sent_id": 69014, "sent": "a stove to the right of a woman and under an imperial sign"}], "file_name": "COCO_train2014_000000329543_1122272.jpg", "ann_id": 1122272, "sent_ids": [69013, 69014], "ref_id": 31524}, {"segmentation": [[393.06, 204.32, 390.6, 191.98, 386.89, 175.32, 401.09, 161.12, 414.04, 148.78, 431.32, 139.53, 446.13, 145.08, 460.33, 148.78, 476.99, 150.63, 503.52, 161.12, 527.59, 169.15, 527.59, 182.11, 532.52, 197.53, 546.72, 204.32, 549.8, 220.36, 534.99, 235.17, 507.84, 250.6, 472.05, 253.07, 462.18, 248.75, 431.32, 237.64, 416.51, 228.39, 408.49, 213.58, 399.85, 208.64, 394.91, 200.62]], "area": 12436.184650000001, "iscrowd": 0, "image_id": 43655, "bbox": [386.89, 139.53, 162.91, 113.54], "category_id": 17, "id": 48202, "split": "val", "sentences": [{"tokens": ["a", "cat", "in", "a", "bed", "to", "the", "right", "of", "another", "cat"], "raw": "A cat in a bed to the right of another cat.", "sent_id": 69097, "sent": "a cat in a bed to the right of another cat"}, {"tokens": ["a", "cat", ",", "sitting", "in", "a", "cushion", ",", "with", "all", "its", "paws", "inside", "the", "cushion"], "raw": "A cat, sitting in a cushion, with all its paws inside the cushion.", "sent_id": 69098, "sent": "a cat , sitting in a cushion , with all its paws inside the cushion"}], "file_name": "COCO_train2014_000000043655_48202.jpg", "ann_id": 48202, "sent_ids": [69097, 69098], "ref_id": 31550}, {"segmentation": [[637.49, 5.96, 621.19, 24.38, 614.81, 42.09, 610.56, 57.67, 604.9, 71.14, 592.85, 82.47, 578.68, 103.02, 571.6, 117.19, 545.39, 169.61, 553.89, 172.45, 575.85, 143.4, 596.4, 115.77, 608.44, 96.64, 617.65, 78.93, 624.73, 61.93, 628.28, 52.01, 629.69, 34.3, 638.9, 15.17, 640.0, 5.25]], "area": 2845.089150000003, "iscrowd": 0, "image_id": 70755, "bbox": [545.39, 5.25, 94.61, 167.2], "category_id": 90, "id": 343303, "split": "val", "sentences": [{"tokens": ["a", "blue", "toothbrush", "on", "a", "sink"], "raw": "A blue toothbrush on a sink.", "sent_id": 69117, "sent": "a blue toothbrush on a sink"}, {"tokens": ["blue", "tooth", "brush", "on", "right"], "raw": "blue tooth brush on right", "sent_id": 69118, "sent": "blue tooth brush on right"}], "file_name": "COCO_train2014_000000070755_343303.jpg", "ann_id": 343303, "sent_ids": [69117, 69118], "ref_id": 31557}, {"segmentation": [[350.21, 337.85, 350.21, 352.27, 350.21, 361.55, 346.09, 381.12, 361.55, 377.0, 359.48, 362.58, 360.52, 346.09, 357.42, 329.61, 357.42, 318.28, 351.24, 302.83, 349.18, 276.05, 354.33, 277.08, 362.58, 299.74, 361.55, 317.25, 363.61, 329.61, 366.7, 338.88, 369.79, 357.42, 369.79, 368.76, 366.7, 385.24, 380.09, 390.39, 379.06, 374.94, 374.94, 341.97, 377.0, 312.1, 374.94, 290.47, 377.0, 270.9, 380.09, 269.87, 390.39, 298.71, 395.54, 311.07, 395.54, 325.49, 391.42, 344.03, 387.3, 360.52, 396.57, 365.67, 399.66, 358.45, 402.75, 352.27, 407.9, 319.31, 406.87, 301.8, 406.87, 288.41, 396.57, 266.78, 406.87, 251.33, 410.99, 268.84, 416.14, 282.23, 415.11, 295.62, 417.17, 304.89, 418.2, 313.13, 415.11, 339.91, 416.14, 359.48, 433.65, 352.27, 424.38, 339.91, 426.44, 322.4, 428.5, 305.92, 436.74, 286.35, 429.53, 249.27, 424.38, 203.95, 406.87, 185.41, 382.15, 179.23, 387.3, 162.75, 374.94, 142.15, 372.88, 125.67, 364.64, 130.82, 361.55, 130.82, 360.52, 125.67, 357.42, 123.61, 349.18, 135.97, 346.09, 146.27, 333.73, 166.87, 330.64, 191.59, 327.55, 201.89, 350.21, 188.5, 343.0, 218.37, 343.0, 224.55, 347.12, 233.82, 350.21, 241.03, 349.18, 252.36, 344.03, 263.69, 341.97, 283.26, 340.94, 300.77, 349.18, 315.19, 349.18, 326.52]], "area": 14189.56845, "iscrowd": 0, "image_id": 342683, "bbox": [327.55, 123.61, 109.19, 266.78], "category_id": 19, "id": 58573, "split": "val", "sentences": [{"tokens": ["the", "horse", "on", "the", "right", "hand", "side", "with", "a", "lighter", "colored", "mane", "and", "with", "white", "on", "its", "snout"], "raw": "The horse on the right hand side with a lighter colored mane and with white on its snout.", "sent_id": 69152, "sent": "the horse on the right hand side with a lighter colored mane and with white on its snout"}, {"tokens": ["a", "horse", "with", "a", "white", "stripe", "on", "it", "'", "s", "nose"], "raw": "A horse with a white stripe on it's nose", "sent_id": 69153, "sent": "a horse with a white stripe on it ' s nose"}], "file_name": "COCO_train2014_000000342683_58573.jpg", "ann_id": 58573, "sent_ids": [69152, 69153], "ref_id": 31574}, {"segmentation": [[639.12, 250.08, 560.43, 243.37, 547.0, 406.5, 550.83, 428.0, 633.36, 428.0, 640.0, 428.0, 640.0, 249.12]], "area": 15764.512200000003, "iscrowd": 0, "image_id": 10870, "bbox": [547.0, 243.37, 93.0, 184.63], "category_id": 67, "id": 1619212, "split": "val", "sentences": [{"tokens": ["a", "partially", "taken", "wooden", "table"], "raw": "A partially taken wooden table", "sent_id": 69166, "sent": "a partially taken wooden table"}], "file_name": "COCO_train2014_000000010870_1619212.jpg", "ann_id": 1619212, "sent_ids": [69166], "ref_id": 31581}, {"segmentation": [[194.56, 28.74, 197.03, 34.67, 198.51, 38.62, 218.77, 66.78, 244.46, 64.31, 241.5, 73.7, 245.45, 82.59, 253.35, 94.45, 243.97, 115.69, 228.65, 139.9, 215.31, 155.22, 222.23, 175.97, 221.24, 188.82, 218.28, 209.57, 320.0, 210.06, 319.06, 57.89, 297.82, 49.98, 297.33, 42.57, 299.8, 36.15, 198.02, 26.76], [140.71, 206.11, 123.91, 185.36, 106.12, 175.97, 85.37, 160.65, 78.46, 169.55, 80.93, 173.5, 71.05, 173.5, 69.07, 175.97, 72.03, 183.38, 67.59, 188.82, 62.15, 189.31, 62.65, 198.2, 66.11, 204.13, 66.11, 211.05, 143.18, 210.06]], "area": 18410.945450000003, "iscrowd": 0, "image_id": 551869, "bbox": [62.15, 26.76, 257.85, 184.29], "category_id": 1, "id": 204243, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "a", "baby", "eating", "a", "banana"], "raw": "A woman with a baby eating a banana", "sent_id": 69220, "sent": "a woman with a baby eating a banana"}, {"tokens": ["a", "woman", "with", "a", "white", "tank", "top", "on", "holding", "a", "baby"], "raw": "A woman with a white tank top on holding a baby.", "sent_id": 69221, "sent": "a woman with a white tank top on holding a baby"}], "file_name": "COCO_train2014_000000551869_204243.jpg", "ann_id": 204243, "sent_ids": [69220, 69221], "ref_id": 31603}, {"segmentation": [[330.62, 32.1, 341.11, 70.22, 355.4, 82.6, 357.3, 111.19, 365.88, 113.09, 371.6, 109.28, 376.36, 117.86, 387.79, 125.48, 395.42, 132.15, 412.57, 146.44, 420.19, 151.21, 411.61, 166.45, 409.71, 187.41, 405.9, 206.47, 410.66, 226.48, 410.66, 236.96, 406.85, 244.58, 413.52, 265.54, 411.61, 273.17, 398.27, 273.17, 369.69, 265.54, 353.49, 264.59, 331.58, 272.21, 308.71, 274.12, 285.84, 305.56, 269.64, 316.04, 266.79, 321.76, 273.46, 325.57, 288.7, 317.95, 305.85, 308.42, 307.76, 331.29, 324.91, 338.91, 337.29, 341.77, 345.87, 344.63, 340.15, 335.1, 352.54, 326.52, 353.49, 318.9, 397.32, 348.44, 410.66, 354.15, 441.15, 349.39, 438.29, 360.82, 431.62, 382.74, 431.62, 397.98, 403.99, 414.18, 404.94, 417.99, 640.0, 417.99, 640.0, 147.39, 624.09, 115.95, 585.02, 92.13, 543.1, 79.74, 526.9, 77.84, 511.66, 63.55, 524.04, 48.3, 536.43, 25.43, 530.71, 0.66, 339.2, 0.66, 331.58, 16.86, 333.48, 31.15]], "area": 99462.38254999998, "iscrowd": 0, "image_id": 258071, "bbox": [266.79, 0.66, 373.21, 417.33], "category_id": 1, "id": 482828, "split": "val", "sentences": [{"tokens": ["older", "woman", "wearing", "dark", "blue", "sweater"], "raw": "older woman wearing dark blue sweater", "sent_id": 69288, "sent": "older woman wearing dark blue sweater"}, {"tokens": ["a", "woman", "in", "a", "blue", "shirt", "is", "pointing", "to", "a", "craft", "project", "a", "girl", "is", "doing"], "raw": "A woman in a blue shirt is pointing to a craft project a girl is doing.", "sent_id": 69289, "sent": "a woman in a blue shirt is pointing to a craft project a girl is doing"}], "file_name": "COCO_train2014_000000258071_482828.jpg", "ann_id": 482828, "sent_ids": [69288, 69289], "ref_id": 31626}, {"segmentation": [[168.88, 130.5, 473.06, 121.86, 468.26, 203.42, 395.33, 201.51, 391.5, 138.18, 370.39, 142.97, 366.55, 145.85, 353.11, 199.59, 325.29, 203.42, 297.46, 143.93, 290.74, 138.18, 282.11, 140.09, 277.31, 162.16, 277.31, 165.04, 277.31, 178.48, 277.31, 196.71, 273.47, 204.38, 164.08, 203.42, 138.18, 159.29, 164.08, 150.65, 170.8, 132.42], [499.93, 126.66, 498.97, 204.38, 525.83, 200.55, 524.87, 155.45, 524.87, 139.13, 526.79, 130.5]], "area": 21945.206850000002, "iscrowd": 0, "image_id": 230436, "bbox": [138.18, 121.86, 388.61, 82.52], "category_id": 7, "id": 173898, "split": "val", "sentences": [{"tokens": ["a", "blue", "and", "yellow", "train"], "raw": "A blue and yellow train.", "sent_id": 69313, "sent": "a blue and yellow train"}, {"tokens": ["the", "blue", "train", "in", "the", "background"], "raw": "The blue train in the background", "sent_id": 69314, "sent": "the blue train in the background"}], "file_name": "COCO_train2014_000000230436_173898.jpg", "ann_id": 173898, "sent_ids": [69313, 69314], "ref_id": 31635}, {"segmentation": [[337.63, 218.63, 478.25, 230.35, 478.25, 336.47, 471.09, 341.03, 454.16, 332.57, 452.21, 314.34, 452.86, 305.22, 459.37, 298.06, 457.42, 292.2, 428.12, 285.69, 414.65, 264.3, 404.71, 272.24, 411.34, 287.04, 378.69, 282.3, 347.29, 298.82, 311.87, 293.9, 306.84, 285.2, 296.28, 284.0, 294.61, 252.09, 309.0, 250.41, 311.55, 266.57, 311.79, 268.01, 380.66, 266.33, 365.06, 222.18]], "area": 9525.640300000001, "iscrowd": 0, "image_id": 100812, "bbox": [294.61, 218.63, 183.64, 122.4], "category_id": 63, "id": 113537, "split": "val", "sentences": [{"tokens": ["the", "black", "couch", "with", "the", "green", "pillow", "on", "it"], "raw": "The black couch with the green pillow on it.", "sent_id": 69401, "sent": "the black couch with the green pillow on it"}, {"tokens": ["black", "couch", "in", "the", "back", "side", "of", "the", "image"], "raw": "black couch in the back side of the image", "sent_id": 69402, "sent": "black couch in the back side of the image"}], "file_name": "COCO_train2014_000000100812_113537.jpg", "ann_id": 113537, "sent_ids": [69401, 69402], "ref_id": 31665}, {"segmentation": [[263.25, 176.49, 269.25, 186.72, 278.07, 206.13, 292.18, 211.07, 307.36, 219.89, 317.59, 228.0, 303.47, 226.24, 288.66, 227.3, 284.77, 237.53, 299.95, 254.11, 334.52, 242.12, 360.63, 253.05, 375.8, 259.76, 382.16, 279.87, 385.68, 331.73, 401.91, 345.85, 444.96, 368.78, 462.6, 378.66, 446.37, 400.89, 463.31, 409.71, 502.82, 375.13, 492.94, 358.2, 475.3, 351.85, 440.73, 329.62, 421.67, 316.56, 434.73, 299.98, 439.31, 295.04, 462.6, 304.92, 479.89, 304.21, 511.64, 303.51, 555.04, 309.51, 544.81, 316.56, 610.44, 308.1, 597.74, 293.98, 553.28, 278.81, 500.71, 267.87, 481.3, 271.4, 460.84, 235.76, 447.43, 210.36, 417.79, 187.43, 387.45, 177.55, 373.33, 164.14, 350.05, 143.32, 326.06, 125.33, 304.89, 116.51, 289.71, 102.39, 271.01, 90.4, 250.9, 78.4, 228.32, 72.76, 207.5, 81.58, 190.92, 109.45, 193.74, 127.45, 211.74, 144.73, 217.38, 157.44, 224.79, 152.14, 229.73, 157.79, 198.68, 166.26, 170.1, 169.79, 129.88, 181.08, 124.59, 181.78, 132.7, 199.42, 153.87, 196.25, 157.4, 200.48], [118.24, 183.55, 121.77, 197.66, 105.89, 190.25, 96.01, 186.02, 90.72, 177.2, 106.24, 184.25], [100.95, 200.48, 96.01, 199.78, 92.13, 198.72, 92.83, 202.6, 98.83, 207.19, 108.71, 208.24, 108.36, 204.36], [85.78, 196.25, 80.84, 198.01, 79.43, 196.25, 81.9, 194.84]], "area": 39690.81339999999, "iscrowd": 0, "image_id": 310457, "bbox": [79.43, 72.76, 531.01, 336.95], "category_id": 1, "id": 516558, "split": "val", "sentences": [{"tokens": ["a", "woman", "standing", "with", "a", "remote", "control", "in", "her", "hand"], "raw": "A woman standing with a remote control in her hand.", "sent_id": 69520, "sent": "a woman standing with a remote control in her hand"}, {"tokens": ["a", "lady", "playing", "a", "game", "and", "another", "lady", "is", "watching", "it"], "raw": "A lady playing a game and another lady is watching it", "sent_id": 69521, "sent": "a lady playing a game and another lady is watching it"}], "file_name": "COCO_train2014_000000310457_516558.jpg", "ann_id": 516558, "sent_ids": [69520, 69521], "ref_id": 31713}, {"segmentation": [[371.66, 251.29, 413.27, 195.32, 439.1, 235.5, 400.36, 259.9, 393.18, 277.12, 393.18, 298.64, 426.19, 376.13, 436.23, 409.14, 434.8, 419.18, 439.1, 429.23, 470.67, 420.62, 473.54, 399.09, 467.8, 379.0, 452.02, 358.91, 447.71, 351.74, 443.41, 341.69, 444.84, 325.91, 454.89, 317.3, 469.24, 312.99, 482.15, 305.82, 490.76, 351.74, 499.37, 368.96, 509.42, 381.87, 522.33, 396.22, 530.94, 409.14, 536.68, 436.4, 538.12, 442.14, 546.73, 416.31, 545.29, 387.61, 545.29, 363.22, 540.99, 337.39, 542.42, 318.73, 548.16, 304.38, 555.34, 279.99, 558.21, 261.33, 558.21, 242.68, 553.9, 225.46, 553.9, 196.76, 533.81, 212.54, 523.77, 222.59, 492.2, 221.15, 467.8, 212.54, 456.32, 180.97, 452.02, 160.88, 452.02, 150.84, 434.8, 132.19, 426.19, 114.97, 426.19, 102.05, 430.49, 94.88, 453.45, 92.01, 487.89, 96.31, 497.94, 96.31, 497.94, 90.57, 496.5, 81.96, 479.28, 70.48, 470.67, 67.61, 444.84, 66.18, 437.67, 73.35, 429.06, 86.27, 424.75, 90.57, 419.01, 102.05, 414.71, 116.4, 410.4, 123.58, 400.36, 130.75, 397.49, 137.93, 391.75, 147.97, 378.83, 176.67, 374.53, 191.02, 354.44, 222.59, 360.18, 241.24, 365.92, 252.72]], "area": 31868.487150000008, "iscrowd": 0, "image_id": 523487, "bbox": [354.44, 66.18, 203.77, 375.96], "category_id": 1, "id": 192214, "split": "val", "sentences": [{"tokens": ["biker", "with", "backpack"], "raw": "biker with backpack", "sent_id": 69538, "sent": "biker with backpack"}, {"tokens": ["the", "man", "biking", "away"], "raw": "the man biking away", "sent_id": 69539, "sent": "the man biking away"}], "file_name": "COCO_train2014_000000523487_192214.jpg", "ann_id": 192214, "sent_ids": [69538, 69539], "ref_id": 31720}, {"segmentation": [[440.03, 376.98, 441.03, 354.93, 431.01, 327.87, 411.96, 302.81, 407.96, 297.8, 416.98, 278.75, 428.0, 272.74, 457.07, 260.71, 473.11, 252.69, 496.16, 243.67, 506.19, 240.66, 546.28, 268.73, 557.31, 296.8, 559.31, 327.87, 558.31, 339.9, 519.22, 360.95, 454.06, 385.0, 442.04, 381.99]], "area": 14356.875399999997, "iscrowd": 0, "image_id": 504744, "bbox": [407.96, 240.66, 151.35, 144.34], "category_id": 53, "id": 1050001, "split": "val", "sentences": [{"tokens": ["an", "apple", "beneath", "a", "banana"], "raw": "An apple beneath a banana", "sent_id": 69569, "sent": "an apple beneath a banana"}, {"tokens": ["apple", "that", "is", "underneath", "a", "banana", "and", "right", "of", "an", "orange", "in", "a", "wooden", "bowl"], "raw": "apple that is underneath a banana and right of an orange in a wooden bowl.", "sent_id": 69570, "sent": "apple that is underneath a banana and right of an orange in a wooden bowl"}], "file_name": "COCO_train2014_000000504744_1050001.jpg", "ann_id": 1050001, "sent_ids": [69569, 69570], "ref_id": 31732}, {"segmentation": [[380.56, 350.09, 301.45, 332.34, 300.71, 310.9, 293.32, 307.94, 297.75, 288.72, 310.32, 282.07, 313.28, 245.1, 361.33, 223.66, 370.21, 187.44, 377.6, 183.74, 390.91, 183.0, 425.65, 184.48, 470.01, 189.65, 480.0, 190.39, 476.67, 236.97, 452.27, 245.84, 442.66, 238.45, 433.79, 235.49, 433.05, 238.45, 360.59, 267.28, 359.12, 275.41, 378.34, 339.74, 382.03, 348.61]], "area": 13609.417849999998, "iscrowd": 0, "image_id": 160866, "bbox": [293.32, 183.0, 186.68, 167.09], "category_id": 62, "id": 1598578, "split": "val", "sentences": [{"tokens": ["a", "recliner", "on", "which", "ther", "is", "an", "orange", "cushion"], "raw": "A recliner on which ther is an orange cushion", "sent_id": 69679, "sent": "a recliner on which ther is an orange cushion"}, {"tokens": ["the", "sole", "sofa", "chair"], "raw": "The sole sofa chair.", "sent_id": 69680, "sent": "the sole sofa chair"}], "file_name": "COCO_train2014_000000160866_1598578.jpg", "ann_id": 1598578, "sent_ids": [69679, 69680], "ref_id": 31780}, {"segmentation": [[640.0, 159.53, 619.4, 151.95, 605.17, 161.43, 599.48, 187.99, 607.07, 195.58, 614.66, 211.7, 630.78, 223.09, 624.14, 255.34, 627.94, 275.26, 634.58, 298.97, 617.5, 344.5, 616.55, 382.44, 625.09, 423.23, 640.0, 423.23], [634.58, 17.25, 629.83, 40.02, 635.53, 55.19, 640.0, 60.88, 640.0, 1.13, 636.47, 2.07]], "area": 5680.719749999998, "iscrowd": 0, "image_id": 241491, "bbox": [599.48, 1.13, 40.52, 422.1], "category_id": 1, "id": 1710109, "split": "val", "sentences": [{"tokens": ["the", "person", "on", "the", "far", "right", "in", "the", "right", "hand", "picture"], "raw": "the person on the far right in the right hand picture", "sent_id": 69686, "sent": "the person on the far right in the right hand picture"}, {"tokens": ["a", "person", "near", "the", "table", "watching", "a", "man", "blowing", "off", "the", "candle"], "raw": "A person near the table watching a man blowing off the candle", "sent_id": 69687, "sent": "a person near the table watching a man blowing off the candle"}], "file_name": "COCO_train2014_000000241491_1710109.jpg", "ann_id": 1710109, "sent_ids": [69686, 69687], "ref_id": 31783}, {"segmentation": [[144.55, 179.02, 134.98, 194.33, 101.47, 259.43, 171.36, 269.96, 198.16, 237.41, 223.05, 227.84, 273.79, 203.91, 339.84, 170.4, 378.13, 150.3, 384.84, 176.14, 399.2, 158.91, 412.6, 176.14, 414.51, 168.49, 436.53, 170.4, 415.47, 145.51, 453.76, 156.04, 449.93, 139.77, 475.78, 138.81, 462.38, 101.47, 475.78, 88.07, 481.52, 75.63, 454.72, 66.05, 482.48, 55.52, 499.71, 23.93, 527.47, 17.23, 527.47, 4.79, 379.09, 2.87, 374.31, 10.53, 356.12, 14.36, 355.16, 30.63, 335.06, 22.02, 302.51, 13.4, 290.06, 18.19, 272.83, 12.44, 262.3, 19.15, 251.77, 17.23, 250.81, 9.57, 232.62, 13.4, 184.76, 0.0, 153.17, 9.57, 154.13, 20.1, 129.24, 28.72, 119.66, 44.99, 89.99, 60.31, 144.55, 92.86, 108.18, 96.69, 134.02, 122.53, 114.88, 134.98, 137.85, 144.55, 123.49, 165.61, 153.17, 157.0, 149.34, 173.27]], "area": 67035.16189999999, "iscrowd": 0, "image_id": 35322, "bbox": [89.99, 0.0, 437.48, 269.96], "category_id": 64, "id": 26183, "split": "val", "sentences": [{"tokens": ["a", "potted", "tree", "leaning", "to", "the", "right"], "raw": "a potted tree leaning to the right.", "sent_id": 69777, "sent": "a potted tree leaning to the right"}, {"tokens": ["trees", "in", "the", "back", "of", "a", "truck"], "raw": "Trees in the back of a truck.", "sent_id": 69778, "sent": "trees in the back of a truck"}], "file_name": "COCO_train2014_000000035322_26183.jpg", "ann_id": 26183, "sent_ids": [69777, 69778], "ref_id": 31814}, {"segmentation": [[446.56, 421.47, 443.66, 411.78, 425.25, 394.35, 415.56, 342.04, 426.22, 329.44, 433.0, 338.16, 436.87, 291.67, 442.69, 258.73, 454.31, 226.76, 500.81, 219.02, 531.81, 208.36, 538.59, 206.42, 575.4, 216.11, 601.55, 235.48, 613.17, 248.08, 622.86, 266.48, 630.61, 287.79, 631.58, 312.98, 631.58, 344.94, 636.42, 405.0, 632.55, 419.53]], "area": 38884.8405, "iscrowd": 0, "image_id": 468602, "bbox": [415.56, 206.42, 220.86, 215.05], "category_id": 1, "id": 185300, "split": "val", "sentences": [{"tokens": ["the", "silhouette", "of", "a", "person", "'", "s", "head"], "raw": "The silhouette of a person's head.", "sent_id": 69806, "sent": "the silhouette of a person ' s head"}, {"tokens": ["head", "in", "shadow"], "raw": "Head in shadow.", "sent_id": 69807, "sent": "head in shadow"}], "file_name": "COCO_train2014_000000468602_185300.jpg", "ann_id": 185300, "sent_ids": [69806, 69807], "ref_id": 31827}, {"segmentation": [[495.07, 470.26, 535.96, 407.84, 515.52, 359.41, 529.51, 258.24, 555.34, 204.43, 572.56, 167.84, 583.32, 147.39, 639.28, 89.27, 634.98, 467.03]], "area": 34833.93375, "iscrowd": 0, "image_id": 551524, "bbox": [495.07, 89.27, 144.21, 380.99], "category_id": 1, "id": 479498, "split": "val", "sentences": [{"tokens": ["the", "brown", "hair", "of", "the", "person", "standing", "on", "the", "far", "right"], "raw": "The brown hair of the person standing on the far right.", "sent_id": 69839, "sent": "the brown hair of the person standing on the far right"}, {"tokens": ["the", "hair", "of", "a", "woman", "standing", "mainly", "out", "of", "view"], "raw": "The hair of a woman standing mainly out of view.", "sent_id": 69840, "sent": "the hair of a woman standing mainly out of view"}], "file_name": "COCO_train2014_000000551524_479498.jpg", "ann_id": 479498, "sent_ids": [69839, 69840], "ref_id": 31839}, {"segmentation": [[425.2, 152.57, 441.73, 148.16, 443.93, 131.64, 450.54, 131.64, 461.55, 144.86, 637.8, 129.43, 640.0, 416.94, 0.0, 416.94, 0.0, 114.01, 120.07, 142.65, 121.17, 127.23, 132.19, 126.13, 137.7, 142.65, 146.51, 148.16, 152.02, 205.44, 189.47, 208.75, 269.88, 208.75, 375.63, 212.05, 424.1, 206.54]], "area": 159801.36035, "iscrowd": 0, "image_id": 74156, "bbox": [0.0, 114.01, 640.0, 302.93], "category_id": 8, "id": 2172072, "split": "val", "sentences": [{"tokens": ["three", "men", "with", "camping", "gear", "in", "the", "back", "of", "a", "truck"], "raw": "three men with camping gear in the back of a truck", "sent_id": 69853, "sent": "three men with camping gear in the back of a truck"}, {"tokens": ["the", "back", "side", "of", "the", "truck"], "raw": "the back side of the truck", "sent_id": 69854, "sent": "the back side of the truck"}], "file_name": "COCO_train2014_000000074156_2172072.jpg", "ann_id": 2172072, "sent_ids": [69853, 69854], "ref_id": 31845}, {"segmentation": [[531.73, 202.98, 558.62, 183.02, 570.76, 167.41, 590.71, 146.59, 591.58, 128.38, 610.66, 129.24, 615.0, 136.18, 627.14, 166.54, 616.73, 173.48, 605.46, 165.68, 599.38, 172.62, 569.89, 222.06, 568.16, 222.93, 569.89, 238.54, 559.48, 281.91, 556.88, 287.11, 553.41, 314.87, 561.22, 336.56, 535.2, 334.82, 541.27, 314.87, 540.4, 261.09, 516.35, 257.83, 508.32, 274.78, 508.77, 309.56, 510.55, 330.52, 501.19, 333.19, 499.4, 287.26, 494.94, 295.74, 497.62, 334.98, 485.13, 333.19, 486.02, 298.86, 479.78, 287.26, 484.69, 264.97, 484.24, 254.27, 492.27, 234.65, 503.86, 217.26, 505.64, 214.14]], "area": 9905.386800000002, "iscrowd": 0, "image_id": 171484, "bbox": [479.78, 128.38, 147.36, 208.18], "category_id": 25, "id": 599656, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "on", "the", "far", "right"], "raw": "The giraffe on the far right.", "sent_id": 69876, "sent": "the giraffe on the far right"}, {"tokens": ["a", "dark", "brown", "and", "white", "giraffe", "facing", "to", "the", "right"], "raw": "A dark brown and white giraffe facing to the right.", "sent_id": 69877, "sent": "a dark brown and white giraffe facing to the right"}], "file_name": "COCO_train2014_000000171484_599656.jpg", "ann_id": 599656, "sent_ids": [69876, 69877], "ref_id": 31854}, {"segmentation": [[377.28, 439.52, 365.07, 394.29, 348.2, 383.16, 344.25, 366.65, 349.31, 346.75, 368.2, 321.87, 395.84, 314.5, 410.59, 309.89, 415.19, 310.81, 437.77, 313.11, 451.59, 312.65, 476.01, 323.25, 483.84, 330.62, 488.45, 348.59, 490.75, 366.56, 490.75, 374.39, 481.54, 386.37, 472.78, 408.94, 469.1, 438.43, 459.42, 445.8, 446.06, 452.71, 423.49, 458.7, 405.06, 455.01]], "area": 16059.3976, "iscrowd": 0, "image_id": 326903, "bbox": [344.25, 309.89, 146.5, 148.81], "category_id": 47, "id": 1884727, "split": "val", "sentences": [{"tokens": ["the", "plastic", "cup", "of", "sauce", "that", "is", "right", "side", "up", "and", "has", "a", "lid", "on", "it"], "raw": "The plastic cup of sauce that is right side up and has a lid on it", "sent_id": 69906, "sent": "the plastic cup of sauce that is right side up and has a lid on it"}, {"tokens": ["the", "small", "plastic", "container", "standing", "upright"], "raw": "The small plastic container standing upright.", "sent_id": 69907, "sent": "the small plastic container standing upright"}, {"tokens": ["a", "small", "closed", "container", "of", "white", "sauce"], "raw": "a small closed container of white sauce", "sent_id": 69908, "sent": "a small closed container of white sauce"}], "file_name": "COCO_train2014_000000326903_1884727.jpg", "ann_id": 1884727, "sent_ids": [69906, 69907, 69908], "ref_id": 31867}, {"segmentation": [[268.83, 240.6, 268.83, 218.53, 275.89, 196.47, 279.42, 179.7, 284.71, 170.88, 292.66, 165.58, 295.3, 139.11, 297.95, 108.22, 305.89, 85.28, 317.37, 71.16, 334.13, 62.33, 375.61, 71.16, 395.03, 121.46, 395.03, 140.87, 381.79, 153.23, 385.32, 161.17, 418.85, 168.23, 429.44, 171.76, 434.74, 177.06, 438.27, 194.71, 429.44, 261.78, 429.44, 277.66, 417.97, 276.78, 405.62, 272.37, 390.61, 248.54, 375.61, 235.3, 363.26, 220.3, 344.72, 215.89, 305.01, 210.59, 286.48, 214.12, 280.3, 221.18, 279.42, 237.07, 281.18, 240.6]], "area": 19423.2304, "iscrowd": 0, "image_id": 235582, "bbox": [268.83, 62.33, 169.44, 215.33], "category_id": 1, "id": 444647, "split": "val", "sentences": [{"tokens": ["the", "birthday", "girl", "with", "glasses", "going", "to", "blow", "our", "her", "candles"], "raw": "the birthday girl with glasses going to blow our her candles", "sent_id": 69954, "sent": "the birthday girl with glasses going to blow our her candles"}, {"tokens": ["a", "woman", "with", "glasses", "on"], "raw": "A woman with glasses on.", "sent_id": 69955, "sent": "a woman with glasses on"}], "file_name": "COCO_train2014_000000235582_444647.jpg", "ann_id": 444647, "sent_ids": [69954, 69955], "ref_id": 31889}, {"segmentation": [[325.84, 227.4, 334.24, 219.35, 341.6, 212.7, 344.4, 210.59, 354.9, 208.49, 362.96, 204.99, 364.36, 198.34, 361.56, 190.99, 362.61, 182.58, 369.61, 175.58, 373.81, 175.58, 380.46, 175.58, 384.31, 178.03, 386.77, 185.38, 387.12, 189.59, 387.82, 190.29, 386.06, 193.79, 385.01, 199.39, 382.56, 202.89, 380.46, 206.39, 381.16, 208.84, 389.57, 214.1, 396.92, 222.5, 398.32, 234.4, 398.32, 245.61, 397.27, 248.41, 393.42, 248.06, 391.67, 260.66, 390.27, 270.12, 389.57, 275.37, 392.02, 280.27, 390.62, 284.12, 391.67, 288.68, 395.17, 296.73, 393.07, 297.08, 396.22, 314.24, 395.87, 336.64, 394.82, 350.65, 392.72, 356.6, 389.92, 358.0, 387.82, 372.71, 386.06, 385.66, 386.42, 393.02, 387.82, 399.32, 385.01, 402.47, 380.81, 402.47, 378.36, 400.37, 373.11, 401.42, 361.91, 401.07, 353.15, 402.82, 348.95, 400.02, 349.3, 397.92, 351.05, 395.82, 357.7, 396.17, 361.56, 393.37, 366.11, 389.16, 360.86, 373.41, 357.0, 363.6, 357.0, 358.7, 357.35, 356.95, 348.25, 356.95, 348.25, 349.95, 346.5, 346.45, 347.9, 341.2, 345.8, 339.09, 345.45, 335.94, 345.1, 332.09, 344.4, 328.59, 342.3, 325.44, 340.55, 312.13, 342.3, 293.23, 342.3, 289.03, 339.85, 285.87, 343.0, 274.32, 345.8, 250.86, 346.15, 240.36, 345.8, 233.0, 344.05, 230.2, 337.4, 235.8, 333.54, 234.75, 325.84, 233.35, 324.79, 230.55]], "area": 9662.194200000004, "iscrowd": 0, "image_id": 442641, "bbox": [324.79, 175.58, 73.53, 227.24], "category_id": 1, "id": 449588, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "the", "back", "side", "position", "holding", "the", "hand", "in", "kite"], "raw": "A MAN STANDING THE BACK SIDE POSITION HOLDING THE HAND IN KITE", "sent_id": 69968, "sent": "a man standing the back side position holding the hand in kite"}, {"tokens": ["a", "guy", "in", "a", "brown", "shirt"], "raw": "A guy in a brown shirt.", "sent_id": 69969, "sent": "a guy in a brown shirt"}], "file_name": "COCO_train2014_000000442641_449588.jpg", "ann_id": 449588, "sent_ids": [69968, 69969], "ref_id": 31895}, {"segmentation": [[52.01, 343.48, 52.01, 334.81, 54.9, 330.47, 56.34, 327.58, 56.34, 323.25, 65.01, 320.36, 78.01, 320.36, 79.46, 320.36, 92.46, 330.47, 92.46, 336.25, 92.46, 349.26, 86.68, 363.7, 86.68, 366.59, 86.68, 366.59, 98.24, 379.59, 108.35, 386.82, 121.35, 394.04, 127.13, 399.82, 141.58, 399.82, 156.03, 399.82, 164.7, 399.82, 173.36, 399.82, 184.92, 401.26, 184.92, 407.04, 184.92, 408.49, 167.58, 412.82, 130.02, 415.71, 114.13, 415.71, 105.46, 415.71, 92.46, 415.71, 80.9, 430.16, 73.68, 450.38, 73.68, 463.39, 79.46, 474.94, 15.89, 444.6, 20.23, 437.38, 21.67, 420.05, 21.67, 405.6, 21.67, 392.6, 21.67, 381.04, 11.56, 379.59, 0.0, 381.04, 4.33, 369.48, 4.33, 356.48, 52.01, 352.14]], "area": 10374.89825, "iscrowd": 0, "image_id": 202076, "bbox": [0.0, 320.36, 184.92, 154.58], "category_id": 1, "id": 460261, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "gloves", "unloading", "luggage", "from", "a", "ship"], "raw": "A man in gloves unloading luggage from a ship", "sent_id": 69982, "sent": "a man in gloves unloading luggage from a ship"}, {"tokens": ["a", "man", "with", "black", "hair", "who", "is", "wearing", "a", "black", "shit", "and", "pulling", "on", "the", "rope"], "raw": "A man with black hair who is wearing a black shit and pulling on the rope.", "sent_id": 69983, "sent": "a man with black hair who is wearing a black shit and pulling on the rope"}], "file_name": "COCO_train2014_000000202076_460261.jpg", "ann_id": 460261, "sent_ids": [69982, 69983], "ref_id": 31902}, {"segmentation": [[475.0, 438.33, 371.67, 416.67, 385.0, 538.33, 355.0, 551.67, 328.33, 536.67, 315.0, 563.33, 291.67, 563.33, 250.0, 510.0, 228.33, 495.0, 175.0, 455.0, 96.67, 373.33, 91.67, 350.0, 35.0, 336.67, 8.33, 366.67, 8.33, 628.33, 475.0, 628.33]], "area": 82407.79995000002, "iscrowd": 0, "image_id": 30973, "bbox": [8.33, 336.67, 466.67, 291.66], "category_id": 65, "id": 1957457, "split": "val", "sentences": [{"tokens": ["the", "gray", "folded", "comforter", "on", "the", "ground"], "raw": "The gray folded comforter on the ground.", "sent_id": 70022, "sent": "the gray folded comforter on the ground"}, {"tokens": ["the", "bottom", "floor", "and", "mattress", "the", "woman", "is", "laying", "on"], "raw": "The bottom floor and mattress the woman is laying on.", "sent_id": 70023, "sent": "the bottom floor and mattress the woman is laying on"}], "file_name": "COCO_train2014_000000030973_1957457.jpg", "ann_id": 1957457, "sent_ids": [70022, 70023], "ref_id": 31915}, {"segmentation": [[218.48, 2.8, 134.53, 26.48, 66.73, 44.77, 36.59, 63.07, 21.52, 110.42, 53.81, 149.17, 113.0, 150.24, 127.0, 143.78, 147.44, 143.78, 157.13, 148.09, 160.36, 151.32, 303.5, 159.93, 314.26, 147.01, 342.24, 143.78, 359.46, 161.0, 639.28, 161.0, 639.28, 30.78, 600.54, 31.86, 562.87, 1.72, 383.14, 1.72, 258.3, 0.65, 228.16, 1.72]], "area": 86680.32884999999, "iscrowd": 0, "image_id": 480797, "bbox": [21.52, 0.65, 617.76, 160.35], "category_id": 9, "id": 250487, "split": "val", "sentences": [{"tokens": ["a", "very", "large", "ship", "called", "aurora"], "raw": "A very large ship called Aurora.", "sent_id": 70059, "sent": "a very large ship called aurora"}, {"tokens": ["the", "giant", "cruise", "ship"], "raw": "The giant cruise ship.", "sent_id": 70060, "sent": "the giant cruise ship"}], "file_name": "COCO_train2014_000000480797_250487.jpg", "ann_id": 250487, "sent_ids": [70059, 70060], "ref_id": 31930}, {"segmentation": [[482.06, 419.1, 493.42, 356.13, 484.13, 341.68, 465.55, 290.06, 458.32, 276.65, 452.13, 262.19, 451.1, 245.68, 460.39, 199.23, 458.32, 185.81, 453.16, 172.39, 440.77, 163.1, 434.58, 155.87, 435.61, 144.52, 438.71, 142.45, 435.61, 126.97, 406.71, 96.0, 371.61, 53.68, 366.45, 52.65, 361.29, 52.65, 353.03, 65.03, 354.06, 77.42, 349.94, 80.52, 334.45, 65.03, 308.65, 58.84, 299.35, 59.87, 259.1, 64.0, 254.97, 64.0, 263.23, 83.61, 258.06, 80.52, 234.32, 73.29, 201.29, 79.48, 161.03, 94.97, 160.0, 96.0, 81.55, 135.23, 57.81, 175.48, 44.39, 181.68, 33.03, 188.9, 9.29, 182.71, 0.0, 189.94, 0.0, 195.1, 1.03, 259.1, 1.03, 354.06, 14.45, 454.19, 23.74, 472.77, 181.68, 477.94, 256.0, 469.68, 262.19, 465.55, 268.39, 352.0, 285.94, 314.84, 296.26, 286.97, 336.52, 320.0, 380.9, 363.35, 414.97, 397.42, 420.13, 419.1, 461.42, 430.45, 469.68, 424.26, 473.81, 422.19]], "area": 148208.5634, "iscrowd": 0, "image_id": 215493, "bbox": [0.0, 52.65, 493.42, 425.29], "category_id": 19, "id": 59286, "split": "val", "sentences": [{"tokens": ["brown", "horse", "head", "with", "harness"], "raw": "brown horse head with harness", "sent_id": 70077, "sent": "brown horse head with harness"}, {"tokens": ["a", "brown", "horse"], "raw": "A brown horse", "sent_id": 70078, "sent": "a brown horse"}], "file_name": "COCO_train2014_000000215493_59286.jpg", "ann_id": 59286, "sent_ids": [70077, 70078], "ref_id": 31937}, {"segmentation": [[482.65, 332.96, 480.73, 275.39, 471.14, 204.38, 486.49, 178.48, 475.94, 135.3, 460.58, 111.31, 463.46, 102.67, 474.02, 94.04, 487.45, 97.87, 494.17, 109.39, 491.29, 120.9, 490.33, 142.97, 511.44, 193.83, 523.91, 205.34, 514.32, 258.12, 526.79, 340.64, 521.04, 339.68, 505.68, 286.91, 505.68, 267.71, 498.01, 292.66, 492.25, 337.76]], "area": 7019.151800000002, "iscrowd": 0, "image_id": 334080, "bbox": [460.58, 94.04, 66.21, 246.6], "category_id": 25, "id": 598568, "split": "val", "sentences": [{"tokens": ["a", "right", "side", "giraffe"], "raw": "A right side giraffe", "sent_id": 70081, "sent": "a right side giraffe"}, {"tokens": ["a", "giraffe", "to", "the", "right", "of", "another"], "raw": "A giraffe to the right of another.", "sent_id": 70082, "sent": "a giraffe to the right of another"}], "file_name": "COCO_train2014_000000334080_598568.jpg", "ann_id": 598568, "sent_ids": [70081, 70082], "ref_id": 31939}, {"segmentation": [[443.17, 2.24, 442.42, 34.29, 437.95, 46.97, 422.29, 78.28, 417.82, 93.94, 432.73, 102.14, 438.69, 102.14, 437.95, 83.5, 445.4, 59.64, 458.08, 41.0, 470.01, 34.29, 482.68, 0.0], [372.34, 0.75, 361.9, 11.93, 343.27, 21.62, 332.08, 29.08, 323.14, 35.79, 325.37, 46.97, 339.54, 51.44, 366.38, 44.73, 390.98, 38.77, 394.71, 22.37, 399.18, 2.24]], "area": 4517.968899999998, "iscrowd": 0, "image_id": 377017, "bbox": [323.14, 0.0, 159.54, 102.14], "category_id": 1, "id": 509100, "split": "val", "sentences": [{"tokens": ["black", "shoes", "with", "white", "socks"], "raw": "Black shoes with white socks.", "sent_id": 70148, "sent": "black shoes with white socks"}, {"tokens": ["the", "guy", "with", "white", "socks", "in", "the", "right", "hand", "picture"], "raw": "the guy with white socks in the right hand picture", "sent_id": 70149, "sent": "the guy with white socks in the right hand picture"}], "file_name": "COCO_train2014_000000377017_509100.jpg", "ann_id": 509100, "sent_ids": [70148, 70149], "ref_id": 31966}, {"segmentation": [[490.09, 292.43, 490.09, 292.43, 495.83, 289.56, 502.53, 284.77, 512.11, 278.07, 517.85, 272.33, 529.34, 266.58, 545.61, 262.75, 553.27, 253.18, 564.75, 242.65, 574.32, 238.82, 596.34, 239.78, 623.14, 240.74, 640.0, 240.74, 640.0, 248.4, 640.0, 257.97, 632.71, 269.45, 626.01, 280.94, 618.36, 295.3, 608.78, 302.96, 599.21, 308.7, 585.81, 314.44, 579.11, 323.06, 576.24, 335.5, 573.37, 338.37, 560.92, 338.37, 547.52, 340.29, 531.25, 342.2, 521.68, 341.24, 513.06, 340.29, 506.36, 346.03, 499.66, 350.82, 492.0, 347.94, 486.26, 336.46, 483.39, 321.14, 483.39, 304.87, 487.22, 290.51, 494.88, 287.64]], "area": 10592.2767, "iscrowd": 0, "image_id": 257867, "bbox": [483.39, 238.82, 156.61, 112.0], "category_id": 3, "id": 359465, "split": "val", "sentences": [{"tokens": ["a", "silver", "sedan", "next", "to", "the", "right", "side", "of", "a", "white", "and", "red", "work", "truck"], "raw": "A silver sedan next to the right side of a white and red work truck.", "sent_id": 70159, "sent": "a silver sedan next to the right side of a white and red work truck"}], "file_name": "COCO_train2014_000000257867_359465.jpg", "ann_id": 359465, "sent_ids": [70159], "ref_id": 31969}, {"segmentation": [[6.48, 238.53, 51.74, 243.64, 75.83, 248.75, 94.81, 265.54, 103.57, 276.49, 108.68, 289.63, 112.33, 304.96, 122.55, 329.05, 132.77, 329.05, 139.34, 326.86, 144.45, 335.62, 147.37, 356.06, 148.1, 364.09, 141.53, 364.09, 118.9, 426.0, 1.37, 426.0, 0.0, 242.18]], "area": 21948.62065, "iscrowd": 0, "image_id": 506592, "bbox": [0.0, 238.53, 148.1, 187.47], "category_id": 33, "id": 1844135, "split": "val", "sentences": [{"tokens": ["part", "of", "the", "black", "luggage"], "raw": "part of the black luggage", "sent_id": 70162, "sent": "part of the black luggage"}], "file_name": "COCO_train2014_000000506592_1844135.jpg", "ann_id": 1844135, "sent_ids": [70162], "ref_id": 31971}, {"segmentation": [[284.92, 618.66, 350.78, 505.55, 333.6, 482.64, 350.78, 445.42, 373.69, 409.62, 402.33, 409.62, 435.26, 355.22, 445.28, 349.49, 476.78, 349.49, 480.0, 561.39, 408.05, 538.48, 365.1, 515.57, 294.94, 622.96]], "area": 21734.837500000005, "iscrowd": 0, "image_id": 100611, "bbox": [284.92, 349.49, 195.08, 273.47], "category_id": 62, "id": 378637, "split": "val", "sentences": [{"tokens": ["a", "black", "chair", "with", "no", "one", "sitting", "in", "it"], "raw": "A black chair with no one sitting in it.", "sent_id": 70209, "sent": "a black chair with no one sitting in it"}, {"tokens": ["black", "patio", "chair", "outside", "on", "the", "sidewalk", "unoccupied"], "raw": "Black patio chair outside on the sidewalk unoccupied.", "sent_id": 70210, "sent": "black patio chair outside on the sidewalk unoccupied"}], "file_name": "COCO_train2014_000000100611_378637.jpg", "ann_id": 378637, "sent_ids": [70209, 70210], "ref_id": 31990}, {"segmentation": [[41.57, 358.43, 0.0, 342.7, 2.25, 300.0, 30.34, 207.87, 28.09, 164.04, 44.94, 113.48, 62.92, 56.18, 85.39, 32.58, 108.99, 1.12, 159.55, 1.12, 170.79, 32.58, 164.04, 48.31, 156.18, 52.81, 151.69, 82.02, 132.58, 77.53, 132.58, 149.44, 115.73, 151.69, 123.6, 191.01, 132.58, 203.37, 108.99, 216.85, 95.51, 216.85, 89.89, 207.87, 51.69, 276.4, 38.2, 300.0, 58.43, 311.24, 48.31, 356.18]], "area": 25359.552850000004, "iscrowd": 0, "image_id": 141952, "bbox": [0.0, 1.12, 170.79, 357.31], "category_id": 1, "id": 1204522, "split": "val", "sentences": [{"tokens": ["a", "standing", "woman", "handing", "a", "sitting", "man", "a", "plate"], "raw": "A standing woman handing a sitting man a plate.", "sent_id": 70246, "sent": "a standing woman handing a sitting man a plate"}, {"tokens": ["a", "woman", "wearing", "a", "scarf", "is", "handing", "a", "plate", "to", "a", "man", "who", "is", "sitting", "on", "the", "side", "walk", "with", "a", "pizza", ",", "pop", "up", "chairs", ",", "and", "another", "man", "who", "seems", "to", "be", "waiting", "for", "something"], "raw": "A woman wearing a scarf is handing a plate to a man who is sitting on the side walk with a pizza, pop up chairs, and another man who seems to be waiting for something.", "sent_id": 70247, "sent": "a woman wearing a scarf is handing a plate to a man who is sitting on the side walk with a pizza , pop up chairs , and another man who seems to be waiting for something"}], "file_name": "COCO_train2014_000000141952_1204522.jpg", "ann_id": 1204522, "sent_ids": [70246, 70247], "ref_id": 32004}, {"segmentation": [[206.24, 54.87, 244.0, 56.8, 278.86, 56.8, 322.43, 68.42, 345.67, 92.63, 356.32, 126.52, 363.1, 153.63, 361.16, 175.9, 327.27, 209.79, 303.06, 223.34, 306.94, 300.8, 311.78, 347.28, 314.68, 392.79, 295.32, 376.33, 278.86, 368.58, 246.9, 363.74, 225.6, 316.3, 225.6, 315.33, 211.08, 330.82, 208.17, 366.65, 195.59, 381.17, 169.44, 403.44, 164.6, 407.31, 154.92, 405.38, 152.98, 369.55, 152.98, 339.53, 152.98, 327.92, 150.08, 306.61, 135.56, 272.72, 122.97, 243.68, 114.25, 199.14, 111.35, 192.36, 93.92, 161.38, 90.05, 129.42, 99.73, 97.47, 125.87, 78.11, 143.3, 69.39, 167.51, 64.55, 191.71, 68.42, 205.27, 54.87]], "area": 63194.476250000014, "iscrowd": 0, "image_id": 70745, "bbox": [90.05, 54.87, 273.05, 352.44], "category_id": 22, "id": 584851, "split": "val", "sentences": [{"tokens": ["elephant", "pushing", "the", "stone"], "raw": "elephant pushing the stone", "sent_id": 70306, "sent": "elephant pushing the stone"}, {"tokens": ["an", "elephant", "standing", "behind", "a", "small", "rock"], "raw": "An elephant standing behind a small rock", "sent_id": 70307, "sent": "an elephant standing behind a small rock"}], "file_name": "COCO_train2014_000000070745_584851.jpg", "ann_id": 584851, "sent_ids": [70306, 70307], "ref_id": 32021}, {"segmentation": [[97.77, 349.59, 150.62, 76.54, 167.9, 0.0, 213.58, 2.47, 297.53, 238.27, 330.86, 330.86, 341.98, 338.27, 348.15, 341.98, 346.91, 351.85, 317.28, 361.73, 239.51, 369.14, 165.43, 371.6, 106.17, 367.9, 93.83, 367.9]], "area": 54509.8149, "iscrowd": 0, "image_id": 429143, "bbox": [93.83, 0.0, 254.32, 371.6], "category_id": 9, "id": 1801844, "split": "val", "sentences": [{"tokens": ["a", "sailboat", "with", "a", "yellow", "base"], "raw": "A sailboat with a yellow base", "sent_id": 70314, "sent": "a sailboat with a yellow base"}, {"tokens": ["a", "yellow", "remote", "control", "boat", "on", "a", "lake"], "raw": "A yellow remote control boat on a lake.", "sent_id": 70315, "sent": "a yellow remote control boat on a lake"}], "file_name": "COCO_train2014_000000429143_1801844.jpg", "ann_id": 1801844, "sent_ids": [70314, 70315], "ref_id": 32025}, {"segmentation": [[134.83, 396.13, 130.52, 363.78, 120.81, 358.38, 121.89, 347.6, 113.26, 296.9, 124.04, 250.52, 133.75, 234.34, 154.25, 225.71, 161.8, 214.92, 157.48, 209.53, 157.48, 196.58, 165.03, 178.25, 183.37, 178.25, 197.39, 187.96, 197.39, 201.98, 197.39, 214.92, 190.92, 222.47, 190.92, 227.87, 200.63, 237.57, 215.73, 255.91, 222.2, 289.35, 228.67, 319.55, 218.97, 345.44, 221.12, 385.35, 240.54, 463.01, 238.38, 472.72, 202.79, 475.96, 198.47, 438.2, 186.61, 392.9, 179.06, 426.34, 186.61, 450.07, 186.61, 466.25, 184.45, 472.72, 176.9, 468.4, 165.03, 454.38, 151.01, 447.91, 148.85, 431.73, 166.11, 417.71, 168.27, 412.31, 154.25, 402.61, 146.7, 397.21, 141.3, 397.21, 134.83, 391.82]], "area": 22523.770249999998, "iscrowd": 0, "image_id": 496053, "bbox": [113.26, 178.25, 127.28, 297.71], "category_id": 1, "id": 183735, "split": "val", "sentences": [{"tokens": ["man", "wearing", "baseball", "cap"], "raw": "man wearing baseball cap", "sent_id": 70323, "sent": "man wearing baseball cap"}, {"tokens": ["a", "man", "standing", "with", "light", "blue", "shirt", "and", "wearing", "cap"], "raw": "A man standing with light blue shirt and wearing cap", "sent_id": 70324, "sent": "a man standing with light blue shirt and wearing cap"}], "file_name": "COCO_train2014_000000496053_183735.jpg", "ann_id": 183735, "sent_ids": [70323, 70324], "ref_id": 32028}, {"segmentation": [[191.56, 278.37, 62.9, 275.51, 73.38, 262.17, 90.54, 153.53, 202.99, 155.43, 408.85, 183.07, 401.22, 261.22, 360.24, 266.94, 353.57, 242.16, 343.09, 263.13, 270.66, 281.23, 268.75, 251.69, 256.36, 245.02, 245.88, 266.94, 243.97, 281.23, 198.23, 279.33]], "area": 35082.56695000001, "iscrowd": 0, "image_id": 131449, "bbox": [62.9, 153.53, 345.95, 127.7], "category_id": 6, "id": 163579, "split": "val", "sentences": [{"tokens": ["a", "bus", ",", "to", "the", "left", "of", "another", "bus"], "raw": "A bus, to the left of another bus", "sent_id": 70407, "sent": "a bus , to the left of another bus"}, {"tokens": ["a", "bus", "with", "text", "on", "its", "screen"], "raw": "a bus with text on its screen", "sent_id": 70408, "sent": "a bus with text on its screen"}], "file_name": "COCO_train2014_000000131449_163579.jpg", "ann_id": 163579, "sent_ids": [70407, 70408], "ref_id": 32059}, {"segmentation": [[638.56, 32.36, 564.13, 76.58, 518.83, 114.34, 489.71, 145.62, 476.76, 156.4, 489.71, 187.69, 551.19, 132.67, 584.63, 120.81, 638.56, 81.98]], "area": 7663.129899999998, "iscrowd": 0, "image_id": 181009, "bbox": [476.76, 32.36, 161.8, 155.33], "category_id": 27, "id": 1170387, "split": "val", "sentences": [{"tokens": ["strap", "on", "other", "person", "'", "s", "shoulder"], "raw": "Strap on other person's shoulder.", "sent_id": 70423, "sent": "strap on other person ' s shoulder"}, {"tokens": ["a", "black", "backpack", "strap", "draped", "over", "a", "shoulder"], "raw": "A black backpack strap draped over a shoulder.", "sent_id": 70424, "sent": "a black backpack strap draped over a shoulder"}], "file_name": "COCO_train2014_000000181009_1170387.jpg", "ann_id": 1170387, "sent_ids": [70423, 70424], "ref_id": 32064}, {"segmentation": [[260.9, 277.48, 288.29, 276.04, 301.26, 280.36, 308.47, 294.77, 299.82, 323.6, 309.91, 336.58, 327.21, 338.02, 347.39, 339.46, 360.36, 304.86, 351.71, 281.8, 369.01, 276.04, 387.75, 277.48, 386.31, 301.98, 386.31, 327.93, 374.77, 356.76, 361.8, 363.96, 332.97, 375.5, 327.21, 387.03, 312.79, 496.58, 324.32, 531.17, 318.56, 627.75, 308.47, 621.98, 285.41, 593.15, 286.85, 574.41, 278.2, 531.17, 273.87, 562.88, 269.55, 597.48, 269.55, 632.07, 227.75, 604.68, 240.72, 584.5, 245.05, 554.23, 230.63, 441.8, 233.51, 382.7, 214.77, 389.91, 197.48, 376.94, 160.0, 301.98, 180.18, 296.22, 191.71, 296.22, 201.8, 317.84, 211.89, 342.34, 216.22, 353.87, 255.14, 326.49, 246.49, 293.33]], "area": 32767.68475, "iscrowd": 0, "image_id": 286132, "bbox": [160.0, 276.04, 227.75, 356.03], "category_id": 1, "id": 487517, "split": "val", "sentences": [{"tokens": ["a", "child", "holding", "skis"], "raw": "a child holding skis", "sent_id": 70438, "sent": "a child holding skis"}, {"tokens": ["small", "boy", "skiing"], "raw": "small boy skiing", "sent_id": 70439, "sent": "small boy skiing"}], "file_name": "COCO_train2014_000000286132_487517.jpg", "ann_id": 487517, "sent_ids": [70438, 70439], "ref_id": 32071}, {"segmentation": [[238.11, 562.92, 239.48, 523.01, 291.78, 491.35, 304.17, 485.85, 353.72, 502.37, 400.52, 527.14, 425.0, 502.37, 425.0, 630.37, 404.65, 638.62, 414.28, 576.69, 417.03, 556.04, 363.35, 613.85, 350.97, 640.0, 333.08, 640.0, 331.7, 615.23, 254.62, 564.3, 242.24, 562.92, 229.85, 640.0, 225.72, 611.1, 236.73, 535.4]], "area": 17884.4883, "iscrowd": 0, "image_id": 417276, "bbox": [225.72, 485.85, 199.28, 154.15], "category_id": 62, "id": 103225, "split": "val", "sentences": [{"tokens": ["chair", "with", "visible", "back"], "raw": "Chair with visible back.", "sent_id": 70498, "sent": "chair with visible back"}], "file_name": "COCO_train2014_000000417276_103225.jpg", "ann_id": 103225, "sent_ids": [70498], "ref_id": 32094}, {"segmentation": [[244.88, 1.9, 223.21, 66.91, 217.79, 140.59, 226.46, 191.51, 243.79, 234.85, 287.13, 259.77, 319.64, 279.28, 288.22, 252.19, 292.55, 228.35, 315.3, 228.35, 331.56, 222.93, 299.05, 183.93, 288.22, 151.42, 261.13, 131.92, 275.21, 97.25, 291.47, 54.99, 318.56, 23.57, 328.31, 11.65, 335.89, 12.73, 335.89, 33.32, 335.89, 53.91, 344.56, 72.33, 333.72, 83.16, 333.72, 120.0, 333.72, 149.26, 333.72, 175.26, 340.23, 190.43, 361.9, 181.76, 405.24, 173.09, 409.57, 192.6, 423.66, 212.1, 438.83, 219.68, 445.33, 219.68, 464.83, 208.85, 483.25, 195.85, 491.92, 187.18, 491.92, 179.59, 496.25, 160.09, 542.84, 137.34, 547.18, 126.5, 615.44, 92.91, 640.0, 82.08, 640.0, 1.9]], "area": 64425.659299999985, "iscrowd": 0, "image_id": 421086, "bbox": [217.79, 1.9, 422.21, 277.38], "category_id": 1, "id": 488434, "split": "val", "sentences": [{"tokens": ["the", "person", "wearing", "the", "black", "shirt"], "raw": "THE PERSON WEARING THE BLACK SHIRT", "sent_id": 70629, "sent": "the person wearing the black shirt"}, {"tokens": ["a", "man", "cutting", "slices", "of", "pizza", "wearing", "gloves", "and", "a", "black", "shirt"], "raw": "a man cutting slices of pizza wearing gloves and a black shirt", "sent_id": 70630, "sent": "a man cutting slices of pizza wearing gloves and a black shirt"}], "file_name": "COCO_train2014_000000421086_488434.jpg", "ann_id": 488434, "sent_ids": [70629, 70630], "ref_id": 32144}, {"segmentation": [[1.44, 267.62, 3.61, 190.44, 19.48, 130.56, 49.05, 120.47, 59.87, 113.97, 62.04, 100.27, 57.71, 98.82, 54.82, 93.05, 55.54, 82.23, 62.04, 62.76, 72.13, 56.99, 95.22, 65.64, 103.15, 77.91, 103.15, 87.28, 100.99, 95.22, 93.05, 103.87, 91.61, 114.69, 91.61, 119.74, 95.22, 128.4, 122.63, 141.38, 130.56, 276.28, 119.74, 298.64, 103.15, 296.47, 101.71, 308.02, 99.55, 317.39, 19.48, 317.39, 24.53, 291.42, 14.43, 290.7, 7.93, 284.93, 5.77, 271.23, 2.16, 271.95, 2.89, 243.09]], "area": 24279.581049999993, "iscrowd": 0, "image_id": 542442, "bbox": [1.44, 56.99, 129.12, 260.4], "category_id": 1, "id": 236319, "split": "val", "sentences": [{"tokens": ["man", "on", "far", "left"], "raw": "MAN ON FAR LEFT", "sent_id": 70746, "sent": "man on far left"}], "file_name": "COCO_train2014_000000542442_236319.jpg", "ann_id": 236319, "sent_ids": [70746], "ref_id": 32188}, {"segmentation": [[237.08, 63.22, 253.59, 50.84, 303.82, 29.51, 331.33, 24.69, 345.78, 36.39, 345.09, 46.71, 338.21, 57.03, 344.41, 74.23, 348.53, 91.43, 344.41, 104.5, 358.85, 117.57, 385.68, 147.84, 398.76, 158.85, 415.27, 174.67, 411.83, 187.06, 402.88, 200.13, 394.63, 202.19, 388.44, 192.56, 378.12, 184.99, 367.8, 173.3, 369.06, 189.89, 307.19, 231.01, 298.73, 227.94, 286.82, 204.49, 279.13, 181.82, 275.29, 193.35, 265.68, 211.03, 259.14, 219.1, 253.38, 226.4, 248.0, 230.25, 241.46, 229.48, 241.08, 219.1, 243.77, 205.65, 252.23, 178.36, 254.92, 167.98, 264.91, 137.62, 269.14, 130.7, 274.13, 127.24, 281.44, 121.86, 276.44, 115.71, 266.45, 108.03, 259.91, 97.65, 254.92, 83.43, 250.3, 83.81, 239.16, 75.74, 237.24, 67.67]], "area": 19917.946849999997, "iscrowd": 0, "image_id": 521338, "bbox": [237.08, 24.69, 178.19, 206.32], "category_id": 88, "id": 1161932, "split": "val", "sentences": [{"tokens": ["teddy", "bear", "that", "you", "can", "see", "both", "eyes"], "raw": "Teddy bear that you can see both eyes.", "sent_id": 70780, "sent": "teddy bear that you can see both eyes"}, {"tokens": ["a", "bear", "with", "a", "button", "on", "its", "chest"], "raw": "a bear with a button on its chest", "sent_id": 70781, "sent": "a bear with a button on its chest"}], "file_name": "COCO_train2014_000000521338_1161932.jpg", "ann_id": 1161932, "sent_ids": [70780, 70781], "ref_id": 32195}, {"segmentation": [[142.31, 146.75, 333.13, 63.47, 506.16, 86.11, 516.67, 297.15, 333.13, 327.06, 256.31, 306.85, 245.8, 310.89, 232.06, 308.47, 222.35, 297.15, 220.74, 281.78, 156.86, 251.87, 147.97, 252.67, 147.97, 247.82, 147.97, 246.21, 143.92, 238.12]], "area": 78105.80014999998, "iscrowd": 0, "image_id": 416586, "bbox": [142.31, 63.47, 374.36, 263.59], "category_id": 6, "id": 166779, "split": "val", "sentences": [{"tokens": ["a", "red", "bus", "with", "number", "419", "and", "an", "ad", "on", "the", "back"], "raw": "A red bus with number 419 and an ad on the back.", "sent_id": 70839, "sent": "a red bus with number 419 and an ad on the back"}], "file_name": "COCO_train2014_000000416586_166779.jpg", "ann_id": 166779, "sent_ids": [70839], "ref_id": 32211}, {"segmentation": [[93.02, 277.38, 214.51, 271.75, 215.13, 394.48, 215.13, 407.01, 209.5, 407.01, 204.49, 369.44, 141.87, 375.07, 144.37, 416.4, 136.23, 416.4, 134.98, 377.58, 134.35, 395.11, 127.47, 392.61, 126.84, 287.4, 94.28, 286.78]], "area": 9750.472999999996, "iscrowd": 0, "image_id": 329543, "bbox": [93.02, 271.75, 122.11, 144.65], "category_id": 79, "id": 1642568, "split": "val", "sentences": [{"tokens": ["the", "appliance", "to", "the", "left", "of", "the", "girl", "in", "the", "black"], "raw": "The appliance to the left of the girl in the black.", "sent_id": 70840, "sent": "the appliance to the left of the girl in the black"}, {"tokens": ["a", "small", "oven", "is", "left", "side", "of", "the", "woman"], "raw": "A small oven is left side of the woman", "sent_id": 70841, "sent": "a small oven is left side of the woman"}], "file_name": "COCO_train2014_000000329543_1642568.jpg", "ann_id": 1642568, "sent_ids": [70840, 70841], "ref_id": 32212}, {"segmentation": [[222.47, 368.26, 218.26, 324.44, 198.03, 321.91, 185.39, 305.9, 186.24, 288.2, 203.09, 273.88, 203.09, 215.73, 198.88, 193.82, 164.33, 176.12, 181.18, 150.0, 192.98, 128.93, 196.35, 113.76, 186.24, 95.22, 176.12, 89.33, 159.27, 85.96, 147.47, 88.48, 134.83, 95.22, 126.4, 103.65, 115.13, 112.03, 109.15, 118.01, 107.96, 125.18, 106.76, 133.56, 113.54, 140.73, 107.96, 160.66, 101.18, 160.66, 70.88, 164.25, 47.76, 170.23, 39.79, 179.8, 29.83, 201.32, 23.45, 223.24, 19.06, 236.0, 21.06, 244.77, 21.06, 249.95, 15.48, 271.88, 6.31, 291.41, 5.91, 317.72, 9.1, 333.66, 0.33, 340.84, 0.73, 374.32, 221.16, 375.0, 223.95, 366.35]], "area": 44052.106750000006, "iscrowd": 0, "image_id": 99451, "bbox": [0.33, 85.96, 223.62, 289.04], "category_id": 1, "id": 530461, "split": "val", "sentences": [{"tokens": ["a", "boy", "with", "blue", "pants", "and", "dark", "blue", "t", "shirt", "smiling", "at", "camera"], "raw": "a boy with blue pants and dark blue t shirt smiling at camera", "sent_id": 70859, "sent": "a boy with blue pants and dark blue t shirt smiling at camera"}], "file_name": "COCO_train2014_000000099451_530461.jpg", "ann_id": 530461, "sent_ids": [70859], "ref_id": 32221}, {"segmentation": [[85.21, 139.42, 228.67, 118.92, 248.09, 232.18, 115.42, 264.54, 103.55, 260.22]], "area": 17789.1614, "iscrowd": 0, "image_id": 217893, "bbox": [85.21, 118.92, 162.88, 145.62], "category_id": 72, "id": 31315, "split": "val", "sentences": [{"tokens": ["a", "grey", "monitor", "that", "is", "off"], "raw": "A grey monitor that is off.", "sent_id": 70884, "sent": "a grey monitor that is off"}, {"tokens": ["a", "flat", "screen", "computer", "monitor", "with", "audio", "plugs", "inserted", "in", "the", "front", "panel"], "raw": "A flat screen computer monitor with audio plugs inserted in the front panel.", "sent_id": 70885, "sent": "a flat screen computer monitor with audio plugs inserted in the front panel"}], "file_name": "COCO_train2014_000000217893_31315.jpg", "ann_id": 31315, "sent_ids": [70884, 70885], "ref_id": 32231}, {"segmentation": [[304.61, 275.69, 354.74, 271.84, 399.08, 261.23, 420.29, 284.37, 454.99, 301.72, 497.41, 352.81, 496.44, 391.37, 479.09, 401.01, 473.31, 409.68, 476.2, 423.18, 20.24, 423.18, 15.42, 398.12, 39.52, 358.59, 39.52, 351.85, 38.56, 341.24, 40.49, 336.42, 96.4, 344.14, 257.38, 306.54, 289.19, 283.41]], "area": 53395.6709, "iscrowd": 0, "image_id": 132889, "bbox": [15.42, 261.23, 481.99, 161.95], "category_id": 67, "id": 413742, "split": "val", "sentences": [{"tokens": ["table", "with", "cloth"], "raw": "table with cloth", "sent_id": 70898, "sent": "table with cloth"}], "file_name": "COCO_train2014_000000132889_413742.jpg", "ann_id": 413742, "sent_ids": [70898], "ref_id": 32235}, {"segmentation": [[384.7, 221.1, 475.96, 229.27, 484.81, 9.97, 466.42, 0.0, 402.41, 0.0, 388.78, 11.34, 384.7, 93.06]], "area": 21227.087850000004, "iscrowd": 0, "image_id": 329616, "bbox": [384.7, 0.0, 100.11, 229.27], "category_id": 44, "id": 92257, "split": "val", "sentences": [{"tokens": ["aceto"], "raw": "aceto", "sent_id": 70915, "sent": "aceto"}, {"tokens": ["bottle", "of", "aceton", "balsemita", "de", "modena"], "raw": "Bottle of aceton balsemita de modena", "sent_id": 70916, "sent": "bottle of aceton balsemita de modena"}], "file_name": "COCO_train2014_000000329616_92257.jpg", "ann_id": 92257, "sent_ids": [70915, 70916], "ref_id": 32240}, {"segmentation": [[0.0, 421.24, 0.96, 243.73, 25.91, 230.29, 72.93, 223.58, 140.09, 243.73, 187.11, 249.48, 257.16, 248.52, 277.31, 232.21, 329.13, 180.4, 372.31, 150.65, 390.54, 142.01, 386.7, 133.38, 385.74, 126.66, 399.17, 127.62, 407.81, 140.09, 415.49, 138.18, 420.28, 131.46, 442.35, 136.26, 455.79, 143.93, 463.46, 156.41, 460.58, 165.04, 487.45, 184.23, 500.89, 196.71, 509.52, 215.9, 524.87, 231.25, 544.07, 257.16, 553.66, 272.51, 542.15, 302.26, 539.27, 312.81, 530.63, 315.69, 490.33, 293.62, 446.19, 280.19, 430.84, 275.39, 415.49, 292.66, 377.1, 345.44, 346.4, 404.93, 340.64, 409.73, 329.13, 406.85, 319.53, 399.17, 294.58, 404.93, 287.87, 413.57, 283.07, 417.4, 284.99, 422.2, 73.89, 420.28, 44.14, 390.54, 34.54, 382.86, 24.95, 405.89, 18.23, 422.2, 0.96, 419.32]], "area": 91925.89129999997, "iscrowd": 0, "image_id": 233022, "bbox": [0.0, 126.66, 553.66, 295.54], "category_id": 24, "id": 593058, "split": "val", "sentences": [{"tokens": ["a", "zebra", "facing", "right"], "raw": "A Zebra facing right.", "sent_id": 70937, "sent": "a zebra facing right"}, {"tokens": ["the", "front", "most", "zebra"], "raw": "the front most zebra", "sent_id": 70938, "sent": "the front most zebra"}], "file_name": "COCO_train2014_000000233022_593058.jpg", "ann_id": 593058, "sent_ids": [70937, 70938], "ref_id": 32250}, {"segmentation": [[554.66, 267.65, 530.89, 51.94, 577.55, 0.0, 640.0, 0.88, 640.0, 252.68, 568.75, 269.41, 552.9, 267.65]], "area": 24943.68170000001, "iscrowd": 0, "image_id": 174774, "bbox": [530.89, 0.0, 109.11, 269.41], "category_id": 72, "id": 33250, "split": "val", "sentences": [{"tokens": ["right", "monitor", "in", "the", "right", "hand", "picture"], "raw": "right monitor in the right hand picture", "sent_id": 70941, "sent": "right monitor in the right hand picture"}, {"tokens": ["the", "black", "computer", "screen", "on", "the", "right"], "raw": "the black computer screen on the right", "sent_id": 70942, "sent": "the black computer screen on the right"}], "file_name": "COCO_train2014_000000174774_33250.jpg", "ann_id": 33250, "sent_ids": [70941, 70942], "ref_id": 32252}, {"segmentation": [[149.55, 431.07, 160.31, 398.81, 148.58, 394.9, 145.64, 385.13, 147.6, 260.99, 150.53, 209.18, 163.24, 178.88, 186.7, 152.49, 215.05, 140.76, 242.41, 125.12, 252.19, 114.36, 262.94, 88.95, 282.49, 60.6, 308.88, 36.17, 327.45, 26.39, 339.18, 25.41, 345.05, 29.32, 357.76, 34.21, 371.44, 40.08, 385.13, 57.67, 388.06, 85.04, 363.62, 115.34, 351.89, 133.91, 333.32, 144.67, 314.75, 156.4, 313.77, 179.86, 327.45, 195.5, 340.16, 206.25, 343.09, 218.95, 343.09, 237.53, 340.16, 294.22, 337.23, 329.41, 317.68, 336.25, 298.13, 338.21, 295.2, 347.0, 296.18, 364.6, 301.06, 373.4, 315.73, 375.35, 340.16, 377.31, 373.4, 389.04, 423.25, 414.45, 446.71, 418.36, 455.5, 425.2, 449.64, 433.02, 392.95, 430.09, 367.53, 414.45, 346.03, 414.45, 332.34, 409.56, 337.23, 418.36, 337.23, 432.05]], "area": 65700.0881, "iscrowd": 0, "image_id": 323960, "bbox": [145.64, 25.41, 309.86, 407.61], "category_id": 1, "id": 462993, "split": "val", "sentences": [{"tokens": ["a", "couple", "smiling", "for", "a", "picture"], "raw": "A couple smiling for a picture.", "sent_id": 70951, "sent": "a couple smiling for a picture"}, {"tokens": ["man", "wearing", "glasses", "and", "a", "tie"], "raw": "Man wearing glasses and a tie.", "sent_id": 70952, "sent": "man wearing glasses and a tie"}], "file_name": "COCO_train2014_000000323960_462993.jpg", "ann_id": 462993, "sent_ids": [70951, 70952], "ref_id": 32257}, {"segmentation": [[169.66, 200.91, 147.83, 222.32, 139.67, 234.13, 124.02, 245.81, 119.61, 256.11, 116.66, 275.99, 114.46, 281.14, 105.62, 271.57, 104.15, 239.92, 101.94, 222.26, 103.42, 206.8, 107.1, 197.23, 115.93, 190.61, 131.38, 186.93, 138.74, 174.42, 141.69, 164.11, 154.94, 157.49, 157.14, 153.07, 159.35, 146.45, 156.41, 133.94, 154.94, 124.37, 155.67, 111.86, 159.35, 97.14, 163.77, 89.78, 183.64, 80.94, 188.06, 86.76, 189.53, 106.63, 185.85, 108.84, 182.9, 114.73, 187.32, 128.71, 189.53, 131.66, 188.79, 145.64, 190.26, 160.36, 193.21, 173.61, 193.94, 179.5, 191.74, 185.39, 182.17, 191.28, 176.28, 197.9, 173.34, 203.05, 155.13, 215.31]], "area": 7140.06085, "iscrowd": 0, "image_id": 131030, "bbox": [101.94, 80.94, 92.0, 200.2], "category_id": 1, "id": 518693, "split": "val", "sentences": [{"tokens": ["a", "black", "man", "sits", "at", "a", "table", "alone"], "raw": "A black man sits at a table alone.", "sent_id": 70977, "sent": "a black man sits at a table alone"}, {"tokens": ["man", "next", "to", "wall", "in", "dark", "shirt", "and", "dark", "hair", "facing", "away"], "raw": "Man next to wall in dark shirt and dark hair facing away.", "sent_id": 70978, "sent": "man next to wall in dark shirt and dark hair facing away"}], "file_name": "COCO_train2014_000000131030_518693.jpg", "ann_id": 518693, "sent_ids": [70977, 70978], "ref_id": 32266}, {"segmentation": [[87.48, 0.45, 88.07, 3.3, 89.02, 5.08, 89.61, 6.26, 90.8, 7.57, 93.05, 10.18, 94.24, 12.43, 94.95, 13.38, 95.78, 14.8, 95.9, 15.28, 95.18, 16.7, 95.07, 17.53, 96.01, 18.6, 96.25, 19.55, 96.37, 20.02, 94.24, 23.64, 92.69, 26.61, 89.97, 31.0, 88.19, 33.84, 86.29, 39.06, 85.7, 43.21, 85.22, 45.7, 84.87, 49.26, 84.51, 50.45, 83.8, 55.73, 83.92, 57.86, 94.59, 57.98, 100.76, 58.1, 104.32, 58.34, 107.16, 59.29, 109.42, 60.35, 111.2, 64.39, 113.81, 71.5, 114.87, 75.89, 115.82, 79.92, 120.09, 97.54, 120.92, 98.72, 125.31, 97.66, 126.62, 97.89, 130.53, 98.49, 131.36, 100.15, 132.07, 101.93, 132.43, 103.11, 138.95, 128.67, 142.91, 143.71, 143.46, 147.75, 145.1, 156.26, 145.2, 158.88, 146.08, 160.08, 152.41, 162.81, 159.39, 163.35, 164.52, 163.9, 165.5, 162.92, 167.47, 156.7, 170.53, 149.06, 171.18, 147.42, 167.91, 146.98, 166.92, 146.98, 166.6, 146.0, 165.4, 145.24, 166.49, 145.35, 172.38, 145.89, 173.91, 144.91, 176.75, 140.54, 180.46, 136.5, 177.73, 136.34, 178.27, 133.83, 176.64, 131.97, 176.2, 131.42, 175.55, 127.82, 175.44, 120.84, 175.11, 113.63, 174.45, 108.18, 170.33, 90.5, 166.33, 81.48, 162.08, 78.12, 155.89, 76.19, 154.22, 75.68, 151.12, 73.23, 149.19, 72.3, 148.68, 69.34, 146.74, 67.28, 143.91, 65.09, 141.97, 63.41, 140.81, 62.38, 139.52, 61.61, 139.52, 60.7, 138.11, 58.51, 136.56, 57.61, 134.63, 53.61, 131.4, 49.62, 130.5, 47.43, 129.73, 44.72, 126.38, 38.13, 124.7, 34.52, 123.67, 30.52, 122.25, 27.94, 121.61, 26.91, 120.96, 26.14, 118.64, 25.37, 116.97, 24.98, 116.58, 24.08, 122.12, 24.21, 124.44, 23.17, 125.86, 21.11, 127.15, 16.73, 128.05, 15.83, 128.44, 14.41, 128.57, 12.86, 128.18, 11.32, 128.83, 10.03, 129.6, 7.96, 127.92, 5.52, 126.76, 4.48, 126.38, 3.32, 126.51, 1.65, 127.28, 0.0], [84.72, 64.46, 98.13, 64.59, 103.67, 65.62, 105.48, 67.17, 107.8, 72.84, 109.47, 78.12, 112.18, 87.4, 112.95, 90.88, 115.27, 97.22, 107.28, 98.51, 99.55, 101.09, 95.68, 101.6, 92.84, 99.15, 90.52, 93.1, 87.69, 86.65, 86.01, 82.78, 85.88, 82.01, 86.66, 79.05, 84.59, 77.89, 83.43, 77.76, 82.79, 76.86, 82.79, 75.57, 82.79, 74.02, 83.18, 72.2, 83.69, 69.1, 83.69, 66.78, 83.56, 64.98]], "area": 6970.058550000001, "iscrowd": 0, "image_id": 35945, "bbox": [82.79, 0.0, 97.67, 163.9], "category_id": 1, "id": 434093, "split": "val", "sentences": [{"tokens": ["the", "boy", "wearing", "a", "maroon", "shirt", "and", "blue", "jeans"], "raw": "the boy wearing a maroon shirt and blue jeans", "sent_id": 70993, "sent": "the boy wearing a maroon shirt and blue jeans"}, {"tokens": ["a", "little", "boy", "in", "a", "red", "sweatshirt", "sitting", "at", "a", "table", "with", "two", "other", ",", "older", ",", "people"], "raw": "A little boy in a red sweatshirt sitting at a table with two other, older, people.", "sent_id": 70994, "sent": "a little boy in a red sweatshirt sitting at a table with two other , older , people"}], "file_name": "COCO_train2014_000000035945_434093.jpg", "ann_id": 434093, "sent_ids": [70993, 70994], "ref_id": 32273}, {"segmentation": [[234.58, 247.4, 220.83, 272.14, 216.25, 293.22, 204.34, 310.63, 186.93, 332.62, 173.18, 341.78, 165.85, 355.53, 157.61, 363.77, 156.69, 367.44, 177.76, 370.19, 193.34, 370.19, 197.92, 343.62, 209.83, 321.62, 223.58, 313.38, 219.0, 321.62, 211.67, 333.54, 205.25, 338.12, 202.5, 345.45, 204.34, 356.44, 228.16, 356.44, 233.66, 333.54, 245.57, 317.04, 256.57, 309.71, 265.73, 306.05, 262.98, 314.29, 259.32, 328.04, 259.32, 344.53, 262.98, 350.03, 284.97, 346.36, 282.22, 334.45, 278.56, 313.38, 274.89, 303.3, 296.88, 284.06, 318.88, 265.73, 329.87, 240.99, 337.2, 199.76, 330.79, 163.1, 324.37, 155.77, 311.55, 156.69, 303.3, 165.85, 302.38, 166.77, 299.63, 152.11, 296.88, 142.94, 282.22, 144.78, 271.23, 142.94, 257.48, 140.2, 245.57, 138.36, 251.07, 148.44, 252.9, 155.77, 248.32, 164.94, 243.74, 174.1, 245.57, 181.43, 245.57, 196.09, 240.99, 214.42, 240.99, 225.41, 238.24, 244.65]], "area": 17304.02495, "iscrowd": 0, "image_id": 83005, "bbox": [156.69, 138.36, 180.51, 231.83], "category_id": 19, "id": 58720, "split": "val", "sentences": [{"tokens": ["a", "brown", "horse", "racing", "and", "leaning", "to", "the", "right", "to", "the", "left", "of", "another", "horse"], "raw": "A brown horse racing and leaning to the right to the left of another horse", "sent_id": 71072, "sent": "a brown horse racing and leaning to the right to the left of another horse"}], "file_name": "COCO_train2014_000000083005_58720.jpg", "ann_id": 58720, "sent_ids": [71072], "ref_id": 32304}, {"segmentation": [[217.89, 181.48, 218.97, 166.38, 235.15, 156.67, 272.9, 155.6, 278.29, 158.83, 267.51, 172.85, 267.51, 177.17, 268.58, 181.48, 251.33, 190.11, 224.36, 190.11], [404.49, 177.17, 423.91, 171.78, 449.8, 163.15, 477.84, 175.01, 492.94, 186.88, 441.17, 191.19, 413.12, 185.8], [330.07, 263.46, 321.44, 316.31, 327.91, 346.52, 319.28, 363.78, 316.04, 376.72, 328.99, 390.74, 337.62, 387.51, 338.7, 362.7, 347.33, 327.1, 348.4, 281.8, 357.03, 285.03, 340.85, 268.85], [467.06, 290.43, 477.84, 319.55, 477.84, 357.3, 463.82, 367.01, 483.24, 381.03, 491.87, 369.17, 499.42, 354.07, 492.94, 328.18, 499.42, 299.06, 495.1, 288.27, 471.37, 294.74]], "area": 7354.503550000001, "iscrowd": 0, "image_id": 332385, "bbox": [217.89, 155.6, 281.53, 235.14], "category_id": 24, "id": 593891, "split": "val", "sentences": [{"tokens": ["a", "zebra", "standing", "behind", "two", "other", "zebras", ",", "with", "only", "it", "'", "s", "mane", "and", "rear", "showing"], "raw": "A zebra standing behind two other zebras, with only it's mane and rear showing.", "sent_id": 71130, "sent": "a zebra standing behind two other zebras , with only it ' s mane and rear showing"}, {"tokens": ["a", "line", "horse", "is", "standing", "behind", "the", "two", "horses"], "raw": "A line horse is standing behind the two horses", "sent_id": 71131, "sent": "a line horse is standing behind the two horses"}], "file_name": "COCO_train2014_000000332385_593891.jpg", "ann_id": 593891, "sent_ids": [71130, 71131], "ref_id": 32327}, {"segmentation": [[95.5, 140.38, 92.05, 165.69, 103.56, 166.84, 103.56, 172.6, 90.9, 182.95, 88.6, 211.72, 98.96, 204.82, 96.65, 185.25, 107.77, 168.4, 97.9, 162.32, 102.46, 134.99, 106.25, 122.09, 102.46, 106.15, 105.49, 87.17, 114.6, 84.13, 122.95, 84.13, 132.06, 92.48, 138.89, 106.15, 132.06, 124.37, 126.75, 128.16, 128.27, 134.24, 154.08, 150.18, 167.74, 191.93, 159.39, 198.76, 163.19, 261.01, 158.63, 271.64, 161.67, 305.04, 160.15, 311.12, 143.45, 312.63, 147.25, 342.24, 151.04, 405.25, 133.58, 396.9, 121.43, 311.88, 115.36, 275.44, 97.14, 400.7, 70.57, 402.21, 66.78, 397.66, 81.96, 388.55, 85.0, 310.36, 69.05, 305.04, 78.92, 241.27, 81.2, 219.26, 72.85, 210.91, 65.26, 193.45, 63.74, 183.58, 79.68, 148.66]], "area": 19422.067299999988, "iscrowd": 0, "image_id": 305219, "bbox": [63.74, 84.13, 104.0, 321.12], "category_id": 1, "id": 2155103, "split": "val", "sentences": [{"tokens": ["the", "young", "boy", "spectator", "holds", "a", "blue", "umbrella", "while", "watching", "a", "softball", "game"], "raw": "The young boy spectator holds a blue umbrella while watching a softball game.", "sent_id": 71191, "sent": "the young boy spectator holds a blue umbrella while watching a softball game"}, {"tokens": ["a", "boy", "standing", "under", "an", "umbrella", "at", "a", "baseball", "game"], "raw": "a boy standing under an umbrella at a baseball game", "sent_id": 71192, "sent": "a boy standing under an umbrella at a baseball game"}], "file_name": "COCO_train2014_000000305219_2155103.jpg", "ann_id": 2155103, "sent_ids": [71191, 71192], "ref_id": 32349}, {"segmentation": [[1.08, 61.62, 28.11, 74.59, 14.05, 128.65, 19.46, 155.68, 31.35, 167.57, 35.68, 124.32, 35.68, 88.65, 47.57, 67.03, 73.51, 48.65, 99.46, 21.62, 130.81, 11.89, 148.11, 16.22, 187.03, 56.22, 210.81, 88.65, 232.43, 83.24, 288.65, 88.65, 348.11, 104.86, 402.16, 113.51, 443.24, 132.97, 456.22, 147.03, 444.32, 184.86, 409.73, 228.11, 368.65, 282.16, 322.16, 320.0, 271.35, 350.27, 291.89, 391.35, 304.86, 432.43, 318.92, 431.35, 330.81, 444.32, 329.73, 459.46, 337.3, 472.43, 181.62, 473.51, 138.38, 290.81, 121.08, 263.78, 108.11, 258.38, 4.32, 269.19, 5.41, 65.95]], "area": 112961.65915, "iscrowd": 0, "image_id": 66376, "bbox": [1.08, 11.89, 455.14, 461.62], "category_id": 1, "id": 508671, "split": "val", "sentences": [{"tokens": ["a", "person", "with", "a", "white", "hoodie", "looking", "at", "a", "computer", "screen"], "raw": "A person with a white hoodie looking at a computer screen.", "sent_id": 71197, "sent": "a person with a white hoodie looking at a computer screen"}, {"tokens": ["a", "man", "leaning", "back", "with", "hoodie", "on"], "raw": "A man leaning back with hoodie on.", "sent_id": 71198, "sent": "a man leaning back with hoodie on"}], "file_name": "COCO_train2014_000000066376_508671.jpg", "ann_id": 508671, "sent_ids": [71197, 71198], "ref_id": 32352}, {"segmentation": [[638.04, 234.11, 635.16, 242.74, 626.53, 267.69, 621.73, 277.28, 614.05, 292.64, 608.3, 302.23, 601.58, 309.91, 600.62, 310.86, 590.07, 297.43, 586.23, 290.72, 578.55, 284.0, 572.8, 278.24, 568.0, 289.76, 568.0, 294.55, 568.96, 294.55, 566.08, 300.31, 561.28, 306.07, 561.28, 311.82, 567.04, 319.5, 571.84, 326.22, 572.8, 337.73, 572.8, 343.49, 575.68, 349.24, 577.59, 357.88, 583.35, 373.23, 588.15, 385.7, 600.62, 407.77, 611.18, 415.45, 626.53, 410.65, 636.12, 408.73, 639.96, 409.69, 639.0, 239.86]], "area": 7877.407200000005, "iscrowd": 0, "image_id": 444033, "bbox": [561.28, 234.11, 78.68, 181.34], "category_id": 1, "id": 519723, "split": "val", "sentences": [{"tokens": ["man", "in", "silver", "holding", "plate", "of", "veggies"], "raw": "man in silver holding plate of veggies.", "sent_id": 71237, "sent": "man in silver holding plate of veggies"}, {"tokens": ["the", "gray", "and", "blue", "shirt"], "raw": "the gray and blue shirt", "sent_id": 71238, "sent": "the gray and blue shirt"}], "file_name": "COCO_train2014_000000444033_519723.jpg", "ann_id": 519723, "sent_ids": [71237, 71238], "ref_id": 32368}, {"segmentation": [[385.31, 70.96, 403.96, 67.98, 414.41, 67.23, 425.6, 62.01, 436.79, 62.01, 451.7, 62.01, 465.13, 62.01, 480.8, 62.75, 506.91, 70.96, 521.08, 82.9, 529.29, 91.85, 530.78, 104.53, 531.52, 117.96, 531.52, 127.65, 533.02, 146.3, 527.05, 162.71, 527.05, 175.4, 524.81, 187.33, 521.83, 202.25, 517.35, 211.2, 511.38, 219.41, 506.16, 217.17, 503.92, 204.49, 502.43, 197.03, 497.96, 188.08, 494.23, 179.87, 489.0, 164.21, 474.83, 157.49, 464.39, 151.52, 451.7, 145.56, 441.26, 144.06, 431.56, 144.06, 418.88, 145.56, 401.72, 148.54, 389.04, 151.52, 377.11, 158.98, 364.43, 162.71, 354.73, 166.44, 347.27, 172.41, 340.56, 178.38, 334.59, 182.86, 329.37, 185.09, 321.16, 181.36, 317.43, 174.65, 316.68, 158.24, 311.46, 139.59, 309.97, 120.94, 311.46, 109.75, 320.41, 97.81, 327.87, 91.85, 335.33, 88.12, 351.0, 82.15, 365.92, 74.69, 374.12, 72.45, 376.36, 72.45]], "area": 20126.710049999998, "iscrowd": 0, "image_id": 128475, "bbox": [309.97, 62.01, 223.05, 157.4], "category_id": 51, "id": 718010, "split": "val", "sentences": [{"tokens": ["an", "ice", "cream", "cup"], "raw": "an ice cream cup", "sent_id": 71261, "sent": "an ice cream cup"}, {"tokens": ["a", "container", "full", "of", "yellow", "dipping", "sauce", "directly", "next", "to", "a", "donut"], "raw": "A container full of yellow dipping sauce directly next to a donut.", "sent_id": 71262, "sent": "a container full of yellow dipping sauce directly next to a donut"}], "file_name": "COCO_train2014_000000128475_718010.jpg", "ann_id": 718010, "sent_ids": [71261, 71262], "ref_id": 32377}, {"segmentation": [[235.19, 143.38, 211.09, 145.31, 208.2, 126.99, 219.77, 121.21, 240.01, 108.68, 256.39, 100.0, 277.6, 97.11, 285.31, 119.28, 282.42, 145.31, 274.71, 151.09, 280.49, 170.37, 280.49, 194.46, 292.06, 214.7, 313.26, 233.98, 322.9, 254.22, 303.62, 262.9, 282.42, 233.98, 284.35, 263.86, 287.24, 300.49, 284.35, 321.7, 284.35, 333.26, 261.21, 326.52, 259.28, 289.89, 259.28, 257.12, 258.32, 287.96, 244.83, 304.35, 237.12, 319.77, 250.61, 335.19, 237.12, 348.68, 214.95, 348.68, 214.95, 336.15, 205.31, 328.44, 203.38, 310.13, 225.55, 287.96, 239.04, 276.39, 225.55, 257.12, 224.58, 239.77, 219.77, 214.7, 219.77, 186.75, 229.4, 155.91, 220.73, 145.31]], "area": 15152.0008, "iscrowd": 0, "image_id": 413391, "bbox": [203.38, 97.11, 119.52, 251.57], "category_id": 1, "id": 439050, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "a", "purple", "shirt"], "raw": "a girl in a purple shirt", "sent_id": 71263, "sent": "a girl in a purple shirt"}, {"tokens": ["the", "girl", "in", "the", "purple", "shirt"], "raw": "The girl in the purple shirt", "sent_id": 71264, "sent": "the girl in the purple shirt"}], "file_name": "COCO_train2014_000000413391_439050.jpg", "ann_id": 439050, "sent_ids": [71263, 71264], "ref_id": 32378}, {"segmentation": [[385.21, 49.32, 385.21, 50.25, 381.95, 65.62, 379.16, 74.46, 378.23, 77.72, 377.29, 83.31, 374.5, 91.69, 374.03, 94.95, 382.42, 104.26, 382.42, 105.66, 382.42, 117.76, 382.42, 117.76, 399.18, 124.75, 409.88, 130.8, 404.76, 141.51, 402.9, 145.23, 406.63, 171.77, 406.63, 175.5, 404.76, 195.52, 392.19, 221.59, 372.17, 233.23, 371.71, 245.33, 372.17, 273.27, 370.31, 283.51, 364.72, 293.76, 351.22, 303.53, 338.18, 316.57, 334.46, 326.81, 329.8, 344.04, 368.91, 426.5, 378.23, 437.21, 430.37, 437.21, 430.37, 437.21, 421.52, 421.85, 413.14, 413.47, 403.37, 389.26, 394.06, 362.25, 398.71, 349.68, 442.94, 331.99, 480.19, 322.68, 494.62, 306.46, 497.42, 278.52, 503.0, 264.09, 498.35, 197.66, 482.98, 164.13, 481.12, 158.55, 478.33, 148.77, 476.46, 145.98, 467.15, 140.39, 457.84, 128.49, 441.08, 117.31, 440.15, 107.07, 447.13, 92.64, 456.91, 59.92, 448.53, 51.54, 441.08, 39.9, 435.03, 38.5, 421.52, 36.17, 411.75, 37.57, 392.19, 40.83, 392.19, 40.83]], "area": 34374.79424999999, "iscrowd": 0, "image_id": 226176, "bbox": [329.8, 36.17, 173.2, 401.04], "category_id": 1, "id": 221528, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "blue", "shirt", "sitting", "in", "the", "back", "in", "the", "two", "weeler"], "raw": "A man wearing blue shirt sitting in the back in the two weeler.", "sent_id": 71383, "sent": "a man wearing blue shirt sitting in the back in the two weeler"}, {"tokens": ["a", "man", "in", "a", "blue", "shirt", "rides", "passenger", "on", "a", "motor", "bike"], "raw": "A man in a blue shirt rides passenger on a motor bike.", "sent_id": 71384, "sent": "a man in a blue shirt rides passenger on a motor bike"}], "file_name": "COCO_train2014_000000226176_221528.jpg", "ann_id": 221528, "sent_ids": [71383, 71384], "ref_id": 32422}, {"segmentation": [[638.56, 5.39, 639.64, 259.96, 638.56, 474.61, 476.76, 472.45, 291.24, 473.53, 285.84, 470.29, 319.28, 378.61, 331.15, 366.74, 430.38, 328.99, 455.19, 322.52, 501.57, 270.74, 487.55, 253.48, 502.65, 245.93, 506.97, 270.74, 509.12, 284.76, 500.49, 324.67, 492.94, 350.56, 497.26, 365.66, 517.75, 367.82, 535.01, 353.8, 546.88, 344.09, 567.37, 313.89, 578.16, 282.61, 569.53, 223.28, 536.09, 189.84, 546.88, 180.13, 574.92, 129.44, 569.53, 117.57, 542.56, 99.24, 533.93, 99.24, 515.6, 119.73, 504.81, 135.91, 484.31, 146.7, 474.61, 147.78, 449.8, 127.28, 449.8, 105.71, 444.4, 60.4, 445.48, 46.38, 450.88, 25.89, 457.35, 18.34, 455.19, 5.39, 581.39, 2.16, 638.56, 1.08]], "area": 84004.20559999999, "iscrowd": 0, "image_id": 100667, "bbox": [285.84, 1.08, 353.8, 473.53], "category_id": 1, "id": 1265445, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "green", "shirt", "eating", "a", "banana"], "raw": "a man in a green shirt eating a banana", "sent_id": 71455, "sent": "a man in a green shirt eating a banana"}, {"tokens": ["man", "eating", "banana", "in", "green", "shirt"], "raw": "man eating banana in green shirt", "sent_id": 71456, "sent": "man eating banana in green shirt"}], "file_name": "COCO_train2014_000000100667_1265445.jpg", "ann_id": 1265445, "sent_ids": [71455, 71456], "ref_id": 32446}, {"segmentation": [[212.61, 353.55, 211.45, 287.14, 217.27, 277.24, 230.09, 305.79, 237.66, 349.48, 239.41, 361.13, 242.9, 362.88, 251.06, 364.04, 259.21, 353.55, 253.39, 322.68, 248.73, 292.97, 244.65, 277.82, 248.73, 260.35, 246.4, 232.97, 246.4, 221.9, 259.21, 220.74, 249.89, 184.04, 239.41, 174.13, 236.49, 161.32, 235.33, 149.08, 222.51, 137.43, 198.63, 153.16, 209.12, 166.56, 209.12, 172.97, 190.47, 173.55, 181.15, 198.02, 178.24, 212.58, 184.65, 221.9, 199.79, 221.9, 198.05, 223.07, 189.31, 246.37, 191.06, 267.92, 194.55, 308.12, 191.64, 336.66, 194.55, 352.97, 193.97, 365.79, 197.46, 378.02, 213.19, 352.97]], "area": 10900.3582, "iscrowd": 0, "image_id": 152922, "bbox": [178.24, 137.43, 80.97, 240.59], "category_id": 1, "id": 549538, "split": "val", "sentences": [{"tokens": ["tallest", "man", "in", "the", "image"], "raw": "tallest man in the image", "sent_id": 71490, "sent": "tallest man in the image"}, {"tokens": ["a", "woman", "in", "a", "white", "hat", "and", "red", "jacket", "cross", "country", "skiing"], "raw": "A woman in a white hat and red jacket cross country skiing.", "sent_id": 71491, "sent": "a woman in a white hat and red jacket cross country skiing"}], "file_name": "COCO_train2014_000000152922_549538.jpg", "ann_id": 549538, "sent_ids": [71490, 71491], "ref_id": 32460}, {"segmentation": [[124.35, 303.11, 116.58, 256.48, 133.42, 246.11, 143.78, 242.23, 160.62, 240.93, 191.71, 246.11, 204.66, 266.84, 212.44, 277.2, 209.84, 297.93, 183.94, 313.47, 183.94, 332.9, 222.8, 344.56, 222.8, 374.35, 226.68, 401.55, 213.73, 468.91, 217.62, 489.64, 186.53, 483.16, 124.35, 487.05, 47.93, 492.23, 63.47, 428.76, 71.24, 395.08, 72.54, 370.47, 88.08, 338.08, 88.08, 329.02, 97.15, 318.65, 104.92, 313.47, 119.17, 313.47, 130.83, 309.59, 129.53, 301.81]], "area": 30920.87910000001, "iscrowd": 0, "image_id": 323664, "bbox": [47.93, 240.93, 178.75, 251.3], "category_id": 1, "id": 2159644, "split": "val", "sentences": [{"tokens": ["the", "woman", "in", "the", "tank", "top", "playing", "wii"], "raw": "The woman in the tank top playing Wii.", "sent_id": 71538, "sent": "the woman in the tank top playing wii"}, {"tokens": ["woman", "holding", "controllers", "playing", "a", "game", "enthusiastically", "with", "another", "person"], "raw": "Woman holding controllers playing a game enthusiastically with another person.", "sent_id": 71539, "sent": "woman holding controllers playing a game enthusiastically with another person"}], "file_name": "COCO_train2014_000000323664_2159644.jpg", "ann_id": 2159644, "sent_ids": [71538, 71539], "ref_id": 32478}, {"segmentation": [[138.07, 260.31, 149.57, 345.17, 148.13, 405.57, 136.63, 455.91, 103.55, 455.91, 94.92, 455.91, 93.48, 500.49, 74.79, 555.15, 40.27, 553.71, 10.07, 527.82, 2.88, 126.56, 2.88, 4.31, 37.39, 2.88, 48.9, 2.88, 46.02, 109.3, 50.34, 135.19, 86.29, 139.51, 115.06, 185.53, 142.38, 251.69]], "area": 54398.355850000014, "iscrowd": 0, "image_id": 301218, "bbox": [2.88, 2.88, 146.69, 552.27], "category_id": 8, "id": 400022, "split": "val", "sentences": [{"tokens": ["a", "front", "of", "a", "white", "delivery", "truck", "on", "the", "road"], "raw": "A front of a white delivery truck on the road.", "sent_id": 71583, "sent": "a front of a white delivery truck on the road"}, {"tokens": ["a", "sideview", "of", "a", "large", "truck"], "raw": "A sideview of a large truck.", "sent_id": 71584, "sent": "a sideview of a large truck"}], "file_name": "COCO_train2014_000000301218_400022.jpg", "ann_id": 400022, "sent_ids": [71583, 71584], "ref_id": 32495}, {"segmentation": [[285.39, 88.84, 344.94, 100.07, 382.02, 161.87, 395.51, 186.59, 404.49, 201.2, 414.61, 227.04, 416.85, 303.45, 401.12, 337.15, 362.92, 338.28, 360.67, 306.82, 322.47, 305.69, 334.83, 210.19, 329.21, 140.52, 308.99, 155.13]], "area": 16695.18885, "iscrowd": 0, "image_id": 244875, "bbox": [285.39, 88.84, 131.46, 249.44], "category_id": 3, "id": 144231, "split": "val", "sentences": [{"tokens": ["the", "car", "that", "is", "in", "the", "front"], "raw": "The car that is in the front.", "sent_id": 71663, "sent": "the car that is in the front"}, {"tokens": ["white", "car", "in", "the", "background"], "raw": "white car in the background", "sent_id": 71664, "sent": "white car in the background"}], "file_name": "COCO_train2014_000000244875_144231.jpg", "ann_id": 144231, "sent_ids": [71663, 71664], "ref_id": 32526}, {"segmentation": [[243.69, 99.86, 261.1, 89.78, 271.17, 86.12, 280.34, 86.12, 305.07, 117.26, 306.9, 140.17, 304.15, 163.99, 307.82, 169.48, 327.97, 174.98, 337.14, 189.64, 338.05, 201.55, 335.3, 235.45, 340.8, 260.18, 346.3, 274.84, 348.13, 287.66, 350.88, 294.99, 333.47, 327.06, 289.5, 339.88, 261.1, 343.55, 229.95, 342.63, 213.46, 338.05, 207.96, 326.14, 208.88, 296.83, 197.88, 294.08, 188.72, 285.83, 186.89, 273.92, 190.55, 260.18, 196.05, 250.1, 202.46, 237.28, 209.79, 222.62, 213.46, 210.71, 219.87, 198.8, 227.2, 187.81, 239.11, 177.73, 244.61, 171.32, 250.1, 168.57, 251.02, 167.65, 251.94, 163.07, 249.19, 158.49, 243.69, 152.99, 242.77, 142.92, 240.94, 131.92, 239.11, 120.01, 243.69, 101.69]], "area": 26780.063850000002, "iscrowd": 0, "image_id": 361939, "bbox": [186.89, 86.12, 163.99, 257.43], "category_id": 1, "id": 189375, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "green", "jacket"], "raw": "A man wearing a green jacket.", "sent_id": 71680, "sent": "a man wearing a green jacket"}, {"tokens": ["the", "passenger", "holding", "a", "bicycle", "with", "the", "'", "wrangler", "'", "jacket", "on"], "raw": "The passenger holding a bicycle with the 'Wrangler' jacket on.", "sent_id": 71681, "sent": "the passenger holding a bicycle with the ' wrangler ' jacket on"}], "file_name": "COCO_train2014_000000361939_189375.jpg", "ann_id": 189375, "sent_ids": [71680, 71681], "ref_id": 32532}, {"segmentation": [[61.41, 3.84, 95.0, 59.49, 119.94, 98.83, 141.05, 116.11, 166.0, 88.28, 189.99, 59.49, 209.18, 71.01, 229.33, 60.45, 237.01, 65.25, 243.73, 52.78, 259.08, 39.34, 269.63, 45.1, 281.15, 28.79, 273.47, 1.92], [29.75, 294.58, 35.5, 380.94, 46.06, 427.0, 104.59, 427.0, 112.27, 390.54, 175.6, 384.78, 189.03, 374.22, 181.36, 364.63, 147.77, 372.31, 131.46, 334.88, 126.66, 329.13, 128.58, 252.36]], "area": 28881.03525, "iscrowd": 0, "image_id": 345882, "bbox": [29.75, 1.92, 251.4, 425.08], "category_id": 1, "id": 496977, "split": "val", "sentences": [{"tokens": ["a", "man", "leaning", "down"], "raw": "a man leaning down", "sent_id": 71685, "sent": "a man leaning down"}, {"tokens": ["a", "man", "wearing", "a", "button", "down", "shirt", "and", "jeans"], "raw": "a man wearing a button down shirt and jeans", "sent_id": 71686, "sent": "a man wearing a button down shirt and jeans"}], "file_name": "COCO_train2014_000000345882_496977.jpg", "ann_id": 496977, "sent_ids": [71685, 71686], "ref_id": 32534}, {"segmentation": [[607.4, 135.3, 577.65, 166.96, 566.13, 206.3, 563.26, 237.97, 548.86, 271.55, 554.62, 279.23, 573.81, 243.73, 575.73, 225.49, 600.68, 297.46, 616.03, 349.28, 618.91, 380.94, 618.91, 390.54, 640.0, 382.86, 640.0, 286.91, 637.14, 188.07, 636.18, 118.02]], "area": 12325.4634, "iscrowd": 0, "image_id": 70745, "bbox": [548.86, 118.02, 91.14, 272.52], "category_id": 22, "id": 584967, "split": "val", "sentences": [{"tokens": ["the", "butt", "and", "tail", "of", "an", "elephant", "to", "the", "right", "of", "a", "front", "facing", "elephant"], "raw": "The butt and tail of an elephant to the right of a front facing elephant.", "sent_id": 71689, "sent": "the butt and tail of an elephant to the right of a front facing elephant"}, {"tokens": ["back", "end", "of", "a", "brown", "elephant"], "raw": "Back end of a brown elephant.", "sent_id": 71690, "sent": "back end of a brown elephant"}], "file_name": "COCO_train2014_000000070745_584967.jpg", "ann_id": 584967, "sent_ids": [71689, 71690], "ref_id": 32536}, {"segmentation": [[0.0, 289.08, 25.89, 271.82, 25.89, 259.96, 34.52, 236.22, 60.4, 217.89, 86.29, 163.96, 119.73, 146.7, 153.17, 153.17, 165.03, 162.88, 168.27, 170.43, 169.35, 198.47, 177.98, 240.54, 174.74, 265.35, 195.24, 295.55, 214.65, 325.75, 217.89, 349.48, 181.21, 371.06, 155.33, 389.39, 142.38, 474.61, 2.16, 468.13]], "area": 48572.50919999999, "iscrowd": 0, "image_id": 209537, "bbox": [0.0, 146.7, 217.89, 327.91], "category_id": 1, "id": 489342, "split": "val", "sentences": [{"tokens": ["a", "man", "weraing", "glasses", ",", "a", "gray", "sweatshort", "with", "writing", "on", "it", ",", "sitting", "at", "a", "table"], "raw": "A man weraing glasses, a gray sweatshort with writing on it, sitting at a table.", "sent_id": 71730, "sent": "a man weraing glasses , a gray sweatshort with writing on it , sitting at a table"}, {"tokens": ["a", "man", "in", "a", "wisconsin", "university", "hoodie", "is", "sitting", "at", "a", "blue", "table", "with", "a", "nearly", "empty", "bowl", "in", "front", "of", "him"], "raw": "A man in a Wisconsin University hoodie is sitting at a blue table with a nearly empty bowl in front of him.", "sent_id": 71731, "sent": "a man in a wisconsin university hoodie is sitting at a blue table with a nearly empty bowl in front of him"}], "file_name": "COCO_train2014_000000209537_489342.jpg", "ann_id": 489342, "sent_ids": [71730, 71731], "ref_id": 32557}, {"segmentation": [[2.21, 0.0, 137.04, 0.0, 194.21, 2.82, 207.16, 0.66, 186.66, 27.63, 181.27, 77.25, 167.25, 133.34, 149.99, 230.42, 147.83, 325.34, 180.19, 385.74, 193.13, 421.34, 228.73, 435.36, 225.49, 440.75, 247.07, 451.54, 260.01, 462.33, 255.7, 480.0, 0.0, 476.35, 0.06, 370.64, 0.0, 281.11, 2.21, 200.21, 2.21, 186.19], [337.67, 463.41, 371.11, 442.91, 399.16, 412.71, 418.57, 400.84, 436.91, 415.95, 445.54, 439.68, 456.33, 442.91, 446.62, 468.8, 441.22, 477.43, 431.52, 480.0, 394.84, 480.0, 377.58, 462.33, 371.11, 453.7, 356.01, 472.04, 343.07, 474.19]], "area": 88326.8621, "iscrowd": 0, "image_id": 1994, "bbox": [0.0, 0.0, 456.33, 480.0], "category_id": 1, "id": 448354, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "checked", "shirt", "bearing", "goblet"], "raw": "a man wearing checked shirt bearing goblet", "sent_id": 71876, "sent": "a man wearing checked shirt bearing goblet"}, {"tokens": ["man", "'", "s", "plaid", "shirt", "and", "hand", ",", "the", "parts", "not", "shown", "behind", "the", "wine", "glass"], "raw": "man's plaid shirt and hand, the parts not shown behind the wine glass", "sent_id": 71877, "sent": "man ' s plaid shirt and hand , the parts not shown behind the wine glass"}], "file_name": "COCO_train2014_000000001994_448354.jpg", "ann_id": 448354, "sent_ids": [71876, 71877], "ref_id": 32611}, {"segmentation": [[475.94, 381.61, 464.42, 309.64, 464.42, 271.26, 461.54, 224.24, 435.64, 216.57, 419.32, 193.54, 412.61, 158.99, 418.36, 145.56, 420.28, 117.73, 434.68, 101.42, 467.3, 109.1, 481.69, 148.44, 483.61, 194.5, 476.9, 212.73, 491.29, 318.28, 498.97, 372.97]], "area": 10191.0501, "iscrowd": 0, "image_id": 560750, "bbox": [412.61, 101.42, 86.36, 280.19], "category_id": 90, "id": 343699, "split": "val", "sentences": [{"tokens": ["the", "reflection", "of", "the", "toothbrush", "in", "the", "mirror"], "raw": "The reflection of the toothbrush in the mirror.", "sent_id": 71958, "sent": "the reflection of the toothbrush in the mirror"}, {"tokens": ["toothbrush", "to", "the", "right"], "raw": "toothbrush to the right", "sent_id": 71959, "sent": "toothbrush to the right"}], "file_name": "COCO_train2014_000000560750_343699.jpg", "ann_id": 343699, "sent_ids": [71958, 71959], "ref_id": 32636}, {"segmentation": [[175.43, 2.15, 192.65, 0.0, 217.4, 87.17, 220.63, 116.23, 198.03, 139.91, 8.61, 145.29, 8.61, 90.4, 8.61, 32.29, 10.76, 0.0]], "area": 28268.210749999995, "iscrowd": 0, "image_id": 421086, "bbox": [8.61, 0.0, 212.02, 145.29], "category_id": 1, "id": 1706357, "split": "val", "sentences": [{"tokens": ["white", "apron"], "raw": "white apron", "sent_id": 71962, "sent": "white apron"}, {"tokens": ["a", "white", "dressed", "chef", "standing", "other", "side", "of", "a", "table"], "raw": "a white dressed chef standing other side of a table", "sent_id": 71963, "sent": "a white dressed chef standing other side of a table"}], "file_name": "COCO_train2014_000000421086_1706357.jpg", "ann_id": 1706357, "sent_ids": [71962, 71963], "ref_id": 32638}, {"segmentation": [[319.39, 312.68, 319.39, 344.33, 352.0, 337.62, 370.23, 353.92, 369.27, 359.68, 352.96, 367.35, 314.6, 386.53, 299.25, 393.25, 284.86, 390.37, 267.6, 376.94, 266.64, 362.55, 264.72, 330.9, 255.13, 304.05, 243.62, 284.86, 231.15, 263.76, 216.77, 242.66, 207.17, 231.15, 205.26, 218.68, 206.22, 201.42, 212.93, 181.28, 214.85, 165.93, 204.3, 134.28, 204.3, 123.73, 240.74, 99.75, 259.93, 99.75, 278.15, 131.4, 278.15, 133.32, 297.33, 135.24, 317.48, 140.03, 347.21, 147.71, 356.8, 149.63, 403.8, 148.67, 431.61, 142.91, 425.86, 163.05, 396.12, 168.81, 374.06, 176.48, 370.23, 181.28, 375.98, 185.11, 378.86, 191.83, 408.59, 183.2, 435.45, 176.48, 458.47, 214.85, 464.22, 241.7, 502.59, 261.85, 511.22, 273.35, 500.67, 281.99, 478.61, 274.31, 458.47, 261.85, 429.69, 245.54, 415.31, 222.52, 406.68, 211.97, 370.23, 199.5, 352.96, 192.79, 319.39, 182.24, 278.15, 192.79, 256.09, 217.72, 253.21, 246.5, 256.09, 259.93, 272.4, 268.56, 297.33, 295.42, 316.52, 308.84, 318.43, 309.8]], "area": 27209.964999999993, "iscrowd": 0, "image_id": 515309, "bbox": [204.3, 99.75, 306.92, 293.5], "category_id": 1, "id": 188879, "split": "val", "sentences": [{"tokens": ["the", "motorcycle", "rider", "in", "red"], "raw": "The motorcycle rider in red.", "sent_id": 71982, "sent": "the motorcycle rider in red"}, {"tokens": ["a", "motorcyle", "rider", "on", "a", "red", "and", "white", "bike"], "raw": "A motorcyle rider on a red and white bike.", "sent_id": 71983, "sent": "a motorcyle rider on a red and white bike"}], "file_name": "COCO_train2014_000000515309_188879.jpg", "ann_id": 188879, "sent_ids": [71982, 71983], "ref_id": 32643}, {"segmentation": [[333.07, 168.21, 338.82, 164.38, 340.73, 162.47, 344.56, 158.64, 344.56, 155.77, 340.73, 150.98, 338.82, 144.28, 338.82, 135.67, 339.77, 131.84, 345.52, 130.88, 352.22, 130.88, 358.92, 133.76, 361.79, 134.71, 361.79, 148.11, 364.66, 157.68, 376.14, 163.43, 379.02, 172.04, 381.89, 184.48, 385.72, 212.24, 385.72, 227.55, 371.36, 249.57, 364.66, 260.09, 367.53, 267.75, 374.23, 278.28, 387.63, 293.59, 401.03, 301.25, 405.81, 302.21, 410.6, 303.16, 414.43, 313.69, 412.51, 321.35, 407.73, 327.09, 401.03, 335.71, 400.07, 335.71, 396.24, 331.88, 396.24, 323.26, 391.46, 316.56, 378.06, 304.12, 366.57, 293.59, 361.79, 287.85, 359.87, 294.55, 357.0, 303.16, 355.09, 315.61, 357.0, 328.05, 357.0, 335.71, 339.77, 350.06, 328.29, 350.06, 321.59, 346.23, 318.72, 342.41, 326.37, 337.62, 334.03, 318.48, 335.95, 296.47, 342.65, 262.97, 342.65, 234.25, 342.65, 230.42, 339.77, 216.07, 333.07, 194.05, 333.07, 182.57, 333.07, 176.83]], "area": 8145.275550000002, "iscrowd": 0, "image_id": 16069, "bbox": [318.72, 130.88, 95.71, 219.18], "category_id": 1, "id": 207888, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "the", "rain", "slicker", "crossing", "the", "bridge"], "raw": "The person in the rain slicker crossing the bridge.", "sent_id": 72000, "sent": "the person in the rain slicker crossing the bridge"}, {"tokens": ["a", "woman", "in", "a", "raincoat", "walking", "by", "the", "water"], "raw": "A woman in a raincoat walking by the water.", "sent_id": 72001, "sent": "a woman in a raincoat walking by the water"}], "file_name": "COCO_train2014_000000016069_207888.jpg", "ann_id": 207888, "sent_ids": [72000, 72001], "ref_id": 32649}, {"segmentation": [[249.4, 175.08, 253.64, 167.13, 262.12, 157.06, 266.89, 149.11, 274.31, 135.86, 276.97, 126.85, 280.68, 120.49, 288.63, 106.18, 291.28, 101.4, 294.46, 91.86, 300.82, 88.15, 313.54, 77.55, 313.54, 72.78, 313.54, 65.89, 311.42, 64.83, 302.41, 63.77, 302.41, 58.47, 301.35, 54.23, 303.47, 46.81, 304.53, 46.81, 313.54, 45.22, 316.19, 39.92, 316.72, 35.68, 317.78, 33.55, 323.61, 32.49, 326.26, 32.49, 326.79, 33.02, 336.33, 33.02, 342.16, 33.55, 345.34, 37.27, 346.94, 48.93, 353.83, 52.11, 357.54, 59.0, 358.6, 60.59, 348.0, 66.42, 353.3, 74.37, 363.37, 76.49, 370.26, 93.98, 373.97, 107.24, 375.56, 113.6, 375.56, 115.19, 376.62, 119.43, 375.03, 135.33, 371.85, 148.58, 372.38, 159.18, 373.44, 166.07, 375.03, 180.92, 375.03, 189.4, 375.03, 194.17, 371.85, 200.53, 367.08, 225.97, 362.31, 235.51, 359.66, 228.09, 355.42, 216.43, 343.22, 195.23, 340.04, 186.75, 332.09, 185.69, 325.73, 208.48, 324.14, 223.85, 321.49, 242.4, 319.9, 253.01, 310.89, 267.85, 306.12, 267.85, 296.05, 268.38, 296.05, 265.73, 300.29, 255.13, 302.94, 249.3, 302.94, 234.45, 299.76, 211.66, 299.76, 196.82, 301.35, 182.51, 301.35, 174.55, 302.94, 161.83, 302.94, 154.94, 305.59, 143.28, 305.59, 131.09, 305.59, 125.79, 297.11, 139.57, 290.75, 147.52, 267.95, 176.67, 261.06, 179.86]], "area": 13869.24425, "iscrowd": 0, "image_id": 269532, "bbox": [249.4, 32.49, 127.22, 235.89], "category_id": 1, "id": 220772, "split": "val", "sentences": [{"tokens": ["man", "wearing", "a", "brown", "cowboy", "hat"], "raw": "man wearing a brown cowboy hat", "sent_id": 72030, "sent": "man wearing a brown cowboy hat"}, {"tokens": ["a", "man", "in", "a", "cowboy", "hat"], "raw": "a man in a cowboy hat", "sent_id": 72031, "sent": "a man in a cowboy hat"}], "file_name": "COCO_train2014_000000269532_220772.jpg", "ann_id": 220772, "sent_ids": [72030, 72031], "ref_id": 32657}, {"segmentation": [[33.08, 348.73, 33.08, 348.73, 8.27, 527.92, 42.73, 561.0, 42.73, 561.0, 89.59, 592.7, 117.16, 587.19, 119.92, 585.81, 143.35, 581.68, 146.11, 581.68, 176.43, 573.41, 176.43, 573.41, 183.32, 551.35, 192.97, 530.68, 198.49, 483.81, 198.49, 474.16, 191.59, 436.95, 191.59, 436.95, 183.32, 412.14, 183.32, 410.76, 164.03, 365.27, 164.03, 365.27, 136.46, 341.84, 136.46, 341.84]], "area": 37909.09425, "iscrowd": 0, "image_id": 427805, "bbox": [8.27, 341.84, 190.22, 250.86], "category_id": 86, "id": 1157148, "split": "val", "sentences": [{"tokens": ["a", "glass", "vase", "with", "some", "white", "flowers", "in", "it"], "raw": "A glass vase with some white flowers in it.", "sent_id": 72132, "sent": "a glass vase with some white flowers in it"}, {"tokens": ["the", "glass", "vase", "with", "a", "lot", "purple", "flowers"], "raw": "The glass vase with a lot purple flowers.", "sent_id": 72133, "sent": "the glass vase with a lot purple flowers"}], "file_name": "COCO_train2014_000000427805_1157148.jpg", "ann_id": 1157148, "sent_ids": [72132, 72133], "ref_id": 32699}, {"segmentation": [[266.97, 92.21, 287.28, 101.15, 283.22, 129.58, 346.6, 176.71, 344.97, 188.08, 298.66, 217.33, 304.35, 263.64, 298.66, 314.83, 297.85, 369.27, 299.47, 378.21, 304.35, 380.64, 301.91, 389.58, 285.66, 405.83, 269.41, 403.39, 262.1, 275.02, 236.91, 405.83, 223.91, 409.08, 203.6, 397.71, 206.76, 382.53, 215.01, 383.91, 219.83, 324.06, 226.71, 313.74, 219.83, 288.28, 228.77, 231.87, 207.44, 216.73, 208.82, 185.09, 227.4, 136.93, 246.66, 128.67, 247.74, 102.67, 266.1, 92.54]], "area": 23514.243650000004, "iscrowd": 0, "image_id": 166975, "bbox": [203.6, 92.21, 143.0, 316.87], "category_id": 1, "id": 230146, "split": "val", "sentences": [{"tokens": ["man", "standing", "in", "front", "of", "bus"], "raw": "man standing in front of  bus", "sent_id": 72157, "sent": "man standing in front of bus"}, {"tokens": ["man", "with", "black", "shirt", "standing", "in", "front", "of", "bus"], "raw": "man with black shirt standing in front of bus", "sent_id": 72158, "sent": "man with black shirt standing in front of bus"}], "file_name": "COCO_train2014_000000166975_230146.jpg", "ann_id": 230146, "sent_ids": [72157, 72158], "ref_id": 32710}, {"segmentation": [[4.81, 347.66, 7.69, 327.46, 22.12, 309.19, 32.7, 300.53, 53.86, 241.87, 56.74, 226.48, 71.17, 206.29, 79.82, 192.82, 82.71, 153.39, 115.41, 136.08, 135.6, 130.31, 125.98, 102.42, 127.91, 71.65, 147.14, 56.26, 190.42, 74.53, 196.19, 89.92, 191.38, 110.12, 179.84, 128.39, 206.77, 145.7, 234.66, 163.97, 227.93, 191.86, 219.27, 226.48, 214.46, 232.25, 211.58, 249.56, 197.15, 250.53, 169.26, 248.6, 133.68, 241.87, 118.29, 238.99, 107.71, 193.78, 104.83, 213.98, 86.55, 256.3, 62.51, 266.88, 73.09, 274.57, 61.55, 287.07, 55.78, 304.38, 38.47, 329.39, 29.81, 345.74, 13.46, 347.66, 1.92, 348.62]], "area": 22725.068199999998, "iscrowd": 0, "image_id": 545145, "bbox": [1.92, 56.26, 232.74, 292.36], "category_id": 1, "id": 516354, "split": "val", "sentences": [{"tokens": ["the", "teen", "reaching", "for", "something", "on", "the", "table", "who", "is", "not", "wearing", "a", "hat"], "raw": "The teen reaching for something on the table who is not wearing a hat.", "sent_id": 72199, "sent": "the teen reaching for something on the table who is not wearing a hat"}, {"tokens": ["the", "man", "with", "blonde", "hair", "and", "a", "black", "shirt"], "raw": "The man with blonde hair and a black shirt", "sent_id": 72200, "sent": "the man with blonde hair and a black shirt"}], "file_name": "COCO_train2014_000000545145_516354.jpg", "ann_id": 516354, "sent_ids": [72199, 72200], "ref_id": 32726}, {"segmentation": [[553.32, 414.51, 558.11, 371.43, 554.28, 374.31, 544.71, 353.24, 573.42, 209.65, 573.42, 199.12, 591.61, 141.68, 542.79, 149.34, 506.41, 153.17, 467.16, 157.0, 446.1, 164.66, 416.43, 157.96, 446.1, 145.51, 464.29, 142.64, 470.99, 105.3, 414.51, 100.52, 415.47, 91.9, 451.85, 81.37, 478.65, 80.41, 512.16, 81.37, 575.34, 62.22, 588.74, 33.51, 598.31, 16.27, 598.31, 3.83, 640.0, 0.96, 640.0, 417.38]], "area": 38989.0254, "iscrowd": 0, "image_id": 563525, "bbox": [414.51, 0.96, 225.49, 416.42], "category_id": 1, "id": 468222, "split": "val", "sentences": [{"tokens": ["a", "waiter", "serving", "wine"], "raw": "A waiter serving wine.", "sent_id": 72262, "sent": "a waiter serving wine"}, {"tokens": ["man", "in", "suit", "standing", "holding", "and", "pouring", "wine"], "raw": "Man in suit standing holding and pouring wine.", "sent_id": 72263, "sent": "man in suit standing holding and pouring wine"}], "file_name": "COCO_train2014_000000563525_468222.jpg", "ann_id": 468222, "sent_ids": [72262, 72263], "ref_id": 32744}, {"segmentation": [[286.49, 143.52, 285.33, 303.72, 456.01, 277.51, 472.33, 194.79, 474.07, 181.97, 464.17, 63.71, 461.26, 34.59, 439.7, 25.85]], "area": 38539.243650000004, "iscrowd": 0, "image_id": 174774, "bbox": [285.33, 25.85, 188.74, 277.87], "category_id": 72, "id": 321307, "split": "val", "sentences": [{"tokens": ["the", "computer", "screen", "with", "the", "image", "of", "the", "dinosaur"], "raw": "the computer screen with the image of the dinosaur", "sent_id": 72282, "sent": "the computer screen with the image of the dinosaur"}, {"tokens": ["television", "with", "a", "raptor", "on", "the", "screen"], "raw": "television with a raptor on the screen", "sent_id": 72283, "sent": "television with a raptor on the screen"}], "file_name": "COCO_train2014_000000174774_321307.jpg", "ann_id": 321307, "sent_ids": [72282, 72283], "ref_id": 32754}, {"segmentation": [[630.16, 183.18, 615.02, 204.94, 596.1, 216.3, 577.17, 218.19, 546.9, 214.41, 527.97, 194.54, 515.67, 165.2, 515.67, 133.98, 531.76, 113.16, 549.74, 103.7, 569.61, 99.92, 590.42, 102.76, 607.45, 113.16, 622.59, 123.57, 631.11, 150.07, 632.05, 168.04]], "area": 10982.377500000004, "iscrowd": 0, "image_id": 7504, "bbox": [515.67, 99.92, 116.38, 118.27], "category_id": 85, "id": 338044, "split": "val", "sentences": [{"tokens": ["a", "clock", "on", "a", "wall", "calling", "the", "time", "in", "bac", "kinh", "as", "8", ":", "30"], "raw": "A clock on a wall calling the time in Bac Kinh as 8:30", "sent_id": 72296, "sent": "a clock on a wall calling the time in bac kinh as 8 : 30"}, {"tokens": ["the", "clock", "for", "bac", "kinh"], "raw": "The clock for bac kinh", "sent_id": 72297, "sent": "the clock for bac kinh"}], "file_name": "COCO_train2014_000000007504_338044.jpg", "ann_id": 338044, "sent_ids": [72296, 72297], "ref_id": 32759}, {"segmentation": [[184.09, 442.73, 163.96, 413.96, 136.63, 426.91, 87.73, 406.77, 37.39, 373.69, 31.64, 355.0, 37.39, 314.73, 61.84, 288.84, 119.37, 206.86, 149.57, 186.73, 182.65, 168.03, 189.84, 159.4, 185.53, 139.27, 169.71, 117.69, 172.58, 90.37, 186.97, 52.97, 201.35, 19.9, 300.58, 24.21, 327.91, 60.16, 320.72, 103.31, 293.39, 160.84, 289.08, 179.54, 303.46, 192.48, 312.09, 278.77, 322.16, 334.86, 320.72, 409.65, 316.4, 445.6, 319.28, 471.49, 297.71, 484.43, 266.07, 477.24, 257.44, 464.3, 261.75, 444.16, 264.63, 441.29, 232.99, 439.85, 212.85, 454.23]], "area": 83555.82854999999, "iscrowd": 0, "image_id": 69344, "bbox": [31.64, 19.9, 296.27, 464.53], "category_id": 1, "id": 462573, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "a", "striped", "t", "-", "shirt", "adding", "a", "candle", "to", "a", "cake"], "raw": "A boy in a striped t-shirt adding a candle to a cake.", "sent_id": 72366, "sent": "a boy in a striped t - shirt adding a candle to a cake"}, {"tokens": ["older", "brother"], "raw": "older brother", "sent_id": 72367, "sent": "older brother"}], "file_name": "COCO_train2014_000000069344_462573.jpg", "ann_id": 462573, "sent_ids": [72366, 72367], "ref_id": 32785}, {"segmentation": [[2.16, 116.49, 17.26, 106.79, 31.28, 96.0, 45.3, 93.84, 61.48, 116.49, 61.48, 136.99, 24.81, 144.54, 17.26, 169.35, 30.2, 194.16, 50.7, 199.55, 52.85, 226.52, 23.73, 211.42, 16.18, 209.26, 4.31, 279.37, 8.63, 345.17, 42.07, 363.51, 33.44, 371.06, 4.31, 374.29]], "area": 5581.292100000001, "iscrowd": 0, "image_id": 356916, "bbox": [2.16, 93.84, 59.32, 280.45], "category_id": 1, "id": 191184, "split": "val", "sentences": [{"tokens": ["the", "woman", "that", "is", "standing", "and", "leaning", "over", "the", "table"], "raw": "The woman that is standing and leaning over the table.", "sent_id": 72397, "sent": "the woman that is standing and leaning over the table"}, {"tokens": ["lady", "with", "red", "top", "in", "the", "left", "side", "of", "the", "image"], "raw": "lady with red top in the left side of the image", "sent_id": 72398, "sent": "lady with red top in the left side of the image"}], "file_name": "COCO_train2014_000000356916_191184.jpg", "ann_id": 191184, "sent_ids": [72397, 72398], "ref_id": 32797}, {"segmentation": [[280.27, 622.3, 287.49, 587.63, 290.38, 542.84, 290.38, 515.4, 300.5, 479.28, 314.94, 473.5, 323.61, 469.16, 348.17, 500.95, 362.62, 529.84, 375.62, 560.18, 391.51, 599.19, 416.07, 629.53, 417.52, 632.42, 431.96, 600.63, 427.63, 577.52, 418.96, 538.51, 408.85, 485.06, 394.4, 415.71, 355.4, 320.36, 316.39, 297.25, 260.05, 268.35, 232.6, 230.79, 225.37, 191.78, 245.6, 126.77, 238.37, 109.44, 215.26, 131.11, 210.93, 131.11, 206.59, 131.11, 182.03, 110.88, 145.91, 126.77, 144.47, 131.11, 115.58, 125.33, 95.35, 152.78, 137.25, 183.12, 153.14, 196.12, 163.25, 210.56, 177.7, 246.68, 177.7, 266.91, 173.36, 307.36, 167.58, 329.03, 173.36, 360.81, 177.7, 389.71, 177.7, 440.27, 156.03, 513.95, 156.03, 542.84, 148.8, 613.63, 148.8, 613.63, 148.8, 625.19, 184.92, 606.41, 184.92, 526.95, 192.14, 486.5, 203.7, 451.83, 206.59, 440.27, 222.48, 457.61, 228.26, 466.28, 245.6, 495.17, 245.6, 544.29, 249.93, 599.19, 249.93, 620.86, 249.93, 628.08, 251.38, 628.08, 271.6, 628.08]], "area": 70952.94605000001, "iscrowd": 0, "image_id": 186255, "bbox": [95.35, 109.44, 336.61, 522.98], "category_id": 24, "id": 590400, "split": "val", "sentences": [{"tokens": ["a", "zebra", "with", "a", "showing", "its", "back", "with", "a", "tail"], "raw": "A zebra with a  showing its back with a tail.", "sent_id": 72470, "sent": "a zebra with a showing its back with a tail"}, {"tokens": ["the", "two", "zebras", "facing", "each", "other"], "raw": "The two zebras facing each other.", "sent_id": 72471, "sent": "the two zebras facing each other"}], "file_name": "COCO_train2014_000000186255_590400.jpg", "ann_id": 590400, "sent_ids": [72470, 72471], "ref_id": 32829}, {"segmentation": [[142.38, 451.96, 115.42, 388.31, 112.18, 348.4, 148.85, 297.71, 197.39, 265.35, 266.43, 265.35, 324.67, 311.73, 330.07, 351.64, 321.44, 401.26, 308.49, 440.09, 259.96, 472.45, 200.63, 474.61, 153.17, 458.43]], "area": 36079.40015, "iscrowd": 0, "image_id": 568840, "bbox": [112.18, 265.35, 217.89, 209.26], "category_id": 60, "id": 1079417, "split": "val", "sentences": [{"tokens": ["donut", "with", "chocolate", "and", "vanilla", "frosting"], "raw": "Donut with chocolate and vanilla frosting.", "sent_id": 72528, "sent": "donut with chocolate and vanilla frosting"}, {"tokens": ["a", "doughnut", "with", "icing", "in", "the", "shape", "of", "a", "spiderweb"], "raw": "A doughnut with icing in the shape of a spiderweb.", "sent_id": 72529, "sent": "a doughnut with icing in the shape of a spiderweb"}], "file_name": "COCO_train2014_000000568840_1079417.jpg", "ann_id": 1079417, "sent_ids": [72528, 72529], "ref_id": 32850}, {"segmentation": [[357.74, 303.96, 283.02, 300.57, 275.09, 173.77, 281.89, 169.25, 332.83, 166.98, 331.7, 173.77, 386.04, 174.91, 386.04, 168.11, 408.68, 168.11, 425.66, 177.17, 425.66, 296.04, 408.68, 296.04, 399.62, 302.83, 361.13, 305.09, 349.81, 306.23, 349.81, 306.23]], "area": 19197.131900000004, "iscrowd": 0, "image_id": 217893, "bbox": [275.09, 166.98, 150.57, 139.25], "category_id": 72, "id": 124421, "split": "val", "sentences": [{"tokens": ["a", "crt", "monitor", "with", "a", "black", "&", "white", "photo", "of", "bruce", "lee", "displayed"], "raw": "A CRT monitor with a black & white photo of Bruce Lee displayed.", "sent_id": 72642, "sent": "a crt monitor with a black & white photo of bruce lee displayed"}, {"tokens": ["a", "white", "desktop", "monitor", "with", "brucelee", "photo", "on", "it"], "raw": "A white desktop monitor with brucelee photo on it", "sent_id": 72643, "sent": "a white desktop monitor with brucelee photo on it"}], "file_name": "COCO_train2014_000000217893_124421.jpg", "ann_id": 124421, "sent_ids": [72642, 72643], "ref_id": 32892}, {"segmentation": [[114.19, 252.36, 85.4, 221.66, 88.28, 207.26, 93.08, 200.55, 121.86, 190.95, 152.57, 189.99, 196.71, 9.6, 200.55, 23.03, 164.08, 189.99, 172.72, 188.07, 178.48, 177.52, 179.44, 188.07, 208.22, 188.07, 242.77, 193.83, 368.47, 219.74, 501.84, 257.16, 512.4, 246.6, 537.35, 243.73, 551.74, 283.07, 609.31, 292.66, 594.92, 255.24, 568.05, 255.24, 596.84, 248.52, 638.1, 254.28, 640.0, 378.06, 615.07, 378.06, 606.44, 419.32, 554.62, 418.36, 570.93, 367.51, 537.35, 404.93, 491.29, 417.4, 449.07, 400.13, 415.49, 389.58, 403.01, 405.89, 332.96, 378.06, 165.04, 295.54, 166.96, 274.43, 143.93, 270.59, 118.98, 370.39, 106.51, 404.93, 103.63, 405.89, 124.74, 292.66, 89.24, 342.56, 80.6, 342.56, 79.64, 330.09, 80.6, 312.81, 87.32, 297.46, 113.23, 254.28]], "area": 80654.52935000003, "iscrowd": 0, "image_id": 421105, "bbox": [79.64, 9.6, 560.36, 409.72], "category_id": 5, "id": 158319, "split": "val", "sentences": [{"tokens": ["the", "nose", "of", "a", "red", ",", "small", "airplane", "with", "sparky", "written", "on", "it"], "raw": "The nose of a red, small airplane with Sparky written on it.", "sent_id": 72711, "sent": "the nose of a red , small airplane with sparky written on it"}, {"tokens": ["an", "airplane", "with", "sparky", "written", "on", "the", "side"], "raw": "An airplane with Sparky written on the side.", "sent_id": 72712, "sent": "an airplane with sparky written on the side"}], "file_name": "COCO_train2014_000000421105_158319.jpg", "ann_id": 158319, "sent_ids": [72711, 72712], "ref_id": 32917}, {"segmentation": [[262.58, 1.07, 216.69, 27.75, 196.4, 60.84, 190.0, 91.8, 196.4, 128.09, 203.88, 155.84, 228.43, 170.79, 257.25, 188.93, 282.87, 211.35, 295.67, 217.75, 344.78, 212.42, 392.81, 183.6, 430.17, 115.28, 417.36, 66.18, 399.21, 32.02, 373.6, 16.01, 347.98, 2.13, 265.79, 0.0]], "area": 39450.1125, "iscrowd": 0, "image_id": 572602, "bbox": [190.0, 0.0, 240.17, 217.75], "category_id": 51, "id": 712556, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "blueberries"], "raw": "A bowl of blueberries", "sent_id": 72785, "sent": "a bowl of blueberries"}, {"tokens": ["bowl", "of", "blueberries"], "raw": "bowl of blueberries", "sent_id": 72786, "sent": "bowl of blueberries"}], "file_name": "COCO_train2014_000000572602_712556.jpg", "ann_id": 712556, "sent_ids": [72785, 72786], "ref_id": 32950}, {"segmentation": [[197.67, 227.41, 174.64, 213.98, 169.84, 184.23, 174.64, 166.0, 199.59, 152.57, 209.18, 146.81, 217.82, 142.01, 241.81, 131.46, 255.24, 126.66, 269.63, 121.86, 270.59, 116.11, 259.08, 110.35, 259.08, 96.91, 266.76, 83.48, 279.23, 76.76, 291.7, 63.33, 306.1, 54.69, 316.65, 47.98, 332.0, 47.98, 348.32, 50.86, 364.63, 59.49, 381.9, 66.21, 394.38, 74.84, 407.81, 80.6, 406.85, 85.4, 414.53, 96.91, 431.8, 110.35, 433.72, 120.9, 411.65, 129.54, 395.33, 142.01, 377.1, 156.41, 376.14, 167.92, 370.39, 196.71, 375.18, 225.49, 303.22, 255.24, 278.27, 258.12, 278.27, 270.59, 292.66, 287.87, 326.25, 284.99, 332.96, 290.74, 330.09, 311.85, 320.49, 317.61, 307.06, 318.57, 300.34, 332.96, 300.34, 356.95, 288.82, 358.87, 246.6, 346.4, 243.73, 336.8, 242.77, 331.04, 248.52, 316.65, 249.48, 295.54, 249.48, 287.87, 242.77, 294.58, 236.05, 320.49, 227.41, 333.92, 213.02, 340.64, 204.38, 341.6, 162.16, 336.8, 149.69, 322.41, 152.57, 299.38, 162.16, 276.35, 176.56, 262.92, 182.31, 257.16, 194.79, 245.64, 197.67, 240.85]], "area": 45620.47725000002, "iscrowd": 0, "image_id": 34739, "bbox": [149.69, 47.98, 284.03, 310.89], "category_id": 88, "id": 1162988, "split": "val", "sentences": [{"tokens": ["a", "toy", "teddy", "bear", "holding", "a", "girl", "baby", "toy"], "raw": "A TOY TEDDY BEAR HOLDING A GIRL BABY TOY", "sent_id": 72822, "sent": "a toy teddy bear holding a girl baby toy"}, {"tokens": ["some", "figures", "made", "on", "rock"], "raw": "SOME FIGURES MADE ON ROCK", "sent_id": 72823, "sent": "some figures made on rock"}], "file_name": "COCO_train2014_000000034739_1162988.jpg", "ann_id": 1162988, "sent_ids": [72822, 72823], "ref_id": 32963}, {"segmentation": [[396.73, 301.09, 396.73, 313.78, 424.99, 325.31, 436.52, 321.28, 439.98, 318.39, 441.71, 317.24, 530.53, 344.34, 525.92, 375.49, 529.95, 379.53, 533.42, 381.26, 542.07, 377.8, 551.29, 372.03, 562.83, 366.26, 573.21, 361.07, 578.4, 339.15, 599.74, 330.5, 596.86, 317.81, 589.94, 313.2, 599.16, 306.28, 538.61, 274.56, 515.54, 278.02, 509.19, 281.48, 502.27, 286.67, 500.54, 286.67, 505.73, 276.29, 503.42, 268.79, 441.71, 255.53, 410.57, 262.45, 396.73, 267.64, 389.23, 276.29, 395.57, 280.9, 390.38, 286.67, 386.35, 291.86, 385.77, 295.9, 390.96, 298.78]], "area": 13367.381449999999, "iscrowd": 0, "image_id": 535874, "bbox": [385.77, 255.53, 213.97, 125.73], "category_id": 63, "id": 389785, "split": "val", "sentences": [{"tokens": ["two", "black", "and", "white", "color", "pillows", "on", "the", "purple", "color", "table", "toy"], "raw": "TWO BLACK AND WHITE COLOR PILLOWS ON THE PURPLE COLOR TABLE TOY", "sent_id": 72830, "sent": "two black and white color pillows on the purple color table toy"}, {"tokens": ["white", "cheetah", "print", "cushions", "on", "a", "bench"], "raw": "White cheetah print cushions on a bench.", "sent_id": 72831, "sent": "white cheetah print cushions on a bench"}], "file_name": "COCO_train2014_000000535874_389785.jpg", "ann_id": 389785, "sent_ids": [72830, 72831], "ref_id": 32967}, {"segmentation": [[285.24, 183.92, 311.67, 183.92, 328.19, 192.73, 330.39, 202.64, 343.61, 207.04, 363.43, 207.04, 379.95, 207.04, 394.26, 210.35, 407.48, 221.36, 403.08, 226.87, 390.96, 233.48, 396.47, 259.91, 399.77, 288.54, 407.48, 311.67, 408.58, 339.2, 406.38, 344.71, 400.87, 316.07, 392.06, 297.35, 376.64, 267.62, 373.34, 263.21, 373.34, 284.14, 378.85, 308.36, 377.75, 340.3, 375.54, 353.52, 363.43, 345.81, 367.83, 310.57, 361.23, 276.43, 357.92, 259.91, 349.11, 254.4, 338.1, 265.41, 330.39, 273.12, 334.79, 318.28, 338.1, 351.31, 328.19, 361.23, 325.98, 334.79, 325.98, 307.26, 317.17, 275.32, 299.55, 268.72, 284.14, 285.24, 285.24, 322.68, 288.54, 350.21, 270.92, 350.21, 272.02, 312.77, 272.02, 279.73, 272.02, 252.2, 273.12, 236.78, 279.73, 226.87, 283.03, 213.65, 283.03, 197.13]], "area": 12107.1625, "iscrowd": 0, "image_id": 217978, "bbox": [270.92, 183.92, 137.66, 177.31], "category_id": 18, "id": 1817228, "split": "val", "sentences": [{"tokens": ["german", "short", "hair", "dog", ",", "has", "lots", "of", "spots"], "raw": "German short hair dog, has lots of spots", "sent_id": 72903, "sent": "german short hair dog , has lots of spots"}, {"tokens": ["spaniel", "closest", "to", "patio"], "raw": "spaniel closest to patio", "sent_id": 72904, "sent": "spaniel closest to patio"}], "file_name": "COCO_train2014_000000217978_1817228.jpg", "ann_id": 1817228, "sent_ids": [72903, 72904], "ref_id": 33000}, {"segmentation": [[297.59, 122.05, 292.02, 117.59, 284.22, 110.9, 270.84, 107.56, 247.44, 113.13, 225.15, 123.16, 205.08, 146.57, 199.51, 161.06, 185.02, 165.52, 161.61, 173.32, 143.78, 177.78, 137.09, 182.23, 137.09, 194.49, 148.24, 303.72, 156.04, 315.98, 168.3, 304.84, 182.79, 297.04, 200.63, 290.35, 212.89, 279.2, 225.15, 273.63, 242.98, 274.74, 248.55, 274.74, 247.44, 250.22, 251.9, 237.96, 259.7, 235.73, 269.73, 219.02, 286.45, 211.21, 290.91, 204.53, 286.45, 193.38, 286.45, 181.12, 286.45, 152.14]], "area": 19522.794150000005, "iscrowd": 0, "image_id": 46592, "bbox": [137.09, 107.56, 160.5, 208.42], "category_id": 62, "id": 2125453, "split": "val", "sentences": [{"tokens": ["an", "empty", "chair", "that", "is", "to", "the", "left", "of", "the", "main", "sitting", "down"], "raw": "An empty chair that is to the left of the main sitting down.", "sent_id": 72940, "sent": "an empty chair that is to the left of the main sitting down"}, {"tokens": ["a", "black", "chair", "to", "the", "left", "of", "the", "dog"], "raw": "A black chair to the left of the dog.", "sent_id": 72941, "sent": "a black chair to the left of the dog"}], "file_name": "COCO_train2014_000000046592_2125453.jpg", "ann_id": 2125453, "sent_ids": [72940, 72941], "ref_id": 33012}, {"segmentation": [[473.81, 415.01, 480.66, 418.44, 339.09, 421.86, 336.8, 320.25, 300.27, 296.27, 278.58, 271.16, 231.77, 262.02, 222.63, 204.94, 238.62, 121.59, 251.18, 110.18, 244.33, 101.04, 303.7, 46.24, 352.79, 46.24, 366.49, 40.53, 382.47, 46.24, 390.47, 33.68, 421.29, 67.93, 424.72, 81.63, 438.42, 87.34, 440.7, 102.18, 464.68, 134.15, 466.96, 168.4, 455.54, 228.91, 448.69, 346.51]], "area": 66211.87270000002, "iscrowd": 0, "image_id": 187577, "bbox": [222.63, 33.68, 258.03, 388.18], "category_id": 1, "id": 1707054, "split": "val", "sentences": [{"tokens": ["young", "girl", "with", "head", "band", "on"], "raw": "young girl with head band on", "sent_id": 73086, "sent": "young girl with head band on"}, {"tokens": ["a", "girl", "wearing", "a", "pink", "bow", "and", "a", "floral", "dress"], "raw": "A girl wearing a pink bow and a floral dress.", "sent_id": 73087, "sent": "a girl wearing a pink bow and a floral dress"}], "file_name": "COCO_train2014_000000187577_1707054.jpg", "ann_id": 1707054, "sent_ids": [73086, 73087], "ref_id": 33063}, {"segmentation": [[88.51, 357.54, 152.5, 334.34, 200.49, 328.74, 206.89, 319.94, 210.89, 230.36, 233.29, 207.17, 258.08, 226.36, 264.48, 222.36, 282.88, 250.36, 311.67, 240.76, 330.07, 245.56, 332.47, 265.55, 322.87, 339.94, 278.88, 351.94, 274.88, 386.33, 269.28, 416.73, 154.1, 450.32, 133.3, 466.32, 134.1, 420.72, 98.11, 415.13, 79.71, 396.73, 78.92, 368.73]], "area": 30851.43695000001, "iscrowd": 0, "image_id": 319396, "bbox": [78.92, 207.17, 253.55, 259.15], "category_id": 70, "id": 1096691, "split": "val", "sentences": [{"tokens": ["western", "toilet", "in", "bathroom"], "raw": "WESTERN TOILET IN BATHROOM", "sent_id": 73092, "sent": "western toilet in bathroom"}, {"tokens": ["a", "blue", "toilet", "in", "a", "bathroom"], "raw": "A blue toilet in a bathroom.", "sent_id": 73093, "sent": "a blue toilet in a bathroom"}], "file_name": "COCO_train2014_000000319396_1096691.jpg", "ann_id": 1096691, "sent_ids": [73092, 73093], "ref_id": 33066}, {"segmentation": [[59.21, 151.8, 83.97, 136.73, 117.35, 119.5, 146.41, 115.19, 163.64, 128.11, 177.64, 153.95, 189.48, 188.4, 193.78, 229.31, 197.01, 260.53, 193.78, 293.91, 188.4, 314.36, 187.32, 334.82, 195.94, 343.43, 216.39, 363.88, 236.85, 471.54, 190.55, 434.94, 143.18, 414.48, 123.81, 419.86, 85.05, 434.94, 51.68, 464.0, 3.23, 471.54, 5.38, 331.59, 31.22, 312.21, 27.99, 218.55, 35.53, 183.02]], "area": 54745.65080000001, "iscrowd": 0, "image_id": 39812, "bbox": [3.23, 115.19, 233.62, 356.35], "category_id": 1, "id": 482280, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "silver", "necklace"], "raw": "A woman wearing a silver necklace.", "sent_id": 73162, "sent": "a woman wearing a silver necklace"}, {"tokens": ["lady", "wearing", "a", "black", "dress", "standing", "with", "a", "man", "and", "another", "woman"], "raw": "Lady wearing a black dress standing with a man and another woman", "sent_id": 73163, "sent": "lady wearing a black dress standing with a man and another woman"}], "file_name": "COCO_train2014_000000039812_482280.jpg", "ann_id": 482280, "sent_ids": [73162, 73163], "ref_id": 33092}, {"segmentation": [[295.23, 74.79, 323.19, 81.78, 347.08, 95.18, 349.41, 103.92, 348.24, 119.07, 341.25, 130.13, 333.09, 134.21, 313.29, 159.84, 329.6, 180.82, 344.16, 191.3, 350.57, 201.2, 375.62, 234.28, 386.11, 241.85, 394.26, 252.34, 396.01, 257.58, 395.43, 270.98, 391.35, 277.39, 378.53, 282.05, 365.72, 283.21, 351.74, 267.48, 351.74, 261.08, 324.94, 230.78, 324.94, 237.19, 333.09, 298.36, 348.82, 333.31, 341.83, 354.28, 318.53, 362.44, 283.58, 359.52, 283.58, 327.48, 277.17, 308.26, 266.1, 291.95, 262.02, 307.68, 267.85, 314.67, 269.01, 337.97, 259.11, 351.95, 248.04, 358.36, 208.43, 351.37, 198.53, 252.34, 184.55, 254.08, 167.65, 241.85, 165.32, 214.47, 174.06, 181.27, 191.54, 156.22, 218.33, 142.82, 217.75, 125.93, 207.27, 114.28, 208.43, 96.8, 222.41, 78.74, 232.31, 65.92, 241.64, 63.59, 261.44, 63.59]], "area": 41865.930149999986, "iscrowd": 0, "image_id": 81372, "bbox": [165.32, 63.59, 230.69, 298.85], "category_id": 88, "id": 1161970, "split": "val", "sentences": [{"tokens": ["a", "large", "teddy", "bear", "with", "a", "smaller", "one", "in", "its", "lap"], "raw": "A large teddy bear with a smaller one in its lap.", "sent_id": 73307, "sent": "a large teddy bear with a smaller one in its lap"}, {"tokens": ["large", "stuffed", "mama", "bear", "seated", "on", "bench", "with", "baby", "bear", "in", "her", "lap"], "raw": "large stuffed mama bear seated on bench with baby bear in her lap", "sent_id": 73308, "sent": "large stuffed mama bear seated on bench with baby bear in her lap"}], "file_name": "COCO_train2014_000000081372_1161970.jpg", "ann_id": 1161970, "sent_ids": [73307, 73308], "ref_id": 33146}, {"segmentation": [[112.54, 224.09, 157.78, 407.25, 164.4, 427.0, 363.01, 427.0, 375.14, 263.81, 386.18, 216.37, 374.04, 165.61, 340.94, 139.13, 294.6, 110.44, 211.84, 115.96, 175.43, 133.61, 147.85, 147.96, 132.4, 176.64, 127.99, 185.47, 124.68, 196.5, 113.65, 218.57]], "area": 71276.86265, "iscrowd": 0, "image_id": 541938, "bbox": [112.54, 110.44, 273.64, 316.56], "category_id": 47, "id": 1884325, "split": "val", "sentences": [{"tokens": ["a", "white", "cup", "of", "chocolate", "with", "four", "streaks", "falling", "from", "its", "lip"], "raw": "A white cup of chocolate with four streaks falling from its lip.", "sent_id": 73309, "sent": "a white cup of chocolate with four streaks falling from its lip"}, {"tokens": ["chocolate", "in", "a", "white", "mug"], "raw": "Chocolate in a white mug.", "sent_id": 73310, "sent": "chocolate in a white mug"}], "file_name": "COCO_train2014_000000541938_1884325.jpg", "ann_id": 1884325, "sent_ids": [73309, 73310], "ref_id": 33147}, {"segmentation": [[0.0, 558.02, 461.66, 609.8, 463.1, 619.87, 454.47, 640.0, 1.44, 640.0, 2.88, 560.9]], "area": 25668.882850000013, "iscrowd": 0, "image_id": 30231, "bbox": [0.0, 558.02, 463.1, 81.98], "category_id": 67, "id": 1614619, "split": "val", "sentences": [{"tokens": ["the", "table", "in", "front", "of", "the", "guy", "with", "the", "red", "sweatshirt"], "raw": "the table in front of the guy with the red sweatshirt", "sent_id": 73323, "sent": "the table in front of the guy with the red sweatshirt"}, {"tokens": ["the", "edge", "of", "a", "table", ".", "part", "of", "a", "pair", "of", "pants", "is", "visible"], "raw": "The edge of a table. Part of a pair of pants is visible.", "sent_id": 73324, "sent": "the edge of a table . part of a pair of pants is visible"}], "file_name": "COCO_train2014_000000030231_1614619.jpg", "ann_id": 1614619, "sent_ids": [73323, 73324], "ref_id": 33153}, {"segmentation": [[400.36, 2.3, 426.19, 0.86, 426.19, 13.78, 396.05, 20.95, 410.4, 43.91, 410.4, 75.48, 420.45, 119.96, 408.97, 165.88, 383.14, 167.32, 365.92, 170.19, 371.66, 213.24, 345.83, 218.98, 338.65, 237.63, 321.43, 267.77, 295.61, 264.9, 276.95, 231.89, 264.04, 216.11, 232.47, 216.11, 220.99, 223.28, 198.03, 233.33, 195.16, 239.07, 137.76, 244.81, 58.83, 239.07, 44.48, 253.42, 5.74, 256.29, 0.0, 5.17, 1.43, 0.0, 391.75, 0.0]], "area": 95152.77429999999, "iscrowd": 0, "image_id": 33017, "bbox": [0.0, 0.0, 426.19, 267.77], "category_id": 3, "id": 347810, "split": "val", "sentences": [{"tokens": ["ford", "suv"], "raw": "Ford SUV", "sent_id": 73392, "sent": "ford suv"}, {"tokens": ["a", "car", "on", "the", "road"], "raw": "a car on the road", "sent_id": 73393, "sent": "a car on the road"}], "file_name": "COCO_train2014_000000033017_347810.jpg", "ann_id": 347810, "sent_ids": [73392, 73393], "ref_id": 33177}, {"segmentation": [[291.7, 291.41, 308.98, 197.37, 328.17, 140.76, 352.16, 110.06, 370.39, 113.89, 370.39, 119.65, 408.77, 144.6, 389.58, 174.34, 377.1, 202.17, 368.47, 226.16, 351.2, 240.55, 326.25, 216.57, 312.81, 285.65]], "area": 8868.030999999999, "iscrowd": 0, "image_id": 560750, "bbox": [291.7, 110.06, 117.07, 181.35], "category_id": 90, "id": 342795, "split": "val", "sentences": [{"tokens": ["a", "white", "toothbrush"], "raw": "A white toothbrush", "sent_id": 73398, "sent": "a white toothbrush"}, {"tokens": ["the", "head", "of", "a", "toothbrush", "in", "sticking", "out", "of", "a", "jar"], "raw": "The head of a toothbrush in sticking out of a jar.", "sent_id": 73399, "sent": "the head of a toothbrush in sticking out of a jar"}], "file_name": "COCO_train2014_000000560750_342795.jpg", "ann_id": 342795, "sent_ids": [73398, 73399], "ref_id": 33179}, {"segmentation": [[5.95, 43.85, 120.24, 21.23, 121.43, 93.85, 3.57, 116.47]], "area": 8415.907599999999, "iscrowd": 0, "image_id": 423343, "bbox": [3.57, 21.23, 117.86, 95.24], "category_id": 84, "id": 1985172, "split": "val", "sentences": [{"tokens": ["the", "newspaper", "titled", "cityam"], "raw": "The newspaper titled CityAM", "sent_id": 73426, "sent": "the newspaper titled cityam"}, {"tokens": ["a", "newspaper"], "raw": "A newspaper.", "sent_id": 73427, "sent": "a newspaper"}], "file_name": "COCO_train2014_000000423343_1985172.jpg", "ann_id": 1985172, "sent_ids": [73426, 73427], "ref_id": 33189}, {"segmentation": [[343.03, 376.66, 337.72, 335.8, 349.98, 273.69, 465.62, 267.15, 489.73, 262.25, 479.1, 325.58, 463.17, 380.75, 458.26, 406.49, 454.18, 454.0, 571.05, 447.36, 542.85, 372.99, 564.1, 367.26, 555.11, 314.96, 546.12, 250.42, 639.29, 233.26, 640.0, 147.17, 506.89, 180.68, 403.92, 168.42, 386.34, 167.2, 387.16, 178.23, 366.73, 183.54, 354.88, 176.6, 351.2, 148.81, 347.11, 140.23, 338.53, 140.23, 336.9, 144.31, 247.0, 135.32, 232.7, 133.69, 225.75, 144.72, 213.49, 151.26, 199.6, 151.67, 196.33, 155.75, 192.25, 152.32, 191.1, 150.91, 187.65, 152.06, 179.62, 147.73, 179.62, 146.07, 177.2, 142.5, 176.81, 138.16, 174.01, 131.15, 163.93, 134.59, 147.61, 148.75, 137.41, 155.12, 118.15, 155.12, 95.96, 157.55, 86.48, 157.23, 61.29, 160.74, 49.28, 161.91, 46.05, 156.64, 36.97, 158.4, 23.2, 153.71, 1.81, 151.37, 1.65, 331.26, 26.16, 329.67, 27.44, 346.86, 15.02, 417.63, 86.66, 407.12, 93.38, 405.4, 101.36, 425.91, 148.1, 428.19, 163.48, 430.47, 193.69, 427.62, 202.81, 419.07, 238.72, 417.93, 250.69, 401.41]], "area": 130969.59300000001, "iscrowd": 0, "image_id": 132746, "bbox": [1.65, 131.15, 638.35, 322.85], "category_id": 5, "id": 267951, "split": "val", "sentences": [{"tokens": ["airplane"], "raw": "Airplane.", "sent_id": 73452, "sent": "airplane"}, {"tokens": ["a", "black", "and", "white", "picture", "of", "a", "steel", "airplane"], "raw": "a black and white picture of a steel airplane", "sent_id": 73453, "sent": "a black and white picture of a steel airplane"}], "file_name": "COCO_train2014_000000132746_267951.jpg", "ann_id": 267951, "sent_ids": [73452, 73453], "ref_id": 33198}, {"segmentation": [[316.44, 345.16, 311.94, 456.64, 273.65, 449.89, 266.89, 429.62, 270.27, 409.35, 263.51, 394.71, 254.5, 378.94, 0.0, 384.57, 0.0, 11.82, 234.23, 23.09, 265.77, 54.62, 304.05, 157.09, 332.21, 144.71, 329.95, 214.53, 322.07, 311.37, 317.57, 341.78]], "area": 114794.36595000002, "iscrowd": 0, "image_id": 244875, "bbox": [0.0, 11.82, 332.21, 444.82], "category_id": 3, "id": 142751, "split": "val", "sentences": [{"tokens": ["white", "car", "in", "road"], "raw": "white car in road", "sent_id": 73467, "sent": "white car in road"}, {"tokens": ["a", "white", "parked", "car", "with", "two", "cats", "underneath", "it"], "raw": "A white parked car with two cats underneath it.", "sent_id": 73468, "sent": "a white parked car with two cats underneath it"}], "file_name": "COCO_train2014_000000244875_142751.jpg", "ann_id": 142751, "sent_ids": [73467, 73468], "ref_id": 33205}, {"segmentation": [[222.35, 22.94, 262.94, 29.12, 271.76, 45.88, 275.29, 70.59, 275.29, 82.06, 270.0, 94.41, 258.53, 103.24, 221.47, 112.94, 191.47, 118.24, 172.94, 111.18, 163.24, 91.76, 161.47, 68.82, 171.18, 49.41, 185.29, 36.18, 203.82, 26.47]], "area": 8516.792650000001, "iscrowd": 0, "image_id": 263744, "bbox": [161.47, 22.94, 113.82, 95.3], "category_id": 55, "id": 1053605, "split": "val", "sentences": [{"tokens": ["orange", "behind", "the", "bannana"], "raw": "orange behind the bannana", "sent_id": 73491, "sent": "orange behind the bannana"}, {"tokens": ["an", "orange", "in", "a", "fruit", "bowl"], "raw": "An orange in a fruit bowl", "sent_id": 73492, "sent": "an orange in a fruit bowl"}], "file_name": "COCO_train2014_000000263744_1053605.jpg", "ann_id": 1053605, "sent_ids": [73491, 73492], "ref_id": 33213}, {"segmentation": [[562.07, 147.34, 567.43, 138.99, 564.75, 133.03, 567.43, 125.58, 574.89, 109.78, 564.45, 87.42, 545.37, 79.08, 537.33, 78.78, 524.81, 89.81, 512.59, 85.93, 501.56, 91.0, 500.96, 95.17, 502.45, 100.84, 514.08, 106.8, 512.59, 113.36, 509.31, 117.23, 508.71, 124.09, 510.5, 133.63, 511.39, 142.87, 508.71, 152.7, 499.77, 153.9, 489.63, 157.18, 483.37, 162.84, 475.62, 172.97, 471.15, 183.41, 466.08, 203.68, 450.53, 222.24, 446.9, 245.0, 446.9, 256.38, 444.72, 281.81, 445.2, 286.65, 440.36, 295.12, 442.78, 305.78, 452.47, 338.22, 459.73, 352.51, 469.17, 363.64, 479.83, 369.7, 480.31, 385.44, 480.07, 398.75, 479.34, 401.17, 479.58, 415.7, 483.46, 419.33, 491.45, 421.27, 504.28, 420.54, 509.85, 414.01, 509.37, 380.11, 510.58, 353.72, 512.76, 346.94, 520.52, 303.34, 535.06, 316.35, 544.24, 343.51, 551.89, 390.95, 554.19, 400.9, 572.93, 414.67, 592.45, 420.41, 608.51, 417.73, 612.72, 412.38, 593.59, 391.72, 582.5, 381.39, 580.59, 332.8, 574.85, 306.02, 570.26, 296.84, 572.17, 292.25, 588.24, 291.1, 575.23, 280.39, 580.22, 276.96, 595.95, 274.4, 583.36, 272.44, 578.84, 264.96, 588.67, 259.65, 595.36, 252.97, 594.18, 238.61, 595.95, 232.51, 597.13, 214.03, 595.36, 200.26, 590.25, 165.84, 588.48, 162.5, 582.97, 157.78, 576.48, 156.01, 563.11, 154.44]], "area": 33851.16140000001, "iscrowd": 0, "image_id": 361939, "bbox": [440.36, 78.78, 172.36, 342.49], "category_id": 1, "id": 235481, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "green", "hat", "holding", "a", "red", "jacket"], "raw": "A woman wearing a green hat holding a red jacket.", "sent_id": 73495, "sent": "a woman wearing a green hat holding a red jacket"}, {"tokens": ["a", "woman", "wearing", "a", "hat", "and", "holding", "a", "red", "blanket"], "raw": "A woman wearing a hat and holding a red blanket.", "sent_id": 73496, "sent": "a woman wearing a hat and holding a red blanket"}], "file_name": "COCO_train2014_000000361939_235481.jpg", "ann_id": 235481, "sent_ids": [73495, 73496], "ref_id": 33215}, {"segmentation": [[138.07, 414.2, 158.78, 363.58, 158.78, 324.46, 185.24, 300.3, 223.21, 248.52, 254.27, 182.94, 235.87, 170.28, 226.66, 144.97, 230.11, 121.96, 196.75, 90.89, 196.75, 64.43, 209.4, 35.67, 208.25, 19.56, 235.87, 16.11, 225.51, 60.98, 238.17, 95.5, 250.82, 105.85, 249.67, 65.58, 308.35, 60.98, 378.53, 74.79, 400.4, 101.25, 391.19, 144.97, 386.59, 155.33, 423.41, 186.39, 461.38, 187.54, 495.89, 174.89, 545.37, 157.63, 558.02, 125.41, 582.18, 134.62, 589.09, 149.57, 544.22, 189.84, 494.74, 216.31, 465.98, 222.06, 432.61, 214.0, 421.11, 226.66, 383.14, 228.96, 364.73, 249.67, 341.72, 298.0, 339.42, 338.27, 327.91, 347.47, 323.31, 391.19, 280.74, 398.09, 291.09, 367.03, 274.98, 364.73, 230.11, 365.88, 192.14, 373.93, 181.79, 411.9], [100.1, 431.46, 87.44, 406.15, 70.18, 408.45, 70.18, 428.01]], "area": 60461.890999999996, "iscrowd": 0, "image_id": 67835, "bbox": [70.18, 16.11, 518.91, 415.35], "category_id": 1, "id": 1227568, "split": "val", "sentences": [{"tokens": ["a", "skateboarder"], "raw": "A skateboarder.", "sent_id": 73507, "sent": "a skateboarder"}, {"tokens": ["a", "long", "haired", "man", "riding", "a", "skate", "board"], "raw": "A long haired man riding a skate board.", "sent_id": 73508, "sent": "a long haired man riding a skate board"}], "file_name": "COCO_train2014_000000067835_1227568.jpg", "ann_id": 1227568, "sent_ids": [73507, 73508], "ref_id": 33221}, {"segmentation": [[237.8, 550.76, 83.16, 382.96, 110.58, 307.29, 235.6, 396.13, 233.41, 460.83, 241.09, 546.38]], "area": 17636.598799999992, "iscrowd": 0, "image_id": 470912, "bbox": [83.16, 307.29, 157.93, 243.47], "category_id": 75, "id": 2135322, "split": "val", "sentences": [{"tokens": ["a", "white", "remote", "control", "in", "a", "box", "with", "a", "kitten"], "raw": "A white remote control in a box with a kitten", "sent_id": 73524, "sent": "a white remote control in a box with a kitten"}, {"tokens": ["a", "wire", "basket", "with", "a", "kitten", "in", "it"], "raw": "a wire basket with a kitten in it", "sent_id": 73525, "sent": "a wire basket with a kitten in it"}], "file_name": "COCO_train2014_000000470912_2135322.jpg", "ann_id": 2135322, "sent_ids": [73524, 73525], "ref_id": 33228}, {"segmentation": [[229.98, 405.58, 225.59, 423.13, 228.33, 476.87, 231.07, 516.9, 238.75, 545.96, 248.62, 563.51, 266.17, 576.12, 290.3, 581.61, 329.78, 581.06, 353.91, 576.67, 368.72, 569.0, 387.36, 552.65, 400.52, 526.88, 403.81, 494.53, 402.72, 463.82, 400.52, 431.46, 393.94, 406.24, 365.98, 361.93, 363.23, 370.7, 350.07, 375.64, 345.14, 373.44, 340.75, 372.89, 340.2, 389.89, 336.91, 401.41, 328.69, 406.35, 322.65, 410.73, 314.43, 416.76, 300.72, 422.8, 293.59, 423.89, 285.36, 421.7, 273.85, 422.8, 267.27, 422.25, 261.78, 419.51, 255.75, 419.51, 244.23, 417.86, 238.75, 416.76, 236.56, 412.93]], "area": 28390.06455, "iscrowd": 0, "image_id": 427805, "bbox": [225.59, 361.93, 178.22, 219.68], "category_id": 86, "id": 1156378, "split": "val", "sentences": [{"tokens": ["the", "vase", "that", "the", "pink", "flowers", "are", "sitting", "in"], "raw": "The vase that the pink flowers are sitting in", "sent_id": 73559, "sent": "the vase that the pink flowers are sitting in"}, {"tokens": ["a", "vase", "with", "red", "and", "pink", "flowers", "in", "it"], "raw": "A vase with red and pink flowers in it.", "sent_id": 73560, "sent": "a vase with red and pink flowers in it"}], "file_name": "COCO_train2014_000000427805_1156378.jpg", "ann_id": 1156378, "sent_ids": [73559, 73560], "ref_id": 33241}, {"segmentation": [[245.38, 305.65, 241.08, 288.43, 243.95, 278.39, 269.78, 272.65, 291.3, 259.73, 302.78, 246.82, 302.78, 239.64, 317.13, 236.77, 321.43, 231.03, 314.26, 219.55, 294.17, 210.94, 275.52, 209.51, 275.52, 187.98, 284.13, 169.33, 317.13, 123.41, 348.7, 117.67, 364.48, 120.54, 386.01, 136.32, 401.79, 142.06, 430.49, 154.98, 447.71, 170.76, 467.8, 190.85, 480.0, 203.77, 479.28, 421.88, 453.45, 440.54, 443.41, 444.84, 426.19, 431.93, 411.84, 433.36, 338.65, 387.44, 315.7, 370.22, 281.26, 365.92, 259.73, 347.26, 253.99, 335.78, 269.78, 324.3]], "area": 53110.776099999995, "iscrowd": 0, "image_id": 74549, "bbox": [241.08, 117.67, 238.92, 327.17], "category_id": 54, "id": 309956, "split": "val", "sentences": [{"tokens": ["a", "half", "of", "a", "sandwhich", "with", "a", "bite", "taken", "out"], "raw": "A half of a sandwhich with a bite taken out.", "sent_id": 73574, "sent": "a half of a sandwhich with a bite taken out"}, {"tokens": ["the", "piece", "of", "bread", "with", "a", "bite", "taken", "from", "it"], "raw": "The piece of bread with a bite taken from it.", "sent_id": 73575, "sent": "the piece of bread with a bite taken from it"}], "file_name": "COCO_train2014_000000074549_309956.jpg", "ann_id": 309956, "sent_ids": [73574, 73575], "ref_id": 33247}, {"segmentation": [[436.56, 218.85, 438.59, 197.58, 457.83, 186.44, 469.99, 177.33, 471.0, 163.14, 510.5, 163.14, 513.54, 182.39, 544.94, 207.71, 542.92, 223.92, 538.86, 254.31, 531.77, 277.6, 525.7, 297.86, 520.63, 309.0, 516.58, 315.08, 518.61, 320.14, 484.17, 326.22, 454.79, 323.18, 453.78, 314.07, 454.79, 230.0, 441.63, 222.91]], "area": 12418.956150000004, "iscrowd": 0, "image_id": 481165, "bbox": [436.56, 163.14, 108.38, 163.08], "category_id": 44, "id": 95391, "split": "val", "sentences": [{"tokens": ["bottle", "with", "the", "name", "lumier", "on", "it"], "raw": "Bottle with the name Lumier on it.", "sent_id": 73594, "sent": "bottle with the name lumier on it"}, {"tokens": ["full", "perfume", "bottle"], "raw": "full perfume bottle", "sent_id": 73595, "sent": "full perfume bottle"}], "file_name": "COCO_train2014_000000481165_95391.jpg", "ann_id": 95391, "sent_ids": [73594, 73595], "ref_id": 33254}, {"segmentation": [[71.19, 474.61, 100.31, 434.7, 91.69, 395.87, 70.11, 355.96, 69.03, 325.75, 81.98, 303.1, 93.84, 251.33, 105.71, 234.07, 117.57, 232.99, 117.57, 208.18, 128.36, 193.08, 143.46, 192.0, 167.19, 198.47, 159.64, 257.8, 171.51, 296.63, 181.21, 303.1, 212.49, 285.84, 250.25, 279.37, 235.15, 304.18, 184.45, 330.07, 155.33, 313.89, 143.46, 364.58, 148.85, 409.89, 120.81, 473.53]], "area": 19454.927999999996, "iscrowd": 0, "image_id": 15658, "bbox": [69.03, 192.0, 181.22, 282.61], "category_id": 1, "id": 487662, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "black", "sweatshirt"], "raw": "a person in a black sweatshirt", "sent_id": 73650, "sent": "a person in a black sweatshirt"}, {"tokens": ["a", "person", "in", "black", "on", "a", "court"], "raw": "A person in black on a court.", "sent_id": 73651, "sent": "a person in black on a court"}], "file_name": "COCO_train2014_000000015658_487662.jpg", "ann_id": 487662, "sent_ids": [73650, 73651], "ref_id": 33275}, {"segmentation": [[286.28, 380.56, 273.36, 403.16, 281.97, 417.15, 265.83, 470.96, 184.04, 474.19, 163.59, 296.61, 170.04, 277.24, 157.13, 199.75, 184.04, 120.11, 227.09, 100.74, 217.4, 65.22, 227.09, 40.47, 242.15, 32.93, 260.45, 31.86, 280.9, 44.77, 287.35, 59.84, 278.74, 98.58, 274.44, 106.12, 289.51, 110.42, 307.8, 141.63, 303.5, 199.75, 303.5, 239.57, 291.66, 298.76, 290.58, 338.58]], "area": 48424.816050000016, "iscrowd": 0, "image_id": 106652, "bbox": [157.13, 31.86, 150.67, 442.33], "category_id": 1, "id": 186102, "split": "val", "sentences": [{"tokens": ["a", "white", "male", "with", "a", "white", "shirt", ",", "black", "pants", ",", "and", "black", "tie", "standing", "next", "to", "a", "woman", "near", "a", "brown", "couch"], "raw": "A white male with a white shirt, black pants, and black tie standing next to a woman near a brown couch", "sent_id": 73655, "sent": "a white male with a white shirt , black pants , and black tie standing next to a woman near a brown couch"}, {"tokens": ["a", "guy", "wearing", "a", "tie"], "raw": "A guy wearing a tie.", "sent_id": 73656, "sent": "a guy wearing a tie"}], "file_name": "COCO_train2014_000000106652_186102.jpg", "ann_id": 186102, "sent_ids": [73655, 73656], "ref_id": 33278}, {"segmentation": [[231.68, 479.6, 221.08, 470.34, 216.45, 451.13, 224.39, 433.26, 240.95, 410.75, 250.22, 384.93, 260.15, 366.39, 268.09, 348.51, 284.64, 310.77, 297.22, 290.25, 311.13, 279.65, 317.75, 269.72, 332.98, 261.11, 348.21, 258.46, 356.81, 256.48, 366.08, 251.84, 352.18, 236.62, 334.3, 228.67, 328.34, 224.04, 326.36, 200.2, 325.69, 176.36, 332.98, 157.83, 336.29, 142.6, 340.92, 132.0, 343.57, 119.42, 352.18, 108.83, 376.68, 102.21, 398.52, 98.24, 421.04, 98.9, 436.26, 107.51, 452.15, 122.07, 461.42, 139.29, 467.38, 169.74, 473.34, 182.99, 478.64, 191.59, 483.94, 208.81, 484.6, 222.05, 470.03, 237.94, 448.18, 232.64, 446.2, 231.98, 452.15, 245.22, 470.69, 252.51, 479.96, 263.76, 481.95, 269.72, 503.14, 280.31, 510.42, 287.6, 509.09, 314.08, 517.04, 335.27, 508.43, 346.52, 509.76, 390.88, 504.46, 453.78, 495.19, 474.31, 495.19, 480.0, 237.64, 480.0]], "area": 74227.06509999999, "iscrowd": 0, "image_id": 408954, "bbox": [216.45, 98.24, 300.59, 381.76], "category_id": 1, "id": 1750798, "split": "val", "sentences": [{"tokens": ["a", "ash", "color", "jacket", "wearing", "lady", "facing", "a", "man", "and", "speaking", "with", "him", "with", "her", "colleague"], "raw": "A ASH COLOR JACKET WEARING LADY FACING A MAN AND SPEAKING WITH HIM WITH HER COLLEAGUE", "sent_id": 73684, "sent": "a ash color jacket wearing lady facing a man and speaking with him with her colleague"}, {"tokens": ["woman", "wearing", "a", "hooded", "jacket"], "raw": "Woman wearing a hooded jacket", "sent_id": 73685, "sent": "woman wearing a hooded jacket"}], "file_name": "COCO_train2014_000000408954_1750798.jpg", "ann_id": 1750798, "sent_ids": [73684, 73685], "ref_id": 33285}, {"segmentation": [[82.44, 211.13, 86.34, 226.15, 91.9, 227.27, 103.58, 246.74, 216.53, 245.07, 312.23, 235.61, 399.03, 228.38, 412.94, 183.31, 392.36, 184.98, 293.32, 31.97, 289.98, 32.53, 290.53, 59.79, 83.0, 212.51]], "area": 35668.1759, "iscrowd": 0, "image_id": 84162, "bbox": [82.44, 31.97, 330.5, 214.77], "category_id": 9, "id": 181330, "split": "val", "sentences": [{"tokens": ["a", "decorated", "passenger", "ship", "is", "waiting", "for", "departure", "in", "a", "port"], "raw": "A decorated passenger ship is waiting for departure in a port.", "sent_id": 73688, "sent": "a decorated passenger ship is waiting for departure in a port"}], "file_name": "COCO_train2014_000000084162_181330.jpg", "ann_id": 181330, "sent_ids": [73688], "ref_id": 33287}, {"segmentation": [[561.72, 170.17, 551.38, 191.9, 462.41, 174.31, 458.28, 174.31, 468.62, 148.45, 471.72, 143.28, 560.69, 162.93, 560.69, 171.21], [457.24, 152.59, 461.38, 166.03, 458.28, 174.31, 404.48, 172.24, 406.55, 150.52, 407.59, 142.24, 459.31, 150.52], [330.0, 146.38, 356.9, 178.45, 361.03, 181.55, 362.07, 154.66, 362.07, 143.28, 282.41, 135.0, 266.9, 145.34, 233.79, 191.9, 247.24, 206.38, 273.1, 201.21, 261.72, 179.48, 264.83, 161.9, 279.31, 152.59, 296.9, 152.59, 316.55, 143.28]], "area": 6986.471700000002, "iscrowd": 0, "image_id": 524227, "bbox": [233.79, 135.0, 327.93, 71.38], "category_id": 63, "id": 114908, "split": "val", "sentences": [{"tokens": ["a", "sofa", "behind", "an", "eating", "boy"], "raw": "A sofa behind an eating boy", "sent_id": 73695, "sent": "a sofa behind an eating boy"}], "file_name": "COCO_train2014_000000524227_114908.jpg", "ann_id": 114908, "sent_ids": [73695], "ref_id": 33290}, {"segmentation": [[313.55, 169.0, 326.12, 171.32, 344.74, 183.43, 349.4, 197.39, 420.62, 249.53, 447.15, 267.68, 547.24, 343.1, 575.17, 361.25, 612.88, 401.29, 614.74, 410.6, 605.43, 411.53, 530.48, 356.13, 482.07, 316.1, 449.02, 287.24, 370.81, 226.25, 336.83, 199.72, 326.12, 190.41, 309.83, 170.86]], "area": 5913.363349999997, "iscrowd": 0, "image_id": 79111, "bbox": [309.83, 169.0, 304.91, 242.53], "category_id": 50, "id": 1894741, "split": "val", "sentences": [{"tokens": ["the", "handles", "of", "several", "wooden", "spoons"], "raw": "The handles of several wooden spoons.", "sent_id": 73719, "sent": "the handles of several wooden spoons"}, {"tokens": ["the", "stick", "sticking", "out", "the", "farthest"], "raw": "the stick sticking out the farthest", "sent_id": 73720, "sent": "the stick sticking out the farthest"}], "file_name": "COCO_train2014_000000079111_1894741.jpg", "ann_id": 1894741, "sent_ids": [73719, 73720], "ref_id": 33299}, {"segmentation": [[212.55, 227.97, 205.94, 196.03, 219.16, 160.79, 244.49, 145.37, 251.1, 129.95, 248.89, 117.84, 241.18, 109.03, 237.88, 100.22, 237.88, 88.1, 242.29, 69.38, 256.6, 58.37, 279.73, 63.88, 291.84, 98.02, 290.74, 113.43, 285.24, 125.55, 288.54, 132.16, 302.86, 144.27, 325.98, 155.28, 348.01, 204.84, 363.43, 287.44, 357.92, 317.17, 353.52, 319.38, 353.52, 325.98, 344.71, 344.71, 335.9, 346.91, 333.69, 362.33, 288.54, 366.73, 285.24, 355.72, 283.03, 356.82, 281.93, 367.83, 237.88, 378.85, 234.58, 351.31, 221.36, 333.69, 227.97, 311.67, 225.77, 279.73, 223.56, 269.82, 236.78, 275.32, 246.69, 275.32, 259.91, 259.91, 255.5, 249.99, 245.59, 237.88, 230.17, 233.48, 218.06, 230.17]], "area": 30603.780249999993, "iscrowd": 0, "image_id": 327209, "bbox": [205.94, 58.37, 157.49, 320.48], "category_id": 1, "id": 2148376, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "the", "middle"], "raw": "The person in the middle.", "sent_id": 73762, "sent": "the person in the middle"}, {"tokens": ["boy", "with", "dark", "hair", "wearing", "royal", "blue", "coat", "and", "t", "-", "shirt"], "raw": "boy with dark hair wearing royal blue coat and t-shirt", "sent_id": 73763, "sent": "boy with dark hair wearing royal blue coat and t - shirt"}], "file_name": "COCO_train2014_000000327209_2148376.jpg", "ann_id": 2148376, "sent_ids": [73762, 73763], "ref_id": 33315}, {"segmentation": [[348.07, 389.64, 353.05, 341.96, 347.36, 309.93, 365.86, 298.55, 372.26, 294.28, 373.69, 245.88, 400.73, 245.88, 416.39, 238.77, 461.22, 248.02, 466.2, 304.95, 458.37, 355.48, 425.64, 364.73, 360.88, 363.31, 348.78, 390.35]], "area": 12171.82955, "iscrowd": 0, "image_id": 328727, "bbox": [347.36, 238.77, 118.84, 151.58], "category_id": 62, "id": 384832, "split": "val", "sentences": [{"tokens": ["a", "blue", "felt", "chair", "in", "a", "class", "room"], "raw": "A blue felt chair in a class room.", "sent_id": 73792, "sent": "a blue felt chair in a class room"}, {"tokens": ["a", "purple", "chair", "in", "a", "classroom"], "raw": "a purple chair in a classroom", "sent_id": 73793, "sent": "a purple chair in a classroom"}], "file_name": "COCO_train2014_000000328727_384832.jpg", "ann_id": 384832, "sent_ids": [73792, 73793], "ref_id": 33328}, {"segmentation": [[364.62, 135.31, 363.7, 100.5, 363.7, 75.76, 400.35, 60.19, 469.06, 52.86, 584.49, 55.61, 614.72, 7.05, 616.55, 3.39, 640.0, 1.56, 640.0, 226.93, 610.14, 225.09, 586.32, 241.58, 589.07, 250.74, 611.06, 269.07, 567.08, 277.31, 576.25, 282.81, 548.76, 302.05, 534.1, 301.13, 497.46, 338.69, 449.82, 349.69, 478.22, 389.08, 530.44, 413.82, 568.92, 421.14, 409.51, 417.48, 433.33, 379.0, 443.41, 323.12, 447.07, 274.56, 445.24, 209.52, 412.26, 140.81, 367.37, 133.48]], "area": 60349.13815000001, "iscrowd": 0, "image_id": 155268, "bbox": [363.7, 1.56, 276.3, 419.58], "category_id": 63, "id": 113668, "split": "val", "sentences": [{"tokens": ["couch", "the", "woman", "is", "leaning", "on"], "raw": "couch the woman is leaning on.", "sent_id": 73800, "sent": "couch the woman is leaning on"}], "file_name": "COCO_train2014_000000155268_113668.jpg", "ann_id": 113668, "sent_ids": [73800], "ref_id": 33331}, {"segmentation": [[261.28, 440.99, 262.96, 432.59, 266.32, 430.92, 266.87, 424.76, 288.69, 424.2, 313.31, 423.08, 320.02, 420.85, 318.9, 412.45, 321.7, 406.3, 326.73, 402.94, 330.65, 399.59, 330.09, 383.92, 365.33, 367.14, 365.89, 363.78, 358.62, 360.99, 334.01, 374.41, 303.8, 377.21, 236.11, 370.5, 172.33, 350.36, 198.07, 340.85, 157.23, 348.68, 156.11, 364.34, 166.18, 372.74, 182.4, 382.25, 200.86, 402.39, 233.31, 415.81, 245.06, 419.73, 246.18, 420.85, 246.18, 425.88, 248.41, 427.56, 247.85, 436.51, 260.16, 439.87]], "area": 7863.433149999998, "iscrowd": 0, "image_id": 258440, "bbox": [156.11, 340.85, 209.78, 100.14], "category_id": 81, "id": 2139764, "split": "val", "sentences": [{"tokens": ["a", "sink", "in", "a", "barber", "shop", "in", "front", "of", "the", "chair", "in", "the", "picture"], "raw": "A sink in a barber shop in front of the chair in the picture.", "sent_id": 73817, "sent": "a sink in a barber shop in front of the chair in the picture"}], "file_name": "COCO_train2014_000000258440_2139764.jpg", "ann_id": 2139764, "sent_ids": [73817], "ref_id": 33339}, {"segmentation": [[307.06, 3.84, 2.88, 0.96, 0.96, 171.76, 20.15, 175.6, 36.46, 161.2, 55.65, 164.08, 79.64, 192.87, 73.89, 214.94, 73.89, 250.44, 103.63, 250.44, 104.59, 191.91, 104.59, 177.52, 119.94, 177.52, 134.34, 240.85, 199.59, 226.45, 190.95, 197.67, 128.58, 199.59, 119.94, 170.8, 206.3, 160.24, 213.02, 144.89, 223.58, 136.26, 222.62, 120.9, 244.69, 120.9, 262.92, 135.3, 265.8, 125.7, 277.31, 134.34, 277.31, 146.81, 315.69, 148.73]], "area": 52805.887350000005, "iscrowd": 0, "image_id": 333842, "bbox": [0.96, 0.96, 314.73, 249.48], "category_id": 72, "id": 31832, "split": "val", "sentences": [{"tokens": ["the", "monitor", "with", "mario", "in", "front", "of", "it"], "raw": "the monitor with mario in front of it.", "sent_id": 73820, "sent": "the monitor with mario in front of it"}, {"tokens": ["the", "monitor", "on", "the", "left"], "raw": "The monitor on the left.", "sent_id": 73821, "sent": "the monitor on the left"}], "file_name": "COCO_train2014_000000333842_31832.jpg", "ann_id": 31832, "sent_ids": [73820, 73821], "ref_id": 33341}, {"segmentation": [[402.03, 303.93, 392.41, 326.05, 379.91, 328.93, 378.95, 305.85, 371.25, 305.85, 361.64, 328.93, 355.87, 318.36, 351.06, 308.74, 352.02, 268.34, 347.21, 179.86, 344.32, 160.62, 350.09, 99.07, 339.51, 84.64, 298.16, 45.2, 281.81, 46.17, 278.92, 36.55, 281.81, 24.04, 291.42, 26.93, 293.35, 22.12, 294.31, 22.12, 298.16, 22.12, 302.0, 34.62, 341.44, 67.33, 367.41, 74.06, 366.44, 66.36, 361.64, 47.13, 370.29, 29.82, 393.38, 33.66, 401.07, 49.05, 399.15, 62.52, 396.26, 68.29, 396.26, 68.29, 417.42, 66.36, 436.66, 59.63, 474.17, 24.04, 480.9, 12.5, 498.21, 7.69, 504.94, 15.39, 505.91, 24.04, 501.1, 34.62, 482.82, 33.66, 448.2, 75.98, 416.46, 92.33, 402.03, 144.27, 406.84, 163.51, 404.92, 216.4, 402.99, 250.07]], "area": 18868.515000000003, "iscrowd": 0, "image_id": 536146, "bbox": [278.92, 7.69, 226.99, 321.24], "category_id": 1, "id": 187159, "split": "val", "sentences": [{"tokens": ["woman", "standign"], "raw": "WOMAN STANDIGN", "sent_id": 73871, "sent": "woman standign"}, {"tokens": ["woman", "in", "air"], "raw": "Woman in air", "sent_id": 73872, "sent": "woman in air"}], "file_name": "COCO_train2014_000000536146_187159.jpg", "ann_id": 187159, "sent_ids": [73871, 73872], "ref_id": 33362}, {"segmentation": [[302.11, 277.86, 324.66, 293.55, 347.22, 295.52, 362.42, 301.89, 371.25, 302.87, 422.73, 297.97, 441.85, 277.86, 451.66, 257.76, 463.43, 227.85, 460.97, 184.7, 484.51, 184.21, 507.06, 179.31, 514.42, 173.92, 509.03, 208.73, 500.69, 228.83, 492.85, 240.11, 529.13, 253.35, 545.8, 266.59, 573.26, 290.61, 589.44, 316.6, 593.85, 323.95, 611.01, 313.17, 618.37, 313.17, 622.29, 327.88, 611.5, 333.27, 600.23, 335.72, 597.77, 343.08, 601.7, 361.22, 604.15, 397.5, 593.85, 428.39, 587.97, 446.05, 574.24, 456.83, 549.23, 480.37, 488.92, 481.0, 441.36, 476.45, 399.68, 456.34, 376.15, 428.39, 351.63, 416.63, 326.63, 414.66, 306.52, 398.97, 300.64, 385.25, 295.74, 356.32, 283.48, 301.89, 291.32, 278.85]], "area": 56435.850600000005, "iscrowd": 0, "image_id": 562100, "bbox": [283.48, 173.92, 338.81, 307.08], "category_id": 53, "id": 1049188, "split": "val", "sentences": [{"tokens": ["apples", "to", "the", "right", "side", "of", "the", "bananas"], "raw": "apples to the right side of the bananas", "sent_id": 73873, "sent": "apples to the right side of the bananas"}, {"tokens": ["a", "red", "and", "green", "apple", "with", "a", "brown", "stem"], "raw": "A red and green apple with a brown stem.", "sent_id": 73874, "sent": "a red and green apple with a brown stem"}], "file_name": "COCO_train2014_000000562100_1049188.jpg", "ann_id": 1049188, "sent_ids": [73873, 73874], "ref_id": 33363}, {"segmentation": [[447.06, 416.58, 448.02, 407.99, 448.02, 395.57, 451.84, 372.64, 457.57, 353.54, 448.97, 341.12, 447.06, 357.36, 443.24, 365.96, 434.64, 373.6, 417.45, 373.6, 413.63, 357.36, 409.81, 349.72, 418.4, 334.43, 426.04, 303.86, 436.55, 275.21, 440.37, 265.65, 458.52, 260.88, 472.85, 251.32, 483.36, 244.64, 477.63, 237.0, 475.72, 226.49, 472.85, 215.03, 467.12, 194.01, 478.58, 179.68, 486.23, 171.08, 504.38, 168.22, 524.44, 174.9, 532.08, 184.46, 533.03, 196.88, 533.03, 212.16, 533.03, 222.67, 526.35, 223.62, 526.35, 235.09, 532.08, 246.55, 534.94, 251.32, 552.14, 251.32, 571.24, 259.92, 581.75, 268.52, 597.99, 301.95, 611.36, 333.48, 618.05, 346.85, 622.83, 356.4, 621.87, 361.18, 619.01, 366.91, 612.32, 378.37, 605.63, 384.11, 598.95, 383.15, 583.66, 373.6, 580.8, 366.91, 581.75, 383.15, 579.84, 403.21, 576.98, 412.76, 576.02, 417.54, 576.02, 422.32]], "area": 31472.948950000005, "iscrowd": 0, "image_id": 333302, "bbox": [409.81, 168.22, 213.02, 254.1], "category_id": 1, "id": 480921, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "flannel", "smiles"], "raw": "a man in flannel smiles", "sent_id": 73954, "sent": "a man in flannel smiles"}, {"tokens": ["the", "man", "with", "a", "backpack"], "raw": "The man with a backpack.", "sent_id": 73955, "sent": "the man with a backpack"}], "file_name": "COCO_train2014_000000333302_480921.jpg", "ann_id": 480921, "sent_ids": [73954, 73955], "ref_id": 33391}, {"segmentation": [[314.97, 259.78, 495.1, 229.57, 578.16, 228.49, 612.67, 284.58, 639.64, 306.16, 640.0, 406.47, 599.73, 435.6, 501.57, 444.22, 440.09, 430.2, 412.04, 336.36, 391.55, 294.29, 373.21, 294.29, 372.13, 312.63, 362.43, 349.3, 362.43, 364.4, 334.38, 311.55, 316.04, 294.29, 302.02, 273.8, 313.89, 265.17]], "area": 48655.54280000001, "iscrowd": 0, "image_id": 119604, "bbox": [302.02, 228.49, 337.98, 215.73], "category_id": 8, "id": 397692, "split": "val", "sentences": [{"tokens": ["a", "yellow", "food", "truck"], "raw": "A yellow food truck", "sent_id": 74000, "sent": "a yellow food truck"}, {"tokens": ["a", "food", "truck", "on", "a", "city", "street", "with", "many", "customers"], "raw": "A food truck on a city street with many customers.", "sent_id": 74001, "sent": "a food truck on a city street with many customers"}], "file_name": "COCO_train2014_000000119604_397692.jpg", "ann_id": 397692, "sent_ids": [74000, 74001], "ref_id": 33410}, {"segmentation": [[163.25, 469.16, 158.92, 443.16, 184.92, 438.83, 218.15, 438.83, 229.71, 443.16, 228.26, 472.05, 229.71, 482.17, 223.93, 490.84, 251.38, 500.95, 252.82, 511.06, 245.6, 531.29, 138.69, 606.41, 117.02, 597.74, 108.35, 583.3, 102.57, 573.18, 95.35, 565.96, 83.79, 563.07, 59.23, 555.85, 52.01, 552.96, 49.12, 545.73, 49.12, 538.51, 49.12, 537.07, 50.56, 529.84, 52.01, 522.62, 56.34, 515.4, 62.12, 505.28, 65.01, 503.84, 70.79, 508.17, 109.8, 538.51, 163.25, 473.5]], "area": 16755.671649999997, "iscrowd": 0, "image_id": 68430, "bbox": [49.12, 438.83, 203.7, 167.58], "category_id": 54, "id": 308623, "split": "val", "sentences": [{"tokens": ["bread", "sandwich", "in", "plate"], "raw": "bread sandwich in plate", "sent_id": 74029, "sent": "bread sandwich in plate"}, {"tokens": ["a", "hoagie", "sandwich", "that", "has", "been", "cut", "in", "three"], "raw": "a hoagie sandwich that has been cut in three", "sent_id": 74030, "sent": "a hoagie sandwich that has been cut in three"}], "file_name": "COCO_train2014_000000068430_308623.jpg", "ann_id": 308623, "sent_ids": [74029, 74030], "ref_id": 33420}, {"segmentation": [[145.74, 92.75, 148.15, 77.09, 155.38, 69.26, 143.94, 68.66, 134.9, 54.8, 136.71, 40.95, 152.97, 34.33, 173.45, 46.37, 174.05, 56.01, 188.5, 53.0, 209.58, 58.42, 209.58, 72.27, 201.15, 75.88, 213.2, 86.72, 226.44, 104.19, 215.6, 102.98, 233.67, 118.64, 246.32, 130.09, 256.56, 138.52, 253.55, 148.15, 228.85, 146.35, 221.02, 132.49, 201.15, 119.24, 186.7, 109.01, 172.84, 102.98, 163.81, 99.37, 163.81, 105.39, 160.8, 106.6, 156.58, 99.37, 147.55, 90.94], [198.74, 170.44, 192.72, 181.88, 193.92, 192.12, 209.58, 196.93, 223.43, 187.9, 224.04, 178.87, 208.98, 170.44]], "area": 5731.918699999999, "iscrowd": 0, "image_id": 551553, "bbox": [134.9, 34.33, 121.66, 162.6], "category_id": 1, "id": 191272, "split": "val", "sentences": [{"tokens": ["a", "man", "riding", "a", "bike", "in", "desert", "runes"], "raw": "A man riding a bike in desert runes", "sent_id": 74031, "sent": "a man riding a bike in desert runes"}, {"tokens": ["person", "riding", "on", "a", "yellow", "dirt", "bike"], "raw": "person riding on a yellow dirt bike", "sent_id": 74032, "sent": "person riding on a yellow dirt bike"}], "file_name": "COCO_train2014_000000551553_191272.jpg", "ann_id": 191272, "sent_ids": [74031, 74032], "ref_id": 33421}, {"segmentation": [[151.64, 201.71, 161.62, 187.75, 169.6, 180.76, 182.57, 176.77, 185.56, 173.78, 174.59, 165.8, 163.62, 159.81, 154.64, 151.83, 150.65, 140.86, 149.65, 125.89, 149.65, 110.93, 154.64, 95.96, 161.62, 79.0, 173.59, 56.06, 197.54, 45.08, 222.48, 43.09, 249.41, 53.06, 257.4, 62.04, 259.39, 92.97, 264.38, 111.92, 266.37, 122.9, 253.41, 126.89, 239.44, 131.88, 241.43, 144.85, 248.42, 155.82, 256.4, 155.82, 265.38, 162.81, 279.34, 171.78, 297.3, 183.76, 306.28, 195.73, 311.27, 202.71, 316.26, 209.7, 330.22, 234.64, 335.21, 246.61, 335.21, 261.57, 330.22, 289.51, 335.21, 321.43, 327.23, 324.43, 299.3, 313.45, 265.38, 301.48, 209.51, 285.52, 183.57, 266.56, 167.61, 253.59, 145.66, 245.61, 136.68, 241.62, 132.69, 225.66, 132.69, 212.69, 139.67, 205.7, 145.66, 203.71, 152.64, 195.73]], "area": 32668.73669999999, "iscrowd": 0, "image_id": 563525, "bbox": [132.69, 43.09, 202.52, 281.34], "category_id": 1, "id": 502169, "split": "val", "sentences": [{"tokens": ["a", "women", "watching", "looking", "at", "the", "waiter", "pouring", "wine"], "raw": "A women watching looking at the waiter pouring wine.", "sent_id": 74041, "sent": "a women watching looking at the waiter pouring wine"}, {"tokens": ["a", "woman", "looking", "up", "and", "smiling", "as", "wine", "as", "being", "poured", "into", "a", "glass"], "raw": "A woman looking up and smiling as wine as being poured into a glass.", "sent_id": 74042, "sent": "a woman looking up and smiling as wine as being poured into a glass"}], "file_name": "COCO_train2014_000000563525_502169.jpg", "ann_id": 502169, "sent_ids": [74041, 74042], "ref_id": 33424}, {"segmentation": [[378.49, 259.92, 374.84, 297.32, 371.19, 327.41, 377.58, 416.79, 402.2, 413.14, 402.2, 396.73, 393.08, 367.54, 470.6, 353.86, 471.51, 342.92, 517.11, 335.62, 529.88, 295.49, 445.06, 234.39, 426.82, 260.84]], "area": 15157.965300000003, "iscrowd": 0, "image_id": 155549, "bbox": [371.19, 234.39, 158.69, 182.4], "category_id": 63, "id": 115398, "split": "val", "sentences": [{"tokens": ["a", "brown", "sofa", "in", "front", "of", "the", "television", "beside", "the", "wall"], "raw": "a brown sofa in front of the television beside the wall", "sent_id": 74051, "sent": "a brown sofa in front of the television beside the wall"}, {"tokens": ["the", "red", "couch", "on", "the", "right"], "raw": "the red couch on the right", "sent_id": 74052, "sent": "the red couch on the right"}], "file_name": "COCO_train2014_000000155549_115398.jpg", "ann_id": 115398, "sent_ids": [74051, 74052], "ref_id": 33429}, {"segmentation": [[290.36, 443.37, 277.5, 399.45, 283.93, 386.59, 289.29, 357.66, 280.71, 322.3, 263.57, 292.3, 261.43, 264.45, 242.14, 245.16, 222.86, 245.16, 213.21, 254.8, 212.14, 277.3, 238.93, 292.3, 245.36, 292.3, 247.5, 331.95, 274.29, 341.59, 282.86, 360.87, 267.86, 375.87, 257.14, 395.16, 257.14, 430.52, 261.43, 466.95]], "area": 5627.568399999999, "iscrowd": 0, "image_id": 95518, "bbox": [212.14, 245.16, 78.22, 221.79], "category_id": 1, "id": 220587, "split": "val", "sentences": [{"tokens": ["man", "on", "the", "frontmost", "bike"], "raw": "man on the frontmost bike", "sent_id": 74087, "sent": "man on the frontmost bike"}], "file_name": "COCO_train2014_000000095518_220587.jpg", "ann_id": 220587, "sent_ids": [74087], "ref_id": 33440}, {"segmentation": [[219.48, 493.51, 219.48, 364.94, 210.39, 336.36, 205.19, 306.49, 188.31, 258.44, 197.4, 254.55, 198.7, 262.34, 202.6, 272.73, 223.38, 305.19, 235.06, 301.3, 240.26, 323.38, 258.44, 333.77, 271.43, 354.55, 274.03, 363.64, 315.58, 367.53, 309.09, 384.42, 264.94, 374.03, 267.53, 448.05, 258.44, 459.74, 251.95, 493.51, 244.16, 493.51, 236.36, 468.83, 235.06, 493.51]], "area": 9426.8745, "iscrowd": 0, "image_id": 565018, "bbox": [188.31, 254.55, 127.27, 238.96], "category_id": 1, "id": 2150249, "split": "val", "sentences": [{"tokens": ["a", "guy", "in", "orange", "and", "white", "jersey", "reaching", "for", "a", "frisbee"], "raw": "A GUY IN ORANGE AND WHITE JERSEY REACHING FOR A FRISBEE.", "sent_id": 74108, "sent": "a guy in orange and white jersey reaching for a frisbee"}, {"tokens": ["the", "man", "in", "the", "white", "and", "red", "shirt", "who", "caught", "the", "frisbee"], "raw": "the man in the white and red shirt who caught the frisbee", "sent_id": 74109, "sent": "the man in the white and red shirt who caught the frisbee"}], "file_name": "COCO_train2014_000000565018_2150249.jpg", "ann_id": 2150249, "sent_ids": [74108, 74109], "ref_id": 33447}, {"segmentation": [[88.41, 117.38, 88.41, 102.31, 112.53, 103.32, 135.64, 112.36, 147.69, 113.36, 162.76, 117.38, 170.8, 92.27, 185.87, 102.31, 193.91, 114.37, 196.92, 122.41, 208.98, 129.44, 227.06, 133.46, 257.2, 124.42, 243.14, 141.5, 231.08, 150.54, 228.07, 158.58, 220.03, 172.64, 220.03, 176.66, 218.02, 180.68, 202.95, 175.66, 227.06, 189.72, 224.05, 217.85, 232.09, 238.95, 242.13, 252.01, 247.16, 282.15, 254.19, 305.26, 262.23, 341.43, 264.24, 355.5, 264.24, 372.58, 267.25, 391.67, 267.25, 401.71, 247.16, 422.81, 245.15, 368.56, 237.11, 310.29, 223.04, 266.08, 232.09, 251.01, 200.94, 217.85, 184.87, 212.83, 173.81, 187.71, 171.8, 171.64, 193.91, 172.64, 193.91, 150.54, 158.74, 141.5, 128.6, 136.47, 129.61, 125.42, 90.42, 116.38]], "area": 10352.003350000003, "iscrowd": 0, "image_id": 320721, "bbox": [88.41, 92.27, 178.84, 330.54], "category_id": 2, "id": 1766509, "split": "val", "sentences": [{"tokens": ["the", "middle", "bicycle", "in", "a", "group", "of", "three"], "raw": "The middle bicycle in a group of three.", "sent_id": 74112, "sent": "the middle bicycle in a group of three"}, {"tokens": ["the", "middle", "bicycle"], "raw": "the middle bicycle", "sent_id": 74113, "sent": "the middle bicycle"}], "file_name": "COCO_train2014_000000320721_1766509.jpg", "ann_id": 1766509, "sent_ids": [74112, 74113], "ref_id": 33448}, {"segmentation": [[385.08, 102.47, 413.12, 126.2, 422.83, 155.33, 423.91, 181.21, 413.12, 204.94, 405.57, 217.89, 392.63, 229.75, 372.13, 232.99, 398.02, 272.9, 427.15, 318.2, 451.96, 353.8, 465.98, 374.29, 469.21, 392.63, 491.87, 403.42, 491.87, 406.65, 478.92, 408.81, 472.45, 408.81, 458.43, 405.57, 443.33, 405.57, 432.54, 392.63, 422.83, 380.76, 409.89, 363.51, 404.49, 360.27, 396.94, 373.21, 378.61, 400.18, 355.96, 419.6, 324.67, 442.25, 300.94, 451.96, 293.39, 454.11, 277.21, 426.07, 267.51, 409.89, 343.01, 299.87, 349.48, 270.74, 336.54, 247.01, 323.6, 241.62, 305.26, 238.38, 279.37, 252.4, 247.01, 269.66, 237.3, 283.69, 238.38, 309.57, 241.62, 332.22, 240.54, 347.33, 230.83, 350.56, 225.44, 339.78, 223.28, 316.04, 224.36, 295.55, 226.52, 289.08, 228.67, 275.06, 232.99, 258.88, 244.85, 237.3, 252.4, 227.6, 266.43, 217.89, 280.45, 214.65, 290.16, 206.02, 294.47, 199.55, 291.24, 179.06, 291.24, 162.88, 296.63, 151.01, 306.34, 132.67, 323.6, 114.34, 336.54, 104.63, 349.48, 94.92, 368.9, 89.53, 384.0, 99.24]], "area": 38582.197349999995, "iscrowd": 0, "image_id": 550760, "bbox": [223.28, 89.53, 268.59, 364.58], "category_id": 1, "id": 566114, "split": "val", "sentences": [{"tokens": ["little", "boy", "getting", "his", "teeth", "brushed"], "raw": "little boy getting his teeth brushed", "sent_id": 74137, "sent": "little boy getting his teeth brushed"}, {"tokens": ["a", "blonde", "boy", "with", "an", "orange", "shirt"], "raw": "A blonde boy with an orange shirt.", "sent_id": 74138, "sent": "a blonde boy with an orange shirt"}], "file_name": "COCO_train2014_000000550760_566114.jpg", "ann_id": 566114, "sent_ids": [74137, 74138], "ref_id": 33459}, {"segmentation": [[80.9, 398.02, 90.61, 396.94, 100.31, 396.94, 108.94, 396.94, 120.81, 403.42, 130.52, 407.73, 142.38, 410.97, 149.93, 412.04, 163.96, 415.28, 170.43, 419.6, 175.82, 424.99, 185.53, 435.78, 192.0, 443.33, 201.71, 451.96, 208.18, 459.51, 217.89, 464.9, 229.75, 470.29, 236.22, 471.37, 253.48, 472.45, 271.82, 470.29, 289.08, 469.21, 299.87, 468.13, 316.04, 463.82, 343.01, 460.58, 353.8, 459.51, 368.9, 457.35, 379.69, 456.27, 392.63, 454.11, 401.26, 450.88, 429.3, 446.56, 441.17, 445.48, 457.35, 437.93, 485.39, 428.22, 506.97, 419.6, 531.78, 409.89, 540.4, 398.02, 547.96, 384.0, 558.74, 355.96, 567.37, 330.07, 569.53, 320.36, 570.61, 312.81, 568.45, 306.34, 558.74, 296.63, 557.66, 278.29, 559.82, 268.58, 557.66, 249.17, 553.35, 235.15, 550.11, 224.36, 542.56, 214.65, 531.78, 204.94, 512.36, 196.31, 501.57, 192.0, 484.31, 183.37, 464.9, 173.66, 437.93, 163.96, 420.67, 154.25, 396.94, 144.54, 386.16, 134.83, 381.84, 131.6, 366.74, 120.81, 346.25, 127.28, 332.22, 131.6, 321.44, 132.67, 299.87, 131.6, 284.76, 132.67, 273.98, 135.91, 248.09, 139.15, 227.6, 135.91, 208.18, 138.07, 199.55, 142.38, 190.92, 143.46, 176.9, 144.54, 160.72, 147.78, 157.48, 149.93, 151.01, 155.33, 142.38, 160.72, 131.6, 168.27, 103.55, 176.9, 92.76, 180.13, 80.9, 195.24, 79.82, 200.63, 71.19, 224.36, 67.96, 230.83, 55.01, 253.48, 47.46, 265.35, 39.91, 270.74, 29.12, 296.63, 29.12, 303.1, 36.67, 338.7, 37.75, 360.27, 40.99, 366.74, 45.3, 369.98, 60.4, 396.94, 89.53, 401.26]], "area": 141484.84355, "iscrowd": 0, "image_id": 539941, "bbox": [29.12, 120.81, 541.49, 351.64], "category_id": 59, "id": 1074048, "split": "val", "sentences": [{"tokens": ["a", "pizza", "that", "has", "10", "pepperoni", "on", "it"], "raw": "A pizza that has 10 pepperoni on it.", "sent_id": 74345, "sent": "a pizza that has 10 pepperoni on it"}, {"tokens": ["pepperoni", "pizza", "on", "wooden", "slab"], "raw": "Pepperoni pizza on wooden slab.", "sent_id": 74346, "sent": "pepperoni pizza on wooden slab"}], "file_name": "COCO_train2014_000000539941_1074048.jpg", "ann_id": 1074048, "sent_ids": [74345, 74346], "ref_id": 33538}, {"segmentation": [[160.43, 1.36, 160.43, 16.14, 134.56, 16.88, 87.24, 19.84, 41.4, 27.97, 39.18, 29.45, 22.18, 101.9, 19.22, 251.99, 14.05, 249.03, 11.83, 245.33, 0.0, 246.81, 0.74, 0.62, 160.43, 0.62]], "area": 8660.009999999998, "iscrowd": 0, "image_id": 105718, "bbox": [0.0, 0.62, 160.43, 251.37], "category_id": 6, "id": 1364873, "split": "val", "sentences": [{"tokens": ["bus", "behind", "full", "bus"], "raw": "bus behind full bus", "sent_id": 74405, "sent": "bus behind full bus"}, {"tokens": ["the", "double", "decker", "bus", "behind", "and", "left", "of", "the", "bus", "in", "full", "view"], "raw": "The double decker bus behind and left of the bus in full view.", "sent_id": 74406, "sent": "the double decker bus behind and left of the bus in full view"}], "file_name": "COCO_train2014_000000105718_1364873.jpg", "ann_id": 1364873, "sent_ids": [74405, 74406], "ref_id": 33562}, {"segmentation": [[356.45, 211.36, 354.62, 189.42, 361.94, 176.63, 363.76, 164.74, 366.51, 151.03, 380.22, 138.24, 393.01, 139.15, 403.06, 146.47, 409.46, 160.17, 409.46, 162.0, 410.38, 172.06, 410.38, 172.06, 410.38, 172.06, 421.34, 190.34, 433.23, 213.19, 439.62, 239.69, 435.05, 276.25, 436.88, 307.33, 436.88, 309.15, 436.88, 310.98, 412.2, 296.36, 397.58, 306.41, 382.96, 305.5, 389.35, 290.87, 372.9, 300.93, 365.59, 303.67, 364.68, 295.44, 372.9, 285.39, 366.51, 274.42, 357.37, 244.26, 350.05, 220.5]], "area": 10677.45315, "iscrowd": 0, "image_id": 400850, "bbox": [350.05, 138.24, 89.57, 172.74], "category_id": 16, "id": 39383, "split": "val", "sentences": [{"tokens": ["a", "large", "white", "parrot", "on", "a", "boy", "'", "s", "left", "shoulder"], "raw": "a large white parrot on a boy's left shoulder", "sent_id": 74415, "sent": "a large white parrot on a boy ' s left shoulder"}, {"tokens": ["a", "white", "parrot", "perched", "on", "a", "boy", "'", "s", "shoulder"], "raw": "A white parrot perched on a boy's shoulder.", "sent_id": 74416, "sent": "a white parrot perched on a boy ' s shoulder"}], "file_name": "COCO_train2014_000000400850_39383.jpg", "ann_id": 39383, "sent_ids": [74415, 74416], "ref_id": 33565}, {"segmentation": [[405.73, 93.65, 404.53, 49.27, 399.33, 26.49, 385.74, 16.49, 369.75, 14.9, 353.36, 20.49, 341.36, 27.29, 332.97, 48.07, 333.37, 58.47, 330.17, 62.47, 334.17, 72.46, 333.37, 82.45, 335.37, 90.45, 344.16, 102.44, 343.36, 108.84, 343.76, 116.03, 336.57, 116.43, 314.58, 116.43, 304.19, 121.63, 290.6, 130.82, 280.2, 135.22, 266.21, 136.02, 264.61, 142.02, 281.8, 146.41, 298.99, 158.01, 301.39, 164.8, 314.18, 165.2, 324.18, 179.99, 333.37, 188.79, 347.36, 239.56, 352.96, 269.94, 352.96, 293.13, 341.76, 310.71, 333.77, 320.31, 328.97, 324.31, 328.57, 332.3, 319.38, 349.89, 312.98, 369.48, 308.58, 395.46, 306.99, 406.66, 306.99, 419.45, 306.99, 427.0, 356.56, 427.0, 375.74, 403.46, 394.13, 386.27, 401.73, 387.87, 420.92, 386.67, 431.31, 411.05, 443.3, 413.05, 458.49, 424.65, 460.49, 426.24, 530.45, 427.0, 524.45, 406.26, 511.66, 378.67, 498.47, 348.29, 495.67, 341.1, 504.07, 282.33, 502.87, 258.35, 502.07, 242.36, 497.27, 229.96, 490.47, 191.99, 490.47, 177.6, 479.68, 147.21, 468.89, 128.43, 451.7, 121.23, 432.11, 112.84, 414.92, 106.84, 410.12, 104.44, 407.32, 98.84], [149.25, 136.91, 147.07, 130.84, 148.28, 119.92, 144.88, 118.22, 135.18, 117.74, 123.53, 125.99, 122.8, 129.39, 118.67, 131.57, 117.95, 141.77, 118.92, 147.35, 121.34, 153.41, 124.01, 150.5, 128.62, 151.23, 131.29, 143.95, 133.72, 143.46, 133.72, 139.82, 139.06, 135.7, 142.46, 138.37, 145.85, 138.37]], "area": 58838.7651, "iscrowd": 0, "image_id": 418500, "bbox": [117.95, 14.9, 412.5, 412.1], "category_id": 1, "id": 198685, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "no", "shirt"], "raw": "The man with no shirt", "sent_id": 74445, "sent": "the man with no shirt"}, {"tokens": ["middle", "aged", "white", "tourist", "sitting", "on", "a", "bench", "next", "to", "a", "statue", "of", "a", "black", "man", "who", "is", "holding", "a", "black", "and", "white", "puppy"], "raw": "Middle aged white tourist sitting on a bench next to a statue of a black man who is holding a black and white puppy.", "sent_id": 74446, "sent": "middle aged white tourist sitting on a bench next to a statue of a black man who is holding a black and white puppy"}], "file_name": "COCO_train2014_000000418500_198685.jpg", "ann_id": 198685, "sent_ids": [74445, 74446], "ref_id": 33577}, {"segmentation": [[205.57, 193.33, 200.43, 172.78, 202.48, 135.77, 210.71, 101.86, 227.15, 47.38, 226.12, 6.27, 257.99, 2.15, 268.27, 3.18, 283.68, 84.38, 306.3, 125.5, 311.43, 188.19, 301.16, 245.75, 302.18, 290.98, 307.32, 293.03, 311.43, 296.12, 313.49, 321.81, 298.07, 343.4, 236.4, 351.62, 244.63, 307.42, 238.46, 259.11, 225.1, 213.89, 214.82, 195.39]], "area": 25696.240299999994, "iscrowd": 0, "image_id": 204529, "bbox": [200.43, 2.15, 113.06, 349.47], "category_id": 44, "id": 94460, "split": "val", "sentences": [{"tokens": ["a", "wine", "bottle", "with", "a", "blue", "label"], "raw": "A wine bottle with a blue label.", "sent_id": 74491, "sent": "a wine bottle with a blue label"}, {"tokens": ["pinot", "blanc", "wine", "bottle"], "raw": "pinot blanc wine bottle", "sent_id": 74492, "sent": "pinot blanc wine bottle"}], "file_name": "COCO_train2014_000000204529_94460.jpg", "ann_id": 94460, "sent_ids": [74491, 74492], "ref_id": 33596}, {"segmentation": [[156.76, 68.79, 184.09, 67.36, 195.6, 90.37, 204.22, 113.38, 230.11, 120.57, 238.74, 136.39, 248.81, 175.22, 248.81, 191.04, 240.18, 195.36, 245.93, 212.61, 247.37, 234.19, 253.12, 260.07, 207.1, 227.0, 202.79, 216.93, 142.38, 225.56, 116.49, 241.38, 102.11, 258.64, 90.61, 250.01, 106.43, 231.31, 143.82, 215.49, 161.08, 199.67, 161.08, 179.54, 159.64, 150.77, 169.71, 133.51, 155.33, 114.82]], "area": 12210.7657, "iscrowd": 0, "image_id": 463224, "bbox": [90.61, 67.36, 162.51, 192.71], "category_id": 1, "id": 516423, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "gray", "shirt", "sitting", "in", "front", "of", "two", "men", "on", "top", "of", "an", "elephant"], "raw": "A man in a gray shirt sitting in front of two men on top of an elephant.", "sent_id": 74497, "sent": "a man in a gray shirt sitting in front of two men on top of an elephant"}, {"tokens": ["a", "mahout", "taking", "two", "other", "men", "for", "a", "ride", "on", "an", "elephant"], "raw": "A mahout taking two other men for a ride on an elephant.", "sent_id": 74498, "sent": "a mahout taking two other men for a ride on an elephant"}], "file_name": "COCO_train2014_000000463224_516423.jpg", "ann_id": 516423, "sent_ids": [74497, 74498], "ref_id": 33599}, {"segmentation": [[316.65, 51.66, 318.57, 34.38, 320.49, 20.95, 325.29, 11.35, 338.72, 6.56, 349.28, 6.56, 363.67, 13.27, 372.31, 28.63, 369.43, 42.06, 361.75, 55.49, 358.87, 62.21, 375.18, 69.89, 380.94, 71.81, 389.58, 96.75, 393.42, 120.74, 404.93, 139.93, 414.53, 168.72, 419.32, 194.63, 439.47, 197.51, 443.31, 211.9, 441.39, 222.46, 437.56, 228.21, 427.96, 227.25, 423.16, 226.29, 409.73, 209.02, 406.85, 199.43, 386.7, 143.77, 371.35, 118.82, 365.59, 147.61, 374.22, 180.24, 373.27, 199.43, 376.14, 235.89, 380.94, 284.83, 366.55, 319.37, 347.36, 344.32, 345.44, 367.35, 335.84, 383.66, 317.61, 384.62, 313.77, 369.27, 312.81, 343.36, 308.98, 328.97, 314.73, 317.45, 320.49, 310.73, 334.88, 315.53, 343.52, 290.58, 345.44, 285.79, 334.88, 279.07, 324.33, 269.47, 309.93, 293.46, 297.46, 327.05, 287.87, 369.27, 285.95, 406.69, 284.99, 423.0, 259.08, 417.24, 259.08, 395.17, 263.88, 337.6, 279.23, 292.5, 277.31, 255.08, 282.11, 204.22, 284.99, 185.99, 282.11, 156.25, 277.31, 99.63, 271.55, 84.28, 236.05, 67.01, 151.61, 37.26, 133.38, 31.51, 126.66, 20.95, 142.01, 10.4, 160.24, 15.19, 207.26, 28.63, 239.89, 41.1, 266.76, 43.98, 304.18, 47.82]], "area": 38472.1094, "iscrowd": 0, "image_id": 251493, "bbox": [126.66, 6.56, 316.65, 416.44], "category_id": 1, "id": 1210716, "split": "val", "sentences": [{"tokens": ["a", "tennis", "player", "in", "a", "black", "shirt"], "raw": "a tennis player in a black shirt", "sent_id": 74520, "sent": "a tennis player in a black shirt"}, {"tokens": ["roger", "federer", "in", "a", "black", "shirt", "playing", "tennis"], "raw": "roger federer in a black shirt playing tennis", "sent_id": 74521, "sent": "roger federer in a black shirt playing tennis"}], "file_name": "COCO_train2014_000000251493_1210716.jpg", "ann_id": 1210716, "sent_ids": [74520, 74521], "ref_id": 33610}, {"segmentation": [[401.79, 261.17, 413.21, 275.85, 420.82, 310.1, 422.99, 323.69, 427.89, 344.35, 442.02, 336.74, 437.13, 316.08, 616.01, 314.45, 620.36, 333.48, 632.32, 336.74, 629.6, 311.73, 638.3, 311.73, 635.04, 257.36]], "area": 13076.760449999994, "iscrowd": 0, "image_id": 305624, "bbox": [401.79, 257.36, 236.51, 86.99], "category_id": 15, "id": 577286, "split": "val", "sentences": [{"tokens": ["an", "empty", "bench", "to", "the", "right", "of", "another", "bench", "that", "has", "people", "on", "it"], "raw": "An empty bench to the right of another bench that has people on it", "sent_id": 74619, "sent": "an empty bench to the right of another bench that has people on it"}, {"tokens": ["the", "bench", "on", "the", "right"], "raw": "The bench on the right.", "sent_id": 74620, "sent": "the bench on the right"}, {"tokens": ["an", "empty", "bench", "in", "a", "park", "along", "a", "waterfront", "with", "people", "and", "boats"], "raw": "An empty bench in a park along a waterfront with people and boats.", "sent_id": 74621, "sent": "an empty bench in a park along a waterfront with people and boats"}], "file_name": "COCO_train2014_000000305624_577286.jpg", "ann_id": 577286, "sent_ids": [74619, 74620, 74621], "ref_id": 33646}, {"segmentation": [[102.45, 376.69, 70.8, 295.11, 64.71, 229.37, 87.84, 190.41, 113.41, 174.58, 118.28, 157.53, 112.19, 152.66, 92.71, 155.1, 95.15, 138.05, 132.89, 99.09, 157.24, 95.44, 182.81, 94.22, 190.11, 105.18, 181.59, 112.49, 181.59, 129.53, 175.5, 142.92, 173.07, 161.19, 176.72, 185.54, 187.68, 257.37, 180.37, 274.42, 198.64, 352.34, 196.2, 387.65, 190.11, 429.04, 187.68, 476.52, 175.5, 466.78, 171.85, 421.74, 137.76, 392.52, 97.58, 363.29]], "area": 29889.28865, "iscrowd": 0, "image_id": 104692, "bbox": [64.71, 94.22, 133.93, 382.3], "category_id": 16, "id": 39433, "split": "val", "sentences": [{"tokens": ["a", "baby", "bird", "beside", "its", "mother"], "raw": "A baby bird beside its mother.", "sent_id": 74691, "sent": "a baby bird beside its mother"}, {"tokens": ["baby", "bird", "being", "fed", "by", "mother"], "raw": "baby bird being fed by mother", "sent_id": 74692, "sent": "baby bird being fed by mother"}], "file_name": "COCO_train2014_000000104692_39433.jpg", "ann_id": 39433, "sent_ids": [74691, 74692], "ref_id": 33674}, {"segmentation": [[497.41, 269.34, 511.15, 274.68, 517.26, 278.5, 532.53, 296.82, 517.26, 311.32, 523.37, 358.65, 531.76, 396.05, 545.5, 425.06, 550.85, 441.09, 543.21, 464.75, 524.13, 451.01, 529.47, 480.02, 517.26, 483.07, 495.12, 481.54, 490.54, 457.88, 486.73, 434.22, 486.73, 429.64, 483.67, 447.19, 474.51, 451.77, 452.38, 436.51, 470.7, 430.4, 476.04, 406.74, 475.28, 383.84, 472.99, 353.3, 476.8, 331.17, 479.86, 306.74, 475.28, 285.37, 476.04, 273.15, 484.44, 272.39]], "area": 11087.305950000002, "iscrowd": 0, "image_id": 195861, "bbox": [452.38, 269.34, 98.47, 213.73], "category_id": 2, "id": 128288, "split": "val", "sentences": [{"tokens": ["the", "bicycle", "of", "the", "man", "with", "a", "black", "coat", "and", "grey", "pants"], "raw": "The bicycle of the man with a black coat and grey pants", "sent_id": 74758, "sent": "the bicycle of the man with a black coat and grey pants"}, {"tokens": ["the", "back", "tire", "on", "the", "bicycle"], "raw": "The back tire on the bicycle", "sent_id": 74759, "sent": "the back tire on the bicycle"}], "file_name": "COCO_train2014_000000195861_128288.jpg", "ann_id": 128288, "sent_ids": [74758, 74759], "ref_id": 33697}, {"segmentation": [[113.38, 219.95, 129.16, 222.13, 140.59, 225.94, 160.73, 236.28, 179.23, 243.9, 195.01, 249.89, 201.54, 255.87, 206.99, 259.68, 214.61, 265.13, 215.7, 268.39, 212.97, 276.55, 213.52, 283.09, 215.15, 287.98, 217.33, 294.51, 218.42, 299.96, 221.68, 304.31, 222.77, 311.93, 225.49, 319.55, 227.12, 324.99, 227.12, 332.07, 224.95, 339.69, 225.49, 348.4, 225.49, 350.57, 217.33, 347.31, 209.16, 341.32, 197.19, 335.33, 186.85, 324.45, 169.43, 312.47, 161.67, 307.49, 147.95, 300.67, 141.13, 291.25, 128.62, 280.91, 120.55, 279.8, 111.98, 271.03, 102.5, 263.02, 96.43, 258.9, 89.44, 252.45, 91.06, 237.91, 93.78, 228.66, 95.96, 223.22, 97.59, 221.04, 102.49, 218.86, 107.93, 217.78]], "area": 8640.648200000001, "iscrowd": 0, "image_id": 470912, "bbox": [89.44, 217.78, 137.68, 132.79], "category_id": 75, "id": 1109830, "split": "val", "sentences": [{"tokens": ["the", "black", "remote", "next", "to", "the", "kitten"], "raw": "The black remote next to the kitten.", "sent_id": 74820, "sent": "the black remote next to the kitten"}, {"tokens": ["remote", "controller", "with", "a", "green", "button"], "raw": "remote controller with a green button", "sent_id": 74821, "sent": "remote controller with a green button"}], "file_name": "COCO_train2014_000000470912_1109830.jpg", "ann_id": 1109830, "sent_ids": [74820, 74821], "ref_id": 33718}, {"segmentation": [[416.42, 71.06, 423.9, 91.01, 435.12, 103.48, 433.87, 114.7, 436.36, 129.66, 402.7, 127.17, 369.04, 133.4, 351.58, 128.42, 311.69, 140.88, 302.96, 158.34, 300.47, 183.27, 295.48, 195.74, 233.14, 192.0, 231.9, 173.3, 221.79, 157.24, 221.79, 149.46, 213.05, 143.64, 203.34, 143.64, 195.56, 151.41, 194.59, 158.21, 180.99, 159.18, 161.56, 118.38, 153.35, 112.21, 144.62, 14.96, 249.35, 2.49, 306.7, 4.99, 374.03, 52.36], [130.91, 14.96, 3.74, 21.19, 1.25, 182.03, 12.47, 182.03, 26.18, 199.48, 42.39, 205.71, 64.83, 201.97, 71.06, 182.03, 58.6, 142.13, 71.06, 114.7, 114.7, 108.47, 123.43, 100.99, 132.16, 100.99]], "area": 53148.9449, "iscrowd": 0, "image_id": 288310, "bbox": [1.25, 2.49, 435.11, 203.22], "category_id": 3, "id": 2168879, "split": "val", "sentences": [{"tokens": ["a", "silver", "and", "blue", "van", "is", "parked", "next", "to", "a", "motorcycle"], "raw": "A silver and blue van is parked next to a motorcycle.", "sent_id": 74885, "sent": "a silver and blue van is parked next to a motorcycle"}, {"tokens": ["a", "ash", "color", "van", "named", "'", "service", "department", "'", "is", "parked", "in", "a", "parking", "bay"], "raw": "A ash color van named 'service department' is parked in a parking bay", "sent_id": 74886, "sent": "a ash color van named ' service department ' is parked in a parking bay"}], "file_name": "COCO_train2014_000000288310_2168879.jpg", "ann_id": 2168879, "sent_ids": [74885, 74886], "ref_id": 33743}, {"segmentation": [[36.46, 419.0, 36.46, 371.99, 33.58, 361.44, 24.94, 356.65, 24.94, 356.65, 20.15, 355.69, 34.54, 319.23, 42.21, 306.76, 66.2, 283.73, 51.81, 265.51, 47.01, 249.2, 56.6, 236.72, 74.83, 230.01, 85.38, 231.93, 96.9, 259.75, 101.69, 273.18, 125.68, 273.18, 142.95, 285.65, 161.17, 330.74, 148.7, 333.62, 152.54, 373.91, 147.74, 403.65, 151.58, 419.0]], "area": 17893.73635, "iscrowd": 0, "image_id": 471136, "bbox": [20.15, 230.01, 141.02, 188.99], "category_id": 1, "id": 477222, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "jeans", "smiling"], "raw": "A man in a white shirt and jeans smiling", "sent_id": 74955, "sent": "a man in a white shirt and jeans smiling"}, {"tokens": ["the", "smiling", "man", "in", "white"], "raw": "The smiling man in white.", "sent_id": 74956, "sent": "the smiling man in white"}], "file_name": "COCO_train2014_000000471136_477222.jpg", "ann_id": 477222, "sent_ids": [74955, 74956], "ref_id": 33773}, {"segmentation": [[250.67, 153.35, 242.67, 60.01, 389.33, 61.35, 378.67, 157.35, 372.0, 156.01, 372.0, 153.35, 358.67, 152.01, 358.67, 158.68, 352.0, 161.35, 349.33, 150.68, 332.0, 153.35, 329.33, 164.01, 325.33, 164.01, 322.67, 154.68, 306.67, 156.01, 306.67, 158.68, 300.0, 154.68, 297.33, 154.68, 284.0, 153.35, 276.0, 150.68, 257.33, 152.01]], "area": 12877.086650000003, "iscrowd": 0, "image_id": 43655, "bbox": [242.67, 60.01, 146.66, 104.0], "category_id": 62, "id": 2192057, "split": "val", "sentences": [{"tokens": ["a", "chair", "sits", "empty", "behind", "two", "cats"], "raw": "A chair sits empty behind two cats.", "sent_id": 75034, "sent": "a chair sits empty behind two cats"}, {"tokens": ["the", "chair", "behind", "the", "two", "cats"], "raw": "The chair behind the two cats", "sent_id": 75035, "sent": "the chair behind the two cats"}], "file_name": "COCO_train2014_000000043655_2192057.jpg", "ann_id": 2192057, "sent_ids": [75034, 75035], "ref_id": 33804}, {"segmentation": [[104.91, 148.07, 85.78, 155.34, 89.22, 120.9, 95.35, 101.01, 106.44, 90.3, 124.04, 79.58, 121.75, 71.55, 125.57, 64.28, 137.43, 60.83, 150.82, 63.13, 154.27, 79.58, 158.48, 89.53, 170.72, 101.77, 161.54, 110.19, 161.16, 118.99, 174.16, 111.72, 179.52, 117.84, 178.37, 124.73, 155.8, 131.24, 150.06, 130.09, 147.38, 138.51, 127.1, 139.65, 121.75, 136.59, 106.82, 138.89], [86.55, 163.76, 88.84, 180.21, 127.87, 191.69, 115.24, 215.03, 131.69, 236.45, 128.25, 187.86, 140.11, 183.65, 94.58, 162.99, 86.55, 161.46]], "area": 5765.368099999999, "iscrowd": 0, "image_id": 321539, "bbox": [85.78, 60.83, 93.74, 175.62], "category_id": 1, "id": 508308, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "black", "shirt", ",", "looking", "overwhelmed", ",", "as", "he", "gazes", "at", "his", "computer", "screen"], "raw": "A man in a black shirt, looking overwhelmed, as he gazes at his computer screen.", "sent_id": 75089, "sent": "a man in a black shirt , looking overwhelmed , as he gazes at his computer screen"}, {"tokens": ["man", "with", "a", "black", "color", "shirt", "looking", "at", "laptop"], "raw": "man with a black color shirt looking at laptop", "sent_id": 75090, "sent": "man with a black color shirt looking at laptop"}, {"tokens": ["the", "man", "in", "the", "black", "shirt", "looking", "at", "a", "laptop"], "raw": "The man in the black shirt looking at a laptop.", "sent_id": 75091, "sent": "the man in the black shirt looking at a laptop"}], "file_name": "COCO_train2014_000000321539_508308.jpg", "ann_id": 508308, "sent_ids": [75089, 75090, 75091], "ref_id": 33826}, {"segmentation": [[627.5, 471.88, 638.75, 316.88, 635.0, 300.63, 623.75, 290.63, 601.25, 278.13, 541.25, 278.13, 516.25, 278.13, 530.0, 298.13, 546.25, 308.13, 550.0, 323.13, 547.5, 341.88, 577.5, 361.88, 583.75, 394.38, 580.0, 415.63, 582.5, 443.13, 565.0, 460.63, 562.5, 468.13]], "area": 13109.375, "iscrowd": 0, "image_id": 496732, "bbox": [516.25, 278.13, 122.5, 193.75], "category_id": 62, "id": 1934847, "split": "val", "sentences": [{"tokens": ["the", "seat", "the", "man", "eating", "the", "sandwich", "is", "sitting", "on"], "raw": "The seat the man eating the sandwich is sitting on.", "sent_id": 75096, "sent": "the seat the man eating the sandwich is sitting on"}, {"tokens": ["a", "green", "bench", "with", "a", "older", "man", "sitting", "on", "it", "eaating", "a", "sandwich"], "raw": "a green bench with a older man sitting on it eaating a sandwich", "sent_id": 75097, "sent": "a green bench with a older man sitting on it eaating a sandwich"}], "file_name": "COCO_train2014_000000496732_1934847.jpg", "ann_id": 1934847, "sent_ids": [75096, 75097], "ref_id": 33829}, {"segmentation": [[4.51, 529.73, 93.15, 487.66, 117.18, 457.62, 138.22, 457.62, 169.77, 469.63, 321.5, 460.62, 423.66, 474.14, 424.0, 630.38, 422.16, 630.38, 237.37, 630.38, 3.0, 631.89]], "area": 65477.22325, "iscrowd": 0, "image_id": 298481, "bbox": [3.0, 457.62, 421.0, 174.27], "category_id": 67, "id": 118239, "split": "val", "sentences": [{"tokens": ["a", "red", "table"], "raw": "A red table", "sent_id": 75163, "sent": "a red table"}, {"tokens": ["the", "red", "table", "fartherest", "away", "from", "the", "windows"], "raw": "THe red table fartherest away from the windows.", "sent_id": 75164, "sent": "the red table fartherest away from the windows"}], "file_name": "COCO_train2014_000000298481_118239.jpg", "ann_id": 118239, "sent_ids": [75163, 75164], "ref_id": 33856}, {"segmentation": [[194.79, 419.32, 190.95, 326.25, 223.58, 335.84, 248.52, 322.41, 260.04, 307.06, 258.12, 275.39, 219.74, 209.18, 215.9, 186.15, 202.47, 165.04, 173.68, 153.53, 166.0, 154.49, 166.0, 157.37, 133.38, 156.41, 133.38, 129.54, 118.98, 120.9, 109.39, 119.94, 91.16, 95.0, 76.76, 89.24, 46.06, 98.83, 32.62, 111.31, 32.62, 137.22, 26.87, 154.49, 25.91, 169.84, 34.54, 188.07, 48.94, 198.63, 46.06, 209.18, 28.79, 212.06, 10.56, 214.94, 0.0, 218.78, 0.0, 315.69, 17.27, 339.68, 9.6, 417.4, 8.64, 420.28]], "area": 60227.10129999999, "iscrowd": 0, "image_id": 340129, "bbox": [0.0, 89.24, 260.04, 331.04], "category_id": 1, "id": 457659, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "man", "taking", "a", "pitcure", "of", "two", "other", "men"], "raw": "The back of a man taking a pitcure of two other men.", "sent_id": 75182, "sent": "the back of a man taking a pitcure of two other men"}, {"tokens": ["a", "man", "wearing", "a", "white", "hat", "and", "holding", "a", "mobile"], "raw": "A man wearing a white hat and holding a mobile.", "sent_id": 75183, "sent": "a man wearing a white hat and holding a mobile"}], "file_name": "COCO_train2014_000000340129_457659.jpg", "ann_id": 457659, "sent_ids": [75182, 75183], "ref_id": 33862}, {"segmentation": [[8.66, 384.68, 73.09, 376.03, 81.75, 409.69, 100.98, 418.34, 182.73, 418.34, 202.92, 392.38, 203.88, 358.72, 204.84, 341.41, 187.53, 294.28, 193.3, 259.66, 191.38, 244.27, 181.76, 201.96, 196.19, 185.61, 178.88, 185.61, 189.46, 175.99, 208.69, 160.61, 214.46, 147.14, 247.16, 149.07, 288.51, 162.53, 312.56, 204.84, 297.17, 243.31, 307.75, 248.12, 335.64, 225.04, 335.64, 215.42, 349.1, 214.46, 356.8, 231.77, 370.26, 241.39, 376.99, 218.31, 376.99, 201.0, 356.8, 182.73, 349.1, 153.87, 339.48, 150.99, 338.52, 127.91, 145.22, 135.6, 50.01, 194.27, 0.0, 199.07], [416.42, 147.14, 413.54, 184.65, 446.23, 199.07, 457.77, 240.43, 478.93, 296.21, 493.36, 286.59, 496.24, 261.59, 491.43, 255.82, 486.63, 221.19, 435.66, 139.45]], "area": 58246.79009999999, "iscrowd": 0, "image_id": 555120, "bbox": [0.0, 127.91, 496.24, 290.43], "category_id": 3, "id": 1192536, "split": "val", "sentences": [{"tokens": ["blue", "car", "behind", "girls", "playing"], "raw": "blue car behind girls playing", "sent_id": 75184, "sent": "blue car behind girls playing"}, {"tokens": ["the", "blue", "car", "in", "the", "back"], "raw": "the blue car in the back", "sent_id": 75185, "sent": "the blue car in the back"}], "file_name": "COCO_train2014_000000555120_1192536.jpg", "ann_id": 1192536, "sent_ids": [75184, 75185], "ref_id": 33863}, {"segmentation": [[188.02, 305.89, 187.81, 301.53, 197.58, 294.05, 196.96, 288.23, 203.19, 282.83, 225.84, 270.15, 224.8, 264.96, 225.42, 258.31, 229.58, 243.76, 248.07, 229.22, 261.16, 217.79, 281.11, 193.89, 288.39, 185.37, 294.0, 179.97, 293.37, 176.85, 300.44, 163.97, 306.05, 149.01, 312.28, 138.83, 322.26, 135.5, 355.09, 114.1, 361.94, 110.57, 359.03, 102.46, 356.75, 96.23, 359.03, 93.94, 362.15, 61.53, 367.76, 51.55, 390.41, 37.22, 408.28, 36.18, 420.75, 37.84, 430.1, 43.45, 439.45, 51.55, 439.24, 73.16, 435.29, 85.42, 434.26, 98.72, 428.85, 110.78, 430.72, 113.68, 444.44, 114.72, 459.4, 118.46, 466.46, 123.87, 467.92, 128.02, 474.98, 142.36, 478.72, 152.54, 478.93, 168.13, 479.97, 203.45, 480.0, 210.93, 480.0, 249.79, 480.0, 252.28, 477.68, 278.26, 472.91, 282.83, 466.05, 283.66, 454.62, 283.45, 448.8, 281.58, 445.89, 281.16, 441.94, 278.88, 438.83, 274.52, 436.33, 271.81, 438.83, 266.62, 442.78, 263.09, 446.1, 256.85, 447.35, 252.9, 447.76, 234.0, 447.55, 233.58, 448.8, 221.74, 447.76, 218.83, 449.01, 199.5, 446.72, 183.5, 444.44, 177.06, 433.42, 159.19, 426.78, 152.54, 419.71, 148.8, 403.71, 148.8, 385.63, 157.32, 365.06, 166.67, 356.75, 181.84, 353.84, 190.78, 352.59, 200.75, 355.09, 212.39, 358.62, 219.45, 362.98, 238.36, 368.18, 245.01, 370.05, 248.13, 371.09, 250.2, 371.5, 250.83, 372.33, 253.32, 377.74, 260.39, 365.06, 263.09, 348.23, 260.8, 340.54, 262.67, 331.61, 264.13, 328.49, 263.92, 327.24, 257.48, 327.45, 251.45, 323.29, 247.92, 323.29, 242.72, 324.96, 240.23, 326.0, 230.26, 324.13, 224.02, 323.09, 219.24, 323.29, 213.01, 318.31, 221.32, 311.66, 232.54, 300.02, 245.42, 294.0, 249.37, 291.71, 252.07, 273.63, 272.02, 267.81, 287.81, 266.15, 293.01, 262.41, 295.09, 244.54, 292.39, 239.35, 310.05, 238.93, 319.61, 235.19, 324.18, 231.66, 327.5, 226.46, 322.93, 228.54, 311.5, 228.54, 304.85, 220.23, 297.37, 210.05, 297.37, 192.39, 303.81]], "area": 27574.6005, "iscrowd": 0, "image_id": 340535, "bbox": [187.81, 36.18, 292.19, 291.32], "category_id": 1, "id": 2157682, "split": "val", "sentences": [{"tokens": ["a", "man", "pouring", "wine", "in", "a", "white", "shirt"], "raw": "A man pouring wine in a white shirt.", "sent_id": 75342, "sent": "a man pouring wine in a white shirt"}, {"tokens": ["man", "with", "glasses", "pouring", "a", "bottle", "of", "wine"], "raw": "man with glasses pouring a bottle of wine", "sent_id": 75343, "sent": "man with glasses pouring a bottle of wine"}], "file_name": "COCO_train2014_000000340535_2157682.jpg", "ann_id": 2157682, "sent_ids": [75342, 75343], "ref_id": 33919}, {"segmentation": [[122.64, 343.49, 143.72, 320.19, 173.13, 342.38, 178.68, 351.26, 251.37, 365.13, 266.9, 358.48, 294.65, 360.14, 302.97, 367.91, 297.98, 395.65, 291.87, 425.0, 222.51, 425.0, 186.45, 411.19, 144.28, 380.67, 127.63, 346.82, 127.08, 345.16]], "area": 10119.796750000003, "iscrowd": 0, "image_id": 155549, "bbox": [122.64, 320.19, 180.33, 104.81], "category_id": 63, "id": 116846, "split": "val", "sentences": [{"tokens": ["a", "red", "recliner", "viewed", "through", "a", "fisheye", "lense"], "raw": "A red recliner viewed through a fisheye lense.", "sent_id": 75362, "sent": "a red recliner viewed through a fisheye lense"}, {"tokens": ["a", "single", "person", "arm", "chair", "in", "a", "living", "room", "setting", "with", "no", "one", "sitting", "in", "it"], "raw": "A single person arm chair in a living room setting with no one sitting in it", "sent_id": 75363, "sent": "a single person arm chair in a living room setting with no one sitting in it"}], "file_name": "COCO_train2014_000000155549_116846.jpg", "ann_id": 116846, "sent_ids": [75362, 75363], "ref_id": 33927}, {"segmentation": [[109.21, 239.21, 115.69, 219.8, 135.1, 181.78, 132.67, 147.8, 148.04, 109.78, 174.74, 87.93, 190.11, 82.27, 215.19, 83.89, 228.13, 83.89, 246.74, 83.08, 254.02, 79.03, 286.38, 74.18, 287.19, 68.52, 303.37, 68.52, 323.6, 75.8, 332.49, 87.12, 349.48, 103.3, 358.38, 112.2, 361.62, 124.34, 368.09, 130.81, 368.09, 130.81, 376.99, 136.47, 390.74, 138.9, 392.36, 139.71, 394.79, 141.33, 372.13, 144.56, 368.9, 144.56, 366.47, 149.42, 365.66, 160.74, 365.66, 166.4, 365.66, 175.3, 368.9, 196.34, 370.52, 198.76, 372.94, 202.81, 372.13, 207.66, 364.85, 210.9, 349.48, 198.76, 343.82, 181.78, 341.39, 164.79, 337.35, 155.08, 317.12, 146.99, 307.42, 144.56, 295.28, 152.65, 287.19, 162.36, 283.15, 175.3, 278.29, 183.39, 266.97, 192.29, 261.3, 194.72, 242.7, 201.19, 234.61, 193.1, 220.85, 214.94, 218.43, 228.7, 215.19, 244.07, 207.1, 252.16, 190.11, 252.16, 188.49, 233.55, 191.73, 219.8, 180.4, 212.52, 171.51, 199.57, 160.18, 198.76, 150.47, 211.71, 132.67, 243.26, 130.25, 244.07]], "area": 26190.354049999998, "iscrowd": 0, "image_id": 550972, "bbox": [109.21, 68.52, 285.58, 183.64], "category_id": 22, "id": 581482, "split": "val", "sentences": [{"tokens": ["elephant", "to", "the", "left"], "raw": "elephant to the left", "sent_id": 75364, "sent": "elephant to the left"}, {"tokens": ["elephant", "on", "left", "side"], "raw": "elephant on left side", "sent_id": 75365, "sent": "elephant on left side"}], "file_name": "COCO_train2014_000000550972_581482.jpg", "ann_id": 581482, "sent_ids": [75364, 75365], "ref_id": 33928}, {"segmentation": [[439.01, 211.42, 446.56, 186.61, 439.01, 165.03, 445.48, 147.78, 469.21, 143.46, 480.0, 152.09, 484.31, 175.82, 497.26, 183.37, 505.89, 190.92, 512.36, 204.94, 511.28, 229.75, 503.73, 235.15, 500.49, 241.62, 504.81, 252.4, 512.36, 264.27, 513.44, 307.42, 516.67, 355.96, 484.31, 363.51, 480.0, 385.08, 473.53, 409.89, 463.82, 406.65, 458.43, 405.57, 446.56, 405.57, 435.78, 405.57, 421.75, 401.26, 421.75, 391.55, 424.99, 390.47, 433.62, 392.63, 443.33, 389.39, 445.48, 385.08, 447.64, 376.45, 441.17, 363.51, 428.22, 346.25, 426.07, 336.54, 436.85, 290.16, 442.25, 263.19, 447.64, 245.93, 448.72, 235.15, 439.01, 241.62, 436.85, 248.09, 428.22, 241.62, 432.54, 230.83, 439.01, 209.26]], "area": 16659.101349999994, "iscrowd": 0, "image_id": 174876, "bbox": [421.75, 143.46, 94.92, 266.43], "category_id": 1, "id": 483118, "split": "val", "sentences": [{"tokens": ["woman", "standing", "at", "sink", "in", "grey", "dress"], "raw": "woman standing at sink in grey dress", "sent_id": 75379, "sent": "woman standing at sink in grey dress"}, {"tokens": ["this", "is", "a", "woman", "in", "a", "grey", "dress"], "raw": "this is a woman in a grey dress", "sent_id": 75380, "sent": "this is a woman in a grey dress"}], "file_name": "COCO_train2014_000000174876_483118.jpg", "ann_id": 483118, "sent_ids": [75379, 75380], "ref_id": 33933}, {"segmentation": [[354.97, 222.78, 375.46, 222.21, 381.72, 194.33, 387.98, 172.13, 401.63, 164.74, 399.93, 121.49, 396.51, 103.28, 389.11, 97.02, 387.41, 85.64, 387.41, 82.79, 378.87, 88.48, 376.03, 86.21, 375.46, 79.95, 368.63, 75.4, 359.52, 80.52, 362.37, 90.76, 354.4, 93.04, 346.44, 91.9, 341.88, 89.62, 345.3, 97.02, 333.35, 106.69, 331.07, 126.04, 325.95, 136.28, 325.95, 162.46, 334.49, 172.7, 339.61, 181.81, 345.3, 197.74, 351.56, 216.52, 353.26, 224.49]], "area": 7516.599600000002, "iscrowd": 0, "image_id": 236406, "bbox": [325.95, 75.4, 75.68, 149.09], "category_id": 24, "id": 592191, "split": "val", "sentences": [{"tokens": ["the", "back", "end", "of", "a", "zebra", "to", "the", "right", "of", "another", "zebra"], "raw": "The back end of a zebra to the right of another zebra", "sent_id": 75420, "sent": "the back end of a zebra to the right of another zebra"}, {"tokens": ["zebra", "walking", "towards", "illuminated", "part", "of", "wall"], "raw": "zebra walking towards illuminated part of wall", "sent_id": 75421, "sent": "zebra walking towards illuminated part of wall"}], "file_name": "COCO_train2014_000000236406_592191.jpg", "ann_id": 592191, "sent_ids": [75420, 75421], "ref_id": 33949}, {"segmentation": [[571.19, 395.44, 586.57, 391.05, 588.77, 353.7, 579.98, 316.35, 539.34, 241.66, 539.34, 226.28, 525.06, 220.79, 477.82, 220.79, 488.81, 242.76, 474.53, 275.71, 455.85, 282.3, 438.28, 310.86, 437.18, 317.45, 419.61, 324.04, 408.62, 346.01, 439.38, 365.78, 450.36, 365.78, 483.32, 365.78, 472.33, 389.95, 509.68, 388.85, 543.73, 371.27]], "area": 18600.15165, "iscrowd": 0, "image_id": 327209, "bbox": [408.62, 220.79, 180.15, 174.65], "category_id": 1, "id": 2150435, "split": "val", "sentences": [{"tokens": ["a", "young", "girl", "wearing", "brown", "holding", "pink", "phone"], "raw": "a young girl wearing brown holding pink phone", "sent_id": 75436, "sent": "a young girl wearing brown holding pink phone"}, {"tokens": ["a", "girl", "in", "a", "black", "jacket", "sitting", "at", "a", "table"], "raw": "A girl in a black jacket sitting at a table.", "sent_id": 75437, "sent": "a girl in a black jacket sitting at a table"}], "file_name": "COCO_train2014_000000327209_2150435.jpg", "ann_id": 2150435, "sent_ids": [75436, 75437], "ref_id": 33953}, {"segmentation": [[103.32, 130.87, 67.8, 88.9, 43.05, 75.98, 2.15, 67.37, 0.0, 71.68, 0.0, 473.11, 5.38, 480.0, 328.25, 480.0, 573.63, 480.0, 557.49, 454.82, 548.88, 435.44, 544.57, 393.47, 528.43, 368.72, 517.67, 362.26, 496.14, 347.19, 474.62, 341.81, 454.17, 349.35, 461.7, 380.56, 473.54, 385.94, 501.52, 398.85, 498.3, 404.23, 453.09, 411.77, 432.65, 411.77, 416.5, 415.0, 425.11, 398.85, 422.96, 390.24, 414.35, 377.33, 407.89, 368.72, 398.21, 373.02, 393.9, 387.01, 405.74, 416.07, 404.66, 420.38, 295.96, 459.12, 242.15, 476.34, 270.13, 408.54, 299.19, 361.18, 333.63, 321.36, 350.85, 288.0, 339.01, 261.09, 320.72, 243.87, 307.8, 253.56, 300.27, 240.65, 274.44, 256.79, 260.45, 270.78, 247.53, 286.92, 244.3, 327.82, 236.77, 353.65, 229.24, 361.18, 209.87, 338.58, 208.79, 315.98, 194.8, 288.0, 176.5, 267.55, 152.83, 249.26, 137.76, 238.49, 131.3, 202.98, 124.84, 170.69, 124.84, 158.85, 130.22, 149.17, 125.92, 140.56, 118.39, 136.25, 113.0, 136.25]], "area": 103341.4742, "iscrowd": 0, "image_id": 550760, "bbox": [0.0, 67.37, 573.63, 412.63], "category_id": 1, "id": 456926, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "glasses", "holding", "a", "boy"], "raw": "a man with glasses holding a boy", "sent_id": 75452, "sent": "a man with glasses holding a boy"}, {"tokens": ["the", "man", "holding", "the", "child"], "raw": "the man holding the child", "sent_id": 75453, "sent": "the man holding the child"}], "file_name": "COCO_train2014_000000550760_456926.jpg", "ann_id": 456926, "sent_ids": [75452, 75453], "ref_id": 33958}, {"segmentation": [[160.79, 315.75, 182.5, 293.44, 185.52, 287.41, 186.12, 266.31, 181.9, 251.24, 181.9, 243.4, 176.47, 216.27, 176.47, 201.79, 182.5, 192.75, 195.76, 186.73, 196.37, 174.67, 205.41, 169.84, 213.85, 170.44, 218.68, 184.31, 210.84, 199.99, 214.45, 210.24, 220.49, 213.85, 224.71, 232.55, 220.49, 245.21, 241.59, 273.54, 230.13, 292.23, 223.5, 299.47, 227.11, 304.29, 223.5, 306.71, 198.78, 306.1, 199.39, 300.07, 219.88, 277.76, 211.44, 272.34, 190.94, 306.1, 175.27, 321.18, 176.47, 335.04, 162.0, 330.22, 155.37, 321.18]], "area": 5800.971000000002, "iscrowd": 0, "image_id": 25455, "bbox": [155.37, 169.84, 86.22, 165.2], "category_id": 1, "id": 440922, "split": "val", "sentences": [{"tokens": ["the", "batter", "with", "the", "blue", "helmet"], "raw": "The batter with the blue helmet", "sent_id": 75454, "sent": "the batter with the blue helmet"}, {"tokens": ["a", "baseball", "player", "dodging", "an", "incoming", "ball"], "raw": "A baseball player dodging an incoming ball", "sent_id": 75455, "sent": "a baseball player dodging an incoming ball"}], "file_name": "COCO_train2014_000000025455_440922.jpg", "ann_id": 440922, "sent_ids": [75454, 75455], "ref_id": 33959}, {"segmentation": [[497.88, 229.06, 500.72, 244.21, 498.83, 272.61, 497.88, 272.61, 497.88, 281.12, 494.1, 286.8, 492.2, 288.7, 491.26, 296.27, 489.37, 302.9, 486.53, 307.63, 483.69, 318.04, 478.95, 324.67, 470.43, 329.4, 466.65, 329.4, 462.86, 329.4, 457.18, 329.4, 461.92, 334.13, 454.34, 335.08, 442.98, 336.02, 437.31, 338.86, 428.98, 326.4, 428.98, 317.93, 428.98, 311.06, 494.02, 223.81, 498.25, 232.27], [407.0, 260.52, 412.84, 260.52, 420.14, 272.2, 424.52, 271.23, 427.92, 267.82, 430.36, 264.41, 430.84, 263.93, 450.93, 231.24, 450.04, 224.74, 451.82, 222.08, 456.54, 220.9, 460.09, 219.72, 460.38, 217.95, 458.91, 214.7, 458.61, 212.04, 458.61, 210.27, 458.61, 209.38, 456.65, 205.14, 455.25, 200.95, 454.2, 194.32, 454.55, 190.83, 456.65, 188.04, 455.25, 180.72, 457.69, 173.04, 459.44, 169.9, 461.18, 168.51, 462.23, 167.81, 465.02, 167.11, 473.04, 166.76, 476.18, 168.86, 480.02, 170.6, 489.09, 177.93, 490.49, 182.11, 491.18, 186.3, 492.23, 192.58, 492.58, 197.81, 492.23, 201.65, 491.53, 203.04, 490.49, 205.14, 485.25, 210.72, 424.9, 283.98, 423.15, 281.19, 421.41, 280.84, 416.53, 281.19, 414.43, 281.89], [432.22, 289.91, 489.09, 218.74, 491.53, 221.19, 444.43, 284.68, 439.9, 285.38, 436.06, 287.12, 433.27, 289.56]], "area": 7217.138599999997, "iscrowd": 0, "image_id": 54282, "bbox": [407.0, 166.76, 93.72, 172.1], "category_id": 1, "id": 445847, "split": "val", "sentences": [{"tokens": ["a", "young", "man", "wearing", "black", "smiling", "at", "the", "camera"], "raw": "A young man wearing black smiling at the camera.", "sent_id": 75551, "sent": "a young man wearing black smiling at the camera"}, {"tokens": ["a", "person", "in", "gray", "clothes"], "raw": "a person in gray clothes", "sent_id": 75552, "sent": "a person in gray clothes"}], "file_name": "COCO_train2014_000000054282_445847.jpg", "ann_id": 445847, "sent_ids": [75551, 75552], "ref_id": 33996}, {"segmentation": [[303.75, 492.32, 295.79, 492.32, 294.34, 482.19, 294.34, 453.97, 289.28, 406.93, 284.94, 369.31, 290.73, 351.94, 285.66, 321.55, 270.47, 299.84, 263.95, 300.57, 259.61, 287.54, 248.76, 275.97, 252.38, 273.07, 259.61, 277.41, 261.06, 280.31, 261.78, 278.86, 260.34, 268.01, 265.4, 268.01, 269.02, 273.8, 270.47, 278.14, 276.98, 278.86, 277.7, 290.44, 297.24, 312.87, 307.37, 347.6, 333.42, 364.24, 339.21, 370.75, 339.21, 401.14, 338.48, 419.23, 338.48, 444.56, 342.1, 474.23, 344.27, 485.8, 341.38, 490.87, 334.86, 486.53, 334.14, 463.37, 332.69, 442.39, 331.25, 435.88, 327.63, 423.58, 323.29, 406.21, 330.52, 440.94, 325.46, 448.9, 328.35, 480.74, 325.51, 488.2, 319.9, 485.71, 321.97, 473.66, 323.22, 452.46, 316.57, 430.44, 315.74, 442.07, 314.08, 456.62, 314.91, 471.16, 318.23, 481.35, 316.99, 492.15, 309.3, 489.66, 309.92, 467.22, 309.3, 446.02, 304.94, 432.93, 305.97, 423.79, 306.18, 419.63, 301.2, 398.65, 298.91, 415.89, 300.57, 433.14, 299.74, 440.0, 298.7, 446.23, 299.74, 454.13, 303.27, 478.23, 301.4, 485.09]], "area": 6644.6158, "iscrowd": 0, "image_id": 566847, "bbox": [248.76, 268.01, 95.51, 224.31], "category_id": 25, "id": 2198714, "split": "val", "sentences": [{"tokens": ["a", "giraffee", "with", "the", "old", "giraffee", "in", "the", "farm"], "raw": "A giraffee with the old giraffee in the farm", "sent_id": 75686, "sent": "a giraffee with the old giraffee in the farm"}, {"tokens": ["the", "baby", "giraffe"], "raw": "The baby giraffe", "sent_id": 75687, "sent": "the baby giraffe"}], "file_name": "COCO_train2014_000000566847_2198714.jpg", "ann_id": 2198714, "sent_ids": [75686, 75687], "ref_id": 34042}, {"segmentation": [[332.18, 323.57, 332.18, 280.49, 339.84, 242.2, 337.93, 212.52, 338.89, 189.55, 362.82, 177.1, 361.86, 157.96, 370.48, 141.68, 373.35, 136.89, 381.96, 130.19, 403.02, 137.85, 407.81, 150.3, 410.68, 172.31, 407.81, 179.97, 417.38, 182.84, 421.21, 185.72, 437.49, 204.86, 458.55, 232.62, 489.18, 273.79, 512.16, 316.87, 504.5, 314.95, 483.44, 305.38, 478.65, 298.68, 448.02, 256.56, 417.38, 238.37, 417.38, 241.24, 415.47, 260.39, 415.47, 298.68, 415.47, 301.55, 412.6, 308.25, 407.81, 308.25, 371.43, 324.53, 341.76, 314.95]], "area": 16302.666050000002, "iscrowd": 0, "image_id": 444033, "bbox": [332.18, 130.19, 179.98, 194.34], "category_id": 1, "id": 438221, "split": "val", "sentences": [{"tokens": ["woman", "with", "hands", "on", "the", "pizza", "box"], "raw": "Woman with hands on the pizza box.", "sent_id": 75741, "sent": "woman with hands on the pizza box"}, {"tokens": ["woman", "standing", "behind", "multiple", "boxes", "of", "pizza", "reaching", "for", "3", "/", "8", "of", "a", "pepperoni", "pizza"], "raw": "Woman standing behind multiple boxes of pizza reaching for 3/8 of a pepperoni pizza", "sent_id": 75742, "sent": "woman standing behind multiple boxes of pizza reaching for 3 / 8 of a pepperoni pizza"}], "file_name": "COCO_train2014_000000444033_438221.jpg", "ann_id": 438221, "sent_ids": [75741, 75742], "ref_id": 34063}, {"segmentation": [[318.87, 490.37, 311.83, 534.66, 335.98, 541.7, 361.15, 533.65, 378.26, 513.52, 386.31, 472.25, 338.0, 398.77, 306.79, 362.53, 293.71, 322.27, 254.45, 290.06, 208.15, 284.02, 147.75, 294.08, 125.61, 324.28, 118.56, 348.44, 64.21, 441.04, 73.26, 447.08, 57.16, 483.32, 75.28, 485.33, 84.34, 505.47, 110.51, 508.49, 132.65, 508.49, 171.91, 497.41, 203.11, 504.46, 221.23, 502.45, 229.29, 516.54, 241.36, 529.62, 289.68, 527.61, 305.79, 500.43, 314.85, 489.36]], "area": 54524.201150000015, "iscrowd": 0, "image_id": 558276, "bbox": [57.16, 284.02, 329.15, 257.68], "category_id": 88, "id": 2147318, "split": "val", "sentences": [{"tokens": ["a", "white", "stuffed", "animal", "beneath", "a", "brown", "stuffed", "animal"], "raw": "A white stuffed animal beneath a brown stuffed animal.", "sent_id": 75751, "sent": "a white stuffed animal beneath a brown stuffed animal"}, {"tokens": ["the", "white", "stuffed", "animal", "on", "the", "bottom"], "raw": "The white stuffed animal on the bottom.", "sent_id": 75752, "sent": "the white stuffed animal on the bottom"}], "file_name": "COCO_train2014_000000558276_2147318.jpg", "ann_id": 2147318, "sent_ids": [75751, 75752], "ref_id": 34067}, {"segmentation": [[640.0, 176.18, 607.83, 181.05, 526.58, 183.49, 524.96, 160.74, 535.52, 150.18, 532.27, 92.49, 489.21, 61.61, 494.08, 46.99, 531.46, 41.3, 563.96, 30.74, 607.83, 33.18, 640.0, 51.86, 639.52, 81.11]], "area": 17019.741, "iscrowd": 0, "image_id": 128475, "bbox": [489.21, 30.74, 150.79, 152.75], "category_id": 51, "id": 1040500, "split": "val", "sentences": [{"tokens": ["the", "cup", "of", "cream", "that", "is", "farthest", "back", "and", "right"], "raw": "The cup of cream that is farthest back and right.", "sent_id": 75755, "sent": "the cup of cream that is farthest back and right"}, {"tokens": ["a", "ramekin", "with", "yellow", "custard", "behind", "another", "ramekin"], "raw": "A ramekin with yellow custard behind another ramekin", "sent_id": 75756, "sent": "a ramekin with yellow custard behind another ramekin"}], "file_name": "COCO_train2014_000000128475_1040500.jpg", "ann_id": 1040500, "sent_ids": [75755, 75756], "ref_id": 34069}, {"segmentation": [[386.67, 241.34, 393.26, 225.14, 399.26, 221.54, 407.06, 219.15, 414.26, 218.55, 420.26, 218.55, 429.26, 221.54, 435.86, 224.54, 438.86, 224.54, 445.45, 224.54, 446.05, 224.54, 455.65, 216.75, 465.85, 214.95, 471.85, 216.15, 477.85, 215.55, 497.64, 219.15, 510.24, 222.74, 520.44, 231.74, 522.24, 240.14, 524.64, 246.74, 526.44, 259.94, 528.84, 266.54, 525.24, 272.53, 529.44, 276.13, 528.24, 285.73, 515.04, 297.13, 505.44, 294.13, 491.05, 273.13, 486.25, 264.74, 481.45, 262.34, 479.05, 267.14, 476.65, 273.73, 470.65, 283.33, 470.05, 288.13, 464.65, 294.73, 461.05, 301.93, 457.45, 303.13, 459.25, 312.13, 459.85, 321.13, 459.85, 324.13, 458.65, 332.52, 450.25, 334.92, 449.05, 321.73, 441.25, 324.72, 440.66, 309.73, 440.66, 301.93, 438.26, 284.53, 430.46, 282.13, 425.06, 282.13, 421.46, 281.53, 420.26, 281.53, 416.66, 285.13, 414.26, 291.73, 414.26, 304.93, 407.66, 310.33, 406.46, 304.93, 404.06, 297.13, 402.86, 292.33, 405.86, 282.73, 407.06, 272.53, 402.86, 270.14, 402.26, 269.54, 396.26, 267.14, 393.26, 262.34, 389.66, 254.54, 388.46, 246.74, 386.07, 240.74]], "area": 9422.36735, "iscrowd": 0, "image_id": 504187, "bbox": [386.07, 214.95, 143.37, 119.97], "category_id": 24, "id": 590323, "split": "val", "sentences": [{"tokens": ["zebra", "in", "a", "cage"], "raw": "zebra in a cage", "sent_id": 75779, "sent": "zebra in a cage"}], "file_name": "COCO_train2014_000000504187_590323.jpg", "ann_id": 590323, "sent_ids": [75779], "ref_id": 34080}, {"segmentation": [[103.55, 595.42, 136.63, 606.92, 244.49, 579.6, 294.83, 560.9, 296.27, 573.84, 140.94, 621.3, 99.24, 598.29], [102.11, 621.3, 117.93, 632.81, 104.99, 629.93, 97.8, 619.87], [212.85, 628.49, 309.21, 602.61, 310.65, 612.67, 228.67, 631.37]], "area": 3114.9494999999965, "iscrowd": 0, "image_id": 62759, "bbox": [97.8, 560.9, 212.85, 71.91], "category_id": 35, "id": 606677, "split": "val", "sentences": [{"tokens": ["skis", "on", "feet", "of", "man"], "raw": "skis on feet of man", "sent_id": 75800, "sent": "skis on feet of man"}, {"tokens": ["the", "skis", "that", "the", "right", "hand", "side", "person", "is", "using"], "raw": "the skis that the right hand side person is using", "sent_id": 75801, "sent": "the skis that the right hand side person is using"}], "file_name": "COCO_train2014_000000062759_606677.jpg", "ann_id": 606677, "sent_ids": [75800, 75801], "ref_id": 34090}, {"segmentation": [[410.65, 299.86, 388.98, 261.94, 431.24, 200.18, 461.58, 149.26, 494.09, 138.42, 499.5, 67.99, 526.59, 45.24, 551.51, 53.91, 568.85, 77.74, 568.85, 126.5, 578.6, 160.09, 624.11, 187.18, 640.0, 240.27, 634.94, 325.87, 620.86, 321.53, 615.44, 277.11, 573.18, 268.44, 555.85, 286.86, 546.09, 311.78, 534.18, 320.45, 508.17, 319.37, 498.42, 309.62, 464.83, 306.37, 447.49, 306.37, 426.91, 309.62]], "area": 38157.6511, "iscrowd": 0, "image_id": 151854, "bbox": [388.98, 45.24, 251.02, 280.63], "category_id": 1, "id": 495616, "split": "val", "sentences": [{"tokens": ["a", "bald", "man", "in", "a", "white", "tee", "shirt", "looking", "at", "his", "phone"], "raw": "A bald man in a white tee shirt looking at his phone.", "sent_id": 75804, "sent": "a bald man in a white tee shirt looking at his phone"}, {"tokens": ["the", "man", "in", "the", "black", "zippered", "shirt"], "raw": "The man in the black zippered shirt", "sent_id": 75805, "sent": "the man in the black zippered shirt"}], "file_name": "COCO_train2014_000000151854_495616.jpg", "ann_id": 495616, "sent_ids": [75804, 75805], "ref_id": 34092}, {"segmentation": [[299.87, 141.3, 340.85, 142.38, 362.43, 145.62, 375.37, 152.09, 380.76, 153.17, 395.87, 153.17, 418.52, 149.93, 435.78, 149.93, 446.56, 151.01, 456.27, 154.25, 465.98, 162.88, 530.7, 187.69, 547.96, 187.69, 557.66, 202.79, 582.47, 212.49, 608.36, 215.73, 581.39, 238.38, 587.87, 272.9, 579.24, 282.61, 573.84, 304.18, 557.66, 310.65, 602.97, 374.29, 609.44, 400.18, 577.08, 405.57, 570.61, 422.83, 552.27, 420.67, 528.54, 401.26, 538.25, 395.87, 543.64, 344.09, 513.44, 250.25, 485.39, 238.38, 480.0, 215.73, 464.9, 208.18, 415.28, 176.9, 331.15, 151.01]], "area": 19090.282950000004, "iscrowd": 0, "image_id": 274853, "bbox": [299.87, 141.3, 309.57, 281.53], "category_id": 17, "id": 273263, "split": "val", "sentences": [{"tokens": ["a", "brown", "cat", "sleeping", "behind", "the", "black", "cat"], "raw": "A brown cat sleeping behind the black cat", "sent_id": 75820, "sent": "a brown cat sleeping behind the black cat"}, {"tokens": ["light", "colored", "cat"], "raw": "light colored cat", "sent_id": 75821, "sent": "light colored cat"}], "file_name": "COCO_train2014_000000274853_273263.jpg", "ann_id": 273263, "sent_ids": [75820, 75821], "ref_id": 34100}, {"segmentation": [[0.0, 257.24, 37.23, 281.58, 45.82, 304.49, 48.68, 307.35, 71.59, 327.4, 75.88, 328.83, 80.18, 330.26, 97.36, 351.74, 105.95, 357.46, 117.4, 363.19, 137.45, 398.99, 137.45, 407.58, 137.45, 414.74, 126.0, 434.78, 97.36, 451.96, 100.22, 459.12, 101.66, 461.98, 103.09, 464.85, 103.09, 464.85, 105.95, 467.71, 108.81, 474.87, 111.68, 493.48, 107.38, 509.23, 94.5, 522.12, 70.16, 527.84, 58.7, 536.44, 48.68, 539.3, 42.95, 536.44, 28.64, 536.44, 4.3, 529.28, 0.0, 512.1, 0.0, 262.97]], "area": 25703.68890000001, "iscrowd": 0, "image_id": 106660, "bbox": [0.0, 257.24, 137.45, 282.06], "category_id": 64, "id": 18842, "split": "val", "sentences": [{"tokens": ["a", "brown", "pot", "with", "a", "plant", "growing", "out", "of", "it"], "raw": "A brown pot with a plant growing out of it.", "sent_id": 75830, "sent": "a brown pot with a plant growing out of it"}], "file_name": "COCO_train2014_000000106660_18842.jpg", "ann_id": 18842, "sent_ids": [75830], "ref_id": 34104}, {"segmentation": [[126.13, 133.44, 284.25, 132.53, 393.01, 131.61, 455.16, 145.32, 467.04, 152.63, 472.53, 158.12, 506.34, 156.29, 501.77, 171.83, 470.7, 173.66, 466.13, 180.97, 465.22, 204.73, 456.08, 245.86, 439.62, 246.77, 435.97, 244.95, 434.14, 244.03, 422.26, 265.97, 411.29, 288.82, 368.33, 308.92, 311.67, 292.47, 286.08, 291.56, 248.6, 302.53, 216.61, 292.47, 203.82, 277.85, 201.08, 310.75, 191.02, 340.91, 161.77, 341.83, 161.77, 319.89, 159.03, 304.35, 162.69, 296.13, 162.69, 286.08, 160.86, 277.85, 152.63, 279.68, 151.72, 298.87, 151.72, 307.1, 147.15, 302.53, 141.67, 327.2, 132.53, 361.94, 116.08, 362.85, 106.94, 360.11, 106.94, 323.55, 102.37, 307.1, 108.76, 297.96, 114.25, 277.85, 104.19, 225.75, 108.76, 167.26, 117.9, 139.84]], "area": 59812.068650000016, "iscrowd": 0, "image_id": 7601, "bbox": [102.37, 131.61, 403.97, 231.24], "category_id": 21, "id": 70627, "split": "val", "sentences": [{"tokens": ["a", "cow", "standing", "in", "high", "grass", "wearing", "an", "ear", "tag", "with", "the", "number", "342"], "raw": "A cow standing in high grass wearing an ear tag with the number 342.", "sent_id": 75855, "sent": "a cow standing in high grass wearing an ear tag with the number 342"}, {"tokens": ["cow", "with", "a", "number", "312", "on", "a", "tag", "on", "its", "ear"], "raw": "Cow with a number 312 on a tag on its ear.", "sent_id": 75856, "sent": "cow with a number 312 on a tag on its ear"}], "file_name": "COCO_train2014_000000007601_70627.jpg", "ann_id": 70627, "sent_ids": [75855, 75856], "ref_id": 34113}, {"segmentation": [[211.5, 500.31, 211.5, 451.42, 210.36, 353.63, 224.0, 352.49, 258.12, 372.96, 341.12, 384.33, 372.96, 421.86, 391.16, 437.78, 403.66, 392.29, 466.2, 421.86, 542.39, 424.13, 577.64, 399.11, 600.38, 350.22, 589.01, 280.86, 565.13, 235.38, 543.52, 227.42, 526.47, 244.47, 541.25, 330.89, 533.29, 352.49, 486.67, 335.44, 454.83, 280.86, 441.19, 217.18, 418.44, 130.76, 383.2, 71.64, 319.52, 45.48, 252.43, 42.07, 206.95, 48.89, 161.47, 36.39, 98.93, 27.29, 28.43, 25.02, 2.27, 17.06, 0.0, 500.31]], "area": 190879.968, "iscrowd": 0, "image_id": 4477, "bbox": [0.0, 17.06, 600.38, 483.25], "category_id": 22, "id": 582062, "split": "val", "sentences": [{"tokens": ["the", "elephant", "who", "has", "it", "'", "s", "trunk", "curving", "upwards"], "raw": "The elephant who has it's trunk curving upwards.", "sent_id": 75901, "sent": "the elephant who has it ' s trunk curving upwards"}, {"tokens": ["the", "elephant", "in", "the", "foreground", "with", "its", "trunk", "slightly", "raised"], "raw": "The elephant in the foreground with its trunk slightly raised.", "sent_id": 75902, "sent": "the elephant in the foreground with its trunk slightly raised"}], "file_name": "COCO_train2014_000000004477_582062.jpg", "ann_id": 582062, "sent_ids": [75901, 75902], "ref_id": 34131}, {"segmentation": [[176.57, 440.27, 179.81, 435.95, 184.14, 426.22, 187.38, 414.33, 189.54, 406.76, 190.62, 385.14, 187.38, 372.17, 183.05, 363.52, 179.81, 354.87, 174.41, 336.49, 172.24, 322.44, 171.16, 306.22, 171.16, 285.68, 171.16, 269.46, 183.05, 265.14, 197.11, 262.98, 204.68, 256.49, 211.16, 245.68, 212.24, 242.44, 214.41, 239.19, 225.22, 229.46, 233.86, 229.46, 243.59, 234.87, 251.16, 244.6, 256.57, 252.17, 251.16, 259.73, 242.51, 268.38, 244.68, 283.52, 249.0, 296.49, 254.41, 321.36, 250.08, 348.38, 249.0, 350.54, 242.51, 354.87, 242.51, 357.03, 241.43, 361.36, 239.27, 365.68, 236.03, 374.33, 234.95, 382.98, 231.7, 394.87, 229.54, 400.27, 229.54, 405.68, 228.46, 412.17, 227.38, 418.65, 228.46, 422.98, 228.46, 428.38, 227.38, 435.95, 226.3, 441.36, 226.3, 445.68, 218.73, 472.71, 224.14, 465.14, 233.86, 462.98, 236.03, 467.3, 234.95, 469.46, 238.19, 479.19, 236.03, 479.19, 228.46, 475.95, 220.89, 475.95, 215.49, 475.95, 209.0, 474.87, 206.84, 466.22, 205.76, 459.73, 203.59, 456.49, 192.78, 452.17, 187.38, 446.76, 185.22, 444.6, 181.97, 442.44, 178.73, 440.27]], "area": 13212.171749999996, "iscrowd": 0, "image_id": 3320, "bbox": [171.16, 229.46, 85.41, 249.73], "category_id": 1, "id": 199964, "split": "val", "sentences": [{"tokens": ["a", "man", "dressed", "in", "all", "black", "with", "a", "black", "backpack"], "raw": "A man dressed in all black with a black backpack", "sent_id": 75951, "sent": "a man dressed in all black with a black backpack"}, {"tokens": ["the", "man", "with", "the", "black", "backpack", "strapped", "to", "his", "chest"], "raw": "The man with the black backpack strapped to his chest.", "sent_id": 75952, "sent": "the man with the black backpack strapped to his chest"}], "file_name": "COCO_train2014_000000003320_199964.jpg", "ann_id": 199964, "sent_ids": [75951, 75952], "ref_id": 34152}, {"segmentation": [[92.45, 586.24, 96.32, 583.14, 91.67, 577.72, 72.32, 548.3, 61.48, 526.63, 54.51, 480.95, 62.25, 465.47, 82.38, 456.95, 139.67, 451.53, 173.74, 463.14, 193.87, 468.56, 205.48, 473.98, 198.51, 530.5, 163.67, 546.76, 157.48, 573.85, 136.58, 589.34, 122.64, 590.11, 100.96, 590.11]], "area": 15177.234650000004, "iscrowd": 0, "image_id": 327404, "bbox": [54.51, 451.53, 150.97, 138.58], "category_id": 47, "id": 675449, "split": "val", "sentences": [{"tokens": ["a", "white", "cup", "with", "coffee", "that", "says", "blue", "and", "white", "restaurant"], "raw": "a white cup with coffee that says blue and white restaurant", "sent_id": 75971, "sent": "a white cup with coffee that says blue and white restaurant"}, {"tokens": ["a", "white", "mug", "that", "says", "blue", "&", "white", "restaurant"], "raw": "A white mug that says Blue & White Restaurant.", "sent_id": 75972, "sent": "a white mug that says blue & white restaurant"}], "file_name": "COCO_train2014_000000327404_675449.jpg", "ann_id": 675449, "sent_ids": [75971, 75972], "ref_id": 34159}, {"segmentation": [[71.0, 3.0, 65.5, 10.0, 68.0, 24.5, 73.5, 46.5, 74.5, 67.0, 80.0, 65.5, 78.5, 45.5, 79.5, 24.5, 79.5, 15.0], [379.5, 81.0, 368.5, 91.5, 368.5, 99.0, 376.5, 97.0], [617.0, 38.5, 594.0, 69.0, 584.0, 95.5, 571.5, 117.0, 576.5, 120.0, 587.0, 100.5, 599.0, 88.0, 596.5, 83.0, 602.0, 78.0, 605.5, 82.0, 622.5, 46.0]], "area": 1460.125, "iscrowd": 0, "image_id": 240961, "bbox": [65.5, 3.0, 557.0, 117.0], "category_id": 43, "id": 655723, "split": "val", "sentences": [{"tokens": ["3", "tennis", "rackets", "pointing", "upwards"], "raw": "3 tennis rackets pointing upwards", "sent_id": 75989, "sent": "3 tennis rackets pointing upwards"}], "file_name": "COCO_train2014_000000240961_655723.jpg", "ann_id": 655723, "sent_ids": [75989], "ref_id": 34166}, {"segmentation": [[335.06, 346.54, 336.01, 315.91, 341.76, 257.51, 358.99, 237.41, 345.59, 192.42, 331.23, 194.33, 326.44, 167.53, 303.47, 165.61, 301.55, 195.29, 284.32, 233.58, 286.23, 297.72, 285.28, 323.57, 291.02, 355.16, 302.51, 355.16, 312.08, 299.64, 326.44, 356.12, 342.71, 348.46]], "area": 8992.289749999998, "iscrowd": 0, "image_id": 277284, "bbox": [284.32, 165.61, 74.67, 190.51], "category_id": 1, "id": 212141, "split": "val", "sentences": [{"tokens": ["a", "person", "wearing", "the", "dress"], "raw": "a person wearing the dress", "sent_id": 75990, "sent": "a person wearing the dress"}, {"tokens": ["a", "man", "holding", "a", "drink"], "raw": "a man holding a drink", "sent_id": 75991, "sent": "a man holding a drink"}], "file_name": "COCO_train2014_000000277284_212141.jpg", "ann_id": 212141, "sent_ids": [75990, 75991], "ref_id": 34167}, {"segmentation": [[311.73, 66.88, 318.2, 1.08, 459.51, 3.24, 448.72, 131.6, 426.07, 129.44, 427.15, 110.02, 427.15, 90.61, 421.75, 86.29, 389.39, 84.13, 375.37, 91.69, 375.37, 99.24, 376.45, 126.2, 324.67, 126.2, 325.75, 90.61, 325.75, 73.35]], "area": 14775.708300000006, "iscrowd": 0, "image_id": 58864, "bbox": [311.73, 1.08, 147.78, 130.52], "category_id": 62, "id": 1580167, "split": "val", "sentences": [{"tokens": ["the", "chair", "on", "the", "right"], "raw": "the chair on the right", "sent_id": 76002, "sent": "the chair on the right"}, {"tokens": ["chair", "back", "pictured", "behind", "beers"], "raw": "Chair back pictured behind beers.", "sent_id": 76003, "sent": "chair back pictured behind beers"}], "file_name": "COCO_train2014_000000058864_1580167.jpg", "ann_id": 1580167, "sent_ids": [76002, 76003], "ref_id": 34171}, {"segmentation": [[37.96, 335.27, 118.08, 322.62, 117.03, 334.22, 121.25, 341.6, 127.57, 348.98, 134.95, 355.31, 140.22, 363.74, 149.71, 374.28, 168.69, 384.83, 171.85, 398.53, 173.96, 421.73, 0.0, 424.89, 1.05, 383.77, 24.25, 379.56, 29.52, 375.34, 33.74, 370.07, 34.79, 362.69, 34.79, 347.93], [341.77, 331.15, 352.02, 329.87, 353.3, 337.55, 353.3, 342.03, 353.94, 347.79, 355.86, 352.91, 355.86, 355.47, 357.78, 361.23, 359.7, 365.07, 355.86, 366.99, 352.02, 369.55, 350.1, 370.83, 350.1, 374.67, 353.3, 377.23, 353.3, 385.55, 352.66, 419.48, 352.66, 423.32, 342.41, 426.52, 339.85, 413.72, 337.93, 407.32, 334.09, 400.28, 327.69, 393.88, 333.45, 392.6, 333.45, 381.71, 333.45, 374.67, 331.53, 371.47, 334.73, 369.55, 337.29, 366.99, 338.57, 363.15, 341.13, 340.75, 341.13, 331.79]], "area": 13954.293050000004, "iscrowd": 0, "image_id": 235582, "bbox": [0.0, 322.62, 359.7, 103.9], "category_id": 67, "id": 2225899, "split": "val", "sentences": [{"tokens": ["a", "dinner", "table"], "raw": "A dinner table.", "sent_id": 76024, "sent": "a dinner table"}], "file_name": "COCO_train2014_000000235582_2225899.jpg", "ann_id": 2225899, "sent_ids": [76024], "ref_id": 34176}, {"segmentation": [[293.13, 156.11, 257.5, 172.74, 230.19, 177.09, 189.81, 171.95, 147.06, 171.15, 113.42, 178.28, 81.75, 194.9, 59.19, 213.9, 46.52, 227.76, 35.44, 247.55, 26.73, 268.53, 25.94, 284.36, 25.94, 299.01, 30.29, 304.15, 40.98, 283.57, 61.56, 259.03, 86.5, 238.84, 112.63, 224.2, 141.13, 212.72, 170.42, 208.76, 196.54, 207.57, 207.23, 205.99, 242.85, 205.2, 269.77, 200.84, 276.11, 189.76, 288.77, 177.49, 302.63, 167.2, 306.98, 166.01, 334.69, 147.8, 360.81, 128.4, 387.73, 113.36, 397.63, 105.05, 392.48, 92.78, 387.33, 86.45, 382.19, 84.86, 377.83, 86.45, 373.88, 91.99, 370.31, 93.57, 298.27, 145.03, 290.36, 153.34]], "area": 12970.788849999997, "iscrowd": 0, "image_id": 560180, "bbox": [25.94, 84.86, 371.69, 219.29], "category_id": 43, "id": 655156, "split": "val", "sentences": [{"tokens": ["the", "black", "tennis", "racket", "in", "the", "back"], "raw": "The black tennis racket in the back.", "sent_id": 76053, "sent": "the black tennis racket in the back"}, {"tokens": ["tennis", "racket", "far", "from", "the", "camera"], "raw": "Tennis racket far from the camera.", "sent_id": 76054, "sent": "tennis racket far from the camera"}], "file_name": "COCO_train2014_000000560180_655156.jpg", "ann_id": 655156, "sent_ids": [76053, 76054], "ref_id": 34187}, {"segmentation": [[405.88, 406.84, 448.2, 403.96, 450.12, 362.6, 459.74, 321.24, 482.82, 275.07, 500.0, 255.84, 500.0, 240.45, 494.36, 221.21, 478.01, 197.17, 455.89, 184.67, 439.54, 171.2, 431.85, 166.39, 436.66, 149.08, 434.73, 132.73, 429.92, 125.03, 428.0, 124.07, 419.34, 122.15, 408.76, 129.84, 397.22, 150.04, 386.64, 148.12, 379.91, 147.16, 384.72, 139.46, 376.06, 129.84, 367.41, 126.96, 357.79, 131.77, 351.06, 151.0, 355.87, 161.58, 336.63, 176.01, 325.09, 189.47, 327.97, 206.79, 321.24, 221.21, 315.47, 232.76, 317.39, 248.14, 332.78, 254.88, 347.21, 258.72, 360.67, 257.76, 373.18, 252.95, 375.1, 251.99, 378.95, 259.69, 375.1, 296.23, 377.99, 342.4, 377.02, 377.99, 379.91, 395.3, 399.15, 402.03, 403.96, 404.92]], "area": 29135.583550000003, "iscrowd": 0, "image_id": 243574, "bbox": [315.47, 122.15, 184.53, 284.69], "category_id": 17, "id": 49131, "split": "val", "sentences": [{"tokens": ["a", "tabby", "cat", "sitting", "outside", "a", "door"], "raw": "A tabby cat sitting outside a door.", "sent_id": 76087, "sent": "a tabby cat sitting outside a door"}, {"tokens": ["the", "cat", "right", "in", "front", "of", "the", "window"], "raw": "The cat right in front of the window.", "sent_id": 76088, "sent": "the cat right in front of the window"}], "file_name": "COCO_train2014_000000243574_49131.jpg", "ann_id": 49131, "sent_ids": [76087, 76088], "ref_id": 34197}, {"segmentation": [[379.66, 49.17, 379.66, 75.31, 360.99, 127.59, 459.33, 233.4, 495.43, 229.66, 529.04, 218.46, 575.09, 126.35, 532.77, 91.49, 474.27, 69.09, 421.98, 52.9, 370.95, 44.19]], "area": 25117.39015, "iscrowd": 0, "image_id": 2411, "bbox": [360.99, 44.19, 214.1, 189.21], "category_id": 61, "id": 1927304, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "chocolate", "layer", "cake", "on", "a", "floral", "patterned", "dish"], "raw": "A piece of chocolate layer cake on a floral patterned dish.", "sent_id": 76112, "sent": "a piece of chocolate layer cake on a floral patterned dish"}, {"tokens": ["chocolate", "dessert", "cake", "on", "a", "plate"], "raw": "Chocolate dessert cake on a plate.", "sent_id": 76113, "sent": "chocolate dessert cake on a plate"}], "file_name": "COCO_train2014_000000002411_1927304.jpg", "ann_id": 1927304, "sent_ids": [76112, 76113], "ref_id": 34211}, {"segmentation": [[337.98, 263.29, 333.66, 253.22, 326.47, 243.15, 339.42, 194.25, 353.8, 172.68, 372.49, 158.3, 373.93, 130.97, 371.06, 106.52, 333.66, 64.81, 320.72, 51.87, 314.97, 38.93, 309.21, 21.67, 287.64, 23.11, 274.7, 48.99, 274.7, 74.88, 263.19, 79.2, 248.81, 106.52, 260.31, 152.55, 260.31, 153.98, 268.94, 155.42, 256.0, 175.56, 260.31, 195.69, 266.07, 197.13, 283.33, 204.32, 291.96, 241.71, 293.39, 244.59, 287.64, 279.11, 304.9, 284.86, 329.35, 281.98, 337.98, 269.04]], "area": 18985.06880000001, "iscrowd": 0, "image_id": 463224, "bbox": [248.81, 21.67, 125.12, 263.19], "category_id": 1, "id": 540778, "split": "val", "sentences": [{"tokens": ["man", "riding", "an", "elephant", "with", "his", "ankles", "crossed"], "raw": "Man riding an elephant with his ankles crossed.", "sent_id": 76168, "sent": "man riding an elephant with his ankles crossed"}, {"tokens": ["this", "is", "the", "man", "on", "the", "elephant", "to", "the", "far", "right"], "raw": "This is the man on the elephant to the far right.", "sent_id": 76169, "sent": "this is the man on the elephant to the far right"}], "file_name": "COCO_train2014_000000463224_540778.jpg", "ann_id": 540778, "sent_ids": [76168, 76169], "ref_id": 34233}, {"segmentation": [[118.39, 276.62, 45.37, 245.64, 2.21, 262.24, 0.0, 82.99, 3.32, 5.53, 115.08, 14.38, 183.68, 43.15, 199.17, 73.03, 184.78, 189.21, 101.8, 141.63, 57.54, 165.97, 121.71, 195.85, 128.35, 271.09]], "area": 38265.55175, "iscrowd": 0, "image_id": 506592, "bbox": [0.0, 5.53, 199.17, 271.09], "category_id": 33, "id": 1844020, "split": "val", "sentences": [{"tokens": ["a", "black", "case", "with", "a", "red", "rag"], "raw": "A black case with a red rag.", "sent_id": 76252, "sent": "a black case with a red rag"}, {"tokens": ["the", "top", "of", "a", "black", "piece", "of", "luggage"], "raw": "the top of a black piece of luggage", "sent_id": 76253, "sent": "the top of a black piece of luggage"}], "file_name": "COCO_train2014_000000506592_1844020.jpg", "ann_id": 1844020, "sent_ids": [76252, 76253], "ref_id": 34269}, {"segmentation": [[238.37, 31.91, 243.65, 31.91, 245.62, 31.91, 252.22, 39.17, 255.52, 42.47, 257.5, 47.09, 257.5, 50.39, 264.1, 52.37, 272.02, 55.67, 280.6, 58.31, 289.84, 73.48, 285.22, 75.46, 299.74, 91.3, 310.29, 109.78, 322.17, 157.29, 315.57, 161.91, 308.97, 165.87, 295.78, 196.88, 295.12, 202.16, 299.08, 208.76, 309.63, 243.07, 314.91, 272.87, 307.65, 286.73, 272.68, 288.71, 266.74, 280.79, 266.74, 273.53, 280.6, 266.27, 282.58, 264.96, 282.58, 261.66, 282.58, 251.1, 252.88, 252.42, 246.28, 246.48, 250.9, 236.58, 259.48, 234.6, 260.8, 231.3, 255.52, 210.18, 248.26, 206.89, 239.69, 184.45, 249.58, 169.93, 256.18, 163.33, 259.48, 156.07, 256.18, 150.79, 250.9, 144.2, 248.92, 137.6, 247.6, 132.98, 244.31, 147.5, 243.65, 154.09, 246.28, 158.71, 248.92, 164.65, 245.62, 170.59, 241.01, 174.55, 234.41, 177.19, 227.81, 163.99, 223.85, 142.88, 225.83, 114.5, 227.81, 94.7, 231.77, 86.13, 227.15, 76.89, 231.11, 74.85, 232.43, 65.62, 229.79, 62.32, 224.51, 52.42, 223.85, 42.52, 235.73, 32.62]], "area": 15049.272099999996, "iscrowd": 0, "image_id": 478899, "bbox": [223.85, 31.91, 98.32, 256.8], "category_id": 1, "id": 495378, "split": "val", "sentences": [{"tokens": ["a", "snowboarder", "with", "light", "blue", "pants"], "raw": "A snowboarder with light blue pants.", "sent_id": 76270, "sent": "a snowboarder with light blue pants"}, {"tokens": ["snowboarder"], "raw": "Snowboarder.", "sent_id": 76271, "sent": "snowboarder"}], "file_name": "COCO_train2014_000000478899_495378.jpg", "ann_id": 495378, "sent_ids": [76270, 76271], "ref_id": 34273}, {"segmentation": [[5.39, 472.45, 1.08, 319.28, 85.21, 424.99, 129.44, 444.4, 111.1, 473.53], [0.0, 169.35, 2.16, 2.16, 453.03, 1.08, 636.4, 1.08, 635.33, 249.17, 615.91, 238.38, 580.31, 142.38, 551.19, 118.65, 497.26, 85.21, 423.91, 46.38, 360.27, 29.12, 309.57, 29.12, 222.2, 33.44, 152.09, 60.4, 62.56, 111.1, 25.89, 158.56]], "area": 61012.17649999999, "iscrowd": 0, "image_id": 196156, "bbox": [0.0, 1.08, 636.4, 472.45], "category_id": 67, "id": 420358, "split": "val", "sentences": [{"tokens": ["floral", "tablecloth", "with", "pink", "flowers", "and", "green", "leaves"], "raw": "Floral tablecloth with pink flowers and green leaves.", "sent_id": 76301, "sent": "floral tablecloth with pink flowers and green leaves"}, {"tokens": ["a", "table", "covered", "in", "a", "floral", "tablecloth"], "raw": "A table covered in a floral tablecloth .", "sent_id": 76302, "sent": "a table covered in a floral tablecloth"}], "file_name": "COCO_train2014_000000196156_420358.jpg", "ann_id": 420358, "sent_ids": [76301, 76302], "ref_id": 34284}, {"segmentation": [[217.49, 415.47, 262.33, 447.98, 288.12, 451.35, 301.57, 458.07, 313.9, 450.22, 362.11, 359.42, 366.59, 284.3, 302.69, 255.16, 290.36, 267.49, 215.25, 407.62]], "area": 18739.392200000002, "iscrowd": 0, "image_id": 215908, "bbox": [215.25, 255.16, 151.34, 202.91], "category_id": 77, "id": 327882, "split": "val", "sentences": [{"tokens": ["the", "device", "with", "a", "a", "macbreak", "weekly", "screen", "on", "it"], "raw": "the device with a a MacBreak Weekly screen on it", "sent_id": 76347, "sent": "the device with a a macbreak weekly screen on it"}, {"tokens": ["macbreak", "weekly", "screen", "using", "the", "phone"], "raw": "MACBREAK WEEKLY  SCREEN USING THE PHONE", "sent_id": 76348, "sent": "macbreak weekly screen using the phone"}], "file_name": "COCO_train2014_000000215908_327882.jpg", "ann_id": 327882, "sent_ids": [76347, 76348], "ref_id": 34303}, {"segmentation": [[299.87, 9.71, 281.53, 38.83, 275.06, 74.43, 284.76, 91.69, 286.92, 99.24, 281.53, 108.94, 272.9, 115.42, 266.43, 127.28, 235.15, 170.43, 234.07, 211.42, 229.75, 243.78, 235.15, 261.03, 243.78, 284.76, 247.01, 303.1, 254.56, 337.62, 266.43, 369.98, 268.58, 378.61, 270.74, 389.39, 279.37, 421.75, 292.31, 418.52, 304.18, 424.99, 306.34, 431.46, 310.65, 456.27, 332.22, 464.9, 345.17, 458.43, 348.4, 453.03, 364.58, 446.56, 367.82, 439.01, 361.35, 429.3, 351.64, 415.28, 353.8, 414.2, 364.58, 391.55, 369.98, 376.45, 366.74, 340.85, 362.43, 320.36, 357.03, 299.87, 341.93, 276.13, 347.33, 273.98, 364.58, 316.04, 371.06, 325.75, 374.29, 333.3, 379.69, 338.7, 395.87, 317.12, 398.02, 312.81, 392.63, 291.24, 390.47, 273.98, 384.0, 249.17, 375.37, 214.65, 375.37, 192.0, 368.9, 160.72, 352.72, 136.99, 346.25, 129.44, 345.17, 115.42, 351.64, 99.24, 358.11, 91.69, 362.43, 97.08, 376.45, 75.51, 373.21, 48.54, 373.21, 30.2, 371.06, 25.89, 363.51, 14.02, 358.11, 6.47, 314.97, 12.94]], "area": 48543.78679999999, "iscrowd": 0, "image_id": 329502, "bbox": [229.75, 6.47, 168.27, 458.43], "category_id": 1, "id": 1216279, "split": "val", "sentences": [{"tokens": ["a", "toddler", "in", "gray", "pants", "and", "a", "striped", "shirt"], "raw": "A toddler in gray pants and a striped shirt", "sent_id": 76357, "sent": "a toddler in gray pants and a striped shirt"}, {"tokens": ["a", "boy", "wearing", "a", "striped", "shirt", "and", "gray", "pants"], "raw": "A boy wearing a striped shirt and gray pants.", "sent_id": 76358, "sent": "a boy wearing a striped shirt and gray pants"}], "file_name": "COCO_train2014_000000329502_1216279.jpg", "ann_id": 1216279, "sent_ids": [76357, 76358], "ref_id": 34308}, {"segmentation": [[9.96, 351.15, 1.08, 352.81, 0.0, 475.47, 2.75, 490.46, 8.3, 495.45, 12.74, 484.91, 17.18, 488.79, 27.17, 487.68, 27.17, 483.24, 24.95, 478.25, 32.72, 473.81, 34.38, 470.48, 24.95, 459.38, 23.28, 422.75, 25.5, 391.67, 29.39, 381.67, 29.39, 377.79, 32.16, 377.23, 35.49, 380.56, 38.27, 383.89, 39.93, 387.23, 44.93, 388.34, 48.81, 388.89, 49.92, 365.02, 51.59, 348.37, 38.82, 347.26, 27.72, 347.26, 12.74, 349.48, 8.85, 351.15], [60.47, 469.37, 101.54, 461.04, 102.65, 437.18, 55.47, 441.06, 56.58, 468.81]], "area": 5608.938050000001, "iscrowd": 0, "image_id": 298481, "bbox": [0.0, 347.26, 102.65, 148.19], "category_id": 67, "id": 118277, "split": "val", "sentences": [{"tokens": ["a", "table", "under", "the", "chandelier"], "raw": "A table under the chandelier.", "sent_id": 76430, "sent": "a table under the chandelier"}], "file_name": "COCO_train2014_000000298481_118277.jpg", "ann_id": 118277, "sent_ids": [76430], "ref_id": 34332}, {"segmentation": [[4.12, 249.41, 30.21, 267.26, 52.19, 250.78, 50.82, 223.31, 71.42, 224.69, 162.06, 145.03, 138.71, 156.02, 137.34, 136.79, 151.07, 123.06, 142.83, 101.08, 163.43, 88.72, 175.79, 107.95, 211.5, 76.36, 244.46, 64.0, 236.22, 87.35, 241.72, 142.28, 271.93, 183.48, 277.42, 205.46, 271.93, 226.06, 282.92, 234.3, 271.93, 250.78, 197.77, 249.41, 156.57, 220.57, 151.07, 226.06, 152.45, 237.05, 167.55, 252.15, 175.79, 267.26, 195.02, 270.01, 200.52, 265.89, 281.55, 282.37, 300.77, 275.5, 311.76, 315.33, 317.25, 345.55, 304.89, 346.92, 302.15, 319.45, 304.89, 401.85, 318.63, 449.92, 348.84, 524.09, 365.32, 535.07, 335.11, 555.67, 330.99, 540.57, 324.12, 496.62, 288.41, 430.7, 285.67, 410.09, 270.56, 377.13, 251.33, 379.88, 277.42, 430.7, 299.4, 466.4, 304.89, 491.12, 314.51, 507.61, 291.16, 521.34, 285.67, 503.48, 285.67, 476.02, 245.84, 412.84, 186.78, 359.28, 190.9, 414.21, 204.64, 489.75, 200.52, 541.94, 179.91, 555.67, 144.21, 551.55, 111.24, 480.14, 74.16, 415.59, 42.58, 394.99, 28.84, 374.39, 17.85, 302.97, 2.75, 287.86, 2.75, 245.29]], "area": 80502.8615, "iscrowd": 0, "image_id": 137173, "bbox": [2.75, 64.0, 362.57, 491.67], "category_id": 19, "id": 57816, "split": "val", "sentences": [{"tokens": ["a", "brown", "horse", "with", "a", "saddle"], "raw": "a brown horse with a saddle", "sent_id": 76494, "sent": "a brown horse with a saddle"}, {"tokens": ["a", "horse", "standing", "in", "front", "of", "another", "horse", "and", "next", "to", "a", "young", "girl"], "raw": "A horse standing in front of another horse and next to a young girl", "sent_id": 76495, "sent": "a horse standing in front of another horse and next to a young girl"}], "file_name": "COCO_train2014_000000137173_57816.jpg", "ann_id": 57816, "sent_ids": [76494, 76495], "ref_id": 34362}, {"segmentation": [[174.88, 429.62, 207.64, 426.47, 225.88, 407.82, 234.61, 411.31, 240.73, 434.88, 260.81, 440.99, 275.65, 441.87, 284.38, 440.12, 286.13, 399.08, 295.73, 372.89, 317.56, 370.27, 302.72, 424.41, 297.48, 440.12, 283.51, 454.97, 280.89, 466.32, 282.64, 480.29, 287.87, 487.27, 268.67, 485.52, 245.96, 519.58, 234.61, 518.7, 222.39, 519.58, 211.04, 520.45, 201.43, 520.45, 185.72, 511.72, 155.16, 431.39, 155.16, 419.17, 161.27, 412.18, 168.26, 416.55], [187.5, 379.9, 242.13, 385.27, 230.43, 398.93, 200.18, 414.05]], "area": 11909.965850000008, "iscrowd": 0, "image_id": 94600, "bbox": [155.16, 370.27, 162.4, 150.18], "category_id": 86, "id": 1151962, "split": "val", "sentences": [{"tokens": ["the", "bottom", "of", "the", "broken", "white", "vase"], "raw": "the bottom of the broken white vase", "sent_id": 76532, "sent": "the bottom of the broken white vase"}, {"tokens": ["a", "broken", "white", "pot", "that", "has", "been", "made", "into", "an", "art", "display", "and", "is", "now", "hanging", "by", "strings"], "raw": "A broken white pot that has been made into an art display and is now hanging by strings.", "sent_id": 76533, "sent": "a broken white pot that has been made into an art display and is now hanging by strings"}], "file_name": "COCO_train2014_000000094600_1151962.jpg", "ann_id": 1151962, "sent_ids": [76532, 76533], "ref_id": 34380}, {"segmentation": [[443.85, 62.25, 468.26, 70.01, 473.81, 80.0, 489.34, 93.32, 492.67, 102.19, 492.67, 113.29, 487.12, 127.71, 482.68, 131.04, 481.57, 134.37, 487.12, 135.48, 498.22, 141.03, 512.64, 153.23, 514.86, 163.22, 507.1, 188.74, 504.88, 203.17, 504.88, 215.37, 507.1, 222.03, 519.3, 248.66, 520.41, 268.64, 525.96, 290.83, 531.51, 324.12, 531.51, 344.09, 529.29, 350.75, 518.19, 354.08, 504.88, 357.4, 500.44, 372.94, 498.22, 372.94, 484.9, 369.61, 478.25, 365.17, 466.04, 360.73, 458.27, 360.73, 451.62, 355.19, 446.07, 344.09, 437.19, 328.55, 437.19, 325.23, 441.63, 308.58, 443.85, 296.38, 446.07, 284.17, 447.18, 276.4, 448.29, 268.64, 448.29, 267.53, 453.83, 263.09, 457.16, 257.54, 452.72, 258.65, 444.96, 249.77, 442.74, 246.44, 459.38, 247.55, 466.04, 247.55, 464.93, 236.46, 460.49, 225.36, 446.07, 215.37, 437.19, 215.37, 427.2, 216.48, 413.89, 225.36, 408.34, 236.46, 407.23, 239.79, 407.23, 246.44, 405.01, 247.55, 401.68, 256.43, 399.46, 257.54, 397.24, 257.54, 393.91, 257.54, 390.59, 245.33, 397.24, 237.57, 399.46, 235.35, 399.46, 230.91, 399.46, 225.36, 402.79, 220.92, 407.23, 210.93, 407.23, 205.39, 407.23, 192.07, 410.56, 153.23, 419.44, 149.91, 424.98, 146.58, 431.64, 143.25, 433.86, 138.81, 440.52, 132.15, 441.63, 132.15, 433.86, 123.27, 430.53, 123.27, 421.66, 116.62, 420.55, 113.29, 420.55, 106.63, 422.77, 101.08, 424.98, 97.75, 428.31, 94.42, 430.53, 88.88, 426.09, 85.55, 423.87, 80.0, 427.2, 73.34, 433.86, 70.01, 438.3, 70.01, 441.63, 66.68]], "area": 22990.4893, "iscrowd": 0, "image_id": 124694, "bbox": [390.59, 62.25, 140.92, 310.69], "category_id": 1, "id": 191655, "split": "val", "sentences": [{"tokens": ["woman", "on", "right"], "raw": "woman on right", "sent_id": 76613, "sent": "woman on right"}, {"tokens": ["a", "woman", "with", "black", "hair", "rubbing", "a", "sheep"], "raw": "A woman with black hair rubbing a sheep.", "sent_id": 76614, "sent": "a woman with black hair rubbing a sheep"}], "file_name": "COCO_train2014_000000124694_191655.jpg", "ann_id": 191655, "sent_ids": [76613, 76614], "ref_id": 34411}, {"segmentation": [[318.36, 0.43, 436.44, 1.05, 437.67, 2.28, 479.09, 17.12, 479.09, 234.1, 323.31, 232.87]], "area": 36458.50964999999, "iscrowd": 0, "image_id": 205223, "bbox": [318.36, 0.43, 160.73, 233.67], "category_id": 1, "id": 2164818, "split": "val", "sentences": [{"tokens": ["a", "white", "silver", "tie", "is", "posed", "to", "the", "left", "of", "the", "logo"], "raw": "A white silver tie is posed to the left of the logo.", "sent_id": 76621, "sent": "a white silver tie is posed to the left of the logo"}, {"tokens": ["a", "man", "wearing", "a", "tuxedo", "standing", "2nd", "from", "the", "right", "of", "four", "people"], "raw": "a man wearing a tuxedo standing 2nd from the right  of four people", "sent_id": 76622, "sent": "a man wearing a tuxedo standing 2nd from the right of four people"}], "file_name": "COCO_train2014_000000205223_2164818.jpg", "ann_id": 2164818, "sent_ids": [76621, 76622], "ref_id": 34414}, {"segmentation": [[105.95, 343.24, 77.84, 347.57, 67.03, 328.11, 69.19, 312.97, 61.62, 298.92, 81.08, 209.19, 98.38, 192.97, 134.05, 177.84, 149.19, 170.27, 153.51, 155.14, 148.11, 135.68, 131.89, 120.54, 135.14, 115.14, 138.38, 112.97, 137.3, 90.27, 144.86, 75.14, 174.05, 54.59, 188.11, 56.76, 200.0, 70.81, 210.81, 91.35, 211.89, 104.32, 211.89, 119.46, 211.89, 138.92, 205.41, 150.81, 204.32, 176.76, 236.76, 186.49, 267.03, 200.54, 287.57, 287.03, 265.95, 290.27, 273.51, 349.73, 284.32, 403.78, 290.81, 453.51, 297.3, 472.97, 296.22, 475.14, 103.78, 463.24, 104.86, 425.41, 110.27, 387.57, 112.43, 369.19, 108.11, 347.57]], "area": 61710.900349999996, "iscrowd": 0, "image_id": 41818, "bbox": [61.62, 54.59, 235.68, 420.55], "category_id": 1, "id": 441631, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "t", "-", "shirt", "with", "faces", "on", "it"], "raw": "A man in a t-shirt with faces on it.", "sent_id": 76651, "sent": "a man in a t - shirt with faces on it"}, {"tokens": ["a", "man", "in", "a", "white", "t", "-", "shirt", "holding", "a", "glass", "of", "juice"], "raw": "A man in a white t-shirt holding a glass of juice.", "sent_id": 76652, "sent": "a man in a white t - shirt holding a glass of juice"}], "file_name": "COCO_train2014_000000041818_441631.jpg", "ann_id": 441631, "sent_ids": [76651, 76652], "ref_id": 34427}, {"segmentation": [[292.64, 280.91, 300.02, 283.01, 358.0, 236.63, 409.65, 198.68, 433.9, 179.18, 328.48, 254.55], [377.5, 220.82, 422.3, 228.2, 422.83, 230.31, 418.61, 235.05, 412.81, 238.74, 366.96, 230.83]], "area": 1072.3543499999982, "iscrowd": 0, "image_id": 464605, "bbox": [292.64, 179.18, 141.26, 103.83], "category_id": 35, "id": 2083474, "split": "val", "sentences": [{"tokens": ["the", "skier", "'", "s", "left", "ski"], "raw": "the skier's left ski", "sent_id": 76700, "sent": "the skier ' s left ski"}], "file_name": "COCO_train2014_000000464605_2083474.jpg", "ann_id": 2083474, "sent_ids": [76700], "ref_id": 34448}, {"segmentation": [[418.34, 7.72, 627.99, 24.0, 627.99, 30.7, 575.34, 196.31, 407.81, 158.02]], "area": 31458.820600000003, "iscrowd": 0, "image_id": 561479, "bbox": [407.81, 7.72, 220.18, 188.59], "category_id": 72, "id": 29221, "split": "val", "sentences": [{"tokens": ["the", "white", "apple", "monitor"], "raw": "The white apple monitor.", "sent_id": 76755, "sent": "the white apple monitor"}, {"tokens": ["white", "coloured", "monitor", "of", "a", "computer"], "raw": "white coloured monitor of a computer", "sent_id": 76756, "sent": "white coloured monitor of a computer"}], "file_name": "COCO_train2014_000000561479_29221.jpg", "ann_id": 29221, "sent_ids": [76755, 76756], "ref_id": 34473}, {"segmentation": [[35.97, 142.73, 48.53, 128.7, 61.83, 125.74, 74.38, 125.74, 80.29, 126.48, 88.42, 126.48, 110.58, 138.3, 123.13, 144.95, 129.04, 156.03, 129.04, 170.8, 126.09, 181.14, 126.09, 190.0, 129.04, 199.61, 134.95, 213.64, 127.57, 216.6, 123.87, 217.33, 122.39, 227.68, 120.18, 229.89, 120.18, 234.32, 120.18, 243.19, 122.39, 255.74, 122.39, 259.44, 119.44, 252.05, 114.27, 244.66, 109.84, 240.97, 99.5, 244.66, 100.24, 254.27, 100.24, 256.48, 93.59, 270.52, 85.46, 280.86, 75.86, 308.19, 72.17, 337.74, 67.0, 346.6, 58.87, 346.6, 48.53, 331.83, 24.15, 304.5, 16.77, 293.42, 21.94, 288.25, 36.71, 280.86, 41.88, 263.13, 42.62, 238.76, 49.27, 226.2, 51.48, 218.07, 48.53, 207.73, 40.4, 195.91, 46.31, 182.62, 46.31, 159.72, 56.65, 157.5, 85.46, 153.81, 87.68, 146.42, 81.77, 144.95, 43.36, 144.95], [148.25, 339.95, 164.5, 314.84, 165.24, 295.63, 165.24, 286.77, 188.87, 287.51, 183.7, 297.11, 163.76, 330.35, 154.9, 343.64, 141.6, 345.12], [288.59, 299.33, 298.93, 291.94, 307.06, 288.98, 316.66, 294.89, 327.74, 300.06, 330.7, 305.97, 324.79, 317.05, 315.18, 320.01, 308.54, 317.05, 299.67, 321.48, 292.29, 323.7, 285.64, 327.39, 304.1, 337.74, 302.63, 344.38, 290.81, 345.86, 287.11, 348.81, 277.51, 353.25, 262.0, 353.99, 245.01, 353.99, 230.98, 351.77, 230.24, 345.12, 242.06, 341.43, 264.96, 334.78, 267.17, 321.48, 273.08, 308.93, 278.99, 303.76]], "area": 16823.392799999998, "iscrowd": 0, "image_id": 578369, "bbox": [16.77, 125.74, 313.93, 228.25], "category_id": 1, "id": 433653, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "white", "shirt"], "raw": "a woman in a white shirt", "sent_id": 76796, "sent": "a woman in a white shirt"}, {"tokens": ["the", "woman", "in", "the", "white", "shirt"], "raw": "The woman in the white shirt", "sent_id": 76797, "sent": "the woman in the white shirt"}], "file_name": "COCO_train2014_000000578369_433653.jpg", "ann_id": 433653, "sent_ids": [76796, 76797], "ref_id": 34487}, {"segmentation": [[215.6, 135.4, 290.59, 174.98, 371.84, 162.48, 419.75, 174.98, 438.5, 199.98, 444.75, 243.72, 460.37, 274.97, 457.24, 293.72, 446.83, 270.81, 446.83, 270.81, 450.99, 308.3, 434.33, 229.14, 421.83, 268.72, 421.83, 268.72, 428.08, 311.43, 429.12, 393.71, 405.17, 380.17, 399.96, 321.84, 370.79, 268.72, 370.79, 268.72, 332.26, 277.05, 260.39, 284.35, 265.6, 391.63, 256.22, 394.75, 223.94, 394.75, 228.1, 368.71, 224.98, 309.34, 207.27, 265.6, 191.65, 240.6, 172.9, 232.27, 172.9, 232.27, 158.32, 242.68, 158.32, 242.68, 142.69, 272.89, 116.65, 273.93, 108.32, 245.81, 113.53, 218.73, 124.99, 139.57, 149.98, 124.99, 197.9, 130.19, 197.9, 130.19]], "area": 45406.06555000004, "iscrowd": 0, "image_id": 370461, "bbox": [108.32, 124.99, 352.05, 269.76], "category_id": 24, "id": 1822192, "split": "val", "sentences": [{"tokens": ["zibra", "with", "one", "zibera"], "raw": "zibra with one zibera", "sent_id": 76822, "sent": "zibra with one zibera"}], "file_name": "COCO_train2014_000000370461_1822192.jpg", "ann_id": 1822192, "sent_ids": [76822], "ref_id": 34496}, {"segmentation": [[210.87, 516.85, 153.34, 511.37, 154.71, 442.88, 227.31, 357.95, 235.52, 336.04, 241.0, 237.42, 175.26, 216.88, 180.74, 205.92, 223.19, 181.26, 264.28, 185.37, 301.27, 182.64, 308.12, 126.48, 364.28, 94.96, 409.47, 94.96, 430.02, 133.32, 419.06, 185.37, 405.37, 227.83, 391.67, 233.31, 384.82, 240.17, 420.43, 277.14, 414.95, 333.3, 390.3, 382.6, 390.3, 448.36, 443.71, 516.85, 373.86, 489.45, 350.58, 504.52, 312.23, 481.22, 242.37, 493.56], [78.01, 319.6, 24.59, 289.47, 45.13, 271.66, 68.42, 270.3, 83.49, 268.93, 109.5, 242.9, 175.26, 211.4, 105.41, 267.55, 112.25, 281.25, 83.49, 316.86]], "area": 76913.74185000002, "iscrowd": 0, "image_id": 89788, "bbox": [24.59, 94.96, 419.12, 421.89], "category_id": 1, "id": 477606, "split": "val", "sentences": [{"tokens": ["a", "woman", "laying", "down", "with", "a", "coffee", "cup", "in", "her", "hand"], "raw": "A woman laying down with a coffee cup in her hand.", "sent_id": 76847, "sent": "a woman laying down with a coffee cup in her hand"}, {"tokens": ["an", "older", "woman", "in", "blue", "is", "leaning", "on", "a", "bed", "behind", "a", "little", "girl"], "raw": "An older woman in blue is leaning on a bed behind a little girl", "sent_id": 76848, "sent": "an older woman in blue is leaning on a bed behind a little girl"}], "file_name": "COCO_train2014_000000089788_477606.jpg", "ann_id": 477606, "sent_ids": [76847, 76848], "ref_id": 34506}, {"segmentation": [[171.67, 354.93, 176.19, 339.87, 177.69, 327.82, 180.71, 320.29, 183.72, 312.76, 204.8, 284.15, 198.78, 222.41, 192.75, 217.89, 192.75, 201.33, 197.27, 187.78, 207.81, 169.7, 213.84, 118.5, 204.8, 95.92, 189.74, 83.87, 177.69, 76.34, 141.55, 67.3, 114.45, 67.3, 93.36, 82.36, 78.31, 94.41, 75.29, 142.6, 78.31, 156.15, 109.93, 205.85, 105.41, 208.86, 94.87, 278.13, 94.87, 278.13, 96.38, 303.73, 97.88, 309.75, 108.42, 324.81, 111.44, 377.52, 141.55, 382.03, 170.16, 366.98]], "area": 30769.272899999996, "iscrowd": 0, "image_id": 362657, "bbox": [75.29, 67.3, 138.55, 314.73], "category_id": 14, "id": 419359, "split": "val", "sentences": [{"tokens": ["the", "left", "side", "of", "the", "parking", "meter"], "raw": "The left side of the parking meter", "sent_id": 76849, "sent": "the left side of the parking meter"}], "file_name": "COCO_train2014_000000362657_419359.jpg", "ann_id": 419359, "sent_ids": [76849], "ref_id": 34507}, {"segmentation": [[253.03, 74.88, 271.15, 80.14, 284.6, 87.74, 294.54, 101.18, 291.61, 139.77, 286.35, 146.79, 286.35, 146.79, 287.52, 155.56, 287.52, 155.56, 293.95, 154.97, 299.8, 152.63, 305.65, 152.63, 302.72, 170.17, 326.69, 180.7, 336.63, 231.56, 329.62, 289.44, 331.37, 368.95, 304.48, 380.64, 302.14, 402.86, 301.55, 411.04, 288.11, 474.77, 288.11, 474.77, 293.95, 515.7, 269.98, 517.45, 274.07, 488.8, 270.57, 487.05, 266.47, 508.68, 260.04, 513.36, 243.67, 509.26, 250.1, 472.43, 250.1, 472.43, 243.67, 428.0, 238.41, 381.81, 217.36, 363.69, 214.44, 318.09, 207.43, 280.67, 207.43, 163.74, 222.63, 126.32, 231.98, 84.81, 233.15, 82.48, 251.27, 73.12, 253.61, 71.37]], "area": 38143.47230000001, "iscrowd": 0, "image_id": 487992, "bbox": [207.43, 71.37, 129.2, 446.08], "category_id": 1, "id": 1720428, "split": "val", "sentences": [{"tokens": ["the", "girl", "with", "red", "tie"], "raw": "the girl with red tie", "sent_id": 76872, "sent": "the girl with red tie"}, {"tokens": ["the", "lady", "on", "the", "right", "with", "the", "red", "necktie"], "raw": "The lady on the right with the red necktie.", "sent_id": 76873, "sent": "the lady on the right with the red necktie"}], "file_name": "COCO_train2014_000000487992_1720428.jpg", "ann_id": 1720428, "sent_ids": [76872, 76873], "ref_id": 34517}, {"segmentation": [[498.25, 348.62, 500.0, 201.26, 500.0, 108.87, 500.0, 16.49, 500.0, 0.0, 274.21, 0.0, 181.82, 0.0, 89.43, 0.0, 0.0, 0.0, 0.0, 85.78, 0.0, 180.01, 0.0, 272.86, 0.0, 365.25, 0.0, 375.0, 0.0, 375.0, 201.68, 375.0, 228.94, 375.0, 263.12, 375.0, 267.74, 375.0]], "area": 184284.46810000003, "iscrowd": 0, "image_id": 548416, "bbox": [0.0, 0.0, 500.0, 375.0], "category_id": 51, "id": 1903307, "split": "val", "sentences": [{"tokens": ["soup", "with", "chicken", "and", "carrots", "and", "yellow", "broth"], "raw": "Soup with chicken and carrots and yellow broth.", "sent_id": 76956, "sent": "soup with chicken and carrots and yellow broth"}, {"tokens": ["bowl", "of", "soup"], "raw": "bowl of soup", "sent_id": 76957, "sent": "bowl of soup"}], "file_name": "COCO_train2014_000000548416_1903307.jpg", "ann_id": 1903307, "sent_ids": [76956, 76957], "ref_id": 34551}, {"segmentation": [[25.44, 208.25, 30.84, 199.77, 49.34, 178.18, 56.27, 175.1, 71.69, 173.56, 86.34, 176.64, 93.28, 179.72, 100.99, 182.81, 111.01, 182.81, 120.26, 182.81, 132.59, 185.89, 141.84, 189.75, 150.32, 193.6, 158.8, 201.31, 167.28, 202.85, 175.76, 203.62, 177.3, 204.39, 183.47, 213.64, 185.01, 295.36, 168.82, 298.44, 177.3, 317.71, 179.61, 320.02, 181.93, 331.59, 181.16, 338.53, 177.3, 343.15, 170.36, 326.19, 168.82, 314.63, 163.43, 309.23, 149.55, 300.75, 148.01, 296.9, 139.53, 289.96, 128.74, 279.17, 118.72, 273.77, 115.63, 269.15, 104.84, 262.98, 93.28, 254.5, 87.11, 250.65, 81.71, 246.02, 79.4, 239.08, 75.55, 232.14, 70.92, 229.06, 65.52, 222.89, 60.13, 216.73, 55.5, 213.64, 47.79, 211.33, 37.0, 211.33, 28.52, 210.56, 18.5, 210.56]], "area": 11720.612400000002, "iscrowd": 0, "image_id": 445628, "bbox": [18.5, 173.56, 166.51, 169.59], "category_id": 16, "id": 36715, "split": "val", "sentences": [{"tokens": ["a", "bird", "standing", "on", "the", "cage"], "raw": "a bird standing on the cage", "sent_id": 77011, "sent": "a bird standing on the cage"}, {"tokens": ["a", "small", "bird", "hanging", "on", "the", "net"], "raw": "A small bird hanging on the net.", "sent_id": 77012, "sent": "a small bird hanging on the net"}], "file_name": "COCO_train2014_000000445628_36715.jpg", "ann_id": 36715, "sent_ids": [77011, 77012], "ref_id": 34576}, {"segmentation": [[427.08, 413.61, 428.04, 372.25, 430.92, 340.51, 425.15, 328.96, 415.53, 302.99, 441.5, 302.99, 470.36, 310.69, 482.87, 302.03, 484.79, 290.49, 473.25, 280.87, 449.2, 283.76, 420.34, 282.79, 409.76, 278.95, 407.84, 259.71, 396.3, 236.62, 393.41, 202.96, 407.84, 185.64, 429.96, 165.44, 414.57, 146.21, 410.72, 126.01, 407.84, 115.43, 427.08, 103.88, 442.47, 101.0, 460.74, 105.81, 473.25, 132.74, 477.09, 152.94, 477.09, 169.29, 484.79, 170.25, 519.42, 198.15, 506.91, 225.08, 500.18, 232.78, 516.53, 241.43, 508.84, 252.98, 527.11, 249.13, 526.15, 283.76, 515.57, 302.99, 520.38, 324.15, 510.76, 336.66, 540.58, 423.23, 512.68, 423.23, 486.71, 384.75, 480.94, 359.74, 467.48, 355.9, 455.93, 424.19, 435.73, 424.19, 411.69, 424.19]], "area": 26386.157750000002, "iscrowd": 0, "image_id": 280191, "bbox": [393.41, 101.0, 147.17, 323.19], "category_id": 1, "id": 459191, "split": "val", "sentences": [{"tokens": ["a", "girl", "sitting", "on", "a", "bench", "near", "a", "boy"], "raw": "A girl sitting on a bench near a boy.", "sent_id": 77025, "sent": "a girl sitting on a bench near a boy"}, {"tokens": ["a", "young", "girl", "sitting", "and", "smiling", "on", "a", "bench"], "raw": "A young girl sitting and smiling on a bench.", "sent_id": 77026, "sent": "a young girl sitting and smiling on a bench"}], "file_name": "COCO_train2014_000000280191_459191.jpg", "ann_id": 459191, "sent_ids": [77025, 77026], "ref_id": 34584}, {"segmentation": [[157.85, 102.74, 153.54, 124.27, 166.46, 170.19, 193.72, 247.68, 206.64, 310.82, 209.51, 342.39, 243.95, 329.47, 289.87, 326.6, 301.35, 338.08, 314.26, 340.95, 342.96, 208.93, 374.53, 130.01, 375.96, 115.66, 350.13, 94.13, 312.83, 76.91, 272.65, 65.43, 238.21, 68.3, 195.16, 85.52, 162.15, 95.57, 159.28, 105.61]], "area": 42102.33314999999, "iscrowd": 0, "image_id": 183392, "bbox": [153.54, 65.43, 222.42, 276.96], "category_id": 47, "id": 672602, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "rice"], "raw": "A glass of rice.", "sent_id": 77047, "sent": "a glass of rice"}, {"tokens": ["a", "clear", "glass", "sits", "on", "a", "white", "plate", "holding", "rice"], "raw": "A clear glass sits on a white plate holding rice", "sent_id": 77048, "sent": "a clear glass sits on a white plate holding rice"}], "file_name": "COCO_train2014_000000183392_672602.jpg", "ann_id": 672602, "sent_ids": [77047, 77048], "ref_id": 34591}, {"segmentation": [[367.38, 137.97, 359.06, 159.58, 375.69, 172.88, 387.32, 374.03, 372.36, 375.69, 364.05, 467.12, 379.01, 503.69, 397.3, 498.7, 397.3, 468.78, 420.57, 462.13, 425.56, 147.95, 412.26, 128.0, 405.61, 106.39, 369.04, 137.97]], "area": 17067.333149999995, "iscrowd": 0, "image_id": 520590, "bbox": [359.06, 106.39, 66.5, 397.3], "category_id": 1, "id": 2164265, "split": "val", "sentences": [{"tokens": ["floral", "fabric"], "raw": "floral fabric", "sent_id": 77109, "sent": "floral fabric"}, {"tokens": ["a", "person", "in", "a", "floral", "suit"], "raw": "A person in a floral suit.", "sent_id": 77110, "sent": "a person in a floral suit"}], "file_name": "COCO_train2014_000000520590_2164265.jpg", "ann_id": 2164265, "sent_ids": [77109, 77110], "ref_id": 34619}, {"segmentation": [[481.35, 234.02, 452.51, 231.8, 424.78, 218.49, 372.65, 208.51, 392.62, 338.27, 408.15, 378.2, 408.15, 378.2, 441.42, 384.85, 449.18, 309.44, 483.56, 319.42, 488.0, 348.25, 469.15, 378.2, 482.45, 383.75, 482.45, 383.75, 511.29, 350.47, 511.29, 350.47, 513.51, 306.11, 500.2, 269.51], [351.58, 298.35, 316.09, 288.36, 299.45, 351.58, 299.45, 351.58, 306.11, 363.78, 324.96, 353.8, 337.16, 384.85, 358.24, 384.85, 354.91, 347.15, 363.78, 337.16, 363.78, 317.2]], "area": 19661.814850000006, "iscrowd": 0, "image_id": 495609, "bbox": [299.45, 208.51, 214.06, 176.34], "category_id": 22, "id": 1821100, "split": "val", "sentences": [{"tokens": ["the", "elephant", "on", "the", "right", "is", "ahead", "of", "the", "other", "one"], "raw": "The elephant on the right is ahead of the other one.", "sent_id": 77239, "sent": "the elephant on the right is ahead of the other one"}, {"tokens": ["an", "elephant", "walking", "in", "the", "front"], "raw": "an elephant walking in the front", "sent_id": 77240, "sent": "an elephant walking in the front"}], "file_name": "COCO_train2014_000000495609_1821100.jpg", "ann_id": 1821100, "sent_ids": [77239, 77240], "ref_id": 34666}, {"segmentation": [[383.98, 127.44, 371.64, 127.44, 370.0, 117.58, 372.47, 104.42, 389.73, 97.02, 397.96, 92.09, 405.36, 83.87, 408.64, 62.49, 407.82, 49.33, 500.0, 49.33, 500.0, 240.09, 477.71, 245.02, 480.18, 232.69, 483.47, 161.98, 471.13, 134.84, 464.56, 118.4, 447.29, 115.11, 416.04, 115.11]], "area": 9922.508149999998, "iscrowd": 0, "image_id": 101140, "bbox": [370.0, 49.33, 130.0, 195.69], "category_id": 8, "id": 1798294, "split": "val", "sentences": [{"tokens": ["the", "yellow", "truck", "behind", "the", "truck", "loaded", "with", "bags"], "raw": "The yellow truck behind the truck loaded with bags", "sent_id": 77241, "sent": "the yellow truck behind the truck loaded with bags"}, {"tokens": ["a", "hidden", "truck"], "raw": "A hidden truck.", "sent_id": 77242, "sent": "a hidden truck"}], "file_name": "COCO_train2014_000000101140_1798294.jpg", "ann_id": 1798294, "sent_ids": [77241, 77242], "ref_id": 34667}, {"segmentation": [[360.34, 293.4, 358.99, 297.44, 357.98, 302.49, 352.26, 305.18, 347.55, 305.85, 346.87, 303.5, 344.85, 301.14, 343.85, 292.73, 348.22, 287.0, 349.9, 278.93, 345.53, 267.15, 332.74, 262.44, 323.99, 261.43, 315.24, 251.67, 313.89, 243.93, 315.24, 238.88, 320.62, 235.51, 326.34, 239.21, 331.06, 244.26, 334.76, 248.64, 336.78, 246.62, 340.82, 249.65, 349.9, 236.86, 364.04, 230.13, 373.8, 231.47, 384.9, 239.55, 386.25, 245.27, 390.29, 242.24, 404.42, 241.23, 414.18, 244.6, 422.26, 249.31, 439.76, 247.96, 451.21, 248.3, 462.65, 249.65, 481.83, 256.04, 495.97, 271.19, 501.69, 282.63, 496.98, 315.95, 497.31, 329.07, 498.66, 337.15, 503.71, 346.91, 505.73, 350.95, 505.05, 357.34, 511.45, 395.04, 509.09, 397.73, 506.74, 400.42, 505.05, 407.83, 501.69, 408.16, 494.28, 407.49, 490.92, 406.14, 495.29, 398.4, 497.99, 392.35, 498.66, 382.25, 495.97, 364.07, 489.57, 348.26, 479.81, 335.8, 478.13, 331.77, 473.75, 325.03, 472.41, 329.07, 469.72, 329.41, 472.07, 341.19, 479.14, 353.64, 476.11, 356.67, 465.0, 393.69, 456.25, 395.37, 457.94, 400.42, 452.89, 400.42, 450.2, 400.76, 444.14, 399.08, 446.16, 394.7, 446.83, 389.65, 453.9, 384.94, 459.62, 371.82, 462.65, 360.37, 456.25, 345.56, 449.19, 332.1, 443.8, 324.7, 434.71, 324.7, 423.61, 324.36, 417.21, 322.68, 415.87, 329.07, 414.18, 339.84, 413.18, 350.61, 415.53, 360.04, 414.18, 364.41, 414.18, 368.45, 411.16, 371.48, 405.1, 371.14, 401.06, 369.46, 401.73, 365.08, 402.07, 361.38, 404.76, 360.04, 405.77, 352.3, 406.44, 341.19, 403.75, 333.45, 404.42, 329.07, 403.75, 321.33, 400.72, 321.67, 396.01, 336.81, 392.31, 352.63, 391.3, 365.76, 391.97, 369.46, 391.64, 375.85, 389.62, 377.54, 388.27, 378.88, 386.59, 385.28, 382.21, 387.3, 373.46, 387.63, 371.44, 384.27, 375.14, 379.56, 378.51, 374.51, 383.9, 364.75, 385.91, 346.91, 384.57, 338.5, 384.57, 326.04, 381.2, 314.26, 374.81, 308.54, 366.06, 296.43, 361.01, 292.39, 361.35, 293.06]], "area": 15335.327350000012, "iscrowd": 0, "image_id": 338819, "bbox": [313.89, 230.13, 197.56, 178.03], "category_id": 20, "id": 66230, "split": "val", "sentences": [{"tokens": ["the", "right", "goat", "of", "the", "ones", "butting", "heads"], "raw": "the right goat of the ones butting heads", "sent_id": 77304, "sent": "the right goat of the ones butting heads"}, {"tokens": ["white", "animal", "closest", "to", "the", "yellow", "line", "in", "the", "road"], "raw": "white animal closest to the yellow line in the road", "sent_id": 77305, "sent": "white animal closest to the yellow line in the road"}], "file_name": "COCO_train2014_000000338819_66230.jpg", "ann_id": 66230, "sent_ids": [77304, 77305], "ref_id": 34693}, {"segmentation": [[215.34, 151.6, 226.01, 137.05, 231.84, 128.32, 230.87, 103.1, 235.72, 89.52, 243.48, 85.64, 254.15, 94.37, 277.43, 92.43, 275.49, 101.16, 302.65, 136.08, 310.41, 135.11, 328.84, 148.69, 343.39, 171.97, 343.39, 174.88, 345.33, 199.13, 345.33, 209.8, 353.09, 203.98, 355.03, 209.8, 334.66, 220.47, 315.26, 231.14, 296.83, 235.02, 296.83, 238.9, 306.53, 245.69, 304.59, 249.57, 295.86, 248.6, 288.1, 268.0, 288.1, 269.94, 297.8, 280.61, 298.77, 277.7, 307.5, 283.52, 311.38, 287.4, 308.47, 292.25, 305.56, 295.16, 296.83, 295.16, 290.04, 289.34, 280.34, 278.67, 275.49, 306.8, 274.52, 323.29, 252.21, 322.32, 260.94, 300.98, 271.61, 275.76, 266.76, 265.09, 265.79, 256.36, 268.7, 216.59, 259.97, 205.92, 256.09, 190.4, 252.21, 183.61, 252.21, 172.94, 252.21, 163.24, 249.3, 155.48, 236.69, 163.24, 215.34, 163.24, 217.28, 156.45], [320.11, 229.2, 322.05, 243.75, 326.9, 265.09, 327.87, 281.58, 323.02, 294.19, 322.05, 298.07, 331.75, 303.89, 335.63, 297.1, 334.66, 287.4, 336.6, 273.82, 341.45, 258.3, 339.51, 250.54, 337.57, 235.99, 340.48, 219.5], [374.43, 239.87, 385.1, 261.21, 385.1, 279.64, 393.83, 295.16, 400.62, 300.01, 407.41, 297.1, 409.35, 285.46, 393.83, 270.91, 392.86, 258.3, 391.89, 246.66, 390.92, 234.05, 386.07, 226.29]], "area": 15240.5333, "iscrowd": 0, "image_id": 238667, "bbox": [215.34, 85.64, 194.01, 237.65], "category_id": 19, "id": 54540, "split": "val", "sentences": [{"tokens": ["a", "man", "horse", "rideing", "and", "take", "helment"], "raw": "A  Man  horse rideing and take helment", "sent_id": 77341, "sent": "a man horse rideing and take helment"}], "file_name": "COCO_train2014_000000238667_54540.jpg", "ann_id": 54540, "sent_ids": [77341], "ref_id": 34705}, {"segmentation": [[222.91, 174.73, 242.56, 255.93, 318.52, 266.4, 313.28, 347.61, 304.11, 345.64, 305.42, 308.97, 299.53, 326.65, 301.49, 382.31, 296.91, 399.34, 293.64, 337.13, 294.95, 322.07, 284.47, 316.83, 291.67, 277.54, 270.06, 280.81, 257.62, 289.32, 237.97, 296.53, 226.19, 299.8, 214.4, 298.49, 211.78, 285.39, 206.54, 272.95, 201.96, 261.82, 200.65, 255.93, 196.72, 250.03, 194.1, 244.14, 187.55, 205.5, 192.13, 194.37, 217.02, 176.04, 221.6, 174.07]], "area": 7961.132499999995, "iscrowd": 0, "image_id": 140821, "bbox": [187.55, 174.07, 130.97, 225.27], "category_id": 62, "id": 1588856, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "sitting", "in", "the", "corner", "next", "to", "a", "few", "rolls", "of", "toilet", "paper"], "raw": "A wooden chair sitting in the corner next to a few rolls of toilet paper.", "sent_id": 77402, "sent": "a wooden chair sitting in the corner next to a few rolls of toilet paper"}, {"tokens": ["the", "chair", "has", "nothing", "on", "it", "and", "is", "in", "the", "corner", "of", "the", "wall"], "raw": "The chair has nothing on it and is in the corner of the wall", "sent_id": 77403, "sent": "the chair has nothing on it and is in the corner of the wall"}], "file_name": "COCO_train2014_000000140821_1588856.jpg", "ann_id": 1588856, "sent_ids": [77402, 77403], "ref_id": 34723}, {"segmentation": [[265.97, 407.68, 446.7, 400.49, 450.81, 351.2, 480.59, 367.63, 496.0, 370.71, 505.24, 364.55, 504.21, 348.12, 473.4, 320.39, 469.3, 299.86, 456.97, 294.72, 440.54, 294.72, 433.35, 297.8, 410.76, 322.45, 396.39, 347.09, 342.99, 354.28, 296.78, 351.2, 276.24, 359.42, 267.0, 372.77, 257.75, 390.22]], "area": 14016.0078, "iscrowd": 0, "image_id": 36546, "bbox": [257.75, 294.72, 247.49, 112.96], "category_id": 24, "id": 591891, "split": "val", "sentences": [{"tokens": ["a", "zebra", "under", "an", "alcove"], "raw": "A zebra under an alcove", "sent_id": 77410, "sent": "a zebra under an alcove"}, {"tokens": ["a", "zebra", "laying", "down"], "raw": "A zebra laying down.", "sent_id": 77411, "sent": "a zebra laying down"}], "file_name": "COCO_train2014_000000036546_591891.jpg", "ann_id": 591891, "sent_ids": [77410, 77411], "ref_id": 34727}, {"segmentation": [[1.13, 465.32, 5.65, 333.18, 1.13, 145.69, 46.31, 146.82, 96.0, 171.67, 131.01, 146.82, 129.88, 114.07, 150.21, 85.84, 193.13, 90.35, 208.94, 125.36, 192.0, 150.21, 222.49, 147.95, 216.85, 114.07, 228.14, 89.22, 262.02, 82.45, 292.52, 107.29, 313.98, 82.45, 350.12, 79.06, 370.45, 106.16, 400.94, 81.32, 432.56, 86.96, 450.64, 116.33, 467.58, 98.26, 503.72, 85.84, 537.6, 114.07, 530.82, 147.95, 564.71, 144.56, 590.68, 167.15, 578.26, 213.46, 611.01, 213.46, 626.82, 234.92, 638.12, 221.36, 640.0, 457.41, 359.15, 465.32, 202.16, 474.35, 2.26, 469.84]], "area": 219395.25460000001, "iscrowd": 0, "image_id": 415447, "bbox": [1.13, 79.06, 638.87, 395.29], "category_id": 55, "id": 1054146, "split": "val", "sentences": [{"tokens": ["oranges", "stacked"], "raw": "Oranges stacked", "sent_id": 77509, "sent": "oranges stacked"}, {"tokens": ["a", "pile", "of", "oranges", "for", "sale"], "raw": "A pile of oranges for sale.", "sent_id": 77510, "sent": "a pile of oranges for sale"}], "file_name": "COCO_train2014_000000415447_1054146.jpg", "ann_id": 1054146, "sent_ids": [77509, 77510], "ref_id": 34773}, {"segmentation": [[247.94, 42.92, 299.64, 47.71, 355.16, 78.34, 488.22, 169.28, 479.61, 220.98, 468.12, 227.68, 468.12, 199.92, 469.08, 172.16, 460.46, 165.45, 457.59, 154.92, 444.19, 159.71, 441.32, 168.33, 442.27, 234.38, 404.94, 257.36, 404.94, 275.54, 386.75, 277.46, 378.13, 275.54, 228.8, 384.68, 159.87, 363.62, 141.68, 356.91, 137.85, 364.57, 114.88, 373.19, 108.18, 403.82, 101.47, 404.78, 106.26, 372.23, 119.66, 363.62, 84.24, 349.26, 97.64, 335.85, 87.11, 287.03, 134.02, 269.8, 123.49, 196.09, 129.24, 161.62, 157.96, 85.04, 188.59, 59.19]], "area": 83572.08395, "iscrowd": 0, "image_id": 497386, "bbox": [84.24, 42.92, 403.98, 361.86], "category_id": 7, "id": 172743, "split": "val", "sentences": [{"tokens": ["a", "train", "numbered", "332010"], "raw": "A train numbered 332010.", "sent_id": 77548, "sent": "a train numbered 332010"}, {"tokens": ["a", "bullet", "train", "with", "a", "japanese", "sun", "on", "the", "side"], "raw": "A bullet train with a Japanese Sun on the side.", "sent_id": 77549, "sent": "a bullet train with a japanese sun on the side"}], "file_name": "COCO_train2014_000000497386_172743.jpg", "ann_id": 172743, "sent_ids": [77548, 77549], "ref_id": 34790}, {"segmentation": [[193.13, 264.28, 187.48, 271.06, 178.45, 274.45, 161.51, 276.71, 161.51, 272.19, 162.64, 265.41, 166.02, 255.25, 166.02, 252.99, 185.22, 257.51, 190.87, 260.89], [154.73, 217.98, 152.47, 211.2, 142.31, 203.29, 133.27, 213.46, 128.75, 220.24, 125.36, 225.88, 119.72, 231.53, 108.42, 234.92, 105.04, 241.69, 94.87, 269.93, 90.35, 284.61, 92.61, 309.46, 92.61, 329.79, 93.74, 367.06, 94.87, 382.87, 102.78, 405.46, 109.55, 422.4, 97.13, 435.95, 84.71, 432.56, 54.21, 426.92, 45.18, 415.62, 35.01, 398.68, 28.24, 372.71, 36.14, 318.49, 42.92, 294.78, 54.21, 266.54, 62.12, 246.21, 68.89, 236.05, 83.58, 222.49, 105.04, 213.46, 114.07, 204.42, 138.92, 184.09, 138.92, 182.96, 135.53, 164.89, 121.98, 119.72, 135.53, 100.52, 152.47, 103.91, 166.02, 132.14, 175.06, 154.73, 182.96, 147.95, 203.29, 145.69, 211.2, 153.6, 224.75, 175.06, 233.79, 201.04, 246.21, 195.39, 267.67, 178.45, 281.22, 176.19, 293.65, 177.32, 306.07, 186.35, 292.52, 206.68, 282.35, 219.11, 272.19, 219.11, 242.82, 220.24, 239.44, 221.36, 241.69, 250.73, 236.05, 266.54, 230.4, 273.32, 213.46, 274.45, 214.59, 254.12, 220.24, 230.4, 222.49, 220.24, 225.88, 206.68, 212.33, 230.4, 207.81, 230.4, 198.78, 228.14, 198.78, 217.98, 186.35, 202.16, 184.09, 185.22, 168.28, 190.87, 162.64, 208.94, 161.51, 210.07, 158.12, 214.59]], "area": 23012.371999999996, "iscrowd": 0, "image_id": 100667, "bbox": [28.24, 100.52, 277.83, 335.43], "category_id": 52, "id": 1045414, "split": "val", "sentences": [{"tokens": ["man", "on", "left", "bite", "banana", "with", "teeth"], "raw": "man on left bite banana with teeth", "sent_id": 77583, "sent": "man on left bite banana with teeth"}], "file_name": "COCO_train2014_000000100667_1045414.jpg", "ann_id": 1045414, "sent_ids": [77583], "ref_id": 34806}, {"segmentation": [[162.57, 97.44, 110.4, 148.59, 93.01, 191.56, 107.33, 269.3, 103.24, 301.01, 112.45, 311.24, 123.7, 316.36, 108.36, 337.84, 100.17, 341.93, 109.38, 371.6, 113.47, 388.99, 120.63, 422.75, 184.06, 427.86, 264.87, 426.84, 271.01, 401.26, 269.99, 398.19, 256.69, 385.92, 275.1, 352.16, 288.4, 345.0, 304.77, 343.98, 301.7, 315.33, 291.47, 309.2, 282.26, 304.08, 280.22, 294.88, 277.15, 232.47, 258.73, 176.21, 245.43, 149.61, 236.23, 140.41, 257.71, 125.06, 272.03, 105.63, 278.17, 88.24, 279.19, 56.53, 277.15, 48.34, 258.73, 26.86, 246.46, 17.65, 229.07, 17.65, 208.61, 23.79, 197.36, 45.27, 191.22, 68.8, 186.1, 79.03, 175.87, 89.26]], "area": 58987.737550000005, "iscrowd": 0, "image_id": 174749, "bbox": [93.01, 17.65, 211.76, 410.21], "category_id": 1, "id": 2166903, "split": "val", "sentences": [{"tokens": ["a", "chef", "wearing", "a", "black", "apron"], "raw": "A chef wearing a black apron.", "sent_id": 77614, "sent": "a chef wearing a black apron"}, {"tokens": ["a", "man", "in", "a", "white", "and", "black", "striped", "apron"], "raw": "A man in a white and black striped apron.", "sent_id": 77615, "sent": "a man in a white and black striped apron"}], "file_name": "COCO_train2014_000000174749_2166903.jpg", "ann_id": 2166903, "sent_ids": [77614, 77615], "ref_id": 34821}, {"segmentation": [[112.27, 68.76, 129.63, 62.19, 167.16, 57.5, 165.75, 31.7, 178.89, 29.35, 184.99, 67.82, 184.05, 71.11, 190.62, 101.13, 193.9, 136.32, 193.9, 167.28, 192.02, 183.23, 184.05, 194.49, 171.85, 200.59, 151.68, 202.47, 139.95, 197.78, 131.5, 189.8, 126.81, 179.01, 115.55, 130.22, 114.14, 108.64, 115.08, 88.93]], "area": 10290.3115, "iscrowd": 0, "image_id": 215908, "bbox": [112.27, 29.35, 81.63, 173.12], "category_id": 77, "id": 326051, "split": "val", "sentences": [{"tokens": ["a", "flip", "phone", "displaying", "the", "time", "7", ":", "45"], "raw": "A flip phone displaying the time 7:45.", "sent_id": 77616, "sent": "a flip phone displaying the time 7 : 45"}, {"tokens": ["a", "silver", "cell", "phone"], "raw": "a silver cell phone", "sent_id": 77617, "sent": "a silver cell phone"}], "file_name": "COCO_train2014_000000215908_326051.jpg", "ann_id": 326051, "sent_ids": [77616, 77617], "ref_id": 34822}, {"segmentation": [[229.17, 337.4, 212.2, 337.4, 212.2, 330.72, 219.91, 315.81, 225.05, 299.35, 226.08, 275.7, 226.08, 269.53, 230.2, 248.96, 234.82, 226.85, 218.37, 200.62, 214.77, 187.25, 223.51, 170.8, 224.03, 167.2, 224.03, 148.69, 234.31, 140.46, 247.68, 144.06, 255.39, 154.86, 265.68, 172.34, 280.07, 196.0, 286.24, 221.71, 282.13, 263.87, 282.13, 285.47, 293.96, 309.12, 285.73, 330.72, 274.42, 338.95, 270.82, 329.69, 268.25, 301.41, 266.19, 287.01, 264.65, 271.58, 264.65, 256.67, 263.62, 249.47, 258.99, 248.96, 251.28, 263.87, 246.65, 280.84, 238.94, 310.66, 232.77, 332.26]], "area": 8660.67565, "iscrowd": 0, "image_id": 122231, "bbox": [212.2, 140.46, 81.76, 198.49], "category_id": 1, "id": 503508, "split": "val", "sentences": [{"tokens": ["the", "asian", "woman", "in", "blue"], "raw": "The asian woman in blue.", "sent_id": 77620, "sent": "the asian woman in blue"}, {"tokens": ["a", "person", "in", "a", "blue", "shirt"], "raw": "A person in a blue shirt.", "sent_id": 77621, "sent": "a person in a blue shirt"}], "file_name": "COCO_train2014_000000122231_503508.jpg", "ann_id": 503508, "sent_ids": [77620, 77621], "ref_id": 34824}, {"segmentation": [[636.76, 475.14, 616.22, 466.49, 595.68, 463.24, 581.62, 460.0, 572.97, 447.03, 570.81, 436.22, 570.81, 421.08, 578.38, 411.35, 591.35, 411.35, 611.89, 409.19, 627.03, 411.35, 636.76, 415.68, 640.0, 417.84], [640.0, 362.7, 628.11, 372.43, 616.22, 381.08, 604.32, 382.16, 592.43, 382.16, 584.86, 375.68, 572.97, 380.0, 566.49, 385.41, 565.41, 391.89, 562.16, 397.3, 555.68, 397.3, 536.22, 372.43, 536.22, 364.86, 540.54, 348.65, 554.59, 336.76, 561.08, 329.19, 570.81, 327.03, 582.7, 333.51, 590.27, 335.68, 598.92, 337.84, 620.54, 337.84, 634.59, 333.51, 640.0, 330.27]], "area": 8178.308200000002, "iscrowd": 0, "image_id": 544701, "bbox": [536.22, 327.03, 103.78, 148.11], "category_id": 1, "id": 523624, "split": "val", "sentences": [{"tokens": ["two", "hands", ",", "one", "with", "a", "silver", "bracelet", ",", "grabbing", "white", "plastic", "-", "ware", "forks"], "raw": "Two hands, one with a silver bracelet, grabbing white plastic-ware forks.", "sent_id": 77659, "sent": "two hands , one with a silver bracelet , grabbing white plastic - ware forks"}, {"tokens": ["hands", "holding", "up", "two", "forks", ",", "on", "hand", "wearing", "a", "ring", "and", "a", "bracelet"], "raw": "Hands holding up two forks, on hand wearing a ring and a bracelet", "sent_id": 77660, "sent": "hands holding up two forks , on hand wearing a ring and a bracelet"}], "file_name": "COCO_train2014_000000544701_523624.jpg", "ann_id": 523624, "sent_ids": [77659, 77660], "ref_id": 34840}, {"segmentation": [[470.53, 425.0, 469.77, 420.58, 471.54, 415.02, 475.83, 408.72, 479.36, 404.68, 479.87, 387.26, 483.4, 372.37, 487.44, 363.79, 500.06, 354.96, 516.72, 354.2, 533.37, 354.71, 539.68, 354.71, 543.97, 348.65, 556.48, 339.52, 575.81, 334.21, 580.65, 333.72, 580.07, 328.11, 580.53, 322.29, 584.05, 316.62, 588.95, 313.1, 599.58, 311.59, 603.92, 311.59, 609.8, 299.71, 621.46, 282.22, 630.86, 267.32, 640.0, 254.36, 639.6, 341.49, 640.0, 425.0, 471.32, 425.0]], "area": 15362.141150000003, "iscrowd": 0, "image_id": 257867, "bbox": [469.77, 254.36, 170.23, 170.64], "category_id": 3, "id": 357994, "split": "val", "sentences": [{"tokens": ["a", "white", "car", "following", "a", "tow", "truck"], "raw": "a white car following a tow truck", "sent_id": 77732, "sent": "a white car following a tow truck"}, {"tokens": ["this", "is", "a", "white", "car", "behind", "a", "tow", "truck"], "raw": "this is a white car behind a tow truck", "sent_id": 77733, "sent": "this is a white car behind a tow truck"}], "file_name": "COCO_train2014_000000257867_357994.jpg", "ann_id": 357994, "sent_ids": [77732, 77733], "ref_id": 34870}, {"segmentation": [[266.07, 465.54, 254.56, 442.53, 258.89, 432.15, 252.25, 414.12, 255.1, 379.01, 256.05, 361.93, 241.81, 343.91, 203.86, 339.16, 197.22, 321.13, 182.03, 312.59, 161.16, 265.15, 162.11, 259.46, 168.75, 257.56, 168.75, 249.02, 163.06, 249.02, 159.26, 254.71, 157.36, 254.71, 157.36, 245.22, 153.57, 247.12, 151.67, 251.87, 149.77, 251.87, 148.82, 247.12, 144.08, 256.61, 142.18, 249.02, 135.54, 245.22, 132.69, 249.97, 138.39, 259.46, 142.18, 264.2, 144.08, 276.54, 149.77, 281.28, 159.26, 352.45, 151.67, 368.58, 159.26, 386.6, 164.01, 411.28, 162.11, 447.33, 164.01, 476.75, 167.8, 477.7, 170.65, 436.89, 172.55, 466.31, 178.24, 479.59, 184.88, 477.7, 180.14, 464.41, 189.63, 391.35, 201.01, 392.3, 216.19, 386.6, 238.02, 424.56, 252.25, 452.08, 254.15, 474.85, 268.38, 465.36]], "area": 10546.606349999995, "iscrowd": 0, "image_id": 348935, "bbox": [132.69, 245.22, 135.69, 234.37], "category_id": 25, "id": 599970, "split": "val", "sentences": [{"tokens": ["small", "giraffe", "on", "left"], "raw": "small giraffe on left", "sent_id": 77876, "sent": "small giraffe on left"}, {"tokens": ["the", "giraffe", "most", "close", "and", "facing", "the", "camera"], "raw": "the giraffe most close and facing the camera", "sent_id": 77877, "sent": "the giraffe most close and facing the camera"}], "file_name": "COCO_train2014_000000348935_599970.jpg", "ann_id": 599970, "sent_ids": [77876, 77877], "ref_id": 34929}, {"segmentation": [[89.04, 301.69, 110.1, 289.25, 134.04, 286.37, 155.1, 279.67, 163.72, 261.48, 203.93, 243.29, 249.88, 217.44, 292.96, 173.4, 317.86, 141.81, 341.79, 127.45, 368.6, 139.89, 375.3, 162.87, 370.51, 190.63, 353.28, 216.48, 344.66, 255.74, 337.96, 334.24, 333.17, 374.45, 321.69, 384.03, 314.98, 394.56, 304.45, 416.58, 306.37, 422.32, 130.21, 421.37, 155.1, 378.28, 155.1, 357.22, 150.31, 335.2, 144.57, 325.63, 135.95, 321.8, 112.02, 316.05, 97.65, 308.39]], "area": 43642.95235000001, "iscrowd": 0, "image_id": 131587, "bbox": [89.04, 127.45, 286.26, 294.87], "category_id": 25, "id": 1413851, "split": "val", "sentences": [{"tokens": ["a", "baby", "giraffe", "feeding", "from", "its", "mother"], "raw": "A baby giraffe feeding from its Mother.", "sent_id": 78021, "sent": "a baby giraffe feeding from its mother"}, {"tokens": ["a", "baby", "giraffe", "sucking", "milk"], "raw": "A baby giraffe sucking milk", "sent_id": 78022, "sent": "a baby giraffe sucking milk"}], "file_name": "COCO_train2014_000000131587_1413851.jpg", "ann_id": 1413851, "sent_ids": [78021, 78022], "ref_id": 34985}, {"segmentation": [[472.75, 244.02, 465.73, 254.2, 463.63, 258.76, 459.76, 264.73, 454.15, 266.48, 412.04, 262.97, 408.18, 269.64, 406.07, 273.5, 403.27, 283.68, 399.76, 327.54, 401.51, 333.16, 413.09, 333.16, 442.92, 331.4, 444.32, 334.21, 442.22, 350.35, 442.92, 354.91, 441.17, 366.5, 457.66, 372.11, 489.59, 364.39, 491.0, 293.15, 490.65, 284.03, 494.86, 278.76, 502.93, 276.31, 507.14, 270.34, 514.86, 265.08, 522.58, 267.53, 527.14, 273.5, 530.65, 276.31, 537.32, 276.66, 539.42, 261.22, 539.42, 259.11, 511.0, 248.94, 495.91, 244.72, 483.28, 242.62, 478.01, 242.62]], "area": 9254.755299999997, "iscrowd": 0, "image_id": 209467, "bbox": [399.76, 242.62, 139.66, 129.49], "category_id": 62, "id": 1579253, "split": "val", "sentences": [{"tokens": ["a", "black", "chair", "underneath", "a", "window"], "raw": "A black chair underneath a window", "sent_id": 78073, "sent": "a black chair underneath a window"}, {"tokens": ["the", "chair", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the chair on the right in the right hand picture", "sent_id": 78074, "sent": "the chair on the right in the right hand picture"}], "file_name": "COCO_train2014_000000209467_1579253.jpg", "ann_id": 1579253, "sent_ids": [78073, 78074], "ref_id": 35005}, {"segmentation": [[547.89, 373.75, 549.59, 363.56, 549.59, 362.71, 551.29, 361.01, 552.13, 356.76, 554.68, 349.97, 569.97, 270.97, 570.82, 270.12, 626.04, 262.48, 640.0, 236.99, 640.0, 255.68, 638.78, 276.92, 586.96, 285.41, 570.82, 373.75], [640.0, 208.11, 614.14, 201.32, 614.99, 192.82, 640.0, 197.92], [383.1, 372.9, 379.7, 315.14, 389.04, 324.49, 392.44, 372.9, 385.64, 372.9], [375.45, 230.2, 439.16, 231.05, 450.2, 226.8, 439.16, 238.69, 385.64, 242.09, 366.96, 243.79, 366.96, 233.6, 381.4, 231.05]], "area": 4661.9366000000055, "iscrowd": 0, "image_id": 371392, "bbox": [366.96, 192.82, 273.04, 180.93], "category_id": 62, "id": 1585114, "split": "val", "sentences": [{"tokens": ["a", "brown", "color", "wooden", "frame", "for", "the", "sofa"], "raw": "A brown color wooden frame for the sofa", "sent_id": 78114, "sent": "a brown color wooden frame for the sofa"}], "file_name": "COCO_train2014_000000371392_1585114.jpg", "ann_id": 1585114, "sent_ids": [78114], "ref_id": 35018}, {"segmentation": [[2.4, 290.71, 29.61, 297.87, 56.81, 306.46, 81.15, 317.92, 98.33, 299.3, 85.45, 270.67, 116.95, 243.47, 177.08, 219.13, 212.87, 224.85, 240.08, 227.72, 251.53, 252.06, 245.81, 296.44, 244.37, 337.96, 212.87, 376.62, 178.51, 405.26, 148.45, 453.94, 138.42, 505.48, 165.63, 571.34, 169.92, 637.2, 2.4, 638.63]], "area": 69747.85715, "iscrowd": 0, "image_id": 89788, "bbox": [2.4, 219.13, 249.13, 419.5], "category_id": 1, "id": 430394, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "red"], "raw": "the person in red", "sent_id": 78130, "sent": "the person in red"}, {"tokens": ["a", "woman", "in", "a", "red", "robe", "looking", "up", "at", "the", "person", "she", "is", "resting", "on"], "raw": "A woman in a red robe looking up at the person she is resting on", "sent_id": 78131, "sent": "a woman in a red robe looking up at the person she is resting on"}], "file_name": "COCO_train2014_000000089788_430394.jpg", "ann_id": 430394, "sent_ids": [78130, 78131], "ref_id": 35024}, {"segmentation": [[250.25, 183.85, 237.3, 136.39, 266.07, 87.49, 303.46, 78.86, 339.42, 103.31, 343.73, 133.51, 335.1, 168.03, 327.91, 205.42, 332.22, 242.82, 332.22, 287.4, 319.28, 308.97, 316.4, 334.86, 302.02, 357.87, 299.15, 373.69, 263.19, 379.45, 264.63, 319.04, 248.81, 284.52, 240.18, 252.88, 245.93, 231.31, 254.56, 212.61]], "area": 22129.645549999997, "iscrowd": 0, "image_id": 362657, "bbox": [237.3, 78.86, 106.43, 300.59], "category_id": 14, "id": 418260, "split": "val", "sentences": [{"tokens": ["a", "parking", "meter", "on", "the", "right", "of", "another", "parking", "meter"], "raw": "A parking meter on the right of another parking meter.", "sent_id": 78132, "sent": "a parking meter on the right of another parking meter"}, {"tokens": ["right", "meter"], "raw": "right meter", "sent_id": 78133, "sent": "right meter"}], "file_name": "COCO_train2014_000000362657_418260.jpg", "ann_id": 418260, "sent_ids": [78132, 78133], "ref_id": 35025}, {"segmentation": [[349.66, 99.83, 367.24, 71.9, 391.03, 49.14, 426.21, 24.31, 431.38, 31.55, 453.1, 29.48, 470.69, 22.24, 475.86, 32.59, 496.55, 40.86, 526.55, 29.48, 537.93, 29.48, 557.59, 25.34, 581.38, 23.28, 615.52, 15.0, 621.72, 10.86, 637.24, 11.9, 640.0, 193.97, 598.97, 187.76, 582.41, 203.28, 570.0, 226.03, 562.76, 237.41, 564.83, 252.93, 552.41, 259.14, 551.38, 233.28, 553.45, 212.59, 535.86, 210.52, 525.52, 202.24, 529.66, 241.55, 512.07, 237.41, 506.9, 207.41, 471.72, 197.07, 458.28, 166.03, 438.62, 156.72, 443.79, 137.07, 451.03, 133.97, 441.72, 128.79, 441.72, 113.28, 448.97, 107.07, 420.0, 101.9, 398.28, 112.24, 377.59, 124.66, 367.24, 116.38, 358.97, 103.97, 351.72, 99.83]], "area": 40384.37479999999, "iscrowd": 0, "image_id": 517123, "bbox": [349.66, 10.86, 290.34, 248.28], "category_id": 20, "id": 64968, "split": "val", "sentences": [{"tokens": ["the", "white", "sheep", "on", "the", "right"], "raw": "the white sheep on the right", "sent_id": 78343, "sent": "the white sheep on the right"}, {"tokens": ["a", "white", "sheep"], "raw": "A white sheep.", "sent_id": 78344, "sent": "a white sheep"}], "file_name": "COCO_train2014_000000517123_64968.jpg", "ann_id": 64968, "sent_ids": [78343, 78344], "ref_id": 35102}, {"segmentation": [[254.38, 322.44, 269.96, 315.94, 275.16, 304.26, 279.06, 270.49, 276.46, 235.43, 269.96, 227.64, 268.67, 222.44, 279.06, 208.16, 271.26, 186.08, 255.68, 171.8, 228.41, 182.19, 212.83, 192.58, 199.84, 192.58, 172.57, 205.56, 160.88, 232.83, 140.1, 392.56, 138.81, 444.51, 160.88, 461.39, 164.78, 496.45, 177.76, 540.6, 192.05, 544.5, 197.24, 526.32, 206.33, 502.94, 198.54, 476.97, 210.23, 445.8, 214.12, 458.79, 214.12, 522.42, 211.53, 549.69, 234.9, 545.8, 262.17, 541.9, 271.26, 528.92, 258.28, 523.72, 254.38, 513.33, 266.07, 467.88, 267.37, 440.61, 259.58, 343.21]], "area": 38827.51394999999, "iscrowd": 0, "image_id": 240500, "bbox": [138.81, 171.8, 140.25, 377.89], "category_id": 1, "id": 2176935, "split": "val", "sentences": [{"tokens": ["a", "picture", "of", "an", "older", "man", "with", "a", "black", "tench", "coat", "on", "standing", "next", "to", "a", "bench"], "raw": "A picture of an older man with a black tench coat on standing next to a bench.", "sent_id": 78429, "sent": "a picture of an older man with a black tench coat on standing next to a bench"}, {"tokens": ["an", "elderly", "man", "standing", "beside", "a", "park", "bench"], "raw": "An elderly man standing beside a park bench", "sent_id": 78430, "sent": "an elderly man standing beside a park bench"}], "file_name": "COCO_train2014_000000240500_2176935.jpg", "ann_id": 2176935, "sent_ids": [78429, 78430], "ref_id": 35134}, {"segmentation": [[220.15, 205.8, 224.32, 143.23, 231.84, 100.68, 238.52, 87.32, 257.71, 78.98, 293.58, 63.13, 514.69, 79.82, 639.86, 89.82, 640.0, 129.04, 518.03, 137.39, 511.35, 235.85, 512.19, 252.53, 392.87, 255.04, 390.37, 262.54, 377.85, 271.73, 356.99, 271.73, 351.16, 266.72, 346.15, 262.54, 264.38, 265.88, 225.16, 252.53]], "area": 60191.90390000001, "iscrowd": 0, "image_id": 358289, "bbox": [220.15, 63.13, 419.85, 208.6], "category_id": 6, "id": 165463, "split": "val", "sentences": [{"tokens": ["a", "double", "-", "decker", "buss", "between", "a", "single", "bus", "and", "another", "double", "decker", "buss", "in", "a", "parking", "lot"], "raw": "A double-decker buss between a single bus and another double decker buss in a parking lot", "sent_id": 78495, "sent": "a double - decker buss between a single bus and another double decker buss in a parking lot"}, {"tokens": ["passport", "application", "air", "bus", "running", "the", "road"], "raw": "PASSPORT APPLICATION AIR BUS RUNNING THE ROAD", "sent_id": 78496, "sent": "passport application air bus running the road"}], "file_name": "COCO_train2014_000000358289_165463.jpg", "ann_id": 165463, "sent_ids": [78495, 78496], "ref_id": 35162}, {"segmentation": [[316.65, 287.87, 336.8, 293.62, 350.24, 297.46, 356.95, 309.93, 363.67, 315.69, 367.51, 344.48, 378.06, 371.35, 391.5, 386.7, 410.69, 384.78, 400.13, 373.27, 393.42, 355.03, 391.5, 336.8, 383.82, 307.06, 381.9, 290.74, 376.14, 240.85, 373.27, 222.62, 365.59, 207.26, 353.11, 199.59, 332.0, 201.51, 323.37, 203.42, 300.34, 191.91, 285.95, 186.15, 268.67, 183.27, 234.13, 177.52, 213.02, 177.52, 182.31, 184.23, 148.73, 197.67, 129.54, 208.22, 108.43, 226.45, 91.16, 262.92, 96.91, 326.25, 96.91, 379.98, 96.91, 382.86, 108.43, 384.78, 107.47, 379.98, 103.63, 372.31, 106.51, 319.53, 105.55, 292.66, 108.43, 331.04, 110.35, 345.44, 114.19, 361.75, 111.31, 384.78, 139.13, 381.9, 136.26, 368.47, 142.01, 350.24, 146.81, 355.03, 152.57, 384.78, 184.23, 384.78, 191.91, 385.74, 199.59, 360.79, 220.7, 358.87, 241.81, 349.28, 260.04, 348.32, 261.96, 365.59, 278.27, 365.59, 303.22, 359.83, 300.34, 351.2]], "area": 45506.500950000016, "iscrowd": 0, "image_id": 495609, "bbox": [91.16, 177.52, 319.53, 209.18], "category_id": 22, "id": 1410007, "split": "val", "sentences": [{"tokens": ["the", "elephant", "in", "front"], "raw": "The elephant in front.", "sent_id": 78503, "sent": "the elephant in front"}, {"tokens": ["the", "elephant", "that", "is", "most", "visible"], "raw": "The elephant that is most visible.", "sent_id": 78504, "sent": "the elephant that is most visible"}], "file_name": "COCO_train2014_000000495609_1410007.jpg", "ann_id": 1410007, "sent_ids": [78503, 78504], "ref_id": 35164}, {"segmentation": [[439.41, 278.46, 373.69, 279.75, 369.83, 223.05, 356.94, 194.7, 369.83, 183.1, 364.67, 163.78, 356.94, 144.45, 399.46, 138.0, 389.15, 117.39, 398.17, 91.61, 411.06, 91.61, 426.52, 95.48, 430.39, 100.63, 430.39, 113.52, 443.28, 123.83, 453.58, 140.58, 461.32, 147.02, 476.78, 163.78, 498.68, 181.82, 499.97, 210.16, 493.53, 229.49, 476.78, 234.65, 441.99, 230.78, 441.99, 274.59]], "area": 16687.808200000003, "iscrowd": 0, "image_id": 458751, "bbox": [356.94, 91.61, 143.03, 188.14], "category_id": 11, "id": 417016, "split": "val", "sentences": [{"tokens": ["a", "bright", "green", "fire", "hydrant"], "raw": "A bright green fire hydrant.", "sent_id": 78556, "sent": "a bright green fire hydrant"}, {"tokens": ["green", "animated", "fire", "hydrant", "with", "foot", "on", "top", "edge"], "raw": "Green animated fire hydrant with foot on top edge.", "sent_id": 78557, "sent": "green animated fire hydrant with foot on top edge"}], "file_name": "COCO_train2014_000000458751_417016.jpg", "ann_id": 417016, "sent_ids": [78556, 78557], "ref_id": 35183}, {"segmentation": [[0.07, 236.77, 163.96, 220.8, 167.32, 262.83, 32.85, 279.64, 11.0, 283.84], [190.01, 216.6, 479.13, 188.03, 474.93, 226.69, 190.85, 256.94, 188.33, 214.08], [491.73, 188.87, 527.03, 188.87, 537.12, 197.27, 575.78, 192.23, 577.46, 208.2, 486.69, 220.8, 485.85, 193.07]], "area": 20510.672749999998, "iscrowd": 0, "image_id": 92685, "bbox": [0.07, 188.03, 577.39, 95.81], "category_id": 7, "id": 174231, "split": "val", "sentences": [{"tokens": ["a", "train", "between", "two", "other", "trains"], "raw": "A train between two other trains.", "sent_id": 78575, "sent": "a train between two other trains"}], "file_name": "COCO_train2014_000000092685_174231.jpg", "ann_id": 174231, "sent_ids": [78575], "ref_id": 35191}, {"segmentation": [[82.57, 549.22, 96.74, 520.86, 108.26, 512.0, 113.58, 439.34, 92.31, 421.61, 52.44, 490.73, 21.42, 536.81, 3.7, 549.22, 46.23, 546.56]], "area": 6370.36675, "iscrowd": 0, "image_id": 487992, "bbox": [3.7, 421.61, 109.88, 127.61], "category_id": 62, "id": 376538, "split": "val", "sentences": [{"tokens": ["the", "wood", "chair", "in", "front"], "raw": "The wood chair in front", "sent_id": 78598, "sent": "the wood chair in front"}, {"tokens": ["wooden", "thing", "in", "the", "front", "of", "the", "picture"], "raw": "wooden thing in the front of the picture", "sent_id": 78599, "sent": "wooden thing in the front of the picture"}], "file_name": "COCO_train2014_000000487992_376538.jpg", "ann_id": 376538, "sent_ids": [78598, 78599], "ref_id": 35202}, {"segmentation": [[12.94, 516.31, 35.96, 494.74, 83.42, 474.61, 129.44, 455.91, 192.72, 442.97, 256.0, 435.78, 379.69, 409.89, 421.39, 422.83, 425.71, 583.91, 307.78, 563.78, 222.92, 552.27, 232.99, 570.97, 159.64, 553.71, 100.67, 568.09, 35.96, 546.52, 5.75, 530.7]], "area": 48133.983700000004, "iscrowd": 0, "image_id": 559700, "bbox": [5.75, 409.89, 419.96, 174.02], "category_id": 22, "id": 583622, "split": "val", "sentences": [{"tokens": ["elephant", "lying", "on", "the", "ground"], "raw": "Elephant lying on the ground", "sent_id": 78655, "sent": "elephant lying on the ground"}, {"tokens": ["an", "elephant", "laying", "on", "its", "side", "with", "two", "other", "elephants", "above", "it"], "raw": "An elephant laying on its side with two other elephants above it.", "sent_id": 78656, "sent": "an elephant laying on its side with two other elephants above it"}], "file_name": "COCO_train2014_000000559700_583622.jpg", "ann_id": 583622, "sent_ids": [78655, 78656], "ref_id": 35222}, {"segmentation": [[403.18, 385.84, 405.33, 374.42, 405.33, 335.87, 403.18, 307.31, 389.62, 302.32, 383.91, 285.9, 383.91, 251.63, 390.33, 220.22, 411.04, 208.8, 411.04, 201.66, 404.61, 190.95, 407.47, 181.67, 420.32, 178.81, 431.74, 180.95, 435.31, 185.95, 432.45, 194.52, 433.17, 208.08, 443.16, 219.51, 453.87, 250.2, 470.29, 279.47, 474.57, 293.75, 466.01, 296.61, 454.58, 282.33, 452.44, 295.18, 453.87, 326.59, 458.15, 343.01, 459.58, 368.71, 459.58, 376.56, 474.57, 388.7, 466.01, 392.98, 438.16, 380.85, 434.6, 328.73, 427.46, 291.61, 421.03, 329.44, 423.17, 363.71, 419.6, 383.7, 415.32, 392.98, 404.61, 390.13]], "area": 10536.31265, "iscrowd": 0, "image_id": 77709, "bbox": [383.91, 178.81, 90.66, 214.17], "category_id": 1, "id": 189178, "split": "val", "sentences": [{"tokens": ["a", "man", "standing", "next", "to", "the", "tire"], "raw": "A man standing next to the tire.", "sent_id": 78807, "sent": "a man standing next to the tire"}, {"tokens": ["a", "man", "with", "cote", "beside", "the", "bog"], "raw": "A man with cote beside the bog", "sent_id": 78808, "sent": "a man with cote beside the bog"}], "file_name": "COCO_train2014_000000077709_189178.jpg", "ann_id": 189178, "sent_ids": [78807, 78808], "ref_id": 35274}, {"segmentation": [[538.4, 266.07, 554.92, 269.25, 554.92, 236.86, 566.35, 238.13, 566.98, 226.69, 577.78, 227.33, 577.78, 239.4, 638.75, 240.03, 639.39, 206.37, 633.67, 205.73, 629.86, 200.02, 622.87, 198.11, 615.89, 181.6, 598.1, 168.9, 597.47, 163.18, 528.88, 154.29, 462.82, 156.83, 463.46, 166.99, 469.81, 229.87, 522.52, 238.76, 534.59, 245.75, 539.04, 259.08, 538.4, 265.44]], "area": 13032.081700000004, "iscrowd": 0, "image_id": 461494, "bbox": [462.82, 154.29, 176.57, 114.96], "category_id": 8, "id": 1798268, "split": "val", "sentences": [{"tokens": ["a", "white", "truck"], "raw": "A white truck.", "sent_id": 78830, "sent": "a white truck"}, {"tokens": ["a", "white", "truck", "parked", "beside", "a", "yellow", "bus"], "raw": "A white truck parked beside a yellow bus.", "sent_id": 78831, "sent": "a white truck parked beside a yellow bus"}], "file_name": "COCO_train2014_000000461494_1798268.jpg", "ann_id": 1798268, "sent_ids": [78830, 78831], "ref_id": 35283}, {"segmentation": [[415.39, 56.82, 416.14, 97.85, 412.41, 111.28, 409.42, 119.49, 406.44, 125.46, 384.8, 148.59, 367.64, 209.02, 357.2, 305.26, 302.74, 317.2, 301.99, 332.0, 425.09, 332.0, 432.55, 295.56, 447.47, 287.36, 452.7, 232.15, 435.54, 231.4, 443.74, 194.1, 454.93, 190.37, 466.87, 144.86, 454.93, 138.89, 464.63, 106.81, 473.59, 103.08, 477.32, 85.17, 477.32, 82.19, 482.54, 54.58, 473.59, 41.9, 456.43, 38.92, 432.55, 46.38, 419.87, 53.09]], "area": 22009.246199999998, "iscrowd": 0, "image_id": 473373, "bbox": [301.99, 38.92, 180.55, 293.08], "category_id": 62, "id": 382824, "split": "val", "sentences": [{"tokens": ["a", "seat", "back", "behind", "a", "baby"], "raw": "A seat back behind a baby.", "sent_id": 78834, "sent": "a seat back behind a baby"}, {"tokens": ["the", "back", "of", "the", "highchair", "covered", "with", "light", "green", "fabric"], "raw": "The back of the highchair covered with light green fabric.", "sent_id": 78835, "sent": "the back of the highchair covered with light green fabric"}], "file_name": "COCO_train2014_000000473373_382824.jpg", "ann_id": 382824, "sent_ids": [78834, 78835], "ref_id": 35285}, {"segmentation": [[219.74, 315.53, 219.74, 252.2, 265.8, 194.63, 253.32, 179.28, 239.89, 189.83, 229.33, 200.39, 159.29, 187.91, 163.12, 169.68, 183.27, 180.24, 219.74, 184.07, 237.97, 149.53, 229.33, 145.69, 216.86, 115.95, 223.58, 94.84, 244.69, 92.92, 254.28, 106.35, 272.51, 114.03, 282.11, 120.74, 284.99, 134.18, 280.19, 138.02, 345.44, 233.97, 340.64, 253.16, 334.88, 257.0, 388.62, 310.73, 388.62, 322.25, 379.98, 349.12, 359.83, 349.12, 367.51, 326.09, 365.59, 313.61, 323.37, 280.99, 299.38, 252.2, 282.11, 234.93, 243.73, 249.32, 248.52, 322.25, 244.69, 326.09, 226.45, 327.05, 210.14, 330.88, 202.47, 326.09]], "area": 16521.608700000004, "iscrowd": 0, "image_id": 505924, "bbox": [159.29, 92.92, 229.33, 256.2], "category_id": 1, "id": 501369, "split": "val", "sentences": [{"tokens": ["a", "young", "lady", "wearing", "dark", "blue", "playing", "soccer"], "raw": "A young lady wearing dark blue playing soccer.", "sent_id": 78836, "sent": "a young lady wearing dark blue playing soccer"}, {"tokens": ["a", "woman", "moving", "the", "ball", "to", "the", "goal", "while", "another", "shout"], "raw": "A woman moving the ball to the goal while another shout", "sent_id": 78837, "sent": "a woman moving the ball to the goal while another shout"}], "file_name": "COCO_train2014_000000505924_501369.jpg", "ann_id": 501369, "sent_ids": [78836, 78837], "ref_id": 35286}, {"segmentation": [[220.54, 553.23, 207.57, 533.05, 204.68, 481.15, 197.48, 437.91, 184.5, 384.58, 190.27, 318.27, 194.59, 250.52, 184.5, 153.95, 224.86, 145.3, 219.1, 117.91, 206.13, 107.82, 239.28, 81.87, 263.78, 104.94, 263.78, 119.35, 253.69, 130.88, 246.49, 142.41, 283.96, 152.5, 294.05, 164.04, 301.26, 179.89, 283.96, 250.52, 289.73, 335.57, 279.64, 388.9, 265.23, 430.7, 253.69, 465.3, 258.02, 514.31, 258.02, 535.93, 245.05, 540.25, 236.4, 524.4, 239.28, 459.53, 239.28, 432.14, 224.86, 445.12, 227.75, 481.15, 224.86, 535.93, 230.63, 548.9]], "area": 34270.63760000001, "iscrowd": 0, "image_id": 72731, "bbox": [184.5, 81.87, 116.76, 471.36], "category_id": 1, "id": 457929, "split": "val", "sentences": [{"tokens": ["woman", "standing", "between", "two", "other", "women", "wearing", "knee", "high", "pants", "and", "sweaters"], "raw": "Woman standing between two other women wearing knee high pants and sweaters.", "sent_id": 78910, "sent": "woman standing between two other women wearing knee high pants and sweaters"}, {"tokens": ["a", "woman", "with", "blonde", "hair", "in", "the", "middle"], "raw": "a woman with blonde hair in the middle", "sent_id": 78911, "sent": "a woman with blonde hair in the middle"}], "file_name": "COCO_train2014_000000072731_457929.jpg", "ann_id": 457929, "sent_ids": [78910, 78911], "ref_id": 35317}, {"segmentation": [[398.49, 193.98, 409.85, 172.43, 425.84, 151.58, 429.55, 149.72, 434.41, 150.19, 432.33, 145.09, 428.39, 139.06, 427.23, 133.27, 430.01, 129.33, 437.89, 131.65, 438.12, 137.67, 438.12, 141.61, 439.74, 146.71, 441.6, 149.72, 444.84, 152.5, 446.0, 158.53, 446.23, 165.48, 446.23, 168.49, 449.01, 171.97, 452.72, 168.03, 457.82, 163.86, 465.93, 165.71, 468.94, 166.18, 471.02, 163.63, 473.57, 163.39, 477.98, 163.39, 480.06, 162.0, 486.55, 155.52, 491.65, 155.52, 498.14, 158.76, 500.0, 165.94, 500.0, 169.88, 492.11, 170.58, 483.77, 167.57, 475.66, 166.41, 475.2, 168.72, 477.28, 170.81, 485.86, 172.66, 497.21, 174.98, 481.92, 176.14, 480.29, 180.77, 477.51, 183.09, 472.65, 183.32, 460.13, 176.83, 452.72, 183.79, 451.33, 185.18, 441.13, 190.51, 440.2, 190.51, 426.07, 190.97, 415.41, 197.0, 411.7, 204.64, 410.08, 214.61, 402.43, 202.79], [441.6, 198.15, 439.05, 210.2, 441.13, 218.78, 447.16, 228.97, 449.94, 237.08, 418.19, 229.67, 416.8, 228.74, 416.57, 210.44, 423.06, 200.7, 433.25, 197.0]], "area": 3442.2362499999995, "iscrowd": 0, "image_id": 321209, "bbox": [398.49, 129.33, 101.51, 107.75], "category_id": 4, "id": 1790001, "split": "val", "sentences": [{"tokens": ["the", "motor", "scooter", "that", "is", "in", "the", "middle", "of", "the", "other", "scooters", "and", "behind", "the", "man", "with", "the", "cane", "that", "is", "sticking", "straight", "out"], "raw": "The motor scooter that is in the middle of the other scooters and behind the man with the cane that is sticking straight out.", "sent_id": 78926, "sent": "the motor scooter that is in the middle of the other scooters and behind the man with the cane that is sticking straight out"}], "file_name": "COCO_train2014_000000321209_1790001.jpg", "ann_id": 1790001, "sent_ids": [78926], "ref_id": 35323}, {"segmentation": [[104.63, 473.6, 104.63, 414.27, 98.16, 350.63, 103.55, 308.57, 145.62, 282.68, 145.62, 282.68, 224.36, 216.88, 215.73, 203.94, 214.65, 184.52, 223.28, 171.58, 226.52, 141.38, 256.72, 120.88, 285.84, 120.88, 304.18, 130.59, 311.73, 150.0, 318.2, 182.36, 310.65, 215.8, 307.42, 251.4, 314.97, 256.79, 323.6, 264.34, 325.75, 270.81, 312.81, 298.86, 312.81, 344.16, 323.6, 401.33, 326.83, 457.42, 330.07, 472.52, 112.18, 473.6]], "area": 57591.171449999994, "iscrowd": 0, "image_id": 221880, "bbox": [98.16, 120.88, 231.91, 352.72], "category_id": 1, "id": 422523, "split": "val", "sentences": [{"tokens": ["the", "man", "on", "the", "left"], "raw": "The man on the left.", "sent_id": 78935, "sent": "the man on the left"}, {"tokens": ["a", "man", "that", "is", "wearing", "glasses"], "raw": "A man that is wearing glasses.", "sent_id": 78936, "sent": "a man that is wearing glasses"}], "file_name": "COCO_train2014_000000221880_422523.jpg", "ann_id": 422523, "sent_ids": [78935, 78936], "ref_id": 35325}, {"segmentation": [[72.7, 346.94, 75.46, 342.34, 83.74, 331.29, 90.19, 322.09, 101.23, 309.21, 106.75, 299.08, 131.6, 264.11, 147.24, 230.98, 154.6, 219.94, 157.36, 197.86, 164.73, 185.89, 164.73, 175.77, 162.89, 140.8, 178.53, 148.16, 184.05, 151.84, 201.54, 158.28, 204.3, 171.17, 204.3, 180.37, 204.3, 185.89, 204.3, 192.33, 209.82, 189.57, 215.34, 183.13, 219.94, 172.09, 223.62, 163.81, 238.35, 153.68, 239.27, 153.68, 244.79, 153.68, 254.91, 153.68, 244.79, 161.05, 244.79, 173.01, 244.79, 187.73, 244.79, 205.22, 238.35, 217.18, 237.43, 229.14, 234.67, 238.35, 230.06, 242.95, 225.46, 253.07, 221.78, 259.51, 219.02, 272.4, 207.98, 283.44, 202.46, 293.56, 189.57, 300.92, 184.05, 304.61, 165.65, 319.33, 146.32, 327.61, 138.96, 346.94, 138.96, 361.66, 139.88, 367.18, 130.68, 367.18, 119.63, 364.42, 136.2, 334.05, 118.71, 359.82, 115.03, 352.46, 119.63, 333.13, 131.6, 319.33, 139.88, 313.81, 140.8, 308.29, 143.56, 293.56, 129.76, 311.97, 118.71, 334.05, 111.35, 354.3, 103.07, 353.38, 107.67, 333.13, 123.31, 311.05, 106.75, 326.69, 82.82, 356.14, 72.7, 356.14]], "area": 15580.3761, "iscrowd": 0, "image_id": 83005, "bbox": [72.7, 140.8, 182.21, 226.38], "category_id": 19, "id": 60074, "split": "val", "sentences": [{"tokens": ["a", "horse", "without", "a", "rideer"], "raw": "A horse without a rideer.", "sent_id": 78958, "sent": "a horse without a rideer"}, {"tokens": ["wild", "horse", "running", "to", "get", "away", "from", "the", "man", "riding", "a", "horse", "at", "a", "rodeo"], "raw": "Wild horse running to get away from the man riding a horse at a rodeo.", "sent_id": 78959, "sent": "wild horse running to get away from the man riding a horse at a rodeo"}], "file_name": "COCO_train2014_000000083005_60074.jpg", "ann_id": 60074, "sent_ids": [78958, 78959], "ref_id": 35335}, {"segmentation": [[435.97, 191.24, 475.7, 186.95, 508.99, 181.58, 537.99, 182.65, 565.91, 204.13, 584.16, 227.75, 585.23, 287.89, 578.79, 305.07, 579.87, 279.3, 572.35, 244.94, 566.98, 262.12, 566.98, 283.59, 573.42, 295.41, 579.87, 315.81, 574.5, 338.36, 574.5, 389.9, 560.54, 398.49, 555.17, 390.98, 564.83, 377.02, 564.83, 361.98, 557.32, 332.99, 556.24, 378.09, 546.58, 390.98, 525.1, 389.9, 541.21, 368.43, 542.28, 344.8, 536.91, 320.1, 519.73, 284.67, 514.36, 278.22, 490.74, 290.04, 451.01, 291.11, 397.32, 285.74, 395.17, 322.25, 397.32, 368.43, 397.32, 396.35, 385.5, 398.49, 379.06, 395.27, 387.65, 368.43, 380.13, 340.51, 381.21, 371.65, 374.77, 390.98, 362.95, 392.05, 369.4, 379.16, 353.29, 388.83, 371.54, 357.69, 367.25, 327.62, 360.81, 281.45, 336.11, 262.12, 337.18, 224.53, 326.44, 203.06, 295.3, 183.73, 264.16, 174.06, 273.83, 160.1, 296.38, 149.37, 321.07, 151.51, 357.58, 154.73, 396.24, 176.21]], "area": 34856.65464999999, "iscrowd": 0, "image_id": 332385, "bbox": [264.16, 149.37, 321.07, 249.12], "category_id": 24, "id": 593613, "split": "val", "sentences": [{"tokens": ["a", "zebra", "standing", "in", "between", "two", "zebras"], "raw": "A zebra standing in between two zebras", "sent_id": 78966, "sent": "a zebra standing in between two zebras"}, {"tokens": ["middle", "of", "the", "three", "zebras"], "raw": "middle of the three zebras", "sent_id": 78967, "sent": "middle of the three zebras"}], "file_name": "COCO_train2014_000000332385_593613.jpg", "ann_id": 593613, "sent_ids": [78966, 78967], "ref_id": 35337}, {"segmentation": [[405.86, 181.51, 414.6, 166.94, 439.07, 160.54, 444.31, 155.88, 439.65, 148.88, 433.24, 129.66, 432.66, 117.43, 437.32, 101.12, 476.35, 99.37, 490.33, 106.94, 486.84, 131.99, 481.59, 150.05, 478.68, 158.21, 505.48, 161.7, 517.71, 176.85, 517.71, 202.48, 519.46, 219.95, 514.21, 226.95, 510.14, 237.43, 508.39, 241.51, 503.15, 243.26, 497.9, 243.26, 495.57, 238.6, 491.5, 238.6, 483.92, 224.03, 437.9, 226.95, 436.15, 241.51, 428.58, 246.75, 422.17, 242.67, 416.93, 246.75, 410.52, 239.18, 404.7, 231.02, 405.86, 221.12]], "area": 10850.846449999997, "iscrowd": 0, "image_id": 564217, "bbox": [404.7, 99.37, 114.76, 147.38], "category_id": 1, "id": 440418, "split": "val", "sentences": [{"tokens": ["the", "guy", "in", "a", "black", "shirt", "where", "it", "says", "you", "guys"], "raw": "The guy in a black shirt where it says you guys.", "sent_id": 79047, "sent": "the guy in a black shirt where it says you guys"}, {"tokens": ["man", "in", "photograph", "in", "collage", "that", "is", "holding", "a", "chair", "back"], "raw": "Man in photograph in collage that is holding a chair back.", "sent_id": 79048, "sent": "man in photograph in collage that is holding a chair back"}], "file_name": "COCO_train2014_000000564217_440418.jpg", "ann_id": 440418, "sent_ids": [79047, 79048], "ref_id": 35370}, {"segmentation": [[48.11, 454.65, 46.06, 466.9, 34.5, 473.7, 27.7, 466.22, 27.02, 458.73, 31.1, 450.57, 39.94, 437.64, 67.83, 450.57, 65.11, 461.46], [53.55, 503.63, 51.51, 513.84, 35.18, 521.32, 24.97, 512.48, 27.7, 504.31, 33.82, 501.59, 39.26, 484.59, 62.39, 477.78, 63.07, 494.79], [129.74, 431.52, 101.17, 478.46, 115.46, 479.14, 146.07, 513.16, 132.46, 515.88, 129.06, 525.4, 141.31, 539.01, 152.87, 534.25, 156.27, 526.08, 159.68, 518.6, 159.68, 507.72, 121.58, 470.3, 137.23, 476.42, 181.45, 475.74, 179.41, 487.99, 182.13, 495.47, 186.21, 498.19, 193.01, 492.07, 176.0, 464.18, 129.74, 466.22, 134.5, 449.21]], "area": 4233.9593, "iscrowd": 0, "image_id": 530635, "bbox": [24.97, 431.52, 168.04, 107.49], "category_id": 62, "id": 1579143, "split": "val", "sentences": [{"tokens": ["rollers", "on", "an", "office", "chair"], "raw": "Rollers on an office chair.", "sent_id": 79055, "sent": "rollers on an office chair"}, {"tokens": ["the", "base", "and", "wheels", "of", "a", "rolling", "chair"], "raw": "The base and wheels of a rolling chair.", "sent_id": 79056, "sent": "the base and wheels of a rolling chair"}], "file_name": "COCO_train2014_000000530635_1579143.jpg", "ann_id": 1579143, "sent_ids": [79055, 79056], "ref_id": 35374}, {"segmentation": [[82.52, 452.41, 49.71, 456.51, 30.02, 449.95, 24.27, 440.92, 24.27, 381.85, 20.99, 320.32, 39.04, 303.91, 43.14, 295.71, 40.68, 279.3, 40.68, 264.53, 53.81, 259.61, 68.58, 258.79, 87.44, 254.69, 106.31, 262.07, 104.67, 286.68, 82.52, 298.99, 75.14, 298.99, 94.01, 316.22, 99.75, 441.74, 86.62, 451.59]], "area": 13285.87315, "iscrowd": 0, "image_id": 547165, "bbox": [20.99, 254.69, 85.32, 201.82], "category_id": 44, "id": 1867685, "split": "val", "sentences": [{"tokens": ["a", "clear", "pink", "water", "bottle", "on", "the", "table"], "raw": "A clear pink water bottle on the table.", "sent_id": 79082, "sent": "a clear pink water bottle on the table"}, {"tokens": ["pink", "water", "bottle"], "raw": "Pink water bottle.", "sent_id": 79083, "sent": "pink water bottle"}], "file_name": "COCO_train2014_000000547165_1867685.jpg", "ann_id": 1867685, "sent_ids": [79082, 79083], "ref_id": 35386}, {"segmentation": [[110.77, 487.5, 91.12, 479.99, 84.05, 467.63, 84.27, 464.32, 98.62, 419.04, 101.94, 414.85, 108.78, 396.3, 112.98, 382.39, 99.29, 374.88, 97.74, 370.24, 99.29, 356.11, 108.12, 328.06, 109.89, 318.79, 124.46, 297.81, 129.98, 294.72, 143.23, 290.96, 151.62, 286.54, 148.09, 278.82, 147.21, 265.34, 152.07, 243.7, 153.83, 238.18, 163.11, 229.35, 176.58, 228.91, 188.72, 234.65, 195.57, 252.09, 197.78, 264.02, 201.31, 270.64, 202.42, 277.71, 201.97, 288.53, 195.79, 291.18, 199.55, 301.78, 205.29, 314.81, 209.48, 330.71, 215.0, 341.75, 215.45, 351.69, 210.81, 359.42, 205.19, 369.33, 200.09, 388.31, 194.42, 407.02, 192.15, 410.42, 194.14, 420.34, 191.87, 444.43, 194.42, 464.84, 194.7, 468.24, 194.99, 503.95, 194.99, 521.81, 194.42, 524.64, 191.3, 537.4, 179.68, 560.35, 169.48, 576.79, 166.93, 579.91, 162.68, 588.69, 160.69, 597.76, 169.48, 608.82, 182.52, 618.74, 187.62, 626.67, 183.08, 630.36, 175.74, 628.96, 167.36, 626.52, 173.99, 634.2, 166.31, 639.78, 137.0, 639.43, 119.21, 623.73, 122.35, 605.23, 123.74, 602.09, 116.07, 575.23, 114.67, 559.18, 115.37, 542.78, 119.21, 526.38, 119.56, 513.47, 113.97, 493.23]], "area": 31546.075150000004, "iscrowd": 0, "image_id": 39159, "bbox": [84.05, 228.91, 131.4, 410.87], "category_id": 1, "id": 509903, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "white", "shirt", "and", "blue", "skirt", "holding", "a", "wine", "glass"], "raw": "a woman wearing a white shirt and blue skirt holding a wine glass", "sent_id": 79112, "sent": "a woman wearing a white shirt and blue skirt holding a wine glass"}, {"tokens": ["a", "woman", "in", "a", "white", "shirt"], "raw": "A woman in a white shirt.", "sent_id": 79113, "sent": "a woman in a white shirt"}], "file_name": "COCO_train2014_000000039159_509903.jpg", "ann_id": 509903, "sent_ids": [79112, 79113], "ref_id": 35397}, {"segmentation": [[313.38, 332.94, 311.16, 296.43, 318.91, 282.04, 310.61, 261.57, 305.63, 258.81, 305.63, 244.42, 313.93, 233.91, 335.51, 226.72, 359.85, 234.46, 382.53, 232.25, 403.56, 222.29, 433.98, 212.33, 450.03, 208.46, 462.75, 213.44, 473.82, 238.34, 483.78, 265.45, 476.03, 268.76, 464.41, 266.55, 448.37, 252.72, 440.62, 250.51, 419.05, 283.15, 422.37, 306.94, 432.32, 328.52, 421.26, 329.07, 409.09, 294.21, 405.77, 317.45, 407.98, 334.05, 399.13, 330.73, 399.68, 283.7, 370.36, 284.81, 347.12, 278.72, 341.59, 281.49, 329.97, 303.62, 343.25, 335.15, 343.81, 339.58, 331.63, 338.47, 328.31, 332.39, 322.23, 302.51, 322.23, 344.01, 312.82, 341.24]], "area": 10704.44565, "iscrowd": 0, "image_id": 505486, "bbox": [305.63, 208.46, 178.15, 135.55], "category_id": 24, "id": 590262, "split": "val", "sentences": [{"tokens": ["zebra", "standing", "facing", "right", "with", "another", "zebra", "walking", "behind", "it"], "raw": "zebra standing facing right with another zebra walking behind it", "sent_id": 79195, "sent": "zebra standing facing right with another zebra walking behind it"}, {"tokens": ["a", "zebra", "looking", "towards", "the", "side"], "raw": "A zebra looking towards the side.", "sent_id": 79196, "sent": "a zebra looking towards the side"}], "file_name": "COCO_train2014_000000505486_590262.jpg", "ann_id": 590262, "sent_ids": [79195, 79196], "ref_id": 35426}, {"segmentation": [[160.63, 221.26, 147.71, 253.55, 138.83, 262.43, 122.69, 260.81, 118.65, 253.55, 118.65, 244.67, 125.92, 234.17, 142.87, 226.1, 134.8, 200.27, 145.29, 196.24, 152.56, 192.2, 103.32, 186.55, 84.75, 176.06, 73.45, 171.22, 72.65, 170.41, 65.38, 166.37, 62.15, 163.95, 38.74, 228.52, 31.48, 243.86, 24.22, 246.28, 9.69, 243.86, 15.34, 229.33, 29.06, 149.42, 38.74, 125.21, 12.91, 112.29, 12.91, 106.64, 29.06, 99.38, 45.2, 96.96, 37.13, 57.4, 37.13, 43.68, 53.27, 80.81, 55.7, 88.88, 91.21, 46.1, 103.32, 46.1, 90.4, 70.32, 90.4, 70.32, 144.48, 76.78, 251.03, 106.64, 268.79, 112.29, 309.15, 100.99, 345.47, 103.41, 395.52, 126.01, 443.14, 147.0, 446.37, 148.61, 450.4, 147.0, 435.87, 139.74, 436.68, 131.66, 447.98, 127.63, 461.7, 135.7, 481.88, 105.03, 508.52, 106.64, 510.94, 132.47, 510.94, 142.16, 510.94, 145.39, 543.23, 111.48, 550.49, 106.64, 559.37, 113.1, 535.16, 148.61, 523.86, 161.53, 567.44, 168.79, 576.32, 179.29, 578.74, 195.43, 526.28, 185.74, 532.74, 192.2, 540.0, 197.04, 542.42, 209.96, 530.31, 214.8, 522.24, 221.26, 512.56, 222.87, 506.1, 222.87, 502.06, 224.49, 496.41, 241.44, 486.73, 239.02, 472.2, 228.52, 460.09, 222.87, 440.72, 217.22, 429.42, 212.38, 423.77, 210.77, 421.35, 210.77, 418.92, 213.19, 418.92, 214.8, 426.19, 224.49, 426.19, 226.1, 417.31, 227.72, 401.17, 227.72, 394.71, 226.1, 380.18, 222.07, 362.42, 220.45, 352.74, 216.42, 347.09, 222.87, 347.89, 233.37, 341.43, 238.21, 339.01, 241.44, 332.56, 241.44, 327.71, 238.21, 328.52, 226.91, 329.33, 215.61, 330.94, 209.15, 332.56, 203.5, 330.13, 201.89, 309.15, 197.85, 295.43, 197.04, 290.58, 195.43, 284.13, 195.43, 272.02, 197.85, 275.25, 204.31, 279.28, 208.35, 280.09, 212.38, 280.09, 214.0, 267.98, 219.65, 233.27, 220.45, 221.17, 221.26, 217.94, 254.35, 226.82, 276.15, 219.55, 289.87, 209.87, 292.29, 207.44, 292.29, 196.14, 289.06, 189.69, 285.83, 189.69, 282.61, 186.46, 275.34, 188.88, 264.85, 192.11, 259.2, 195.34, 256.78, 199.37, 252.74, 200.99, 242.25, 201.79, 234.17, 201.79, 227.72, 201.79, 226.91, 164.66, 223.68]], "area": 61814.67029999998, "iscrowd": 0, "image_id": 534155, "bbox": [9.69, 43.68, 569.05, 248.61], "category_id": 5, "id": 247579, "split": "val", "sentences": [{"tokens": ["a", "blue", "and", "red", "airplane"], "raw": "A blue and red airplane.", "sent_id": 79259, "sent": "a blue and red airplane"}, {"tokens": ["small", "red", "white", "and", "blue", "airplane", "that", "says", "bud", "light"], "raw": "Small red white and blue airplane that says Bud Light.", "sent_id": 79260, "sent": "small red white and blue airplane that says bud light"}], "file_name": "COCO_train2014_000000534155_247579.jpg", "ann_id": 247579, "sent_ids": [79259, 79260], "ref_id": 35453}, {"segmentation": [[335.14, 218.38, 348.11, 177.3, 371.89, 147.03, 398.92, 135.14, 448.65, 135.14, 483.24, 143.78, 517.84, 163.24, 551.35, 190.27, 564.32, 223.78, 557.84, 267.03, 538.38, 298.38, 509.19, 315.68, 464.86, 326.49, 418.38, 315.68, 368.65, 304.86, 342.7, 280.0, 331.89, 242.16, 332.97, 216.22, 336.22, 203.24]], "area": 34650.835800000015, "iscrowd": 0, "image_id": 228133, "bbox": [331.89, 135.14, 232.43, 191.35], "category_id": 60, "id": 1080795, "split": "val", "sentences": [{"tokens": ["the", "chocolate", "pastry"], "raw": "The chocolate pastry.", "sent_id": 79303, "sent": "the chocolate pastry"}, {"tokens": ["a", "doughnut", "with", "chocolate", "drizzled", "on", "black", "cookies", "as", "a", "topping"], "raw": "A doughnut with chocolate drizzled on black cookies as a topping.", "sent_id": 79304, "sent": "a doughnut with chocolate drizzled on black cookies as a topping"}], "file_name": "COCO_train2014_000000228133_1080795.jpg", "ann_id": 1080795, "sent_ids": [79303, 79304], "ref_id": 35466}, {"segmentation": [[412.5, 219.7, 420.22, 214.7, 423.85, 211.53, 426.12, 210.16, 432.02, 204.72, 434.29, 202.45, 439.28, 203.36, 440.19, 206.08, 437.92, 208.8, 447.0, 216.52, 457.43, 243.75, 461.07, 255.55, 467.87, 264.18, 476.95, 272.8, 483.76, 280.97, 491.02, 288.69, 501.74, 294.64, 510.82, 296.91, 516.72, 296.91, 523.53, 305.99, 526.71, 311.44, 524.89, 319.15, 470.42, 336.86, 459.08, 334.59, 451.36, 318.7, 450.45, 308.26, 457.26, 300.09, 452.27, 283.3, 441.37, 262.87, 437.74, 229.74, 433.2, 223.84, 425.49, 224.29, 415.96, 226.56, 409.6, 224.29]], "area": 4664.5828, "iscrowd": 0, "image_id": 453475, "bbox": [409.6, 202.45, 117.11, 134.41], "category_id": 25, "id": 600119, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "standing", "between", "two", "other", "giraffes"], "raw": "the giraffe standing between two other giraffes", "sent_id": 79321, "sent": "the giraffe standing between two other giraffes"}, {"tokens": ["a", "giraffe", "in", "the", "background", "visible", "between", "two", "closer", "giraffes"], "raw": "A giraffe in the background visible between two closer giraffes.", "sent_id": 79322, "sent": "a giraffe in the background visible between two closer giraffes"}], "file_name": "COCO_train2014_000000453475_600119.jpg", "ann_id": 600119, "sent_ids": [79321, 79322], "ref_id": 35474}, {"segmentation": [[222.05, 151.03, 216.68, 201.42, 215.45, 222.48, 202.23, 236.94, 202.23, 236.94, 200.58, 247.27, 215.86, 241.07, 228.66, 232.81, 226.18, 221.25, 230.73, 209.27, 238.99, 208.86, 244.77, 186.55, 253.44, 211.33, 253.44, 211.75, 260.88, 217.12, 268.72, 236.53, 267.07, 246.85, 273.68, 259.24, 284.01, 258.83, 288.14, 255.53, 285.25, 248.5, 281.53, 241.9, 279.88, 233.22, 274.92, 224.14, 274.51, 210.92, 272.44, 193.99, 271.2, 176.23, 267.49, 181.18, 263.77, 185.73, 252.62, 182.84, 247.25, 174.16, 252.62, 163.84, 263.77, 149.79, 275.75, 128.32, 272.03, 111.8, 267.9, 99.41, 267.9, 99.41, 260.05, 92.8, 251.79, 83.3, 251.38, 79.58, 253.86, 72.56, 251.79, 65.95, 244.77, 58.52, 239.4, 55.21, 227.84, 57.28, 223.29, 62.65, 223.29, 62.65, 223.29, 62.65, 222.47, 69.67, 221.64, 73.8, 224.12, 72.97, 224.12, 72.97, 225.36, 71.73, 225.77, 76.69, 216.27, 79.99, 205.95, 82.06, 197.27, 82.89, 189.43, 86.19, 181.58, 88.67, 174.97, 89.08, 176.21, 96.1, 178.27, 102.71, 178.69, 102.3, 186.53, 95.69, 191.9, 93.21, 210.08, 92.8, 212.14, 102.3, 219.16, 104.78, 218.75, 104.78, 220.81, 124.19, 220.81, 134.51, 220.81, 134.51, 222.47, 155.16, 222.47, 155.16]], "area": 8146.651300000002, "iscrowd": 0, "image_id": 269532, "bbox": [174.97, 55.21, 113.17, 204.03], "category_id": 1, "id": 235082, "split": "val", "sentences": [{"tokens": ["a", "small", "boy", "in", "a", "baseball", "cap", "helping", "two", "men", "herd", "sheep"], "raw": "A small boy in a baseball cap helping two men herd sheep.", "sent_id": 79396, "sent": "a small boy in a baseball cap helping two men herd sheep"}, {"tokens": ["boy", "standing", "near", "the", "shed"], "raw": "boy standing near the shed", "sent_id": 79397, "sent": "boy standing near the shed"}], "file_name": "COCO_train2014_000000269532_235082.jpg", "ann_id": 235082, "sent_ids": [79396, 79397], "ref_id": 35500}, {"segmentation": [[25.62, 382.69, 131.08, 428.54, 155.15, 474.39, 159.74, 488.15, 135.66, 529.41, 108.15, 536.29, 62.3, 516.8, 29.06, 512.22, 23.33, 529.41, 25.62, 559.22, 68.03, 581.0, 0.0, 584.44, 0.0, 379.25]], "area": 19743.990499999996, "iscrowd": 0, "image_id": 498854, "bbox": [0.0, 379.25, 159.74, 205.19], "category_id": 62, "id": 1933346, "split": "val", "sentences": [{"tokens": ["the", "seat", "cushion", "directly", "to", "the", "left", "side", "of", "the", "boot"], "raw": "The seat cushion directly to the left side of the boot.", "sent_id": 79475, "sent": "the seat cushion directly to the left side of the boot"}, {"tokens": ["the", "green", "seat", "in", "the", "bottom", "left", "of", "the", "photo"], "raw": "the green seat in the bottom left of the photo", "sent_id": 79476, "sent": "the green seat in the bottom left of the photo"}], "file_name": "COCO_train2014_000000498854_1933346.jpg", "ann_id": 1933346, "sent_ids": [79475, 79476], "ref_id": 35528}, {"segmentation": [[182.33, 499.68, 173.15, 484.77, 167.99, 474.44, 159.96, 468.71, 158.24, 466.42, 161.68, 464.7, 154.23, 454.95, 151.93, 448.06, 146.77, 438.32, 147.92, 425.13, 145.05, 417.1, 143.33, 426.27, 138.17, 433.15, 136.45, 437.17, 128.99, 441.18, 123.83, 445.2, 118.67, 450.93, 114.08, 455.52, 107.78, 458.96, 104.34, 457.81, 102.04, 450.93, 103.19, 444.05, 111.22, 436.6, 112.36, 425.13, 119.82, 407.92, 122.11, 403.33, 138.74, 386.13, 142.18, 379.82, 145.63, 374.66, 142.76, 370.07, 144.48, 367.21, 142.76, 361.47, 142.18, 356.88, 141.04, 352.87, 144.48, 339.11, 147.92, 335.09, 156.52, 335.09, 164.55, 345.41, 166.27, 352.87, 167.99, 356.31, 171.43, 356.88, 176.59, 363.76, 180.61, 366.06, 189.21, 367.21, 191.5, 367.78, 200.68, 375.81, 204.69, 375.81, 206.41, 378.1, 212.15, 378.67, 223.62, 386.13, 224.76, 391.29, 223.04, 395.88, 221.9, 402.19, 213.87, 407.92, 204.69, 405.05, 202.4, 405.05, 200.68, 407.35, 208.13, 415.38, 212.72, 422.26, 211.57, 432.58, 218.46, 458.96, 233.94, 464.7, 244.26, 472.72, 259.75, 489.35, 259.17, 499.1, 263.19, 505.99, 271.79, 517.46, 268.92, 520.9, 258.03, 521.47, 248.28, 524.34, 247.13, 523.19, 244.84, 514.01, 241.4, 509.43, 236.81, 510.57, 227.63, 499.68, 226.48, 495.09, 219.03, 489.93, 215.59, 489.35, 209.28, 482.47, 205.27, 479.61, 208.13, 488.78, 211.0, 489.93, 212.15, 495.09, 218.46, 505.99, 228.21, 517.46, 220.18, 521.47, 209.85, 518.03, 205.27, 518.03, 200.11, 520.32, 197.24, 511.72, 193.8, 510.57, 186.34, 505.41, 182.9, 500.82, 180.61, 497.38]], "area": 12666.687549999999, "iscrowd": 0, "image_id": 56616, "bbox": [102.04, 335.09, 169.75, 189.25], "category_id": 1, "id": 442403, "split": "val", "sentences": [{"tokens": ["a", "person", "skiing", "in", "a", "red", "coat", "leaning", "to", "the", "left", "holding", "ski", "poles"], "raw": "A person skiing in a red coat leaning to the left holding ski poles.", "sent_id": 79481, "sent": "a person skiing in a red coat leaning to the left holding ski poles"}], "file_name": "COCO_train2014_000000056616_442403.jpg", "ann_id": 442403, "sent_ids": [79481], "ref_id": 35531}, {"segmentation": [[315.84, 239.84, 337.56, 259.58, 343.48, 277.35, 336.57, 292.16, 324.73, 297.09, 307.95, 300.05, 286.23, 298.08, 267.48, 286.23, 265.51, 277.35, 274.39, 257.61, 288.21, 240.83, 295.12, 233.92, 290.18, 197.4, 276.36, 188.52, 268.47, 182.6, 264.52, 173.71, 257.61, 155.95, 253.66, 144.1, 248.73, 136.21, 237.87, 121.4, 239.84, 109.56, 246.75, 96.73, 252.68, 94.75, 250.7, 69.09, 250.7, 68.1, 231.95, 79.95, 226.03, 72.05, 231.95, 66.13, 241.82, 64.16, 245.77, 53.3, 253.66, 45.4, 259.58, 33.56, 269.45, 18.75, 274.39, 17.77, 275.38, 37.51, 280.31, 49.35, 284.26, 57.25, 290.18, 75.01, 292.16, 87.84, 295.12, 92.78, 299.06, 105.61, 298.08, 118.44, 294.13, 127.32, 304.0, 136.21, 307.95, 142.13, 323.74, 154.96, 322.75, 164.83, 317.82, 174.7, 312.88, 186.55, 321.77, 193.45, 321.77, 196.42, 312.88, 208.26, 327.69, 208.26, 330.65, 217.14, 327.69, 224.05, 328.68, 228.99, 307.95, 232.94]], "area": 12851.26265, "iscrowd": 0, "image_id": 333748, "bbox": [226.03, 17.77, 117.45, 282.28], "category_id": 64, "id": 1954077, "split": "val", "sentences": [{"tokens": ["a", "plant", "in", "a", "white", "vase", "in", "the", "middle", "of", "a", "table"], "raw": "A plant in a white vase in the middle of a table.", "sent_id": 79486, "sent": "a plant in a white vase in the middle of a table"}, {"tokens": ["a", "plant", "in", "a", "white", "vase", "in", "the", "middle", "of", "a", "table"], "raw": "A plant in a white vase in the middle of a table.", "sent_id": 79487, "sent": "a plant in a white vase in the middle of a table"}], "file_name": "COCO_train2014_000000333748_1954077.jpg", "ann_id": 1954077, "sent_ids": [79486, 79487], "ref_id": 35532}, {"segmentation": [[227.53, 2.53, 302.53, 9.27, 337.08, 5.06, 353.93, 3.37, 421.35, 0.84, 419.66, 13.48, 416.29, 25.28, 410.39, 38.76, 409.55, 41.29, 400.28, 37.92, 400.28, 37.92, 395.16, 36.9, 386.47, 31.27, 377.77, 27.18, 364.47, 27.18, 342.47, 29.74, 329.68, 33.83, 323.03, 34.85, 315.36, 33.32, 310.24, 30.25, 303.08, 31.78, 288.24, 30.25, 275.45, 29.22, 263.17, 29.22, 247.82, 43.04, 242.2, 43.55, 237.59, 49.18, 229.41, 48.15, 217.13, 22.06, 218.66, 5.69, 221.73, 2.62]], "area": 5766.135200000001, "iscrowd": 0, "image_id": 421298, "bbox": [217.13, 0.84, 204.22, 48.34], "category_id": 62, "id": 1590507, "split": "val", "sentences": [{"tokens": ["a", "plastic", "chair", "behind", "the", "far", "table"], "raw": "A plastic chair behind the far table.", "sent_id": 79511, "sent": "a plastic chair behind the far table"}], "file_name": "COCO_train2014_000000421298_1590507.jpg", "ann_id": 1590507, "sent_ids": [79511], "ref_id": 35542}, {"segmentation": [[69.0, 507.62, 69.0, 507.62, 66.36, 498.65, 68.47, 490.21, 72.16, 486.52, 78.49, 482.29, 83.24, 482.29, 95.91, 487.57, 97.49, 498.65, 95.38, 506.04, 98.02, 512.9, 105.41, 519.76, 118.6, 525.57, 123.88, 539.29, 129.68, 548.26, 133.38, 542.45, 133.9, 536.12, 139.71, 536.65, 144.98, 545.62, 141.82, 556.17, 137.07, 561.98, 132.85, 571.48, 129.15, 577.28, 118.07, 574.64, 117.54, 582.03, 120.71, 597.33, 117.02, 618.44, 114.91, 632.69, 113.32, 640.0, 102.24, 640.0, 90.63, 640.0, 66.36, 640.0, 52.64, 640.0, 49.47, 629.52, 47.36, 616.33, 45.78, 604.19, 46.83, 595.75, 50.0, 582.56, 50.0, 569.89, 46.3, 568.31, 41.03, 568.31, 34.17, 567.78, 31.53, 557.23, 34.17, 542.45, 42.61, 529.26, 55.28, 520.29, 64.25, 510.79, 66.36, 509.21]], "area": 10728.3771, "iscrowd": 0, "image_id": 148983, "bbox": [31.53, 482.29, 113.45, 157.71], "category_id": 1, "id": 488831, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "gree", "flies", "a", "kite"], "raw": "A woman wearing gree flies a kite.", "sent_id": 79517, "sent": "a woman wearing gree flies a kite"}, {"tokens": ["a", "woman", "on", "the", "beach", "with", "a", "kite"], "raw": "A woman on the beach with a kite.", "sent_id": 79518, "sent": "a woman on the beach with a kite"}], "file_name": "COCO_train2014_000000148983_488831.jpg", "ann_id": 488831, "sent_ids": [79517, 79518], "ref_id": 35544}, {"segmentation": [[89.54, 412.26, 8.04, 389.3, 3.44, 140.19, 16.07, 114.93, 37.88, 103.45, 57.4, 100.01, 71.17, 103.45, 120.54, 112.64, 137.76, 141.34, 152.68, 176.92, 152.68, 207.92, 153.83, 245.8, 156.13, 277.95, 161.87, 321.57, 180.23, 358.3, 179.09, 361.75, 166.46, 378.97]], "area": 43300.87015, "iscrowd": 0, "image_id": 106397, "bbox": [3.44, 100.01, 176.79, 312.25], "category_id": 14, "id": 418586, "split": "val", "sentences": [{"tokens": ["left", "side", "of", "parking", "meter", "in", "front", "of", "passenger", "side", "of", "truck"], "raw": "Left side of parking meter in front of passenger side of truck.", "sent_id": 79560, "sent": "left side of parking meter in front of passenger side of truck"}, {"tokens": ["meter", "in", "the", "left", "of", "the", "other"], "raw": "Meter in the left of the other", "sent_id": 79561, "sent": "meter in the left of the other"}], "file_name": "COCO_train2014_000000106397_418586.jpg", "ann_id": 418586, "sent_ids": [79560, 79561], "ref_id": 35567}, {"segmentation": [[1.92, 382.95, 0.95, 480.0, 261.88, 479.59, 259.95, 467.03, 258.98, 456.4, 258.01, 445.77, 254.15, 438.04, 253.18, 436.11, 245.45, 432.24, 237.72, 432.24, 228.06, 432.24, 214.53, 448.67, 204.86, 457.37, 183.6, 455.43, 160.41, 452.54, 152.68, 392.62, 143.01, 382.95, 140.11, 381.02, 127.55, 378.12, 81.16, 404.22]], "area": 17176.264449999988, "iscrowd": 0, "image_id": 209467, "bbox": [0.95, 378.12, 260.93, 101.88], "category_id": 62, "id": 1934571, "split": "val", "sentences": [{"tokens": ["the", "leather", "chair", "is", "facing", "the", "television"], "raw": "The leather chair is facing the television.", "sent_id": 79637, "sent": "the leather chair is facing the television"}, {"tokens": ["a", "black", "leather", "chair", "sitting", "beside", "a", "floral", "couch"], "raw": "A black leather chair sitting beside a floral couch", "sent_id": 79638, "sent": "a black leather chair sitting beside a floral couch"}], "file_name": "COCO_train2014_000000209467_1934571.jpg", "ann_id": 1934571, "sent_ids": [79637, 79638], "ref_id": 35603}, {"segmentation": [[114.34, 469.21, 143.46, 360.27, 192.0, 314.97, 179.06, 268.58, 169.35, 223.28, 169.35, 194.16, 149.93, 161.8, 182.29, 119.73, 226.52, 145.62, 239.46, 179.06, 265.35, 216.81, 263.19, 252.4, 259.96, 288.0, 279.37, 321.44, 275.06, 344.09, 300.94, 424.99, 316.04, 451.96, 286.92, 457.35, 253.48, 451.96, 218.97, 399.1, 211.42, 377.53, 194.16, 407.73, 190.92, 453.03, 185.53, 464.9, 177.98, 468.13]], "area": 33885.68519999999, "iscrowd": 0, "image_id": 131277, "bbox": [114.34, 119.73, 201.7, 349.48], "category_id": 1, "id": 422611, "split": "val", "sentences": [{"tokens": ["the", "woman", "with", "her", "hand", "on", "her", "butt"], "raw": "The woman with her hand on her butt.", "sent_id": 79683, "sent": "the woman with her hand on her butt"}, {"tokens": ["a", "female", "wearing", "a", "black", "shirt"], "raw": "A female wearing a black shirt.", "sent_id": 79684, "sent": "a female wearing a black shirt"}], "file_name": "COCO_train2014_000000131277_422611.jpg", "ann_id": 422611, "sent_ids": [79683, 79684], "ref_id": 35626}, {"segmentation": [[381.04, 201.01, 366.68, 193.35, 360.94, 183.77, 354.24, 169.41, 352.32, 159.84, 341.79, 150.26, 340.83, 132.07, 359.02, 116.75, 382.96, 112.93, 400.19, 115.8, 413.6, 120.58, 415.51, 133.99, 417.43, 153.14, 413.6, 172.28, 422.21, 179.94, 433.7, 186.64, 448.06, 213.45, 462.42, 254.62, 468.17, 275.68, 481.57, 303.45, 488.27, 326.43, 490.19, 362.81, 485.4, 390.57, 482.53, 421.21, 427.0, 421.21, 395.41, 355.15, 383.92, 309.19, 376.26, 282.38, 352.32, 269.94, 342.75, 257.49, 340.83, 243.13, 355.2, 236.43, 366.68, 240.26, 373.39, 247.92, 379.13, 240.26, 382.0, 221.11]], "area": 25325.11639999999, "iscrowd": 0, "image_id": 555120, "bbox": [340.83, 112.93, 149.36, 308.28], "category_id": 1, "id": 473636, "split": "val", "sentences": [{"tokens": ["a", "little", "girl", "with", "a", "pink", "shirt", "on"], "raw": "A little girl with a pink shirt on.", "sent_id": 79687, "sent": "a little girl with a pink shirt on"}, {"tokens": ["a", "black", "girl", "in", "a", "bright", "pink", "shirt"], "raw": "A black girl in a bright pink shirt.", "sent_id": 79688, "sent": "a black girl in a bright pink shirt"}], "file_name": "COCO_train2014_000000555120_473636.jpg", "ann_id": 473636, "sent_ids": [79687, 79688], "ref_id": 35627}, {"segmentation": [[461.74, 325.81, 447.71, 320.41, 442.32, 311.78, 433.69, 306.39, 423.98, 291.28, 408.88, 274.02, 395.93, 266.47, 390.54, 254.6, 391.61, 236.26, 398.09, 216.84, 401.32, 204.98, 401.32, 194.19, 412.11, 178.01, 420.74, 175.85, 429.37, 181.24, 438.0, 194.19, 443.4, 203.9, 452.03, 213.61, 459.58, 239.5, 464.98, 254.6, 474.68, 266.47, 496.26, 280.5, 516.76, 296.68, 526.47, 309.62, 532.94, 319.33, 532.94, 327.96, 527.55, 332.28, 522.15, 332.28, 516.76, 323.65, 513.52, 321.49, 507.05, 324.73, 501.66, 323.65, 496.26, 317.18, 486.55, 307.47, 459.58, 286.97, 450.95, 280.5, 457.42, 293.44, 464.98, 306.39, 467.13, 318.25]], "area": 9018.31295, "iscrowd": 0, "image_id": 119244, "bbox": [390.54, 175.85, 142.4, 156.43], "category_id": 1, "id": 508146, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "blue", "coat", "and", "black", "pants", "skiing", "downhill"], "raw": "A person in a blue coat and black pants skiing downhill", "sent_id": 79783, "sent": "a person in a blue coat and black pants skiing downhill"}, {"tokens": ["a", "skier", "with", "a", "blue", "shirt", ",", "black", "pants", ",", "black", "and", "white", "skies", ",", "black", "helmet"], "raw": "A skier with a blue shirt, black pants, black and white skies, black helmet.", "sent_id": 79784, "sent": "a skier with a blue shirt , black pants , black and white skies , black helmet"}], "file_name": "COCO_train2014_000000119244_508146.jpg", "ann_id": 508146, "sent_ids": [79783, 79784], "ref_id": 35662}, {"segmentation": [[166.49, 345.88, 162.76, 296.69, 179.9, 249.0, 201.51, 188.64, 205.98, 167.77, 229.09, 149.14, 246.23, 151.38, 264.11, 175.22, 270.82, 214.72, 290.94, 231.86, 317.77, 262.41, 369.93, 301.16, 413.9, 303.4, 434.02, 301.16, 436.26, 306.38, 324.47, 365.25, 300.63, 371.96, 290.19, 360.04, 267.84, 352.58, 245.48, 347.37, 211.2, 354.82, 170.21, 348.11]], "area": 28327.6665, "iscrowd": 0, "image_id": 286483, "bbox": [162.76, 149.14, 273.5, 222.82], "category_id": 1, "id": 432162, "split": "val", "sentences": [{"tokens": ["woman", "snowboarder"], "raw": "Woman snowboarder.", "sent_id": 79801, "sent": "woman snowboarder"}, {"tokens": ["a", "woman", "with", "a", "snowboard", "sitting", "down", "on", "the", "hill"], "raw": "a woman with a snowboard sitting down on the hill", "sent_id": 79802, "sent": "a woman with a snowboard sitting down on the hill"}], "file_name": "COCO_train2014_000000286483_432162.jpg", "ann_id": 432162, "sent_ids": [79801, 79802], "ref_id": 35671}, {"segmentation": [[108.75, 141.38, 117.0, 147.38, 116.25, 159.38, 123.75, 165.38, 131.25, 174.38, 133.5, 188.63, 135.75, 196.13, 137.25, 208.88, 137.25, 220.88, 137.25, 234.38, 139.5, 241.88, 145.5, 248.63, 147.0, 266.63, 145.5, 272.63, 136.5, 272.63, 135.0, 254.63, 121.5, 239.63, 112.5, 234.38, 105.0, 236.63, 106.5, 250.88, 98.25, 274.88, 96.0, 280.13, 84.75, 283.88, 84.0, 269.63, 90.75, 232.88, 93.0, 217.12, 99.0, 208.13, 99.75, 190.13, 94.5, 184.88, 89.25, 185.63, 87.0, 194.63, 92.25, 205.13, 96.0, 206.63, 88.5, 212.63, 82.5, 210.38, 81.0, 199.88, 86.25, 171.38, 95.25, 165.38, 96.0, 159.38, 93.75, 150.38, 100.5, 143.63]], "area": 4843.72875, "iscrowd": 0, "image_id": 111000, "bbox": [81.0, 141.38, 66.0, 142.5], "category_id": 1, "id": 488238, "split": "val", "sentences": [{"tokens": ["a", "blond", "male", "in", "a", "white", "t", "-", "shirt", "and", "gray", "pants", "running", "during", "a", "frisbee", "game"], "raw": "A blond male in a white t-shirt and gray pants running during a Frisbee game", "sent_id": 79920, "sent": "a blond male in a white t - shirt and gray pants running during a frisbee game"}, {"tokens": ["a", "boy", "with", "a", "white", "shirt", "with", "teal", "sleeves"], "raw": "A boy with a white shirt with teal sleeves.", "sent_id": 79921, "sent": "a boy with a white shirt with teal sleeves"}], "file_name": "COCO_train2014_000000111000_488238.jpg", "ann_id": 488238, "sent_ids": [79920, 79921], "ref_id": 35718}, {"segmentation": [[438.86, 408.66, 422.23, 328.87, 448.83, 297.28, 455.48, 272.35, 458.81, 235.77, 462.13, 227.46, 453.82, 215.83, 440.52, 172.61, 450.49, 164.29, 487.06, 164.29, 523.64, 179.26, 510.34, 204.19, 526.96, 240.76, 543.58, 340.5, 550.23, 393.7, 545.25, 458.53, 531.95, 463.52, 538.6, 564.92, 478.75, 576.55, 475.43, 564.92, 495.38, 548.29, 480.42, 546.63, 463.79, 539.98, 460.47, 531.67, 488.73, 533.33, 475.43, 466.84, 448.83, 463.52, 440.52, 445.23, 448.83, 420.29, 448.83, 418.63]], "area": 33398.0376, "iscrowd": 0, "image_id": 240500, "bbox": [422.23, 164.29, 128.0, 412.26], "category_id": 1, "id": 2176946, "split": "val", "sentences": [{"tokens": ["woman", "in", "coat", "standing", "outside"], "raw": "woman in coat standing outside", "sent_id": 80000, "sent": "woman in coat standing outside"}, {"tokens": ["a", "lady", "wearing", "a", "black", "and", "white", "coat", ",", "holding", "a", "purse"], "raw": "A lady wearing a black and white coat, holding a purse.", "sent_id": 80001, "sent": "a lady wearing a black and white coat , holding a purse"}], "file_name": "COCO_train2014_000000240500_2176946.jpg", "ann_id": 2176946, "sent_ids": [80000, 80001], "ref_id": 35748}, {"segmentation": [[212.99, 189.27, 195.88, 189.27, 192.67, 199.44, 185.18, 206.92, 180.91, 214.94, 174.49, 221.36, 172.35, 226.71, 173.42, 234.73, 175.02, 239.54, 164.86, 239.54, 154.7, 239.54, 148.82, 239.54, 142.4, 241.15, 132.77, 239.54, 131.17, 236.87, 134.91, 233.13, 145.08, 228.85, 148.28, 226.17, 152.03, 220.83, 157.38, 219.22, 155.24, 220.83, 157.38, 221.9, 165.93, 208.53, 183.05, 173.23, 188.93, 168.95, 195.88, 167.88, 207.65, 160.93, 210.85, 159.33, 190.53, 142.75, 183.05, 140.61, 179.3, 144.35, 178.77, 147.03, 177.16, 147.03, 160.58, 154.51, 154.17, 158.26, 149.35, 162.0, 141.87, 162.53, 133.31, 165.74, 126.89, 168.42, 122.61, 169.49, 116.73, 172.16, 111.92, 172.16, 108.17, 168.42, 108.17, 161.47, 115.13, 159.86, 118.34, 159.86, 123.68, 155.58, 125.82, 156.12, 130.64, 156.12, 141.87, 148.63, 147.21, 145.96, 153.1, 144.35, 159.51, 137.4, 168.61, 132.59, 169.14, 127.24, 179.3, 119.75, 180.91, 116.54, 181.44, 113.33, 182.51, 111.73, 177.7, 106.92, 172.88, 106.38, 169.68, 103.17, 170.21, 97.82, 171.81, 95.15, 168.61, 95.15, 171.81, 89.8, 173.42, 86.59, 175.56, 80.71, 179.84, 75.9, 187.86, 73.22, 200.16, 74.29, 206.04, 79.11, 207.11, 84.99, 206.58, 91.41, 202.3, 94.62, 214.06, 96.22, 225.83, 98.89, 238.13, 96.22, 248.82, 94.62, 271.29, 89.27, 278.24, 83.39, 281.98, 78.57, 285.73, 76.97, 283.59, 82.32, 288.4, 81.25, 294.82, 78.04, 296.42, 80.18, 291.61, 83.39, 287.86, 86.06, 287.86, 86.06, 298.03, 84.99, 300.16, 87.66, 290.54, 89.27, 299.63, 91.94, 298.03, 95.15, 290.54, 95.15, 288.93, 95.15, 297.49, 100.5, 292.68, 102.1, 286.79, 98.36, 281.45, 98.36, 274.49, 99.43, 261.66, 101.03, 250.96, 106.92, 239.2, 109.59, 230.64, 110.13, 225.29, 111.73, 222.09, 113.87, 222.09, 117.61, 233.32, 125.1, 236.52, 131.52, 247.76, 139.54, 247.76, 144.89, 252.03, 147.56, 254.17, 155.58, 258.99, 164.67, 258.99, 173.23, 253.64, 180.18, 248.29, 183.39, 246.69, 192.48, 244.01, 201.04, 240.8, 208.53, 255.24, 218.69, 257.92, 229.38, 263.26, 242.22, 273.43, 248.64, 279.84, 249.71, 282.52, 252.38, 281.98, 261.47, 270.75, 262.01, 259.52, 263.61, 249.89, 263.61, 248.82, 255.59, 253.64, 250.24, 249.89, 241.68, 237.59, 225.64, 226.36, 213.34, 221.02, 202.11, 221.02, 194.09, 215.13, 189.81]], "area": 10983.884799999998, "iscrowd": 0, "image_id": 142225, "bbox": [108.17, 73.22, 191.99, 190.39], "category_id": 1, "id": 458754, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "blue", "diving", "to", "hit", "a", "ball", "with", "a", "racket"], "raw": "A man in blue diving to hit a ball with a racket.", "sent_id": 80009, "sent": "a man in blue diving to hit a ball with a racket"}, {"tokens": ["a", "male", "tennis", "player", "reaching", "for", "a", "shot"], "raw": "A male tennis player reaching for a shot.", "sent_id": 80010, "sent": "a male tennis player reaching for a shot"}], "file_name": "COCO_train2014_000000142225_458754.jpg", "ann_id": 458754, "sent_ids": [80009, 80010], "ref_id": 35752}, {"segmentation": [[87.71, 26.07, 91.52, 3.22, 419.06, 1.95, 424.13, 179.68, 335.27, 188.56, 304.8, 126.36, 221.01, 62.88, 151.19, 85.73, 108.03, 131.44, 101.68, 177.14, 95.33, 199.99, 72.48, 178.41], [317.84, 270.48, 326.47, 333.76, 371.06, 422.93, 381.12, 448.81, 365.3, 457.44, 326.47, 457.44, 290.52, 448.81, 271.82, 443.06]], "area": 51820.29075000001, "iscrowd": 0, "image_id": 398172, "bbox": [72.48, 1.95, 351.65, 455.49], "category_id": 22, "id": 583041, "split": "val", "sentences": [{"tokens": ["back", "legs", "and", "tail", "of", "adult", "elephant", "behind", "the", "baby"], "raw": "back legs and tail of adult elephant behind the baby", "sent_id": 80015, "sent": "back legs and tail of adult elephant behind the baby"}, {"tokens": ["tallest", "elephant", "in", "the", "back", "side"], "raw": "tallest elephant in the back side", "sent_id": 80016, "sent": "tallest elephant in the back side"}], "file_name": "COCO_train2014_000000398172_583041.jpg", "ann_id": 583041, "sent_ids": [80015, 80016], "ref_id": 35754}, {"segmentation": [[512.15, 254.53, 511.55, 257.53, 504.35, 267.74, 490.55, 323.55, 468.34, 328.35, 485.15, 388.97, 484.55, 390.77, 482.75, 390.17, 468.34, 400.97, 471.94, 417.78, 462.34, 418.38, 459.94, 403.97, 438.33, 402.17, 427.53, 402.17, 403.52, 393.77, 399.92, 405.77, 392.72, 401.57, 413.73, 338.55, 413.73, 322.95, 388.52, 308.55, 392.12, 300.74, 395.12, 302.54, 390.32, 281.54, 386.72, 275.54, 389.72, 269.54, 395.12, 276.74, 403.52, 281.54, 413.13, 283.94, 431.13, 277.94, 432.33, 267.13, 429.93, 266.53, 428.13, 261.13, 439.53, 262.33, 439.53, 257.53, 448.54, 256.33, 467.14, 249.13, 479.14, 246.73, 489.95, 248.53, 497.75, 255.13]], "area": 12132.495899999998, "iscrowd": 0, "image_id": 363190, "bbox": [386.72, 246.73, 125.43, 171.65], "category_id": 62, "id": 103375, "split": "val", "sentences": [{"tokens": ["a", "wicker", "chair", "standing", "on", "the", "edge", "of", "the", "counter", "across", "from", "the", "cardenza"], "raw": "A wicker chair standing on the edge of the counter across from the cardenza", "sent_id": 80052, "sent": "a wicker chair standing on the edge of the counter across from the cardenza"}], "file_name": "COCO_train2014_000000363190_103375.jpg", "ann_id": 103375, "sent_ids": [80052], "ref_id": 35768}, {"segmentation": [[355.5, 264.39, 359.09, 255.86, 365.38, 250.02, 372.12, 249.12, 379.76, 249.57, 383.8, 252.26, 386.5, 256.76, 389.64, 263.5, 392.79, 265.29, 399.08, 260.8, 406.72, 258.55, 411.21, 259.45, 416.15, 262.6, 416.15, 264.39, 413.91, 268.44, 411.21, 272.93, 408.07, 276.53, 413.46, 281.92, 424.24, 281.92, 436.37, 282.37, 450.75, 283.71, 464.68, 283.71, 481.3, 281.92, 511.86, 281.02, 536.57, 277.87, 557.24, 274.28, 568.92, 271.13, 580.15, 272.03, 587.34, 272.93, 598.58, 275.18, 605.32, 281.02, 609.81, 289.56, 612.95, 297.64, 616.55, 308.43, 617.45, 322.81, 619.24, 355.16, 616.1, 369.53, 614.75, 376.27, 617.9, 396.94, 620.14, 402.78, 620.61, 425.05, 620.13, 444.58, 621.59, 457.28, 621.59, 460.21, 616.22, 457.76, 611.34, 455.32, 606.94, 454.35, 606.45, 442.63, 603.03, 426.03, 599.13, 415.77, 595.71, 411.38, 592.29, 405.52, 587.9, 397.7, 583.99, 387.94, 585.94, 402.1, 586.92, 412.84, 584.97, 426.03, 577.64, 451.42, 577.64, 457.76, 573.74, 461.18, 563.48, 462.16, 560.07, 460.21, 561.53, 450.93, 565.44, 434.81, 565.93, 421.63, 565.93, 415.28, 562.51, 407.47, 562.02, 403.08, 556.65, 396.24, 555.67, 393.31, 553.72, 387.45, 551.76, 383.54, 540.53, 390.38, 534.67, 393.8, 527.84, 396.73, 516.12, 397.7, 502.45, 397.7, 490.73, 397.7, 479.5, 397.7, 467.29, 396.73, 460.45, 394.77, 457.53, 394.77, 456.06, 394.77, 452.15, 400.15, 450.69, 407.47, 450.69, 415.28, 448.74, 422.12, 446.29, 428.47, 444.83, 432.86, 443.85, 441.16, 443.85, 448.49, 445.32, 466.55, 436.04, 468.51, 426.76, 464.6, 419.44, 463.14, 418.46, 448.0, 418.46, 439.21, 417.0, 424.56, 412.6, 413.82, 409.67, 406.01, 396.0, 401.12, 382.33, 383.06, 379.89, 373.78, 378.42, 360.59, 375.49, 352.78, 371.1, 344.97, 365.73, 334.72, 362.31, 326.41, 361.82, 322.02, 358.89, 317.63, 354.98, 314.21, 353.03, 311.77, 353.03, 299.15, 350.1, 290.85, 350.1, 284.5, 349.13, 280.59, 343.75, 281.08, 340.82, 281.08, 334.96, 278.64, 331.55, 273.76, 329.59, 270.34, 326.18, 264.97, 326.18, 262.04, 329.59, 259.6, 334.48, 259.6, 341.8, 259.11, 347.17, 262.04, 349.61, 262.04, 353.52, 262.04, 355.96, 261.06]], "area": 35550.63284999997, "iscrowd": 0, "image_id": 160852, "bbox": [326.18, 249.12, 295.41, 219.39], "category_id": 21, "id": 74894, "split": "val", "sentences": [{"tokens": ["the", "cow", "on", "the", "far", "right", "of", "the", "herd"], "raw": "The cow on the far right of the herd.", "sent_id": 80065, "sent": "the cow on the far right of the herd"}, {"tokens": ["the", "cow", "on", "the", "right"], "raw": "the cow on the right", "sent_id": 80066, "sent": "the cow on the right"}], "file_name": "COCO_train2014_000000160852_74894.jpg", "ann_id": 74894, "sent_ids": [80065, 80066], "ref_id": 35771}, {"segmentation": [[64.72, 376.9, 67.6, 359.65, 112.18, 359.65, 224.36, 506.34, 304.9, 627.15, 179.78, 630.03, 148.13, 628.59, 113.62, 519.29, 93.48, 456.01, 66.16, 379.78]], "area": 28843.6333, "iscrowd": 0, "image_id": 431761, "bbox": [64.72, 359.65, 240.18, 270.38], "category_id": 7, "id": 174213, "split": "val", "sentences": [{"tokens": ["a", "train", "going", "through", "the", "station"], "raw": "A train going through the station.", "sent_id": 80132, "sent": "a train going through the station"}, {"tokens": ["a", "train", "is", "parked", "at", "the", "station"], "raw": "A train is parked at the station.", "sent_id": 80133, "sent": "a train is parked at the station"}], "file_name": "COCO_train2014_000000431761_174213.jpg", "ann_id": 174213, "sent_ids": [80132, 80133], "ref_id": 35797}, {"segmentation": [[1.1, 142.07, 0.0, 277.53, 17.62, 313.87, 22.03, 313.87, 34.14, 339.2, 31.94, 341.4, 31.94, 364.53, 41.85, 364.53, 56.17, 361.23, 61.67, 360.12, 83.7, 355.72, 95.81, 351.31, 101.32, 340.3, 94.71, 335.9, 85.9, 333.69, 72.69, 330.39, 62.77, 327.09, 55.06, 321.58, 48.46, 296.25, 33.04, 245.59, 26.43, 226.87, 26.43, 205.94, 12.11, 165.19, 2.2, 145.37]], "area": 6968.905450000002, "iscrowd": 0, "image_id": 288234, "bbox": [0.0, 142.07, 101.32, 222.46], "category_id": 1, "id": 2155825, "split": "val", "sentences": [{"tokens": ["the", "right", "leg", "of", "a", "person", "playing", "a", "baseman", "in", "a", "baseball", "game"], "raw": "the right leg of a person playing a baseman in a baseball game", "sent_id": 80215, "sent": "the right leg of a person playing a baseman in a baseball game"}, {"tokens": ["a", "leg", "sticks", "out", "ahead", "of", "the", "base"], "raw": "A leg sticks out ahead of the base.", "sent_id": 80216, "sent": "a leg sticks out ahead of the base"}], "file_name": "COCO_train2014_000000288234_2155825.jpg", "ann_id": 2155825, "sent_ids": [80215, 80216], "ref_id": 35828}, {"segmentation": [[228.67, 434.34, 228.67, 349.48, 186.97, 353.8, 162.52, 356.67, 153.89, 359.55, 158.2, 402.7, 152.45, 405.57, 143.82, 402.7, 136.63, 378.25, 135.19, 352.36, 143.82, 320.72, 165.39, 270.38, 231.55, 245.93, 281.89, 260.31, 310.65, 271.82, 360.99, 261.75, 414.2, 299.15, 426.0, 345.17, 405.57, 418.52, 366.74, 411.33, 335.1, 418.52, 322.16, 419.96, 306.34, 428.58, 277.57, 434.34, 232.99, 442.97]], "area": 38075.68075, "iscrowd": 0, "image_id": 559700, "bbox": [135.19, 245.93, 290.81, 197.04], "category_id": 22, "id": 580853, "split": "val", "sentences": [{"tokens": ["a", "baby", "elephant", "between", "a", "sleeping", "elephant", "and", "a", "standing", "large", "elephant"], "raw": "A baby elephant between a sleeping elephant and a standing large elephant.", "sent_id": 80223, "sent": "a baby elephant between a sleeping elephant and a standing large elephant"}, {"tokens": ["a", "calf"], "raw": "A calf", "sent_id": 80224, "sent": "a calf"}], "file_name": "COCO_train2014_000000559700_580853.jpg", "ann_id": 580853, "sent_ids": [80223, 80224], "ref_id": 35832}, {"segmentation": [[388.02, 398.01, 388.02, 392.19, 370.58, 368.92, 358.93, 323.52, 385.7, 232.75, 392.69, 217.62, 367.08, 167.58, 322.86, 148.96, 317.03, 90.77, 314.71, 60.51, 324.02, 65.16, 339.14, 133.83, 383.37, 128.01, 379.88, 110.55, 365.91, 96.58, 382.21, 80.29, 410.13, 79.13, 410.13, 87.27, 412.47, 122.19, 485.79, 116.37, 532.34, 96.58, 538.15, 88.44, 548.64, 87.27, 554.45, 103.57, 543.98, 105.89, 483.46, 145.46, 460.19, 155.94, 454.36, 208.31, 471.82, 260.68, 443.89, 349.13, 414.8, 378.23, 404.32, 363.09, 428.76, 309.56, 436.91, 278.14, 427.59, 266.51, 417.12, 279.3, 391.52, 322.36, 399.66, 365.43, 406.65, 396.85, 396.17, 396.85]], "area": 25384.867899999997, "iscrowd": 0, "image_id": 289425, "bbox": [314.71, 60.51, 239.74, 337.5], "category_id": 1, "id": 459375, "split": "val", "sentences": [{"tokens": ["a", "white", "andble", "unfirom", "with", "the", "number", "14", "on", "it"], "raw": "A white andble unfirom with the number 14 on it.", "sent_id": 80269, "sent": "a white andble unfirom with the number 14 on it"}, {"tokens": ["playing", "man"], "raw": "PLAYING MAN", "sent_id": 80270, "sent": "playing man"}], "file_name": "COCO_train2014_000000289425_459375.jpg", "ann_id": 459375, "sent_ids": [80269, 80270], "ref_id": 35855}, {"segmentation": [[552.9, 123.47, 552.9, 108.33, 552.6, 101.36, 551.38, 96.82, 551.69, 92.58, 553.5, 88.95, 557.74, 83.8, 561.07, 81.08, 562.59, 78.96, 563.8, 74.72, 563.5, 71.69, 558.35, 67.76, 553.81, 64.42, 551.38, 58.07, 552.9, 43.53, 555.02, 33.54, 558.35, 28.7, 562.59, 25.06, 572.28, 26.28, 584.08, 32.33, 588.02, 36.57, 593.47, 41.72, 595.89, 47.17, 596.8, 49.89, 597.0, 58.65, 596.09, 76.21, 595.78, 83.18, 593.97, 87.42, 587.61, 94.98, 572.77, 102.86, 567.02, 124.14, 566.72, 129.89, 566.72, 135.04, 566.72, 139.28, 565.2, 143.82, 563.69, 147.75, 563.99, 149.57, 567.63, 154.42, 570.96, 160.17, 570.35, 162.89, 563.69, 164.41, 556.42, 164.71, 551.88, 160.77, 551.58, 157.75, 550.97, 153.81, 548.25, 145.33, 549.16, 143.21, 550.97, 134.74, 552.49, 129.29, 552.49, 125.95], [575.34, 178.77, 568.27, 216.47, 571.8, 212.34, 575.34, 207.04, 575.93, 182.3], [612.44, 219.41, 611.85, 234.72, 610.68, 244.74, 610.68, 254.16, 610.68, 261.23, 611.26, 265.94, 610.09, 267.71, 608.32, 271.83, 608.32, 281.25, 608.32, 305.4, 605.96, 317.77, 602.43, 326.02, 594.77, 320.13, 593.01, 308.94, 592.42, 297.75, 593.6, 280.08, 594.18, 268.3, 594.18, 261.82, 595.36, 254.75, 595.36, 248.27, 597.13, 240.03, 600.66, 232.96, 608.32, 217.64], [633.06, 253.57, 638.95, 261.82, 640.0, 268.3, 640.0, 273.6, 640.0, 319.54, 638.36, 324.25, 631.29, 323.07, 631.88, 318.36, 633.65, 309.53, 634.24, 302.46, 634.24, 295.98, 634.24, 292.45, 631.88, 285.97, 628.93, 281.84, 628.35, 280.67]], "area": 5844.379600000005, "iscrowd": 0, "image_id": 505924, "bbox": [548.25, 25.06, 91.75, 300.96], "category_id": 1, "id": 1757576, "split": "val", "sentences": [{"tokens": ["there", "is", "a", "girl", "standing", "behind", "another", "girl", "on", "the", "right", "side", "of", "the", "picture"], "raw": "There is a girl standing behind another girl on the right side of the picture.", "sent_id": 80375, "sent": "there is a girl standing behind another girl on the right side of the picture"}, {"tokens": ["white", "girl", "in", "blue", "uniform"], "raw": "white girl in blue uniform", "sent_id": 80376, "sent": "white girl in blue uniform"}], "file_name": "COCO_train2014_000000505924_1757576.jpg", "ann_id": 1757576, "sent_ids": [80375, 80376], "ref_id": 35893}, {"segmentation": [[231.46, 139.33, 229.21, 89.89, 231.46, 57.3, 250.56, 19.1, 255.06, 1.12, 359.0, 0.0, 357.3, 71.91, 357.3, 179.78, 359.0, 311.24, 358.43, 471.91, 349.44, 410.11, 346.07, 386.52, 331.46, 355.06, 333.71, 326.97, 340.45, 289.89, 341.57, 243.82, 329.21, 213.48, 308.99, 202.25, 289.89, 203.37, 287.64, 242.7, 289.89, 300.0, 294.38, 342.7, 285.39, 403.37, 282.02, 455.06, 279.78, 493.26, 256.18, 491.01, 259.55, 432.58, 264.04, 383.15, 259.55, 349.44, 262.92, 311.24, 262.92, 275.28, 255.06, 228.09, 243.82, 210.11, 269.66, 195.51, 300.0, 187.64, 302.25, 160.67, 286.52, 115.73, 250.56, 114.61, 241.57, 143.82, 231.46, 149.44, 228.09, 134.83]], "area": 32649.41494999997, "iscrowd": 0, "image_id": 378791, "bbox": [228.09, 0.0, 130.91, 493.26], "category_id": 25, "id": 597885, "split": "val", "sentences": [{"tokens": ["the", "side", "of", "a", "giraffe"], "raw": "the side of a giraffe", "sent_id": 80391, "sent": "the side of a giraffe"}, {"tokens": ["large", "giraffe", "that", "is", "barely", "in", "the", "photo"], "raw": "Large giraffe that is barely in the photo.", "sent_id": 80392, "sent": "large giraffe that is barely in the photo"}], "file_name": "COCO_train2014_000000378791_597885.jpg", "ann_id": 597885, "sent_ids": [80391, 80392], "ref_id": 35898}, {"segmentation": [[286.91, 5.6, 287.87, 105.39, 287.87, 110.19, 309.93, 119.78, 343.52, 138.02, 370.39, 162.96, 377.1, 171.6, 387.66, 220.54, 375.18, 259.88, 374.22, 310.73, 413.57, 304.98, 454.83, 280.03, 462.5, 261.8, 478.82, 177.36, 498.97, 64.13, 500.89, 37.26, 509.52, 17.11, 506.64, 1.76, 288.82, 0.8]], "area": 43181.66849999999, "iscrowd": 0, "image_id": 541938, "bbox": [286.91, 0.8, 222.61, 309.93], "category_id": 47, "id": 1507110, "split": "val", "sentences": [{"tokens": ["cup", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "cup on the right in the right hand picture", "sent_id": 80506, "sent": "cup on the right in the right hand picture"}, {"tokens": ["pot", "with", "lighter", "chocolate"], "raw": "pot with lighter chocolate", "sent_id": 80507, "sent": "pot with lighter chocolate"}], "file_name": "COCO_train2014_000000541938_1507110.jpg", "ann_id": 1507110, "sent_ids": [80506, 80507], "ref_id": 35938}, {"segmentation": [[566.61, 183.77, 599.02, 180.73, 604.76, 180.73, 608.13, 185.12, 609.82, 185.8, 625.69, 186.47, 631.76, 190.19, 635.14, 197.95, 635.48, 198.29, 621.3, 201.33, 611.85, 204.03, 611.51, 217.53, 617.92, 216.18, 632.44, 216.18, 632.44, 222.93, 626.7, 224.96, 615.56, 229.01, 610.5, 250.27, 612.19, 270.87, 612.19, 276.94, 615.56, 316.1, 624.34, 312.39, 633.11, 312.39, 638.18, 317.79, 638.52, 322.51, 633.45, 328.25, 623.33, 329.94, 615.22, 337.37, 608.81, 338.38, 607.46, 343.78, 608.47, 369.77, 603.07, 375.17, 592.94, 375.17, 587.88, 361.0, 578.43, 362.01, 573.37, 360.66, 568.64, 356.27, 568.64, 344.46, 568.64, 342.43, 565.6, 341.08, 548.72, 337.37, 546.02, 325.89, 557.84, 323.19, 577.75, 319.81, 573.37, 284.71, 568.3, 248.59, 564.25, 229.34, 559.19, 230.36, 555.81, 225.63, 554.8, 216.18, 560.2, 211.79, 563.91, 191.87]], "area": 9357.489600000003, "iscrowd": 0, "image_id": 195861, "bbox": [546.02, 180.73, 92.5, 194.44], "category_id": 4, "id": 1790058, "split": "val", "sentences": [{"tokens": ["the", "motorcycle", "that", "is", "riding", "towards", "the", "camera", "with", "the", "guy", "in", "the", "blue", "shirt", "on", "it"], "raw": "The motorcycle that is riding towards the camera with the guy in the blue shirt on it", "sent_id": 80514, "sent": "the motorcycle that is riding towards the camera with the guy in the blue shirt on it"}, {"tokens": ["the", "motorcycle", "on", "the", "right", "coming", "towards", "camera"], "raw": "The motorcycle on the right coming towards camera", "sent_id": 80515, "sent": "the motorcycle on the right coming towards camera"}], "file_name": "COCO_train2014_000000195861_1790058.jpg", "ann_id": 1790058, "sent_ids": [80514, 80515], "ref_id": 35941}, {"segmentation": [[367.62, 302.16, 307.54, 250.16, 291.4, 235.81, 298.58, 205.33, 289.61, 177.53, 275.27, 159.6, 260.02, 145.25, 251.95, 141.67, 251.95, 128.22, 246.57, 118.36, 239.4, 113.87, 229.54, 115.67, 225.95, 117.46, 219.67, 125.53, 209.81, 132.7, 220.57, 138.98, 216.09, 142.56, 193.67, 153.32, 161.39, 190.98, 158.7, 205.33, 147.05, 220.57, 140.77, 232.23, 151.53, 236.71, 157.81, 236.71, 138.08, 268.99, 134.49, 286.02, 117.46, 297.68, 113.87, 308.44, 107.6, 326.37, 117.46, 329.96, 128.22, 324.58, 132.7, 323.68, 134.49, 314.72, 162.29, 288.71, 176.64, 251.06, 216.98, 234.02, 291.4, 263.61, 327.27, 296.78, 331.75, 303.06, 335.34, 311.13, 364.03, 313.82]], "area": 17778.583599999998, "iscrowd": 0, "image_id": 482731, "bbox": [107.6, 113.87, 260.02, 216.09], "category_id": 1, "id": 461500, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "baseball", "uniform", "straddled", "with", "hand", "ready", "to", "catch", "a", "ball"], "raw": "a man in baseball uniform straddled with hand ready to catch a ball.", "sent_id": 80523, "sent": "a man in baseball uniform straddled with hand ready to catch a ball"}, {"tokens": ["first", "baseman", "for", "the", "seattle", "mariners", "holding", "his", "foot", "on", "first", "base", "and", "trying", "to", "catch", "the", "ball"], "raw": "First baseman for the Seattle Mariners  holding his foot on first base and trying to catch the ball.", "sent_id": 80524, "sent": "first baseman for the seattle mariners holding his foot on first base and trying to catch the ball"}], "file_name": "COCO_train2014_000000482731_461500.jpg", "ann_id": 461500, "sent_ids": [80523, 80524], "ref_id": 35945}, {"segmentation": [[517.11, 359.83, 471.94, 283.75, 452.92, 212.43, 461.24, 162.5, 495.71, 104.25, 540.89, 60.26, 558.72, 113.76, 567.04, 240.96, 542.08, 355.08, 525.43, 357.45]], "area": 22707.752899999996, "iscrowd": 0, "image_id": 382469, "bbox": [452.92, 60.26, 114.12, 299.57], "category_id": 28, "id": 284847, "split": "val", "sentences": [{"tokens": ["umbrella", "to", "the", "right", "of", "glasses"], "raw": "Umbrella to the right of glasses.", "sent_id": 80589, "sent": "umbrella to the right of glasses"}, {"tokens": ["the", "right", "umbrella"], "raw": "The right umbrella.", "sent_id": 80590, "sent": "the right umbrella"}], "file_name": "COCO_train2014_000000382469_284847.jpg", "ann_id": 284847, "sent_ids": [80589, 80590], "ref_id": 35974}, {"segmentation": [[480.0, 294.45, 478.97, 273.81, 492.39, 239.74, 518.19, 203.61, 532.65, 188.13, 544.0, 186.06, 633.81, 181.94, 638.97, 189.16, 640.0, 339.87, 591.48, 339.87, 581.16, 353.29, 545.03, 356.39, 545.03, 330.58, 519.23, 333.68, 518.19, 347.1, 491.35, 347.1, 485.16, 337.81, 482.06, 300.65]], "area": 23265.834749999998, "iscrowd": 0, "image_id": 352185, "bbox": [478.97, 181.94, 161.03, 174.45], "category_id": 3, "id": 134613, "split": "val", "sentences": [{"tokens": ["a", "black", "suv", "stopped", "in", "traffic"], "raw": "A black SUV stopped in traffic.", "sent_id": 80599, "sent": "a black suv stopped in traffic"}, {"tokens": ["black", "suv"], "raw": "black suv", "sent_id": 80600, "sent": "black suv"}], "file_name": "COCO_train2014_000000352185_134613.jpg", "ann_id": 134613, "sent_ids": [80599, 80600], "ref_id": 35979}, {"segmentation": [[394.3, 188.92, 393.46, 186.4, 393.46, 156.2, 393.46, 141.1, 403.52, 119.28, 420.3, 110.9, 419.46, 109.22, 404.36, 103.35, 401.85, 102.51, 401.01, 102.51, 395.13, 93.28, 394.3, 89.08, 394.3, 82.37, 393.46, 78.18, 387.58, 64.75, 390.94, 58.04, 400.17, 24.49, 403.52, 12.74, 432.05, 1.84, 465.6, 6.87, 474.83, 15.26, 479.03, 21.97, 485.74, 37.07, 485.74, 54.69, 484.06, 63.92, 473.15, 84.89, 478.19, 99.15, 486.58, 107.54, 500.0, 125.16, 498.32, 370.96, 360.74, 373.48, 391.78, 339.08, 379.19, 292.94, 343.96, 265.26, 331.38, 266.1, 330.54, 242.61, 333.89, 230.02, 328.02, 230.86, 328.02, 227.51, 330.54, 222.47, 334.73, 224.15, 334.73, 224.15, 352.35, 224.15, 358.22, 235.06, 359.06, 232.54, 359.9, 226.67, 348.15, 214.08, 343.12, 209.05, 348.15, 209.05, 357.38, 209.05, 376.68, 222.47, 393.46, 193.11]], "area": 40902.612100000006, "iscrowd": 0, "image_id": 479396, "bbox": [328.02, 1.84, 171.98, 371.64], "category_id": 1, "id": 209456, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "brown", "sweater", "and", "holding", "a", "game", "control"], "raw": "A man wearing a brown sweater and holding a game control.", "sent_id": 80613, "sent": "a man wearing a brown sweater and holding a game control"}, {"tokens": ["a", "man", "in", "a", "sweater", "playing", "a", "video", "game", "with", "a", "woman"], "raw": "A man in a sweater playing a video game with a woman.", "sent_id": 80614, "sent": "a man in a sweater playing a video game with a woman"}], "file_name": "COCO_train2014_000000479396_209456.jpg", "ann_id": 209456, "sent_ids": [80613, 80614], "ref_id": 35984}, {"segmentation": [[311.72, 116.4, 444.99, 183.04, 507.11, 257.58, 521.79, 257.58, 531.95, 236.12, 519.53, 203.37, 478.87, 152.55, 431.44, 115.28, 362.54, 88.17, 319.62, 93.82, 312.85, 102.85]], "area": 11907.474949999996, "iscrowd": 0, "image_id": 450914, "bbox": [311.72, 88.17, 220.23, 169.41], "category_id": 52, "id": 1044442, "split": "val", "sentences": [{"tokens": ["the", "bannana", "in", "the", "back"], "raw": "The bannana in the back", "sent_id": 80688, "sent": "the bannana in the back"}], "file_name": "COCO_train2014_000000450914_1044442.jpg", "ann_id": 1044442, "sent_ids": [80688], "ref_id": 36013}, {"segmentation": [[94.92, 282.43, 154.25, 237.12, 181.21, 209.08, 206.02, 206.92, 223.28, 199.37, 279.37, 195.06, 290.16, 181.03, 350.56, 189.66, 462.74, 183.19, 483.24, 206.92, 508.04, 286.74, 489.71, 293.21, 482.16, 349.3, 472.45, 323.42, 467.06, 306.16, 462.74, 302.92, 455.19, 325.57, 227.6, 327.73, 101.39, 323.42]], "area": 48371.8819, "iscrowd": 0, "image_id": 205794, "bbox": [94.92, 181.03, 413.12, 168.27], "category_id": 65, "id": 318373, "split": "val", "sentences": [{"tokens": ["an", "unmade", "bed", "with", "white", "sheets", "and", "brown", "blankets"], "raw": "An unmade bed with white sheets and brown blankets.", "sent_id": 81129, "sent": "an unmade bed with white sheets and brown blankets"}, {"tokens": ["the", "matteress", "of", "the", "bed", "with", "pillows", "and", "blankets"], "raw": "the matteress of the bed with pillows and blankets", "sent_id": 81130, "sent": "the matteress of the bed with pillows and blankets"}], "file_name": "COCO_train2014_000000205794_318373.jpg", "ann_id": 318373, "sent_ids": [81129, 81130], "ref_id": 36176}, {"segmentation": [[218.55, 480.0, 266.82, 478.3, 266.82, 444.78, 273.52, 443.44, 289.61, 428.69, 288.27, 467.57, 288.27, 476.96, 332.51, 479.64, 335.2, 434.06, 339.22, 405.9, 332.51, 389.81, 339.22, 373.72, 339.22, 367.02, 332.51, 340.2, 333.85, 312.04, 343.24, 301.32, 349.94, 275.84, 355.31, 254.39, 360.67, 235.62, 355.31, 224.89, 344.58, 207.46, 327.15, 198.08, 327.15, 183.33, 327.15, 165.9, 321.79, 152.49, 309.72, 139.08, 293.63, 132.38, 274.86, 132.38, 253.41, 155.17, 249.39, 188.69, 256.09, 211.49, 245.36, 214.17, 258.77, 238.3, 260.11, 274.5, 252.07, 302.66, 244.02, 322.77, 256.09, 330.82, 234.64, 376.4, 231.96, 401.88, 219.89, 451.49, 215.87, 478.3]], "area": 31137.36775, "iscrowd": 0, "image_id": 416076, "bbox": [215.87, 132.38, 144.8, 347.62], "category_id": 1, "id": 488012, "split": "val", "sentences": [{"tokens": ["man", "wearing", "a", "green", "coat"], "raw": "Man wearing a green coat.", "sent_id": 81172, "sent": "man wearing a green coat"}, {"tokens": ["a", "skiier", "in", "green", "and", "black", "wearing", "large", "goggles"], "raw": "A skiier in green and black wearing large goggles", "sent_id": 81173, "sent": "a skiier in green and black wearing large goggles"}], "file_name": "COCO_train2014_000000416076_488012.jpg", "ann_id": 488012, "sent_ids": [81172, 81173], "ref_id": 36188}, {"segmentation": [[293.46, 340.17, 283.57, 341.27, 268.18, 383.04, 273.68, 461.07, 298.95, 470.96, 306.65, 461.07, 306.65, 447.88, 323.14, 445.68, 329.73, 454.48, 357.21, 445.68, 364.9, 441.29, 370.4, 451.18, 382.49, 448.98, 390.18, 470.96, 411.06, 467.67, 407.77, 421.5, 411.06, 423.7, 407.77, 418.21, 411.06, 379.74, 405.57, 359.95, 384.68, 363.25, 363.8, 333.58, 336.32, 334.68, 339.62, 368.75, 301.15, 370.95, 303.35, 353.36]], "area": 14200.8341, "iscrowd": 0, "image_id": 540110, "bbox": [268.18, 333.58, 142.88, 137.38], "category_id": 8, "id": 394104, "split": "val", "sentences": [{"tokens": ["grey", "lifted", "truk", "with", "red", "and", "white", "signal", "signs", "on", "the", "tailgate"], "raw": "Grey lifted truk with red and white signal signs on the tailgate", "sent_id": 81174, "sent": "grey lifted truk with red and white signal signs on the tailgate"}, {"tokens": ["blue", "pickup", "truck"], "raw": "blue pickup truck", "sent_id": 81175, "sent": "blue pickup truck"}], "file_name": "COCO_train2014_000000540110_394104.jpg", "ann_id": 394104, "sent_ids": [81174, 81175], "ref_id": 36189}, {"segmentation": [[105.52, 104.77, 118.85, 74.42, 125.51, 72.94, 141.79, 72.94, 145.5, 76.64, 152.9, 90.71, 153.64, 104.77, 152.9, 115.87, 155.12, 130.68, 89.24, 130.68, 87.02, 126.98, 93.68, 114.39, 104.04, 106.25], [86.28, 142.52, 73.7, 177.31, 77.4, 207.66, 92.2, 224.68, 87.76, 281.68, 83.32, 304.63, 97.38, 309.81, 107.0, 300.93, 99.6, 269.1, 104.04, 254.29, 105.52, 146.22]], "area": 6061.606749999999, "iscrowd": 0, "image_id": 547165, "bbox": [73.7, 72.94, 81.42, 236.87], "category_id": 1, "id": 186587, "split": "val", "sentences": [{"tokens": ["a", "woman"], "raw": "A woman.", "sent_id": 81245, "sent": "a woman"}, {"tokens": ["woman", "in", "blue", "shirt", "on", "phone"], "raw": "Woman in blue shirt on phone.", "sent_id": 81246, "sent": "woman in blue shirt on phone"}], "file_name": "COCO_train2014_000000547165_186587.jpg", "ann_id": 186587, "sent_ids": [81245, 81246], "ref_id": 36214}, {"segmentation": [[46.14, 38.95, 131.32, 31.21, 186.64, 24.56, 289.52, 21.26, 322.7, 22.36, 351.47, 51.13, 370.28, 66.62, 268.5, 77.68, 232.0, 104.23, 191.07, 72.14, 151.23, 71.03, 136.84, 57.76, 105.88, 65.51, 85.96, 97.58, 83.75, 123.04, 70.47, 129.67, 72.69, 234.77, 67.15, 266.86, 67.15, 324.39, 64.93, 349.83, 53.88, 384.12, 42.82, 384.12, 32.86, 364.21, 33.97, 339.88, 30.65, 321.06, 8.51, 304.47, 2.99, 294.52, 0.78, 120.82, 28.43, 65.51, 38.39, 41.16]], "area": 33818.7317, "iscrowd": 0, "image_id": 517920, "bbox": [0.78, 21.26, 369.5, 362.86], "category_id": 3, "id": 352256, "split": "val", "sentences": [{"tokens": ["car", "parked", "furthest", "from", "meters"], "raw": "Car parked furthest from meters.", "sent_id": 81255, "sent": "car parked furthest from meters"}, {"tokens": ["car", "furthest", "from", "parking", "meters"], "raw": "Car furthest from parking meters", "sent_id": 81256, "sent": "car furthest from parking meters"}], "file_name": "COCO_train2014_000000517920_352256.jpg", "ann_id": 352256, "sent_ids": [81255, 81256], "ref_id": 36219}, {"segmentation": [[511.24, 387.52, 496.68, 385.7, 493.05, 374.79, 485.77, 364.78, 481.22, 350.23, 485.77, 333.85, 486.68, 323.85, 490.32, 313.84, 490.32, 306.56, 493.05, 293.83, 496.68, 280.18, 500.32, 277.45, 509.42, 276.54, 513.06, 276.54, 517.61, 276.54, 517.61, 276.54, 519.43, 274.72, 519.43, 269.26, 519.43, 263.81, 526.7, 259.26, 537.62, 254.71, 552.17, 252.89, 557.63, 252.89, 565.82, 251.98, 578.55, 251.98, 583.1, 263.81, 582.19, 271.99, 581.28, 277.45, 580.37, 282.91, 577.65, 295.65, 576.74, 311.11, 572.19, 322.03, 565.82, 339.31, 563.09, 355.68, 563.09, 372.97, 559.45, 382.06, 543.08, 388.43, 529.43, 390.25, 513.06, 390.25, 505.78, 390.25, 464.85, 382.06]], "area": 10405.219000000005, "iscrowd": 0, "image_id": 363190, "bbox": [464.85, 251.98, 118.25, 138.27], "category_id": 62, "id": 105202, "split": "val", "sentences": [{"tokens": ["the", "chair", "in", "between", "two", "other", "chairs", "at", "the", "counter"], "raw": "The chair in between two other chairs at the counter", "sent_id": 81283, "sent": "the chair in between two other chairs at the counter"}, {"tokens": ["a", "tan", "wicker", "chair", ",", "in", "between", "two", "other", "chairs"], "raw": "A tan wicker chair, in between two other chairs", "sent_id": 81284, "sent": "a tan wicker chair , in between two other chairs"}], "file_name": "COCO_train2014_000000363190_105202.jpg", "ann_id": 105202, "sent_ids": [81283, 81284], "ref_id": 36232}, {"segmentation": [[188.48, 71.32, 183.39, 99.84, 168.11, 99.84, 158.94, 88.64, 72.34, 102.9, 50.94, 125.32, 12.23, 125.32, 13.24, 11.21, 155.88, 1.02, 183.39, 29.55, 189.5, 72.34]], "area": 16812.422450000002, "iscrowd": 0, "image_id": 208243, "bbox": [12.23, 1.02, 177.27, 124.3], "category_id": 3, "id": 1776742, "split": "val", "sentences": [{"tokens": ["a", "black", "honda", "car"], "raw": "A black Honda car", "sent_id": 81286, "sent": "a black honda car"}, {"tokens": ["the", "black", "honda"], "raw": "The black honda", "sent_id": 81287, "sent": "the black honda"}], "file_name": "COCO_train2014_000000208243_1776742.jpg", "ann_id": 1776742, "sent_ids": [81286, 81287], "ref_id": 36233}, {"segmentation": [[639.02, 19.45, 627.77, 58.87, 635.81, 63.7, 593.98, 183.55, 591.57, 188.37, 587.54, 193.2, 566.64, 265.58, 626.95, 330.74, 640.0, 338.78]], "area": 11044.7844, "iscrowd": 0, "image_id": 70755, "bbox": [566.64, 19.45, 73.36, 319.33], "category_id": 44, "id": 1872324, "split": "val", "sentences": [{"tokens": ["the", "clear", "container", "on", "the", "right"], "raw": "The clear container on the right.", "sent_id": 81310, "sent": "the clear container on the right"}, {"tokens": ["an", "empty", "bottle", "off", "the", "screen"], "raw": "An empty bottle off the screen.", "sent_id": 81311, "sent": "an empty bottle off the screen"}], "file_name": "COCO_train2014_000000070755_1872324.jpg", "ann_id": 1872324, "sent_ids": [81310, 81311], "ref_id": 36242}, {"segmentation": [[400.61, 145.21, 426.52, 197.04, 430.97, 245.17, 414.68, 286.64, 392.46, 328.18, 279.91, 329.66, 285.09, 286.71, 251.77, 262.27, 246.58, 243.76, 245.84, 243.76, 248.06, 238.58, 259.17, 240.06, 260.65, 229.69, 278.43, 223.77, 297.68, 226.73, 308.04, 230.43, 328.78, 194.15, 313.23, 181.56, 325.08, 164.53, 297.68, 141.57, 302.12, 131.21, 288.05, 119.36, 286.57, 104.55, 288.05, 85.3, 302.12, 69.75, 317.67, 57.9, 331.0, 43.09, 337.66, 41.61, 360.62, 46.05, 385.06, 75.67, 382.09, 87.52, 386.54, 108.99]], "area": 31858.568600000002, "iscrowd": 0, "image_id": 266369, "bbox": [245.84, 41.61, 185.13, 288.05], "category_id": 1, "id": 458941, "split": "val", "sentences": [{"tokens": ["female", "standing", "outside", "on", "her", "phone"], "raw": "Female standing outside on her phone.", "sent_id": 81358, "sent": "female standing outside on her phone"}, {"tokens": ["woman", "texting"], "raw": "Woman texting", "sent_id": 81359, "sent": "woman texting"}], "file_name": "COCO_train2014_000000266369_458941.jpg", "ann_id": 458941, "sent_ids": [81358, 81359], "ref_id": 36261}, {"segmentation": [[0.0, 249.64, 9.74, 249.64, 21.73, 249.64, 32.23, 249.64, 36.72, 242.14, 38.22, 236.9, 29.23, 231.65, 22.48, 215.91, 20.23, 205.42, 21.73, 195.68, 26.98, 185.93, 33.72, 182.19, 38.97, 179.19, 41.97, 178.44, 45.72, 173.19, 52.46, 174.69, 68.95, 179.19, 71.95, 171.69, 77.94, 164.2, 62.2, 159.7, 50.21, 151.46, 42.72, 140.97, 42.72, 133.47, 46.47, 126.73, 52.46, 132.72, 52.46, 136.47, 58.46, 143.97, 68.2, 150.71, 83.19, 158.95, 81.69, 169.45, 83.94, 174.69, 89.93, 177.69, 92.93, 182.94, 95.93, 188.93, 104.17, 194.18, 116.91, 188.18, 128.9, 182.19, 134.15, 179.94, 140.89, 176.19, 146.89, 174.69, 152.89, 173.94, 157.38, 173.94, 158.13, 167.2, 149.89, 167.95, 134.15, 168.7, 126.66, 171.69, 111.67, 170.94, 97.43, 170.94, 94.43, 155.96, 95.18, 143.22, 97.43, 136.47, 104.92, 132.72, 115.41, 137.22, 119.91, 143.97, 120.66, 151.46, 121.41, 156.71, 128.9, 161.2, 129.65, 164.95, 134.9, 162.7, 140.89, 161.2, 146.14, 161.2, 150.64, 160.45, 156.63, 157.45, 149.89, 153.71, 142.39, 149.21, 132.65, 147.71, 126.66, 146.21, 120.66, 142.47, 130.4, 141.72, 146.89, 143.97, 156.63, 143.97, 161.88, 141.72, 171.62, 141.72, 176.87, 134.97, 181.36, 129.73, 188.86, 124.48, 193.36, 121.48, 191.86, 115.49, 195.6, 104.99, 200.1, 99.75, 214.34, 102.0, 221.83, 111.74, 223.33, 119.98, 220.34, 127.48, 213.59, 130.48, 207.6, 131.97, 200.1, 129.73, 189.61, 134.22, 179.87, 142.47, 177.62, 145.46, 177.62, 156.71, 175.37, 160.45, 170.87, 162.7, 167.13, 168.7, 165.63, 174.69, 165.63, 176.94, 167.13, 179.94, 178.37, 182.94, 188.86, 187.43, 200.1, 194.18, 204.6, 199.42, 204.6, 201.67, 197.1, 198.67, 186.61, 194.93, 178.37, 195.68, 171.62, 190.43, 165.63, 189.68, 157.38, 192.68, 149.89, 203.17, 146.89, 206.92, 137.15, 207.67, 145.39, 198.67, 154.38, 187.43, 143.89, 184.43, 131.9, 190.43, 123.66, 191.93, 119.16, 197.18, 120.66, 201.67, 134.9, 206.92, 126.66, 205.42, 127.4, 212.16, 138.65, 214.41, 151.39, 215.16, 164.13, 217.41, 177.62, 224.16, 179.12, 232.4, 177.62, 243.64, 176.12, 251.88, 157.38, 249.64, 141.64, 246.64, 137.15, 251.88, 139.4, 259.38, 139.4, 265.37, 139.4, 276.62, 139.4, 282.61, 136.4, 286.36, 130.4, 289.36, 131.9, 294.6, 136.4, 302.85, 138.65, 309.59, 135.65, 319.33, 137.15, 324.58, 128.15, 326.83, 101.17, 324.58, 78.69, 325.33, 56.96, 324.58, 32.23, 325.33, 15.74, 324.58, 4.5, 324.58, 0.0, 324.58, 1.5, 302.1, 2.25, 279.61, 1.5, 251.14]], "area": 23166.458949999993, "iscrowd": 0, "image_id": 254176, "bbox": [0.0, 99.75, 223.33, 227.08], "category_id": 4, "id": 150895, "split": "val", "sentences": [{"tokens": ["a", "motorbike", "occupied", "by", "two", "men", "dressed", "like", "teddy", "bear"], "raw": "A motorbike occupied by two men dressed like teddy bear.", "sent_id": 81360, "sent": "a motorbike occupied by two men dressed like teddy bear"}, {"tokens": ["motorcyle", "under", "humans", "with", "costumes"], "raw": "Motorcyle under humans with costumes.", "sent_id": 81361, "sent": "motorcyle under humans with costumes"}], "file_name": "COCO_train2014_000000254176_150895.jpg", "ann_id": 150895, "sent_ids": [81360, 81361], "ref_id": 36262}, {"segmentation": [[4.31, 560.9, 25.89, 530.7, 60.4, 488.99, 77.66, 468.85, 94.92, 455.91, 103.55, 445.84, 129.44, 438.65, 143.82, 450.16, 163.96, 422.83, 214.29, 455.91, 248.81, 438.65, 258.88, 460.22, 268.94, 493.3, 277.57, 519.19, 279.01, 552.27, 271.82, 562.34, 287.64, 578.16, 329.35, 566.65, 360.99, 565.21, 353.8, 559.46, 323.6, 550.83, 312.09, 536.45, 300.58, 516.31, 290.52, 427.15, 290.52, 418.52, 208.54, 356.67, 215.73, 307.78, 232.99, 284.76, 290.52, 306.34, 309.21, 304.9, 319.28, 280.45, 336.54, 211.42, 325.03, 178.34, 309.21, 191.28, 314.97, 225.8, 297.71, 264.63, 281.89, 273.26, 243.06, 244.49, 228.67, 232.99, 232.99, 201.35, 244.49, 194.16, 243.06, 156.76, 231.55, 142.38, 212.85, 138.07, 191.28, 149.57, 186.97, 165.39, 189.84, 185.53, 197.03, 202.79, 185.53, 205.66, 156.76, 204.22, 116.49, 247.37, 103.55, 264.63, 107.87, 280.45, 128.0, 296.27, 102.11, 358.11, 86.29, 384.0, 64.72, 432.9, 47.46, 458.79, 4.31, 529.26]], "area": 47682.12394999994, "iscrowd": 0, "image_id": 97563, "bbox": [4.31, 138.07, 356.68, 440.09], "category_id": 1, "id": 431724, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "gray", "shirt", "about", "to", "throw", "a", "frisbee"], "raw": "A man wearing a gray shirt about to throw a Frisbee.", "sent_id": 81380, "sent": "a man wearing a gray shirt about to throw a frisbee"}, {"tokens": ["a", "man", "in", "a", "blue", "shirt", "with", "the", "numbers", "01", "printed", "on", "the", "back", ",", "preparing", "to", "pass", "a", "frisbee"], "raw": "A man in a blue shirt with the numbers 01 printed on the back, preparing to pass a frisbee", "sent_id": 81381, "sent": "a man in a blue shirt with the numbers 01 printed on the back , preparing to pass a frisbee"}], "file_name": "COCO_train2014_000000097563_431724.jpg", "ann_id": 431724, "sent_ids": [81380, 81381], "ref_id": 36271}, {"segmentation": [[38.74, 121.61, 82.87, 82.87, 196.95, 74.26, 399.28, 76.41, 421.88, 92.56, 485.38, 90.4, 497.22, 122.69, 496.14, 221.7, 383.14, 238.92, 25.83, 241.08]], "area": 71927.3259, "iscrowd": 0, "image_id": 383512, "bbox": [25.83, 74.26, 471.39, 166.82], "category_id": 6, "id": 163873, "split": "val", "sentences": [{"tokens": ["bus", "driving", "down", "street"], "raw": "Bus driving down street.", "sent_id": 81480, "sent": "bus driving down street"}, {"tokens": ["a", "bus", "ridding", "in", "a", "road"], "raw": "A bus ridding in a road", "sent_id": 81481, "sent": "a bus ridding in a road"}], "file_name": "COCO_train2014_000000383512_163873.jpg", "ann_id": 163873, "sent_ids": [81480, 81481], "ref_id": 36307}, {"segmentation": [[21.23, 190.88, 43.72, 219.81, 52.56, 235.88, 96.75, 255.16, 128.89, 263.19, 140.94, 265.6, 110.41, 272.84, 81.49, 263.19, 59.79, 253.55, 54.17, 245.52, 43.72, 233.47, 27.66, 210.97, 14.8, 193.29, 0.34, 181.24, 0.34, 172.41]], "area": 1565.8198000000004, "iscrowd": 0, "image_id": 33581, "bbox": [0.34, 172.41, 140.6, 100.43], "category_id": 50, "id": 708422, "split": "val", "sentences": [{"tokens": ["the", "spoon", "to", "the", "left", "of", "the", "cup"], "raw": "The spoon to the left of the cup", "sent_id": 81503, "sent": "the spoon to the left of the cup"}], "file_name": "COCO_train2014_000000033581_708422.jpg", "ann_id": 708422, "sent_ids": [81503], "ref_id": 36315}, {"segmentation": [[0.0, 266.7, 7.64, 222.75, 7.64, 208.43, 12.42, 194.1, 24.84, 164.48, 60.18, 137.74, 75.47, 127.23, 76.42, 106.21, 76.42, 74.69, 92.66, 50.81, 100.3, 46.03, 115.59, 38.39, 149.98, 46.99, 172.9, 80.42, 171.95, 99.53, 177.68, 112.9, 178.63, 117.68, 173.86, 128.18, 172.9, 132.96, 154.75, 158.75, 140.42, 160.66, 145.2, 176.9, 146.15, 179.77, 158.57, 201.74, 164.3, 228.49, 168.13, 238.99, 198.69, 248.55, 214.93, 250.46, 228.31, 231.35, 249.32, 217.98, 267.47, 212.25, 277.02, 233.26, 247.41, 261.92, 236.9, 295.35, 219.71, 311.59, 199.65, 320.19, 213.02, 341.21, 334.34, 352.67, 362.04, 381.33, 369.68, 397.57, 359.18, 421.45, 0.96, 421.45]], "area": 74328.48835, "iscrowd": 0, "image_id": 230436, "bbox": [0.0, 38.39, 369.68, 383.06], "category_id": 1, "id": 185259, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "black", "jacket", "working", "on", "a", "laptop"], "raw": "A man in black jacket working on a laptop", "sent_id": 81508, "sent": "a man in black jacket working on a laptop"}, {"tokens": ["man", "in", "suit", "looking", "at", "laptop"], "raw": "man in suit looking at laptop", "sent_id": 81509, "sent": "man in suit looking at laptop"}], "file_name": "COCO_train2014_000000230436_185259.jpg", "ann_id": 185259, "sent_ids": [81508, 81509], "ref_id": 36318}, {"segmentation": [[255.14, 499.46, 258.02, 457.66, 265.23, 430.27, 263.78, 392.79, 239.28, 374.05, 253.69, 286.13, 249.37, 267.39, 223.42, 245.77, 232.07, 214.05, 283.96, 225.59, 291.17, 205.41, 288.29, 182.34, 312.79, 152.07, 337.3, 176.58, 324.32, 227.03, 338.74, 251.53, 360.36, 281.8, 366.13, 313.51, 343.06, 307.75, 341.62, 356.76, 341.62, 412.97, 332.97, 449.01, 321.44, 470.63, 341.62, 500.9, 291.17, 477.84, 294.05, 451.89, 314.23, 420.18, 299.82, 388.47, 289.73, 443.24, 276.76, 490.81, 279.64, 526.85, 266.67, 532.61, 255.14, 503.78]], "area": 26562.086649999997, "iscrowd": 0, "image_id": 385704, "bbox": [223.42, 152.07, 142.71, 380.54], "category_id": 1, "id": 502274, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "purple", "tie"], "raw": "The man with the purple tie.", "sent_id": 81593, "sent": "the man with the purple tie"}, {"tokens": ["an", "older", "man"], "raw": "an older man", "sent_id": 81594, "sent": "an older man"}], "file_name": "COCO_train2014_000000385704_502274.jpg", "ann_id": 502274, "sent_ids": [81593, 81594], "ref_id": 36354}, {"segmentation": [[204.87, 208.77, 203.71, 214.01, 201.96, 214.01, 198.47, 214.59, 193.23, 213.42, 190.9, 206.44, 187.99, 199.46, 187.41, 183.74, 186.25, 173.26, 182.76, 170.35, 179.26, 165.12, 179.26, 154.06, 178.68, 144.75, 178.1, 136.02, 176.35, 125.54, 175.19, 113.9, 175.77, 104.0, 183.92, 97.6, 199.63, 90.62, 206.04, 90.62, 217.68, 93.53, 229.9, 97.02, 237.47, 102.84, 250.27, 108.66, 262.49, 112.15, 264.82, 112.15, 270.06, 112.73, 273.55, 117.39, 277.62, 113.9, 282.86, 120.88, 291.59, 141.84, 299.16, 149.98, 304.98, 159.3, 308.47, 163.37, 315.46, 163.95, 316.04, 171.52, 311.38, 178.5, 310.8, 188.4, 311.96, 199.46, 311.96, 207.6, 311.96, 218.08, 312.55, 222.15, 312.55, 222.74, 311.38, 227.39, 302.65, 229.14, 299.16, 229.14, 292.76, 224.48, 288.68, 216.33, 286.36, 201.78, 277.04, 190.73, 275.88, 179.09, 270.64, 170.94, 260.75, 169.19, 259.0, 167.44, 253.76, 166.86, 250.27, 169.19, 248.52, 175.59, 245.03, 183.16, 243.29, 194.22, 242.12, 202.95, 238.63, 207.02, 237.47, 214.59, 239.79, 224.48, 231.06, 223.32, 225.82, 219.83, 229.32, 211.1, 233.39, 197.13, 235.14, 188.98, 236.3, 176.76, 238.63, 171.52, 237.47, 165.7, 233.39, 164.53, 224.66, 165.7, 218.84, 163.37, 209.53, 158.71, 206.62, 161.62, 206.04, 166.86, 203.71, 172.1, 202.54, 173.85, 201.38, 180.83, 199.05, 187.82, 199.05, 190.14, 201.96, 194.22, 201.96, 200.04, 201.96, 202.37]], "area": 10452.833500000004, "iscrowd": 0, "image_id": 309338, "bbox": [175.19, 90.62, 140.85, 138.52], "category_id": 24, "id": 588193, "split": "val", "sentences": [{"tokens": ["the", "zebra", "in", "the", "middle"], "raw": "the zebra in the middle", "sent_id": 81601, "sent": "the zebra in the middle"}, {"tokens": ["zebra", "drinking", "water", "in", "the", "left", "side", "of", "the", "image"], "raw": "zebra drinking water in the left side of the image", "sent_id": 81602, "sent": "zebra drinking water in the left side of the image"}], "file_name": "COCO_train2014_000000309338_588193.jpg", "ann_id": 588193, "sent_ids": [81601, 81602], "ref_id": 36358}, {"segmentation": [[74.09, 284.67, 67.65, 186.95, 91.28, 153.66, 162.15, 152.59, 210.47, 160.1, 224.43, 204.13, 234.09, 234.2, 220.13, 261.04, 214.77, 299.7, 123.49, 309.37, 100.94, 304.0]], "area": 22004.4455, "iscrowd": 0, "image_id": 149202, "bbox": [67.65, 152.59, 166.44, 156.78], "category_id": 61, "id": 1088748, "split": "val", "sentences": [{"tokens": ["mini", "cake", "with", "a", "black", "bow", "on", "top", "and", "black", "and", "blue", "stripes", "around", "it"], "raw": "mini cake with a black bow on top and black and blue stripes around it.", "sent_id": 81632, "sent": "mini cake with a black bow on top and black and blue stripes around it"}, {"tokens": ["mini", "cale", "with", "brown", "bow", "an", "blue", "stripes"], "raw": "mini cale with brown bow an blue stripes", "sent_id": 81633, "sent": "mini cale with brown bow an blue stripes"}], "file_name": "COCO_train2014_000000149202_1088748.jpg", "ann_id": 1088748, "sent_ids": [81632, 81633], "ref_id": 36372}, {"segmentation": [[289.61, 188.58, 149.38, 356.66, 130.81, 375.24, 105.74, 408.67, 89.95, 411.45, 25.87, 378.02, 20.3, 213.65, 136.38, 108.71, 231.1, 140.29, 278.46, 158.86, 286.82, 168.15]], "area": 48817.94655, "iscrowd": 0, "image_id": 445540, "bbox": [20.3, 108.71, 269.31, 302.74], "category_id": 77, "id": 2137263, "split": "val", "sentences": [{"tokens": ["a", "white", "rectangular", "mp3", "player"], "raw": "a white rectangular mp3 player", "sent_id": 81773, "sent": "a white rectangular mp3 player"}, {"tokens": ["white", "mp3", "player", "sitting", "on", "left", "side", "of", "phones"], "raw": "White MP3 player sitting on left side of phones.", "sent_id": 81774, "sent": "white mp3 player sitting on left side of phones"}], "file_name": "COCO_train2014_000000445540_2137263.jpg", "ann_id": 2137263, "sent_ids": [81773, 81774], "ref_id": 36427}, {"segmentation": [[435.46, 139.73, 425.11, 103.51, 433.98, 87.98, 479.82, 85.76, 496.83, 85.76, 510.87, 107.94, 499.04, 127.16, 492.39, 149.34, 513.83, 177.44, 517.53, 207.75, 508.66, 233.63, 491.65, 228.45, 475.39, 212.19, 453.95, 212.19, 432.51, 208.49, 411.07, 207.75, 387.41, 209.97, 389.62, 194.44, 381.49, 169.31, 408.11, 158.22, 439.16, 177.44, 449.51, 161.17]], "area": 11458.550500000003, "iscrowd": 0, "image_id": 102144, "bbox": [381.49, 85.76, 136.04, 147.87], "category_id": 88, "id": 1163291, "split": "val", "sentences": [{"tokens": ["a", "darker", "brown", "teddy", "bear", "in", "a", "row", "of", "lighter", "teddy", "bears"], "raw": "A darker brown teddy bear in a row of lighter teddy bears.", "sent_id": 81884, "sent": "a darker brown teddy bear in a row of lighter teddy bears"}, {"tokens": ["a", "stuffed", "brown", "teddy", "bear", "with", "a", "red", "bow"], "raw": "A stuffed brown teddy bear with a red bow", "sent_id": 81885, "sent": "a stuffed brown teddy bear with a red bow"}], "file_name": "COCO_train2014_000000102144_1163291.jpg", "ann_id": 1163291, "sent_ids": [81884, 81885], "ref_id": 36466}, {"segmentation": [[524.51, 234.81, 529.5, 249.78, 538.37, 233.14, 550.57, 240.9, 551.12, 249.22, 560.0, 239.24, 575.52, 232.59, 576.63, 250.89, 591.05, 264.19, 608.24, 290.25, 637.62, 288.04, 639.29, 250.89, 638.73, 244.23, 632.08, 230.37, 627.09, 218.17, 638.18, 189.89, 640.0, 129.45, 603.8, 125.57, 580.51, 168.82, 527.84, 231.48]], "area": 10255.148400000002, "iscrowd": 0, "image_id": 41233, "bbox": [524.51, 125.57, 115.49, 164.68], "category_id": 8, "id": 401649, "split": "val", "sentences": [{"tokens": ["an", "orange", "dump", "truck", "with", "its", "back", "raised", "up"], "raw": "An orange dump truck with its back raised up.", "sent_id": 81894, "sent": "an orange dump truck with its back raised up"}, {"tokens": ["orange", "dump", "truck"], "raw": "Orange dump truck.", "sent_id": 81895, "sent": "orange dump truck"}], "file_name": "COCO_train2014_000000041233_401649.jpg", "ann_id": 401649, "sent_ids": [81894, 81895], "ref_id": 36469}, {"segmentation": [[470.27, 222.7, 486.49, 215.14, 523.24, 223.78, 538.38, 244.32, 536.22, 270.27, 520.0, 277.84, 502.7, 283.24, 481.08, 282.16, 469.19, 267.03, 464.86, 252.97, 460.54, 236.76, 472.43, 224.86], [538.38, 161.08, 582.7, 154.59, 597.84, 164.32, 602.16, 195.68, 588.11, 212.97, 569.73, 222.7, 554.59, 217.3, 539.46, 202.16, 525.41, 179.46, 536.22, 163.24], [552.43, 234.59, 565.41, 268.11, 592.43, 280.0, 615.14, 274.59, 629.19, 260.54, 625.95, 241.08, 616.22, 232.43, 600.0, 221.62, 588.11, 216.22, 571.89, 223.78, 558.92, 218.38], [511.35, 283.24, 481.08, 303.78, 472.43, 322.16, 492.97, 341.62, 514.59, 351.35, 537.3, 352.43, 551.35, 343.78, 560.0, 330.81, 554.59, 311.35, 534.05, 294.05, 520.0, 286.49], [578.38, 285.41, 566.49, 301.62, 564.32, 320.0, 566.49, 339.46, 581.62, 350.27, 612.97, 351.35, 632.43, 342.7, 636.76, 329.73, 632.43, 308.11, 619.46, 299.46, 601.08, 290.81, 585.95, 284.32]], "area": 18823.295850000002, "iscrowd": 0, "image_id": 74201, "bbox": [460.54, 154.59, 176.22, 197.84], "category_id": 61, "id": 1576777, "split": "val", "sentences": [{"tokens": ["blue", "cupcakes", "sitting", "in", "a", "clear", "container"], "raw": "Blue cupcakes sitting in a clear container", "sent_id": 81980, "sent": "blue cupcakes sitting in a clear container"}], "file_name": "COCO_train2014_000000074201_1576777.jpg", "ann_id": 1576777, "sent_ids": [81980], "ref_id": 36505}, {"segmentation": [[391.35, 474.05, 396.76, 430.81, 393.51, 407.03, 376.22, 388.65, 352.43, 365.95, 349.19, 345.41, 364.32, 345.41, 392.43, 363.78, 406.49, 382.16, 406.49, 372.43, 401.08, 354.05, 410.81, 337.84, 428.11, 325.95, 458.38, 333.51, 471.35, 346.49, 470.27, 475.14, 390.27, 474.05]], "area": 11849.069699999998, "iscrowd": 0, "image_id": 136651, "bbox": [349.19, 325.95, 122.16, 149.19], "category_id": 1, "id": 1249864, "split": "val", "sentences": [{"tokens": ["the", "person", "wearing", "a", "yellow", "headband"], "raw": "the person wearing a yellow headband", "sent_id": 82088, "sent": "the person wearing a yellow headband"}, {"tokens": ["a", "woman", ",", "kneeling", ",", "with", "a", "yellow", "headband", "looking", "at", "a", "display", "of", "a", "cow"], "raw": "A woman, kneeling, with a yellow headband looking at a display of a cow.", "sent_id": 82089, "sent": "a woman , kneeling , with a yellow headband looking at a display of a cow"}], "file_name": "COCO_train2014_000000136651_1249864.jpg", "ann_id": 1249864, "sent_ids": [82088, 82089], "ref_id": 36542}, {"segmentation": [[11.25, 590.9, 22.56, 574.38, 5.6, 576.56, 8.21, 564.82, 16.03, 556.99, 11.69, 546.99, 14.73, 532.65, 34.29, 522.21, 57.77, 504.82, 85.16, 506.56, 96.9, 513.95, 113.42, 513.95, 119.07, 523.52, 125.59, 528.73, 135.59, 521.78, 152.55, 530.91, 153.42, 544.38, 161.68, 565.25, 170.38, 570.47, 179.51, 586.12, 192.98, 596.56, 184.72, 614.38, 151.25, 614.38, 125.16, 625.68, 87.34, 636.12, 53.42, 633.94, 32.99, 623.51, 30.38, 606.55, 12.99, 600.03]], "area": 16686.24299999999, "iscrowd": 0, "image_id": 230570, "bbox": [5.6, 504.82, 187.38, 131.3], "category_id": 54, "id": 2191812, "split": "val", "sentences": [{"tokens": ["smaller", "portion", "of", "a", "sandwich", "on", "tin", "foil"], "raw": "Smaller portion of a sandwich on tin foil.", "sent_id": 82090, "sent": "smaller portion of a sandwich on tin foil"}], "file_name": "COCO_train2014_000000230570_2191812.jpg", "ann_id": 2191812, "sent_ids": [82090], "ref_id": 36543}, {"segmentation": [[273.83, 344.8, 298.03, 311.6, 300.24, 301.67, 327.28, 293.94, 331.15, 295.6, 342.19, 305.53, 343.29, 341.41, 339.98, 350.24, 344.4, 366.8, 338.32, 390.54, 327.28, 405.44, 327.84, 414.28, 333.36, 417.59, 344.4, 415.38, 354.89, 399.92, 361.51, 404.34, 380.28, 403.79, 373.65, 393.3, 368.13, 381.16, 370.34, 363.15, 396.29, 303.53, 409.53, 301.32, 438.24, 341.07, 443.21, 375.84, 438.79, 407.86, 437.69, 415.04, 434.93, 422.52, 447.62, 417.0, 450.38, 404.31, 453.69, 397.68, 452.04, 387.75, 450.93, 378.36, 457.01, 351.87, 463.63, 366.77, 461.42, 400.44, 461.42, 413.14, 458.66, 419.76, 471.36, 418.66, 473.57, 394.92, 469.7, 344.14, 466.39, 328.13, 459.21, 309.02, 461.97, 268.72, 475.77, 266.51, 476.33, 234.5, 463.63, 241.12, 463.63, 247.74, 438.24, 221.8, 355.99, 232.29, 294.72, 245.54, 275.95, 269.82, 264.36, 289.14, 262.15, 300.18, 266.01, 317.3, 259.94, 334.96, 271.53, 344.35]], "area": 21496.78654999999, "iscrowd": 0, "image_id": 565664, "bbox": [259.94, 221.8, 216.39, 200.72], "category_id": 24, "id": 591483, "split": "val", "sentences": [{"tokens": ["a", "baby", "zebra", "nestled", "under", "an", "adult", "zebra"], "raw": "A baby zebra nestled under an adult zebra.", "sent_id": 82135, "sent": "a baby zebra nestled under an adult zebra"}, {"tokens": ["a", "zebra", "calf", "leaning", "into", "mother"], "raw": "A zebra calf leaning into mother", "sent_id": 82136, "sent": "a zebra calf leaning into mother"}], "file_name": "COCO_train2014_000000565664_591483.jpg", "ann_id": 591483, "sent_ids": [82135, 82136], "ref_id": 36563}, {"segmentation": [[64.76, 439.27, 74.51, 438.19, 75.95, 430.97, 81.0, 428.44, 82.08, 427.72, 86.78, 428.8, 88.22, 430.61, 91.11, 432.77, 92.91, 433.85, 93.63, 435.66, 93.63, 436.74, 93.63, 439.27, 92.91, 439.27, 111.32, 439.99, 111.68, 436.02, 111.68, 435.3, 113.84, 434.94, 115.29, 434.58, 117.45, 433.85, 122.14, 432.41, 123.22, 425.19, 123.22, 424.47, 126.47, 419.78, 130.44, 415.81, 132.97, 410.4, 132.97, 406.43, 133.33, 403.9, 133.69, 398.49, 133.33, 398.13, 133.33, 396.68, 134.41, 393.44, 135.13, 388.02, 133.33, 373.95, 126.11, 358.07, 116.01, 349.77, 107.71, 346.16, 100.49, 349.41, 96.16, 348.69, 93.99, 346.16, 88.22, 345.8, 83.17, 347.96, 80.28, 351.93, 80.28, 357.35, 78.11, 359.87, 74.87, 364.2, 73.06, 368.9, 70.17, 369.98, 60.79, 380.44, 58.27, 387.66, 57.54, 391.99, 57.9, 394.52, 56.46, 399.93, 56.46, 405.71, 56.1, 408.95, 54.3, 412.56, 53.57, 417.25, 53.21, 419.78, 53.93, 423.75, 54.66, 427.0, 54.66, 430.25, 56.1, 431.33, 57.54, 433.85, 59.35, 435.3, 59.71, 435.66, 60.43, 437.82, 60.79, 438.91]], "area": 5841.519399999997, "iscrowd": 0, "image_id": 184224, "bbox": [53.21, 345.8, 81.92, 94.19], "category_id": 18, "id": 4179, "split": "val", "sentences": [{"tokens": ["a", "dog", "with", "long", "hair"], "raw": "a dog with long hair", "sent_id": 82196, "sent": "a dog with long hair"}, {"tokens": ["a", "small", "fluffy", "dog", "with", "long", "hair", "that", "is", "lightly", "colored", "but", "with", "some", "areas", "of", "grey", "hair"], "raw": "A small fluffy dog with long hair that is lightly colored but with some areas of grey hair.", "sent_id": 82197, "sent": "a small fluffy dog with long hair that is lightly colored but with some areas of grey hair"}], "file_name": "COCO_train2014_000000184224_4179.jpg", "ann_id": 4179, "sent_ids": [82196, 82197], "ref_id": 36588}, {"segmentation": [[415.45, 113.3, 566.52, 101.5, 639.69, 100.32, 636.15, 204.18, 607.83, 185.3, 607.83, 185.3, 593.66, 185.3, 553.54, 203.0, 501.6, 193.56, 493.34, 178.22, 437.87, 175.86, 413.09, 121.57, 413.09, 121.57]], "area": 17923.032600000002, "iscrowd": 0, "image_id": 109095, "bbox": [413.09, 100.32, 226.6, 103.86], "category_id": 7, "id": 1795725, "split": "val", "sentences": [{"tokens": ["a", "black", "train", "behind", "a", "man"], "raw": "A black train behind a man", "sent_id": 82241, "sent": "a black train behind a man"}, {"tokens": ["a", "cargo", "car", "on", "a", "train", "is", "sitting", "on", "the", "snowy", "tracks"], "raw": "A cargo car on a train is sitting on the snowy tracks.", "sent_id": 82242, "sent": "a cargo car on a train is sitting on the snowy tracks"}], "file_name": "COCO_train2014_000000109095_1795725.jpg", "ann_id": 1795725, "sent_ids": [82241, 82242], "ref_id": 36605}, {"segmentation": [[311.73, 474.61, 296.63, 419.6, 306.34, 408.81, 297.71, 380.76, 279.37, 341.93, 273.98, 325.75, 255.64, 290.16, 247.01, 269.66, 241.62, 247.01, 254.56, 225.44, 257.8, 217.89, 254.56, 197.39, 269.66, 172.58, 283.69, 155.33, 300.94, 155.33, 316.04, 157.48, 314.97, 146.7, 299.87, 139.15, 279.37, 139.15, 248.09, 167.19, 235.15, 185.53, 203.87, 203.87, 171.51, 218.97, 165.03, 204.94, 143.46, 186.61, 133.75, 182.29, 117.57, 185.53, 98.16, 194.16, 93.84, 212.49, 98.16, 228.67, 116.49, 245.93, 112.18, 252.4, 124.04, 258.88, 136.99, 258.88, 139.15, 265.35, 131.6, 283.69, 132.67, 303.1, 141.3, 323.6, 143.46, 358.11, 145.62, 390.47, 140.22, 418.52, 157.48, 424.99, 161.8, 417.44, 162.88, 396.94, 162.88, 369.98, 165.03, 343.01, 170.43, 347.33, 176.9, 398.02, 175.82, 444.4, 179.06, 454.11, 180.13, 464.9, 185.53, 472.45, 210.34, 462.74, 220.04, 456.27, 228.67, 446.56, 237.3, 406.65, 251.33, 437.93, 265.35, 459.51, 272.9, 474.61, 309.57, 473.53]], "area": 36988.0711, "iscrowd": 0, "image_id": 121453, "bbox": [93.84, 139.15, 222.2, 335.46], "category_id": 1, "id": 216079, "split": "val", "sentences": [{"tokens": ["a", "boy", "who", "is", "tilted", "to", "the", "left", "and", "has", "his", "arms", "out", "playing", "a", "video", "game"], "raw": "A boy who is tilted to the left and has his arms out playing a video game.", "sent_id": 82254, "sent": "a boy who is tilted to the left and has his arms out playing a video game"}, {"tokens": ["boy", "leaning", "sideways", "while", "playing", "a", "game"], "raw": "Boy leaning sideways while playing a game", "sent_id": 82255, "sent": "boy leaning sideways while playing a game"}], "file_name": "COCO_train2014_000000121453_216079.jpg", "ann_id": 216079, "sent_ids": [82254, 82255], "ref_id": 36609}, {"segmentation": [[15.13, 411.21, 222.8, 354.82, 228.3, 324.57, 191.16, 286.06, 167.78, 210.42, 182.91, 103.15, 221.42, 39.88, 283.31, 28.88, 364.45, 53.64, 397.46, 107.27, 407.08, 196.67, 394.71, 273.68, 376.83, 336.94, 390.58, 376.83, 444.22, 401.58, 534.98, 437.34, 603.75, 533.61, 595.5, 598.25, 574.87, 603.75, 27.51, 592.75]], "area": 182882.42964999998, "iscrowd": 0, "image_id": 104344, "bbox": [15.13, 28.88, 588.62, 574.87], "category_id": 1, "id": 533397, "split": "val", "sentences": [{"tokens": ["a", "smiling", "man", "with", "brown", "hair", "wearing", "a", "checked", "shirt", "and", "green", "tie"], "raw": "A smiling man with brown hair wearing a checked shirt and green tie.", "sent_id": 82270, "sent": "a smiling man with brown hair wearing a checked shirt and green tie"}, {"tokens": ["an", "man", "wearing", "a", "white", "plaid", "shirt", "and", "a", "green", "tie", ",", "smiling"], "raw": "An man wearing a white plaid shirt and a green tie, smiling.", "sent_id": 82271, "sent": "an man wearing a white plaid shirt and a green tie , smiling"}], "file_name": "COCO_train2014_000000104344_533397.jpg", "ann_id": 533397, "sent_ids": [82270, 82271], "ref_id": 36615}, {"segmentation": [[187.77, 140.21, 189.34, 201.87, 191.43, 282.85, 191.43, 322.04, 193.52, 352.87, 207.63, 348.17, 210.24, 344.51, 233.75, 339.81, 261.45, 340.85, 273.46, 339.28, 276.08, 324.65, 276.08, 316.29, 276.08, 311.59, 265.63, 312.64, 259.36, 313.16, 252.56, 302.19, 252.56, 296.44, 253.61, 293.83, 266.15, 291.21, 304.29, 293.3, 364.38, 290.69, 410.88, 293.83, 410.88, 305.84, 406.18, 320.47, 427.07, 320.47, 464.17, 320.47, 499.18, 317.86, 523.21, 314.2, 589.57, 308.98, 589.57, 299.05, 589.57, 215.45, 588.0, 179.4, 578.07, 173.13, 490.82, 163.2, 485.59, 160.59, 478.28, 155.37, 457.38, 154.32, 454.24, 155.37, 446.93, 161.11, 410.88, 157.98, 337.21, 152.75, 257.79, 147.01, 238.98, 147.01, 209.2, 144.92], [283.39, 312.64, 281.82, 339.28, 311.6, 333.01, 327.8, 331.97, 349.22, 330.92, 369.08, 327.79, 383.71, 326.22, 384.23, 308.46, 346.61, 308.46], [389.98, 311.07, 409.31, 309.5, 405.65, 325.18, 388.41, 325.18], [166.88, 139.69, 166.88, 234.26, 166.88, 319.43, 168.44, 350.26, 166.88, 353.91, 157.47, 348.69, 148.59, 347.12, 121.42, 347.64, 93.73, 347.64, 76.48, 343.46, 68.12, 335.63, 63.94, 312.11, 67.08, 272.4, 73.35, 188.28, 81.71, 151.19, 86.41, 145.44, 123.51, 140.21, 145.45, 140.21]], "area": 84671.66060000005, "iscrowd": 0, "image_id": 480064, "bbox": [63.94, 139.69, 525.63, 214.22], "category_id": 6, "id": 165366, "split": "val", "sentences": [{"tokens": ["an", "aquamarine", "bus"], "raw": "An aquamarine bus.", "sent_id": 82272, "sent": "an aquamarine bus"}, {"tokens": ["an", "aqua", "colored", "bus", "with", "woodvale", "circular", "displayed", "on", "the", "front"], "raw": "An aqua colored bus with Woodvale circular displayed on the front", "sent_id": 82273, "sent": "an aqua colored bus with woodvale circular displayed on the front"}], "file_name": "COCO_train2014_000000480064_165366.jpg", "ann_id": 165366, "sent_ids": [82272, 82273], "ref_id": 36616}, {"segmentation": [[360.27, 457.17, 303.1, 381.66, 313.89, 319.1, 295.55, 312.63, 281.53, 313.71, 281.53, 287.82, 327.91, 278.11, 319.28, 252.22, 318.2, 225.26, 326.83, 184.27, 334.38, 172.4, 323.6, 149.75, 314.97, 136.81, 307.42, 115.24, 316.04, 95.82, 328.99, 79.64, 345.17, 71.01, 354.88, 65.62, 373.21, 74.25, 385.08, 87.19, 396.94, 128.18, 409.89, 148.67, 433.62, 176.72, 441.17, 209.08, 439.01, 236.04, 446.56, 272.72, 436.85, 286.74, 443.33, 322.34, 455.19, 474.43, 457.35, 480.0, 364.58, 479.82, 364.58, 465.8]], "area": 46116.81260000001, "iscrowd": 0, "image_id": 136331, "bbox": [281.53, 65.62, 175.82, 414.38], "category_id": 1, "id": 1234464, "split": "val", "sentences": [{"tokens": ["the", "woman", "holding", "a", "pan", "in", "her", "left", "hand"], "raw": "The woman holding a pan in her left hand.", "sent_id": 82296, "sent": "the woman holding a pan in her left hand"}, {"tokens": ["a", "woman", "in", "an", "apron", "and", "uniform", "holding", "two", "pots"], "raw": "A woman in an apron and uniform holding two pots.", "sent_id": 82297, "sent": "a woman in an apron and uniform holding two pots"}], "file_name": "COCO_train2014_000000136331_1234464.jpg", "ann_id": 1234464, "sent_ids": [82296, 82297], "ref_id": 36622}, {"segmentation": [[177.05, 318.1, 190.67, 318.1, 208.18, 318.1, 214.99, 317.13, 218.88, 315.18, 241.25, 299.62, 238.33, 289.89, 227.63, 278.22, 204.29, 286.97, 192.61, 293.78, 180.94, 293.78, 175.1, 278.22, 159.54, 271.41, 148.84, 259.73, 125.49, 251.95, 113.82, 247.09, 129.38, 239.31, 124.52, 217.9, 110.9, 189.69, 90.47, 177.05, 79.77, 173.16, 77.82, 171.21, 82.69, 150.78, 85.61, 130.35, 86.58, 116.73, 74.9, 96.31, 51.56, 85.61, 35.99, 85.61, 21.4, 93.39, 15.56, 101.17, 15.56, 104.09, 12.65, 118.68, 16.54, 134.24, 17.51, 149.81, 19.46, 153.7, 28.21, 162.46, 31.13, 167.32, 11.67, 174.13, 1.95, 182.88, 3.89, 235.41, 28.21, 241.25, 35.02, 249.03, 56.42, 251.95, 73.93, 286.0, 75.88, 301.56, 109.93, 289.89, 155.65, 297.67]], "area": 19877.411750000003, "iscrowd": 0, "image_id": 226817, "bbox": [1.95, 85.61, 239.3, 232.49], "category_id": 1, "id": 226433, "split": "val", "sentences": [{"tokens": ["baby", "with", "brown", "hair", "and", "wearing", "all", "yellow", "and", "holding", "a", "white", "controller"], "raw": "Baby with brown hair and wearing all yellow and holding a white controller.", "sent_id": 82320, "sent": "baby with brown hair and wearing all yellow and holding a white controller"}, {"tokens": ["the", "youngest", "child", "in", "yellow"], "raw": "The youngest child in yellow.", "sent_id": 82321, "sent": "the youngest child in yellow"}], "file_name": "COCO_train2014_000000226817_226433.jpg", "ann_id": 226433, "sent_ids": [82320, 82321], "ref_id": 36631}, {"segmentation": [[165.13, 237.05, 152.48, 225.15, 152.48, 213.25, 150.25, 206.55, 134.63, 199.12, 119.76, 196.14, 101.16, 199.12, 95.21, 201.35, 61.74, 190.19, 42.4, 189.45, 27.52, 190.93, 14.88, 206.55, 12.64, 221.43, 2.23, 236.31, 0.74, 55.56, 11.9, 42.17, 20.08, 16.88, 31.98, 1.26, 45.37, 3.49, 59.51, 16.14, 71.41, 40.68, 70.66, 47.38, 85.54, 63.74, 101.16, 99.44, 101.16, 106.88, 114.55, 125.48, 113.8, 147.79, 113.8, 156.72, 120.5, 168.62, 135.38, 176.8, 154.71, 187.96, 168.85, 202.84, 185.96, 205.81, 190.42, 210.27, 182.24, 227.38, 182.24, 248.21, 188.19, 279.45, 180.75, 277.22, 182.98, 263.09, 180.0, 249.7, 169.59, 238.54]], "area": 19768.4871, "iscrowd": 0, "image_id": 292751, "bbox": [0.74, 1.26, 189.68, 278.19], "category_id": 88, "id": 1162476, "split": "val", "sentences": [{"tokens": ["a", "purple", "teddy", "bear"], "raw": "A purple teddy bear.", "sent_id": 82340, "sent": "a purple teddy bear"}, {"tokens": ["the", "pruple", "bear", "next", "to", "the", "baby"], "raw": "The pruple bear next to the baby.", "sent_id": 82341, "sent": "the pruple bear next to the baby"}], "file_name": "COCO_train2014_000000292751_1162476.jpg", "ann_id": 1162476, "sent_ids": [82340, 82341], "ref_id": 36638}, {"segmentation": [[176.5, 193.65, 331.48, 190.78, 327.17, 314.19, 162.15, 319.93]], "area": 19935.03435, "iscrowd": 0, "image_id": 183236, "bbox": [162.15, 190.78, 169.33, 129.15], "category_id": 72, "id": 1625651, "split": "val", "sentences": [{"tokens": ["the", "largest", "monitor", "in", "between", "two", "smaller", "ones"], "raw": "The largest monitor in between two smaller ones.", "sent_id": 82379, "sent": "the largest monitor in between two smaller ones"}, {"tokens": ["the", "large", "mac", "computer", "on", "the", "hdesk"], "raw": "The large Mac computer on the hdesk.", "sent_id": 82380, "sent": "the large mac computer on the hdesk"}], "file_name": "COCO_train2014_000000183236_1625651.jpg", "ann_id": 1625651, "sent_ids": [82379, 82380], "ref_id": 36650}, {"segmentation": [[299.6, 136.99, 300.4, 58.06, 410.74, 50.82, 517.05, 55.65, 515.44, 143.43, 306.04, 149.88]], "area": 20049.19535, "iscrowd": 0, "image_id": 492894, "bbox": [299.6, 50.82, 217.45, 99.06], "category_id": 10, "id": 403130, "split": "val", "sentences": [{"tokens": ["traffic", "signal", "machine"], "raw": "traffic signal machine", "sent_id": 82575, "sent": "traffic signal machine"}, {"tokens": ["the", "3", "lights", "in", "the", "right", "hand", "picture"], "raw": "the 3 lights in the right hand picture", "sent_id": 82576, "sent": "the 3 lights in the right hand picture"}], "file_name": "COCO_train2014_000000492894_403130.jpg", "ann_id": 403130, "sent_ids": [82575, 82576], "ref_id": 36722}, {"segmentation": [[480.0, 345.64, 480.0, 377.36, 477.68, 403.13, 459.18, 373.72, 433.41, 370.75, 409.95, 365.13, 406.32, 358.19, 404.0, 349.6, 402.68, 342.33, 400.37, 288.15, 404.66, 247.84, 399.71, 246.19, 402.02, 197.62, 422.84, 153.67, 444.97, 122.29, 455.88, 117.0, 470.41, 108.74, 480.0, 109.07, 480.0, 141.12, 480.0, 173.17, 480.0, 208.52, 480.0, 235.28, 480.0, 261.72, 480.0, 287.82, 480.0, 325.15]], "area": 18494.611500000003, "iscrowd": 0, "image_id": 399276, "bbox": [399.71, 108.74, 80.29, 294.39], "category_id": 3, "id": 2170756, "split": "val", "sentences": [{"tokens": ["awhite", "suv", "to", "the", "right", "of", "a", "parking", "meter"], "raw": "Awhite SUV to the right of a parking meter.", "sent_id": 82632, "sent": "awhite suv to the right of a parking meter"}, {"tokens": ["a", "white", "vehicle"], "raw": "A white vehicle", "sent_id": 82633, "sent": "a white vehicle"}], "file_name": "COCO_train2014_000000399276_2170756.jpg", "ann_id": 2170756, "sent_ids": [82632, 82633], "ref_id": 36744}, {"segmentation": [[491.85, 122.07, 514.37, 104.3, 640.0, 105.48, 640.0, 209.78, 501.33, 227.56]], "area": 16253.9582, "iscrowd": 0, "image_id": 383512, "bbox": [491.85, 104.3, 148.15, 123.26], "category_id": 6, "id": 1794960, "split": "val", "sentences": [{"tokens": ["the", "rear", "window", "of", "a", "bus"], "raw": "The rear window of a bus.", "sent_id": 82722, "sent": "the rear window of a bus"}, {"tokens": ["back", "half", "of", "bus"], "raw": "back half of bus", "sent_id": 82723, "sent": "back half of bus"}], "file_name": "COCO_train2014_000000383512_1794960.jpg", "ann_id": 1794960, "sent_ids": [82722, 82723], "ref_id": 36777}, {"segmentation": [[474.94, 35.0, 477.91, 35.0, 474.19, 29.06, 473.45, 23.12, 484.59, 14.95, 499.44, 8.27, 508.35, 9.01, 518.0, 14.21, 535.08, 7.52, 588.54, 14.21, 633.83, 24.6, 639.77, 31.28, 639.77, 136.72, 628.63, 138.94, 608.58, 142.65, 592.99, 142.65, 570.72, 142.65, 547.7, 133.0, 503.15, 104.05, 480.88, 70.63, 474.19, 52.82, 471.97, 44.65]], "area": 18209.826449999997, "iscrowd": 0, "image_id": 159299, "bbox": [471.97, 7.52, 167.8, 135.13], "category_id": 51, "id": 710369, "split": "val", "sentences": [{"tokens": ["french", "fries", "occupy", "half", "of", "a", "white", "bowl"], "raw": "French fries occupy half of a white bowl.", "sent_id": 82726, "sent": "french fries occupy half of a white bowl"}, {"tokens": ["a", "white", "bowl", "with", "french", "fries"], "raw": "A white bowl with french fries.", "sent_id": 82727, "sent": "a white bowl with french fries"}], "file_name": "COCO_train2014_000000159299_710369.jpg", "ann_id": 710369, "sent_ids": [82726, 82727], "ref_id": 36779}, {"segmentation": [[606.12, 412.71, 560.59, 399.43, 533.08, 357.69, 512.21, 278.02, 476.17, 255.25, 429.69, 252.4, 376.57, 272.32, 369.93, 330.19, 368.04, 340.62, 304.48, 386.15, 275.08, 373.82, 228.6, 396.58, 131.85, 300.78, 94.85, 293.19, 89.16, 258.1, 138.49, 250.51, 151.77, 273.27, 203.94, 324.49, 236.19, 345.36, 285.51, 273.27, 216.27, 273.27, 199.19, 278.02, 168.84, 275.17, 168.84, 261.89, 180.22, 240.07, 240.93, 245.77, 304.48, 235.33, 256.11, 213.51, 239.98, 173.68, 203.94, 155.65, 202.99, 152.81, 226.7, 133.84, 239.98, 94.95, 301.64, 82.62, 335.79, 104.43, 349.06, 114.87, 351.91, 141.42, 356.65, 157.55, 422.1, 165.14, 569.13, 307.42, 610.86, 363.38, 608.97, 410.81]], "area": 59992.34240000001, "iscrowd": 0, "image_id": 270248, "bbox": [89.16, 82.62, 521.7, 330.09], "category_id": 1, "id": 444513, "split": "val", "sentences": [{"tokens": ["baseball", "player", "`", "gibson", "\u00b4."], "raw": "Baseball player `Gibson\u00b4.", "sent_id": 82742, "sent": "baseball player ` gibson \u00b4."}, {"tokens": ["a", "man", "leans", "in", "to", "bunt", "a", "ball"], "raw": "a man leans in to bunt a ball", "sent_id": 82743, "sent": "a man leans in to bunt a ball"}], "file_name": "COCO_train2014_000000270248_444513.jpg", "ann_id": 444513, "sent_ids": [82742, 82743], "ref_id": 36783}, {"segmentation": [[28.84, 471.35, 20.6, 457.96, 9.27, 405.42, 28.84, 362.16, 19.57, 329.2, 29.87, 294.18, 41.2, 257.1, 47.38, 235.47, 41.2, 221.05, 52.53, 195.3, 105.06, 257.1, 121.55, 269.46, 155.54, 298.3, 178.2, 245.77, 208.07, 203.54, 234.85, 186.03, 277.08, 174.7, 284.29, 174.7, 285.32, 163.36, 296.65, 156.15, 299.74, 162.33, 309.01, 159.24, 327.55, 203.54, 327.55, 229.29, 340.94, 240.62, 337.85, 252.98, 319.31, 247.83, 318.28, 257.1, 307.98, 275.64, 296.65, 275.64, 292.53, 295.21, 291.5, 323.02, 294.59, 343.62, 296.65, 372.46, 304.89, 406.45, 306.95, 474.44, 27.81, 474.44, 26.78, 469.29]], "area": 71388.54305, "iscrowd": 0, "image_id": 33992, "bbox": [9.27, 156.15, 331.67, 318.29], "category_id": 16, "id": 38554, "split": "val", "sentences": [{"tokens": ["the", "brown", "chicken", "in", "front", "of", "more", "chickens"], "raw": "The brown chicken in front of more chickens.", "sent_id": 82744, "sent": "the brown chicken in front of more chickens"}, {"tokens": ["a", "brown", "chicken", "in", "a", "barnyard", "is", "looking", "at", "the", "camera", "suspiciously"], "raw": "A brown chicken in a barnyard is looking at the camera suspiciously.", "sent_id": 82745, "sent": "a brown chicken in a barnyard is looking at the camera suspiciously"}], "file_name": "COCO_train2014_000000033992_38554.jpg", "ann_id": 38554, "sent_ids": [82744, 82745], "ref_id": 36784}, {"segmentation": [[379.02, 400.8, 394.38, 398.88, 410.69, 382.57, 422.2, 358.58, 422.2, 348.98, 422.2, 344.19, 458.67, 302.92, 484.57, 301.01, 518.16, 308.68, 522.0, 293.33, 509.52, 275.1, 483.61, 243.43, 460.58, 236.72, 444.27, 224.24, 453.87, 223.28, 497.05, 235.76, 524.87, 253.03, 541.19, 234.8, 544.07, 215.61, 550.78, 177.22, 528.71, 174.34, 524.87, 160.91, 518.16, 149.4, 521.04, 141.72, 527.75, 126.37, 527.75, 110.06, 548.86, 92.78, 583.41, 87.03, 599.72, 94.7, 605.48, 113.89, 616.99, 158.99, 625.63, 177.22, 638.1, 202.17, 640.0, 420.95, 368.47, 420.95, 365.59, 419.99, 374.22, 397.92]], "area": 47952.04034999998, "iscrowd": 0, "image_id": 230436, "bbox": [365.59, 87.03, 274.41, 333.92], "category_id": 1, "id": 205556, "split": "val", "sentences": [{"tokens": ["woman", "wearing", "a", "pink", "scarf", "working", "on", "a", "laptop", "computer"], "raw": "Woman wearing a pink scarf working on a laptop computer.", "sent_id": 82750, "sent": "woman wearing a pink scarf working on a laptop computer"}, {"tokens": ["a", "lady", "using", "a", "laptop"], "raw": "A lady using a laptop.", "sent_id": 82751, "sent": "a lady using a laptop"}], "file_name": "COCO_train2014_000000230436_205556.jpg", "ann_id": 205556, "sent_ids": [82750, 82751], "ref_id": 36786}, {"segmentation": [[1.44, 277.57, 21.05, 291.89, 22.64, 324.22, 12.57, 338.53, 76.18, 353.37, 93.67, 382.0, 94.2, 401.08, 99.5, 422.81, 98.44, 439.25, 94.73, 452.5, 91.55, 463.63, 91.02, 471.05, 89.43, 492.25, 87.31, 510.28, 78.3, 551.62, 74.06, 565.93, 67.17, 575.47, 55.51, 588.73, 49.67, 597.21, 24.76, 596.15, 23.17, 590.32, 0.38, 610.99]], "area": 22439.951300000008, "iscrowd": 0, "image_id": 291658, "bbox": [0.38, 277.57, 99.12, 333.42], "category_id": 3, "id": 1340516, "split": "val", "sentences": [{"tokens": ["black", "vehicle", "parked", "on", "side", "of", "road"], "raw": "Black Vehicle parked on side of road.", "sent_id": 82781, "sent": "black vehicle parked on side of road"}, {"tokens": ["black", "car", "parked", "by", "curb"], "raw": "black car parked by curb", "sent_id": 82782, "sent": "black car parked by curb"}], "file_name": "COCO_train2014_000000291658_1340516.jpg", "ann_id": 1340516, "sent_ids": [82781, 82782], "ref_id": 36796}, {"segmentation": [[491.1, 360.9, 440.36, 421.21, 456.63, 238.37, 448.98, 223.05, 441.32, 194.33, 452.8, 138.81, 483.44, 134.98, 490.14, 125.41, 474.82, 119.66, 471.95, 100.52, 483.44, 84.24, 497.8, 66.05, 538.0, 72.76, 539.92, 97.64, 528.43, 116.79, 510.24, 141.68, 536.09, 162.74, 534.18, 223.05, 554.28, 232.62, 565.77, 221.14, 579.17, 241.24, 566.72, 259.43, 543.75, 248.9, 531.3, 420.26, 493.97, 415.47]], "area": 27525.510949999993, "iscrowd": 0, "image_id": 205131, "bbox": [440.36, 66.05, 138.81, 355.16], "category_id": 1, "id": 542946, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "grey", "hat"], "raw": "A woman wearing a grey hat.", "sent_id": 82793, "sent": "a woman wearing a grey hat"}, {"tokens": ["woman", "holding", "yellow", "streamers"], "raw": "woman holding yellow streamers", "sent_id": 82794, "sent": "woman holding yellow streamers"}], "file_name": "COCO_train2014_000000205131_542946.jpg", "ann_id": 542946, "sent_ids": [82793, 82794], "ref_id": 36800}, {"segmentation": [[23.65, 219.83, 14.71, 222.06, 14.71, 232.49, 61.65, 242.18, 60.9, 289.12, 40.04, 335.32, 40.04, 353.2, 45.26, 353.2, 45.26, 339.05, 56.43, 314.46, 114.55, 302.54, 130.2, 319.67, 128.71, 333.83, 133.18, 333.09, 132.44, 316.69, 111.57, 282.42, 111.57, 267.51, 133.93, 259.32, 205.46, 274.97, 209.19, 269.75, 214.4, 266.02, 225.58, 259.32, 233.77, 263.79, 239.74, 258.57, 252.4, 248.14, 258.36, 251.12, 264.33, 260.06, 269.54, 257.83, 266.56, 250.38, 268.05, 245.91, 265.07, 246.65, 258.36, 243.67, 256.13, 242.18, 253.15, 241.43, 250.17, 237.71, 244.95, 237.71, 243.46, 220.57, 227.81, 218.34, 228.56, 228.02, 221.11, 226.53, 224.09, 222.81, 203.97, 221.32, 203.97, 219.83, 200.99, 217.59, 192.79, 215.35, 188.32, 212.37, 185.34, 213.12, 177.89, 212.37, 162.99, 212.37, 152.56, 211.63, 152.56, 201.2, 157.03, 189.27, 135.42, 187.04, 138.4, 200.45, 139.14, 204.18, 139.89, 213.86, 120.51, 209.39, 119.02, 196.73, 104.87, 196.73, 104.12, 208.65, 62.39, 214.61, 61.65, 208.65, 52.71, 206.41, 46.75, 209.39, 55.69, 218.34, 55.69, 224.3, 46.75, 225.79, 37.06, 221.32, 33.33, 214.61, 25.88, 214.61, 24.39, 215.35]], "area": 13924.149200000005, "iscrowd": 0, "image_id": 356916, "bbox": [14.71, 187.04, 254.83, 166.16], "category_id": 67, "id": 123586, "split": "val", "sentences": [{"tokens": ["table", "woman", "in", "blue", "sweater", "is", "sitting", "at"], "raw": "table woman in blue sweater is sitting at", "sent_id": 82886, "sent": "table woman in blue sweater is sitting at"}, {"tokens": ["table", "in", "front", "of", "seated", "woman"], "raw": "Table in front of seated woman.", "sent_id": 82887, "sent": "table in front of seated woman"}], "file_name": "COCO_train2014_000000356916_123586.jpg", "ann_id": 123586, "sent_ids": [82886, 82887], "ref_id": 36836}, {"segmentation": [[246.74, 292.04, 252.4, 316.31, 263.73, 315.51, 268.58, 264.54, 237.84, 203.06, 228.94, 191.73, 207.91, 209.53, 181.21, 221.66, 166.65, 218.43, 163.42, 216.0, 155.33, 251.6, 172.31, 262.11, 188.49, 255.64, 191.73, 236.22, 205.48, 223.28, 212.76, 222.47, 225.71, 237.03, 234.61, 260.49]], "area": 4659.869549999999, "iscrowd": 0, "image_id": 348315, "bbox": [155.33, 191.73, 113.25, 124.58], "category_id": 24, "id": 589712, "split": "val", "sentences": [{"tokens": ["the", "zebra", "furthest", "away"], "raw": "The zebra furthest away.", "sent_id": 82904, "sent": "the zebra furthest away"}, {"tokens": ["a", "zebra", "in", "the", "back"], "raw": "a zebra in the back", "sent_id": 82905, "sent": "a zebra in the back"}], "file_name": "COCO_train2014_000000348315_589712.jpg", "ann_id": 589712, "sent_ids": [82904, 82905], "ref_id": 36842}, {"segmentation": [[194.67, 418.93, 193.35, 370.26, 192.04, 312.39, 192.04, 262.41, 192.04, 242.68, 201.24, 211.11, 205.19, 199.27, 205.19, 190.06, 205.19, 182.17, 197.3, 157.18, 202.56, 128.24, 201.24, 117.72, 194.67, 104.57, 193.35, 90.1, 194.67, 74.32, 205.19, 65.11, 480.09, 73.0, 480.09, 165.07, 484.04, 182.17, 490.61, 196.64, 499.82, 228.21, 510.34, 358.42, 514.29, 376.84, 502.45, 397.88, 494.56, 412.35, 484.04, 418.93, 473.51, 422.87, 473.51, 433.4, 466.94, 449.18, 459.05, 455.76, 453.78, 455.76, 440.63, 445.23, 431.42, 436.03, 228.86, 433.4, 226.23, 449.18, 218.34, 454.44, 209.14, 447.86, 199.93, 429.45]], "area": 110073.32719999994, "iscrowd": 0, "image_id": 438663, "bbox": [192.04, 65.11, 322.25, 390.65], "category_id": 8, "id": 397307, "split": "val", "sentences": [{"tokens": ["a", "white", "truck", "that", "has", "damages", "on", "the", "front"], "raw": "A white truck that has damages on the front.", "sent_id": 83012, "sent": "a white truck that has damages on the front"}, {"tokens": ["the", "front", "of", "a", "staples", "truck", "that", "seems", "to", "have", "been", "in", "a", "small", "wreck"], "raw": "The front of a Staples truck that seems to have been in a small wreck.", "sent_id": 83013, "sent": "the front of a staples truck that seems to have been in a small wreck"}], "file_name": "COCO_train2014_000000438663_397307.jpg", "ann_id": 397307, "sent_ids": [83012, 83013], "ref_id": 36880}, {"segmentation": [[161.24, 0.0, 166.55, 119.87, 186.7, 145.33, 194.13, 195.19, 239.74, 264.14, 251.41, 293.84, 248.23, 302.33, 268.39, 301.27, 374.47, 245.05, 427.51, 32.89, 414.78, 4.24]], "area": 58696.33265, "iscrowd": 0, "image_id": 32105, "bbox": [161.24, 0.0, 266.27, 302.33], "category_id": 33, "id": 1186846, "split": "val", "sentences": [{"tokens": ["a", "black", "suitcase", "with", "a", "red", "tie", "on", "the", "zipper", "stands", "beside", "an", "identical", "black", "suitcase"], "raw": "A black suitcase with a red tie on the zipper stands beside an identical black suitcase.", "sent_id": 83022, "sent": "a black suitcase with a red tie on the zipper stands beside an identical black suitcase"}, {"tokens": ["a", "black", "suitcase", "touching", "a", "blue", "and", "black", "bag", "with", "a", "green", "hat", "on", "top"], "raw": "a black suitcase touching a blue and black bag with a green hat on top", "sent_id": 83023, "sent": "a black suitcase touching a blue and black bag with a green hat on top"}], "file_name": "COCO_train2014_000000032105_1186846.jpg", "ann_id": 1186846, "sent_ids": [83022, 83023], "ref_id": 36884}, {"segmentation": [[488.28, 176.95, 499.88, 185.07, 493.3, 210.98, 484.8, 236.89, 491.37, 257.0, 500.0, 260.48, 499.5, 279.43, 482.87, 278.27, 472.42, 267.44, 472.81, 285.23, 463.14, 294.13, 460.05, 294.9, 456.96, 302.64, 450.76, 306.12, 435.3, 298.77, 431.04, 285.62, 438.39, 263.96, 432.2, 252.75, 444.19, 241.53, 449.22, 243.08, 451.15, 235.73, 479.77, 196.16, 475.13, 191.14, 478.61, 180.31]], "area": 4489.332450000002, "iscrowd": 0, "image_id": 321209, "bbox": [431.04, 176.95, 68.96, 129.17], "category_id": 4, "id": 150694, "split": "val", "sentences": [{"tokens": ["black", "motor", "scooter", "parked", "on", "the", "curb"], "raw": "Black motor scooter parked on the curb.", "sent_id": 83064, "sent": "black motor scooter parked on the curb"}, {"tokens": ["the", "moped", "on", "the", "right", "edge"], "raw": "the moped on the right edge", "sent_id": 83065, "sent": "the moped on the right edge"}], "file_name": "COCO_train2014_000000321209_150694.jpg", "ann_id": 150694, "sent_ids": [83064, 83065], "ref_id": 36903}, {"segmentation": [[208.26, 377.64, 205.98, 320.58, 177.44, 266.37, 183.15, 250.96, 187.15, 244.11, 173.45, 243.55, 168.89, 238.41, 163.18, 220.72, 178.59, 221.29, 194.57, 220.15, 204.27, 226.99, 201.98, 235.56, 228.23, 269.22, 264.75, 284.63, 281.87, 302.32, 281.3, 354.82, 284.72, 390.19, 279.59, 385.06, 254.48, 324.58, 241.93, 326.28, 226.52, 324.58, 223.1, 329.14, 220.81, 380.5, 207.12, 379.35]], "area": 7730.628700000001, "iscrowd": 0, "image_id": 510611, "bbox": [163.18, 220.15, 121.54, 170.04], "category_id": 25, "id": 595030, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "that", "'", "s", "the", "smallest", "in", "the", "picture"], "raw": "A giraffe that's the smallest in the picture.", "sent_id": 83135, "sent": "a giraffe that ' s the smallest in the picture"}, {"tokens": ["the", "smallest", "giraffe", "with", "it", "'", "s", "head", "in", "the", "feed", "cage"], "raw": "The smallest giraffe with it's head in the feed cage.", "sent_id": 83136, "sent": "the smallest giraffe with it ' s head in the feed cage"}], "file_name": "COCO_train2014_000000510611_595030.jpg", "ann_id": 595030, "sent_ids": [83135, 83136], "ref_id": 36927}, {"segmentation": [[236.93, 189.03, 247.62, 225.23, 221.3, 254.84, 219.66, 286.1, 226.24, 350.25, 227.88, 382.33, 218.01, 397.96, 198.27, 389.74, 203.21, 370.82, 198.27, 332.16, 190.05, 287.74, 189.22, 316.53, 191.69, 344.5, 192.51, 365.88, 192.51, 378.22, 164.55, 392.2, 156.32, 391.38, 172.77, 360.12, 166.19, 324.76, 163.72, 299.26, 158.79, 276.22, 149.74, 250.0, 149.74, 239.3, 128.35, 245.88, 124.24, 231.08, 124.24, 224.5, 131.64, 211.34, 139.05, 186.66, 150.56, 171.85, 162.08, 158.69, 167.01, 156.23, 167.01, 151.29, 170.3, 139.78, 177.71, 129.9, 186.75, 121.68, 199.92, 124.15, 204.03, 129.9, 210.61, 147.18, 211.43, 156.23, 220.48, 168.56, 243.51, 189.13]], "area": 17866.48755000001, "iscrowd": 0, "image_id": 335524, "bbox": [124.24, 121.68, 123.38, 276.28], "category_id": 1, "id": 2152664, "split": "val", "sentences": [{"tokens": ["a", "skier", "in", "yellow", "pants"], "raw": "A skier in yellow pants.", "sent_id": 83154, "sent": "a skier in yellow pants"}, {"tokens": ["a", "women", "with", "green", "jacket"], "raw": "A women with green jacket", "sent_id": 83155, "sent": "a women with green jacket"}], "file_name": "COCO_train2014_000000335524_2152664.jpg", "ann_id": 2152664, "sent_ids": [83154, 83155], "ref_id": 36934}, {"segmentation": [[206.11, 180.28, 206.11, 229.11, 214.73, 226.24, 217.6, 220.49, 228.14, 231.98, 228.14, 239.64, 224.31, 246.35, 213.77, 246.35, 235.8, 262.62, 232.92, 293.26, 296.12, 313.37, 309.52, 337.31, 307.61, 342.09, 319.1, 342.09, 326.76, 316.24, 361.23, 321.03, 361.23, 329.65, 369.85, 331.56, 380.38, 327.73, 401.44, 327.73, 437.83, 322.94, 447.4, 325.82, 451.23, 311.45, 452.19, 304.75, 453.15, 303.79, 456.02, 293.26, 451.23, 288.47, 453.15, 266.45, 445.49, 249.22, 415.81, 238.69, 395.7, 205.17, 390.91, 199.43, 391.87, 170.7, 264.52, 159.21, 206.11, 178.36]], "area": 31217.377250000005, "iscrowd": 0, "image_id": 277188, "bbox": [206.11, 159.21, 249.91, 182.88], "category_id": 8, "id": 399435, "split": "val", "sentences": [{"tokens": ["the", "center", "ambulance", "of", "three", ",", "white", "with", "yellow", "stripes"], "raw": "The center ambulance of three, white with yellow stripes.", "sent_id": 83287, "sent": "the center ambulance of three , white with yellow stripes"}, {"tokens": ["an", "ambulance", "in", "the", "middle", "of", "two", "others"], "raw": "An ambulance in the middle of two others.", "sent_id": 83288, "sent": "an ambulance in the middle of two others"}], "file_name": "COCO_train2014_000000277188_399435.jpg", "ann_id": 399435, "sent_ids": [83287, 83288], "ref_id": 36985}, {"segmentation": [[211.4, 175.47, 206.54, 187.09, 198.3, 198.92, 189.85, 208.0, 179.08, 214.76, 164.92, 219.83, 146.33, 222.36, 133.45, 220.46, 123.73, 216.45, 119.72, 214.55, 124.15, 212.01, 123.52, 210.32, 121.62, 209.9, 119.93, 210.32, 119.93, 208.21, 119.08, 207.58, 117.6, 209.9, 115.91, 209.06, 115.91, 212.22, 106.62, 205.68, 98.38, 196.8, 92.89, 187.51, 86.97, 172.72, 86.34, 157.3, 88.03, 142.09, 92.04, 133.85, 97.11, 123.93, 105.56, 112.52, 119.93, 102.59, 135.35, 96.68, 150.14, 95.83, 169.57, 98.37, 189.85, 108.93, 202.1, 121.18, 208.65, 134.7, 211.82, 142.3, 213.93, 158.36, 211.61, 173.36]], "area": 12565.039000000002, "iscrowd": 0, "image_id": 7504, "bbox": [86.34, 95.83, 127.59, 126.53], "category_id": 85, "id": 334244, "split": "val", "sentences": [{"tokens": ["a", "round", "wall", "clock", "showing", "london", "time", "next", "to", "two", "other", "clocks", "showing", "times", "for", "other", "cities"], "raw": "A round wall clock showing London time next to two other clocks showing times for other cities.", "sent_id": 83333, "sent": "a round wall clock showing london time next to two other clocks showing times for other cities"}, {"tokens": ["clock", "on", "wall", "showing", "12", ":", "21"], "raw": "clock on wall showing 12:21", "sent_id": 83334, "sent": "clock on wall showing 12 : 21"}], "file_name": "COCO_train2014_000000007504_334244.jpg", "ann_id": 334244, "sent_ids": [83333, 83334], "ref_id": 37004}, {"segmentation": [[375.37, 271.26, 384.72, 219.16, 396.07, 196.45, 388.06, 183.08, 364.67, 235.19, 358.0, 225.84, 382.71, 180.42, 397.41, 149.69, 411.44, 136.99, 439.5, 131.65, 454.19, 113.61, 476.24, 114.95, 513.65, 77.54, 518.99, 70.19, 524.34, 58.83, 527.01, 70.19, 531.02, 58.83, 536.36, 68.85, 541.7, 76.2, 535.02, 90.9, 542.37, 106.26, 534.35, 107.6, 521.66, 98.92, 480.25, 147.01, 486.26, 170.39, 470.89, 199.79, 488.26, 271.93, 501.63, 297.99, 486.93, 294.65, 462.21, 223.17, 454.19, 265.25, 456.87, 293.98, 448.18, 288.63, 447.51, 226.51, 450.19, 195.78, 434.82, 194.44, 416.11, 198.45, 409.43, 225.17, 415.44, 285.3, 408.1, 284.63, 397.41, 229.85, 380.71, 287.3, 373.36, 282.62]], "area": 12685.696649999994, "iscrowd": 0, "image_id": 17997, "bbox": [358.0, 58.83, 184.37, 239.16], "category_id": 25, "id": 599851, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "closest", "to", "the", "gate"], "raw": "The giraffe closest to the gate", "sent_id": 83340, "sent": "the giraffe closest to the gate"}], "file_name": "COCO_train2014_000000017997_599851.jpg", "ann_id": 599851, "sent_ids": [83340], "ref_id": 37007}, {"segmentation": [[348.53, 210.88, 308.82, 195.0, 255.0, 165.0, 238.24, 138.53, 237.35, 130.59, 241.76, 126.18, 257.65, 127.94, 264.71, 131.47, 266.47, 120.88, 278.82, 114.71, 274.41, 107.65, 275.29, 99.71, 290.29, 94.41, 327.35, 105.88, 363.53, 126.18, 383.82, 146.47, 397.06, 172.06, 396.18, 186.18, 392.65, 196.76, 386.47, 202.94, 380.29, 201.18, 374.12, 199.41, 369.71, 203.82]], "area": 11225.02965, "iscrowd": 0, "image_id": 554706, "bbox": [237.35, 94.41, 159.71, 116.47], "category_id": 58, "id": 1067522, "split": "val", "sentences": [{"tokens": ["a", "hotdog", "with", "nothing", "on", "it"], "raw": "a hotdog with nothing on it", "sent_id": 83361, "sent": "a hotdog with nothing on it"}, {"tokens": ["a", "hot", "dog", "in", "a", "toasted", "bun", ",", "served", "without", "any", "toppings", ",", "laying", "on", "a", "yellow", "bag"], "raw": "A hot dog in a toasted bun, served without any toppings, laying on a yellow bag.", "sent_id": 83362, "sent": "a hot dog in a toasted bun , served without any toppings , laying on a yellow bag"}], "file_name": "COCO_train2014_000000554706_1067522.jpg", "ann_id": 1067522, "sent_ids": [83361, 83362], "ref_id": 37015}, {"segmentation": [[638.29, 47.73, 596.22, 52.58, 566.29, 68.76, 562.25, 84.13, 557.39, 109.21, 560.63, 128.63, 568.72, 149.66, 582.47, 173.12, 597.03, 194.97, 609.17, 210.34, 624.54, 218.43, 601.89, 248.36, 606.74, 313.08, 606.74, 330.07, 566.29, 334.11, 558.2, 327.64, 546.07, 330.88, 545.26, 338.16, 493.48, 345.44, 493.48, 355.96, 561.44, 355.15, 639.1, 355.96, 640.0, 314.7, 637.48, 313.08, 639.1, 202.25, 638.29, 119.73, 639.91, 47.73]], "area": 17094.628449999997, "iscrowd": 0, "image_id": 520112, "bbox": [493.48, 47.73, 146.52, 308.23], "category_id": 1, "id": 504078, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "bald", "head", "near", "a", "man", "in", "a", "striped", "shirt"], "raw": "A man with a bald head near a man in a striped shirt.", "sent_id": 83440, "sent": "a man with a bald head near a man in a striped shirt"}, {"tokens": ["the", "younger", "bald", "man", "with", "the", "mole", "on", "his", "right", "cheek"], "raw": "The younger bald man with the mole on his right cheek", "sent_id": 83441, "sent": "the younger bald man with the mole on his right cheek"}], "file_name": "COCO_train2014_000000520112_504078.jpg", "ann_id": 504078, "sent_ids": [83440, 83441], "ref_id": 37043}, {"segmentation": [[349.94, 236.2, 365.33, 278.61, 368.65, 287.34, 373.23, 296.08, 400.67, 304.39, 416.47, 303.98, 452.23, 305.64, 505.45, 310.63, 542.87, 302.73, 542.87, 295.24, 534.97, 277.78, 528.32, 258.65, 526.24, 246.6, 518.76, 242.02, 531.23, 237.45, 544.95, 233.29, 571.98, 229.55, 579.05, 226.22, 579.05, 218.74, 584.45, 213.75, 587.36, 209.17, 591.11, 197.95, 584.04, 184.23, 568.65, 181.32, 548.28, 185.06, 483.83, 198.78, 450.15, 208.34, 416.89, 215.0, 391.11, 222.9, 367.41, 229.55, 349.11, 233.29]], "area": 19081.130500000003, "iscrowd": 0, "image_id": 213419, "bbox": [349.11, 181.32, 242.0, 129.31], "category_id": 9, "id": 181073, "split": "val", "sentences": [{"tokens": ["a", "boat", "with", "a", "person", "in", "it"], "raw": "A boat with a person in it.", "sent_id": 83451, "sent": "a boat with a person in it"}, {"tokens": ["the", "boat", "on", "the", "right", "with", "the", "person", "in", "it"], "raw": "The boat on the right with the person in it.", "sent_id": 83452, "sent": "the boat on the right with the person in it"}], "file_name": "COCO_train2014_000000213419_181073.jpg", "ann_id": 181073, "sent_ids": [83451, 83452], "ref_id": 37049}, {"segmentation": [[170.6, 101.86, 166.17, 98.54, 189.43, 116.25, 189.43, 130.65, 200.5, 121.79, 209.36, 112.93, 225.97, 104.07, 234.83, 122.9, 247.01, 112.93, 255.87, 125.11, 240.36, 156.12, 231.5, 167.19, 227.08, 170.51, 233.72, 186.02, 252.54, 180.48, 271.37, 195.98, 294.62, 215.92, 291.3, 241.38, 312.34, 272.39, 316.77, 310.04, 316.77, 329.97, 321.2, 352.12, 348.88, 382.02, 361.07, 394.2, 353.31, 419.67, 341.13, 418.56, 312.34, 365.41, 293.52, 348.8, 285.77, 332.19, 275.8, 312.26, 273.58, 302.29, 265.83, 305.61, 309.02, 403.06, 302.38, 404.17, 283.55, 404.17, 274.69, 398.63, 260.3, 363.19, 250.33, 342.15, 244.79, 333.3, 228.18, 324.44, 210.47, 321.11, 203.82, 321.11, 206.04, 398.63, 194.96, 401.95, 187.21, 388.66, 165.06, 329.97, 141.81, 270.18, 162.85, 195.98, 173.92, 172.73, 170.6, 157.23, 153.99, 109.61, 167.28, 89.68]], "area": 32962.509249999996, "iscrowd": 0, "image_id": 287302, "bbox": [141.81, 89.68, 219.26, 329.99], "category_id": 24, "id": 593912, "split": "val", "sentences": [{"tokens": ["the", "zebra", "on", "the", "left"], "raw": "The zebra on the left.", "sent_id": 83453, "sent": "the zebra on the left"}], "file_name": "COCO_train2014_000000287302_593912.jpg", "ann_id": 593912, "sent_ids": [83453], "ref_id": 37050}, {"segmentation": [[188.4, 616.99, 197.03, 632.81, 221.48, 615.55, 225.8, 579.6, 198.47, 558.02, 169.71, 552.27, 116.49, 572.4, 112.18, 609.8, 136.63, 616.99, 159.64, 605.48, 166.83, 583.91, 174.02, 583.91, 189.84, 592.54, 186.97, 606.92], [309.21, 588.22, 290.52, 621.3, 258.88, 624.18, 244.49, 609.8, 240.18, 583.91, 228.67, 572.4, 227.24, 549.39, 238.74, 532.13, 266.07, 532.13, 287.64, 542.2, 293.39, 560.9, 286.2, 569.53, 271.82, 570.97, 266.07, 586.79, 274.7, 592.54, 287.64, 582.47, 300.58, 575.28, 309.21, 583.91]], "area": 10047.838349999995, "iscrowd": 0, "image_id": 74577, "bbox": [112.18, 532.13, 197.03, 100.68], "category_id": 61, "id": 1577278, "split": "val", "sentences": [{"tokens": ["donuts"], "raw": "donuts", "sent_id": 83464, "sent": "donuts"}], "file_name": "COCO_train2014_000000074577_1577278.jpg", "ann_id": 1577278, "sent_ids": [83464], "ref_id": 37055}, {"segmentation": [[279.3, 236.88, 293.87, 141.63, 311.8, 134.91, 606.51, 146.11, 625.56, 161.8, 634.53, 250.33, 627.81, 267.14, 301.71, 252.57, 288.26, 248.09, 280.42, 236.88]], "area": 40583.16684999999, "iscrowd": 0, "image_id": 445540, "bbox": [279.3, 134.91, 355.23, 132.23], "category_id": 77, "id": 329260, "split": "val", "sentences": [{"tokens": ["an", "older", "generation", "apple", "iphone"], "raw": "An older generation Apple iPhone.", "sent_id": 83534, "sent": "an older generation apple iphone"}, {"tokens": ["black", "color", "cellphone", "with", "wooden", "table"], "raw": "BLACK COLOR CELLPHONE  WITH WOODEN TABLE", "sent_id": 83535, "sent": "black color cellphone with wooden table"}], "file_name": "COCO_train2014_000000445540_329260.jpg", "ann_id": 329260, "sent_ids": [83534, 83535], "ref_id": 37084}, {"segmentation": [[137.68, 372.22, 159.63, 342.29, 173.59, 326.33, 172.59, 315.36, 162.62, 293.41, 160.62, 273.45, 169.6, 262.48, 180.58, 254.5, 192.55, 248.51, 203.52, 242.53, 213.5, 237.54, 224.47, 212.6, 233.45, 192.64, 237.44, 177.68, 246.42, 156.73, 252.41, 139.77, 261.39, 118.82, 268.37, 96.87, 273.36, 82.9, 289.32, 73.92, 303.29, 67.94, 321.25, 61.95, 346.19, 62.95, 363.15, 70.93, 379.11, 79.91, 404.05, 96.87, 411.04, 111.83, 416.02, 128.79, 416.02, 143.76, 408.04, 185.66, 403.05, 224.57, 398.07, 242.53, 394.07, 256.49, 381.11, 273.45, 384.1, 293.41, 394.07, 302.39, 422.01, 307.38, 431.99, 325.33, 447.95, 362.25, 462.91, 377.21, 489.85, 375.22, 511.8, 361.25, 540.73, 335.31, 552.7, 307.38, 558.69, 304.38, 567.67, 308.37, 585.63, 301.39, 603.58, 310.37, 610.57, 316.35, 606.58, 336.31, 605.58, 356.26, 607.57, 367.23, 584.63, 385.19, 568.67, 386.19, 546.72, 398.16, 548.71, 404.15, 526.76, 406.14, 495.84, 414.12, 464.91, 418.12, 349.18, 419.11, 302.29, 414.12, 279.34, 405.15, 182.57, 394.17, 170.6, 392.18, 142.67, 382.2, 137.68, 380.2]], "area": 80443.13884999997, "iscrowd": 0, "image_id": 278549, "bbox": [137.68, 61.95, 472.89, 357.16], "category_id": 1, "id": 502229, "split": "val", "sentences": [{"tokens": ["a", "child", "is", "holding", "a", "piece", "of", "bread"], "raw": "A child is holding a piece of bread.", "sent_id": 83696, "sent": "a child is holding a piece of bread"}, {"tokens": ["the", "baby", "in", "green"], "raw": "the baby in  green", "sent_id": 83697, "sent": "the baby in green"}], "file_name": "COCO_train2014_000000278549_502229.jpg", "ann_id": 502229, "sent_ids": [83696, 83697], "ref_id": 37137}, {"segmentation": [[156.76, 204.86, 172.97, 212.43, 190.27, 171.35, 235.68, 144.32, 281.08, 142.16, 418.38, 150.81, 424.86, 124.86, 517.84, 111.89, 550.27, 112.97, 567.57, 104.32, 555.68, 148.65, 578.38, 189.73, 595.68, 222.16, 574.05, 239.46, 558.92, 226.49, 520.0, 197.3, 462.7, 234.05, 454.05, 240.54, 423.78, 221.08, 368.65, 229.73, 296.22, 241.62, 282.16, 257.84, 259.46, 298.92, 262.7, 306.49, 258.38, 316.22, 256.22, 337.84, 284.32, 373.51, 296.22, 401.62, 294.05, 413.51, 270.27, 405.95, 238.92, 336.76, 227.03, 322.7, 235.68, 289.19, 233.51, 274.05, 224.86, 281.62, 201.08, 336.76, 206.49, 388.65, 222.7, 407.03, 204.32, 408.11, 194.59, 407.03, 184.86, 386.49, 188.11, 331.35, 189.19, 317.3, 192.43, 284.86, 189.19, 237.3, 182.7, 214.59, 157.84, 251.35, 151.35, 223.24]], "area": 46953.81530000001, "iscrowd": 0, "image_id": 565664, "bbox": [151.35, 104.32, 444.33, 309.19], "category_id": 24, "id": 589200, "split": "val", "sentences": [{"tokens": ["larger", "of", "the", "two", "zebras"], "raw": "Larger of the two zebras.", "sent_id": 83704, "sent": "larger of the two zebras"}, {"tokens": ["a", "mother", "and", "young", "baby", "zebra", "bonding"], "raw": "A mother and young baby zebra bonding.", "sent_id": 83705, "sent": "a mother and young baby zebra bonding"}], "file_name": "COCO_train2014_000000565664_589200.jpg", "ann_id": 589200, "sent_ids": [83704, 83705], "ref_id": 37141}, {"segmentation": [[67.35, 277.62, 70.34, 254.43, 67.35, 225.24, 60.61, 214.02, 53.88, 200.55, 51.63, 188.58, 59.87, 173.61, 68.1, 165.38, 71.09, 161.64, 77.08, 149.66, 86.8, 138.44, 95.04, 132.45, 114.49, 132.45, 118.98, 147.42, 122.72, 168.37, 128.71, 196.81, 128.71, 210.28, 114.49, 206.53, 107.01, 208.78, 115.24, 217.76, 121.23, 223.0, 119.73, 240.96, 121.23, 268.64, 115.24, 260.41, 115.24, 247.69, 100.27, 240.21, 89.05, 252.18, 86.06, 271.64, 88.3, 279.12]], "area": 6925.573050000002, "iscrowd": 0, "image_id": 306561, "bbox": [51.63, 132.45, 77.08, 146.67], "category_id": 1, "id": 1730510, "split": "val", "sentences": [{"tokens": ["woman", "have", "a", "beer", "cup"], "raw": "woman have a beer cup", "sent_id": 83710, "sent": "woman have a beer cup"}, {"tokens": ["a", "lady", "holding", "a", "cup", "and", "listening", "the", "conversation", "in", "a", "house"], "raw": "A lady holding a cup and listening the conversation in a house", "sent_id": 83711, "sent": "a lady holding a cup and listening the conversation in a house"}], "file_name": "COCO_train2014_000000306561_1730510.jpg", "ann_id": 1730510, "sent_ids": [83710, 83711], "ref_id": 37144}, {"segmentation": [[345.78, 159.11, 504.89, 147.56, 519.11, 138.67, 533.33, 125.33, 535.11, 127.11, 534.22, 187.56, 533.33, 191.11, 440.89, 206.22, 354.67, 213.33, 344.89, 208.89, 339.56, 184.89, 336.0, 165.33]], "area": 10376.95015, "iscrowd": 0, "image_id": 492894, "bbox": [336.0, 125.33, 199.11, 88.0], "category_id": 10, "id": 1804665, "split": "val", "sentences": [{"tokens": ["white", "base", "of", "the", "signal"], "raw": "White base of the signal", "sent_id": 83781, "sent": "white base of the signal"}], "file_name": "COCO_train2014_000000492894_1804665.jpg", "ann_id": 1804665, "sent_ids": [83781], "ref_id": 37177}, {"segmentation": [[342.99, 203.07, 339.64, 194.16, 339.64, 184.69, 337.42, 178.0, 344.1, 166.86, 356.36, 166.3, 369.73, 170.76, 369.73, 178.56, 364.16, 191.93, 362.49, 199.17, 371.96, 202.52, 375.86, 208.09, 378.09, 217.56, 380.32, 229.82, 380.32, 242.08, 377.53, 252.66, 376.97, 257.68, 380.32, 268.26, 383.1, 277.73, 383.1, 287.76, 381.99, 302.8, 374.74, 312.28, 366.94, 318.41, 373.07, 329.55, 376.42, 340.13, 388.67, 367.96, 399.26, 381.86, 384.22, 383.53, 369.73, 380.75, 358.59, 376.29, 369.73, 367.93, 361.93, 365.71, 355.8, 346.2, 349.67, 331.16, 345.77, 338.4, 344.1, 354.0, 345.77, 396.32, 354.69, 432.51, 356.92, 434.73, 348.0, 438.63, 341.32, 439.75, 338.53, 438.08, 326.27, 441.98, 304.54, 448.66, 295.07, 439.75, 302.31, 435.29, 322.93, 423.59, 324.04, 411.89, 324.6, 394.06, 322.37, 374.59, 314.57, 361.28, 316.8, 350.69, 327.39, 292.25, 332.4, 286.12, 330.17, 274.98, 326.27, 268.29, 320.7, 281.66, 318.47, 286.68, 320.7, 293.36, 322.93, 297.26, 319.03, 298.38, 311.79, 296.15, 315.13, 300.61, 315.13, 303.95, 307.89, 305.06, 305.1, 294.48, 307.33, 287.79, 311.23, 277.2, 317.92, 256.62, 329.06, 228.23, 331.84, 212.66, 336.86, 207.09, 341.87, 203.19]], "area": 12619.311550000002, "iscrowd": 0, "image_id": 525039, "bbox": [295.07, 166.3, 104.19, 282.36], "category_id": 1, "id": 421262, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "the", "desert", "throwing", "a", "frisbee"], "raw": "A man in the desert throwing a frisbee", "sent_id": 83867, "sent": "a man in the desert throwing a frisbee"}, {"tokens": ["man"], "raw": "Man", "sent_id": 83868, "sent": "man"}], "file_name": "COCO_train2014_000000525039_421262.jpg", "ann_id": 421262, "sent_ids": [83867, 83868], "ref_id": 37210}, {"segmentation": [[120.87, 329.72, 112.83, 264.83, 71.43, 267.29, 41.76, 267.29, 0.0, 277.8, 0.97, 269.77, 31.87, 230.83, 64.01, 209.81, 89.97, 206.73, 106.03, 203.64, 125.2, 204.25, 149.92, 203.02, 189.47, 222.8, 216.66, 246.9, 227.79, 256.79, 115.93, 265.44, 123.34, 328.48]], "area": 10202.109550000001, "iscrowd": 0, "image_id": 355345, "bbox": [0.0, 203.02, 227.79, 126.7], "category_id": 28, "id": 281160, "split": "val", "sentences": [{"tokens": ["the", "umbrella", "the", "person", "in", "the", "pink", "hat", "is", "holding"], "raw": "The umbrella the person in the pink hat is holding", "sent_id": 83992, "sent": "the umbrella the person in the pink hat is holding"}, {"tokens": ["light", "blue", "umbrella", "bottom", "left"], "raw": "light blue umbrella bottom left", "sent_id": 83993, "sent": "light blue umbrella bottom left"}], "file_name": "COCO_train2014_000000355345_281160.jpg", "ann_id": 281160, "sent_ids": [83992, 83993], "ref_id": 37258}, {"segmentation": [[440.09, 289.08, 422.83, 333.3, 416.36, 360.27, 422.83, 396.94, 464.9, 444.4, 501.57, 457.35, 560.9, 460.58, 600.81, 435.78, 616.99, 388.31, 623.46, 357.03, 623.46, 319.28, 597.57, 278.29, 572.76, 263.19, 518.83, 258.88, 485.39, 263.19, 457.35, 278.29, 442.25, 288.0]], "area": 33511.7129, "iscrowd": 0, "image_id": 87792, "bbox": [416.36, 258.88, 207.1, 201.7], "category_id": 60, "id": 1082789, "split": "val", "sentences": [{"tokens": ["a", "doughnut", "without", "a", "hole", "sitting", "below", "a", "light", "colored", "doughnut", "with", "a", "hole"], "raw": "A doughnut without a hole sitting below a light colored doughnut with a hole.", "sent_id": 84004, "sent": "a doughnut without a hole sitting below a light colored doughnut with a hole"}, {"tokens": ["a", "small", "donut", ",", "with", "no", "whole", "and", "a", "lot", "of", "powdered", "sugar"], "raw": "A small donut, with no whole and a lot of powdered sugar", "sent_id": 84005, "sent": "a small donut , with no whole and a lot of powdered sugar"}], "file_name": "COCO_train2014_000000087792_1082789.jpg", "ann_id": 1082789, "sent_ids": [84004, 84005], "ref_id": 37262}, {"segmentation": [[4.72, 201.0, 101.65, 206.16, 150.11, 249.47, 167.64, 294.84, 165.58, 330.93, 148.05, 355.68, 148.05, 384.55, 142.89, 388.67, 133.61, 376.3, 94.43, 383.52, 75.87, 353.61, 7.81, 337.12, 12.97, 336.08, 18.12, 331.96, 22.25, 319.59, 23.28, 302.06, 8.84, 282.46, 0.0, 279.37, 0.59, 201.0]], "area": 22503.253150000004, "iscrowd": 0, "image_id": 291658, "bbox": [0.0, 201.0, 167.64, 187.67], "category_id": 3, "id": 344864, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "white", "van"], "raw": "The back of a white van.", "sent_id": 84020, "sent": "the back of a white van"}, {"tokens": ["a", "white", "van", "under", "streetlamps", "is", "parked", "next", "to", "a", "sidewalk"], "raw": "A white van under streetlamps is parked next to a sidewalk.", "sent_id": 84021, "sent": "a white van under streetlamps is parked next to a sidewalk"}], "file_name": "COCO_train2014_000000291658_344864.jpg", "ann_id": 344864, "sent_ids": [84020, 84021], "ref_id": 37269}, {"segmentation": [[637.63, 415.51, 636.67, 161.8, 522.74, 153.18, 510.29, 168.5, 494.98, 207.76, 484.44, 223.07, 467.21, 228.82, 431.79, 222.12, 411.68, 227.86, 402.11, 255.63, 391.58, 273.82, 404.02, 264.24, 409.77, 250.84, 425.09, 267.11, 417.43, 289.13, 425.09, 293.92, 435.62, 267.11, 473.91, 300.62, 463.38, 330.3, 468.17, 333.17, 478.7, 307.33, 542.85, 353.28, 540.93, 381.04, 539.02, 401.15, 555.29, 392.53, 562.95, 367.64, 632.84, 412.64]], "area": 35837.770049999985, "iscrowd": 0, "image_id": 346026, "bbox": [391.58, 153.18, 246.05, 262.33], "category_id": 15, "id": 578787, "split": "val", "sentences": [{"tokens": ["the", "bench", "the", "bird", "is", "walking", "under"], "raw": "The bench the bird is walking under", "sent_id": 84080, "sent": "the bench the bird is walking under"}], "file_name": "COCO_train2014_000000346026_578787.jpg", "ann_id": 578787, "sent_ids": [84080], "ref_id": 37297}, {"segmentation": [[242.25, 321.81, 246.08, 272.02, 364.81, 261.49, 449.06, 261.49, 487.36, 314.15, 450.02, 321.81]], "area": 12872.7928, "iscrowd": 0, "image_id": 513221, "bbox": [242.25, 261.49, 245.11, 60.32], "category_id": 61, "id": 1086833, "split": "val", "sentences": [{"tokens": ["a", "large", "sheet", "cake", "with", "a", "black", "dog", "on", "it"], "raw": "A large sheet cake with a black dog on it.", "sent_id": 84083, "sent": "a large sheet cake with a black dog on it"}, {"tokens": ["the", "white", "cake", "with", "blue", ",", "white", ",", "and", "green", "frosting", "in", "front", "of", "a", "woman", "wearing", "a", "black", "and", "read", "flowered", "shirt"], "raw": "The white cake with blue, white, and green frosting in front of a woman wearing a black and read flowered shirt", "sent_id": 84084, "sent": "the white cake with blue , white , and green frosting in front of a woman wearing a black and read flowered shirt"}], "file_name": "COCO_train2014_000000513221_1086833.jpg", "ann_id": 1086833, "sent_ids": [84083, 84084], "ref_id": 37299}, {"segmentation": [[363.03, 439.19, 379.53, 422.69, 389.69, 412.53, 399.84, 402.38, 473.46, 420.15, 478.54, 420.15, 469.65, 413.8, 462.04, 407.46, 455.69, 376.99, 454.42, 357.95, 453.15, 324.95, 458.23, 302.1, 458.23, 271.64, 449.34, 244.98, 429.03, 218.33, 384.61, 204.36, 390.95, 145.97, 376.99, 105.35, 326.22, 79.97, 309.72, 78.7, 280.52, 88.85, 260.21, 111.7, 250.06, 138.36, 244.98, 157.4, 244.98, 184.05, 244.98, 198.02, 229.75, 239.9, 223.4, 258.94, 222.13, 302.1, 222.13, 310.99, 203.09, 280.52, 191.67, 271.64, 149.78, 280.52, 137.09, 289.41, 125.66, 307.18, 125.66, 324.95, 139.63, 336.37, 154.86, 366.84, 166.28, 376.99, 189.13, 411.26, 220.86, 441.73, 247.52, 464.58, 264.02, 462.04, 276.71, 441.73, 281.79, 431.57, 289.41, 420.15, 300.83, 439.19, 324.95, 449.34]], "area": 77295.27565000001, "iscrowd": 0, "image_id": 290185, "bbox": [125.66, 78.7, 352.88, 385.88], "category_id": 1, "id": 430704, "split": "val", "sentences": [{"tokens": ["a", "bride", "with", "pizza", "cheese", "hanging", "off", "pizza"], "raw": "A bride with pizza cheese hanging off pizza.", "sent_id": 84105, "sent": "a bride with pizza cheese hanging off pizza"}, {"tokens": ["a", "woman", "holds", "up", "a", "piece", "of", "pizza", ",", "she", "is", "wearing", "a", "dress"], "raw": "A woman holds up a piece of pizza, she is wearing a dress.", "sent_id": 84106, "sent": "a woman holds up a piece of pizza , she is wearing a dress"}], "file_name": "COCO_train2014_000000290185_430704.jpg", "ann_id": 430704, "sent_ids": [84105, 84106], "ref_id": 37308}, {"segmentation": [[200.49, 123.14, 196.63, 163.62, 192.78, 221.45, 196.63, 238.8, 193.74, 294.71, 191.81, 320.73, 196.63, 363.14, 208.2, 367.96, 232.3, 359.29, 255.43, 362.18, 270.85, 391.1, 280.49, 373.75, 317.12, 378.56, 369.17, 377.6, 492.54, 370.85, 480.98, 183.86, 467.48, 73.01, 451.1, 47.95, 420.25, 40.24, 373.99, 35.42, 331.58, 38.31, 303.62, 44.1, 239.04, 89.4, 203.38, 116.39]], "area": 90248.56885000003, "iscrowd": 0, "image_id": 459082, "bbox": [191.81, 35.42, 300.73, 355.68], "category_id": 6, "id": 166901, "split": "val", "sentences": [{"tokens": ["the", "red", "double", "decker", "bus"], "raw": "The red double decker bus", "sent_id": 84177, "sent": "the red double decker bus"}, {"tokens": ["a", "red", "bus"], "raw": "A red bus", "sent_id": 84178, "sent": "a red bus"}], "file_name": "COCO_train2014_000000459082_166901.jpg", "ann_id": 166901, "sent_ids": [84177, 84178], "ref_id": 37331}, {"segmentation": [[122.97, 46.2, 143.46, 4.13, 163.96, 0.9, 495.1, 1.98, 515.6, 10.61, 522.07, 28.94, 525.3, 41.89, 528.54, 61.3, 528.54, 76.4, 522.07, 91.51, 520.99, 91.51, 129.44, 80.72]], "area": 33188.35414999999, "iscrowd": 0, "image_id": 219680, "bbox": [122.97, 0.9, 405.57, 90.61], "category_id": 51, "id": 1038100, "split": "val", "sentences": [{"tokens": ["a", "rectangular", "bowl", "of", "rice", "pudding"], "raw": "A rectangular bowl of rice pudding.", "sent_id": 84193, "sent": "a rectangular bowl of rice pudding"}, {"tokens": ["white", "rice", "in", "dish", "furthest", "away", "from", "the", "carrots"], "raw": "White rice in dish furthest away from the carrots", "sent_id": 84194, "sent": "white rice in dish furthest away from the carrots"}], "file_name": "COCO_train2014_000000219680_1038100.jpg", "ann_id": 1038100, "sent_ids": [84193, 84194], "ref_id": 37338}, {"segmentation": [[1.9, 116.43, 76.99, 102.17, 160.63, 87.92, 302.24, 90.77, 489.48, 67.01, 612.09, 61.3, 638.7, 75.56, 638.7, 250.44, 460.02, 258.05, 304.14, 258.05, 266.13, 248.54, 210.05, 255.2, 169.18, 272.3, 48.47, 317.93, 0.95, 343.59]], "area": 118040.56629999999, "iscrowd": 0, "image_id": 164935, "bbox": [0.95, 61.3, 637.75, 282.29], "category_id": 24, "id": 591176, "split": "val", "sentences": [{"tokens": ["a", "zebra", "doesn", "'", "t", "have", "birds", "on", "its", "back"], "raw": "A zebra doesn't have birds on its back.", "sent_id": 84197, "sent": "a zebra doesn ' t have birds on its back"}, {"tokens": ["the", "back", "of", "a", "zebra", "behind", "two", "birds"], "raw": "The back of a zebra behind two birds", "sent_id": 84198, "sent": "the back of a zebra behind two birds"}], "file_name": "COCO_train2014_000000164935_591176.jpg", "ann_id": 591176, "sent_ids": [84197, 84198], "ref_id": 37340}, {"segmentation": [[0.0, 345.35, 107.22, 345.35, 143.38, 314.18, 154.6, 316.68, 159.58, 331.64, 164.57, 346.6, 165.82, 346.6, 263.06, 341.61, 285.51, 349.09, 337.76, 388.26, 351.15, 407.91, 339.12, 463.79, 329.14, 478.21, 276.37, 480.0, 2.29, 480.0]], "area": 45690.51789999999, "iscrowd": 0, "image_id": 499966, "bbox": [0.0, 314.18, 351.15, 165.82], "category_id": 63, "id": 2126980, "split": "val", "sentences": [{"tokens": ["a", "red", "pillow"], "raw": "A red pillow.", "sent_id": 84250, "sent": "a red pillow"}, {"tokens": ["couch", "and", "pillow", "in", "the", "left", "bottom", "corner"], "raw": "couch and pillow in the left bottom corner", "sent_id": 84251, "sent": "couch and pillow in the left bottom corner"}], "file_name": "COCO_train2014_000000499966_2126980.jpg", "ann_id": 2126980, "sent_ids": [84250, 84251], "ref_id": 37360}, {"segmentation": [[45.92, 628.45, 64.57, 581.09, 140.63, 528.0, 186.55, 515.09, 156.41, 450.51, 114.8, 394.55, 110.49, 261.09, 119.1, 225.22, 143.5, 196.52, 172.2, 202.26, 182.24, 230.96, 203.77, 241.0, 218.12, 242.44, 274.08, 281.18, 302.78, 317.06, 345.83, 337.15, 370.22, 368.72, 377.4, 413.2, 357.31, 466.3, 384.57, 453.38, 444.84, 428.99, 479.28, 406.03, 480.0, 427.55, 476.41, 476.34, 466.37, 520.83, 459.19, 529.43, 417.58, 538.04, 370.22, 542.35, 353.0, 545.22, 332.91, 566.74, 302.78, 591.14, 256.86, 605.49, 187.98, 618.4, 183.68, 619.84, 166.46, 632.75]], "area": 94003.9675, "iscrowd": 0, "image_id": 87522, "bbox": [45.92, 196.52, 434.08, 436.23], "category_id": 1, "id": 459159, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "bananas", "on", "her", "head"], "raw": "A woman wearing bananas on her head.", "sent_id": 84270, "sent": "a woman wearing bananas on her head"}, {"tokens": ["a", "young", ",", "caucasian", "woman", "wearing", "a", "bunch", "of", "bananas", "on", "her", "head"], "raw": "A young, caucasian woman wearing a bunch of bananas on her head.", "sent_id": 84271, "sent": "a young , caucasian woman wearing a bunch of bananas on her head"}], "file_name": "COCO_train2014_000000087522_459159.jpg", "ann_id": 459159, "sent_ids": [84270, 84271], "ref_id": 37368}, {"segmentation": [[366.18, 355.14, 284.83, 324.44, 144.65, 263.56, 160.51, 245.65, 183.54, 218.03, 199.91, 202.68, 277.67, 236.44, 274.6, 241.05, 274.6, 246.16, 276.14, 249.23, 280.23, 252.82, 289.44, 253.33, 294.04, 254.35, 295.58, 254.86, 313.99, 283.51, 327.3, 286.07, 350.83, 294.77, 351.85, 295.28, 368.73, 332.62, 394.83, 354.62, 418.87, 368.44]], "area": 14618.074249999998, "iscrowd": 0, "image_id": 136092, "bbox": [144.65, 202.68, 274.22, 165.76], "category_id": 84, "id": 1652673, "split": "val", "sentences": [{"tokens": ["a", "book", "on", "a", "lady", "'", "s", "lap"], "raw": "A book on a lady's lap", "sent_id": 84425, "sent": "a book on a lady ' s lap"}], "file_name": "COCO_train2014_000000136092_1652673.jpg", "ann_id": 1652673, "sent_ids": [84425], "ref_id": 37418}, {"segmentation": [[440.47, 149.83, 434.52, 175.95, 436.9, 219.89, 432.15, 268.56, 422.65, 292.31, 426.22, 333.88, 426.22, 360.0, 421.46, 395.62, 394.15, 412.24, 387.03, 405.12, 387.03, 401.55, 384.65, 393.24, 376.34, 387.3, 372.78, 380.18, 376.34, 360.0, 378.71, 348.12, 345.48, 323.18, 353.78, 227.01, 362.09, 154.58, 356.16, 153.39, 328.84, 175.95, 287.29, 187.82, 275.41, 187.82, 275.41, 178.32, 287.29, 171.2, 299.16, 168.82, 335.98, 139.14, 350.21, 117.77, 349.03, 115.4, 338.34, 102.33, 335.98, 102.33, 331.22, 89.27, 331.22, 85.71, 330.03, 67.9, 328.84, 57.21, 332.41, 46.53, 338.34, 39.4, 352.59, 34.66, 368.03, 32.28, 376.34, 29.91, 383.46, 29.91, 394.15, 32.28, 402.46, 40.59, 413.15, 59.59, 413.15, 59.59, 428.58, 80.96, 404.83, 95.21, 427.4, 99.96, 445.22, 107.08, 459.45, 113.02, 472.52, 118.95, 476.09, 123.7, 492.7, 139.14, 506.95, 159.34, 509.32, 162.89, 518.82, 173.57, 520.02, 180.7, 521.21, 189.01, 512.89, 198.51, 501.02, 185.45, 496.27, 179.52, 489.14, 175.95, 478.45, 165.27, 471.34, 159.34, 467.77, 154.58, 463.02, 151.02, 454.7, 147.45, 445.22, 147.45]], "area": 32632.219950000002, "iscrowd": 0, "image_id": 240225, "bbox": [275.41, 29.91, 245.8, 382.33], "category_id": 1, "id": 2154453, "split": "val", "sentences": [{"tokens": ["a", "little", "girl", "wearing", "a", "yellow", "shirt", "with", "a", "ladybug", "on", "it"], "raw": "A little girl wearing a yellow shirt with a ladybug on it", "sent_id": 84524, "sent": "a little girl wearing a yellow shirt with a ladybug on it"}, {"tokens": ["a", "small", "girl", "wearing", "pink", "and", "yellow", "dress", "playing", "food", "ball"], "raw": "A small girl wearing pink and yellow dress playing food ball.", "sent_id": 84525, "sent": "a small girl wearing pink and yellow dress playing food ball"}], "file_name": "COCO_train2014_000000240225_2154453.jpg", "ann_id": 2154453, "sent_ids": [84524, 84525], "ref_id": 37451}, {"segmentation": [[251.76, 99.82, 265.07, 84.29, 291.69, 75.42, 317.2, 73.2, 342.71, 74.31, 357.13, 92.05, 360.45, 99.82, 362.67, 107.58, 364.89, 107.58, 364.89, 119.78, 360.45, 123.11, 354.91, 129.76, 351.58, 164.15, 353.8, 181.89, 343.82, 196.31, 323.85, 205.18, 301.67, 209.62, 286.15, 204.07, 272.84, 197.42, 267.29, 192.98, 262.85, 155.27, 260.64, 134.2, 248.44, 128.65, 248.44, 117.56, 248.44, 107.58, 248.44, 100.93, 252.87, 96.49]], "area": 12059.558849999998, "iscrowd": 0, "image_id": 199958, "bbox": [248.44, 73.2, 116.45, 136.42], "category_id": 47, "id": 1878914, "split": "val", "sentences": [{"tokens": ["a", "white", "tub", "of", "yogurt"], "raw": "A white tub of yogurt", "sent_id": 84532, "sent": "a white tub of yogurt"}, {"tokens": ["yogurt", "behind", "onions"], "raw": "yogurt behind onions", "sent_id": 84533, "sent": "yogurt behind onions"}], "file_name": "COCO_train2014_000000199958_1878914.jpg", "ann_id": 1878914, "sent_ids": [84532, 84533], "ref_id": 37455}, {"segmentation": [[162.9, 144.34, 160.0, 163.62, 168.68, 176.15, 174.46, 185.79, 163.86, 203.14, 150.37, 208.92, 140.73, 226.27, 125.3, 241.69, 118.56, 255.19, 105.06, 277.36, 99.28, 288.92, 92.53, 305.31, 92.53, 313.98, 100.24, 320.73, 109.88, 319.77, 115.67, 311.09, 125.3, 294.71, 137.84, 265.79, 144.58, 246.51, 149.4, 269.65, 149.4, 276.39, 143.62, 293.74, 133.02, 304.35, 128.2, 314.95, 142.65, 322.66, 144.58, 322.66, 176.39, 332.3, 186.99, 341.94, 197.6, 356.4, 210.13, 363.14, 221.69, 367.96, 226.51, 334.23, 231.33, 325.55, 255.43, 296.63, 261.21, 287.0, 270.85, 257.12, 273.74, 242.66, 269.89, 209.89, 258.32, 206.99, 240.97, 199.28, 210.13, 141.45, 167.72, 122.17, 158.08, 151.09]], "area": 22279.28875, "iscrowd": 0, "image_id": 533220, "bbox": [92.53, 122.17, 181.21, 245.79], "category_id": 1, "id": 460565, "split": "val", "sentences": [{"tokens": ["a", "man", "laughs", "at", "a", "table"], "raw": "A man laughs at a table.", "sent_id": 84576, "sent": "a man laughs at a table"}, {"tokens": ["a", "man", "in", "a", "dark", "blue", "shirt", ",", "laughing"], "raw": "A man in a dark blue shirt, laughing.", "sent_id": 84577, "sent": "a man in a dark blue shirt , laughing"}], "file_name": "COCO_train2014_000000533220_460565.jpg", "ann_id": 460565, "sent_ids": [84576, 84577], "ref_id": 37469}, {"segmentation": [[414.49, 214.59, 371.58, 222.49, 363.67, 204.42, 354.64, 201.04, 350.12, 201.04, 347.86, 199.91, 350.12, 185.22, 354.64, 175.06, 359.15, 160.38, 361.41, 151.34, 365.93, 141.18, 371.58, 132.14, 374.96, 126.49, 380.61, 119.72, 384.0, 116.33, 393.04, 111.81, 403.2, 107.29, 411.11, 98.26, 430.31, 86.96, 435.95, 79.06, 448.38, 70.02, 461.93, 64.38, 467.58, 59.86, 489.04, 58.73, 491.29, 60.99, 500.33, 64.38, 524.05, 68.89, 529.69, 70.02, 544.38, 79.06, 548.89, 97.13, 548.89, 98.26, 554.54, 134.4, 545.51, 151.34, 545.51, 151.34, 543.25, 160.38, 550.02, 167.15, 563.58, 173.93, 590.68, 178.45, 616.66, 189.74, 620.05, 195.39, 617.79, 212.33, 586.16, 224.75, 564.71, 227.01, 554.54, 227.01, 527.44, 231.53, 524.05, 231.53, 496.94, 237.18, 474.35, 233.79, 451.76, 229.27, 440.47, 222.49, 424.66, 219.11]], "area": 30132.639149999995, "iscrowd": 0, "image_id": 517985, "bbox": [347.86, 58.73, 272.19, 178.45], "category_id": 56, "id": 1056448, "split": "val", "sentences": [{"tokens": ["broccoli", "above", "the", "piece", "of", "baby", "corn"], "raw": "broccoli above the piece of baby corn", "sent_id": 84622, "sent": "broccoli above the piece of baby corn"}, {"tokens": ["broccoli", "on", "top", "of", "the", "corn"], "raw": "Broccoli on top of the corn.", "sent_id": 84623, "sent": "broccoli on top of the corn"}], "file_name": "COCO_train2014_000000517985_1056448.jpg", "ann_id": 1056448, "sent_ids": [84622, 84623], "ref_id": 37492}, {"segmentation": [[199.32, 391.41, 210.49, 383.13, 212.15, 381.06, 226.22, 373.2, 224.57, 372.78, 229.53, 371.54, 232.85, 371.54, 252.3, 342.57, 250.65, 328.08, 246.09, 310.28, 242.78, 299.51, 240.71, 311.93, 232.43, 314.42, 197.66, 311.93, 180.28, 309.04, 178.62, 308.62, 173.24, 305.31, 171.58, 304.9, 170.75, 304.07, 171.58, 302.83, 177.79, 297.03, 181.52, 296.2, 175.31, 294.13, 174.07, 291.65, 176.14, 287.51, 172.0, 285.85, 174.48, 282.13, 176.14, 282.13, 180.69, 277.99, 179.03, 272.19, 172.0, 266.4, 162.48, 265.16, 157.09, 252.74, 144.26, 237.84, 128.53, 229.97, 103.28, 221.28, 86.72, 223.76, 80.1, 228.32, 73.48, 232.04, 65.61, 235.35, 61.47, 240.73, 59.82, 243.22, 54.44, 248.19, 50.71, 255.22, 49.47, 261.85, 40.78, 281.72, 41.19, 290.82, 42.85, 294.96, 53.61, 297.03, 54.44, 297.45, 58.16, 300.76, 61.06, 307.79, 60.65, 309.04, 39.12, 315.24, 35.81, 318.14, 30.43, 325.59, 18.84, 353.74, 9.32, 395.96, 5.18, 407.97, 3.93, 430.74, 0.0, 431.15, 0.0, 466.75, 3.52, 466.33, 7.25, 480.0, 21.32, 485.79, 50.71, 485.38, 64.78, 485.38, 85.9, 485.38, 103.28, 484.13, 102.04, 466.33, 102.45, 452.26, 107.01, 440.67, 53.19, 451.85, 35.81, 452.26, 34.98, 449.36, 41.6, 446.88, 44.92, 434.88, 36.64, 433.63, 46.57, 431.98, 52.78, 403.42, 52.78, 394.31, 61.06, 410.87, 70.99, 429.91, 79.69, 429.91, 90.86, 427.01, 93.35, 426.6, 116.53, 419.15, 148.82, 416.25, 199.73, 392.65]], "area": 36358.917799999996, "iscrowd": 0, "image_id": 101573, "bbox": [0.0, 221.28, 252.3, 264.51], "category_id": 1, "id": 449814, "split": "val", "sentences": [{"tokens": ["girl", "laying", "on", "the", "ground"], "raw": "Girl laying on the ground", "sent_id": 84698, "sent": "girl laying on the ground"}, {"tokens": ["a", "woman", "in", "a", "tank", "top", "is", "lying", "on", "the", "grass", "next", "to", "the", "other", "woman", "in", "front", "of", "a", "laptop"], "raw": "A woman in a tank top is lying on the grass next to the other woman in front of a laptop", "sent_id": 84699, "sent": "a woman in a tank top is lying on the grass next to the other woman in front of a laptop"}], "file_name": "COCO_train2014_000000101573_449814.jpg", "ann_id": 449814, "sent_ids": [84698, 84699], "ref_id": 37518}, {"segmentation": [[0.15, 258.16, 0.15, 313.02, 22.52, 307.16, 25.72, 323.68, 27.85, 350.84, 31.58, 373.75, 35.31, 373.22, 40.1, 333.8, 50.22, 301.84, 53.95, 278.4, 51.29, 262.42, 64.07, 238.98, 68.87, 215.54, 74.73, 188.91, 88.04, 188.91, 96.57, 192.1, 100.29, 176.12, 94.43, 173.46, 87.51, 164.93, 74.19, 156.41, 69.4, 160.67, 67.8, 169.2, 57.68, 178.78, 48.62, 203.82, 36.9, 224.6, 21.99, 235.78, 11.34, 247.5]], "area": 6787.7198499999995, "iscrowd": 0, "image_id": 510611, "bbox": [0.15, 156.41, 100.14, 217.34], "category_id": 25, "id": 596498, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "on", "the", "far", "left"], "raw": "The giraffe on the far left.", "sent_id": 84746, "sent": "the giraffe on the far left"}, {"tokens": ["giraffe", "standing", "to", "the", "left", "of", "a", "tree"], "raw": "Giraffe standing to the left of a tree.", "sent_id": 84747, "sent": "giraffe standing to the left of a tree"}], "file_name": "COCO_train2014_000000510611_596498.jpg", "ann_id": 596498, "sent_ids": [84746, 84747], "ref_id": 37543}, {"segmentation": [[329.33, 318.48, 321.02, 274.67, 309.93, 173.75, 307.71, 127.18, 313.81, 122.74, 327.67, 125.51, 344.86, 124.4, 365.37, 124.4, 381.45, 129.95, 391.99, 161.0, 395.32, 168.76, 391.44, 189.28, 391.99, 218.67, 390.33, 263.03, 389.22, 309.05, 380.9, 322.91, 372.03, 325.13, 365.37, 319.03, 365.37, 310.71, 375.91, 309.6, 374.25, 263.58, 372.58, 224.21, 363.16, 208.69, 354.84, 207.02, 352.07, 271.34, 354.84, 305.17, 351.51, 312.38], [269.45, 207.58, 281.65, 242.51, 285.53, 285.76, 302.72, 291.31, 278.32, 206.47]], "area": 13015.3952, "iscrowd": 0, "image_id": 27070, "bbox": [269.45, 122.74, 125.87, 202.39], "category_id": 22, "id": 583621, "split": "val", "sentences": [{"tokens": ["the", "smaller", "elephant"], "raw": "the smaller elephant", "sent_id": 84874, "sent": "the smaller elephant"}], "file_name": "COCO_train2014_000000027070_583621.jpg", "ann_id": 583621, "sent_ids": [84874], "ref_id": 37596}, {"segmentation": [[206.95, 364.88, 236.21, 345.37, 243.79, 324.79, 264.38, 322.62, 366.23, 355.12, 379.23, 359.46, 388.98, 403.88, 393.32, 437.47, 385.73, 452.64, 291.47, 473.23, 302.3, 429.89, 306.64, 422.3, 250.29, 399.55]], "area": 15693.75395, "iscrowd": 0, "image_id": 580979, "bbox": [206.95, 322.62, 186.37, 150.61], "category_id": 15, "id": 572757, "split": "val", "sentences": [{"tokens": ["a", "bench", "next", "to", "a", "green", "suitcase"], "raw": "A bench next to a green suitcase.", "sent_id": 84889, "sent": "a bench next to a green suitcase"}], "file_name": "COCO_train2014_000000580979_572757.jpg", "ann_id": 572757, "sent_ids": [84889], "ref_id": 37599}, {"segmentation": [[28.15, 215.3, 50.21, 202.37, 71.51, 165.85, 92.81, 146.07, 95.1, 127.81, 101.18, 112.59, 114.88, 113.36, 123.25, 122.48, 134.66, 122.48, 124.77, 128.57, 123.25, 135.42, 137.7, 141.5, 143.79, 152.92, 135.42, 188.67, 127.05, 202.37, 136.94, 220.63, 159.76, 245.73, 180.3, 251.82, 171.17, 260.19, 153.68, 260.19, 153.68, 247.25, 126.29, 215.3, 106.51, 221.39, 85.97, 229.75, 66.95, 241.93, 69.23, 260.19, 70.75, 263.99, 60.1, 263.99, 60.1, 244.21, 47.17, 278.44, 38.04, 278.44, 53.25, 245.73, 29.67, 214.54]], "area": 8450.2477, "iscrowd": 0, "image_id": 315221, "bbox": [28.15, 112.59, 152.15, 165.85], "category_id": 16, "id": 37705, "split": "val", "sentences": [{"tokens": ["bird", "on", "left", "in", "photo"], "raw": "bird on left in photo", "sent_id": 84899, "sent": "bird on left in photo"}, {"tokens": ["a", "bird", "that", "is", "off", "the", "ground"], "raw": "A bird that is off the ground.", "sent_id": 84900, "sent": "a bird that is off the ground"}], "file_name": "COCO_train2014_000000315221_37705.jpg", "ann_id": 37705, "sent_ids": [84899, 84900], "ref_id": 37603}, {"segmentation": [[0.0, 69.62, 12.5, 76.47, 19.04, 84.26, 25.58, 90.49, 28.39, 98.58, 31.81, 108.55, 37.42, 114.78, 43.03, 121.63, 45.52, 127.55, 48.63, 135.33, 55.17, 144.99, 59.84, 152.77, 63.27, 165.86, 63.27, 177.07, 62.65, 183.92, 71.37, 184.54, 86.63, 190.77, 95.04, 191.71, 102.2, 200.74, 111.85, 209.15, 117.15, 212.57, 122.76, 209.15, 133.34, 209.15, 137.7, 211.33, 143.62, 217.87, 155.46, 239.98, 161.06, 250.57, 167.6, 271.44, 164.18, 277.98, 161.37, 286.7, 163.24, 292.3, 166.36, 301.65, 170.09, 307.56, 172.59, 310.68, 174.45, 315.04, 167.6, 328.74, 163.87, 337.15, 157.33, 343.07, 155.46, 348.67, 153.59, 357.08, 150.47, 365.18, 147.36, 369.85, 138.95, 374.21, 132.41, 383.56, 0.0, 356.77]], "area": 33004.3616, "iscrowd": 0, "image_id": 278549, "bbox": [0.0, 69.62, 174.45, 313.94], "category_id": 1, "id": 1715706, "split": "val", "sentences": [{"tokens": ["a", "little", "boy", "putting", "finger", "into", "the", "mouth"], "raw": "A little boy putting finger into the mouth", "sent_id": 84923, "sent": "a little boy putting finger into the mouth"}, {"tokens": ["a", "boy", "licking", "his", "fingers"], "raw": "A boy licking his fingers", "sent_id": 84924, "sent": "a boy licking his fingers"}], "file_name": "COCO_train2014_000000278549_1715706.jpg", "ann_id": 1715706, "sent_ids": [84923, 84924], "ref_id": 37612}, {"segmentation": [[308.87, 417.65, 308.87, 417.65, 291.67, 461.32, 291.67, 495.73, 275.78, 524.84, 270.49, 572.49, 245.35, 588.37, 224.17, 589.69, 214.91, 583.07, 246.67, 549.99, 238.73, 540.72, 247.99, 530.14, 245.35, 494.41, 253.29, 449.41, 246.67, 430.88, 228.14, 426.91, 236.08, 422.94, 246.67, 395.15, 247.99, 318.39, 251.96, 303.83, 234.76, 306.48, 221.52, 289.28, 225.49, 233.69, 263.87, 187.37, 274.46, 184.73, 270.49, 168.84, 269.17, 160.9, 267.84, 154.29, 273.14, 133.11, 283.73, 126.5, 303.58, 123.85, 312.84, 141.05, 316.81, 166.2, 324.75, 193.99, 355.19, 196.64, 392.25, 240.31, 368.42, 261.48, 357.84, 266.78, 364.45, 295.89, 375.04, 325.01, 375.04, 362.06, 382.98, 403.09, 394.89, 426.91, 380.33, 446.76, 408.13, 547.34, 424.01, 581.75, 439.0, 601.6, 408.13, 604.25, 373.72, 561.9, 343.28, 502.35, 314.16, 385.88, 307.55, 395.15]], "area": 49010.42950000001, "iscrowd": 0, "image_id": 65011, "bbox": [214.91, 123.85, 224.09, 480.4], "category_id": 1, "id": 443858, "split": "val", "sentences": [{"tokens": ["the", "heavier", "man", "is", "making", "a", "phone", "call"], "raw": "The heavier man is making a phone call.", "sent_id": 85109, "sent": "the heavier man is making a phone call"}, {"tokens": ["a", "man", "with", "a", "mobile", "to", "his", "ear"], "raw": "A man with a mobile to his ear.", "sent_id": 85110, "sent": "a man with a mobile to his ear"}], "file_name": "COCO_train2014_000000065011_443858.jpg", "ann_id": 443858, "sent_ids": [85109, 85110], "ref_id": 37680}, {"segmentation": [[222.3, 605.14, 222.3, 590.04, 242.88, 566.72, 263.46, 546.13, 296.39, 529.67, 326.58, 521.43, 356.77, 513.2, 400.68, 510.46, 462.43, 510.46, 483.01, 510.46, 507.71, 511.83, 526.92, 521.43, 557.11, 526.92, 581.81, 537.9, 606.51, 550.25, 612.0, 553.0, 612.0, 612.0, 220.92, 612.0]], "area": 33456.890250000004, "iscrowd": 0, "image_id": 5587, "bbox": [220.92, 510.46, 391.08, 101.54], "category_id": 51, "id": 1040605, "split": "val", "sentences": [{"tokens": ["a", "plate", "with", "four", "biscuits", ",", "sitting", "under", "two", "other", "plates"], "raw": "A plate with four biscuits, sitting under two other plates.", "sent_id": 85200, "sent": "a plate with four biscuits , sitting under two other plates"}, {"tokens": ["the", "muffins", "on", "the", "bottom", "of", "the", "photo"], "raw": "The muffins on the bottom of the photo.", "sent_id": 85201, "sent": "the muffins on the bottom of the photo"}], "file_name": "COCO_train2014_000000005587_1040605.jpg", "ann_id": 1040605, "sent_ids": [85200, 85201], "ref_id": 37712}, {"segmentation": [[61.62, 84.86, 61.62, 84.86, 64.86, 134.59, 64.86, 134.59, 132.97, 212.43, 202.16, 210.27, 234.59, 208.11, 295.14, 143.24, 285.41, 74.05, 252.97, 22.16, 218.38, 4.86, 120.0, 0.54, 76.76, 34.05, 68.11, 55.68]], "area": 39275.185249999995, "iscrowd": 0, "image_id": 87792, "bbox": [61.62, 0.54, 233.52, 211.89], "category_id": 60, "id": 1082048, "split": "val", "sentences": [{"tokens": ["the", "filled", "donut", "upper", "left"], "raw": "the filled donut upper left", "sent_id": 85258, "sent": "the filled donut upper left"}, {"tokens": ["the", "donut", "on", "the", "top", "left"], "raw": "The donut on the top left.", "sent_id": 85259, "sent": "the donut on the top left"}], "file_name": "COCO_train2014_000000087792_1082048.jpg", "ann_id": 1082048, "sent_ids": [85258, 85259], "ref_id": 37734}, {"segmentation": [[377.95, 341.08, 411.04, 368.66, 423.91, 400.83, 418.39, 455.97, 405.52, 489.98, 393.58, 492.74, 385.3, 506.52, 366.92, 535.93, 336.59, 541.45, 331.08, 550.64, 383.46, 571.78, 390.82, 586.49, 390.82, 603.03, 368.76, 604.87, 364.16, 586.49, 355.89, 580.05, 335.67, 575.46, 335.67, 626.93, 320.05, 640.0, 319.13, 553.4, 328.32, 534.1, 322.8, 524.91, 314.53, 514.8, 330.16, 462.41, 349.46, 423.8, 360.49, 407.26, 361.41, 380.61, 360.49, 354.87, 368.76, 344.76]], "area": 15427.276799999996, "iscrowd": 0, "image_id": 28281, "bbox": [314.53, 341.08, 109.38, 298.92], "category_id": 62, "id": 2192172, "split": "val", "sentences": [{"tokens": ["a", "chair", "which", "is", "girl", "sitting"], "raw": "A chair which is girl sitting", "sent_id": 85301, "sent": "a chair which is girl sitting"}, {"tokens": ["a", "chair", "on", "which", "a", "girl", "is", "sitting"], "raw": "A chair on which a girl is sitting", "sent_id": 85302, "sent": "a chair on which a girl is sitting"}], "file_name": "COCO_train2014_000000028281_2192172.jpg", "ann_id": 2192172, "sent_ids": [85301, 85302], "ref_id": 37754}, {"segmentation": [[38.83, 359.55, 38.83, 378.25, 38.83, 386.88, 40.27, 408.45, 41.71, 421.39, 43.15, 438.65, 43.15, 454.47, 43.15, 480.36, 44.58, 497.62, 47.46, 506.25, 54.65, 516.31, 57.53, 529.26, 56.09, 549.39, 51.78, 565.21, 44.58, 578.16, 38.83, 592.54, 21.57, 581.03, 15.82, 576.72, 2.88, 566.65, 1.44, 386.88, 1.44, 325.03, 1.44, 273.26, 11.51, 235.87, 23.01, 240.18, 35.96, 248.81, 27.33, 253.12, 10.07, 261.75, 10.07, 280.45, 14.38, 299.15, 17.26, 310.65, 20.13, 317.84, 7.19, 348.04, 15.82, 365.3, 25.89, 371.06]], "area": 10993.885449999996, "iscrowd": 0, "image_id": 102662, "bbox": [1.44, 235.87, 56.09, 356.67], "category_id": 64, "id": 26164, "split": "val", "sentences": [{"tokens": ["a", "white", "vase", "that", "is", "located", "on", "the", "edge", "of", "the", "picture"], "raw": "A white vase that is located on the edge of the picture.", "sent_id": 85303, "sent": "a white vase that is located on the edge of the picture"}, {"tokens": ["white", "cylinder", "to", "the", "left", "of", "the", "vase"], "raw": "white cylinder to the left of the vase", "sent_id": 85304, "sent": "white cylinder to the left of the vase"}], "file_name": "COCO_train2014_000000102662_26164.jpg", "ann_id": 26164, "sent_ids": [85303, 85304], "ref_id": 37755}, {"segmentation": [[78.83, 69.57, 89.76, 56.08, 108.39, 45.79, 122.53, 54.79, 126.38, 51.26, 136.05, 57.25, 145.73, 48.04, 166.92, 41.13, 173.84, 54.03, 178.44, 52.19, 190.42, 46.2, 194.11, 52.19, 189.5, 59.56, 175.68, 67.85, 175.68, 82.6, 186.74, 86.74, 209.77, 101.49, 213.92, 92.73, 218.07, 83.52, 213.0, 73.38, 224.06, 56.33, 244.79, 54.49, 262.3, 50.34, 266.9, 72.46, 268.75, 96.88, 265.52, 101.49, 263.22, 101.49, 265.98, 115.77, 266.9, 145.26, 263.68, 154.93, 251.24, 162.3, 205.17, 166.91, 186.74, 147.1, 173.84, 150.32, 173.84, 164.15, 170.15, 165.53, 141.58, 165.99, 121.31, 165.99, 88.14, 167.37, 72.47, 166.91, 61.87, 165.07, 59.11, 156.31, 56.35, 137.88, 55.42, 116.69, 60.95, 108.86, 60.95, 102.87, 69.25, 97.8, 89.52, 95.5, 95.97, 87.66, 101.04, 79.83, 94.13, 72.46, 78.46, 79.37, 72.01, 81.67, 64.18, 73.84, 71.55, 72.0]], "area": 20495.916350000003, "iscrowd": 0, "image_id": 174892, "bbox": [55.42, 41.13, 213.33, 126.24], "category_id": 52, "id": 2110741, "split": "val", "sentences": [{"tokens": ["container", "with", "bananas", "and", "blueberries"], "raw": "container with bananas and blueberries", "sent_id": 85336, "sent": "container with bananas and blueberries"}, {"tokens": ["a", "bowl", "of", "banana", "slices", "and", "blueberries"], "raw": "A bowl of banana slices and blueberries.", "sent_id": 85337, "sent": "a bowl of banana slices and blueberries"}], "file_name": "COCO_train2014_000000174892_2110741.jpg", "ann_id": 2110741, "sent_ids": [85336, 85337], "ref_id": 37764}, {"segmentation": [[41.8, 5.48, 70.74, 165.17, 70.74, 182.32, 1.07, 329.15, 2.14, 1.2], [0.0, 398.82, 32.15, 469.55, 1.07, 472.77, 0.0, 422.39]], "area": 16202.065949999998, "iscrowd": 0, "image_id": 151729, "bbox": [0.0, 1.2, 70.74, 471.57], "category_id": 15, "id": 1392487, "split": "val", "sentences": [{"tokens": ["the", "bench", "next", "to", "the", "one", "the", "kids", "are", "sitting", "on"], "raw": "The bench next to the one the kids are sitting on", "sent_id": 85371, "sent": "the bench next to the one the kids are sitting on"}, {"tokens": ["the", "bench", "with", "no", "one", "seen", "on", "it"], "raw": "The bench with no one seen on it", "sent_id": 85372, "sent": "the bench with no one seen on it"}], "file_name": "COCO_train2014_000000151729_1392487.jpg", "ann_id": 1392487, "sent_ids": [85371, 85372], "ref_id": 37778}, {"segmentation": [[171.51, 88.45, 171.51, 49.62, 171.51, 21.57, 171.51, 17.26, 206.02, 12.94, 218.97, 10.79, 237.3, 9.71, 256.72, 9.71, 270.74, 10.79, 277.21, 36.67, 282.61, 55.01, 284.76, 67.96, 279.37, 94.92, 279.37, 125.12, 279.37, 152.09, 277.21, 156.4, 232.99, 154.25, 204.94, 155.33, 180.13, 155.33, 173.66, 103.55], [272.9, 15.1, 334.38, 33.44, 362.43, 42.07, 381.84, 51.78, 391.55, 53.93, 402.34, 62.56, 408.81, 72.27, 384.0, 80.9, 363.51, 76.58, 340.85, 76.58, 311.73, 73.35, 284.76, 71.19]], "area": 20004.645, "iscrowd": 0, "image_id": 569889, "bbox": [171.51, 9.71, 237.3, 146.69], "category_id": 6, "id": 163556, "split": "val", "sentences": [{"tokens": ["white", "bus", "on", "a", "road"], "raw": "White bus on a road", "sent_id": 85491, "sent": "white bus on a road"}, {"tokens": ["white", "hj", "buss", "bus"], "raw": "White HJ Buss bus.", "sent_id": 85492, "sent": "white hj buss bus"}], "file_name": "COCO_train2014_000000569889_163556.jpg", "ann_id": 163556, "sent_ids": [85491, 85492], "ref_id": 37821}, {"segmentation": [[485.65, 73.67, 492.6, 98.55, 517.84, 128.18, 546.01, 151.96, 548.2, 163.3, 519.3, 191.1, 503.57, 204.27, 499.55, 205.0, 490.77, 210.13, 487.84, 194.03, 501.01, 182.32, 522.6, 165.13, 507.96, 152.33, 495.16, 150.5, 486.01, 161.84, 468.82, 135.5, 458.21, 123.79, 476.14, 113.18, 486.38, 77.7], [383.05, 285.69, 377.09, 268.82, 365.18, 283.71, 365.18, 255.92, 377.09, 250.95, 386.02, 281.72]], "area": 4452.1779000000015, "iscrowd": 0, "image_id": 8856, "bbox": [365.18, 73.67, 183.02, 212.02], "category_id": 1, "id": 1253902, "split": "val", "sentences": [{"tokens": ["person", "in", "dark", "brown", "sweater", "behind", "blonde"], "raw": "person in dark brown sweater behind blonde", "sent_id": 85503, "sent": "person in dark brown sweater behind blonde"}], "file_name": "COCO_train2014_000000008856_1253902.jpg", "ann_id": 1253902, "sent_ids": [85503], "ref_id": 37828}, {"segmentation": [[215.8, 261.85, 275.74, 241.14, 285.55, 236.78, 292.09, 238.96, 295.36, 225.88, 304.08, 230.24, 304.08, 244.41, 311.71, 254.22, 311.71, 269.47, 296.45, 271.65, 285.55, 260.76, 217.98, 292.36, 210.35, 296.72, 210.35, 318.52, 207.08, 334.87, 195.09, 345.77, 183.1, 351.22, 188.55, 328.33, 199.45, 296.72, 204.9, 274.92, 210.35, 267.29], [117.71, 317.43, 105.72, 340.32, 107.9, 368.65, 98.09, 391.54, 101.36, 410.07, 112.26, 371.92, 112.26, 406.8, 105.72, 465.65, 116.62, 467.83, 117.71, 454.76, 128.61, 467.83, 129.7, 463.47, 130.79, 390.45, 153.67, 355.58, 162.39, 349.04, 167.84, 306.53, 161.3, 298.9, 141.69, 307.62, 125.34, 307.62, 112.26, 320.7]], "area": 9409.485049999996, "iscrowd": 0, "image_id": 177353, "bbox": [98.09, 225.88, 213.62, 241.95], "category_id": 25, "id": 600268, "split": "val", "sentences": [{"tokens": ["a", "small", "giraffe", "leaning", "over", "a", "car", "behind", "a", "larger", "giraffe"], "raw": "A small giraffe leaning over a car behind a larger giraffe", "sent_id": 85522, "sent": "a small giraffe leaning over a car behind a larger giraffe"}], "file_name": "COCO_train2014_000000177353_600268.jpg", "ann_id": 600268, "sent_ids": [85522], "ref_id": 37837}, {"segmentation": [[470.27, 342.16, 468.11, 337.84, 465.95, 325.95, 463.78, 314.05, 463.78, 306.49, 463.78, 301.08, 463.78, 292.43, 463.78, 289.19, 467.03, 276.22, 469.19, 267.57, 470.27, 258.92, 473.51, 253.51, 476.76, 247.03, 480.0, 243.78, 491.89, 239.46, 495.14, 236.22, 496.22, 226.49, 496.22, 215.68, 496.22, 211.35, 500.54, 201.62, 503.78, 198.38, 507.03, 197.3, 511.35, 197.3, 523.24, 198.38, 528.65, 201.62, 531.89, 207.03, 534.05, 212.43, 536.22, 220.0, 534.05, 227.57, 527.57, 235.14, 527.57, 242.7, 532.97, 256.76, 537.3, 265.41, 543.78, 278.38, 547.03, 289.19, 552.43, 302.16, 553.51, 308.65, 555.68, 319.46, 554.59, 331.35, 556.76, 337.84, 569.73, 350.81, 576.22, 357.3, 582.7, 364.86, 585.95, 378.92, 587.03, 392.97, 587.03, 399.46, 588.11, 421.08, 588.11, 428.65, 593.51, 438.38, 597.84, 444.86, 605.41, 452.43, 605.41, 462.16, 591.35, 456.76, 582.7, 455.68, 570.81, 449.19, 567.57, 444.86, 563.24, 430.81, 560.0, 417.84, 557.84, 399.46, 557.84, 397.3, 553.51, 378.92, 551.35, 372.43, 541.62, 357.3, 530.81, 342.16, 520.0, 332.43, 513.51, 340.0, 525.41, 357.3, 534.05, 367.03, 540.54, 377.84, 543.78, 394.05, 544.86, 408.11, 548.11, 423.24, 553.51, 443.78, 561.08, 462.16, 562.16, 474.05, 542.7, 470.81, 534.05, 461.08, 528.65, 447.03, 522.16, 437.3, 515.68, 414.59, 505.95, 382.16, 499.46, 375.68, 483.24, 364.86, 471.35, 358.38, 467.03, 350.81, 463.78, 342.16]], "area": 17404.6546, "iscrowd": 0, "image_id": 449158, "bbox": [463.78, 197.3, 141.63, 276.75], "category_id": 1, "id": 201635, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "in", "a", "white", "shirt"], "raw": "A man sitting in a white shirt.", "sent_id": 85583, "sent": "a man sitting in a white shirt"}, {"tokens": ["man", "in", "white", "shirt"], "raw": "Man in white shirt.", "sent_id": 85584, "sent": "man in white shirt"}], "file_name": "COCO_train2014_000000449158_201635.jpg", "ann_id": 201635, "sent_ids": [85583, 85584], "ref_id": 37864}, {"segmentation": [[29.74, 220.08, 79.05, 213.92, 96.52, 145.09, 142.74, 142.0, 222.87, 142.0, 260.88, 149.2, 283.48, 185.15, 317.38, 270.42, 325.6, 322.81, 319.43, 373.15, 311.21, 384.44, 285.53, 385.48, 280.4, 368.01, 148.91, 366.98, 141.71, 406.02, 119.12, 409.1, 106.79, 401.91, 94.46, 353.63, 73.91, 353.63, 68.77, 372.12, 46.18, 364.93, 38.98, 332.05, 28.71, 263.22]], "area": 58500.848500000015, "iscrowd": 0, "image_id": 327271, "bbox": [28.71, 142.0, 296.89, 267.1], "category_id": 8, "id": 399963, "split": "val", "sentences": [{"tokens": ["white", "pickup", "truck", "parked", "on", "the", "side", "of", "the", "road"], "raw": "White pickup truck parked on the side of the road.", "sent_id": 85632, "sent": "white pickup truck parked on the side of the road"}, {"tokens": ["a", "pickup", "vehicle"], "raw": "a pickup vehicle", "sent_id": 85633, "sent": "a pickup vehicle"}], "file_name": "COCO_train2014_000000327271_399963.jpg", "ann_id": 399963, "sent_ids": [85632, 85633], "ref_id": 37885}, {"segmentation": [[8.29, 310.61, 69.19, 319.9, 131.13, 295.13, 151.77, 264.16, 165.19, 256.93, 217.84, 267.26, 263.26, 327.13, 287.0, 349.84, 301.45, 370.48, 275.65, 398.35, 247.77, 391.13, 219.9, 402.48, 211.65, 431.39, 112.55, 476.81, 0.0, 479.9, 0.03, 310.61, 1.06, 309.58]], "area": 43636.110349999995, "iscrowd": 0, "image_id": 136651, "bbox": [0.0, 256.93, 301.45, 222.97], "category_id": 21, "id": 71103, "split": "val", "sentences": [{"tokens": ["a", "large", "animal", "with", "long", "ears", "in", "an", "enclosure", "that", "people", "are", "looking", "at"], "raw": "A large animal with long ears in an enclosure that people are looking at.", "sent_id": 85670, "sent": "a large animal with long ears in an enclosure that people are looking at"}, {"tokens": ["white", "animal", "fenced", "in"], "raw": "White animal fenced in.", "sent_id": 85671, "sent": "white animal fenced in"}], "file_name": "COCO_train2014_000000136651_71103.jpg", "ann_id": 71103, "sent_ids": [85670, 85671], "ref_id": 37898}, {"segmentation": [[293.56, 361.59, 279.74, 374.84, 260.73, 381.75, 237.69, 384.63, 223.86, 380.02, 185.84, 287.28, 189.87, 275.76, 201.39, 263.66, 191.6, 239.46, 172.02, 187.04, 173.17, 178.4, 177.78, 172.64, 180.66, 177.83, 191.6, 175.52, 192.18, 175.52, 195.63, 190.5, 200.82, 187.04, 198.51, 176.68, 201.97, 176.68, 211.19, 183.01, 215.22, 177.83, 242.87, 249.26, 262.46, 252.14, 282.62, 262.51, 298.75, 281.52, 306.81, 306.86, 307.96, 332.78, 302.2, 350.07, 300.47, 351.22]], "area": 15638.2204, "iscrowd": 0, "image_id": 261696, "bbox": [172.02, 172.64, 135.94, 211.99], "category_id": 86, "id": 1151505, "split": "val", "sentences": [{"tokens": ["a", "white", "round", "vase", "with", "a", "long", "neck"], "raw": "A white round vase with a long neck.", "sent_id": 85674, "sent": "a white round vase with a long neck"}, {"tokens": ["a", "flower", "vase", "that", "is", "round", "at", "the", "bottom", "and", "a", "narrow", "cylinder", "at", "the", "top"], "raw": "A flower vase that is round at the bottom and a narrow cylinder at the top.", "sent_id": 85675, "sent": "a flower vase that is round at the bottom and a narrow cylinder at the top"}], "file_name": "COCO_train2014_000000261696_1151505.jpg", "ann_id": 1151505, "sent_ids": [85674, 85675], "ref_id": 37900}, {"segmentation": [[317.41, 182.26, 338.15, 185.3, 356.86, 184.79, 365.46, 184.28, 380.13, 182.26, 377.6, 237.4, 382.15, 249.54, 393.79, 243.47, 387.21, 278.88, 387.72, 302.65, 388.22, 327.94, 384.18, 333.51, 377.6, 342.1, 377.6, 345.65, 382.66, 355.76, 374.06, 363.35, 373.05, 374.48, 376.59, 379.03, 386.71, 379.03, 397.83, 373.47, 405.42, 364.87, 408.46, 356.77, 411.49, 347.67, 417.06, 333.0, 417.06, 322.88, 430.21, 367.4, 435.77, 369.93, 440.83, 384.59, 454.49, 380.04, 457.02, 370.94, 460.56, 347.16, 453.48, 328.95, 444.88, 301.13, 444.48, 297.19, 448.42, 286.16, 450.39, 271.57, 450.39, 264.08, 447.64, 249.9, 442.51, 238.47, 442.12, 217.97, 439.36, 203.78, 439.36, 193.93, 439.36, 184.47, 435.42, 175.41, 432.26, 162.4, 426.75, 148.6, 420.05, 140.33, 415.71, 132.84, 414.53, 122.59, 410.19, 114.32, 403.1, 111.95, 388.91, 115.5, 381.42, 123.38, 379.45, 129.69, 382.6, 136.39, 388.12, 142.3, 392.46, 147.03, 388.52, 147.82, 371.96, 153.73, 346.34, 160.43, 329.4, 162.79, 321.91, 160.43, 316.0, 156.49, 309.3, 154.52, 305.75, 164.37, 303.78, 167.52, 306.54, 170.68, 308.11, 171.07, 311.27, 173.43, 312.06, 173.43, 316.39, 181.32]], "area": 16715.13355, "iscrowd": 0, "image_id": 109095, "bbox": [303.78, 111.95, 156.78, 272.64], "category_id": 1, "id": 199654, "split": "val", "sentences": [{"tokens": ["man", "pulling", "a", "lever", "near", "a", "track"], "raw": "man pulling a lever near a track", "sent_id": 85704, "sent": "man pulling a lever near a track"}, {"tokens": ["person", "dressed", "in", "all", "black", "in", "the", "foreground"], "raw": "Person dressed in all black in the foreground.", "sent_id": 85705, "sent": "person dressed in all black in the foreground"}], "file_name": "COCO_train2014_000000109095_199654.jpg", "ann_id": 199654, "sent_ids": [85704, 85705], "ref_id": 37911}, {"segmentation": [[120.77, 18.98, 113.45, 11.45, 106.94, 0.26, 162.89, 0.0, 164.31, 0.0, 160.45, 4.13, 157.39, 8.2, 152.51, 10.44, 156.99, 16.95, 181.6, 31.19, 186.89, 49.9, 191.98, 84.9, 193.41, 120.1, 191.78, 136.58, 189.95, 148.58, 181.6, 154.07, 175.91, 154.07, 173.87, 151.22, 171.23, 150.0, 169.6, 146.34, 172.04, 141.46, 181.4, 127.62, 179.37, 107.89, 172.86, 88.15, 170.62, 94.66, 172.25, 109.92, 172.25, 114.2, 170.41, 135.56, 167.57, 148.17, 163.09, 187.85, 162.07, 198.63, 156.58, 199.85, 164.72, 226.09, 164.31, 247.25, 164.51, 257.43, 168.58, 266.17, 168.99, 274.11, 169.8, 281.84, 156.58, 286.72, 147.42, 285.5, 144.58, 281.03, 142.95, 270.65, 143.15, 259.46, 144.78, 251.12, 139.29, 252.95, 128.71, 258.44, 119.35, 261.9, 110.6, 261.9, 104.7, 258.24, 101.44, 252.75, 100.83, 246.03, 108.16, 242.17, 111.62, 237.28, 112.23, 233.42, 105.51, 218.36, 100.22, 205.14, 97.99, 199.44, 97.38, 191.91, 100.63, 159.77, 102.06, 144.1, 103.28, 123.76, 104.7, 103.62, 105.11, 91.61, 104.29, 84.08, 96.16, 92.22, 84.97, 100.56, 70.11, 109.52, 60.55, 114.4, 56.89, 113.38, 53.43, 109.31, 52.21, 104.02, 51.6, 99.95, 53.02, 98.33, 54.45, 98.33, 59.13, 99.55, 61.57, 99.55, 65.03, 99.55, 63.81, 97.51, 56.89, 95.48, 56.89, 92.83, 58.72, 92.02, 63.81, 91.21, 75.0, 92.63, 84.97, 81.64, 94.12, 71.88, 95.54, 67.2, 99.82, 49.7, 101.44, 34.65, 102.26, 27.93, 109.79, 21.63, 114.47, 20.81, 119.55, 19.59]], "area": 19961.058750000004, "iscrowd": 0, "image_id": 240225, "bbox": [51.6, 0.0, 141.81, 286.72], "category_id": 1, "id": 530947, "split": "val", "sentences": [{"tokens": ["the", "toddler", "boy", "kicking", "the", "soccer", "ball"], "raw": "The toddler boy kicking the soccer ball.", "sent_id": 85771, "sent": "the toddler boy kicking the soccer ball"}, {"tokens": ["a", "young", "boy", "in", "a", "red", "&", "white", "outfit", "playing", "with", "a", "soccer", "ball"], "raw": "A young boy in a red & white outfit playing with a soccer ball", "sent_id": 85772, "sent": "a young boy in a red & white outfit playing with a soccer ball"}], "file_name": "COCO_train2014_000000240225_530947.jpg", "ann_id": 530947, "sent_ids": [85771, 85772], "ref_id": 37939}, {"segmentation": [[163.25, 322.65, 185.73, 373.69, 188.63, 398.58, 179.92, 419.33, 173.28, 438.41, 189.05, 456.67, 167.06, 460.82, 148.39, 455.42, 147.56, 447.13, 147.56, 431.77, 154.2, 427.21, 148.39, 395.27, 145.48, 379.5, 135.94, 367.05, 123.5, 401.07, 116.03, 413.52, 113.54, 435.09, 118.52, 450.03, 101.09, 445.88, 87.4, 437.17, 85.33, 432.19, 95.7, 422.65, 100.68, 382.4, 108.97, 362.9, 111.88, 353.78, 100.26, 316.02, 112.29, 283.25, 123.91, 265.82, 142.16, 238.44, 167.47, 213.55, 189.05, 229.31, 194.02, 239.27, 186.56, 253.79, 183.65, 264.99, 199.83, 250.47, 199.0, 242.17, 203.15, 237.61, 206.47, 231.8, 216.43, 244.25, 228.87, 251.72, 232.19, 260.43, 226.8, 262.5, 221.41, 260.01, 209.79, 267.07, 202.32, 267.07, 180.75, 295.28, 175.36, 295.28, 165.81, 311.46, 160.0, 311.46], [194.02, 224.33, 198.59, 215.21, 201.49, 202.35, 199.0, 195.71, 184.07, 192.39, 177.43, 194.46, 173.7, 195.29, 170.38, 205.67]], "area": 15713.40835, "iscrowd": 0, "image_id": 573360, "bbox": [85.33, 192.39, 146.86, 268.43], "category_id": 1, "id": 440006, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "baseball", "bat", "in", "a", "field"], "raw": "A man with a baseball bat in a field.", "sent_id": 85851, "sent": "a man with a baseball bat in a field"}, {"tokens": ["a", "man", "holding", "a", "baseball", "bat"], "raw": "A man holding a baseball bat.", "sent_id": 85852, "sent": "a man holding a baseball bat"}], "file_name": "COCO_train2014_000000573360_440006.jpg", "ann_id": 440006, "sent_ids": [85851, 85852], "ref_id": 37970}, {"segmentation": [[23.72, 321.27, 23.72, 321.27, 33.75, 307.58, 63.85, 296.64, 63.85, 287.52, 102.17, 272.92, 139.57, 281.13, 190.65, 272.01, 187.91, 298.46, 189.74, 338.6, 196.12, 365.05, 199.77, 397.89, 203.42, 417.05, 112.2, 416.14, 44.7, 424.35, 36.49, 424.35, 34.66, 377.82, 30.1, 377.82, 29.19, 359.58, 31.93, 357.76, 20.98, 347.72, 23.72, 318.53], [246.3, 410.66, 245.38, 396.98, 245.38, 378.74, 254.51, 368.7, 257.24, 380.56, 268.19, 392.42, 280.96, 392.42, 287.34, 384.21, 280.96, 375.09, 272.75, 357.76, 276.4, 348.63, 280.96, 347.72, 278.22, 333.13, 278.22, 327.65, 283.7, 319.44, 299.2, 312.15, 300.12, 278.39, 282.78, 269.27, 304.68, 269.27, 332.96, 269.27, 337.52, 284.78, 346.64, 290.25, 358.5, 297.55, 364.88, 303.94, 369.44, 315.79, 369.44, 326.74, 363.06, 333.13, 349.37, 333.13, 329.31, 332.21, 316.54, 333.13, 304.68, 336.77, 299.2, 344.98, 299.2, 350.46, 299.2, 362.32, 301.03, 368.7, 303.76, 378.74, 303.76, 387.86, 303.76, 403.37]], "area": 28634.751300000004, "iscrowd": 0, "image_id": 487284, "bbox": [20.98, 269.27, 348.46, 155.08], "category_id": 63, "id": 114936, "split": "val", "sentences": [{"tokens": ["a", "sofa", "in", "a", "hall"], "raw": "a sofa in a hall", "sent_id": 85862, "sent": "a sofa in a hall"}, {"tokens": ["couch", "behind", "lady", "in", "pink"], "raw": "couch behind lady in pink", "sent_id": 85863, "sent": "couch behind lady in pink"}], "file_name": "COCO_train2014_000000487284_114936.jpg", "ann_id": 114936, "sent_ids": [85862, 85863], "ref_id": 37974}, {"segmentation": [[60.26, 194.55, 64.0, 210.95, 69.63, 215.16, 73.37, 224.53, 82.74, 235.31, 97.73, 247.02, 125.84, 269.51, 148.33, 288.24, 163.32, 297.15, 181.59, 250.77, 184.4, 239.52, 189.08, 241.4, 191.89, 254.52, 195.17, 266.7, 194.7, 284.97, 196.11, 290.59, 301.98, 316.35, 316.03, 271.38, 320.25, 269.51, 316.5, 221.72, 251.45, 203.15, 243.3, 202.13, 230.58, 191.95, 203.09, 181.26, 187.3, 175.66, 178.65, 163.44, 168.47, 153.26, 150.65, 144.09, 149.63, 136.46, 135.89, 132.89, 129.78, 135.95, 119.09, 134.93, 90.07, 137.98, 77.34, 146.13, 68.18, 160.89, 62.58, 177.18]], "area": 27125.864800000003, "iscrowd": 0, "image_id": 209356, "bbox": [60.26, 132.89, 259.99, 183.46], "category_id": 54, "id": 308045, "split": "val", "sentences": [{"tokens": ["partially", "split", "sandwich", "to", "the", "left", "of", "two", "bags", "of", "chips"], "raw": "partially split sandwich to the left of two bags of chips", "sent_id": 85941, "sent": "partially split sandwich to the left of two bags of chips"}, {"tokens": ["the", "sandwich", "on", "the", "left", ",", "that", "'", "s", "partially", "bent", "apart"], "raw": "The sandwich on the left, that's partially bent apart.", "sent_id": 85942, "sent": "the sandwich on the left , that ' s partially bent apart"}], "file_name": "COCO_train2014_000000209356_308045.jpg", "ann_id": 308045, "sent_ids": [85941, 85942], "ref_id": 38003}, {"segmentation": [[333.8, 192.36, 359.26, 178.22, 393.21, 185.29, 420.08, 203.68, 432.81, 229.14, 439.88, 241.86, 478.07, 265.91, 463.93, 272.98, 448.37, 261.67, 442.71, 251.77, 428.57, 244.69, 413.01, 243.28, 388.96, 239.04, 360.68, 236.21, 345.12, 223.48, 338.05, 203.68, 332.39, 193.77], [424.32, 200.85, 428.57, 188.12, 421.5, 172.56, 415.84, 157.0, 444.13, 132.95, 478.07, 134.37, 490.8, 141.44, 452.61, 147.1, 452.61, 162.66, 445.54, 175.39, 456.86, 186.7, 438.47, 195.19, 429.98, 210.75, 425.74, 216.41, 420.08, 206.5], [207.92, 229.14, 200.85, 206.5, 198.02, 182.46, 189.53, 159.83, 182.46, 151.34, 178.22, 165.49, 178.22, 186.7, 179.63, 203.68, 183.87, 214.99, 192.36, 220.65, 200.85, 226.31, 203.68, 233.38, 207.92, 229.14]], "area": 8300.172100000002, "iscrowd": 0, "image_id": 100034, "bbox": [178.22, 132.95, 312.58, 140.03], "category_id": 43, "id": 659804, "split": "val", "sentences": [{"tokens": ["tennis", "bat", "with", "ball"], "raw": "tennis bat with ball", "sent_id": 86020, "sent": "tennis bat with ball"}], "file_name": "COCO_train2014_000000100034_659804.jpg", "ann_id": 659804, "sent_ids": [86020], "ref_id": 38036}, {"segmentation": [[415.49, 366.78, 420.27, 353.41, 424.09, 341.95, 425.04, 326.66, 425.04, 304.7, 426.96, 219.69, 420.27, 204.4, 419.31, 154.74, 411.67, 146.14, 418.36, 127.99, 420.27, 120.35, 427.91, 116.53, 440.33, 120.35, 453.7, 129.9, 461.34, 144.23, 468.03, 155.69, 471.85, 180.52, 480.44, 210.13, 487.13, 232.1, 492.86, 244.52, 498.59, 259.8, 498.59, 277.95, 502.41, 285.59, 485.22, 280.82, 470.89, 277.0, 454.65, 270.31, 454.65, 280.82, 454.65, 296.1, 452.74, 327.62, 445.1, 360.09, 438.42, 368.69, 431.73, 380.15, 417.4, 387.79, 411.67, 383.02, 414.54, 366.78]], "area": 11687.739099999997, "iscrowd": 0, "image_id": 355717, "bbox": [411.67, 116.53, 90.74, 271.26], "category_id": 1, "id": 1718307, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "the", "background", "jumping", "to", "return", "the", "tennis", "ball"], "raw": "A man in the background jumping to return the tennis ball.", "sent_id": 86029, "sent": "a man in the background jumping to return the tennis ball"}, {"tokens": ["the", "player", "that", "is", "out", "of", "focus"], "raw": "The player that is out of focus", "sent_id": 86030, "sent": "the player that is out of focus"}], "file_name": "COCO_train2014_000000355717_1718307.jpg", "ann_id": 1718307, "sent_ids": [86029, 86030], "ref_id": 38040}, {"segmentation": [[44.13, 333.63, 44.13, 325.02, 43.05, 316.41, 44.13, 307.8, 44.13, 300.27, 47.35, 292.74, 51.66, 290.58, 105.47, 289.51, 110.85, 286.28, 142.06, 279.82, 156.05, 101.17, 210.94, 109.78, 260.45, 109.78, 349.78, 140.99, 350.85, 143.14, 369.15, 213.09, 383.14, 298.12, 382.06, 334.71, 374.53, 346.55, 276.59, 377.76, 241.08, 364.84, 238.92, 368.07, 236.77, 376.68, 220.63, 380.99, 210.94, 379.91, 204.48, 374.53, 193.72, 364.84, 190.49, 361.61, 86.1, 342.24, 77.49, 350.85, 49.51, 347.62, 44.13, 337.94, 45.2, 318.57]], "area": 61606.10525, "iscrowd": 0, "image_id": 41233, "bbox": [43.05, 101.17, 340.09, 279.82], "category_id": 8, "id": 399852, "split": "val", "sentences": [{"tokens": ["a", "white", "tractor", "big", "rig", "with", "a", "blue", "rope", "around", "the", "bumper"], "raw": "a white tractor big rig with a blue rope around the bumper", "sent_id": 86065, "sent": "a white tractor big rig with a blue rope around the bumper"}, {"tokens": ["a", "white", "semi", "truck", "is", "parked", "by", "a", "black", "one", ",", "with", "a", "blue", "strap", "attached", "to", "the", "front"], "raw": "A white semi truck is parked by a black one, with a blue strap attached to the front.", "sent_id": 86066, "sent": "a white semi truck is parked by a black one , with a blue strap attached to the front"}], "file_name": "COCO_train2014_000000041233_399852.jpg", "ann_id": 399852, "sent_ids": [86065, 86066], "ref_id": 38051}, {"segmentation": [[30.2, 470.29, 30.2, 438.65, 33.08, 419.96, 33.08, 388.31, 31.64, 350.92, 41.71, 312.09, 47.46, 284.76, 63.28, 264.63, 77.66, 245.93, 100.67, 225.8, 133.75, 218.61, 172.58, 212.85, 179.78, 201.35, 194.16, 176.9, 224.36, 159.64, 231.55, 158.2, 261.75, 184.09, 263.19, 195.6, 280.45, 222.92, 263.19, 227.24, 254.56, 245.93, 257.44, 260.31, 257.44, 280.45, 268.94, 293.39, 276.13, 284.76, 267.51, 267.51, 260.31, 250.25, 261.75, 244.49, 291.96, 247.37, 327.91, 263.19, 335.1, 271.82, 314.97, 310.65, 291.96, 327.91, 227.24, 323.6, 218.61, 320.72, 214.29, 336.54, 204.22, 348.04, 240.18, 355.24, 277.57, 360.99, 306.34, 382.56, 293.39, 402.7, 276.13, 401.26, 221.48, 385.44, 188.4, 379.69, 175.46, 378.25, 179.78, 392.63, 179.78, 428.58, 176.9, 444.4, 178.34, 491.87, 186.97, 537.89, 182.65, 575.28, 182.65, 592.54, 176.9, 609.8, 182.65, 627.06, 148.13, 631.37, 148.13, 614.11, 148.13, 592.54, 136.63, 583.91, 133.75, 572.4, 129.44, 545.08, 126.56, 526.38, 115.06, 517.75, 71.91, 500.49, 41.71, 486.11, 34.52, 477.48]], "area": 66307.47279999999, "iscrowd": 0, "image_id": 547726, "bbox": [30.2, 158.2, 304.9, 473.17], "category_id": 1, "id": 438815, "split": "val", "sentences": [{"tokens": ["a", "child", "playing", "baseball"], "raw": "A child playing baseball.", "sent_id": 86067, "sent": "a child playing baseball"}, {"tokens": ["a", "boy", "in", "a", "red", "shirt", "throwing", "a", "baseball"], "raw": "A boy in a red shirt throwing a baseball.", "sent_id": 86068, "sent": "a boy in a red shirt throwing a baseball"}], "file_name": "COCO_train2014_000000547726_438815.jpg", "ann_id": 438815, "sent_ids": [86067, 86068], "ref_id": 38052}, {"segmentation": [[275.08, 419.35, 262.75, 407.02, 280.77, 370.97, 324.4, 351.05, 372.78, 334.93, 424.95, 352.95, 454.35, 370.02, 494.19, 400.38, 481.86, 420.21, 273.18, 420.21]], "area": 13773.559999999996, "iscrowd": 0, "image_id": 334600, "bbox": [262.75, 334.93, 231.44, 85.28], "category_id": 28, "id": 286487, "split": "val", "sentences": [{"tokens": ["a", "open", "red", "umbrella", "with", "a", "person", "laying", "on", "a", "towel", "in", "front", "of", "it"], "raw": "A open red umbrella with a person laying on a towel in front of it.", "sent_id": 86111, "sent": "a open red umbrella with a person laying on a towel in front of it"}, {"tokens": ["the", "top", "of", "a", "red", "umbrella", "on", "a", "beach"], "raw": "The top of a red umbrella on a beach.", "sent_id": 86112, "sent": "the top of a red umbrella on a beach"}], "file_name": "COCO_train2014_000000334600_286487.jpg", "ann_id": 286487, "sent_ids": [86111, 86112], "ref_id": 38069}, {"segmentation": [[23.4, 427.06, 12.39, 410.54, 17.89, 396.78, 41.29, 385.77, 71.57, 377.51, 103.23, 355.49, 119.74, 355.49, 123.87, 383.01, 107.35, 447.7, 112.86, 462.84, 132.13, 465.59, 163.78, 468.35, 192.69, 466.97, 213.33, 476.61, 207.83, 511.01, 187.18, 535.79, 151.4, 548.17, 125.25, 548.17, 79.83, 535.79, 101.85, 509.64, 108.73, 484.86, 107.35, 466.97, 82.58, 451.83, 64.69, 453.21, 42.67, 444.95]], "area": 15410.302199999993, "iscrowd": 0, "image_id": 100812, "bbox": [12.39, 355.49, 200.94, 192.68], "category_id": 62, "id": 111208, "split": "val", "sentences": [{"tokens": ["a", "white", "chair", "on", "the", "side", "of", "the", "table", "closest", "to", "the", "cat"], "raw": "A white chair on the side of the table closest to the cat.", "sent_id": 86162, "sent": "a white chair on the side of the table closest to the cat"}, {"tokens": ["the", "white", "chair", "on", "the", "left"], "raw": "The white chair on the left.", "sent_id": 86163, "sent": "the white chair on the left"}], "file_name": "COCO_train2014_000000100812_111208.jpg", "ann_id": 111208, "sent_ids": [86162, 86163], "ref_id": 38090}, {"segmentation": [[534.8, 227.71, 534.05, 256.49, 527.98, 261.04, 546.92, 260.28, 542.38, 249.68, 553.74, 218.62, 549.95, 212.56, 556.77, 223.16, 577.22, 221.65, 586.31, 243.62, 597.68, 233.77, 586.31, 224.68, 580.25, 217.1, 571.16, 219.38, 559.04, 217.1, 557.53, 207.25, 568.13, 195.89, 586.31, 173.92, 587.07, 152.71, 584.04, 141.35, 578.74, 130.75, 565.86, 126.2, 559.04, 124.69, 580.25, 123.93, 575.71, 117.87, 562.07, 115.6, 550.71, 111.05, 541.62, 109.54, 536.32, 110.29, 536.32, 130.75, 537.08, 151.96, 523.44, 163.32, 511.32, 191.35, 509.8, 204.22, 494.65, 218.62, 486.32, 235.28, 486.32, 238.31, 501.47, 230.74, 506.02, 235.28, 517.38, 223.16, 519.65, 228.47, 528.74, 222.41]], "area": 6963.454149999995, "iscrowd": 0, "image_id": 315221, "bbox": [486.32, 109.54, 111.36, 151.5], "category_id": 16, "id": 38010, "split": "val", "sentences": [{"tokens": ["the", "bird", "in", "front", "of", "the", "other", "bird"], "raw": "The bird in front of the other bird.", "sent_id": 86183, "sent": "the bird in front of the other bird"}, {"tokens": ["a", "gray", "bird", "on", "the", "right", "of", "another", "gray", "bird"], "raw": "A gray bird on the right of another gray bird.", "sent_id": 86184, "sent": "a gray bird on the right of another gray bird"}], "file_name": "COCO_train2014_000000315221_38010.jpg", "ann_id": 38010, "sent_ids": [86183, 86184], "ref_id": 38098}, {"segmentation": [[169.77, 420.06, 229.86, 456.11, 291.46, 480.15, 344.04, 501.18, 387.61, 517.71, 390.61, 553.77, 386.1, 586.82, 353.05, 594.33, 301.97, 570.29, 292.96, 546.25, 243.38, 522.22, 189.3, 486.16, 135.21, 453.11, 135.21, 430.57, 159.25, 421.56, 166.76, 426.07]], "area": 16558.34645000001, "iscrowd": 0, "image_id": 175116, "bbox": [135.21, 420.06, 255.4, 174.27], "category_id": 57, "id": 1061926, "split": "val", "sentences": [{"tokens": ["2", "carrots"], "raw": "2 carrots", "sent_id": 86199, "sent": "2 carrots"}, {"tokens": ["the", "two", "carrots", "in", "front"], "raw": "The two carrots in front.", "sent_id": 86200, "sent": "the two carrots in front"}], "file_name": "COCO_train2014_000000175116_1061926.jpg", "ann_id": 1061926, "sent_ids": [86199, 86200], "ref_id": 38104}, {"segmentation": [[132.67, 190.92, 119.73, 161.8, 136.99, 122.97, 192.0, 84.13, 278.29, 93.84, 306.34, 118.65, 313.89, 203.87, 328.99, 337.62, 320.36, 350.56, 303.1, 338.7, 303.1, 300.94, 276.13, 203.87, 248.09, 215.73, 239.46, 264.27, 254.56, 336.54, 229.75, 347.33, 199.55, 314.97, 200.63, 298.79, 204.94, 253.48, 204.94, 248.09, 187.69, 247.01, 198.47, 294.47, 182.29, 305.26, 173.66, 242.7, 182.29, 211.42, 139.15, 175.82, 133.75, 192.0]], "area": 30430.465549999994, "iscrowd": 0, "image_id": 27070, "bbox": [119.73, 84.13, 209.26, 266.43], "category_id": 22, "id": 580086, "split": "val", "sentences": [{"tokens": ["an", "elephant", "with", "a", "long", "trunk", "stands", "next", "to", "another", "elephant"], "raw": "An elephant with a long trunk stands next to another elephant.", "sent_id": 86203, "sent": "an elephant with a long trunk stands next to another elephant"}], "file_name": "COCO_train2014_000000027070_580086.jpg", "ann_id": 580086, "sent_ids": [86203], "ref_id": 38106}, {"segmentation": [[0.96, 99.34, 16.24, 93.61, 42.03, 102.2, 49.67, 150.91, 79.28, 173.84, 96.47, 226.37, 77.37, 274.13, 22.92, 312.34, 10.51, 319.02, 1.91, 314.25, 0.0, 101.25]], "area": 14473.873, "iscrowd": 0, "image_id": 181929, "bbox": [0.0, 93.61, 96.47, 225.41], "category_id": 1, "id": 520916, "split": "val", "sentences": [{"tokens": ["man", "with", "beard", "and", "glasses", ",", "wearing", "a", "navy", "blue", "hooded", "sweatshirt"], "raw": "Man with beard and glasses, wearing a navy blue hooded sweatshirt.", "sent_id": 86204, "sent": "man with beard and glasses , wearing a navy blue hooded sweatshirt"}, {"tokens": ["a", "person", "wearing", "blue", "sweater", "and", "wearing", "glasses"], "raw": "A person wearing blue sweater and wearing glasses.", "sent_id": 86205, "sent": "a person wearing blue sweater and wearing glasses"}], "file_name": "COCO_train2014_000000181929_520916.jpg", "ann_id": 520916, "sent_ids": [86204, 86205], "ref_id": 38107}, {"segmentation": [[217.17, 53.21, 268.94, 67.6, 294.83, 93.48, 294.83, 139.51, 299.15, 155.33, 293.39, 181.21, 336.54, 205.66, 396.94, 220.04, 428.58, 293.39, 457.35, 363.87, 460.22, 421.39, 451.6, 454.47, 414.2, 488.99, 412.76, 491.87, 411.33, 565.21, 401.26, 575.28, 407.01, 614.11, 396.94, 625.62, 396.94, 632.81, 125.12, 632.81, 132.31, 606.92, 116.49, 609.8, 94.92, 601.17, 76.22, 598.29, 70.47, 588.22, 51.78, 581.03, 14.38, 513.44, 34.52, 283.33, 41.71, 273.26, 97.8, 270.38, 125.12, 245.93, 172.58, 215.73, 178.34, 211.42, 169.71, 171.15, 158.2, 161.08, 149.57, 123.69, 162.52, 74.79]], "area": 178415.14834999994, "iscrowd": 0, "image_id": 163764, "bbox": [14.38, 53.21, 445.84, 579.6], "category_id": 1, "id": 1718355, "split": "val", "sentences": [{"tokens": ["a", "man", "drinking", "through", "a", "straw", ",", "and", "holding", "a", "pink", "box", "of", "pink", ",", "sprinkled", "doughnuts"], "raw": "A man drinking through a straw, and holding a pink box of pink, sprinkled doughnuts.", "sent_id": 86293, "sent": "a man drinking through a straw , and holding a pink box of pink , sprinkled doughnuts"}, {"tokens": ["the", "man", "taking", "a", "sip", "of", "his", "drink", "and", "holding", "donuts"], "raw": "The man taking a sip of his drink and holding donuts.", "sent_id": 86294, "sent": "the man taking a sip of his drink and holding donuts"}], "file_name": "COCO_train2014_000000163764_1718355.jpg", "ann_id": 1718355, "sent_ids": [86293, 86294], "ref_id": 38140}, {"segmentation": [[640.0, 269.41, 521.05, 259.69, 520.3, 261.19, 524.04, 265.68, 515.07, 265.68, 509.84, 259.69, 510.59, 231.28, 513.58, 196.89, 510.59, 182.69, 514.32, 181.19, 518.06, 175.21, 527.03, 169.23, 536.01, 166.24, 548.72, 158.01, 555.44, 155.02, 565.91, 153.53, 570.4, 149.04, 580.86, 149.04, 584.6, 148.3, 592.08, 144.56, 604.79, 142.31, 631.7, 135.59, 639.93, 133.34, 639.18, 167.73, 639.93, 268.67]], "area": 14426.733149999993, "iscrowd": 0, "image_id": 160313, "bbox": [509.84, 133.34, 130.16, 136.07], "category_id": 7, "id": 174669, "split": "val", "sentences": [{"tokens": ["the", "red", "train", "car", "on", "the", "right", "sits", "at", "the", "platform"], "raw": "The red train car on the right sits at the platform.", "sent_id": 86303, "sent": "the red train car on the right sits at the platform"}, {"tokens": ["red", "train", "car", "on", "train", "tracks"], "raw": "Red train car on train tracks.", "sent_id": 86304, "sent": "red train car on train tracks"}], "file_name": "COCO_train2014_000000160313_174669.jpg", "ann_id": 174669, "sent_ids": [86303, 86304], "ref_id": 38144}, {"segmentation": [[494.42, 395.76, 492.22, 382.52, 504.36, 374.79, 535.26, 375.9, 536.36, 362.65, 543.14, 355.79, 555.56, 353.43, 556.74, 344.56, 566.8, 341.6, 566.21, 332.73, 570.35, 327.41, 589.86, 320.31, 580.4, 314.99, 580.99, 310.26, 607.01, 241.06, 590.45, 235.15, 552.6, 223.32, 527.76, 273.0, 526.58, 278.32, 493.46, 275.36, 477.49, 278.91, 469.8, 291.92, 455.61, 293.1, 453.24, 310.85, 469.8, 339.24, 465.07, 358.16, 469.8, 360.53, 473.94, 341.01, 484.59, 339.24, 489.32, 349.88, 498.19, 363.48, 488.14, 369.99, 483.41, 378.86, 482.22, 391.28]], "area": 12708.2841, "iscrowd": 0, "image_id": 200010, "bbox": [453.24, 223.32, 153.77, 172.44], "category_id": 62, "id": 2190089, "split": "val", "sentences": [{"tokens": ["an", "outdoor", "patio", "chair", "placed", "closest", "to", "the", "fence"], "raw": "An outdoor patio chair placed closest to the fence.", "sent_id": 86305, "sent": "an outdoor patio chair placed closest to the fence"}], "file_name": "COCO_train2014_000000200010_2190089.jpg", "ann_id": 2190089, "sent_ids": [86305], "ref_id": 38145}, {"segmentation": [[158.2, 394.07, 178.34, 438.65, 204.22, 474.61, 214.29, 507.69, 205.66, 522.07, 188.4, 517.75, 146.7, 487.55, 123.69, 542.2, 89.17, 624.18, 97.8, 629.93, 80.54, 631.37, 69.03, 605.48, 53.21, 592.54, 47.46, 618.43, 23.01, 627.06, 20.13, 609.8, 2.88, 602.61, 1.44, 468.85, 48.9, 460.22, 69.03, 437.21, 93.48, 408.45, 151.01, 388.31, 169.71, 389.75]], "area": 27892.33155, "iscrowd": 0, "image_id": 22287, "bbox": [1.44, 388.31, 212.85, 243.06], "category_id": 24, "id": 592184, "split": "val", "sentences": [{"tokens": ["a", "zebra", "sniffs", "the", "rear", "of", "another", "zebra"], "raw": "A zebra sniffs the rear of another zebra.", "sent_id": 86327, "sent": "a zebra sniffs the rear of another zebra"}, {"tokens": ["a", "black", "and", "white", "zebra", "standing", "in", "the", "dirt", "next", "to", "another", "zebra", "and", "a", "giaraff"], "raw": "A black and white zebra standing in the dirt next to another zebra and a giaraff.", "sent_id": 86328, "sent": "a black and white zebra standing in the dirt next to another zebra and a giaraff"}], "file_name": "COCO_train2014_000000022287_592184.jpg", "ann_id": 592184, "sent_ids": [86327, 86328], "ref_id": 38154}, {"segmentation": [[86.22, 560.81, 117.73, 463.56, 109.5, 401.92, 95.81, 348.51, 58.82, 297.82, 72.53, 249.89, 43.76, 212.9, 84.85, 141.68, 164.3, 127.99, 173.88, 96.47, 202.64, 74.56, 225.94, 91.0, 224.56, 126.6, 195.8, 159.48, 217.72, 188.25, 225.94, 204.68, 235.52, 212.9, 217.72, 262.21, 210.87, 337.55, 187.58, 347.14, 167.03, 482.73, 158.82, 503.28, 171.15, 569.02, 183.47, 574.5, 167.03, 589.58, 173.88, 632.03, 128.69, 632.03, 119.1, 590.94, 91.7, 589.58, 84.85, 559.45]], "area": 53119.635600000016, "iscrowd": 0, "image_id": 65011, "bbox": [43.76, 74.56, 191.76, 557.47], "category_id": 1, "id": 437565, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "mustache"], "raw": "A man with a mustache.", "sent_id": 86355, "sent": "a man with a mustache"}, {"tokens": ["man", "in", "black", "coat", "and", "pants", "holding", "radio"], "raw": "man in black coat and pants holding radio", "sent_id": 86356, "sent": "man in black coat and pants holding radio"}], "file_name": "COCO_train2014_000000065011_437565.jpg", "ann_id": 437565, "sent_ids": [86355, 86356], "ref_id": 38165}, {"segmentation": [[459.41, 232.69, 448.58, 251.11, 439.91, 293.36, 437.74, 320.45, 448.58, 330.2, 443.16, 331.29, 436.66, 321.53, 434.49, 311.78, 434.49, 286.86, 433.41, 281.44, 431.24, 281.44, 423.66, 294.45, 423.66, 309.62, 425.82, 326.95, 423.66, 332.37, 422.57, 332.37, 421.49, 321.53, 417.16, 272.78, 405.24, 261.94, 395.49, 260.86, 391.15, 268.44, 385.73, 286.86, 383.57, 290.11, 383.57, 292.28, 394.4, 326.95, 382.48, 328.04, 368.4, 260.86, 361.9, 260.86, 355.4, 261.94, 355.4, 250.02, 355.4, 234.85, 356.48, 221.85, 361.9, 206.68, 377.07, 200.18, 394.4, 201.26, 425.82, 211.02, 448.58, 186.09, 476.75, 186.09, 482.17, 190.43, 475.67, 194.76, 476.75, 200.18, 480.0, 202.35, 482.17, 213.18, 487.58, 225.1, 488.67, 229.44, 488.67, 234.85, 487.58, 240.27, 483.25, 243.52, 480.0, 244.6, 472.42, 238.1, 463.75, 229.44]], "area": 9179.0872, "iscrowd": 0, "image_id": 181393, "bbox": [355.4, 186.09, 133.27, 146.28], "category_id": 24, "id": 593103, "split": "val", "sentences": [{"tokens": ["this", "is", "a", "zebra", "in", "front", "of", "another", "one"], "raw": "This is a zebra in front of another one", "sent_id": 86438, "sent": "this is a zebra in front of another one"}, {"tokens": ["zebra", "in", "front", "of", "another", "zebra"], "raw": "zebra in front of another zebra", "sent_id": 86439, "sent": "zebra in front of another zebra"}], "file_name": "COCO_train2014_000000181393_593103.jpg", "ann_id": 593103, "sent_ids": [86438, 86439], "ref_id": 38199}, {"segmentation": [[178.58, 468.65, 172.39, 470.71, 166.19, 462.45, 171.35, 452.13, 173.42, 444.9, 260.13, 443.87, 212.65, 430.45, 188.9, 400.52, 181.68, 368.52, 180.65, 335.48, 180.65, 316.9, 182.71, 293.16, 174.45, 261.16, 158.97, 232.26, 150.71, 213.68, 149.68, 202.32, 199.23, 252.9, 243.61, 272.52, 271.48, 304.52, 275.61, 331.35, 288.0, 323.1, 364.39, 373.68, 340.65, 395.35, 335.48, 408.77, 338.58, 421.16, 355.1, 419.1, 362.32, 416.0, 358.19, 431.48, 349.94, 454.19, 346.84, 455.23, 299.35, 456.26, 282.84, 460.39, 286.97, 473.81, 245.68, 473.81, 252.9, 461.42, 233.29, 461.42, 194.06, 457.29, 176.52, 455.23]], "area": 26686.44945, "iscrowd": 0, "image_id": 44266, "bbox": [149.68, 202.32, 214.71, 271.49], "category_id": 62, "id": 104781, "split": "val", "sentences": [{"tokens": ["a", "black", "coloured", "revolving", "chair"], "raw": "A BLACK COLOURED REVOLVING CHAIR", "sent_id": 86460, "sent": "a black coloured revolving chair"}, {"tokens": ["a", "black", "computer", "chair", "on", "wheels"], "raw": "A black computer chair on wheels", "sent_id": 86461, "sent": "a black computer chair on wheels"}], "file_name": "COCO_train2014_000000044266_104781.jpg", "ann_id": 104781, "sent_ids": [86460, 86461], "ref_id": 38205}, {"segmentation": [[174.22, 225.36, 190.8, 217.71, 225.25, 213.25, 254.58, 220.9, 271.8, 226.0, 276.27, 234.93, 271.8, 279.58, 239.91, 270.01, 232.26, 276.39, 266.06, 305.73, 234.17, 332.51, 240.55, 343.36, 286.47, 303.18, 287.75, 346.55, 277.54, 373.97, 268.62, 389.91, 239.28, 417.98, 206.11, 426.27, 193.36, 415.43, 186.98, 389.28, 191.44, 366.32, 193.99, 345.27, 190.8, 323.58, 186.98, 308.92, 181.24, 289.78, 178.69, 277.03, 153.18, 247.69, 153.18, 237.48, 172.31, 232.38]], "area": 17341.1693, "iscrowd": 0, "image_id": 309, "bbox": [153.18, 213.25, 134.57, 213.02], "category_id": 88, "id": 1161269, "split": "val", "sentences": [{"tokens": ["the", "torso", "of", "a", "brown", "furry", "teddy", "bear", "wearing", "a", "red", "ribbon"], "raw": "The torso of a brown furry teddy bear wearing a red ribbon.", "sent_id": 86579, "sent": "the torso of a brown furry teddy bear wearing a red ribbon"}, {"tokens": ["stuffed", "teddy", "bear", "with", "a", "red", "ribbon"], "raw": "stuffed teddy bear with a red ribbon", "sent_id": 86580, "sent": "stuffed teddy bear with a red ribbon"}], "file_name": "COCO_train2014_000000000309_1161269.jpg", "ann_id": 1161269, "sent_ids": [86579, 86580], "ref_id": 38252}, {"segmentation": [[408.18, 172.63, 413.07, 168.23, 424.8, 169.7, 429.69, 172.14, 433.11, 176.54, 434.09, 180.45, 435.56, 186.81, 437.02, 191.21, 440.93, 197.08, 442.4, 200.99, 444.36, 206.37, 447.29, 210.28, 448.76, 213.21, 451.69, 214.19, 455.11, 214.19, 460.49, 212.72, 465.38, 211.25, 471.74, 207.83, 479.56, 206.37, 495.21, 197.08, 497.16, 190.72, 496.67, 184.85, 496.67, 176.54, 499.12, 171.16, 501.07, 162.36, 502.54, 158.94, 506.94, 157.96, 512.32, 157.47, 519.16, 157.47, 524.05, 160.89, 526.01, 163.83, 529.92, 167.25, 533.34, 169.7, 536.77, 171.65, 540.68, 175.56, 542.14, 177.03, 542.63, 178.5, 542.63, 180.94, 542.14, 183.39, 538.72, 189.74, 537.74, 190.23, 533.83, 192.68, 531.88, 193.16, 526.5, 195.12, 523.08, 196.1, 513.3, 204.9, 497.65, 215.17, 457.56, 239.61, 477.12, 281.36, 487.38, 305.81, 485.43, 313.14, 480.05, 317.05, 474.18, 319.98, 469.78, 321.94, 464.4, 324.39, 460.98, 324.39, 455.11, 324.39, 447.29, 309.72, 438.0, 314.61, 426.27, 312.65, 426.27, 307.27, 424.8, 306.78, 418.44, 304.83, 416.98, 301.41, 421.87, 299.45, 417.95, 295.05, 412.09, 286.74, 409.15, 282.83, 403.29, 282.34, 399.38, 282.83, 389.11, 284.78, 385.68, 285.76, 382.75, 286.25, 379.82, 286.74, 378.84, 286.74, 377.37, 286.25, 373.46, 284.78, 371.99, 282.83, 371.51, 281.36, 369.06, 281.36, 369.55, 285.27, 371.99, 288.2, 372.97, 291.63, 373.95, 294.56, 378.35, 297.98, 380.8, 301.89, 381.77, 303.85, 381.28, 304.34, 376.88, 300.92, 373.95, 298.96, 373.95, 295.05, 371.51, 292.12, 370.53, 288.69, 368.57, 285.76, 368.57, 285.76, 368.57, 285.76, 359.77, 284.78, 352.44, 285.27, 359.28, 275.0, 354.88, 263.76, 347.24, 247.42, 362.39, 271.86, 365.82, 270.88, 364.84, 264.53, 367.28, 258.66, 373.15, 256.22, 379.99, 254.75, 383.91, 253.28, 387.33, 248.88, 363.98, 168.54, 374.73, 156.8, 383.53, 150.45, 395.27, 151.43, 400.16, 157.29, 402.11, 161.69, 403.58, 167.07, 406.51, 172.94, 410.43, 173.43, 413.85, 169.03]], "area": 14598.330299999985, "iscrowd": 0, "image_id": 310006, "bbox": [347.24, 150.45, 195.39, 173.94], "category_id": 5, "id": 161681, "split": "val", "sentences": [{"tokens": ["centermost", "plane"], "raw": "centermost plane", "sent_id": 86583, "sent": "centermost plane"}, {"tokens": ["middle", "plane"], "raw": "middle plane", "sent_id": 86584, "sent": "middle plane"}], "file_name": "COCO_train2014_000000310006_161681.jpg", "ann_id": 161681, "sent_ids": [86583, 86584], "ref_id": 38254}, {"segmentation": [[374.44, 373.95, 351.34, 410.62, 333.75, 400.23, 309.89, 380.52, 270.78, 341.71, 264.42, 333.45, 264.21, 330.9, 262.73, 328.15, 260.61, 325.82, 257.43, 324.97, 255.95, 326.03, 256.58, 329.21, 256.37, 337.05, 255.1, 340.44, 256.37, 344.04, 244.93, 363.54, 243.23, 366.3, 238.36, 380.07, 237.08, 387.07, 232.42, 384.1, 229.88, 384.52, 229.03, 386.01, 229.24, 388.13, 229.45, 395.75, 218.65, 404.38, 219.49, 416.88, 228.82, 426.63, 232.42, 431.93, 237.3, 464.38, 240.69, 474.55, 240.05, 476.88, 233.69, 477.73, 231.15, 480.06, 230.94, 481.76, 236.87, 482.39, 236.02, 486.42, 238.57, 489.39, 242.59, 491.29, 245.77, 496.38, 250.22, 500.0, 375.0, 500.0]], "area": 17903.502050000006, "iscrowd": 0, "image_id": 141952, "bbox": [218.65, 324.97, 156.35, 175.03], "category_id": 62, "id": 382560, "split": "val", "sentences": [{"tokens": ["a", "yellow", "chair", "with", "a", "blanket"], "raw": "A yellow chair with a blanket.", "sent_id": 86597, "sent": "a yellow chair with a blanket"}, {"tokens": ["a", "yellow", "lawn", "chair", "with", "nobody", "on", "it"], "raw": "A yellow lawn chair with nobody on it.", "sent_id": 86598, "sent": "a yellow lawn chair with nobody on it"}], "file_name": "COCO_train2014_000000141952_382560.jpg", "ann_id": 382560, "sent_ids": [86597, 86598], "ref_id": 38260}, {"segmentation": [[639.27, 420.32, 604.84, 424.64, 541.5, 431.39, 495.99, 433.12, 476.43, 417.55, 456.53, 404.74, 435.94, 399.21, 421.93, 400.76, 398.39, 404.22, 373.13, 419.28, 363.78, 434.68, 361.88, 442.47, 364.13, 453.37, 366.2, 456.66, 371.22, 464.96, 381.78, 474.13, 381.78, 474.13, 394.41, 479.33, 473.67, 479.85, 482.15, 471.37, 482.15, 471.37, 490.45, 456.66, 500.32, 450.6, 561.92, 445.93, 596.53, 445.93, 618.33, 448.01, 632.0, 447.66, 639.27, 448.87]], "area": 11376.939600000005, "iscrowd": 0, "image_id": 281464, "bbox": [361.88, 399.21, 277.39, 80.64], "category_id": 50, "id": 704059, "split": "val", "sentences": [{"tokens": ["the", "spoon", "on", "the", "bottom", "right", "under", "the", "bowl", "with", "the", "black", "stuff", "in", "it"], "raw": "The spoon on the bottom right under the bowl with the black stuff in it.", "sent_id": 86609, "sent": "the spoon on the bottom right under the bowl with the black stuff in it"}, {"tokens": ["a", "spoon", "in", "front", "of", "a", "cup", "which", "has", "black", "cream", "in", "it"], "raw": "A spoon in front of a cup which has black cream in it", "sent_id": 86610, "sent": "a spoon in front of a cup which has black cream in it"}], "file_name": "COCO_train2014_000000281464_704059.jpg", "ann_id": 704059, "sent_ids": [86609, 86610], "ref_id": 38265}, {"segmentation": [[214.89, 242.7, 208.99, 279.78, 215.73, 321.91, 241.01, 352.25, 280.62, 370.79, 344.66, 365.73, 376.69, 345.51, 397.75, 283.99, 395.22, 242.7, 378.37, 222.47, 362.36, 203.09, 332.02, 186.24, 294.1, 177.81, 248.6, 194.66, 231.74, 209.83, 222.47, 230.9, 216.57, 242.7]], "area": 28398.44815, "iscrowd": 0, "image_id": 322411, "bbox": [208.99, 177.81, 188.76, 192.98], "category_id": 51, "id": 1039951, "split": "val", "sentences": [{"tokens": ["bowl", "with", "banana", "slices", ",", "raisins", ",", "and", "cookies"], "raw": "bowl with banana slices, raisins, and cookies", "sent_id": 86616, "sent": "bowl with banana slices , raisins , and cookies"}, {"tokens": ["a", "plate", "of", "cookies", "and", "banana", "slice", ",", "raisins", ",", "and", "craisins"], "raw": "a plate of cookies and banana slice, raisins, and craisins", "sent_id": 86617, "sent": "a plate of cookies and banana slice , raisins , and craisins"}], "file_name": "COCO_train2014_000000322411_1039951.jpg", "ann_id": 1039951, "sent_ids": [86616, 86617], "ref_id": 38266}, {"segmentation": [[289.95, 116.05, 267.25, 103.34, 244.1, 98.81, 227.76, 109.7, 205.69, 116.65, 182.09, 116.65, 139.42, 128.45, 118.06, 138.98, 95.86, 156.24, 82.03, 182.21, 76.6, 185.66, 67.23, 205.88, 70.19, 241.4, 79.56, 281.85, 91.04, 294.8, 98.44, 296.27, 94.99, 320.94, 89.56, 339.19, 91.04, 350.04, 104.36, 353.99, 123.6, 353.99, 147.77, 352.01, 140.86, 339.68, 159.61, 324.39, 184.27, 299.73, 203.51, 280.98, 219.78, 317.98, 225.7, 326.36, 241.49, 321.43, 252.34, 294.8, 258.26, 268.65, 273.06, 250.4, 287.85, 248.92, 295.75, 246.46, 297.23, 280.98, 309.56, 309.59, 318.44, 329.82, 349.51, 318.96, 348.03, 293.81, 365.6, 291.03, 365.25, 285.38, 349.69, 255.32, 342.26, 217.12, 334.56, 187.22, 318.78, 146.28, 299.05, 127.54, 289.68, 115.7]], "area": 49060.9902, "iscrowd": 0, "image_id": 313724, "bbox": [67.23, 98.81, 298.37, 255.18], "category_id": 23, "id": 586652, "split": "val", "sentences": [{"tokens": ["bear", "closer", "to", "beach", ",", "on", "left"], "raw": "bear closer to beach, on left", "sent_id": 86680, "sent": "bear closer to beach , on left"}, {"tokens": ["the", "bear", "with", "his", "head", "down"], "raw": "the bear with his head down", "sent_id": 86681, "sent": "the bear with his head down"}], "file_name": "COCO_train2014_000000313724_586652.jpg", "ann_id": 586652, "sent_ids": [86680, 86681], "ref_id": 38290}, {"segmentation": [[240.83, 239.06, 239.06, 195.67, 247.91, 190.36, 285.98, 192.13, 247.91, 233.74], [374.52, 373.64, 378.06, 355.04, 417.91, 365.67, 385.15, 372.75], [301.03, 351.5, 307.23, 353.27, 324.94, 366.55, 301.03, 363.01], [426.76, 365.67, 428.53, 385.15, 422.33, 371.87, 379.83, 381.6, 379.83, 374.52, 415.25, 368.32], [430.3, 208.07, 416.13, 237.29, 422.33, 270.04, 432.07, 285.98, 424.99, 299.26, 425.87, 309.0, 463.95, 317.86, 455.98, 242.6, 441.81, 242.6, 432.07, 214.27]], "area": 5051.948450000002, "iscrowd": 0, "image_id": 56677, "bbox": [239.06, 190.36, 224.89, 194.79], "category_id": 62, "id": 386326, "split": "val", "sentences": [{"tokens": ["the", "chair", "in", "which", "the", "old", "man", "seated"], "raw": "The chair in which the old man seated", "sent_id": 86825, "sent": "the chair in which the old man seated"}, {"tokens": ["the", "chair", "that", "the", "old", "woman", "is", "sitting", "on"], "raw": "The chair that the old woman is sitting on", "sent_id": 86826, "sent": "the chair that the old woman is sitting on"}], "file_name": "COCO_train2014_000000056677_386326.jpg", "ann_id": 386326, "sent_ids": [86825, 86826], "ref_id": 38349}, {"segmentation": [[325.7, 254.16, 327.28, 237.56, 329.66, 220.17, 339.14, 206.73, 351.0, 213.84, 357.32, 232.02, 363.65, 237.56, 370.76, 235.19, 363.65, 212.26, 354.95, 188.54, 349.42, 171.94, 349.42, 165.62, 369.97, 164.04, 384.99, 160.88, 391.32, 160.88, 393.69, 158.5, 400.01, 157.71, 399.22, 152.18, 387.36, 152.18, 380.25, 156.13, 355.74, 155.34, 344.68, 155.34, 330.45, 156.92, 320.96, 145.06, 309.89, 148.23, 309.1, 159.29, 312.26, 165.62, 313.05, 171.94, 305.15, 184.59, 303.57, 203.56, 293.29, 221.75, 290.92, 224.91, 301.99, 228.07, 307.52, 215.42, 313.05, 201.98, 317.01, 189.33, 324.12, 188.54, 318.59, 214.63, 318.59, 242.3, 320.17, 255.74, 326.49, 254.95]], "area": 3874.5688, "iscrowd": 0, "image_id": 268197, "bbox": [290.92, 145.06, 109.09, 110.68], "category_id": 1, "id": 511021, "split": "val", "sentences": [{"tokens": ["a", "surfer", "is", "leaning", "forward", "away", "from", "the", "wave", ",", "next", "to", "another", "surfer", "leaning", "into", "the", "wave"], "raw": "A surfer is leaning forward away from the wave, next to another surfer leaning into the wave.", "sent_id": 86858, "sent": "a surfer is leaning forward away from the wave , next to another surfer leaning into the wave"}, {"tokens": ["the", "surfer", "who", "is", "displaying", "better", "balance"], "raw": "the surfer who is displaying better balance", "sent_id": 86859, "sent": "the surfer who is displaying better balance"}], "file_name": "COCO_train2014_000000268197_511021.jpg", "ann_id": 511021, "sent_ids": [86858, 86859], "ref_id": 38362}, {"segmentation": [[380.76, 44.22, 598.65, 48.54, 580.31, 188.76, 368.9, 184.45, 379.69, 45.3]], "area": 30233.0714, "iscrowd": 0, "image_id": 445127, "bbox": [368.9, 44.22, 229.75, 144.54], "category_id": 72, "id": 30228, "split": "val", "sentences": [{"tokens": ["monitor", "closer", "to", "the", "mouse"], "raw": "Monitor closer to the mouse.", "sent_id": 86903, "sent": "monitor closer to the mouse"}, {"tokens": ["the", "computer", "monitor", "by", "the", "corner", "of", "the", "desk"], "raw": "The computer monitor by the corner of the desk.", "sent_id": 86904, "sent": "the computer monitor by the corner of the desk"}], "file_name": "COCO_train2014_000000445127_30228.jpg", "ann_id": 30228, "sent_ids": [86903, 86904], "ref_id": 38374}, {"segmentation": [[227.82, 184.8, 221.37, 194.47, 213.31, 212.74, 209.55, 218.65, 210.62, 224.57, 218.68, 224.57, 224.59, 228.33, 232.65, 219.73, 241.25, 214.36, 250.92, 206.83, 258.44, 208.98, 263.82, 212.21, 267.04, 227.79, 267.58, 245.52, 265.97, 277.76, 264.35, 284.21, 272.41, 279.37, 277.25, 274.54, 279.94, 273.46, 283.16, 245.52, 286.92, 230.48, 290.68, 226.18, 293.37, 249.82, 299.28, 257.88, 297.67, 273.46, 302.51, 275.07, 300.36, 282.6, 308.42, 284.75, 314.86, 279.91, 308.95, 278.84, 304.12, 249.82, 305.73, 240.15, 307.88, 226.71, 309.49, 217.58, 319.7, 199.85, 308.95, 166.53, 298.21, 157.94, 285.31, 157.4, 275.1, 160.09, 271.88, 163.31, 248.23, 166.53, 229.43, 172.98, 221.91, 176.74, 221.37, 181.04, 219.22, 182.65]], "area": 6813.996349999999, "iscrowd": 0, "image_id": 276444, "bbox": [209.55, 157.4, 110.15, 127.35], "category_id": 24, "id": 589185, "split": "val", "sentences": [{"tokens": ["a", "baby", "zebra", "leaning", "to", "its", "mom", "seeking", "comfort"], "raw": "A baby zebra leaning to its mom seeking comfort", "sent_id": 86915, "sent": "a baby zebra leaning to its mom seeking comfort"}, {"tokens": ["a", "child", "zebra", "with", "its", "parent", "in", "jungle"], "raw": "A CHILD ZEBRA WITH ITS PARENT IN JUNGLE", "sent_id": 86916, "sent": "a child zebra with its parent in jungle"}], "file_name": "COCO_train2014_000000276444_589185.jpg", "ann_id": 589185, "sent_ids": [86915, 86916], "ref_id": 38379}, {"segmentation": [[0.96, 5.82, 638.1, 1.98, 519.12, 93.14, 328.17, 68.19, 180.4, 79.71, 142.97, 84.5, 107.47, 105.61, 96.91, 313.84, 101.71, 331.11, 0.96, 391.56], [520.08, 93.14, 545.02, 120.97, 569.01, 312.88, 512.4, 343.58, 363.67, 360.85, 208.22, 347.42, 129.54, 340.7, 102.67, 327.27, 1.92, 412.67, 636.18, 413.63, 640.0, 355.1, 640.0, 13.5, 640.0, 7.74]], "area": 139025.76864999998, "iscrowd": 0, "image_id": 18093, "bbox": [0.96, 1.98, 639.04, 411.65], "category_id": 79, "id": 1642365, "split": "val", "sentences": [{"tokens": ["the", "inside", "of", "an", "oven"], "raw": "the inside of an oven", "sent_id": 86941, "sent": "the inside of an oven"}, {"tokens": ["the", "inside", "of", "the", "oven"], "raw": "The inside of the oven.", "sent_id": 86942, "sent": "the inside of the oven"}], "file_name": "COCO_train2014_000000018093_1642365.jpg", "ann_id": 1642365, "sent_ids": [86941, 86942], "ref_id": 38391}, {"segmentation": [[148.19, 337.9, 154.63, 273.47, 192.21, 191.86, 253.42, 170.38, 235.17, 112.39, 285.64, 67.29, 340.4, 104.88, 350.07, 165.01, 372.62, 258.43, 354.36, 395.88, 224.43, 403.4, 204.03, 346.49, 150.34, 350.78]], "area": 50460.81304999999, "iscrowd": 0, "image_id": 513683, "bbox": [148.19, 67.29, 224.43, 336.11], "category_id": 1, "id": 184146, "split": "val", "sentences": [{"tokens": ["man", "drinking", "wine", "in", "blue", "tshirt", "with", "obama", "on", "it"], "raw": "Man drinking wine in blue tshirt with obama on it", "sent_id": 86947, "sent": "man drinking wine in blue tshirt with obama on it"}, {"tokens": ["a", "man", "with", "blue", "coloured", "t", "shirt", "is", "drinking"], "raw": "a man with blue coloured t shirt is drinking", "sent_id": 86948, "sent": "a man with blue coloured t shirt is drinking"}], "file_name": "COCO_train2014_000000513683_184146.jpg", "ann_id": 184146, "sent_ids": [86947, 86948], "ref_id": 38393}, {"segmentation": [[300.54, 408.11, 297.3, 410.27, 295.14, 475.14, 592.43, 474.05, 591.35, 454.59]], "area": 12867.970050000002, "iscrowd": 0, "image_id": 220842, "bbox": [295.14, 408.11, 297.29, 67.03], "category_id": 79, "id": 1642795, "split": "val", "sentences": [{"tokens": ["the", "face", "of", "the", "oven"], "raw": "The face of the oven", "sent_id": 86991, "sent": "the face of the oven"}], "file_name": "COCO_train2014_000000220842_1642795.jpg", "ann_id": 1642795, "sent_ids": [86991], "ref_id": 38410}, {"segmentation": [[287.89, 292.62, 363.47, 299.49, 402.74, 309.31, 428.26, 320.1, 458.69, 324.03, 495.99, 327.96, 551.95, 336.79, 589.25, 353.48, 609.86, 371.15, 609.86, 430.05, 612.0, 457.53, 612.0, 588.25, 597.1, 603.95, 568.64, 609.84, 529.37, 607.88, 402.74, 606.9, 191.69, 608.86, 76.84, 612.0, 0.0, 610.82, 3.21, 397.81, 0.27, 319.28, 48.37, 301.61, 114.14, 294.74, 158.31, 280.99, 223.1, 279.03, 264.33, 289.83]], "area": 183595.08435, "iscrowd": 0, "image_id": 153814, "bbox": [0.0, 279.03, 612.0, 332.97], "category_id": 59, "id": 1072407, "split": "val", "sentences": [{"tokens": ["the", "cheese", "and", "pepperoni", "pizza", "farthest", "away", "from", "the", "woman", "sitting", "at", "the", "table"], "raw": "The cheese and pepperoni pizza farthest away from the woman sitting at the table.", "sent_id": 87015, "sent": "the cheese and pepperoni pizza farthest away from the woman sitting at the table"}, {"tokens": ["the", "pizza", "that", "is", "closer", "to", "the", "camera", "than", "the", "other", ".", "it", "is", "in", "front", "of", "the", "glasses", "and", "the", "water"], "raw": "The pizza that is closer to the camera than the other. It is in front of the glasses and the water.", "sent_id": 87016, "sent": "the pizza that is closer to the camera than the other . it is in front of the glasses and the water"}], "file_name": "COCO_train2014_000000153814_1072407.jpg", "ann_id": 1072407, "sent_ids": [87015, 87016], "ref_id": 38419}, {"segmentation": [[1.8, 371.62, 2.7, 2.25, 636.94, 0.45, 638.74, 156.31, 637.84, 167.12, 585.59, 105.86, 564.86, 84.23, 532.43, 62.61, 486.49, 51.8, 362.16, 35.59, 325.23, 33.78, 269.37, 19.37, 254.05, 13.96, 236.04, 64.41, 204.5, 80.63, 191.89, 123.87, 190.99, 198.65, 201.8, 219.37, 209.01, 284.23, 235.14, 305.86, 262.16, 305.86, 245.95, 345.5, 184.68, 364.41, 148.65, 366.22, 144.14, 363.51, 153.15, 310.36, 151.35, 287.84, 136.94, 255.41, 109.91, 103.15, 89.19, 226.58, 83.78, 307.66, 99.1, 358.11, 83.78, 368.02, 50.45, 377.03], [548.65, 371.62, 564.86, 357.21, 570.27, 278.83, 558.56, 234.68, 569.37, 140.09, 579.28, 96.85, 562.16, 80.63, 555.86, 101.35, 561.26, 152.7, 551.35, 190.54, 541.44, 215.77, 529.73, 277.03, 530.63, 317.57, 536.94, 353.6], [638.74, 379.73, 623.42, 367.12, 640.0, 326.58, 636.94, 376.13]], "area": 96782.54055, "iscrowd": 0, "image_id": 500214, "bbox": [1.8, 0.45, 638.2, 379.28], "category_id": 22, "id": 585100, "split": "val", "sentences": [{"tokens": ["the", "body", "of", "the", "adult", "elephant"], "raw": "The body of the adult elephant", "sent_id": 87062, "sent": "the body of the adult elephant"}], "file_name": "COCO_train2014_000000500214_585100.jpg", "ann_id": 585100, "sent_ids": [87062], "ref_id": 38440}, {"segmentation": [[150.3, 420.26, 161.78, 373.35, 173.27, 362.82, 224.01, 357.07, 344.63, 337.93, 470.99, 329.31, 523.64, 390.58, 521.73, 393.45, 372.39, 420.26]], "area": 24773.012949999997, "iscrowd": 0, "image_id": 237853, "bbox": [150.3, 329.31, 373.34, 90.95], "category_id": 76, "id": 1114965, "split": "val", "sentences": [{"tokens": ["a", "white", "computer", "keyboard", "placed", "in", "front", "of", "a", "computer", "desk"], "raw": "A white computer keyboard placed in front of a computer desk.", "sent_id": 87072, "sent": "a white computer keyboard placed in front of a computer desk"}, {"tokens": ["a", "white", "computer", "keyboard", "in", "front", "of", "a", "stuffed", "monkey"], "raw": "A white computer keyboard in front of a stuffed monkey.", "sent_id": 87073, "sent": "a white computer keyboard in front of a stuffed monkey"}], "file_name": "COCO_train2014_000000237853_1114965.jpg", "ann_id": 1114965, "sent_ids": [87072, 87073], "ref_id": 38445}, {"segmentation": [[590.05, 101.77, 571.54, 137.75, 561.26, 142.89, 524.26, 123.35, 518.09, 117.19, 569.49, 39.06, 573.6, 33.92, 583.88, 27.75, 602.38, 21.59, 609.58, 8.22, 619.86, 4.11, 637.33, 3.08, 637.33, 16.45, 628.08, 24.67, 619.86, 25.7, 614.72, 32.89, 615.75, 41.12, 615.75, 51.4, 603.41, 56.54, 589.02, 58.59, 584.91, 65.79, 586.96, 75.04, 590.05, 84.29, 591.08, 94.57, 586.96, 105.88]], "area": 6023.370699999996, "iscrowd": 0, "image_id": 343154, "bbox": [518.09, 3.08, 119.24, 139.81], "category_id": 44, "id": 79299, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "oil", "in", "a", "wooden", "bowl"], "raw": "A bottle of oil in a wooden bowl.", "sent_id": 87120, "sent": "a bottle of oil in a wooden bowl"}], "file_name": "COCO_train2014_000000343154_79299.jpg", "ann_id": 79299, "sent_ids": [87120], "ref_id": 38466}, {"segmentation": [[214.77, 289.6, 200.55, 233.47, 189.32, 187.08, 193.07, 149.66, 183.34, 104.76, 203.54, 84.56, 204.29, 68.84, 226.74, 70.34, 222.25, 85.31, 222.25, 96.53, 214.77, 90.55, 218.51, 95.78, 224.49, 98.78, 226.74, 121.98, 237.22, 104.76, 230.48, 79.32, 228.98, 57.62, 236.47, 56.87, 241.71, 71.09, 246.94, 111.5, 237.22, 149.66, 235.72, 185.58, 240.96, 217.01, 240.96, 228.98, 240.96, 249.19, 225.99, 261.16, 225.99, 228.98, 214.77, 224.49, 215.51, 258.92, 224.49, 291.84, 223.75, 300.07, 220.0, 305.31, 217.76, 305.31], [223.75, 272.39, 227.49, 297.83, 235.72, 278.37, 239.46, 274.63]], "area": 8598.925599999999, "iscrowd": 0, "image_id": 111000, "bbox": [183.34, 56.87, 63.6, 248.44], "category_id": 1, "id": 487650, "split": "val", "sentences": [{"tokens": ["man", "with", "both", "arms", "high", "above", "his", "head"], "raw": "Man with both arms high above his head", "sent_id": 87127, "sent": "man with both arms high above his head"}], "file_name": "COCO_train2014_000000111000_487650.jpg", "ann_id": 487650, "sent_ids": [87127], "ref_id": 38469}, {"segmentation": [[83.56, 261.87, 85.05, 237.25, 78.34, 205.17, 85.05, 158.91, 100.72, 134.29, 108.93, 127.58, 124.59, 123.1, 161.9, 122.36, 271.57, 167.12, 264.85, 174.58, 260.38, 174.58, 259.63, 166.37, 254.41, 164.88, 248.44, 167.87, 251.42, 174.58, 251.42, 176.07, 242.47, 176.07, 238.0, 185.77, 232.77, 200.69, 222.33, 185.77, 223.07, 177.56, 218.6, 172.34, 213.38, 175.33, 200.69, 172.34, 198.45, 180.55, 199.2, 190.25, 196.22, 190.99, 190.99, 208.15, 192.49, 214.12, 187.26, 236.5, 146.23, 266.35]], "area": 16278.01105, "iscrowd": 0, "image_id": 795, "bbox": [78.34, 122.36, 193.23, 143.99], "category_id": 7, "id": 175179, "split": "val", "sentences": [{"tokens": ["train"], "raw": "Train", "sent_id": 87128, "sent": "train"}, {"tokens": ["a", "yellow", "train", "is", "in", "the", "station", "with", "people", "walking", "away", "from", "it"], "raw": "A yellow train is in the station with people walking away from it.", "sent_id": 87129, "sent": "a yellow train is in the station with people walking away from it"}], "file_name": "COCO_train2014_000000000795_175179.jpg", "ann_id": 175179, "sent_ids": [87128, 87129], "ref_id": 38470}, {"segmentation": [[312.52, 435.53, 305.87, 606.75, 259.32, 616.73, 222.75, 605.09, 219.43, 563.53, 212.78, 460.47, 186.18, 467.12, 169.56, 468.78, 179.53, 435.53, 186.18, 423.9, 144.62, 437.19, 124.68, 437.19, 114.7, 430.55, 108.05, 417.25, 96.42, 407.27, 74.81, 400.62, 59.84, 379.01, 78.13, 337.45, 58.18, 329.14, 43.22, 364.05, 24.94, 367.38, 21.61, 332.47, 28.26, 312.52, 99.74, 332.47, 126.34, 340.78, 118.03, 305.87, 101.4, 292.57, 99.74, 279.27, 114.7, 257.66, 124.68, 226.08, 131.32, 199.48, 132.99, 179.53, 124.68, 164.57, 126.34, 144.62, 106.39, 136.31, 98.08, 118.03, 94.75, 98.08, 119.69, 103.06, 128.0, 93.09, 136.31, 91.43, 144.62, 78.13, 159.58, 89.77, 177.87, 106.39, 189.51, 114.7, 197.82, 134.65, 206.13, 157.92, 221.09, 166.23, 239.38, 151.27, 226.08, 132.99, 239.38, 126.34, 249.35, 141.3, 247.69, 124.68, 272.62, 124.68, 295.9, 119.69, 310.86, 99.74, 305.87, 78.13, 305.87, 64.83, 327.48, 61.51, 317.51, 34.91, 329.14, 23.27, 342.44, 28.26, 340.78, 104.73, 337.45, 132.99, 332.47, 161.25, 350.75, 171.22, 365.71, 186.18, 380.68, 199.48, 387.32, 211.12, 390.65, 262.65, 397.3, 297.56, 415.58, 299.22, 420.57, 285.92, 458.81, 277.61, 477.09, 256.0, 467.12, 285.92, 480.0, 300.88, 475.43, 324.16, 442.18, 295.9, 423.9, 309.19, 425.56, 319.17, 443.84, 335.79, 453.82, 345.77, 463.79, 354.08, 433.87, 367.38, 417.25, 360.73, 417.25, 374.03, 392.31, 375.69, 377.35, 365.71, 360.73, 384.0, 344.1, 395.64, 325.82, 407.27, 314.18, 408.94, 310.86, 420.57]], "area": 109531.23630000002, "iscrowd": 0, "image_id": 102662, "bbox": [21.61, 23.27, 458.39, 593.46], "category_id": 64, "id": 1954483, "split": "val", "sentences": [{"tokens": ["a", "vase", "with", "blue", "liquid", "containing", "yellow", "and", "purple", "flowers"], "raw": "A vase with blue liquid containing yellow and purple flowers.", "sent_id": 87138, "sent": "a vase with blue liquid containing yellow and purple flowers"}, {"tokens": ["a", "glass", "of", "flowers"], "raw": "A glass of flowers.", "sent_id": 87139, "sent": "a glass of flowers"}], "file_name": "COCO_train2014_000000102662_1954483.jpg", "ann_id": 1954483, "sent_ids": [87138, 87139], "ref_id": 38474}, {"segmentation": [[271.29, 365.09, 256.96, 385.15, 256.01, 412.85, 255.05, 409.98, 244.55, 423.36, 209.2, 425.27, 204.43, 394.7, 221.62, 326.88, 176.72, 350.76, 162.39, 361.27, 171.95, 427.0, 106.03, 427.0, 106.99, 336.43, 162.39, 295.35, 159.53, 264.79, 189.14, 239.95, 229.26, 221.8, 252.19, 175.95, 259.83, 163.53, 257.92, 167.35, 286.58, 157.8, 279.89, 119.59, 286.58, 102.39, 324.79, 97.62, 334.34, 112.9, 340.07, 132.0, 331.47, 151.11, 367.77, 177.86, 386.88, 263.83, 372.55, 267.65, 371.6, 282.94, 364.91, 286.76, 333.38, 309.68, 306.64, 324.97, 287.53, 324.97, 277.02, 362.22]], "area": 43422.744399999996, "iscrowd": 0, "image_id": 224734, "bbox": [106.03, 97.62, 280.85, 329.38], "category_id": 1, "id": 483835, "split": "val", "sentences": [{"tokens": ["the", "gentleman", "sitting", "in", "the", "chair", "wearing", "a", "light", "blue", "short", "sleeved", "oxford", "shirt", "and", "black", "slacks"], "raw": "The gentleman sitting in the chair wearing a light blue short sleeved oxford shirt and black slacks.", "sent_id": 87202, "sent": "the gentleman sitting in the chair wearing a light blue short sleeved oxford shirt and black slacks"}, {"tokens": ["a", "man", "wearing", "a", "blue", "shirt", "and", "sitting", "on", "a", "chair"], "raw": "A man wearing a blue shirt and sitting on a chair.", "sent_id": 87203, "sent": "a man wearing a blue shirt and sitting on a chair"}], "file_name": "COCO_train2014_000000224734_483835.jpg", "ann_id": 483835, "sent_ids": [87202, 87203], "ref_id": 38495}, {"segmentation": [[250.34, 217.69, 256.09, 206.19, 254.76, 189.39, 253.44, 181.87, 253.44, 169.49, 252.55, 166.4, 249.46, 160.65, 255.21, 152.25, 258.3, 145.17, 264.49, 147.39, 279.52, 147.83, 291.02, 145.62, 305.17, 143.85, 314.01, 149.15, 310.92, 142.52, 317.11, 140.75, 321.53, 144.29, 324.62, 143.41, 323.74, 134.12, 314.01, 134.12, 299.86, 135.01, 295.44, 133.68, 275.99, 127.49, 266.7, 126.16, 262.72, 122.18, 260.07, 118.2, 260.95, 114.67, 267.14, 114.67, 268.91, 113.78, 278.2, 121.3, 282.18, 123.51, 284.83, 123.51, 279.97, 99.63, 278.2, 95.65, 268.03, 85.93, 255.65, 84.6, 247.69, 86.37, 245.04, 95.21, 239.73, 99.19, 239.73, 103.61, 239.73, 105.82, 230.45, 108.48, 222.04, 112.46, 215.41, 119.97, 212.76, 127.05, 212.76, 135.01, 208.34, 144.73, 208.34, 154.02, 210.55, 159.32, 208.34, 161.98, 208.78, 176.12, 214.53, 184.97, 218.07, 190.27]], "area": 6114.69895, "iscrowd": 0, "image_id": 287140, "bbox": [208.34, 84.6, 116.28, 133.09], "category_id": 1, "id": 2151867, "split": "val", "sentences": [{"tokens": ["the", "man", "on", "the", "back", "wearing", "a", "white", ",", "red", "and", "yellow", "jacket"], "raw": "The man on the back wearing a white, red and yellow jacket.", "sent_id": 87210, "sent": "the man on the back wearing a white , red and yellow jacket"}, {"tokens": ["a", "man", "in", "the", "black", "healmate"], "raw": "a man in the black healmate", "sent_id": 87211, "sent": "a man in the black healmate"}], "file_name": "COCO_train2014_000000287140_2151867.jpg", "ann_id": 2151867, "sent_ids": [87210, 87211], "ref_id": 38499}, {"segmentation": [[387.9, 99.41, 416.07, 73.41, 434.49, 72.33, 476.75, 98.33, 496.25, 109.16, 499.5, 120.0, 591.6, 219.68, 611.11, 240.27, 577.52, 268.44, 545.01, 298.78, 465.91, 218.6, 404.15, 157.92, 385.73, 124.33, 380.32, 99.41]], "area": 22397.5039, "iscrowd": 0, "image_id": 209356, "bbox": [380.32, 72.33, 230.79, 226.45], "category_id": 54, "id": 310114, "split": "val", "sentences": [{"tokens": ["sandwich", "to", "right", "of", "chips", "with", "white", "substance", "on", "it"], "raw": "Sandwich to right of chips with white substance on it.", "sent_id": 87239, "sent": "sandwich to right of chips with white substance on it"}, {"tokens": ["a", "sandwich", "that", "is", "to", "the", "right", "of", "the", "other", "food"], "raw": "A sandwich that is to the right of the other food.", "sent_id": 87240, "sent": "a sandwich that is to the right of the other food"}], "file_name": "COCO_train2014_000000209356_310114.jpg", "ann_id": 310114, "sent_ids": [87239, 87240], "ref_id": 38510}, {"segmentation": [[418.39, 61.01, 435.98, 56.36, 457.7, 53.77, 483.57, 54.29, 505.3, 56.87, 527.54, 63.08, 547.2, 69.29, 561.68, 80.67, 568.41, 94.12, 564.27, 111.19, 554.44, 133.44, 543.58, 146.89, 527.02, 158.78, 512.54, 165.51, 510.47, 167.06, 508.4, 172.23, 500.64, 175.34, 491.33, 180.51, 485.64, 183.1, 476.33, 183.61, 464.95, 184.13, 452.53, 178.44, 444.25, 174.82, 440.11, 167.06, 438.04, 160.34, 431.84, 156.71, 415.28, 142.23, 407.52, 129.3, 400.8, 110.67, 393.04, 91.02, 394.59, 77.57, 398.73, 69.29, 405.97, 65.15, 416.84, 62.56]], "area": 16569.88835, "iscrowd": 0, "image_id": 20917, "bbox": [393.04, 53.77, 175.37, 130.36], "category_id": 51, "id": 710981, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "sesame"], "raw": "a bowl of sesame", "sent_id": 87251, "sent": "a bowl of sesame"}, {"tokens": ["a", "white", "bowl", "decorated", "with", "flowers", "containing", "sesame", "seeds"], "raw": "A white bowl decorated with flowers containing sesame seeds.", "sent_id": 87252, "sent": "a white bowl decorated with flowers containing sesame seeds"}], "file_name": "COCO_train2014_000000020917_710981.jpg", "ann_id": 710981, "sent_ids": [87251, 87252], "ref_id": 38513}, {"segmentation": [[387.58, 321.12, 380.37, 279.54, 383.15, 269.0, 388.69, 263.46, 395.9, 261.79, 395.35, 252.92, 404.22, 224.64, 409.76, 216.33, 420.3, 210.78, 431.94, 217.44, 438.04, 225.75, 443.59, 230.74, 444.14, 235.73, 443.03, 237.4, 429.72, 230.74, 418.63, 230.74, 409.21, 234.07, 403.11, 252.37, 405.88, 262.35, 412.53, 269.56, 413.64, 264.01, 417.52, 269.0, 416.97, 269.56, 425.29, 261.79, 422.52, 270.67, 429.72, 272.33, 433.05, 278.43, 435.27, 275.1, 441.37, 267.34, 443.59, 315.03, 451.35, 339.42, 450.24, 345.52, 459.11, 353.84, 470.76, 371.58, 490.16, 405.41, 496.82, 418.16, 501.25, 440.89, 514.01, 466.95, 521.21, 480.0, 505.13, 480.0, 490.72, 476.94, 486.28, 473.61, 488.5, 456.97, 473.53, 434.79, 467.43, 408.18, 453.01, 389.33, 448.02, 390.44, 450.24, 417.05, 447.47, 448.66, 455.78, 479.71, 435.27, 478.6, 428.61, 476.38, 431.39, 459.75, 429.17, 450.87, 429.17, 450.87, 424.73, 448.66, 425.84, 411.51, 425.29, 403.74, 405.88, 388.22, 404.22, 385.45, 390.91, 374.91, 379.82, 368.26, 380.37, 365.48, 380.37, 359.38, 381.48, 349.96, 393.68, 354.39, 406.99, 351.62, 411.98, 347.19, 409.76, 316.69, 416.42, 303.94, 408.1, 318.91, 394.79, 329.44, 388.69, 327.78, 387.58, 321.12]], "area": 12817.368099999998, "iscrowd": 0, "image_id": 449158, "bbox": [379.82, 210.78, 141.39, 269.22], "category_id": 1, "id": 199459, "split": "val", "sentences": [{"tokens": ["girl", "covering", "her", "face"], "raw": "Girl covering her face.", "sent_id": 87259, "sent": "girl covering her face"}, {"tokens": ["the", "person", "covering", "their", "face", "with", "a", "circular", "object"], "raw": "The person covering their face with a circular  object", "sent_id": 87260, "sent": "the person covering their face with a circular object"}], "file_name": "COCO_train2014_000000449158_199459.jpg", "ann_id": 199459, "sent_ids": [87259, 87260], "ref_id": 38516}, {"segmentation": [[57.81, 262.45, 74.32, 268.65, 87.74, 234.58, 129.03, 239.74, 163.1, 236.65, 166.19, 250.06, 251.87, 252.13, 273.55, 304.77, 297.29, 294.45, 305.55, 298.58, 322.06, 313.03, 323.1, 321.29, 402.58, 312.0, 413.94, 317.16, 423.23, 332.65, 474.84, 327.48, 501.68, 334.71, 501.68, 476.13, 85.68, 472.0, 51.61, 401.81, 51.61, 261.42]], "area": 83880.4424, "iscrowd": 0, "image_id": 323133, "bbox": [51.61, 234.58, 450.07, 241.55], "category_id": 63, "id": 114243, "split": "val", "sentences": [{"tokens": ["the", "couch", "with", "the", "cat", "on", "it"], "raw": "The couch with the cat on it", "sent_id": 87354, "sent": "the couch with the cat on it"}, {"tokens": ["the", "black", "sofa", "with", "the", "cat", "on", "it"], "raw": "the black sofa with the cat on it", "sent_id": 87355, "sent": "the black sofa with the cat on it"}], "file_name": "COCO_train2014_000000323133_114243.jpg", "ann_id": 114243, "sent_ids": [87354, 87355], "ref_id": 38547}, {"segmentation": [[201.86, 177.92, 200.77, 132.21, 204.03, 110.99, 209.47, 90.86, 214.91, 78.89, 225.25, 72.91, 227.43, 69.64, 227.43, 64.2, 222.53, 62.03, 216.55, 51.69, 212.19, 58.76, 210.02, 63.11, 210.02, 66.92, 208.38, 76.72, 200.22, 77.8, 195.33, 73.45, 196.42, 60.94, 198.05, 48.97, 210.02, 37.54, 220.9, 32.1, 238.85, 31.56, 245.93, 33.73, 267.15, 34.28, 291.09, 32.1, 305.78, 44.62, 310.67, 55.5, 312.85, 60.94, 313.94, 69.64, 313.94, 77.26, 309.58, 83.25, 309.58, 83.79, 344.95, 94.13, 372.15, 101.74, 416.77, 108.82, 446.69, 107.18, 464.65, 110.99, 476.08, 120.24, 491.31, 136.57, 500.02, 152.34, 502.19, 164.86, 507.09, 183.9, 505.46, 195.33, 458.12, 200.22, 439.62, 196.96, 366.17, 191.52, 324.82, 188.25, 278.57, 183.9, 229.6, 179.55, 202.94, 180.64, 200.77, 175.74]], "area": 32459.716549999994, "iscrowd": 0, "image_id": 498297, "bbox": [195.33, 31.56, 311.76, 168.66], "category_id": 20, "id": 61335, "split": "val", "sentences": [{"tokens": ["a", "fluffy", "sheep", "standing", "between", "two", "other", "sheep"], "raw": "A fluffy sheep standing between two other sheep.", "sent_id": 87362, "sent": "a fluffy sheep standing between two other sheep"}, {"tokens": ["a", "picture", "of", "a", "white", "sheep", "with", "black", "horns", "standing", "in", "the", "middle", "of", "two", "other", "sheep"], "raw": "A picture of a white sheep with black horns standing in the middle of two other sheep.", "sent_id": 87363, "sent": "a picture of a white sheep with black horns standing in the middle of two other sheep"}], "file_name": "COCO_train2014_000000498297_61335.jpg", "ann_id": 61335, "sent_ids": [87362, 87363], "ref_id": 38550}, {"segmentation": [[10.79, 255.64, 38.83, 294.47, 65.8, 311.73, 128.36, 333.3, 195.24, 322.52, 249.17, 264.27, 264.27, 216.81, 247.01, 183.37, 211.42, 163.96, 163.96, 158.56, 84.13, 167.19, 32.36, 188.76, 7.55, 212.49, 3.24, 244.85]], "area": 33871.7632, "iscrowd": 0, "image_id": 226046, "bbox": [3.24, 158.56, 261.03, 174.74], "category_id": 51, "id": 711780, "split": "val", "sentences": [{"tokens": ["a", "soup", "served", "with", "hamburg", "on", "atable"], "raw": "A soup served with hamburg on atable", "sent_id": 87558, "sent": "a soup served with hamburg on atable"}, {"tokens": ["brown", "bowl", "of", "soup"], "raw": "brown bowl of soup", "sent_id": 87559, "sent": "brown bowl of soup"}], "file_name": "COCO_train2014_000000226046_711780.jpg", "ann_id": 711780, "sent_ids": [87558, 87559], "ref_id": 38633}, {"segmentation": [[52.88, 37.84, 44.64, 180.69, 57.69, 194.43, 146.29, 194.43, 159.34, 181.38, 157.96, 173.83, 150.41, 36.47, 143.54, 30.97, 78.3, 26.16, 54.94, 30.29]], "area": 17362.24835, "iscrowd": 0, "image_id": 243823, "bbox": [44.64, 26.16, 114.7, 168.27], "category_id": 85, "id": 335921, "split": "val", "sentences": [{"tokens": ["the", "grey", "digital", "clock", "that", "displays", "temperature"], "raw": "The grey digital clock that displays temperature.", "sent_id": 87626, "sent": "the grey digital clock that displays temperature"}, {"tokens": ["a", "silver", ",", "rectangular", "digital", "clock", "with", "weather", "and", "temperature", "options"], "raw": "A silver, rectangular digital clock with weather and temperature options.", "sent_id": 87627, "sent": "a silver , rectangular digital clock with weather and temperature options"}], "file_name": "COCO_train2014_000000243823_335921.jpg", "ann_id": 335921, "sent_ids": [87626, 87627], "ref_id": 38660}, {"segmentation": [[161.44, 249.46, 151.89, 221.76, 154.75, 211.25, 153.8, 190.23, 152.84, 182.59, 162.39, 168.26, 169.08, 152.02, 189.14, 129.1, 222.57, 132.92, 241.68, 179.72, 243.59, 198.83, 237.86, 220.8, 233.08, 271.43, 227.35, 299.13, 189.14, 316.33, 162.39, 308.68, 150.93, 304.86, 149.02, 298.18, 150.93, 283.85, 165.26, 253.28, 163.35, 243.73]], "area": 13469.743500000002, "iscrowd": 0, "image_id": 395013, "bbox": [149.02, 129.1, 94.57, 187.23], "category_id": 4, "id": 149634, "split": "val", "sentences": [{"tokens": ["a", "police", "motorcycle", "to", "the", "left", "of", "the", "other", "motorcycle"], "raw": "A police motorcycle to the left of the other motorcycle.", "sent_id": 87636, "sent": "a police motorcycle to the left of the other motorcycle"}, {"tokens": ["a", "police", "officer", "driving", "a", "motorcycle", "on", "the", "right", "side", "of", "the", "road"], "raw": "a police officer driving a motorcycle on the right side of the road", "sent_id": 87637, "sent": "a police officer driving a motorcycle on the right side of the road"}], "file_name": "COCO_train2014_000000395013_149634.jpg", "ann_id": 149634, "sent_ids": [87636, 87637], "ref_id": 38663}, {"segmentation": [[589.39, 242.73, 589.39, 222.67, 594.17, 219.8, 602.77, 186.37, 601.81, 174.9, 619.01, 162.49, 619.01, 142.43, 612.32, 130.96, 594.17, 128.1, 577.93, 135.74, 563.6, 153.89, 562.65, 157.71, 545.45, 155.8, 529.21, 162.49, 507.24, 180.64, 487.18, 218.85, 484.32, 225.53, 472.85, 232.22, 469.99, 244.64, 467.12, 260.88, 465.21, 277.12, 462.34, 302.91, 463.3, 331.57, 476.67, 351.63, 480.49, 369.78, 482.4, 378.37, 507.24, 379.33, 520.62, 370.73, 529.21, 341.12, 541.63, 336.34, 542.59, 299.09, 534.94, 269.47, 544.5, 256.1, 553.09, 243.68, 561.69, 225.53, 561.69, 267.56, 579.84, 269.47, 592.26, 273.3, 600.86, 280.94, 601.81, 290.49, 607.54, 299.09, 616.14, 288.58, 619.01, 275.21, 609.45, 260.88, 592.26, 242.73]], "area": 20630.16455, "iscrowd": 0, "image_id": 455874, "bbox": [462.34, 128.1, 156.67, 251.23], "category_id": 1, "id": 496039, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "white", "with", "a", "black", "apron"], "raw": "A man in white with a black apron.", "sent_id": 87693, "sent": "a man in white with a black apron"}, {"tokens": ["a", "cook", "in", "a", "white", "shirt", "bending", "over", "to", "wash", "his", "hands"], "raw": "A cook in a white shirt bending over to wash his hands.", "sent_id": 87694, "sent": "a cook in a white shirt bending over to wash his hands"}], "file_name": "COCO_train2014_000000455874_496039.jpg", "ann_id": 496039, "sent_ids": [87693, 87694], "ref_id": 38682}, {"segmentation": [[109.25, 193.69, 113.74, 202.67, 133.2, 199.68, 180.34, 206.41, 249.19, 211.65, 241.71, 223.62, 243.95, 228.11, 150.41, 219.88, 160.89, 264.78, 152.66, 264.78, 137.69, 214.64, 89.05, 210.15, 83.81, 238.59, 75.58, 271.51, 71.84, 271.51, 72.59, 209.4, 65.85, 200.42, 74.08, 196.68, 65.1, 163.01, 80.82, 151.78, 97.28, 151.78, 103.27, 189.95, 110.75, 197.43], [136.94, 156.27, 143.68, 128.59, 321.03, 139.06, 309.05, 159.27, 266.4, 158.52, 240.21, 154.03, 227.49, 163.76, 184.09, 166.0, 151.91, 173.48, 138.44, 165.25], [411.57, 142.06, 442.25, 143.55, 440.76, 170.49, 428.04, 203.42, 433.27, 244.57, 447.49, 290.22, 437.02, 293.21, 415.31, 226.61, 373.41, 234.1, 355.45, 304.44, 351.71, 295.46, 347.22, 227.36, 251.43, 225.12, 264.9, 216.14, 299.33, 216.14, 349.46, 216.14, 352.46, 177.97, 385.38, 170.49, 402.59, 170.49, 416.81, 173.48]], "area": 18590.6348, "iscrowd": 0, "image_id": 132430, "bbox": [65.1, 128.59, 382.39, 175.85], "category_id": 15, "id": 578197, "split": "val", "sentences": [{"tokens": ["a", "faded", "and", "worn", "light", "wood", "bench", "with", "iron", "legs", "that", "also", "form", "arm", "braces"], "raw": "A faded and worn light wood bench with iron legs that also form arm braces.", "sent_id": 87722, "sent": "a faded and worn light wood bench with iron legs that also form arm braces"}, {"tokens": ["wooden", "bench", "in", "the", "image"], "raw": "wooden bench in the image", "sent_id": 87723, "sent": "wooden bench in the image"}], "file_name": "COCO_train2014_000000132430_578197.jpg", "ann_id": 578197, "sent_ids": [87722, 87723], "ref_id": 38690}, {"segmentation": [[368.81, 250.86, 356.55, 241.52, 350.13, 218.75, 355.39, 204.16, 341.37, 173.21, 327.36, 167.96, 322.69, 149.27, 311.01, 144.6, 304.01, 147.52, 305.76, 159.2, 306.93, 169.13, 307.51, 172.04, 310.43, 183.14, 314.52, 192.48, 311.01, 204.16, 308.68, 217.0, 309.85, 225.76, 307.51, 243.86, 310.43, 252.62, 306.34, 260.21, 304.59, 285.31, 313.93, 294.07, 315.68, 304.58, 321.52, 315.09, 333.2, 322.68, 338.45, 320.34, 329.11, 302.83, 332.03, 298.16, 330.28, 281.81, 334.95, 273.63, 332.62, 257.87, 336.12, 252.03, 344.29, 270.13, 360.06, 300.49, 366.48, 302.24, 374.65, 314.5, 385.16, 316.26, 386.33, 308.67, 375.24, 291.15, 378.16, 278.89, 371.15, 262.54]], "area": 6925.495299999999, "iscrowd": 0, "image_id": 577206, "bbox": [304.01, 144.6, 82.32, 178.08], "category_id": 1, "id": 532308, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "sunglasses", "and", "a", "pink", "shirt", "is", "skiing"], "raw": "A woman in sunglasses and a pink shirt is skiing.", "sent_id": 87766, "sent": "a woman in sunglasses and a pink shirt is skiing"}, {"tokens": ["the", "girl", "in", "a", "pink", "top"], "raw": "the girl in a pink top.", "sent_id": 87767, "sent": "the girl in a pink top"}], "file_name": "COCO_train2014_000000577206_532308.jpg", "ann_id": 532308, "sent_ids": [87766, 87767], "ref_id": 38709}, {"segmentation": [[392.7, 204.78, 358.99, 198.03, 324.44, 175.28, 311.8, 144.1, 317.7, 116.29, 323.6, 87.64, 341.29, 61.52, 381.74, 48.03, 417.13, 49.72, 450.0, 68.26, 466.85, 100.28, 471.91, 144.1, 455.9, 174.44, 430.62, 192.98, 394.38, 201.4]], "area": 19326.6013, "iscrowd": 0, "image_id": 322411, "bbox": [311.8, 48.03, 160.11, 156.75], "category_id": 51, "id": 1039995, "split": "val", "sentences": [{"tokens": ["bowl", "of", "watermelon"], "raw": "Bowl of watermelon.", "sent_id": 87893, "sent": "bowl of watermelon"}, {"tokens": ["a", "bowl", "of", "cut", "watermelon", "chunks"], "raw": "A bowl of cut watermelon chunks.", "sent_id": 87894, "sent": "a bowl of cut watermelon chunks"}], "file_name": "COCO_train2014_000000322411_1039995.jpg", "ann_id": 1039995, "sent_ids": [87893, 87894], "ref_id": 38755}, {"segmentation": [[1.52, 60.85, 12.26, 67.3, 13.34, 81.26, 12.26, 93.07, 7.97, 98.44, 9.04, 104.88, 16.56, 116.69, 29.44, 138.17, 35.89, 154.28, 38.03, 167.16, 42.33, 181.12, 44.48, 197.23, 44.48, 204.75, 43.4, 214.41, 39.11, 220.85, 34.81, 224.07, 33.74, 228.37, 33.74, 240.18, 36.96, 250.92, 45.55, 267.03, 50.92, 275.62, 51.99, 283.13, 46.62, 297.09, 46.62, 307.83, 45.55, 317.5, 47.7, 333.6, 57.36, 351.86, 67.03, 380.85, 70.25, 389.44, 80.99, 411.99, 82.06, 422.73, 82.06, 430.25, 69.17, 424.88, 62.73, 420.58, 50.92, 416.29, 34.81, 411.99, 14.41, 406.62, 3.67, 406.62, 0.45, 405.55]], "area": 14269.0021, "iscrowd": 0, "image_id": 485014, "bbox": [0.45, 60.85, 81.61, 369.4], "category_id": 1, "id": 561742, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "striped", "shirt", "facing", "away", "from", "an", "overjoyed", "woman", "playing", "a", "nintendo", "wii", "game"], "raw": "The back of a striped shirt facing away from an overjoyed woman playing a Nintendo Wii game.", "sent_id": 88016, "sent": "the back of a striped shirt facing away from an overjoyed woman playing a nintendo wii game"}, {"tokens": ["a", "man", "in", "a", "striped", "shirt"], "raw": "a man in a striped shirt", "sent_id": 88017, "sent": "a man in a striped shirt"}], "file_name": "COCO_train2014_000000485014_561742.jpg", "ann_id": 561742, "sent_ids": [88016, 88017], "ref_id": 38800}, {"segmentation": [[193.45, 157.57, 193.45, 173.13, 196.13, 176.89, 212.23, 176.89, 217.6, 170.99, 220.82, 164.55, 214.91, 160.79, 214.91, 155.96], [244.43, 134.49, 236.38, 139.86, 236.38, 161.33, 233.16, 169.91, 228.33, 173.67, 227.79, 182.79, 253.55, 179.03, 262.14, 173.67, 270.19, 170.99, 275.02, 169.91, 288.43, 169.91, 294.34, 169.91, 294.34, 146.84, 299.17, 148.98, 308.29, 146.3, 313.12, 127.52, 321.7, 83.51, 307.22, 80.83, 270.19, 79.76, 270.19, 85.66, 278.77, 91.03, 281.99, 99.07, 284.68, 111.42, 279.85, 121.61, 279.85, 130.2, 277.16, 132.88, 265.36, 133.96]], "area": 5081.61615, "iscrowd": 0, "image_id": 65407, "bbox": [193.45, 79.76, 128.25, 103.03], "category_id": 63, "id": 2225012, "split": "val", "sentences": [{"tokens": ["the", "chair", "where", "the", "woman", "in", "a", "spotted", "shirt", "is", "sitting"], "raw": "The chair where the woman in a spotted shirt is sitting.", "sent_id": 88044, "sent": "the chair where the woman in a spotted shirt is sitting"}, {"tokens": ["the", "red", "chair", "the", "woman", "in", "blue", "jeans", "is", "sitting", "in"], "raw": "The red chair the woman in blue jeans is sitting in.", "sent_id": 88045, "sent": "the red chair the woman in blue jeans is sitting in"}], "file_name": "COCO_train2014_000000065407_2225012.jpg", "ann_id": 2225012, "sent_ids": [88044, 88045], "ref_id": 38810}, {"segmentation": [[183.31, 284.91, 198.5, 284.91, 230.05, 284.33, 249.91, 284.33, 261.59, 288.42, 264.51, 292.51, 260.05, 305.94, 265.9, 320.51, 253.04, 316.42, 230.85, 305.32, 227.34, 302.4, 220.92, 298.32, 210.99, 295.39, 202.22, 294.81, 185.87, 294.23], [225.81, 346.37, 239.83, 348.7, 249.76, 349.29, 257.93, 348.7, 264.94, 349.29, 266.11, 371.48, 262.61, 367.98, 255.01, 365.64, 248.59, 365.06, 235.15, 365.06, 231.65, 368.56, 226.39, 369.73, 224.05, 369.15, 222.89, 358.05, 222.89, 351.04, 222.89, 346.95], [124.75, 380.21, 124.75, 393.06, 146.36, 393.65, 147.53, 387.22, 147.53, 383.72, 144.61, 378.46, 143.44, 378.46, 139.35, 377.88, 128.84, 380.21], [124.75, 338.15, 119.49, 351.59, 126.5, 351.59, 132.93, 346.92, 132.34, 342.83, 130.59, 340.49], [115.4, 310.12, 111.32, 325.89, 115.4, 324.13, 119.49, 321.21, 121.25, 315.37, 121.25, 311.28]], "area": 2732.12775, "iscrowd": 0, "image_id": 56677, "bbox": [111.32, 284.33, 154.79, 109.32], "category_id": 62, "id": 380823, "split": "val", "sentences": [{"tokens": ["the", "chair", "in", "which", "the", "child", "is", "sitting"], "raw": "the chair in which the child is sitting", "sent_id": 88117, "sent": "the chair in which the child is sitting"}, {"tokens": ["a", "blue", "and", "white", "lawn", "chair"], "raw": "A blue and white lawn chair.", "sent_id": 88118, "sent": "a blue and white lawn chair"}], "file_name": "COCO_train2014_000000056677_380823.jpg", "ann_id": 380823, "sent_ids": [88117, 88118], "ref_id": 38838}, {"segmentation": [[156.25, 250.62, 118.75, 253.13, 107.5, 275.63, 102.5, 336.88, 96.25, 421.88, 146.25, 426.88, 177.5, 428.13, 203.75, 433.13, 211.25, 433.13, 211.25, 396.88, 192.5, 408.13, 178.75, 415.63, 145.0, 410.63, 123.75, 379.38, 116.25, 360.63, 130.0, 328.13, 123.75, 306.88, 146.25, 276.88]], "area": 6442.325, "iscrowd": 0, "image_id": 496732, "bbox": [96.25, 250.62, 115.0, 182.51], "category_id": 62, "id": 1939387, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "the", "seat", "to", "the", "left", "of", "the", "man"], "raw": "The back of the seat to the left of the man.", "sent_id": 88119, "sent": "the back of the seat to the left of the man"}], "file_name": "COCO_train2014_000000496732_1939387.jpg", "ann_id": 1939387, "sent_ids": [88119], "ref_id": 38839}, {"segmentation": [[296.41, 146.56, 289.1, 152.41, 287.46, 157.16, 287.64, 161.91, 287.46, 168.3, 288.74, 175.06, 291.29, 179.44, 289.65, 180.17, 291.11, 182.55, 291.66, 184.37, 289.28, 185.84, 286.91, 187.66, 287.09, 191.13, 281.98, 193.14, 277.96, 198.26, 276.5, 206.29, 274.67, 214.15, 273.21, 217.8, 271.38, 222.0, 271.02, 225.47, 268.83, 235.7, 267.73, 239.53, 267.91, 243.01, 268.83, 244.65, 268.1, 249.4, 267.73, 253.23, 269.92, 254.51, 267.18, 257.43, 266.63, 259.81, 265.17, 263.83, 267.36, 263.65, 269.37, 270.4, 273.21, 271.13, 277.78, 267.85, 277.96, 273.51, 279.24, 279.17, 278.87, 283.74, 278.51, 288.12, 277.78, 292.32, 271.93, 293.6, 265.11, 320.06, 264.15, 337.42, 265.14, 348.32, 266.13, 357.24, 271.09, 364.67, 272.57, 351.29, 274.06, 348.32, 277.03, 342.37, 288.43, 340.88, 292.4, 333.45, 281.99, 331.47, 273.56, 323.54, 276.04, 320.57, 284.47, 325.03, 302.31, 330.97, 320.15, 329.98, 318.66, 324.53, 320.15, 322.05, 325.1, 307.68, 324.61, 302.23, 320.64, 297.27, 323.62, 289.35, 322.13, 276.96, 328.57, 272.5, 328.57, 259.61, 340.96, 256.14, 341.46, 237.81, 341.95, 207.58, 337.99, 203.12, 336.01, 193.7, 337.99, 186.76, 332.54, 182.3, 324.61, 177.84, 318.17, 175.36, 322.63, 170.5, 319.65, 157.62, 316.18, 151.17, 311.72, 146.22, 305.78, 145.23, 298.84, 146.22], [292.01, 335.33, 289.49, 339.52, 295.36, 347.49, 297.88, 355.05, 302.08, 356.73, 309.63, 354.21, 314.25, 353.37, 319.7, 339.1, 319.28, 337.84, 311.73, 336.58, 303.76, 335.75, 294.94, 334.07], [348.08, 208.1, 347.09, 222.97, 347.09, 234.86, 346.59, 250.23, 349.56, 252.21, 352.04, 244.28, 349.07, 242.3, 353.53, 237.84, 354.02, 222.47, 354.02, 218.01, 351.55, 210.08, 349.56, 209.09]], "area": 10934.238949999999, "iscrowd": 0, "image_id": 186198, "bbox": [264.15, 145.23, 89.87, 219.44], "category_id": 1, "id": 436416, "split": "val", "sentences": [{"tokens": ["a", "person", "wearing", "a", "black", "and", "yellow", "stripped", "jacket"], "raw": "A person wearing a black and yellow stripped jacket.", "sent_id": 88138, "sent": "a person wearing a black and yellow stripped jacket"}], "file_name": "COCO_train2014_000000186198_436416.jpg", "ann_id": 436416, "sent_ids": [88138], "ref_id": 38846}, {"segmentation": [[527.62, 128.33, 495.92, 149.8, 489.79, 164.11, 523.53, 165.14, 535.8, 153.89, 550.12, 148.78, 548.07, 131.39, 557.27, 116.06, 571.59, 116.06, 570.57, 91.52, 580.79, 52.66, 587.95, 36.3, 595.11, 79.25, 594.09, 107.88, 596.13, 128.33, 604.31, 152.87, 593.06, 163.09, 603.29, 172.3, 637.03, 178.43, 640.0, 173.32, 626.81, 157.98, 616.58, 144.69, 618.63, 122.19, 628.85, 103.79, 627.83, 78.22, 631.92, 60.84, 634.77, 44.24, 640.0, 28.72, 639.73, 0.0, 534.2, 0.79, 534.82, 21.27, 530.49, 43.51, 534.47, 64.22, 528.1, 92.9, 528.1, 106.45, 529.69, 125.57, 527.3, 131.15]], "area": 13538.935849999996, "iscrowd": 0, "image_id": 295613, "bbox": [489.79, 0.0, 150.21, 178.43], "category_id": 1, "id": 511031, "split": "val", "sentences": [{"tokens": ["black", "capri", "'", "s", "that", "a", "being", "worn", "by", "the", "person", "in", "the", "background"], "raw": "Black capri's that a being worn by the person in the background.", "sent_id": 88166, "sent": "black capri ' s that a being worn by the person in the background"}, {"tokens": ["a", "person", "wearing", "black", "shoes", "stands", "behind", "a", "child", "holding", "out", "a", "toy", "to", "another", "person"], "raw": "A person wearing black shoes stands behind a child holding out a toy to another person", "sent_id": 88167, "sent": "a person wearing black shoes stands behind a child holding out a toy to another person"}], "file_name": "COCO_train2014_000000295613_511031.jpg", "ann_id": 511031, "sent_ids": [88166, 88167], "ref_id": 38859}, {"segmentation": [[400.08, 135.93, 429.0, 142.68, 458.89, 143.64, 497.45, 136.89, 511.91, 132.07, 514.8, 153.28, 509.02, 156.18, 507.09, 197.63, 512.87, 200.52, 509.98, 241.01, 496.48, 244.87, 481.06, 254.51, 466.6, 260.29, 467.56, 277.64, 466.6, 290.18, 306.57, 316.21, 285.36, 348.98, 266.08, 375.98, 251.62, 374.05, 239.08, 363.44, 230.41, 363.44, 229.44, 345.13, 210.16, 329.7, 206.31, 322.96, 201.49, 305.6, 190.88, 296.93, 192.81, 285.36, 193.77, 279.57, 187.02, 268.0, 197.63, 240.05, 208.23, 231.37, 231.37, 231.37, 306.57, 224.62, 333.56, 223.66, 362.48, 220.77, 368.27, 215.95, 360.55, 209.2, 371.16, 202.45, 378.87, 190.88, 397.19, 194.74, 402.01, 137.86]], "area": 37546.96045, "iscrowd": 0, "image_id": 54318, "bbox": [187.02, 132.07, 327.78, 243.91], "category_id": 65, "id": 1611326, "split": "val", "sentences": [{"tokens": ["a", "bed", "with", "red", "bedding", "next", "to", "a", "window"], "raw": "A bed with red bedding next to a window", "sent_id": 88271, "sent": "a bed with red bedding next to a window"}, {"tokens": ["a", "bed", "with", "two", "pillows", "on", "it", "near", "the", "windows"], "raw": "A bed with two pillows on it near the windows.", "sent_id": 88272, "sent": "a bed with two pillows on it near the windows"}], "file_name": "COCO_train2014_000000054318_1611326.jpg", "ann_id": 1611326, "sent_ids": [88271, 88272], "ref_id": 38901}, {"segmentation": [[232.16, 73.49, 289.92, 55.11, 350.31, 37.61, 403.7, 37.61, 514.84, 56.86, 539.35, 69.12, 554.23, 100.62, 561.23, 126.88, 556.85, 150.51, 542.85, 222.27, 527.97, 278.29, 534.1, 336.05, 543.73, 376.31, 526.22, 381.56, 513.09, 382.43, 485.96, 372.81, 502.59, 305.42, 524.47, 221.4, 524.47, 199.52, 506.97, 224.9, 471.96, 272.16, 471.08, 308.04, 478.96, 343.05, 476.34, 377.18, 417.7, 377.18, 430.83, 318.55, 416.82, 276.54, 400.19, 245.91, 394.94, 233.65, 391.44, 229.28, 386.19, 228.4, 380.94, 232.78, 376.56, 243.28, 381.82, 311.54, 394.94, 368.43, 393.19, 371.93, 358.19, 378.93, 344.18, 376.31, 338.06, 365.81, 345.06, 351.8, 351.18, 342.18, 322.3, 268.66, 296.05, 336.05, 297.8, 365.81, 286.42, 368.43, 264.54, 368.43, 246.16, 368.43, 236.53, 362.31, 257.54, 339.55, 265.42, 327.3, 255.79, 300.17, 236.53, 302.79, 214.65, 293.17, 210.28, 259.03, 208.53, 218.77, 192.77, 132.13, 202.4, 105.87]], "area": 92770.17550000004, "iscrowd": 0, "image_id": 500214, "bbox": [192.77, 37.61, 368.46, 344.82], "category_id": 22, "id": 1821102, "split": "val", "sentences": [{"tokens": ["a", "baby", "elephant", "with", "it", "'", "s", "mouth", "open"], "raw": "A baby elephant with it's mouth open.", "sent_id": 88323, "sent": "a baby elephant with it ' s mouth open"}, {"tokens": ["a", "baby", "elephant", "looking", "at", "the", "ground"], "raw": "A baby Elephant looking at the ground.", "sent_id": 88324, "sent": "a baby elephant looking at the ground"}], "file_name": "COCO_train2014_000000500214_1821102.jpg", "ann_id": 1821102, "sent_ids": [88323, 88324], "ref_id": 38919}, {"segmentation": [[512.43, 384.04, 511.92, 348.05, 511.42, 335.38, 511.42, 321.69, 511.42, 295.84, 505.84, 265.43, 508.88, 236.03, 521.99, 186.18, 531.11, 175.54, 515.91, 157.8, 508.81, 134.99, 504.76, 118.26, 500.3, 110.48, 502.26, 76.65, 502.26, 68.2, 510.06, 57.14, 531.53, 38.92, 550.4, 38.27, 570.56, 46.08, 588.13, 66.9, 588.78, 271.17, 589.81, 420.34, 584.88, 405.69, 559.54, 390.81, 535.3, 385.31], [584.0, 449.52, 547.3, 476.1, 509.34, 479.9, 513.13, 576.07, 548.57, 598.85, 592.86, 593.79, 589.07, 446.99]], "area": 36788.0929, "iscrowd": 0, "image_id": 119714, "bbox": [500.3, 38.27, 92.56, 560.58], "category_id": 1, "id": 455161, "split": "val", "sentences": [{"tokens": ["man", "on", "far", "right", "of", "photo", "in", "original", "shirt"], "raw": "Man on far right of photo in original shirt.", "sent_id": 88366, "sent": "man on far right of photo in original shirt"}], "file_name": "COCO_train2014_000000119714_455161.jpg", "ann_id": 455161, "sent_ids": [88366], "ref_id": 38935}, {"segmentation": [[142.33, 420.41, 113.68, 393.66, 104.12, 391.83, 65.91, 418.58, 64.0, 425.27, 0.0, 426.22, 0.96, 207.47, 49.67, 217.98, 119.41, 248.55, 170.04, 264.79, 235.95, 330.7, 260.79, 388.97, 269.38, 426.22, 142.33, 426.22, 142.33, 420.49]], "area": 41110.86120000001, "iscrowd": 0, "image_id": 210279, "bbox": [0.0, 207.47, 269.38, 218.75], "category_id": 24, "id": 590634, "split": "val", "sentences": [{"tokens": ["a", "zebras", "neck", "is", "bent", "down"], "raw": "A zebras neck is bent down.", "sent_id": 88367, "sent": "a zebras neck is bent down"}, {"tokens": ["a", "zebra", "grazing", "in", "the", "field"], "raw": "A zebra grazing in the field", "sent_id": 88368, "sent": "a zebra grazing in the field"}], "file_name": "COCO_train2014_000000210279_590634.jpg", "ann_id": 590634, "sent_ids": [88367, 88368], "ref_id": 38936}, {"segmentation": [[36.62, 4.77, 43.84, 21.19, 29.4, 25.13, 14.95, 32.35, 5.76, 47.45, 5.1, 60.58, 12.32, 73.71, 24.8, 84.88, 43.18, 84.22, 66.82, 79.62, 68.79, 77.65, 81.27, 80.28, 88.23, 86.11, 108.1, 93.34, 113.98, 99.66, 128.88, 91.98, 160.49, 77.08, 187.13, 66.24, 193.91, 49.53, 196.16, 26.5, 199.33, 17.02, 200.23, 0.76, 187.08, 0.0, 120.51, 0.0, 37.08, 1.69, 37.08, 5.06]], "area": 14462.306400000001, "iscrowd": 0, "image_id": 229002, "bbox": [5.1, 0.0, 195.13, 99.66], "category_id": 47, "id": 671189, "split": "val", "sentences": [{"tokens": ["a", "rose", "cup", "with", "a", "handle", "containing", "some", "black", "tea"], "raw": "A rose cup with a handle containing some black tea.", "sent_id": 88402, "sent": "a rose cup with a handle containing some black tea"}, {"tokens": ["a", "pink", "coffee", "cup", "with", "someting", "in", "it"], "raw": "A pink coffee cup with someting in it.", "sent_id": 88403, "sent": "a pink coffee cup with someting in it"}], "file_name": "COCO_train2014_000000229002_671189.jpg", "ann_id": 671189, "sent_ids": [88402, 88403], "ref_id": 38952}, {"segmentation": [[594.75, 426.2, 498.24, 426.62, 482.23, 427.0, 355.79, 427.0, 352.0, 423.67, 339.35, 395.43, 335.56, 396.69, 310.69, 383.21, 303.95, 380.68, 313.22, 368.46, 325.44, 373.51, 363.8, 362.13, 411.42, 342.75, 450.62, 328.42, 444.29, 295.97, 470.42, 288.8, 477.59, 317.88, 498.24, 307.35, 496.56, 298.07, 501.19, 293.02, 513.83, 297.23, 533.22, 293.02, 540.81, 290.07, 537.44, 274.47, 533.22, 224.74, 537.44, 226.0, 541.65, 274.89, 540.81, 257.61, 547.55, 260.14, 549.24, 285.01, 582.11, 272.79, 578.74, 250.87, 582.95, 250.87, 584.64, 269.84, 626.79, 252.56, 638.67, 244.18, 640.0, 239.96, 640.0, 368.93, 639.09, 422.88, 639.09, 427.0]], "area": 36898.66205, "iscrowd": 0, "image_id": 266228, "bbox": [303.95, 224.74, 336.05, 202.26], "category_id": 9, "id": 179457, "split": "val", "sentences": [{"tokens": ["a", "green", "and", "white", "boat"], "raw": "A green and white boat.", "sent_id": 88414, "sent": "a green and white boat"}, {"tokens": ["the", "boat", "that", "is", "green", "and", "white"], "raw": "The boat that is green and white.", "sent_id": 88415, "sent": "the boat that is green and white"}], "file_name": "COCO_train2014_000000266228_179457.jpg", "ann_id": 179457, "sent_ids": [88414, 88415], "ref_id": 38957}, {"segmentation": [[451.45, 3.32, 459.19, 53.11, 448.13, 101.8, 407.19, 96.26, 407.19, 70.82, 381.74, 55.32, 373.99, 48.69, 357.4, 25.45, 356.29, 45.37, 359.61, 63.07, 351.86, 75.24, 351.86, 86.31, 315.35, 84.09, 279.94, 84.09, 235.68, 86.31, 227.94, 75.24, 217.98, 69.71, 214.66, 53.11, 226.83, 52.01, 208.02, 39.83, 184.78, 40.94, 160.44, 47.58, 134.99, 57.54, 132.78, 26.56, 142.74, 4.43]], "area": 21441.06235, "iscrowd": 0, "image_id": 491249, "bbox": [132.78, 3.32, 326.41, 98.48], "category_id": 1, "id": 2031382, "split": "val", "sentences": [{"tokens": ["blurry", "person", "sitting", "behind", "pizza"], "raw": "Blurry person sitting behind pizza.", "sent_id": 88446, "sent": "blurry person sitting behind pizza"}, {"tokens": ["the", "person", "in", "the", "purple", "behind", "the", "pizza"], "raw": "the person in the purple behind the pizza", "sent_id": 88447, "sent": "the person in the purple behind the pizza"}], "file_name": "COCO_train2014_000000491249_2031382.jpg", "ann_id": 2031382, "sent_ids": [88446, 88447], "ref_id": 38970}, {"segmentation": [[522.38, 337.16, 381.53, 363.78, 401.49, 330.51, 407.04, 309.44, 399.27, 285.04, 388.18, 265.07, 317.2, 258.42, 298.35, 256.2, 283.93, 241.78, 451.4, 235.13], [206.29, 348.25, 138.64, 338.27, 173.02, 279.49, 190.76, 299.45, 209.62, 306.11, 197.42, 324.96]], "area": 15413.953899999997, "iscrowd": 0, "image_id": 18093, "bbox": [138.64, 235.13, 383.74, 128.65], "category_id": 79, "id": 2139695, "split": "val", "sentences": [{"tokens": ["the", "door", "of", "the", "oven"], "raw": "The door of the oven", "sent_id": 88571, "sent": "the door of the oven"}, {"tokens": ["the", "oven", "door"], "raw": "The oven door.", "sent_id": 88572, "sent": "the oven door"}], "file_name": "COCO_train2014_000000018093_2139695.jpg", "ann_id": 2139695, "sent_ids": [88571, 88572], "ref_id": 39013}, {"segmentation": [[196.31, 343.01, 181.21, 332.22, 170.43, 314.97, 172.58, 295.55, 177.98, 281.53, 176.9, 259.96, 174.74, 238.38, 174.74, 225.44, 179.06, 214.65, 185.53, 198.47, 216.81, 181.21, 227.6, 181.21, 255.64, 175.82, 282.61, 187.69, 298.79, 200.63, 312.81, 216.81, 318.2, 224.36, 321.44, 266.43, 321.44, 278.29, 321.44, 297.71, 326.83, 306.34, 321.44, 318.2, 320.36, 326.83, 317.12, 336.54, 296.63, 345.17, 291.24, 354.88, 277.21, 361.35, 251.33, 366.74, 244.85, 366.74, 225.44, 367.82, 211.42, 359.19, 197.39, 343.01]], "area": 23755.641400000008, "iscrowd": 0, "image_id": 566319, "bbox": [170.43, 175.82, 156.4, 192.0], "category_id": 64, "id": 20286, "split": "val", "sentences": [{"tokens": ["a", "reddish", "planter", "filled", "with", "soil", "and", "plants", "just", "beginning", "to", "emerge"], "raw": "A reddish planter filled with soil and plants just beginning to emerge.", "sent_id": 88609, "sent": "a reddish planter filled with soil and plants just beginning to emerge"}], "file_name": "COCO_train2014_000000566319_20286.jpg", "ann_id": 20286, "sent_ids": [88609], "ref_id": 39028}, {"segmentation": [[45.05, 235.92, 30.41, 278.72, 25.9, 345.16, 25.9, 422.86, 23.65, 482.55, 30.41, 499.44, 222.97, 500.0, 197.07, 489.3, 120.5, 439.75, 29.28, 382.32, 32.66, 358.67, 43.92, 354.17, 97.97, 348.54, 111.49, 338.4, 114.86, 331.64, 147.52, 331.64, 156.53, 346.28, 172.3, 344.03, 183.56, 292.23, 167.79, 225.79, 183.56, 217.91, 189.19, 192.0, 200.45, 190.88, 204.95, 186.37, 194.82, 166.1, 201.58, 155.97, 201.58, 141.33, 200.45, 118.81, 194.82, 107.55, 164.41, 96.28, 126.13, 98.54, 106.98, 114.3, 102.48, 149.21, 108.11, 181.87, 104.73, 189.75, 94.59, 196.51, 61.94, 208.9, 51.8, 221.28]], "area": 41053.31079999999, "iscrowd": 0, "image_id": 426705, "bbox": [23.65, 96.28, 199.32, 403.72], "category_id": 1, "id": 501107, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "black", "shirt", "sitting", "to", "the", "left", "of", "a", "woman", "wearing", "glasses"], "raw": "a man in a black shirt sitting to the left of a woman wearing glasses", "sent_id": 88724, "sent": "a man in a black shirt sitting to the left of a woman wearing glasses"}, {"tokens": ["the", "man", "sitting", "at", "the", "table"], "raw": "The man sitting at the table", "sent_id": 88725, "sent": "the man sitting at the table"}], "file_name": "COCO_train2014_000000426705_501107.jpg", "ann_id": 501107, "sent_ids": [88724, 88725], "ref_id": 39081}, {"segmentation": [[124.7, 211.46, 126.82, 163.2, 132.12, 148.35, 143.26, 144.11, 151.21, 138.28, 158.64, 136.69, 163.41, 129.79, 160.76, 119.19, 160.76, 110.7, 162.88, 101.69, 170.84, 93.2, 179.32, 94.79, 187.27, 91.08, 200.53, 105.93, 202.12, 118.65, 206.9, 125.02, 198.41, 129.79, 198.41, 138.81, 197.35, 140.4, 196.82, 141.99, 205.84, 144.11, 213.26, 152.59, 220.15, 175.4, 221.21, 200.47, 224.93, 213.2, 222.8, 234.41, 226.52, 246.08, 223.87, 253.5, 224.4, 264.64, 224.4, 276.3, 222.8, 290.09, 215.38, 299.64, 212.2, 301.76, 213.79, 324.56, 214.85, 340.47, 220.68, 381.83, 222.27, 399.33, 222.27, 404.11, 222.27, 410.47, 221.21, 424.26, 232.88, 439.11, 236.06, 449.18, 222.27, 448.65, 213.26, 448.65, 205.3, 442.29, 201.06, 436.98, 194.17, 429.56, 192.05, 425.32, 192.05, 418.95, 188.34, 409.94, 188.87, 397.21, 191.52, 385.02, 184.62, 354.11, 179.85, 327.59, 177.73, 317.52, 174.02, 328.65, 170.3, 346.68, 173.49, 358.88, 172.96, 379.56, 175.08, 399.71, 179.32, 409.26, 173.49, 420.4, 171.9, 436.31, 163.41, 442.67, 151.21, 441.61, 145.91, 438.43, 149.09, 425.17, 152.27, 418.28, 149.09, 406.08, 149.62, 402.37, 145.91, 398.65, 143.26, 348.81, 139.55, 317.52, 130.0, 265.33, 126.82, 253.67, 127.88, 241.47, 128.94, 231.93, 125.23, 228.21, 121.52, 220.79, 122.58, 216.55]], "area": 25442.66185, "iscrowd": 0, "image_id": 105358, "bbox": [121.52, 91.08, 114.54, 358.1], "category_id": 1, "id": 451639, "split": "val", "sentences": [{"tokens": ["an", "elderly", "man", "in", "a", "blue", "cardigan", "standing", "and", "holding", "a", "controller"], "raw": "An elderly man in a blue cardigan standing and holding a controller.", "sent_id": 88763, "sent": "an elderly man in a blue cardigan standing and holding a controller"}, {"tokens": ["a", "man", "wearing", "a", "yellow", "shirt"], "raw": "A man wearing a yellow shirt", "sent_id": 88764, "sent": "a man wearing a yellow shirt"}], "file_name": "COCO_train2014_000000105358_451639.jpg", "ann_id": 451639, "sent_ids": [88763, 88764], "ref_id": 39097}, {"segmentation": [[252.4, 355.96, 180.13, 413.12, 133.75, 454.11, 128.36, 470.29, 244.85, 473.53, 325.75, 470.29, 318.2, 414.2, 336.54, 376.45, 321.44, 348.4, 302.02, 318.2, 281.53, 327.91], [336.54, 254.56, 340.85, 212.49, 362.43, 190.92, 359.19, 167.19, 377.53, 176.9, 389.39, 163.96, 393.71, 153.17, 401.26, 167.19, 398.02, 146.7, 420.67, 172.58, 444.4, 204.94, 448.72, 225.44, 426.07, 220.04, 400.18, 217.89, 377.53, 268.58, 362.43, 303.1, 347.33, 289.08]], "area": 25720.396399999998, "iscrowd": 0, "image_id": 444346, "bbox": [128.36, 146.7, 320.36, 326.83], "category_id": 25, "id": 600194, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "who", "'", "s", "head", "is", "back", "of", "another", "giraffe"], "raw": "A giraffe who's head is back of another giraffe", "sent_id": 88841, "sent": "a giraffe who ' s head is back of another giraffe"}], "file_name": "COCO_train2014_000000444346_600194.jpg", "ann_id": 600194, "sent_ids": [88841], "ref_id": 39131}, {"segmentation": [[505.69, 186.27, 539.49, 191.79, 573.99, 180.75, 605.72, 155.22, 622.28, 122.11, 626.42, 91.76, 615.38, 56.57, 597.44, 32.42, 576.75, 16.56, 543.63, 6.21, 518.11, 9.66, 489.13, 16.56, 464.29, 35.87, 447.74, 63.47, 440.15, 98.65, 447.74, 135.22, 469.12, 166.26]], "area": 26269.380550000005, "iscrowd": 0, "image_id": 243823, "bbox": [440.15, 6.21, 186.27, 185.58], "category_id": 85, "id": 334841, "split": "val", "sentences": [{"tokens": ["a", "round", "white", "clock", "with", "black", "hands"], "raw": "a round white clock with black hands", "sent_id": 88883, "sent": "a round white clock with black hands"}, {"tokens": ["white", "clock"], "raw": "White clock", "sent_id": 88884, "sent": "white clock"}], "file_name": "COCO_train2014_000000243823_334841.jpg", "ann_id": 334841, "sent_ids": [88883, 88884], "ref_id": 39149}, {"segmentation": [[203.26, 465.95, 215.13, 471.89, 222.06, 487.71, 235.91, 494.64, 240.85, 510.46, 252.72, 515.41, 260.64, 529.26, 264.59, 538.16, 274.48, 539.15, 283.39, 532.22, 281.41, 527.28, 269.54, 518.38, 261.62, 501.56, 247.78, 473.86, 235.91, 461.01, 232.94, 459.03, 229.97, 443.2, 223.05, 421.44, 224.04, 410.56, 224.04, 390.78, 229.97, 382.86, 233.93, 378.91, 241.84, 372.97, 256.68, 363.08, 262.61, 359.12, 285.36, 351.21, 300.2, 338.35, 304.16, 333.4, 310.09, 309.66, 314.05, 292.85, 310.09, 281.97, 304.16, 276.03, 296.25, 274.06, 288.33, 275.04, 294.27, 285.92, 295.26, 293.84, 296.25, 304.72, 290.31, 317.58, 286.35, 328.46, 271.52, 329.45, 267.56, 329.45, 264.59, 329.45, 277.45, 313.62, 274.48, 294.83, 260.64, 290.87, 255.69, 286.91, 245.8, 284.94, 237.89, 284.94, 239.86, 288.89, 233.93, 295.82, 225.03, 293.84, 238.87, 250.32, 242.83, 234.49, 251.73, 214.71, 253.71, 200.86, 247.78, 198.88, 230.96, 198.88, 228.98, 199.87, 228.98, 209.76, 229.97, 215.69, 227.99, 230.53, 223.05, 244.38, 217.11, 267.13, 217.11, 272.08, 214.15, 279.0, 214.15, 290.87, 209.2, 294.83, 205.24, 295.82, 205.24, 306.7, 206.23, 312.63, 205.24, 316.59, 193.37, 334.39, 182.49, 343.3, 179.52, 350.22, 177.55, 355.17, 172.6, 370.99, 167.66, 378.91, 160.73, 394.73, 152.82, 402.65, 139.96, 449.14, 138.97, 470.9, 139.96, 485.73, 152.82, 487.71, 157.76, 500.57, 165.68, 514.42, 169.63, 520.35, 173.59, 524.31, 173.59, 529.26, 160.73, 534.2, 155.79, 539.15, 154.8, 546.07, 159.74, 552.01, 176.56, 553.99, 192.38, 553.99, 204.25, 550.03, 201.29, 541.13, 189.42, 521.34, 176.56, 492.66, 171.61, 472.87, 167.66, 471.89, 167.66, 465.95, 177.55, 448.15, 193.37, 436.28, 196.34, 446.17, 205.24, 463.97, 207.22, 466.94]], "area": 20449.62315, "iscrowd": 0, "image_id": 1407, "bbox": [138.97, 198.88, 175.08, 355.11], "category_id": 1, "id": 434962, "split": "val", "sentences": [{"tokens": ["a", "man", "playing", "tennis", "reaching", "far", "back", "to", "serve"], "raw": "A man playing tennis reaching far back to serve.", "sent_id": 88906, "sent": "a man playing tennis reaching far back to serve"}, {"tokens": ["the", "tennis", "player", "about", "to", "hit", "the", "ball"], "raw": "The tennis player about to hit the ball", "sent_id": 88907, "sent": "the tennis player about to hit the ball"}], "file_name": "COCO_train2014_000000001407_434962.jpg", "ann_id": 434962, "sent_ids": [88906, 88907], "ref_id": 39156}, {"segmentation": [[32.43, 89.1, 43.94, 115.0, 49.7, 121.48, 54.02, 127.96, 59.77, 135.87, 65.53, 142.35, 74.88, 148.82, 76.32, 156.74, 77.76, 168.97, 78.48, 174.01, 68.41, 169.69, 63.37, 169.69, 58.34, 174.01, 57.62, 198.47, 50.42, 256.75, 45.38, 268.26, 32.43, 263.23, 24.52, 165.37, 13.72, 127.96, 10.85, 86.22, 18.04, 85.5, 24.52, 85.5], [0.77, 317.19, 0.77, 144.5, 10.85, 266.1, 2.93, 277.62, 3.65, 289.85, 6.53, 300.64, 8.69, 310.71, 10.13, 312.87, 12.29, 323.67, 10.85, 330.86, 3.65, 329.42], [56.9, 330.86, 60.49, 296.32, 69.85, 297.04, 77.04, 302.08, 76.32, 307.84, 72.01, 320.79, 69.85, 327.26, 64.81, 333.02, 59.05, 335.9, 55.46, 336.62]], "area": 7364.9653, "iscrowd": 0, "image_id": 255016, "bbox": [0.77, 85.5, 77.71, 251.12], "category_id": 1, "id": 1752220, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "light", "blue", "shirt", "-", "dress", "wearing", "a", "large", "crocheted", "looking", "backpack"], "raw": "A woman in a light blue shirt-dress wearing a large crocheted looking backpack.", "sent_id": 88943, "sent": "a woman in a light blue shirt - dress wearing a large crocheted looking backpack"}, {"tokens": ["a", "person", "in", "a", "blue", "shirt"], "raw": "a person in a blue shirt", "sent_id": 88944, "sent": "a person in a blue shirt"}], "file_name": "COCO_train2014_000000255016_1752220.jpg", "ann_id": 1752220, "sent_ids": [88943, 88944], "ref_id": 39167}, {"segmentation": [[531.99, 179.27, 544.21, 173.16, 550.31, 163.17, 553.64, 160.95, 563.63, 153.18, 580.84, 145.41, 588.61, 147.07, 596.38, 148.18, 605.82, 150.96, 613.04, 154.29, 628.02, 166.5, 630.24, 168.72, 614.15, 173.72, 611.37, 174.27, 605.82, 178.71, 600.27, 185.37, 595.83, 193.7, 594.72, 204.8, 591.39, 215.35, 589.17, 222.01, 584.73, 228.67, 570.29, 242.55, 567.52, 244.77, 552.53, 254.2, 545.87, 256.98, 538.66, 259.2, 534.77, 260.31, 533.66, 260.86, 530.33, 182.04]], "area": 6164.6362500000005, "iscrowd": 0, "image_id": 445628, "bbox": [530.33, 145.41, 99.91, 115.45], "category_id": 16, "id": 40363, "split": "val", "sentences": [{"tokens": ["black", "bird", "sitting", "on", "top", "of", "a", "piece", "of", "wood", "looking", "off", "the", "screen"], "raw": "Black bird sitting on top of a piece of wood looking off the screen.", "sent_id": 89019, "sent": "black bird sitting on top of a piece of wood looking off the screen"}, {"tokens": ["the", "bird", "on", "the", "right", "is", "so", "dark", "it", "looks", "like", "a", "shadow"], "raw": "The bird on the right is so dark it looks like a shadow.", "sent_id": 89020, "sent": "the bird on the right is so dark it looks like a shadow"}], "file_name": "COCO_train2014_000000445628_40363.jpg", "ann_id": 40363, "sent_ids": [89019, 89020], "ref_id": 39199}, {"segmentation": [[67.47, 234.48, 79.96, 220.95, 98.69, 181.92, 113.78, 157.46, 130.95, 151.74, 133.56, 146.54, 129.91, 135.61, 133.03, 124.68, 140.84, 117.39, 151.25, 115.83, 161.14, 120.52, 168.42, 132.49, 168.42, 149.14, 165.82, 155.9, 160.62, 160.59, 171.54, 166.31, 190.8, 182.96, 205.37, 188.17, 213.7, 207.42, 213.7, 219.39, 190.8, 215.23, 162.18, 204.82, 151.25, 223.03, 148.13, 230.32, 148.65, 247.49, 148.65, 261.02, 145.0, 265.19, 91.92, 264.67, 82.04, 259.98, 70.07, 246.45, 66.95, 237.08]], "area": 10544.124399999997, "iscrowd": 0, "image_id": 305624, "bbox": [66.95, 115.83, 146.75, 149.36], "category_id": 1, "id": 212883, "split": "val", "sentences": [{"tokens": ["the", "couple", "sitting", "close", "together", "on", "the", "bench"], "raw": "The couple sitting close together on the bench.", "sent_id": 89030, "sent": "the couple sitting close together on the bench"}, {"tokens": ["the", "couple", "hugging", "each", "other"], "raw": "The couple hugging each other", "sent_id": 89031, "sent": "the couple hugging each other"}], "file_name": "COCO_train2014_000000305624_212883.jpg", "ann_id": 212883, "sent_ids": [89030, 89031], "ref_id": 39204}, {"segmentation": [[180.81, 406.03, 176.5, 439.03, 173.63, 466.3, 163.59, 489.26, 162.15, 512.22, 165.02, 535.17, 160.72, 549.52, 144.93, 549.52, 134.89, 542.35, 126.28, 546.65, 114.8, 556.7, 104.75, 545.22, 104.75, 515.09, 113.36, 496.43, 111.93, 459.12, 94.71, 423.25, 84.66, 365.85, 68.88, 352.93, 70.31, 317.06, 60.27, 282.62, 71.75, 196.52, 87.53, 147.73, 117.67, 141.99, 113.36, 134.82, 100.45, 127.64, 87.53, 111.86, 96.14, 91.77, 110.49, 77.42, 114.8, 73.11, 130.58, 73.11, 166.46, 81.72, 165.02, 103.25, 156.41, 119.03, 157.85, 131.95, 169.33, 147.73, 177.94, 156.34, 185.11, 167.82, 186.55, 179.3, 192.29, 271.14]], "area": 43113.792949999995, "iscrowd": 0, "image_id": 72731, "bbox": [60.27, 73.11, 132.02, 483.59], "category_id": 1, "id": 473674, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "black", "stockings"], "raw": "A woman in black stockings", "sent_id": 89048, "sent": "a woman in black stockings"}, {"tokens": ["man", "in", "the", "left"], "raw": "man in the left", "sent_id": 89049, "sent": "man in the left"}], "file_name": "COCO_train2014_000000072731_473674.jpg", "ann_id": 473674, "sent_ids": [89048, 89049], "ref_id": 39211}, {"segmentation": [[518.19, 256.0, 497.55, 267.35, 485.16, 274.58, 486.19, 284.9, 478.97, 291.1, 485.16, 315.87, 487.23, 328.26, 495.48, 342.71, 502.71, 355.1, 520.26, 368.52, 537.81, 368.52, 544.0, 376.77, 617.29, 404.65, 630.71, 412.9, 637.94, 412.9, 640.0, 384.0, 640.0, 316.9, 601.81, 285.94, 583.23, 284.9, 548.13, 260.13, 538.84, 256.0, 525.42, 256.0]], "area": 16273.625649999996, "iscrowd": 0, "image_id": 538108, "bbox": [478.97, 256.0, 161.03, 156.9], "category_id": 44, "id": 87688, "split": "val", "sentences": [{"tokens": ["a", "flower", "pot", "bottle", "near", "by", "the", "keyboard", "and", "mug"], "raw": "A FLOWER POT BOTTLE  NEAR BY THE KEYBOARD AND MUG", "sent_id": 89075, "sent": "a flower pot bottle near by the keyboard and mug"}], "file_name": "COCO_train2014_000000538108_87688.jpg", "ann_id": 87688, "sent_ids": [89075], "ref_id": 39223}, {"segmentation": [[65.27, 241.36, 64.28, 221.54, 66.26, 187.83, 72.21, 173.95, 91.04, 165.03, 131.69, 180.89, 136.65, 215.59, 123.76, 239.38, 126.73, 252.27, 143.59, 255.24, 172.34, 311.75, 163.42, 317.7, 106.91, 285.98, 82.12, 266.15, 59.32, 249.3]], "area": 8439.756699999998, "iscrowd": 0, "image_id": 512561, "bbox": [59.32, 165.03, 113.02, 152.67], "category_id": 1, "id": 515622, "split": "val", "sentences": [{"tokens": ["a", "man", "holding", "a", "steering", "of", "a", "video", "game", "sitting", "next", "to", "3", "other", "men", "holding", "steering", "of", "video", "games"], "raw": "A man holding a steering of a video game sitting next to 3 other men holding steering of video games", "sent_id": 89088, "sent": "a man holding a steering of a video game sitting next to 3 other men holding steering of video games"}, {"tokens": ["the", "man", "all", "the", "way", "in", "the", "back", "with", "the", "blue", "shirt"], "raw": "The man all the way in the back with the blue shirt.", "sent_id": 89089, "sent": "the man all the way in the back with the blue shirt"}], "file_name": "COCO_train2014_000000512561_515622.jpg", "ann_id": 515622, "sent_ids": [89088, 89089], "ref_id": 39229}, {"segmentation": [[276.37, 176.16, 289.69, 178.0, 298.29, 181.08, 302.38, 186.61, 320.2, 176.98, 329.63, 169.81, 333.31, 167.76, 333.52, 164.69, 339.46, 162.64, 341.51, 159.98, 348.06, 160.39, 353.59, 154.86, 355.23, 151.17, 355.84, 147.89, 354.0, 145.23, 358.1, 144.0, 357.28, 141.13, 349.7, 141.54, 339.87, 145.64, 332.9, 149.94, 329.01, 152.4, 328.19, 153.63, 326.55, 151.58, 323.69, 151.78, 307.71, 161.0, 301.77, 162.44, 298.49, 166.74, 292.55, 166.74, 286.41, 166.53, 281.49, 164.48, 280.06, 157.72, 281.49, 153.63, 277.6, 141.54, 271.05, 134.37, 267.15, 132.33, 260.19, 133.76, 256.5, 134.17, 250.15, 140.52, 247.29, 146.66, 246.06, 148.51, 243.39, 147.28, 242.17, 152.19, 238.27, 150.15, 228.44, 165.3, 223.32, 174.32, 225.98, 176.57, 227.21, 179.85, 230.49, 180.67, 229.88, 183.53, 228.85, 183.12, 223.94, 193.57, 221.07, 209.75, 220.04, 216.92, 222.5, 243.75, 228.24, 254.4, 228.24, 258.09, 231.11, 268.74, 234.38, 269.56, 240.32, 280.42, 251.38, 279.19, 261.21, 277.55, 275.76, 278.37, 296.85, 265.87, 315.08, 255.84, 319.8, 254.4, 346.83, 270.17, 353.18, 276.52, 364.24, 278.37, 373.05, 285.13, 376.94, 291.27, 384.32, 294.75, 387.8, 289.43, 395.79, 278.98, 402.55, 267.51, 407.87, 254.2, 407.87, 252.56, 404.39, 251.13, 399.06, 257.27, 394.56, 261.37, 384.93, 264.44, 376.94, 260.14, 375.1, 254.2, 372.64, 248.05, 367.11, 252.97, 363.22, 246.82, 358.51, 244.57, 344.37, 237.4, 342.74, 235.56, 340.07, 227.98, 335.36, 219.17, 324.3, 217.12, 322.66, 214.67, 314.88, 211.39, 306.07, 209.34, 293.17, 207.29, 287.64, 203.4, 283.54, 201.15, 274.32, 189.88, 274.32, 180.05, 275.96, 176.98]], "area": 13554.742650000004, "iscrowd": 0, "image_id": 578990, "bbox": [220.04, 132.33, 187.83, 162.42], "category_id": 1, "id": 476521, "split": "val", "sentences": [{"tokens": ["person"], "raw": "person", "sent_id": 89096, "sent": "person"}, {"tokens": ["a", "man", "wearing", "a", "red", "jacket"], "raw": "a man wearing a red jacket", "sent_id": 89097, "sent": "a man wearing a red jacket"}], "file_name": "COCO_train2014_000000578990_476521.jpg", "ann_id": 476521, "sent_ids": [89096, 89097], "ref_id": 39232}, {"segmentation": [[92.97, 274.59, 128.65, 331.89, 110.27, 354.59, 102.7, 372.97, 101.62, 389.19, 101.62, 389.19, 124.32, 358.92, 131.89, 341.62, 137.3, 334.05, 143.78, 337.3, 153.51, 338.38, 170.81, 327.57, 193.51, 320.0, 207.57, 331.89, 221.62, 350.27, 235.68, 372.97, 241.08, 381.62, 254.05, 384.86, 285.41, 384.86, 289.73, 375.14, 297.3, 389.19, 249.73, 409.73, 242.16, 431.35, 230.27, 455.14, 227.03, 460.54, 221.62, 468.11, 220.54, 472.43, 1.08, 473.51, 20.54, 366.49, 34.59, 336.22], [350.27, 355.68, 363.24, 352.43, 377.3, 357.84, 380.54, 375.14, 368.65, 395.68, 305.95, 474.59, 231.35, 471.35, 285.41, 418.38]], "area": 41082.5064, "iscrowd": 0, "image_id": 11282, "bbox": [1.08, 274.59, 379.46, 200.0], "category_id": 1, "id": 463559, "split": "val", "sentences": [{"tokens": ["a", "hand", "holding", "a", "chocolate", "covered", "doughnut", "with", "sprinkles"], "raw": "A hand holding a chocolate covered doughnut with sprinkles", "sent_id": 89105, "sent": "a hand holding a chocolate covered doughnut with sprinkles"}, {"tokens": ["hand", "holding", "a", "chocolate", "donut"], "raw": "hand holding a chocolate donut", "sent_id": 89106, "sent": "hand holding a chocolate donut"}], "file_name": "COCO_train2014_000000011282_463559.jpg", "ann_id": 463559, "sent_ids": [89105, 89106], "ref_id": 39237}, {"segmentation": [[355.98, 522.8, 464.33, 524.0, 502.43, 456.13, 526.24, 408.51, 592.91, 371.6, 564.34, 281.12, 547.67, 233.49, 467.9, 213.25, 460.76, 212.06, 467.9, 202.54, 470.28, 194.2, 444.09, 183.49, 435.75, 163.25, 413.13, 151.34, 371.46, 165.63, 360.75, 197.78, 367.89, 220.4, 385.75, 251.35, 377.41, 287.07, 375.03, 313.26, 355.98, 319.22, 353.6, 326.36, 367.89, 343.03, 384.56, 343.03, 391.7, 337.07, 410.75, 337.07, 427.42, 351.36, 430.99, 379.93, 419.09, 384.7, 407.18, 395.41, 400.04, 408.51, 414.32, 425.18, 414.32, 428.75, 360.75, 487.09]], "area": 51477.913499999995, "iscrowd": 0, "image_id": 275917, "bbox": [353.6, 151.34, 239.31, 372.66], "category_id": 1, "id": 444048, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "green", "hat", "and", "white", "shirt", "using", "his", "phone", "and", "holding", "a", "skateboard"], "raw": "The man in the green hat and white shirt using his phone and holding a skateboard.", "sent_id": 89117, "sent": "the man in the green hat and white shirt using his phone and holding a skateboard"}, {"tokens": ["a", "man", "wearing", "a", "green", "hat", ",", "white", "tshirt", "and", "jeans", "as", "he", "holds", "onto", "his", "skateboard", "by", "the", "wheels", "and", "a", "cell", "phone", "in", "the", "other", "hand"], "raw": "A man wearing a green hat, white tshirt and jeans as he holds onto his skateboard by the wheels and a cell phone in the other hand", "sent_id": 89118, "sent": "a man wearing a green hat , white tshirt and jeans as he holds onto his skateboard by the wheels and a cell phone in the other hand"}], "file_name": "COCO_train2014_000000275917_444048.jpg", "ann_id": 444048, "sent_ids": [89117, 89118], "ref_id": 39243}, {"segmentation": [[157.37, 96.02, 137.22, 84.5, 140.09, 57.64, 147.77, 31.73, 167.92, 22.13, 203.42, 22.13, 228.37, 27.89, 228.37, 22.13, 225.49, 13.5, 235.09, 1.02, 337.76, 5.82, 349.28, 12.54, 368.47, 13.5, 376.14, 1.98, 419.32, 1.98, 429.88, 22.13, 437.56, 27.89, 450.03, 39.41, 454.83, 50.92, 460.58, 60.52, 460.58, 87.38, 454.83, 108.49, 443.31, 120.97, 423.16, 129.6, 410.69, 130.56, 380.94, 121.93, 380.94, 115.21, 351.2, 77.79, 359.83, 55.72, 352.16, 72.03, 345.44, 84.5, 342.56, 93.14, 335.84, 101.78, 312.81, 92.18, 301.3, 84.5, 272.51, 70.11, 255.24, 66.27, 237.97, 66.27, 226.45, 70.11, 210.14, 76.83, 198.63, 82.59, 185.19, 87.38]], "area": 25573.349499999993, "iscrowd": 0, "image_id": 343158, "bbox": [137.22, 1.02, 323.36, 129.54], "category_id": 4, "id": 155860, "split": "val", "sentences": [{"tokens": ["a", "motorcycle", "with", "orange", "lights"], "raw": "a motorcycle with orange lights", "sent_id": 89130, "sent": "a motorcycle with orange lights"}, {"tokens": ["a", "motorcycle", "is", "in", "the", "back", "of", "the", "room", "behind", "another", "motorcycle"], "raw": "a motorcycle is in the back of the room behind another motorcycle.", "sent_id": 89131, "sent": "a motorcycle is in the back of the room behind another motorcycle"}], "file_name": "COCO_train2014_000000343158_155860.jpg", "ann_id": 155860, "sent_ids": [89130, 89131], "ref_id": 39248}, {"segmentation": [[345.6, 210.89, 362.32, 193.24, 379.97, 177.45, 401.34, 168.15, 416.21, 160.72, 422.71, 157.94, 431.07, 149.57, 439.43, 146.79, 441.29, 144.0, 437.57, 130.99, 441.29, 117.99, 448.72, 117.06, 458.94, 115.2, 466.37, 118.92, 472.88, 125.42, 476.59, 129.14, 478.45, 130.99, 467.3, 135.64, 464.52, 140.28, 460.8, 144.93, 454.3, 151.43, 447.79, 160.72, 445.01, 165.37, 456.15, 160.72, 462.66, 157.94, 466.37, 159.79, 467.3, 167.23, 466.37, 169.08, 460.8, 174.66, 463.59, 177.45, 462.66, 190.45, 460.8, 199.74, 457.08, 209.03, 444.08, 224.83, 434.79, 233.19, 434.79, 237.83, 433.86, 240.62, 433.86, 248.98, 429.21, 261.06, 429.21, 264.77, 429.21, 272.21, 429.21, 275.92, 432.0, 278.71, 433.86, 280.57, 431.07, 280.57, 425.5, 279.64, 419.92, 279.64, 414.35, 279.64, 421.78, 274.06, 423.64, 270.35, 419.92, 263.85, 417.14, 256.41, 413.42, 248.05, 408.77, 261.06, 408.77, 270.35, 409.7, 276.85, 410.63, 284.28, 405.99, 286.14, 402.27, 284.28, 398.55, 277.78, 398.55, 266.63, 397.63, 262.92, 395.77, 256.41, 394.84, 249.91, 394.84, 246.19, 377.19, 253.63, 360.46, 261.06, 355.82, 261.06, 344.67, 257.34, 339.1, 262.92, 339.1, 268.49, 336.31, 272.21, 334.45, 273.14, 324.23, 274.06, 318.66, 271.28, 314.94, 272.21, 308.44, 272.21, 313.08, 264.77, 313.08, 257.34, 313.08, 255.48, 308.44, 256.41, 305.65, 256.41, 301.01, 256.41, 296.36, 256.41, 307.51, 245.26, 311.23, 241.55, 319.59, 229.47, 327.02, 220.18, 333.52, 218.32, 341.88, 212.75, 348.39, 207.17]], "area": 12131.012100000004, "iscrowd": 0, "image_id": 266816, "bbox": [296.36, 115.2, 182.09, 170.94], "category_id": 16, "id": 41962, "split": "val", "sentences": [{"tokens": ["black", "bird", "toward", "left", "side"], "raw": "black bird toward left side", "sent_id": 89191, "sent": "black bird toward left side"}, {"tokens": ["bird", "on", "the", "left"], "raw": "Bird on the left", "sent_id": 89192, "sent": "bird on the left"}], "file_name": "COCO_train2014_000000266816_41962.jpg", "ann_id": 41962, "sent_ids": [89191, 89192], "ref_id": 39271}, {"segmentation": [[290.26, 465.48, 335.19, 397.28, 362.25, 389.7, 430.45, 385.91, 473.21, 396.73, 484.04, 408.1, 485.12, 417.84, 482.96, 433.54, 478.08, 463.31, 474.3, 480.0, 382.82, 480.0, 381.74, 480.0, 384.99, 469.78, 396.35, 455.7, 401.77, 449.75, 383.36, 449.75, 369.29, 461.12, 364.42, 475.73, 361.17, 480.0, 314.08, 480.0, 301.63, 480.0, 293.51, 473.57, 289.72, 467.07]], "area": 14554.1003, "iscrowd": 0, "image_id": 501773, "bbox": [289.72, 385.91, 195.4, 94.09], "category_id": 81, "id": 1983117, "split": "val", "sentences": [{"tokens": ["the", "inside", "of", "an", "empty", "bathtub"], "raw": "The inside of an empty bathtub", "sent_id": 89267, "sent": "the inside of an empty bathtub"}, {"tokens": ["a", "white", "bathtub", "below", "a", "city", "view", "in", "a", "window"], "raw": "A white bathtub below a city view in a window.", "sent_id": 89268, "sent": "a white bathtub below a city view in a window"}], "file_name": "COCO_train2014_000000501773_1983117.jpg", "ann_id": 1983117, "sent_ids": [89267, 89268], "ref_id": 39297}, {"segmentation": [[514.82, 166.85, 540.44, 222.35, 545.42, 233.03, 548.98, 240.14, 558.94, 164.0, 640.0, 168.27, 640.0, 72.2, 521.23, 72.91, 514.11, 136.24]], "area": 13186.9767, "iscrowd": 0, "image_id": 303703, "bbox": [514.11, 72.2, 125.89, 167.94], "category_id": 79, "id": 1643054, "split": "val", "sentences": [{"tokens": ["stovetop", "on", "the", "stove", "that", "is", "white", "in", "color"], "raw": "Stovetop on the stove that is white in color.", "sent_id": 89277, "sent": "stovetop on the stove that is white in color"}, {"tokens": ["stovetop"], "raw": "stovetop", "sent_id": 89278, "sent": "stovetop"}], "file_name": "COCO_train2014_000000303703_1643054.jpg", "ann_id": 1643054, "sent_ids": [89277, 89278], "ref_id": 39302}, {"segmentation": [[417.4, 86.03, 415.07, 0.0, 639.35, 0.4, 640.0, 78.46, 445.95, 92.44, 417.99, 84.87]], "area": 19140.521249999998, "iscrowd": 0, "image_id": 560691, "bbox": [415.07, 0.0, 224.93, 92.44], "category_id": 72, "id": 30532, "split": "val", "sentences": [{"tokens": ["television", "showing", "fried", "chicken"], "raw": "television showing fried chicken", "sent_id": 89328, "sent": "television showing fried chicken"}, {"tokens": ["a", "tv", "above", "and", "to", "the", "right", "of", "an", "elderly", "woman"], "raw": "A TV above and to the right of an elderly woman", "sent_id": 89329, "sent": "a tv above and to the right of an elderly woman"}], "file_name": "COCO_train2014_000000560691_30532.jpg", "ann_id": 30532, "sent_ids": [89328, 89329], "ref_id": 39324}, {"segmentation": [[259.37, 283.0, 261.52, 328.2, 259.37, 332.5, 242.15, 335.73, 227.09, 338.96, 218.48, 336.81, 214.17, 323.89, 214.17, 272.23, 206.64, 233.49, 194.8, 207.66, 205.56, 173.22, 218.48, 158.15, 246.46, 144.16, 276.59, 137.7, 319.64, 143.09, 341.17, 145.24, 362.69, 148.47, 384.22, 148.47, 405.74, 148.47, 418.65, 164.61, 420.81, 202.28, 421.88, 257.17, 415.43, 326.04, 404.66, 343.26, 391.75, 346.49, 377.76, 346.49, 370.22, 346.49, 364.84, 343.26, 358.39, 332.5, 365.92, 312.05, 347.62, 269.0, 331.48, 255.01, 331.48, 284.07, 327.17, 334.65, 320.72, 342.19, 311.03, 343.26, 297.04, 341.11, 294.89, 336.81, 293.81, 326.04, 294.89, 289.45, 294.89, 272.23]], "area": 36497.83645000001, "iscrowd": 0, "image_id": 433435, "bbox": [194.8, 137.7, 227.08, 208.79], "category_id": 22, "id": 583190, "split": "val", "sentences": [{"tokens": ["the", "elephant", "which", "is", "in", "the", "centre", "of", "the", "picture"], "raw": "The elephant which is in the centre of the picture", "sent_id": 89381, "sent": "the elephant which is in the centre of the picture"}, {"tokens": ["a", "large", "brown", "elephant", "is", "standing", "in", "a", "area", "of", "dirt"], "raw": "A large brown elephant is standing in a area of dirt.", "sent_id": 89382, "sent": "a large brown elephant is standing in a area of dirt"}], "file_name": "COCO_train2014_000000433435_583190.jpg", "ann_id": 583190, "sent_ids": [89381, 89382], "ref_id": 39346}, {"segmentation": [[305.91, 171.29, 342.77, 139.13, 388.26, 132.07, 425.91, 154.03, 427.0, 187.76, 427.0, 249.72, 401.6, 268.54, 362.38, 274.82, 338.85, 263.05, 312.97, 246.58, 303.56, 223.84, 300.42, 202.66, 303.56, 175.99]], "area": 14578.648300000003, "iscrowd": 0, "image_id": 92988, "bbox": [300.42, 132.07, 126.58, 142.75], "category_id": 85, "id": 2197145, "split": "val", "sentences": [{"tokens": ["the", "face", "of", "a", "large", "coco", "tower", "in", "a", "city"], "raw": "The face of a large coco tower in a city.", "sent_id": 89426, "sent": "the face of a large coco tower in a city"}, {"tokens": ["face", "of", "clock", "on", "tower", "closest", "to", "camera"], "raw": "face of clock on tower closest to camera", "sent_id": 89427, "sent": "face of clock on tower closest to camera"}], "file_name": "COCO_train2014_000000092988_2197145.jpg", "ann_id": 2197145, "sent_ids": [89426, 89427], "ref_id": 39364}, {"segmentation": [[460.55, 202.81, 466.61, 240.65, 465.09, 264.12, 463.58, 287.58, 464.34, 308.78, 478.72, 329.97, 476.45, 356.46, 473.42, 365.54, 429.52, 370.84, 403.78, 368.57, 406.06, 290.61, 400.76, 257.31, 402.27, 250.49, 362.91, 266.39, 328.85, 276.99, 316.74, 282.28, 309.93, 280.01, 303.12, 273.2, 295.55, 271.69, 294.03, 261.85, 279.65, 261.85, 299.33, 255.79, 335.66, 256.55, 371.24, 235.36, 384.11, 226.27, 396.97, 206.59, 399.24, 201.3, 398.49, 192.97, 394.7, 184.64, 399.24, 171.78, 400.0, 161.18, 403.78, 154.37, 411.35, 145.29, 432.55, 145.29, 446.17, 149.83, 452.23, 167.99, 453.74, 180.86, 462.07, 202.81]], "area": 16574.04325, "iscrowd": 0, "image_id": 419324, "bbox": [279.65, 145.29, 199.07, 225.55], "category_id": 1, "id": 2176914, "split": "val", "sentences": [{"tokens": ["woman", "with", "long", "hair", "and", "a", "red", "shirt"], "raw": "Woman with long hair and a red shirt.", "sent_id": 89449, "sent": "woman with long hair and a red shirt"}, {"tokens": ["the", "blonde", "-", "haired", "woman", "wearing", "a", "red", "long", "sleeve", "top"], "raw": "The blonde-haired woman wearing a red long sleeve top.", "sent_id": 89450, "sent": "the blonde - haired woman wearing a red long sleeve top"}], "file_name": "COCO_train2014_000000419324_2176914.jpg", "ann_id": 2176914, "sent_ids": [89449, 89450], "ref_id": 39372}, {"segmentation": [[314.97, 286.92, 314.97, 244.85, 302.02, 212.49, 308.49, 183.37, 276.13, 175.82, 265.35, 201.71, 276.13, 230.83, 242.7, 262.11, 240.54, 313.89, 249.17, 380.76, 259.96, 465.98, 307.42, 465.98, 323.6, 366.74]], "area": 17539.717950000006, "iscrowd": 0, "image_id": 115505, "bbox": [240.54, 175.82, 83.06, 290.16], "category_id": 1, "id": 452686, "split": "val", "sentences": [{"tokens": ["wrapped", "flowers", "with", "woman", "in", "pink", "top", "directly", "behind"], "raw": "wrapped flowers with woman in pink top directly behind", "sent_id": 89465, "sent": "wrapped flowers with woman in pink top directly behind"}, {"tokens": ["a", "woman", "in", "a", "pink", "shirt", "and", "black", "pants"], "raw": "A woman in a pink shirt and black pants.", "sent_id": 89466, "sent": "a woman in a pink shirt and black pants"}], "file_name": "COCO_train2014_000000115505_452686.jpg", "ann_id": 452686, "sent_ids": [89465, 89466], "ref_id": 39378}, {"segmentation": [[283.53, 331.6, 280.51, 297.03, 283.1, 262.9, 287.42, 234.82, 324.58, 231.8, 374.69, 233.09, 426.97, 245.62, 446.84, 250.81, 448.57, 281.91, 449.0, 313.45, 437.34, 319.93, 431.72, 324.68, 423.08, 325.12, 405.37, 329.87, 395.0, 339.37, 372.1, 336.35, 340.13, 336.78, 322.85, 340.67, 311.61, 335.49]], "area": 15894.260750000001, "iscrowd": 0, "image_id": 37169, "bbox": [280.51, 231.8, 168.49, 108.87], "category_id": 6, "id": 166416, "split": "val", "sentences": [{"tokens": ["red", "bus", "on", "a", "road"], "raw": "Red bus on a road", "sent_id": 89477, "sent": "red bus on a road"}, {"tokens": ["a", "single", "story", "red", "bus", "number", "272"], "raw": "A single story red bus number 272.", "sent_id": 89478, "sent": "a single story red bus number 272"}], "file_name": "COCO_train2014_000000037169_166416.jpg", "ann_id": 166416, "sent_ids": [89477, 89478], "ref_id": 39382}, {"segmentation": [[245.61, 437.89, 168.63, 459.69, 166.64, 446.81, 164.66, 436.9, 164.66, 430.62, 164.66, 421.7, 164.33, 411.78, 171.93, 401.21, 181.18, 402.2, 193.74, 410.13, 247.59, 395.26, 258.5, 387.0, 260.81, 375.44, 258.5, 371.48, 264.44, 363.55, 285.26, 363.55, 306.07, 378.74, 303.1, 424.34], [102.93, 398.01, 148.49, 431.58, 149.58, 453.38, 94.65, 412.83, 95.74, 404.98]], "area": 8164.709849999999, "iscrowd": 0, "image_id": 229990, "bbox": [94.65, 363.55, 211.42, 96.14], "category_id": 65, "id": 2193910, "split": "val", "sentences": [{"tokens": ["the", "bottom", "bunk", "with", "a", "blue", "blanket"], "raw": "The bottom bunk with a blue blanket.", "sent_id": 89505, "sent": "the bottom bunk with a blue blanket"}, {"tokens": ["bottom", "bed", "of", "bunkbed", "set"], "raw": "bottom bed of bunkbed set", "sent_id": 89506, "sent": "bottom bed of bunkbed set"}], "file_name": "COCO_train2014_000000229990_2193910.jpg", "ann_id": 2193910, "sent_ids": [89505, 89506], "ref_id": 39392}, {"segmentation": [[232.16, 336.55, 247.36, 333.65, 248.81, 331.48, 250.98, 324.25, 247.36, 314.12, 243.74, 309.78, 255.32, 291.69, 335.64, 172.3, 331.29, 160.0, 329.85, 152.76, 326.95, 147.7, 322.61, 144.08, 237.23, 121.65, 219.14, 121.65, 204.67, 127.44, 188.75, 135.4, 98.3, 250.44, 97.58, 259.85, 93.96, 269.98, 97.58, 275.05, 205.39, 311.95, 219.86, 316.29, 223.48, 320.63, 227.82, 324.97, 229.27, 325.7]], "area": 29227.25245, "iscrowd": 0, "image_id": 503022, "bbox": [93.96, 121.65, 241.68, 214.9], "category_id": 51, "id": 1903024, "split": "val", "sentences": [{"tokens": ["carrots", "and", "cauliflower", "in", "a", "clear", "container"], "raw": "Carrots and cauliflower in a clear container.", "sent_id": 89529, "sent": "carrots and cauliflower in a clear container"}, {"tokens": ["a", "clear", "plastic", "container", "holding", "chopped", "carrots", "and", "some", "white", "dip"], "raw": "A clear plastic container holding chopped carrots and some white dip", "sent_id": 89530, "sent": "a clear plastic container holding chopped carrots and some white dip"}], "file_name": "COCO_train2014_000000503022_1903024.jpg", "ann_id": 1903024, "sent_ids": [89529, 89530], "ref_id": 39403}, {"segmentation": [[149.24, 391.68, 160.72, 324.23, 166.46, 308.45, 120.54, 271.14, 129.15, 230.96, 147.8, 176.43, 180.81, 164.95, 176.5, 149.17, 180.81, 113.29, 218.12, 111.86, 231.03, 131.95, 232.47, 154.91, 248.25, 170.69, 281.26, 203.7, 298.48, 269.7, 271.21, 292.66, 264.04, 315.62, 272.65, 361.54, 253.99, 417.51, 241.08, 474.91, 228.16, 561.0, 229.6, 581.09, 219.55, 583.96, 225.29, 608.36, 199.46, 618.4, 193.72, 614.1, 186.55, 588.27, 173.63, 546.65, 179.37, 496.43]], "area": 46767.08404999999, "iscrowd": 0, "image_id": 298262, "bbox": [120.54, 111.86, 177.94, 506.54], "category_id": 1, "id": 193041, "split": "val", "sentences": [{"tokens": ["man", "wearing", "bow", "tie", "holding", "black", "umbrella"], "raw": "Man wearing bow tie holding black umbrella", "sent_id": 89576, "sent": "man wearing bow tie holding black umbrella"}, {"tokens": ["the", "man", "with", "glasses", "and", "a", "bow", "tie", ",", "holding", "an", "umbrella"], "raw": "The man with glasses and a bow tie , holding an umbrella.", "sent_id": 89577, "sent": "the man with glasses and a bow tie , holding an umbrella"}], "file_name": "COCO_train2014_000000298262_193041.jpg", "ann_id": 193041, "sent_ids": [89576, 89577], "ref_id": 39419}, {"segmentation": [[350.67, 109.14, 387.58, 120.05, 399.33, 106.62, 484.06, 74.75, 469.8, 42.87, 361.58, 94.88]], "area": 3839.9155499999997, "iscrowd": 0, "image_id": 332613, "bbox": [350.67, 42.87, 133.39, 77.18], "category_id": 49, "id": 694614, "split": "val", "sentences": [{"tokens": ["a", "knife", "server", "underneath", "the", "shrimp", "pizza"], "raw": "A knife server underneath the shrimp pizza.", "sent_id": 89590, "sent": "a knife server underneath the shrimp pizza"}, {"tokens": ["a", "pizza", "slicer", "in", "a", "pizza"], "raw": "A pizza slicer in a pizza", "sent_id": 89591, "sent": "a pizza slicer in a pizza"}], "file_name": "COCO_train2014_000000332613_694614.jpg", "ann_id": 694614, "sent_ids": [89590, 89591], "ref_id": 39424}, {"segmentation": [[271.82, 491.87, 240.18, 536.45, 208.54, 545.08, 176.9, 542.2, 130.88, 467.42, 53.21, 297.71, 25.89, 258.88, 24.45, 235.87, 67.6, 260.31, 123.69, 243.06, 139.51, 207.1, 138.07, 179.78], [48.9, 184.09, 100.67, 171.15, 107.87, 178.34, 102.11, 189.84, 89.17, 192.72, 79.1, 188.4]], "area": 39087.62325000001, "iscrowd": 0, "image_id": 261696, "bbox": [24.45, 171.15, 247.37, 373.93], "category_id": 86, "id": 1152554, "split": "val", "sentences": [{"tokens": ["a", "tall", "white", "cylindrical", "vase"], "raw": "a tall white cylindrical vase", "sent_id": 89633, "sent": "a tall white cylindrical vase"}, {"tokens": ["a", "cylinder", "shapped", "vase"], "raw": "A cylinder shapped vase.", "sent_id": 89634, "sent": "a cylinder shapped vase"}], "file_name": "COCO_train2014_000000261696_1152554.jpg", "ann_id": 1152554, "sent_ids": [89633, 89634], "ref_id": 39438}, {"segmentation": [[207.94, 108.2, 223.54, 113.58, 236.18, 113.58, 243.45, 112.51, 251.51, 109.28, 258.51, 111.7, 263.89, 120.04, 268.46, 124.07, 275.99, 125.96, 285.41, 128.65, 289.44, 128.65, 294.01, 126.23, 298.59, 125.15, 298.05, 127.57, 294.01, 129.99, 292.94, 131.61, 296.43, 139.41, 294.82, 142.1, 297.51, 151.24, 298.32, 157.16, 295.9, 158.77, 291.86, 158.77, 288.63, 156.08, 287.02, 153.93, 282.99, 151.24, 280.3, 152.86, 277.34, 151.24, 272.76, 151.78, 267.38, 155.81, 263.08, 158.23, 262.54, 158.23, 258.51, 157.97, 255.01, 155.01, 256.09, 163.35, 257.43, 173.84, 259.32, 178.14, 262.0, 179.48, 259.58, 181.37, 254.47, 181.1, 253.67, 178.68, 251.51, 174.1, 251.25, 166.84, 251.25, 159.85, 250.98, 151.51, 247.75, 150.7, 246.94, 158.77, 245.6, 168.73, 246.94, 177.06, 249.9, 181.1, 245.87, 182.71, 241.83, 180.83, 241.02, 170.34, 241.02, 158.77, 239.14, 151.78, 238.33, 148.28, 227.31, 150.17, 219.77, 148.82, 210.09, 143.17, 207.67, 144.25, 207.67, 145.59, 206.33, 145.86, 205.25, 144.79, 204.44, 148.01, 201.48, 151.24, 200.14, 158.5, 201.75, 167.11, 204.71, 172.76, 207.94, 174.64, 209.55, 175.72, 206.86, 177.33, 203.64, 178.95, 200.14, 173.84, 198.26, 169.26, 198.26, 166.57, 196.64, 171.68, 193.68, 170.07, 193.95, 165.23, 195.3, 161.19, 195.83, 156.62, 194.76, 148.01, 192.07, 139.67, 189.65, 129.72, 189.11, 121.65, 190.19, 116.0, 195.3, 111.43, 200.95, 108.2, 205.79, 107.13, 207.94, 107.67]], "area": 4216.742200000001, "iscrowd": 0, "image_id": 396825, "bbox": [189.11, 107.13, 109.48, 75.58], "category_id": 21, "id": 70886, "split": "val", "sentences": [{"tokens": ["the", "swaybacked", "cow", "in", "the", "left", "image", "that", "is", "in", "front", "of", "the", "smaller", "cow"], "raw": "the swaybacked cow in the left image that is in front of the smaller cow", "sent_id": 89727, "sent": "the swaybacked cow in the left image that is in front of the smaller cow"}, {"tokens": ["a", "white", "ox", "standing", "in", "front", "of", "other", "ox", "and", "a", "bus"], "raw": "A white ox standing in front of other ox and a bus.", "sent_id": 89728, "sent": "a white ox standing in front of other ox and a bus"}], "file_name": "COCO_train2014_000000396825_70886.jpg", "ann_id": 70886, "sent_ids": [89727, 89728], "ref_id": 39471}, {"segmentation": [[242.89, 312.76, 170.8, 310.55, 144.18, 173.02, 148.62, 167.47, 228.47, 167.47, 232.91, 215.16, 230.69, 222.93, 246.22, 266.18, 269.51, 296.13, 244.0, 312.76]], "area": 12179.516099999997, "iscrowd": 0, "image_id": 429059, "bbox": [144.18, 167.47, 125.33, 145.29], "category_id": 38, "id": 1856548, "split": "val", "sentences": [{"tokens": ["yellow", "fabric", "on", "a", "shelf", "behind", "a", "man"], "raw": "Yellow fabric on a shelf behind a man", "sent_id": 89747, "sent": "yellow fabric on a shelf behind a man"}, {"tokens": ["yellow", "bag", "with", "part", "of", "mans", "eyes", "and", "ear", "in", "the", "foreground"], "raw": "Yellow bag with part of mans eyes and ear in the foreground.", "sent_id": 89748, "sent": "yellow bag with part of mans eyes and ear in the foreground"}], "file_name": "COCO_train2014_000000429059_1856548.jpg", "ann_id": 1856548, "sent_ids": [89747, 89748], "ref_id": 39479}, {"segmentation": [[297.07, 365.53, 303.69, 339.87, 310.32, 312.96, 307.0, 263.29, 317.77, 257.08, 328.12, 246.32, 331.84, 240.52, 338.05, 231.42, 339.71, 205.75, 337.22, 185.88, 335.15, 178.02, 331.84, 170.98, 323.56, 159.39, 315.28, 147.8, 301.21, 122.96, 284.24, 109.3, 271.4, 97.71, 256.09, 86.12, 238.7, 74.12, 225.04, 67.91, 208.07, 64.6, 180.75, 76.6, 155.91, 91.5, 131.9, 110.54, 114.11, 129.17, 106.65, 154.01, 105.41, 158.98, 100.45, 201.61, 99.2, 222.31, 102.51, 226.45, 104.58, 233.07, 106.65, 240.94, 107.9, 258.32, 112.86, 274.05, 110.38, 305.93, 107.48, 328.69, 101.69, 343.18, 102.1, 358.91, 102.93, 375.47, 100.45, 383.75, 89.27, 409.41, 80.58, 426.8, 82.65, 434.66, 89.27, 437.15, 104.17, 438.8, 125.7, 437.97, 138.53, 436.32, 141.43, 436.32, 149.7, 467.78, 150.95, 488.06, 144.32, 528.63, 136.46, 543.12, 136.04, 553.88, 141.43, 553.88, 159.64, 547.67, 167.5, 549.74, 208.48, 556.78, 222.97, 556.36, 218.42, 542.29, 239.53, 548.91, 256.5, 536.91, 254.85, 529.04, 278.86, 498.82, 282.58, 478.13, 282.99, 465.71, 273.47, 454.12, 280.1, 415.21, 287.13, 397.41]], "area": 85773.24434999998, "iscrowd": 0, "image_id": 398172, "bbox": [80.58, 64.6, 259.13, 492.18], "category_id": 22, "id": 581852, "split": "val", "sentences": [{"tokens": ["a", "baby", "elephant", "walking", "along", "with", "his", "mother"], "raw": "A baby elephant walking along with his mother.", "sent_id": 89757, "sent": "a baby elephant walking along with his mother"}, {"tokens": ["a", "baby", "elephant", "walking", "with", "a", "long", "piece", "of", "grass", "in", "mouth"], "raw": "A baby elephant walking with a long piece of grass in mouth.", "sent_id": 89758, "sent": "a baby elephant walking with a long piece of grass in mouth"}], "file_name": "COCO_train2014_000000398172_581852.jpg", "ann_id": 581852, "sent_ids": [89757, 89758], "ref_id": 39482}, {"segmentation": [[373.89, 189.23, 461.65, 232.2, 458.91, 292.53, 467.14, 290.7, 467.14, 228.54, 530.21, 224.88, 518.33, 285.22, 527.47, 282.48, 533.87, 210.26, 446.11, 176.43, 384.86, 186.49]], "area": 5470.0160499999965, "iscrowd": 0, "image_id": 259120, "bbox": [373.89, 176.43, 159.98, 116.1], "category_id": 67, "id": 118036, "split": "val", "sentences": [{"tokens": ["the", "desk", "with", "the", "green", "chair"], "raw": "the desk with the green chair", "sent_id": 89780, "sent": "the desk with the green chair"}, {"tokens": ["a", "table", "sitting", "below", "a", "picture", "frame"], "raw": "A table sitting below a picture frame.", "sent_id": 89781, "sent": "a table sitting below a picture frame"}], "file_name": "COCO_train2014_000000259120_118036.jpg", "ann_id": 118036, "sent_ids": [89780, 89781], "ref_id": 39490}, {"segmentation": [[114.37, 462.45, 125.22, 425.54, 124.5, 392.98, 128.12, 371.27, 138.25, 366.93, 151.27, 357.53, 152.0, 337.99, 68.79, 337.27, 83.98, 471.85, 90.49, 473.3, 97.73, 543.49, 104.24, 638.27, 128.84, 634.66, 113.65, 464.62]], "area": 10911.752, "iscrowd": 0, "image_id": 94702, "bbox": [68.79, 337.27, 83.21, 301.0], "category_id": 67, "id": 1964520, "split": "val", "sentences": [{"tokens": ["a", "table", "near", "a", "chair"], "raw": "A table near a chair.", "sent_id": 89788, "sent": "a table near a chair"}, {"tokens": ["a", "wooden", "table", "and", "empty", "chair"], "raw": "a wooden table and empty chair", "sent_id": 89789, "sent": "a wooden table and empty chair"}], "file_name": "COCO_train2014_000000094702_1964520.jpg", "ann_id": 1964520, "sent_ids": [89788, 89789], "ref_id": 39494}, {"segmentation": [[86.31, 96.79, 72.45, 92.34, 63.05, 91.35, 51.17, 91.35, 51.67, 96.3, 53.15, 98.28, 58.1, 108.67, 65.52, 115.1, 65.52, 122.53, 70.47, 132.92, 75.42, 139.85, 90.76, 142.81, 122.43, 146.77, 179.34, 148.26, 280.79, 152.71, 339.18, 154.2, 356.01, 159.15, 361.45, 152.71, 365.91, 135.39, 368.38, 130.44, 374.32, 133.91, 378.28, 130.94, 386.2, 117.58, 380.26, 111.64, 370.36, 106.69, 358.48, 102.24, 343.14, 101.74, 297.61, 103.72, 254.56, 106.69, 219.43, 108.17, 167.46, 102.24, 101.65, 99.27, 90.76, 98.77]], "area": 14547.31235, "iscrowd": 0, "image_id": 510027, "bbox": [51.17, 91.35, 335.03, 67.8], "category_id": 54, "id": 2218140, "split": "val", "sentences": [{"tokens": ["the", "piece", "of", "bread", "second", "from", "the", "top"], "raw": "The piece of bread second from the top.", "sent_id": 89809, "sent": "the piece of bread second from the top"}], "file_name": "COCO_train2014_000000510027_2218140.jpg", "ann_id": 2218140, "sent_ids": [89809], "ref_id": 39502}, {"segmentation": [[1.65, 364.86, 4.41, 380.84, 95.37, 379.19, 108.6, 382.5, 104.74, 413.92, 108.6, 464.64, 102.54, 479.52, 25.91, 576.54, 0.55, 614.03, 0.0, 477.9, 0.55, 407.34]], "area": 17259.961099999997, "iscrowd": 0, "image_id": 228215, "bbox": [0.0, 364.86, 108.6, 249.17], "category_id": 63, "id": 113402, "split": "val", "sentences": [{"tokens": ["the", "brown", "couch", "on", "the", "left"], "raw": "The brown couch on the left.", "sent_id": 89814, "sent": "the brown couch on the left"}, {"tokens": ["a", "couch", "in", "the", "living", "room"], "raw": "A couch in the living room", "sent_id": 89815, "sent": "a couch in the living room"}], "file_name": "COCO_train2014_000000228215_113402.jpg", "ann_id": 113402, "sent_ids": [89814, 89815], "ref_id": 39504}, {"segmentation": [[415.49, 418.44, 425.0, 373.75, 417.39, 350.93, 465.88, 268.21, 484.9, 209.26, 501.06, 199.76, 520.08, 201.66, 532.44, 205.46, 548.6, 209.26, 557.16, 205.46, 553.36, 192.15, 534.34, 181.69, 517.23, 170.28, 513.42, 161.72, 502.96, 160.77, 494.41, 151.27, 491.55, 155.07, 490.6, 167.43, 478.24, 168.38, 457.33, 196.9, 417.39, 256.8, 393.62, 276.77, 361.3, 295.79, 343.23, 310.05, 336.58, 318.6, 301.4, 340.47, 257.66, 368.04, 247.2, 399.42, 247.2, 419.39]], "area": 25043.94614999999, "iscrowd": 0, "image_id": 8300, "bbox": [247.2, 151.27, 309.96, 268.12], "category_id": 25, "id": 596841, "split": "val", "sentences": [{"tokens": ["the", "third", "giraffe", "from", "the", "left"], "raw": "the third giraffe from the left", "sent_id": 89857, "sent": "the third giraffe from the left"}, {"tokens": ["second", "giraffe", "from", "the", "right"], "raw": "second giraffe from the right", "sent_id": 89858, "sent": "second giraffe from the right"}], "file_name": "COCO_train2014_000000008300_596841.jpg", "ann_id": 596841, "sent_ids": [89857, 89858], "ref_id": 39520}, {"segmentation": [[144.69, 305.35, 130.48, 258.3, 131.37, 230.79, 131.37, 205.04, 102.08, 204.16, 90.54, 204.16, 81.66, 201.49, 74.56, 200.61, 61.25, 193.51, 52.37, 187.29, 49.71, 174.87, 65.69, 165.99, 76.34, 152.67, 83.44, 142.02, 93.2, 133.15, 102.08, 122.49, 99.42, 110.96, 95.87, 98.53, 95.87, 93.2, 101.19, 90.54, 110.07, 93.2, 117.17, 109.18, 132.26, 118.06, 136.7, 107.4, 142.02, 102.08, 161.55, 102.08, 165.1, 105.63, 175.75, 126.93, 174.87, 133.15, 206.82, 131.37, 230.79, 129.6, 272.51, 136.7, 299.13, 171.31, 311.56, 191.73, 313.34, 216.58, 304.46, 262.74, 295.58, 298.25, 290.26, 308.9, 274.28, 311.56, 260.08, 314.22, 251.2, 317.78, 246.76, 306.24, 237.89, 276.94, 230.79, 300.91, 214.81, 309.79, 183.74, 326.65, 172.2, 330.2, 164.21, 332.87, 146.46, 336.42, 134.03, 336.42, 128.71, 336.42, 112.73, 333.75, 113.62, 320.44, 127.82, 317.78, 135.81, 308.01]], "area": 37877.862949999995, "iscrowd": 0, "image_id": 90310, "bbox": [49.71, 90.54, 263.63, 245.88], "category_id": 23, "id": 588102, "split": "val", "sentences": [{"tokens": ["a", "small", "black", "bear", "standing", "in", "front", "of", "another", "bear", "in", "the", "grass"], "raw": "A small black bear standing in front of another bear in the grass.", "sent_id": 89867, "sent": "a small black bear standing in front of another bear in the grass"}, {"tokens": ["the", "bear", "cub", "on", "the", "left"], "raw": "The bear cub on the left.", "sent_id": 89868, "sent": "the bear cub on the left"}], "file_name": "COCO_train2014_000000090310_588102.jpg", "ann_id": 588102, "sent_ids": [89867, 89868], "ref_id": 39524}, {"segmentation": [[3.7, 223.06, 75.68, 224.02, 222.51, 226.88, 225.38, 228.8, 217.1, 238.67, 80.14, 237.08, 81.74, 258.42, 186.84, 261.28, 177.29, 271.47, 11.03, 267.65, 9.75, 272.75, 176.97, 276.89, 176.65, 286.44, 7.84, 279.44, 7.21, 287.08, 0.0, 286.13, 0.2, 231.34, 0.84, 223.06], [230.68, 279.0, 220.06, 284.72, 271.56, 285.54, 269.52, 280.23], [326.34, 232.81, 421.17, 236.49, 451.42, 236.9, 449.38, 243.85, 338.6, 243.44, 337.38, 278.59, 427.71, 284.72, 430.98, 291.26, 340.65, 287.59, 338.6, 296.58, 327.56, 288.4, 325.93, 282.68, 330.02, 279.82, 330.43, 269.19, 326.75, 269.19, 323.89, 265.51, 330.43, 265.51, 331.24, 242.62, 325.93, 241.39], [311.21, 267.96, 312.85, 286.77, 305.08, 285.95, 298.95, 280.64, 308.76, 281.86, 309.99, 275.32, 305.49, 272.87, 302.63, 265.92]], "area": 10526.7059, "iscrowd": 0, "image_id": 206198, "bbox": [0.0, 223.06, 451.42, 73.52], "category_id": 15, "id": 1812129, "split": "val", "sentences": [{"tokens": ["bench", "on", "baseball", "dugout", "with", "people", "sitting", "on", "it"], "raw": "Bench on baseball dugout with people sitting on it.", "sent_id": 89893, "sent": "bench on baseball dugout with people sitting on it"}], "file_name": "COCO_train2014_000000206198_1812129.jpg", "ann_id": 1812129, "sent_ids": [89893], "ref_id": 39535}, {"segmentation": [[3.09, 169.19, 22.51, 165.95, 61.34, 164.88, 69.97, 154.09, 58.1, 147.62, 47.32, 127.12, 40.85, 127.12, 39.77, 138.99, 39.77, 124.97, 21.43, 141.15, 25.74, 122.81, 30.06, 112.02, 17.12, 108.79, 30.06, 99.08, 30.06, 99.08, 22.51, 87.21, 32.22, 83.98, 31.14, 63.48, 44.08, 64.56, 50.55, 55.93, 60.26, 59.17, 103.41, 28.97, 144.4, 13.86, 162.73, 28.97, 174.6, 27.89, 186.46, 38.67, 184.31, 51.62, 172.44, 63.48, 172.44, 71.03, 201.56, 76.43, 209.12, 53.77, 230.69, 54.85, 235.0, 67.8, 239.32, 85.06, 238.24, 105.55, 229.61, 106.63, 212.35, 90.45, 186.46, 89.37, 176.76, 103.39, 192.94, 127.12, 205.88, 118.49, 215.59, 137.91, 192.94, 190.76, 165.97, 185.37, 127.14, 195.08, 100.17, 228.52, 88.31, 267.35, 82.91, 297.55, 62.42, 311.57, 43.0, 308.34, 12.8, 318.04, 2.01, 314.81]], "area": 37790.5538, "iscrowd": 0, "image_id": 234819, "bbox": [2.01, 13.86, 237.31, 304.18], "category_id": 4, "id": 153242, "split": "val", "sentences": [{"tokens": ["the", "motorcycle", "that", "has", "a", "burgundy", "windshield"], "raw": "The motorcycle that has a burgundy windshield.", "sent_id": 89960, "sent": "the motorcycle that has a burgundy windshield"}, {"tokens": ["the", "dark", "maroon", "motorcycle", "behind", "the", "red", "one"], "raw": "the dark maroon motorcycle behind the red one", "sent_id": 89961, "sent": "the dark maroon motorcycle behind the red one"}], "file_name": "COCO_train2014_000000234819_153242.jpg", "ann_id": 153242, "sent_ids": [89960, 89961], "ref_id": 39564}, {"segmentation": [[365.66, 180.13, 367.82, 210.34, 368.9, 234.07, 374.29, 249.17, 365.66, 276.13, 351.64, 303.1, 340.85, 324.67, 338.7, 341.93, 341.93, 369.98, 341.93, 386.16, 339.78, 423.91, 350.56, 465.98, 349.48, 472.45, 331.15, 472.45, 331.15, 462.74, 332.22, 437.93, 327.91, 388.31, 322.52, 409.89, 323.6, 442.25, 327.91, 460.58, 319.28, 458.43, 308.49, 437.93, 313.89, 388.31, 310.65, 369.98, 325.75, 344.09, 314.97, 322.52, 307.42, 300.94, 294.47, 308.49, 285.84, 331.15, 269.66, 355.96, 275.06, 380.76, 269.66, 390.47, 280.45, 446.56, 280.45, 455.19, 273.98, 459.51, 268.58, 432.54, 263.19, 390.47, 258.88, 417.44, 254.56, 441.17, 250.25, 450.88, 239.46, 451.96, 234.07, 439.01, 244.85, 432.54, 250.25, 395.87, 252.4, 343.01, 249.17, 323.6, 243.78, 318.2, 248.09, 337.62, 238.38, 352.72, 225.44, 378.61, 231.91, 351.64, 238.38, 336.54, 243.78, 324.67, 241.62, 299.87, 236.22, 281.53, 231.91, 259.96, 235.15, 239.46, 251.33, 230.83, 256.72, 216.81, 278.29, 206.02, 300.94, 186.61, 320.36, 146.7, 340.85, 131.6, 379.69, 86.29, 391.55, 62.56, 391.55, 53.93, 384.0, 53.93, 368.9, 38.83, 380.76, 39.91, 394.79, 44.22, 396.94, 30.2, 400.18, 21.57, 408.81, 21.57, 408.81, 32.36, 417.44, 17.26, 421.75, 20.49, 423.91, 34.52, 423.91, 40.99, 423.91, 48.54, 435.78, 45.3, 434.7, 51.78, 423.91, 59.33, 426.07, 77.66, 424.99, 88.45, 428.22, 84.13, 427.15, 91.69, 417.44, 91.69, 407.73, 83.06]], "area": 29402.818800000015, "iscrowd": 0, "image_id": 226527, "bbox": [225.44, 17.26, 210.34, 455.19], "category_id": 25, "id": 599405, "split": "val", "sentences": [{"tokens": ["it", "is", "a", "giraffe", "in", "the", "forground", "facing", "forward"], "raw": "It is a giraffe in the forground facing forward", "sent_id": 89964, "sent": "it is a giraffe in the forground facing forward"}, {"tokens": ["the", "front", "giraffe"], "raw": "the front giraffe", "sent_id": 89965, "sent": "the front giraffe"}], "file_name": "COCO_train2014_000000226527_599405.jpg", "ann_id": 599405, "sent_ids": [89964, 89965], "ref_id": 39566}, {"segmentation": [[107.94, 366.91, 102.21, 348.76, 106.03, 343.03, 111.77, 322.01, 115.59, 285.71, 126.09, 237.95, 159.53, 237.0, 174.81, 237.0, 200.6, 238.91, 200.6, 221.71, 198.69, 208.34, 197.74, 196.88, 201.56, 195.92, 203.47, 208.34, 205.38, 217.89, 211.11, 218.85, 222.57, 216.94, 218.75, 222.67, 209.2, 222.67, 213.98, 234.13, 238.81, 251.32, 255.05, 265.65, 279.89, 284.76, 305.68, 299.09, 339.12, 308.64, 345.8, 315.33, 341.03, 335.39, 341.03, 346.85, 327.65, 350.67, 314.28, 356.4, 285.62, 360.22, 245.5, 360.22, 202.51, 365.96, 179.59, 365.96, 152.84, 365.96, 128.0, 366.91]], "area": 23477.404049999997, "iscrowd": 0, "image_id": 266228, "bbox": [102.21, 195.92, 243.59, 170.99], "category_id": 9, "id": 177927, "split": "val", "sentences": [{"tokens": ["old", "boat", "in", "the", "middle"], "raw": "Old boat in the middle.", "sent_id": 90145, "sent": "old boat in the middle"}, {"tokens": ["boat", "in", "motion"], "raw": "boat in motion", "sent_id": 90146, "sent": "boat in motion"}], "file_name": "COCO_train2014_000000266228_177927.jpg", "ann_id": 177927, "sent_ids": [90145, 90146], "ref_id": 39637}, {"segmentation": [[97.89, 233.35, 131.51, 205.66, 180.94, 334.2, 312.45, 345.08, 325.3, 404.4, 242.25, 397.48, 218.52, 373.75, 184.9, 341.12, 126.56, 298.61]], "area": 10548.382950000003, "iscrowd": 0, "image_id": 259514, "bbox": [97.89, 205.66, 227.41, 198.74], "category_id": 73, "id": 1103260, "split": "val", "sentences": [{"tokens": ["a", "black", "laptop", "with", "a", "blue", "screen"], "raw": "A black laptop with a blue screen", "sent_id": 90174, "sent": "a black laptop with a blue screen"}], "file_name": "COCO_train2014_000000259514_1103260.jpg", "ann_id": 1103260, "sent_ids": [90174], "ref_id": 39648}, {"segmentation": [[314.27, 17.01, 337.99, 53.06, 331.35, 63.5, 317.11, 76.79, 299.09, 85.33, 290.55, 101.46, 270.62, 111.89, 261.13, 106.2, 256.39, 131.82, 250.69, 149.85, 232.67, 154.59, 208.94, 151.75, 198.51, 142.26, 203.25, 124.23, 214.64, 106.2, 227.92, 93.87, 243.1, 80.58, 253.54, 62.55, 263.98, 45.47, 266.83, 38.83, 272.52, 23.65, 279.16, 16.06, 279.16, 2.77, 284.85, 0.0, 306.68, 0.0, 313.32, 2.77, 319.01, 16.06]], "area": 8922.419399999995, "iscrowd": 0, "image_id": 1407, "bbox": [198.51, 0.0, 139.48, 154.59], "category_id": 1, "id": 1246131, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "wheelchair"], "raw": "The man in the wheelchair", "sent_id": 90211, "sent": "the man in the wheelchair"}, {"tokens": ["the", "man", "in", "the", "wheelchair", "watching", "the", "tennis", "game"], "raw": "the man in the wheelchair watching the tennis game", "sent_id": 90212, "sent": "the man in the wheelchair watching the tennis game"}], "file_name": "COCO_train2014_000000001407_1246131.jpg", "ann_id": 1246131, "sent_ids": [90211, 90212], "ref_id": 39664}, {"segmentation": [[110.35, 422.04, 116.11, 328.97, 122.82, 300.18, 134.34, 276.19, 140.09, 265.64, 142.97, 257.0, 159.29, 255.08, 165.04, 253.16, 159.29, 235.89, 164.08, 218.62, 158.33, 206.14, 162.16, 183.11, 172.72, 178.32, 197.67, 169.68, 213.98, 167.76, 233.17, 181.2, 239.89, 195.59, 254.28, 200.39, 261.96, 220.54, 263.88, 248.36, 282.11, 255.08, 295.54, 285.79, 306.1, 313.61, 311.85, 350.08, 303.22, 379.82, 285.95, 378.86, 271.55, 375.98, 275.39, 421.08, 275.39, 423.0, 145.85, 421.08, 148.73, 385.58, 146.81, 362.55, 139.13, 395.17, 141.05, 423.0]], "area": 36352.880450000004, "iscrowd": 0, "image_id": 558824, "bbox": [110.35, 167.76, 201.5, 255.24], "category_id": 1, "id": 421795, "split": "val", "sentences": [{"tokens": ["lady", "with", "curly", "hair", "in", "ponyail", "under", "umbrella", "and", "looking", "to", "her", "left"], "raw": "lady with curly hair in ponyail under umbrella and looking to her left", "sent_id": 90241, "sent": "lady with curly hair in ponyail under umbrella and looking to her left"}, {"tokens": ["a", "girl", "walking", "on", "the", "road", "holding", "an", "umbrella", "and", "looking", "towards", "her", "left"], "raw": "A girl walking on the road holding an umbrella and looking towards her left", "sent_id": 90242, "sent": "a girl walking on the road holding an umbrella and looking towards her left"}], "file_name": "COCO_train2014_000000558824_421795.jpg", "ann_id": 421795, "sent_ids": [90241, 90242], "ref_id": 39678}, {"segmentation": [[70.03, 140.41, 78.92, 129.97, 89.14, 120.86, 84.25, 120.19, 86.03, 115.75, 84.92, 100.63, 89.59, 91.3, 95.14, 83.74, 107.14, 86.19, 113.58, 81.52, 124.91, 85.52, 129.36, 95.08, 132.47, 109.52, 128.91, 117.52, 139.8, 123.52, 139.36, 133.29, 137.14, 141.07, 137.36, 157.15, 137.58, 178.26, 133.36, 185.45, 139.36, 189.0, 141.58, 194.56, 139.36, 203.44, 136.69, 207.0, 136.69, 238.56, 135.8, 250.34, 137.58, 263.89, 137.8, 280.26, 138.02, 290.79, 141.36, 290.79, 143.13, 302.34, 145.8, 310.34, 150.02, 313.9, 147.58, 318.78, 140.91, 314.78, 119.14, 307.01, 125.14, 295.23, 127.58, 294.79, 126.03, 280.57, 122.25, 272.57, 121.58, 256.13, 121.58, 248.13, 119.36, 240.13, 112.92, 215.38, 107.36, 216.27, 106.47, 225.38, 105.14, 240.49, 101.59, 252.05, 103.14, 263.38, 101.81, 271.38, 98.92, 283.15, 101.14, 287.68, 102.25, 295.01, 102.03, 297.9, 98.47, 298.34, 88.25, 296.12, 86.25, 294.12, 89.59, 287.9, 91.59, 283.01, 90.03, 273.24, 87.81, 261.9, 87.37, 251.24, 88.7, 248.13, 89.36, 237.24, 86.25, 217.01, 73.81, 217.23, 74.26, 211.01, 82.25, 193.24, 75.37, 187.01, 73.59, 178.57, 68.92, 159.91]], "area": 10450.973199999999, "iscrowd": 0, "image_id": 494257, "bbox": [68.92, 81.52, 81.1, 237.26], "category_id": 1, "id": 464219, "split": "val", "sentences": [{"tokens": ["a", "girl", "on", "the", "tennis", "court", "lagging", "while", "her", "friend", "is", "in", "a", "bag"], "raw": "A girl on the tennis court lagging while her friend is in a bag.", "sent_id": 90274, "sent": "a girl on the tennis court lagging while her friend is in a bag"}, {"tokens": ["a", "woman", "smile", "and", "stand", "in", "a", "tennis", "court"], "raw": "A WOMAN SMILE  AND STAND IN A TENNIS COURT", "sent_id": 90275, "sent": "a woman smile and stand in a tennis court"}], "file_name": "COCO_train2014_000000494257_464219.jpg", "ann_id": 464219, "sent_ids": [90274, 90275], "ref_id": 39690}, {"segmentation": [[208.71, 164.29, 214.46, 149.93, 223.07, 143.23, 266.16, 137.48, 290.09, 154.72, 314.03, 154.72, 321.69, 143.23, 306.37, 124.08, 308.28, 100.14, 304.45, 86.74, 296.79, 75.25, 296.79, 64.72, 290.09, 53.23, 261.37, 67.59, 208.71, 81.95, 170.42, 79.08, 159.89, 76.21, 147.44, 112.59, 151.27, 135.57, 145.52, 160.46, 141.7, 177.69, 133.08, 196.84, 128.29, 223.65, 120.63, 239.92, 123.5, 257.16, 132.12, 263.86, 144.57, 260.99, 152.23, 254.29, 140.74, 242.8, 147.44, 221.73, 156.06, 199.71, 159.89, 240.88, 163.72, 269.6, 167.54, 288.75, 181.91, 295.45, 194.35, 281.09, 181.91, 260.99, 178.08, 243.75, 179.03, 210.24, 182.86, 192.05, 200.1, 169.08], [34.47, 55.15, 2.87, 61.85, 1.91, 101.1, 0.96, 193.01, 0.96, 227.48, 1.91, 238.97, 11.49, 241.84, 14.36, 235.14, 13.4, 225.56, 8.62, 221.73, 12.45, 208.33, 19.15, 193.97, 21.06, 169.08, 17.23, 154.72, 14.36, 135.57, 20.11, 110.68, 22.98, 104.93, 21.06, 94.4, 20.11, 79.08, 23.93, 60.89], [1.91, 283.96, 20.11, 292.58, 18.19, 302.16, 7.66, 309.81, 0.96, 308.86, 0.96, 288.75]], "area": 21067.853549999996, "iscrowd": 0, "image_id": 88671, "bbox": [0.96, 53.23, 320.73, 256.58], "category_id": 18, "id": 17163, "split": "val", "sentences": [{"tokens": ["a", "larger", "dog", "staring", "at", "a", "smaller", "dog"], "raw": "A larger dog staring at a smaller dog.", "sent_id": 90327, "sent": "a larger dog staring at a smaller dog"}], "file_name": "COCO_train2014_000000088671_17163.jpg", "ann_id": 17163, "sent_ids": [90327], "ref_id": 39712}, {"segmentation": [[270.18, 359.81, 245.52, 368.78, 237.67, 364.29, 233.18, 340.75, 245.52, 327.3, 237.67, 279.09, 238.79, 267.88, 246.64, 248.82, 255.61, 227.52, 274.66, 237.61, 284.75, 255.55, 308.3, 275.73, 327.35, 290.3, 323.99, 300.39, 310.54, 312.72, 295.96, 320.57, 279.15, 327.3, 275.78, 349.72]], "area": 6970.510799999998, "iscrowd": 0, "image_id": 105358, "bbox": [233.18, 227.52, 94.17, 141.26], "category_id": 1, "id": 461072, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "shirt", "sitting", "on", "the", "couch", "watching", "an", "elderly", "man", "play", "a", "video", "game"], "raw": "A man in a blue shirt sitting on the couch watching an elderly man play a video game.", "sent_id": 90355, "sent": "a man in a blue shirt sitting on the couch watching an elderly man play a video game"}, {"tokens": ["a", "man", "sitting", "on", "the", "couch", "wearing", "a", "blue", "shirt"], "raw": "A man sitting on the couch wearing a blue shirt.", "sent_id": 90356, "sent": "a man sitting on the couch wearing a blue shirt"}], "file_name": "COCO_train2014_000000105358_461072.jpg", "ann_id": 461072, "sent_ids": [90355, 90356], "ref_id": 39723}, {"segmentation": [[204.8, 481.17, 202.6, 456.95, 202.6, 428.32, 203.7, 415.11, 202.6, 394.18, 203.7, 354.55, 209.2, 339.13, 243.34, 339.13, 271.97, 329.22, 295.09, 317.11, 309.4, 302.8, 323.72, 291.78, 339.13, 295.09, 372.16, 301.69, 401.89, 328.12, 412.9, 351.24, 406.3, 357.85, 382.07, 360.05, 352.34, 382.07, 339.13, 387.58, 339.13, 422.81, 328.12, 459.15, 330.32, 493.28, 314.91, 495.48, 310.5, 487.78, 310.5, 470.16, 311.6, 447.04, 302.8, 434.92, 298.39, 434.92, 295.09, 456.95, 302.8, 498.79, 287.38, 500.99, 275.27, 493.28, 277.47, 469.06, 268.66, 434.92, 265.36, 450.34, 274.17, 480.07, 267.56, 484.47, 262.06, 481.17, 257.65, 450.34, 241.14, 429.42, 230.12, 409.6, 222.42, 450.34, 229.02, 487.78, 215.81, 488.88, 207.0, 478.97]], "area": 23514.749649999998, "iscrowd": 0, "image_id": 71970, "bbox": [202.6, 291.78, 210.3, 209.21], "category_id": 21, "id": 71307, "split": "val", "sentences": [{"tokens": ["a", "cow", "statue", "with", "two", "other", "cows", "standing", "on", "its", "back"], "raw": "A cow statue with two other cows standing on its back.", "sent_id": 90357, "sent": "a cow statue with two other cows standing on its back"}, {"tokens": ["a", "bull", "at", "the", "bottom", "of", "a", "bovine", "sculpture"], "raw": "a bull at the bottom of a bovine sculpture", "sent_id": 90358, "sent": "a bull at the bottom of a bovine sculpture"}], "file_name": "COCO_train2014_000000071970_71307.jpg", "ann_id": 71307, "sent_ids": [90357, 90358], "ref_id": 39724}, {"segmentation": [[113.73, 167.53, 172.87, 225.93, 203.53, 298.2, 207.91, 313.53, 218.13, 301.12, 199.15, 241.26, 179.44, 212.79, 142.21, 179.94, 129.79, 170.45]], "area": 2327.656099999999, "iscrowd": 0, "image_id": 543642, "bbox": [113.73, 167.53, 104.4, 146.0], "category_id": 31, "id": 1836211, "split": "val", "sentences": [{"tokens": ["the", "purse", "strap", "on", "the", "woman"], "raw": "the purse strap on the woman", "sent_id": 90368, "sent": "the purse strap on the woman"}, {"tokens": ["brown", "purse", "strap"], "raw": "Brown purse strap", "sent_id": 90369, "sent": "brown purse strap"}], "file_name": "COCO_train2014_000000543642_1836211.jpg", "ann_id": 1836211, "sent_ids": [90368, 90369], "ref_id": 39729}, {"segmentation": [[245.11, 203.05, 269.69, 145.33, 313.12, 116.76, 329.11, 93.91, 317.69, 53.9, 329.11, 12.76, 351.97, 3.05, 390.83, 7.62, 423.4, 45.34, 414.26, 72.19, 401.11, 81.34, 403.4, 98.48, 395.97, 106.48, 435.4, 118.48, 466.83, 185.33, 485.69, 231.05, 491.97, 250.48, 377.11, 249.91, 386.26, 231.05, 383.97, 216.19, 376.54, 205.33, 243.97, 203.62]], "area": 30500.37264999999, "iscrowd": 0, "image_id": 402264, "bbox": [243.97, 3.05, 248.0, 247.43], "category_id": 1, "id": 479905, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "buttoned", "up", "shirt"], "raw": "A man in a buttoned up shirt.", "sent_id": 90380, "sent": "a man in a buttoned up shirt"}, {"tokens": ["a", "man", "who", "stand", "in", "the", "middle", "with", "grey", "shirt"], "raw": "A man who stand in the middle with grey shirt", "sent_id": 90381, "sent": "a man who stand in the middle with grey shirt"}], "file_name": "COCO_train2014_000000402264_479905.jpg", "ann_id": 479905, "sent_ids": [90380, 90381], "ref_id": 39733}, {"segmentation": [[1.08, 217.84, 23.78, 218.92, 40.0, 221.08, 43.24, 203.78, 47.57, 167.03, 56.22, 144.32, 74.59, 119.46, 95.14, 106.49, 108.11, 103.24, 128.65, 103.24, 156.76, 107.57, 178.38, 125.95, 196.76, 142.16, 200.0, 165.95, 193.51, 173.51, 192.43, 183.24, 192.43, 189.73, 197.84, 195.14, 192.43, 210.27, 189.19, 214.59, 192.43, 223.24, 184.86, 228.65, 182.7, 232.97, 182.7, 241.62, 177.3, 254.59, 170.81, 266.49, 158.92, 268.65, 142.7, 268.65, 125.41, 272.97, 134.05, 281.62, 147.03, 294.59, 162.16, 306.49, 164.32, 318.38, 169.73, 328.11, 179.46, 338.92, 187.03, 348.65, 216.22, 369.19, 221.62, 372.43, 249.73, 322.7, 276.76, 263.24, 277.84, 252.43, 274.59, 235.14, 288.65, 204.86, 302.7, 191.89, 310.27, 190.81, 324.32, 191.89, 331.89, 211.35, 339.46, 229.73, 340.54, 238.38, 339.46, 248.11, 329.73, 268.65, 313.51, 277.3, 299.46, 304.32, 281.08, 374.59, 262.7, 377.84, 256.22, 382.16, 247.57, 402.7, 250.81, 413.51, 251.89, 416.76, 241.08, 421.08, 238.92, 425.41, 236.76, 436.22, 232.43, 436.22, 189.19, 421.08, 154.59, 401.62, 142.7, 404.86, 129.73, 404.86, 110.27, 382.16, 91.89, 440.54, 97.3, 439.46, 102.7, 429.73, 109.19, 424.32, 117.84, 422.16, 131.89, 427.57, 174.05, 472.97, 3.24, 472.97]], "area": 68922.59080000003, "iscrowd": 0, "image_id": 265625, "bbox": [1.08, 103.24, 339.46, 369.73], "category_id": 1, "id": 463326, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "black", "shirt", "holding", "an", "umbrella"], "raw": "A MAN IN A BLACK SHIRT HOLDING AN UMBRELLA.", "sent_id": 90414, "sent": "a man in a black shirt holding an umbrella"}, {"tokens": ["a", "man", "holding", "an", "umbrella", "over", "a", "woman"], "raw": "a man holding an umbrella over a woman", "sent_id": 90415, "sent": "a man holding an umbrella over a woman"}], "file_name": "COCO_train2014_000000265625_463326.jpg", "ann_id": 463326, "sent_ids": [90414, 90415], "ref_id": 39749}, {"segmentation": [[322.6, 288.86, 323.32, 279.52, 319.73, 268.04, 319.73, 257.27, 316.86, 253.68, 314.71, 242.19, 308.96, 235.73, 309.68, 232.14, 308.24, 225.68, 306.09, 222.09, 304.65, 238.6, 303.94, 253.68, 306.81, 260.14, 301.07, 285.98, 297.48, 300.34, 300.35, 321.88, 301.07, 331.93, 295.32, 332.65, 292.45, 326.19, 294.6, 337.68, 284.55, 336.24, 283.12, 326.91, 285.27, 320.45, 286.71, 308.96, 290.3, 298.19, 288.86, 288.14, 287.42, 275.93, 286.71, 267.32, 287.42, 253.68, 290.3, 224.96, 283.12, 225.68, 278.81, 209.16, 279.53, 201.26, 287.42, 191.93, 293.89, 186.19, 306.09, 175.42, 310.4, 169.67, 302.5, 163.93, 298.91, 157.47, 295.32, 153.16, 291.01, 140.24, 290.3, 132.34, 293.89, 120.85, 298.91, 115.83, 304.65, 113.67, 313.99, 111.52, 322.6, 114.39, 327.63, 122.29, 331.22, 131.62, 334.09, 135.21, 335.53, 143.11, 332.66, 151.72, 331.22, 156.75, 331.94, 159.62, 339.12, 160.34, 351.32, 162.49, 359.22, 163.21, 369.27, 163.21, 370.71, 164.65, 372.86, 167.52, 372.14, 171.11, 366.4, 181.88, 362.81, 190.49, 362.81, 202.7, 365.68, 210.6, 367.84, 221.37, 372.14, 229.26, 377.89, 234.29, 380.76, 239.32, 386.5, 250.8, 387.22, 253.68, 379.62, 273.19, 379.62, 287.38, 377.26, 299.2, 377.26, 301.57, 376.7, 304.37, 371.1, 306.6, 365.51, 306.05, 359.92, 309.96, 357.12, 312.2, 351.53, 313.32, 333.62, 311.64, 343.13, 322.83, 349.85, 327.3, 355.44, 330.66, 364.39, 337.93, 368.31, 342.41, 368.31, 347.44, 357.68, 351.36, 352.64, 355.83, 344.25, 360.87, 334.18, 362.55, 320.76, 367.58, 316.28, 362.55, 312.93, 353.6, 312.93, 344.65, 312.93, 337.37, 314.6, 328.42, 312.37, 301.57, 315.72, 294.3, 318.52, 289.26, 319.64, 285.91, 320.76, 284.79]], "area": 15699.764050000007, "iscrowd": 0, "image_id": 275917, "bbox": [278.81, 111.52, 108.41, 256.06], "category_id": 1, "id": 457515, "split": "val", "sentences": [{"tokens": ["a", "guy", "with", "glasses", "wear", "a", "dc", "hat"], "raw": "A guy with glasses wear a DC hat.", "sent_id": 90418, "sent": "a guy with glasses wear a dc hat"}, {"tokens": ["a", "man", "wearing", "a", "blue", "shirt", "and", "black", "sunglasses"], "raw": "A man wearing a blue shirt and black sunglasses.", "sent_id": 90419, "sent": "a man wearing a blue shirt and black sunglasses"}], "file_name": "COCO_train2014_000000275917_457515.jpg", "ann_id": 457515, "sent_ids": [90418, 90419], "ref_id": 39751}, {"segmentation": [[0.84, 228.37, 42.13, 197.19, 58.15, 188.76, 68.26, 185.39, 72.47, 185.39, 107.87, 158.43, 169.38, 152.53, 172.75, 225.0, 175.28, 330.34, 176.97, 342.13, 194.66, 358.99, 291.57, 357.3, 332.02, 346.35, 353.93, 334.55, 379.21, 339.61, 391.85, 350.56, 390.17, 363.2, 379.21, 370.79, 1.69, 369.1, 1.69, 302.53, 48.03, 261.24, 4.21, 257.02], [311.8, 20.22, 321.91, 22.75, 334.55, 22.75, 342.13, 35.39, 350.56, 58.15, 337.08, 91.85, 337.92, 107.02, 350.56, 106.18, 359.83, 111.24, 366.57, 133.99, 370.79, 172.75, 368.26, 200.56, 364.04, 215.73, 357.3, 267.13, 342.98, 296.63, 337.08, 303.37, 330.34, 105.34, 326.12, 32.02]], "area": 42610.61390000001, "iscrowd": 0, "image_id": 273600, "bbox": [0.84, 20.22, 391.01, 350.57], "category_id": 1, "id": 496564, "split": "val", "sentences": [{"tokens": ["the", "palm", "on", "which", "the", "device", "is", "been", "displaying"], "raw": "the palm on which the device is been displaying", "sent_id": 90483, "sent": "the palm on which the device is been displaying"}, {"tokens": ["a", "person", "'", "s", "hand", "who", "is", "holding", "a", "samsung", "phone"], "raw": "a person's hand who is holding a samsung phone", "sent_id": 90484, "sent": "a person ' s hand who is holding a samsung phone"}], "file_name": "COCO_train2014_000000273600_496564.jpg", "ann_id": 496564, "sent_ids": [90483, 90484], "ref_id": 39777}, {"segmentation": [[168.26, 472.77, 179.61, 453.16, 184.77, 441.81, 194.06, 428.39, 202.32, 423.23, 210.48, 423.98, 212.55, 419.85, 211.52, 412.63, 219.77, 385.79, 223.9, 378.56, 197.06, 362.05, 196.03, 355.85, 196.03, 347.6, 197.06, 339.34, 198.1, 334.18, 205.32, 335.21, 204.29, 361.02, 217.71, 369.27, 263.13, 378.56, 284.81, 361.02, 291.0, 358.95, 286.87, 367.21, 265.19, 379.6, 272.42, 398.18, 271.39, 406.44, 265.19, 425.02, 262.1, 450.82, 260.03, 453.92, 246.61, 453.92, 239.39, 443.6, 238.35, 440.5, 237.32, 432.24, 237.32, 426.05, 229.06, 420.89, 230.1, 430.18, 230.1, 433.27, 232.16, 451.85, 229.06, 464.24, 229.06, 473.53, 229.06, 477.66, 211.52, 478.69, 170.23, 474.56, 168.16, 476.63], [295.13, 385.79, 301.32, 380.63, 316.81, 399.21, 316.81, 411.6, 314.74, 425.02, 307.52, 438.44, 304.42, 446.69, 292.03, 466.31, 286.87, 471.47, 277.58, 471.47, 267.26, 465.27, 267.26, 458.05, 264.16, 452.89, 266.23, 449.79, 284.81, 442.56, 292.03, 437.4, 295.13, 429.15, 297.19, 410.56, 289.97, 391.98, 289.97, 386.82]], "area": 8334.02635, "iscrowd": 0, "image_id": 142014, "bbox": [168.16, 334.18, 148.65, 144.51], "category_id": 2, "id": 126456, "split": "val", "sentences": [{"tokens": ["a", "red", "bicycle"], "raw": "A red bicycle.", "sent_id": 90487, "sent": "a red bicycle"}, {"tokens": ["the", "red", "bicycle"], "raw": "the red bicycle", "sent_id": 90488, "sent": "the red bicycle"}], "file_name": "COCO_train2014_000000142014_126456.jpg", "ann_id": 126456, "sent_ids": [90487, 90488], "ref_id": 39779}, {"segmentation": [[221.54, 229.33, 218.29, 207.4, 220.73, 180.58, 228.85, 166.77, 237.79, 155.4, 252.41, 155.4, 266.23, 157.83, 272.73, 165.15, 273.54, 185.46, 273.54, 207.4, 271.1, 226.08, 288.16, 230.15, 306.04, 230.15, 310.1, 238.27, 310.91, 282.15, 309.29, 318.71, 290.6, 321.15, 275.98, 321.96, 254.04, 313.83, 245.1, 318.71, 242.66, 328.46, 246.73, 341.46, 258.1, 355.27, 240.23, 366.65, 219.91, 395.08, 210.98, 389.4, 207.73, 378.02, 203.67, 371.52, 186.6, 369.08, 176.85, 386.96, 153.29, 392.65, 143.54, 391.83, 141.92, 380.46, 143.54, 356.9, 150.85, 334.15, 161.42, 311.4, 168.73, 300.02, 186.6, 263.46, 202.85, 252.9, 215.85, 243.15]], "area": 21086.26705, "iscrowd": 0, "image_id": 314319, "bbox": [141.92, 155.4, 168.99, 239.68], "category_id": 1, "id": 443143, "split": "val", "sentences": [{"tokens": ["a", "woman", "holding", "an", "umbrella", "and", "a", "baby"], "raw": "A woman holding an umbrella and a baby.", "sent_id": 90505, "sent": "a woman holding an umbrella and a baby"}, {"tokens": ["a", "woman", "holding", "an", "umbrella"], "raw": "A woman holding an umbrella.", "sent_id": 90506, "sent": "a woman holding an umbrella"}], "file_name": "COCO_train2014_000000314319_443143.jpg", "ann_id": 443143, "sent_ids": [90505, 90506], "ref_id": 39787}, {"segmentation": [[337.57, 101.63, 378.97, 34.36, 404.84, 8.49, 429.68, 7.45, 604.58, 54.02, 640.0, 65.41, 635.63, 239.27, 628.38, 239.27, 607.68, 232.03, 436.92, 170.97, 340.68, 138.88, 331.36, 132.67]], "area": 46076.54245, "iscrowd": 0, "image_id": 178763, "bbox": [331.36, 7.45, 308.64, 231.82], "category_id": 51, "id": 2109673, "split": "val", "sentences": [{"tokens": ["a", "lunch", "box", "in", "top", "right", "corner", "with", "a", "green", "color", "small", "box", "in", "one", "of", "the", "compartments"], "raw": "A lunch box in top right corner with a green color small box in one of the compartments.", "sent_id": 90528, "sent": "a lunch box in top right corner with a green color small box in one of the compartments"}, {"tokens": ["lunch", "box", "with", "the", "small", "green", "container", "in", "it"], "raw": "lunch box with the small green container in it", "sent_id": 90529, "sent": "lunch box with the small green container in it"}], "file_name": "COCO_train2014_000000178763_2109673.jpg", "ann_id": 2109673, "sent_ids": [90528, 90529], "ref_id": 39795}, {"segmentation": [[453.89, 395.29, 439.46, 347.21, 434.65, 323.17, 432.73, 305.86, 452.93, 247.2, 427.92, 244.32, 435.62, 195.27, 433.69, 179.89, 439.46, 167.39, 459.66, 154.89, 461.58, 153.92, 470.23, 177.0, 487.54, 222.2, 487.54, 193.35, 501.97, 180.85, 495.24, 158.73, 492.35, 145.27, 505.81, 103.92, 541.4, 100.07, 562.55, 155.85, 542.36, 165.46, 563.51, 202.97, 557.74, 251.05, 541.4, 319.32, 513.51, 378.94, 501.97, 382.79, 501.97, 400.1, 453.89, 403.95, 451.96, 390.48]], "area": 27019.829749999997, "iscrowd": 0, "image_id": 181929, "bbox": [427.92, 100.07, 135.59, 303.88], "category_id": 1, "id": 518725, "split": "val", "sentences": [{"tokens": ["man", "with", "phone"], "raw": "Man with phone", "sent_id": 90566, "sent": "man with phone"}, {"tokens": ["a", "man", "in", "a", "brown", "jacket", "holding", "a", "camera"], "raw": "a man in a brown jacket holding a camera", "sent_id": 90567, "sent": "a man in a brown jacket holding a camera"}], "file_name": "COCO_train2014_000000181929_518725.jpg", "ann_id": 518725, "sent_ids": [90566, 90567], "ref_id": 39808}, {"segmentation": [[140.14, 247.77, 131.08, 240.98, 132.25, 232.37, 133.79, 228.42, 134.71, 213.81, 128.82, 207.92, 118.7, 205.44, 109.18, 211.79, 108.38, 220.55, 110.25, 226.94, 113.42, 233.28, 115.69, 243.24, 113.97, 242.04, 109.81, 243.73, 102.27, 246.59, 96.94, 248.8, 92.26, 252.18, 88.74, 258.55, 87.96, 260.01, 85.62, 264.95, 83.28, 270.67, 81.98, 275.49, 79.51, 280.56, 78.99, 281.99, 82.24, 283.29, 84.45, 283.94, 83.8, 285.69, 81.46, 289.85, 80.16, 292.45, 80.29, 296.48, 82.5, 299.99, 84.97, 303.37, 87.57, 306.24, 90.17, 307.93, 93.69, 308.06, 95.64, 306.11, 96.55, 303.5, 96.03, 301.16, 94.6, 299.7, 93.17, 297.23, 91.09, 293.85, 93.69, 285.79, 93.95, 284.88, 97.98, 284.75, 98.37, 293.59, 99.2, 303.01, 100.87, 309.02, 100.87, 314.69, 100.2, 319.53, 100.37, 323.04, 98.53, 328.71, 92.86, 360.45, 90.52, 393.16, 103.88, 393.66, 99.7, 405.34, 98.03, 413.81, 99.2, 426.0, 115.56, 425.99, 116.89, 413.98, 116.73, 404.8, 118.06, 397.29, 120.23, 391.78, 123.57, 370.13, 125.74, 370.8, 132.08, 389.66, 132.42, 393.16, 137.26, 394.33, 140.09, 406.35, 140.76, 418.82, 142.6, 426.0, 157.12, 426.0, 157.62, 418.65, 158.22, 413.08, 156.4, 405.27, 154.48, 397.98, 153.06, 393.62, 152.55, 391.7, 156.5, 388.96, 154.88, 363.77, 155.27, 353.76, 154.48, 341.37, 152.42, 321.34, 151.39, 313.83, 149.92, 311.33, 149.77, 294.24, 149.92, 293.21, 147.64, 283.29, 149.2, 281.74, 152.62, 284.23, 162.59, 277.38, 156.05, 259.31, 153.56, 254.64, 138.92, 247.17], [159.18, 279.71, 160.34, 278.85, 163.03, 284.85, 163.83, 287.89, 163.11, 291.02, 161.95, 293.43, 158.64, 293.88, 156.85, 294.33, 153.99, 294.24, 152.02, 293.43, 151.49, 292.54, 150.86, 292.27, 149.7, 291.82, 148.63, 288.33, 148.27, 286.01, 148.09, 285.03, 152.02, 285.56, 152.92, 284.31, 152.63, 284.1, 158.55, 280.37, 159.72, 279.75]], "area": 11039.49665000001, "iscrowd": 0, "image_id": 205131, "bbox": [78.99, 205.44, 84.84, 220.56], "category_id": 1, "id": 546256, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "blue", "shirt", "flying", "a", "kite"], "raw": "A man wearing a blue shirt flying a kite.", "sent_id": 90651, "sent": "a man wearing a blue shirt flying a kite"}, {"tokens": ["a", "young", "man", "flying", "a", "kite", "with", "his", "back", "turned", "to", "the", "camera"], "raw": "A young man flying a kite with his back turned to the camera.", "sent_id": 90652, "sent": "a young man flying a kite with his back turned to the camera"}], "file_name": "COCO_train2014_000000205131_546256.jpg", "ann_id": 546256, "sent_ids": [90651, 90652], "ref_id": 39841}, {"segmentation": [[407.22, 327.12, 405.62, 341.54, 406.02, 354.36, 407.62, 408.45, 409.23, 425.67, 345.93, 426.0, 340.72, 410.05, 341.52, 392.82, 337.12, 361.18, 336.32, 340.74, 326.3, 335.54, 320.29, 317.91, 315.48, 284.26, 319.09, 275.04, 322.29, 237.79, 327.9, 204.93, 335.91, 177.69, 336.32, 170.88, 339.12, 169.68, 343.93, 159.66, 349.13, 150.85, 342.73, 145.24, 341.52, 142.44, 338.32, 143.24, 337.52, 140.44, 335.91, 137.63, 332.71, 135.23, 334.71, 132.02, 334.31, 126.81, 329.5, 120.81, 330.71, 108.39, 326.3, 111.59, 323.9, 110.39, 325.1, 99.97, 329.91, 93.96, 333.91, 94.77, 347.93, 86.75, 357.55, 85.15, 371.57, 90.36, 376.78, 99.17, 381.18, 118.4, 379.58, 126.81, 386.79, 125.61, 396.41, 140.44, 398.01, 140.44, 404.42, 149.65, 420.04, 165.27, 422.05, 169.68, 423.65, 174.09, 427.26, 236.98, 424.05, 245.8, 417.64, 259.42, 415.64, 311.9, 407.62, 326.72]], "area": 26682.99930000001, "iscrowd": 0, "image_id": 454144, "bbox": [315.48, 85.15, 111.78, 340.85], "category_id": 1, "id": 498536, "split": "val", "sentences": [{"tokens": ["a", "man", "dressed", "in", "a", "black", "leather", "jacket", "and", "denim", "pants", "is", "standing", "while", "looking", "downward"], "raw": "A man dressed in a black leather jacket and denim pants is standing while looking downward.", "sent_id": 90653, "sent": "a man dressed in a black leather jacket and denim pants is standing while looking downward"}, {"tokens": ["the", "man", "wearing", "the", "black", "leather", "jacket", "and", "blue", "jeans"], "raw": "The man wearing the black leather jacket and blue jeans.", "sent_id": 90654, "sent": "the man wearing the black leather jacket and blue jeans"}], "file_name": "COCO_train2014_000000454144_498536.jpg", "ann_id": 498536, "sent_ids": [90653, 90654], "ref_id": 39842}, {"segmentation": [[90.26, 423.68, 105.48, 401.36, 115.62, 391.22, 121.7, 388.18, 157.2, 391.22, 181.54, 382.09, 221.09, 359.78, 228.19, 326.31, 243.4, 319.21, 251.52, 327.33, 274.84, 314.14, 302.23, 294.87, 310.34, 271.55, 322.51, 266.48, 349.89, 263.43, 384.38, 273.58, 396.55, 276.62, 436.1, 263.43, 499.99, 281.69, 581.13, 280.68, 640.0, 312.12, 639.95, 423.68]], "area": 62747.36355000001, "iscrowd": 0, "image_id": 569214, "bbox": [90.26, 263.43, 549.74, 160.25], "category_id": 67, "id": 119923, "split": "val", "sentences": [{"tokens": ["a", "plate", "of", "cheese", "and", "crackers"], "raw": "A plate of cheese and crackers.", "sent_id": 90708, "sent": "a plate of cheese and crackers"}, {"tokens": ["a", "platter", "of", "cheese", "and", "crackers"], "raw": "A platter of cheese and crackers.", "sent_id": 90709, "sent": "a platter of cheese and crackers"}], "file_name": "COCO_train2014_000000569214_119923.jpg", "ann_id": 119923, "sent_ids": [90708, 90709], "ref_id": 39865}, {"segmentation": [[640.0, 375.1, 634.51, 148.49, 593.3, 159.47, 572.7, 177.33, 593.3, 149.86, 590.56, 140.25, 585.06, 140.25, 524.64, 177.33, 431.24, 144.37, 417.51, 185.57, 457.34, 185.57, 473.82, 175.95, 528.76, 200.68, 532.88, 252.86, 501.29, 285.83, 453.22, 344.88, 421.63, 436.9, 423.0, 548.14, 460.09, 601.71, 494.42, 608.57, 542.49, 571.49, 572.7, 513.81, 586.44, 461.62, 597.42, 395.7, 638.63, 370.98]], "area": 64947.231500000016, "iscrowd": 0, "image_id": 490887, "bbox": [417.51, 140.25, 222.49, 468.32], "category_id": 2, "id": 129365, "split": "val", "sentences": [{"tokens": ["the", "bike", "to", "the", "right", "of", "the", "frame"], "raw": "The bike to the right of the frame.", "sent_id": 90768, "sent": "the bike to the right of the frame"}, {"tokens": ["blue", "bicycle", "leaning", "against", "the", "pole"], "raw": "Blue bicycle leaning against the pole.", "sent_id": 90769, "sent": "blue bicycle leaning against the pole"}], "file_name": "COCO_train2014_000000490887_129365.jpg", "ann_id": 129365, "sent_ids": [90768, 90769], "ref_id": 39889}, {"segmentation": [[188.41, 2.01, 134.12, 38.2, 134.12, 47.25, 141.16, 61.33, 162.27, 82.44, 256.77, 135.72, 324.13, 54.29, 329.16, 23.12, 322.12, 16.09, 320.11, 16.09, 307.04, 1.01, 191.43, 0.0]], "area": 17366.9497, "iscrowd": 0, "image_id": 29473, "bbox": [134.12, 0.0, 195.04, 135.72], "category_id": 54, "id": 1909556, "split": "val", "sentences": [{"tokens": ["the", "bowl", "with", "bread"], "raw": "the bowl with bread", "sent_id": 90864, "sent": "the bowl with bread"}, {"tokens": ["a", "sandwich", "with", "thick", "wheat", "bread", "in", "a", "white", "bowl"], "raw": "A sandwich with thick wheat bread in a white bowl.", "sent_id": 90865, "sent": "a sandwich with thick wheat bread in a white bowl"}], "file_name": "COCO_train2014_000000029473_1909556.jpg", "ann_id": 1909556, "sent_ids": [90864, 90865], "ref_id": 39927}, {"segmentation": [[509.73, 177.94, 512.37, 193.79, 521.61, 205.67, 534.82, 214.92, 533.5, 230.76, 512.37, 238.69, 480.68, 263.78, 456.91, 267.74, 415.97, 241.33, 404.09, 218.88, 389.56, 214.92, 386.92, 224.16, 388.24, 233.41, 393.52, 246.61, 415.97, 270.38, 435.78, 279.62, 463.51, 283.59, 472.75, 286.23, 489.92, 287.55, 515.01, 276.98, 533.5, 278.3, 553.31, 304.72, 561.23, 306.04, 581.04, 310.0, 585.0, 310.0, 595.56, 310.0, 591.6, 300.75, 579.72, 294.15, 569.15, 292.83, 554.63, 290.19, 546.7, 284.91, 541.42, 279.62, 558.59, 274.34, 585.0, 274.34, 604.81, 280.95, 632.54, 286.23, 633.86, 271.7, 632.54, 263.78, 624.62, 251.89, 615.37, 230.76, 611.41, 214.92, 588.96, 208.32, 585.0, 205.67, 592.92, 192.47, 586.32, 162.1, 571.79, 151.53, 545.38, 142.29, 520.29, 152.85, 513.69, 167.38], [624.62, 317.92, 624.62, 346.97, 625.94, 358.86, 632.54, 370.74, 633.86, 398.47, 627.26, 399.79, 615.37, 397.15, 602.17, 395.83, 598.21, 395.83, 595.56, 402.44, 599.53, 410.36, 627.26, 410.36, 640.0, 418.28, 639.14, 550.34, 621.98, 545.05, 604.81, 530.53, 582.36, 492.23, 582.36, 482.99, 578.4, 452.62, 562.55, 419.6, 562.55, 378.67, 561.23, 339.05, 558.59, 331.13]], "area": 28307.687550000002, "iscrowd": 0, "image_id": 431817, "bbox": [386.92, 142.29, 253.08, 408.05], "category_id": 1, "id": 204368, "split": "val", "sentences": [{"tokens": ["a", "women", "in", "a", "pink", "shirt", "petting", "a", "horse"], "raw": "A women in a pink shirt petting a horse.", "sent_id": 90874, "sent": "a women in a pink shirt petting a horse"}, {"tokens": ["woman", "touching", "the", "horse"], "raw": "Woman touching the horse.", "sent_id": 90875, "sent": "woman touching the horse"}], "file_name": "COCO_train2014_000000431817_204368.jpg", "ann_id": 204368, "sent_ids": [90874, 90875], "ref_id": 39932}, {"segmentation": [[339.29, 344.12, 327.11, 290.53, 318.59, 288.1, 319.81, 217.47, 448.89, 207.72, 472.03, 236.95, 467.16, 357.51, 426.97, 356.29, 397.74, 291.75, 379.48, 294.19, 375.82, 352.64], [341.73, 370.91, 341.73, 435.45, 369.73, 439.1, 373.39, 362.38], [429.41, 387.96, 431.84, 457.37, 462.29, 447.63, 464.72, 389.17], [312.5, 189.46, 434.28, 187.02, 356.34, 146.83, 312.5, 176.06], [252.83, 156.58, 227.25, 111.52, 184.63, 128.57, 174.89, 109.08, 198.03, 88.38, 215.08, 55.5, 227.25, 64.02, 227.25, 78.64, 252.83, 70.11, 250.39, 88.38, 291.8, 127.35]], "area": 29818.398400000002, "iscrowd": 0, "image_id": 74663, "bbox": [174.89, 55.5, 297.14, 401.87], "category_id": 25, "id": 599032, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "that", "is", "on", "the", "other", "side", "of", "the", "fence", "and", "further", "from", "the", "camera", ".", "the", "giraffe", "is", "facing", "towards", "the", "left"], "raw": "The giraffe that is on the other side of the fence and further from the camera. The giraffe is facing towards the left.", "sent_id": 90933, "sent": "the giraffe that is on the other side of the fence and further from the camera . the giraffe is facing towards the left"}, {"tokens": ["entire", "giraffe", "on", "the", "right", "behind", "the", "bars"], "raw": "Entire giraffe on the right behind the bars", "sent_id": 90934, "sent": "entire giraffe on the right behind the bars"}], "file_name": "COCO_train2014_000000074663_599032.jpg", "ann_id": 599032, "sent_ids": [90933, 90934], "ref_id": 39955}, {"segmentation": [[87.85, 478.64, 46.85, 425.93, 21.75, 356.48, 17.57, 312.14, 24.26, 277.84, 32.63, 250.23, 47.69, 236.84, 66.93, 224.29, 75.3, 220.94, 79.48, 239.35, 71.95, 267.8, 74.46, 282.02, 76.97, 302.94, 79.48, 324.69, 97.05, 375.73, 105.42, 400.83, 112.11, 420.07, 120.48, 437.64, 127.17, 448.52, 130.52, 461.91, 131.36, 472.78, 135.54, 480.0, 90.36, 479.48]], "area": 14611.002300000006, "iscrowd": 0, "image_id": 578523, "bbox": [17.57, 220.94, 117.97, 259.06], "category_id": 62, "id": 374754, "split": "val", "sentences": [{"tokens": ["chair", "with", "woman", "in", "blue", "shirt", "sitting", "on", "it"], "raw": "Chair with woman in blue shirt sitting on it.", "sent_id": 90945, "sent": "chair with woman in blue shirt sitting on it"}, {"tokens": ["back", "of", "wooden", "chair", "being", "occupied", "by", "woman", "in", "blue"], "raw": "Back of wooden chair being occupied by woman in blue", "sent_id": 90946, "sent": "back of wooden chair being occupied by woman in blue"}], "file_name": "COCO_train2014_000000578523_374754.jpg", "ann_id": 374754, "sent_ids": [90945, 90946], "ref_id": 39959}, {"segmentation": [[286.21, 400.87, 303.72, 368.49, 291.46, 343.98, 289.71, 309.85, 308.97, 267.83, 329.98, 252.95, 327.35, 237.2, 326.48, 217.94, 313.35, 211.82, 289.71, 190.81, 287.09, 175.93, 308.97, 178.55, 308.97, 149.67, 284.46, 134.79, 251.2, 132.17, 228.45, 166.3, 258.2, 170.68, 259.08, 199.56, 236.32, 235.45, 228.45, 294.09, 225.82, 309.85, 210.06, 314.22, 217.07, 378.12, 256.45, 364.99, 262.58, 400.0, 287.09, 396.5]], "area": 17726.869400000003, "iscrowd": 0, "image_id": 216150, "bbox": [210.06, 132.17, 119.92, 268.7], "category_id": 1, "id": 187348, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "purple", "dress"], "raw": "a woman in a purple dress", "sent_id": 90951, "sent": "a woman in a purple dress"}, {"tokens": ["a", "woman", "in", "a", "long", "purple", "sarong", "type", "dress"], "raw": "a woman in a long purple sarong type dress", "sent_id": 90952, "sent": "a woman in a long purple sarong type dress"}], "file_name": "COCO_train2014_000000216150_187348.jpg", "ann_id": 187348, "sent_ids": [90951, 90952], "ref_id": 39961}, {"segmentation": [[394.45, 241.22, 401.15, 295.79, 401.15, 307.28, 372.43, 298.66, 347.54, 346.53, 372.43, 380.04, 362.85, 393.44, 330.3, 387.7, 312.11, 383.87, 323.6, 362.81, 300.62, 336.0, 259.46, 341.74, 209.67, 344.62, 176.16, 336.96, 147.44, 350.36, 122.55, 321.64, 96.7, 339.83, 90.95, 318.77, 98.61, 293.87, 137.87, 268.98, 158.93, 249.83, 117.76, 201.01, 115.85, 174.2, 139.78, 147.39, 180.95, 130.16, 269.03, 119.63, 311.15, 127.29, 361.9, 155.05, 376.26, 191.43, 372.43, 208.67, 377.22, 221.11]], "area": 55315.621799999986, "iscrowd": 0, "image_id": 197289, "bbox": [90.95, 119.63, 310.2, 273.81], "category_id": 54, "id": 313700, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "with", "no", "bread", "on", "top"], "raw": "the sandwich with no bread on top.", "sent_id": 90955, "sent": "the sandwich with no bread on top"}, {"tokens": ["the", "burger", "that", "only", "has", "a", "tomato", "and", "cheese", "on", "top", "of", "it"], "raw": "The burger that only has a tomato and cheese on top of it.", "sent_id": 90956, "sent": "the burger that only has a tomato and cheese on top of it"}], "file_name": "COCO_train2014_000000197289_313700.jpg", "ann_id": 313700, "sent_ids": [90955, 90956], "ref_id": 39963}, {"segmentation": [[428.0, 420.11, 431.99, 329.32, 424.0, 322.34, 444.96, 313.36, 447.95, 345.29, 442.96, 381.2, 436.97, 421.11, 428.99, 420.11], [498.83, 302.39, 599.59, 279.44, 600.59, 290.41, 625.53, 292.41, 626.53, 285.43, 638.5, 290.41, 639.5, 414.12, 619.55, 421.11, 560.68, 420.11, 538.74, 406.14, 540.73, 391.18, 540.73, 334.31, 530.75, 332.32, 518.78, 326.33, 507.81, 313.36, 497.83, 302.39], [463.91, 358.26, 459.92, 323.34, 477.88, 332.32, 478.88, 366.24, 464.91, 360.25], [507.81, 347.28, 526.76, 362.25, 522.77, 395.17, 507.81, 388.19, 499.83, 372.22, 499.83, 354.27, 504.81, 346.28]], "area": 16860.81895, "iscrowd": 0, "image_id": 259120, "bbox": [424.0, 279.44, 215.5, 141.67], "category_id": 67, "id": 121412, "split": "val", "sentences": [{"tokens": ["a", "dinner", "table"], "raw": "A dinner table.", "sent_id": 90958, "sent": "a dinner table"}, {"tokens": ["a", "red", "stained", "mahogany", "table", "and", "a", "matching", "chair", "sit", "in", "the", "corner", "of", "the", "room"], "raw": "A red stained mahogany table and a matching chair sit in the corner of the room", "sent_id": 90959, "sent": "a red stained mahogany table and a matching chair sit in the corner of the room"}], "file_name": "COCO_train2014_000000259120_121412.jpg", "ann_id": 121412, "sent_ids": [90958, 90959], "ref_id": 39965}, {"segmentation": [[350.32, 216.94, 355.39, 213.56, 356.83, 209.46, 358.77, 206.8, 358.77, 201.01, 363.35, 200.05, 362.87, 196.91, 356.59, 190.39, 349.84, 180.25, 346.94, 169.64, 343.8, 160.95, 343.56, 154.67, 344.04, 152.02, 341.63, 140.67, 342.84, 119.19, 346.46, 117.26, 361.66, 106.88, 372.76, 104.95, 384.59, 106.16, 391.11, 109.78, 401.24, 122.09, 405.83, 133.67, 404.86, 150.09, 404.14, 159.98, 402.93, 191.6, 401.49, 204.87, 401.49, 208.73, 399.8, 235.28, 400.52, 244.46, 402.45, 246.39, 402.93, 239.39, 403.66, 223.46, 406.31, 184.6, 417.41, 185.56, 424.41, 201.01, 451.2, 213.32, 459.89, 221.04, 467.86, 227.56, 473.17, 238.18, 477.75, 250.25, 479.68, 257.49, 482.34, 278.0, 487.89, 301.42, 489.82, 304.79, 495.13, 320.48, 497.3, 327.24, 496.34, 337.14, 493.2, 350.65, 490.79, 357.89, 476.31, 366.34, 469.31, 364.89, 460.62, 360.06, 457.72, 370.2, 449.27, 378.41, 442.27, 379.13, 443.24, 387.1, 443.72, 402.06, 445.89, 423.3, 450.72, 430.78, 449.76, 442.37, 448.31, 450.57, 448.31, 468.67, 448.31, 479.54, 317.49, 479.54, 314.36, 458.54, 313.63, 451.78, 317.25, 424.51, 319.91, 398.2, 320.63, 388.79, 313.87, 401.34, 309.53, 405.2, 316.14, 388.56, 316.35, 367.9, 315.71, 362.15, 321.87, 348.22, 323.87, 334.76, 325.53, 332.44, 327.86, 328.78, 325.04, 325.13, 324.87, 322.81, 330.18, 317.83, 328.36, 311.52, 328.36, 306.04, 328.22, 296.73, 328.72, 291.42, 328.55, 283.62, 326.39, 270.34, 326.72, 262.7, 327.72, 244.11, 334.53, 233.15, 344.32, 224.02, 349.8, 217.22], [281.33, 392.93, 279.45, 396.5, 281.33, 400.45, 278.51, 404.4, 279.45, 408.72, 282.46, 411.92, 282.65, 418.88, 285.1, 424.9, 289.04, 422.08, 288.67, 418.13, 294.87, 421.14, 295.25, 414.93, 291.68, 412.3, 289.23, 407.97, 295.44, 410.04, 301.46, 412.3, 302.77, 408.54, 295.06, 405.15, 290.74, 402.52, 289.23, 398.57, 281.33, 393.3, 281.33, 393.3]], "area": 45064.47545000002, "iscrowd": 0, "image_id": 115505, "bbox": [278.51, 104.95, 218.79, 374.59], "category_id": 1, "id": 441503, "split": "val", "sentences": [{"tokens": ["man", "in", "blue", "shirt", "and", "pants", "holding", "umbrella", "and", "flowers"], "raw": "Man in blue shirt and pants holding umbrella and flowers", "sent_id": 91031, "sent": "man in blue shirt and pants holding umbrella and flowers"}, {"tokens": ["a", "man", "holding", "a", "striped", "umbrella"], "raw": "A man holding a striped umbrella.", "sent_id": 91032, "sent": "a man holding a striped umbrella"}], "file_name": "COCO_train2014_000000115505_441503.jpg", "ann_id": 441503, "sent_ids": [91031, 91032], "ref_id": 39992}, {"segmentation": [[456.16, 177.11, 471.53, 180.24, 477.48, 174.29, 484.7, 178.36, 493.48, 189.97, 494.11, 196.87, 502.89, 208.47, 504.77, 220.07, 505.71, 237.01, 511.04, 240.14, 511.04, 232.93, 512.92, 224.78, 514.18, 238.89, 526.09, 249.24, 535.82, 256.77, 540.21, 256.14, 538.01, 247.04, 526.72, 242.03, 520.76, 232.62, 522.64, 224.15, 524.84, 210.04, 534.25, 210.35, 536.76, 200.94, 530.17, 181.5, 530.17, 165.19, 531.74, 157.98, 527.35, 157.35, 522.33, 160.49, 519.51, 163.31, 508.84, 162.06, 492.22, 156.72, 479.05, 151.39, 471.84, 149.2, 467.76, 150.14, 461.49, 164.25, 457.73, 173.66], [553.69, 161.43, 544.6, 171.46, 538.32, 180.24, 543.03, 188.08, 543.66, 198.12, 543.66, 201.88, 545.22, 207.84, 544.28, 211.29, 556.2, 209.41, 566.24, 203.14, 567.49, 205.96, 568.12, 221.64, 565.29, 231.05, 553.69, 249.55, 547.42, 254.57, 546.79, 256.77, 557.45, 256.45, 559.34, 252.69, 560.59, 252.38, 561.85, 249.24, 573.76, 231.68, 576.9, 227.91, 577.84, 217.56, 580.98, 210.35, 591.32, 225.09, 595.4, 231.99, 596.97, 249.87, 592.27, 257.71, 602.3, 257.39, 604.81, 246.42, 601.05, 228.54, 600.42, 221.33, 595.09, 213.17, 593.52, 205.65, 597.28, 192.16, 599.48, 184.01, 597.6, 178.05, 599.48, 177.42, 601.36, 183.69, 600.73, 195.3, 600.73, 203.45, 605.12, 201.26, 613.28, 212.23, 618.3, 229.48, 635.86, 230.11, 629.27, 212.55, 618.61, 198.12, 609.51, 178.05, 605.44, 174.6, 592.27, 168.64, 570.63, 162.68, 558.4, 161.74, 556.51, 159.55], [498.5, 250.49, 492.85, 254.88, 504.77, 255.2, 505.4, 252.06]], "area": 7556.488899999997, "iscrowd": 0, "image_id": 171581, "bbox": [456.16, 149.2, 179.7, 108.51], "category_id": 19, "id": 368501, "split": "val", "sentences": [{"tokens": ["a", "white", "horse", "on", "the", "beach", "being", "ridden", "by", "a", "young", "woman"], "raw": "A white horse on the beach being ridden by a young woman.", "sent_id": 91056, "sent": "a white horse on the beach being ridden by a young woman"}, {"tokens": ["a", "woman", "riding", "a", "white", "horse"], "raw": "A woman riding a white horse.", "sent_id": 91057, "sent": "a woman riding a white horse"}], "file_name": "COCO_train2014_000000171581_368501.jpg", "ann_id": 368501, "sent_ids": [91056, 91057], "ref_id": 40000}, {"segmentation": [[45.1, 261.04, 67.65, 214.87, 95.57, 195.54, 137.45, 148.29, 175.03, 104.26, 271.68, 109.63, 297.45, 115.0, 289.93, 131.11, 303.89, 154.73, 295.3, 163.33, 301.74, 207.35, 410.2, 208.43, 428.46, 210.57, 462.82, 200.91, 471.41, 182.65, 477.85, 164.4, 463.89, 141.85, 469.26, 126.82, 546.58, 135.41, 579.87, 282.52, 575.57, 426.41, 473.56, 413.53, 129.93, 371.65, 51.54, 358.76, 48.32, 336.21, 48.32, 311.51, 44.03, 296.48]], "area": 120970.55344999999, "iscrowd": 0, "image_id": 213241, "bbox": [44.03, 104.26, 535.84, 322.15], "category_id": 61, "id": 1085897, "split": "val", "sentences": [{"tokens": ["rectangular", "decorated", "cake"], "raw": "Rectangular decorated cake.", "sent_id": 91058, "sent": "rectangular decorated cake"}, {"tokens": ["white", "and", "green", "color", "cake"], "raw": "WHITE AND GREEN COLOR CAKE", "sent_id": 91059, "sent": "white and green color cake"}], "file_name": "COCO_train2014_000000213241_1085897.jpg", "ann_id": 1085897, "sent_ids": [91058, 91059], "ref_id": 40001}, {"segmentation": [[318.53, 291.18, 320.29, 272.65, 320.29, 264.71, 320.29, 254.12, 322.06, 242.65, 333.53, 237.35, 340.59, 233.82, 345.88, 231.18, 350.29, 230.29, 357.35, 231.18, 362.65, 240.0, 364.41, 251.47, 364.41, 262.94, 367.94, 272.65, 373.24, 277.06, 384.71, 282.35, 397.06, 288.53, 400.59, 291.18, 406.76, 300.0, 410.29, 307.94, 412.94, 315.88, 409.41, 325.59, 403.24, 332.65, 395.29, 335.29, 392.65, 336.18, 377.65, 338.82, 361.76, 338.82, 355.59, 337.94, 346.76, 329.12, 340.59, 320.29, 335.29, 315.88, 328.24, 311.47, 323.82, 305.29, 317.65, 298.24, 316.76, 293.82]], "area": 6263.431350000001, "iscrowd": 0, "image_id": 174892, "bbox": [316.76, 230.29, 96.18, 108.53], "category_id": 55, "id": 1052835, "split": "val", "sentences": [{"tokens": ["the", "slice", "of", "orange", "that", "is", "touching", "the", "bottom", "right", "corner", "of", "its", "container"], "raw": "The slice of orange that is touching the bottom right corner of its container.", "sent_id": 91117, "sent": "the slice of orange that is touching the bottom right corner of its container"}, {"tokens": ["the", "orange", "slice", "closest", "to", "the", "camera"], "raw": "The orange slice closest to the camera.", "sent_id": 91118, "sent": "the orange slice closest to the camera"}], "file_name": "COCO_train2014_000000174892_1052835.jpg", "ann_id": 1052835, "sent_ids": [91117, 91118], "ref_id": 40024}, {"segmentation": [[584.36, 434.07, 580.4, 401.44, 577.44, 366.83, 579.42, 350.02, 576.45, 337.17, 555.69, 313.44, 532.94, 302.56, 514.16, 288.72, 506.25, 277.84, 503.28, 264.99, 511.19, 248.18, 511.19, 221.48, 504.27, 203.69, 476.58, 197.75, 449.89, 204.67, 434.07, 214.56, 429.12, 227.42, 435.06, 244.22, 440.99, 256.09, 433.08, 267.96, 438.02, 278.83, 440.99, 285.75, 450.88, 293.66, 459.78, 297.62, 459.78, 302.56, 441.98, 318.38, 438.02, 320.36, 431.1, 319.37, 426.16, 321.35, 422.2, 320.36, 416.27, 329.26, 439.01, 350.02, 471.64, 428.13, 471.64, 428.13, 475.6, 435.06]], "area": 23863.24945, "iscrowd": 0, "image_id": 242090, "bbox": [416.27, 197.75, 168.09, 237.31], "category_id": 1, "id": 548623, "split": "val", "sentences": [{"tokens": ["boy", "on", "the", "right", "closest", "to", "the", "pepsi", "cooler"], "raw": "Boy on the right closest to the PEPSI cooler", "sent_id": 91191, "sent": "boy on the right closest to the pepsi cooler"}, {"tokens": ["a", "man", "in", "a", "solid", "white", "shirt", "with", "his", "back", "turned"], "raw": "A man in a solid white shirt with his back turned.", "sent_id": 91192, "sent": "a man in a solid white shirt with his back turned"}], "file_name": "COCO_train2014_000000242090_548623.jpg", "ann_id": 548623, "sent_ids": [91191, 91192], "ref_id": 40053}, {"segmentation": [[105.05, 419.92, 79.79, 380.03, 65.16, 354.77, 57.18, 333.49, 58.51, 328.17, 83.78, 310.88, 125.0, 297.58, 127.66, 296.25, 118.35, 267.0, 110.37, 244.39, 106.38, 239.07, 73.14, 244.39, 15.96, 259.02, 6.65, 270.99, 5.32, 281.63, 17.29, 308.22, 34.57, 358.75, 46.54, 422.58, 50.53, 427.9, 105.05, 425.24]], "area": 11653.24085, "iscrowd": 0, "image_id": 238187, "bbox": [5.32, 239.07, 122.34, 188.83], "category_id": 52, "id": 1043283, "split": "val", "sentences": [{"tokens": ["a", "cut", "piece", "of", "bananaplaced", "on", "the", "left", "corner", "of", "the", "apple"], "raw": "A cut piece of Bananaplaced on the left corner of the apple", "sent_id": 91252, "sent": "a cut piece of bananaplaced on the left corner of the apple"}, {"tokens": ["a", "small", "banana", "piece", "on", "table", "towards", "left", "side", "of", "the", "image"], "raw": "A small banana piece on table towards left side of the image.", "sent_id": 91253, "sent": "a small banana piece on table towards left side of the image"}], "file_name": "COCO_train2014_000000238187_1043283.jpg", "ann_id": 1043283, "sent_ids": [91252, 91253], "ref_id": 40076}, {"segmentation": [[325.68, 317.24, 247.14, 339.16, 234.35, 347.38, 230.7, 351.03, 206.95, 340.07, 186.85, 376.61, 154.89, 423.19, 121.09, 422.27, 120.18, 400.35, 132.97, 381.17, 147.58, 374.78, 161.28, 361.08, 161.28, 323.63, 157.63, 272.49, 162.19, 224.08, 162.19, 220.42, 132.97, 214.94, 132.97, 214.94, 126.57, 228.64, 120.18, 228.64, 103.74, 225.9, 93.69, 215.86, 68.12, 207.64, 54.42, 194.85, 48.94, 174.76, 58.99, 164.71, 63.55, 161.97, 79.08, 170.19, 107.39, 177.5, 195.08, 161.06, 256.27, 149.18, 273.62, 120.87, 291.89, 122.7, 291.89, 110.82, 311.98, 103.52, 328.42, 87.08, 332.99, 71.55, 346.69, 74.29, 354.91, 65.16, 380.48, 73.38, 401.49, 97.12, 403.32, 123.61, 404.23, 138.22, 407.88, 144.62, 398.75, 161.97, 388.7, 171.1, 361.3, 200.33, 332.99, 262.44, 331.15, 288.0, 343.01, 304.18, 332.22, 316.04]], "area": 51286.1496, "iscrowd": 0, "image_id": 201897, "bbox": [48.94, 65.16, 358.94, 358.03], "category_id": 1, "id": 207563, "split": "val", "sentences": [{"tokens": ["the", "woman", "with", "the", "high", "white", "socks"], "raw": "The woman with the high white socks.", "sent_id": 91259, "sent": "the woman with the high white socks"}, {"tokens": ["a", "girl", "wearing", "white", "knee", "socks"], "raw": "A girl wearing white knee socks", "sent_id": 91260, "sent": "a girl wearing white knee socks"}], "file_name": "COCO_train2014_000000201897_207563.jpg", "ann_id": 207563, "sent_ids": [91259, 91260], "ref_id": 40078}, {"segmentation": [[57.41, 242.29, 43.79, 203.36, 39.89, 179.04, 31.14, 146.93, 22.38, 136.22, 25.3, 133.31, 48.65, 139.14, 57.41, 133.31, 91.47, 113.84, 127.47, 116.76, 153.74, 116.76, 161.52, 128.44, 173.2, 138.17, 191.69, 139.14, 220.88, 125.52, 240.34, 118.71, 259.8, 95.36, 264.67, 84.65, 255.91, 89.52, 241.31, 95.36, 244.23, 86.6, 252.99, 71.03, 261.75, 64.22, 270.5, 65.19, 274.4, 65.19, 277.31, 65.19, 291.91, 52.54, 302.61, 38.92, 303.59, 30.16, 311.37, 14.6, 349.32, 9.73, 327.91, 39.89, 348.35, 62.27, 363.91, 65.19, 368.78, 75.9, 382.4, 72.98, 387.27, 88.55, 385.32, 92.44, 397.97, 116.76, 407.7, 116.76, 364.89, 139.14, 346.4, 141.09, 344.45, 117.74, 332.78, 133.31, 336.67, 171.25, 320.13, 196.55, 284.13, 204.34, 254.93, 213.09, 223.8, 191.69, 171.25, 198.5, 160.55, 205.31, 142.06, 180.98, 124.55, 190.71, 137.2, 201.42, 137.2, 213.09, 124.55, 219.91, 103.14, 219.91, 100.22, 226.72, 96.33, 235.47, 82.71, 254.93, 82.71, 257.85, 81.73, 257.85, 72.0, 257.85]], "area": 35766.00935000001, "iscrowd": 0, "image_id": 208243, "bbox": [22.38, 9.73, 385.32, 248.12], "category_id": 4, "id": 151982, "split": "val", "sentences": [{"tokens": ["a", "blue", "motorcycle"], "raw": "A blue motorcycle.", "sent_id": 91313, "sent": "a blue motorcycle"}, {"tokens": ["a", "black", "motorcycle", "between", "the", "car", "and", "the", "silver", "motorcycle"], "raw": "A black motorcycle between the car and the silver motorcycle.", "sent_id": 91314, "sent": "a black motorcycle between the car and the silver motorcycle"}], "file_name": "COCO_train2014_000000208243_151982.jpg", "ann_id": 151982, "sent_ids": [91313, 91314], "ref_id": 40098}, {"segmentation": [[226.89, 305.34, 220.0, 262.94, 229.01, 200.92, 252.33, 168.58, 251.27, 163.28, 228.48, 154.8, 185.01, 169.11, 177.06, 196.68, 170.17, 231.66, 161.69, 259.23, 159.57, 280.43, 182.89, 307.99, 218.94, 309.05]], "area": 8442.00715, "iscrowd": 0, "image_id": 339579, "bbox": [159.57, 154.8, 92.76, 154.25], "category_id": 54, "id": 313886, "split": "val", "sentences": [{"tokens": ["the", "piece", "of", "sandwich", "that", "is", "to", "the", "left", "of", "two", "other", "sandwich", "pieces"], "raw": "The piece of sandwich that is to the left of two other sandwich pieces.", "sent_id": 91322, "sent": "the piece of sandwich that is to the left of two other sandwich pieces"}, {"tokens": ["the", "left", "most", "piece", "of", "sanwhich"], "raw": "the left most piece of sanwhich", "sent_id": 91323, "sent": "the left most piece of sanwhich"}], "file_name": "COCO_train2014_000000339579_313886.jpg", "ann_id": 313886, "sent_ids": [91322, 91323], "ref_id": 40101}, {"segmentation": [[153.14, 525.51, 145.91, 422.93, 138.69, 363.7, 134.36, 313.14, 121.35, 272.69, 115.58, 229.35, 137.25, 213.45, 193.59, 193.23, 166.14, 171.56, 222.48, 157.11, 251.38, 162.89, 267.27, 193.23, 254.27, 233.68, 236.93, 240.9, 235.49, 285.69, 228.26, 336.25, 222.48, 373.81, 216.7, 431.6, 221.04, 486.5, 221.04, 515.4, 221.04, 532.73, 192.14, 537.07, 163.25, 560.18, 144.47, 537.07]], "area": 33943.42715, "iscrowd": 0, "image_id": 101832, "bbox": [115.58, 157.11, 151.69, 403.07], "category_id": 1, "id": 496306, "split": "val", "sentences": [{"tokens": ["a", "girl", "on", "a", "skateboard"], "raw": "A girl on a skateboard.", "sent_id": 91355, "sent": "a girl on a skateboard"}, {"tokens": ["a", "girl", "wearing", "jeans", "and", "a", "paisley", "shirt"], "raw": "A girl wearing jeans and a paisley shirt.", "sent_id": 91356, "sent": "a girl wearing jeans and a paisley shirt"}], "file_name": "COCO_train2014_000000101832_496306.jpg", "ann_id": 496306, "sent_ids": [91355, 91356], "ref_id": 40114}, {"segmentation": [[379.87, 3.9, 378.49, 52.07, 406.02, 94.74, 392.26, 309.45, 385.38, 323.21, 342.71, 257.15, 322.06, 207.6, 339.96, 87.86, 344.09, 75.47, 339.96, 74.09, 308.3, 75.47, 333.08, 49.32, 339.96, 2.52]], "area": 17997.62555, "iscrowd": 0, "image_id": 56032, "bbox": [308.3, 2.52, 97.72, 320.69], "category_id": 44, "id": 90961, "split": "val", "sentences": [{"tokens": ["a", "bottle", "of", "wine", "with", "a", "tan", "label"], "raw": "A bottle of wine with a tan label.", "sent_id": 91359, "sent": "a bottle of wine with a tan label"}], "file_name": "COCO_train2014_000000056032_90961.jpg", "ann_id": 90961, "sent_ids": [91359], "ref_id": 40116}, {"segmentation": [[340.83, 59.55, 338.92, 75.83, 469.13, 80.61, 481.57, 94.97, 482.53, 93.06, 488.27, 99.76, 487.32, 103.59, 493.06, 109.33, 501.68, 109.33, 510.29, 116.99, 507.42, 122.74, 511.25, 120.82, 518.91, 121.78, 524.65, 136.14, 533.27, 146.67, 532.31, 172.52, 528.48, 177.31, 514.12, 199.33, 515.08, 253.9, 515.08, 259.65, 514.12, 277.84, 507.42, 322.83, 513.17, 328.58, 505.51, 355.39, 473.91, 356.34, 468.17, 375.49, 462.42, 381.24, 446.15, 384.11, 428.91, 383.15, 421.26, 367.83, 419.34, 359.22, 333.17, 364.0, 296.79, 371.66, 289.13, 367.83, 287.22, 354.43, 285.3, 354.43, 286.26, 370.7, 282.43, 383.15, 274.77, 389.85, 255.63, 386.98, 245.09, 386.02, 242.22, 383.15, 237.43, 367.83, 234.56, 358.26, 229.78, 352.51, 201.05, 337.2, 185.74, 347.73, 179.99, 350.6, 152.23, 345.81, 141.7, 342.94, 134.99, 331.45, 134.99, 329.54, 131.16, 306.56, 128.29, 313.26, 121.59, 311.35, 122.55, 301.77, 124.46, 284.54, 116.8, 304.64, 107.23, 314.22, 91.91, 320.92, 59.36, 314.22, 45.96, 296.99, 42.13, 283.58, 34.47, 285.5, 24.89, 279.75, 28.72, 264.43, 10.53, 268.26, 2.87, 271.14, 1.91, 237.63, 13.4, 235.71, 23.93, 233.8, 36.38, 225.18, 55.53, 221.35, 69.89, 218.48, 109.14, 223.27, 125.42, 237.63, 132.12, 244.33, 148.4, 247.2, 161.8, 245.29, 163.72, 144.76, 164.67, 46.15, 166.59, 42.32, 168.5, 49.02, 231.69, 39.44, 234.56, 27.0, 240.31, 30.83, 238.39, 39.44, 272.86, 38.49, 272.86, 25.08, 288.18, 22.21, 285.3, 38.49, 337.96, 42.32]], "area": 119325.92189999999, "iscrowd": 0, "image_id": 293966, "bbox": [1.91, 22.21, 531.36, 367.64], "category_id": 8, "id": 394449, "split": "val", "sentences": [{"tokens": ["vintage", "red", "erf", "truck"], "raw": "Vintage red ERF Truck", "sent_id": 91425, "sent": "vintage red erf truck"}, {"tokens": ["a", "red", "truck", "labeled", "dent", "'", "s", "transport"], "raw": "A red truck labeled Dent's Transport.", "sent_id": 91426, "sent": "a red truck labeled dent ' s transport"}], "file_name": "COCO_train2014_000000293966_394449.jpg", "ann_id": 394449, "sent_ids": [91425, 91426], "ref_id": 40147}, {"segmentation": [[336.63, 48.54, 340.19, 43.79, 348.51, 42.6, 360.39, 63.19, 358.41, 73.89, 359.99, 82.2, 366.33, 92.5, 361.18, 106.76, 360.78, 109.93, 359.6, 110.32, 361.97, 115.72, 377.81, 97.51, 382.96, 93.55, 386.53, 94.74, 392.07, 104.24, 365.93, 124.44, 365.54, 125.63, 368.31, 136.71, 370.29, 160.08, 369.5, 174.59, 366.72, 175.78, 366.33, 176.18, 370.29, 194.39, 373.06, 196.37, 380.59, 214.05, 383.36, 236.63, 381.77, 241.51, 354.45, 241.9, 352.86, 240.32, 352.86, 233.98, 359.99, 228.04, 365.54, 224.48, 358.41, 205.87, 349.3, 208.24, 346.53, 207.85, 340.59, 207.85, 339.79, 223.69, 336.63, 233.59, 334.65, 238.74, 328.71, 238.34, 319.6, 232.4, 313.66, 230.82, 308.51, 227.65, 312.07, 220.12, 316.03, 219.33, 322.76, 219.33, 325.93, 218.93, 329.5, 213.79, 331.87, 210.22, 333.46, 189.63, 339.79, 181.31, 338.61, 155.84, 337.81, 150.69, 329.5, 143.96, 322.37, 136.04, 320.78, 131.68, 330.29, 130.1, 338.61, 125.09, 337.81, 118.36, 337.81, 112.02, 335.44, 106.47, 331.08, 104.49, 327.12, 102.51, 326.73, 97.76, 328.71, 96.18, 335.04, 83.25, 335.04, 77.71, 339.0, 71.76, 339.0, 65.43, 337.42, 59.49, 335.04, 46.56]], "area": 6660.880649999998, "iscrowd": 0, "image_id": 337621, "bbox": [308.51, 42.6, 83.56, 199.3], "category_id": 1, "id": 497898, "split": "val", "sentences": [{"tokens": ["child", "in", "orange"], "raw": "child in orange", "sent_id": 91530, "sent": "child in orange"}, {"tokens": ["a", "child", "wearing", "a", "white", "and", "red", "striped", "hat", "and", "orange", "coat"], "raw": "a child wearing a white and red striped hat and orange coat", "sent_id": 91531, "sent": "a child wearing a white and red striped hat and orange coat"}], "file_name": "COCO_train2014_000000337621_497898.jpg", "ann_id": 497898, "sent_ids": [91530, 91531], "ref_id": 40190}, {"segmentation": [[123.21, 439.92, 125.04, 398.82, 98.55, 299.27, 110.42, 297.44, 110.42, 275.52, 149.7, 260.0, 190.8, 274.61, 217.28, 315.71, 273.0, 312.06, 279.39, 332.15, 292.18, 333.98, 304.97, 395.17, 273.91, 423.48, 258.38, 445.4, 193.54, 438.1, 145.13, 430.79]], "area": 25824.879, "iscrowd": 0, "image_id": 436025, "bbox": [98.55, 260.0, 206.42, 185.4], "category_id": 62, "id": 382089, "split": "val", "sentences": [{"tokens": ["the", "chair", "sitting", "beside", "the", "lamp"], "raw": "The chair sitting beside the lamp.", "sent_id": 91567, "sent": "the chair sitting beside the lamp"}, {"tokens": ["a", "plaided", "chair", "with", "a", "white", "object", "on", "the", "back", "of", "it"], "raw": "A plaided chair with a white object on the back of it", "sent_id": 91568, "sent": "a plaided chair with a white object on the back of it"}], "file_name": "COCO_train2014_000000436025_382089.jpg", "ann_id": 382089, "sent_ids": [91567, 91568], "ref_id": 40206}, {"segmentation": [[31.62, 329.73, 29.36, 316.18, 36.89, 282.3, 34.63, 259.72, 36.89, 241.65, 35.38, 203.26, 39.15, 181.43, 47.43, 170.13, 62.48, 163.36, 62.48, 153.57, 53.45, 143.03, 49.69, 127.22, 56.46, 121.2, 68.51, 124.97, 70.01, 114.43, 77.54, 103.13, 89.58, 99.37, 106.9, 102.38, 119.7, 112.17, 120.45, 124.97, 118.19, 133.25, 121.2, 138.52, 118.19, 148.3, 123.46, 154.33, 128.73, 164.87, 127.98, 180.67, 138.52, 188.96, 140.02, 210.79, 137.76, 236.38, 131.74, 259.72, 117.44, 254.45, 121.96, 271.01, 132.49, 290.58, 140.02, 309.4, 145.29, 329.73, 106.15, 331.24, 62.48, 330.48]], "area": 19980.705000000005, "iscrowd": 0, "image_id": 454923, "bbox": [29.36, 99.37, 115.93, 231.87], "category_id": 1, "id": 472226, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "her", "hair", "in", "a", "bun", "talks", "on", "her", "cellphone"], "raw": "A woman with her hair in a bun talks on her cellphone.", "sent_id": 91597, "sent": "a woman with her hair in a bun talks on her cellphone"}, {"tokens": ["a", "businesswoman", "on", "a", "phone"], "raw": "a businesswoman on a phone", "sent_id": 91598, "sent": "a businesswoman on a phone"}], "file_name": "COCO_train2014_000000454923_472226.jpg", "ann_id": 472226, "sent_ids": [91597, 91598], "ref_id": 40215}, {"segmentation": [[116.33, 83.19, 147.61, 76.77, 178.1, 73.56, 212.6, 71.15, 241.48, 73.56, 271.16, 75.17, 294.42, 77.57, 296.83, 91.21, 300.04, 108.86, 308.06, 116.88, 304.85, 120.89, 303.25, 134.53, 277.58, 131.32, 192.54, 114.48, 154.03, 102.44, 126.76, 89.61], [308.87, 80.78, 331.33, 83.99, 348.98, 86.4, 370.64, 90.41, 401.93, 97.63, 431.61, 105.65, 451.67, 111.27, 473.33, 122.5, 481.35, 129.72, 484.56, 134.53, 481.35, 142.55, 460.49, 145.76, 414.76, 146.57, 372.24, 142.55, 339.35, 138.54, 312.88, 134.53, 314.48, 128.92, 317.69, 130.52, 313.68, 118.49, 309.67, 94.42, 306.46, 88.8]], "area": 14890.9519, "iscrowd": 0, "image_id": 88425, "bbox": [116.33, 71.15, 368.23, 75.42], "category_id": 42, "id": 648591, "split": "val", "sentences": [{"tokens": ["a", "white", "surfboard", "being", "carried", "by", "a", "blond", "man"], "raw": "A white surfboard being carried by a blond man.", "sent_id": 91613, "sent": "a white surfboard being carried by a blond man"}, {"tokens": ["white", "surf", "board", "being", "carried", "into", "the", "water", "by", "a", "man"], "raw": "White surf board being carried into the water by a man.", "sent_id": 91614, "sent": "white surf board being carried into the water by a man"}], "file_name": "COCO_train2014_000000088425_648591.jpg", "ann_id": 648591, "sent_ids": [91613, 91614], "ref_id": 40220}, {"segmentation": [[3.22, 178.97, 2.15, 234.81, 31.14, 232.66, 52.62, 228.37, 63.36, 245.55, 78.39, 254.14, 84.83, 264.88, 108.46, 269.17, 112.75, 282.06, 120.27, 280.98, 119.19, 269.17, 223.36, 275.62, 229.8, 287.43, 238.39, 284.21, 235.17, 272.39, 252.35, 272.39, 263.09, 287.43, 264.16, 298.17, 270.6, 291.72, 273.83, 291.72, 267.38, 227.29, 277.05, 229.44, 281.34, 225.15, 279.19, 215.48, 272.75, 211.19, 265.23, 211.19, 260.94, 211.19, 265.23, 216.55, 262.01, 221.92, 256.64, 217.63, 233.02, 221.92, 227.65, 175.75, 220.13, 174.68, 215.84, 174.68, 211.54, 181.12, 129.93, 180.04, 32.21, 175.75, 7.52, 173.6]], "area": 21294.6034, "iscrowd": 0, "image_id": 366148, "bbox": [2.15, 173.6, 279.19, 124.57], "category_id": 15, "id": 578540, "split": "val", "sentences": [{"tokens": ["the", "wooden", "bench", "on", "the", "left", "-", "hand", "side"], "raw": "The wooden bench on the left-hand side", "sent_id": 91621, "sent": "the wooden bench on the left - hand side"}, {"tokens": ["a", "wooden", "bench", "facing", "the", "ocean"], "raw": "A wooden bench facing the ocean.", "sent_id": 91622, "sent": "a wooden bench facing the ocean"}], "file_name": "COCO_train2014_000000366148_578540.jpg", "ann_id": 578540, "sent_ids": [91621, 91622], "ref_id": 40224}, {"segmentation": [[211.42, 350.56, 210.34, 295.55, 212.49, 267.51, 168.27, 264.27, 155.33, 341.93, 139.15, 320.36, 155.33, 216.81, 185.53, 194.16, 308.49, 189.84, 361.35, 242.7, 354.88, 288.0, 332.22, 313.89, 326.83, 360.27, 293.39, 343.01, 281.53, 288.0, 237.3, 295.55, 243.78, 357.03]], "area": 23283.076850000005, "iscrowd": 0, "image_id": 221927, "bbox": [139.15, 189.84, 222.2, 170.43], "category_id": 22, "id": 582088, "split": "val", "sentences": [{"tokens": ["an", "elephant", "in", "front", "of", "a", "smaller", "elephant"], "raw": "An elephant in front of a smaller elephant", "sent_id": 91685, "sent": "an elephant in front of a smaller elephant"}, {"tokens": ["elephant", "that", "is", "front", "and", "center"], "raw": "Elephant that is front and center.", "sent_id": 91686, "sent": "elephant that is front and center"}], "file_name": "COCO_train2014_000000221927_582088.jpg", "ann_id": 582088, "sent_ids": [91685, 91686], "ref_id": 40247}, {"segmentation": [[211.36, 388.81, 211.36, 388.81, 237.22, 435.56, 232.25, 455.45, 213.35, 481.0, 148.7, 479.33, 34.32, 478.33, 13.43, 474.35, 9.45, 453.46, 8.46, 424.62, 14.43, 400.75, 27.36, 374.89, 41.28, 356.99, 42.28, 356.99, 63.16, 341.07, 85.05, 334.11, 112.9, 333.11, 103.94, 361.96, 104.94, 361.96, 110.91, 385.83, 110.91, 386.82, 123.84, 403.73, 123.84, 403.73, 137.76, 405.72, 150.69, 405.72, 186.5, 405.72, 187.49, 404.73, 204.4, 391.8, 204.4, 391.8]], "area": 21697.711349999998, "iscrowd": 0, "image_id": 562100, "bbox": [8.46, 333.11, 228.76, 147.89], "category_id": 53, "id": 1549327, "split": "val", "sentences": [{"tokens": ["green", "apple", "next", "to", "a", "yellow", "banana"], "raw": "green apple next to a yellow banana.", "sent_id": 91719, "sent": "green apple next to a yellow banana"}, {"tokens": ["a", "yellow", "green", "apple", "under", "a", "bunch", "of", "bananas"], "raw": "a yellow green apple under a bunch of bananas", "sent_id": 91720, "sent": "a yellow green apple under a bunch of bananas"}], "file_name": "COCO_train2014_000000562100_1549327.jpg", "ann_id": 1549327, "sent_ids": [91719, 91720], "ref_id": 40263}, {"segmentation": [[216.5, 355.34, 210.17, 326.21, 216.5, 304.68, 231.7, 290.75, 244.37, 290.75, 259.57, 297.08, 268.44, 308.48, 276.04, 326.21, 276.04, 333.81, 279.84, 354.08, 288.7, 359.14, 301.37, 419.94, 297.57, 437.68, 320.37, 466.81, 334.3, 485.81, 316.57, 489.61, 296.3, 492.14, 281.1, 492.14, 265.9, 469.34, 251.97, 470.61, 184.84, 484.54, 159.51, 483.28, 158.24, 465.54, 191.17, 454.14, 201.3, 431.34, 205.1, 385.74, 207.64, 361.68]], "area": 17213.19775, "iscrowd": 0, "image_id": 166985, "bbox": [158.24, 290.75, 176.06, 201.39], "category_id": 1, "id": 1731429, "split": "val", "sentences": [{"tokens": ["girl", "sitting", "on", "board"], "raw": "girl sitting on board", "sent_id": 91727, "sent": "girl sitting on board"}, {"tokens": ["woman", "sitting", "on", "surf", "board", "in", "water"], "raw": "woman sitting on surf board in water", "sent_id": 91728, "sent": "woman sitting on surf board in water"}], "file_name": "COCO_train2014_000000166985_1731429.jpg", "ann_id": 1731429, "sent_ids": [91727, 91728], "ref_id": 40266}, {"segmentation": [[299.69, 115.79, 300.93, 74.76, 302.18, 58.59, 320.83, 43.67, 324.56, 22.53, 324.56, 1.39, 365.6, 1.39, 361.87, 28.75, 373.06, 46.16, 384.25, 74.76, 391.71, 100.87, 387.98, 184.19, 384.25, 165.53, 365.6, 159.32, 336.99, 159.32, 313.37, 165.53]], "area": 11501.81795, "iscrowd": 0, "image_id": 204529, "bbox": [299.69, 1.39, 92.02, 182.8], "category_id": 44, "id": 2093348, "split": "val", "sentences": [{"tokens": ["a", "white", "strewn", "wine", "bottle"], "raw": "A white strewn wine bottle.", "sent_id": 91748, "sent": "a white strewn wine bottle"}], "file_name": "COCO_train2014_000000204529_2093348.jpg", "ann_id": 2093348, "sent_ids": [91748], "ref_id": 40274}, {"segmentation": [[409.53, 131.47, 398.01, 119.24, 392.25, 117.8, 388.65, 110.6, 384.34, 101.96, 376.42, 84.69, 409.53, 45.82, 427.52, 48.7, 453.43, 65.26, 463.51, 100.52, 494.46, 153.78, 496.61, 172.5, 490.86, 202.72, 478.62, 237.27, 477.18, 259.58, 476.46, 296.29, 462.79, 316.44, 408.81, 300.61, 395.13, 305.65, 387.22, 309.96, 386.5, 307.09, 387.22, 294.13, 387.22, 288.37, 390.81, 270.38, 354.11, 267.5, 343.31, 258.14, 342.59, 243.75, 362.02, 240.15, 379.3, 238.71, 389.37, 202.72, 389.37, 189.05, 401.61, 165.3, 389.37, 168.9, 381.46, 178.25, 364.18, 185.45, 365.62, 196.25, 360.59, 196.25, 353.39, 174.65, 369.22, 164.58, 380.02, 150.9, 401.61, 135.07]], "area": 24618.82289999999, "iscrowd": 0, "image_id": 350280, "bbox": [342.59, 45.82, 154.02, 270.62], "category_id": 1, "id": 475589, "split": "val", "sentences": [{"tokens": ["person", "far", "right", "bottom", "corner"], "raw": "person far right bottom corner", "sent_id": 91773, "sent": "person far right bottom corner"}, {"tokens": ["a", "woman", "in", "white", "pours", "a", "glass", "of", "wine"], "raw": "A woman in white pours a glass of wine.", "sent_id": 91774, "sent": "a woman in white pours a glass of wine"}], "file_name": "COCO_train2014_000000350280_475589.jpg", "ann_id": 475589, "sent_ids": [91773, 91774], "ref_id": 40285}, {"segmentation": [[238.26, 310.77, 243.36, 303.53, 245.14, 300.54, 246.58, 295.96, 245.83, 292.23, 248.07, 286.25, 243.59, 280.27, 244.34, 278.78, 243.88, 274.44, 243.44, 269.97, 243.74, 263.54, 248.52, 225.13, 250.31, 219.75, 246.58, 219.0, 250.31, 207.05, 247.32, 198.08, 243.59, 200.32, 239.85, 199.58, 237.61, 187.62, 239.11, 184.63, 245.83, 179.4, 251.06, 159.97, 257.47, 156.91, 259.49, 151.46, 256.3, 145.03, 257.73, 136.37, 264.65, 129.1, 274.91, 130.26, 281.2, 138.01, 281.24, 144.74, 281.48, 152.01, 288.12, 153.92, 296.6, 162.48, 303.36, 200.32, 293.65, 218.26, 293.65, 224.23, 291.41, 246.65, 287.55, 277.92, 289.47, 284.46, 288.37, 300.75, 283.88, 318.48, 277.9, 323.43, 269.9, 325.56, 261.97, 327.5, 259.13, 322.12, 260.77, 315.39, 266.0, 310.16, 261.29, 310.49, 254.8, 311.66, 246.72, 311.79, 242.23, 313.01]], "area": 8343.4027, "iscrowd": 0, "image_id": 42308, "bbox": [237.61, 129.1, 65.75, 198.4], "category_id": 1, "id": 452182, "split": "val", "sentences": [{"tokens": ["the", "person", "holding", "the", "snowboard"], "raw": "The person holding the snowboard", "sent_id": 91804, "sent": "the person holding the snowboard"}, {"tokens": ["a", "man", "standing", "with", "a", "snowboard"], "raw": "A man standing with a snowboard.", "sent_id": 91805, "sent": "a man standing with a snowboard"}], "file_name": "COCO_train2014_000000042308_452182.jpg", "ann_id": 452182, "sent_ids": [91804, 91805], "ref_id": 40299}, {"segmentation": [[535.2, 163.57, 534.6, 172.59, 529.19, 176.8, 526.78, 186.42, 523.18, 197.84, 517.76, 215.28, 515.96, 223.1, 509.34, 235.73, 506.94, 239.94, 493.71, 240.54, 493.71, 248.96, 513.55, 253.77, 620.59, 249.56, 616.39, 217.69, 598.95, 167.78, 584.51, 153.34, 568.88, 138.31, 562.86, 112.45, 562.26, 89.0, 550.24, 79.38, 528.59, 77.57, 523.78, 78.18, 502.13, 90.8, 496.72, 96.22, 493.11, 107.04, 476.87, 110.05, 497.32, 121.47, 499.12, 125.68, 502.73, 134.1, 503.33, 139.51, 511.15, 149.74, 518.36, 160.56, 530.99, 162.97]], "area": 13783.017850000004, "iscrowd": 0, "image_id": 402264, "bbox": [476.87, 77.57, 143.72, 176.2], "category_id": 1, "id": 524026, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "orange", "hat", "is", "on", "the", "right", "of", "the", "other", "two", "men"], "raw": "The man in the orange hat is on the right of the other two men.", "sent_id": 91857, "sent": "the man in the orange hat is on the right of the other two men"}, {"tokens": ["man", "in", "a", "black", "tshirt", "and", "red", "cap", "walking", "in", "the", "background"], "raw": "Man in a black tshirt and red cap walking in the background.", "sent_id": 91858, "sent": "man in a black tshirt and red cap walking in the background"}], "file_name": "COCO_train2014_000000402264_524026.jpg", "ann_id": 524026, "sent_ids": [91857, 91858], "ref_id": 40322}, {"segmentation": [[640.0, 99.2, 550.87, 91.14, 485.41, 90.13, 438.08, 117.32, 383.7, 205.95, 381.68, 221.05, 374.63, 235.15, 363.55, 242.2, 349.46, 250.26, 337.37, 249.25, 327.3, 250.26, 323.27, 258.31, 355.5, 303.63, 390.75, 363.05, 388.73, 294.57, 381.68, 280.47, 379.67, 267.38, 390.75, 247.24, 424.99, 213.0, 438.08, 209.98, 453.18, 229.11, 465.27, 243.21, 471.31, 249.25, 479.37, 260.33, 479.37, 275.44, 471.31, 298.6, 468.29, 322.77, 463.25, 361.04, 468.29, 385.21, 475.34, 412.4, 472.32, 421.46, 640.0, 421.46]], "area": 67075.40440000001, "iscrowd": 0, "image_id": 121619, "bbox": [323.27, 90.13, 316.73, 331.33], "category_id": 3, "id": 1775119, "split": "val", "sentences": [{"tokens": ["the", "darker", "car"], "raw": "The darker car", "sent_id": 91871, "sent": "the darker car"}, {"tokens": ["the", "black", "volkswagon"], "raw": "The black volkswagon", "sent_id": 91872, "sent": "the black volkswagon"}], "file_name": "COCO_train2014_000000121619_1775119.jpg", "ann_id": 1775119, "sent_ids": [91871, 91872], "ref_id": 40326}, {"segmentation": [[487.59, 286.11, 488.55, 276.49, 495.28, 271.68, 515.48, 242.83, 548.18, 235.14, 640.0, 233.22, 640.0, 343.81, 610.69, 344.77, 601.07, 339.97, 597.22, 351.51, 566.45, 357.28, 557.79, 356.31, 543.37, 343.81, 514.52, 337.08, 506.82, 341.89, 490.47, 344.77]], "area": 16087.65965, "iscrowd": 0, "image_id": 459082, "bbox": [487.59, 233.22, 152.41, 124.06], "category_id": 3, "id": 243187, "split": "val", "sentences": [{"tokens": ["a", "grey", "minivan", "driving", "in", "the", "opposite", "direction", "of", "a", "red", "bus"], "raw": "A grey minivan driving in the opposite direction of a red bus.", "sent_id": 91873, "sent": "a grey minivan driving in the opposite direction of a red bus"}, {"tokens": ["a", "white", "van", "driving", "next", "to", "a", "double", "decker", "bus"], "raw": "A white van driving next to a double decker bus.", "sent_id": 91874, "sent": "a white van driving next to a double decker bus"}], "file_name": "COCO_train2014_000000459082_243187.jpg", "ann_id": 243187, "sent_ids": [91873, 91874], "ref_id": 40327}, {"segmentation": [[346.96, 188.41, 350.09, 184.66, 348.21, 177.77, 351.34, 167.75, 354.47, 166.5, 361.35, 155.86, 349.46, 160.87, 343.83, 148.35, 341.32, 155.23, 336.31, 149.6, 333.18, 155.86, 330.68, 160.87, 320.66, 155.86, 320.04, 159.62, 322.54, 165.25, 327.55, 167.13, 333.18, 170.88, 338.19, 267.29, 331.3, 292.33, 321.29, 321.75, 319.41, 342.41, 336.94, 383.73, 338.82, 408.14, 341.95, 422.54, 345.08, 459.48, 340.07, 471.37, 343.2, 475.75, 341.32, 482.01, 351.96, 487.02, 356.97, 485.14, 356.97, 473.87, 365.74, 472.0, 359.48, 453.84, 368.24, 418.16, 370.74, 412.53, 364.48, 385.61, 373.25, 372.46, 376.38, 397.5, 380.76, 395.0, 380.13, 382.48, 384.52, 396.25, 385.77, 410.02, 384.52, 416.28, 384.52, 423.79, 389.52, 430.05, 390.78, 472.62, 389.52, 480.14, 390.15, 488.27, 402.67, 492.03, 402.67, 485.14, 400.79, 478.26, 400.17, 472.0, 397.04, 467.61, 396.41, 426.3, 399.54, 411.9, 395.16, 403.76, 400.79, 358.06, 398.91, 331.77, 393.28, 321.13, 392.65, 314.87, 369.49, 291.7, 360.1, 269.17, 355.72, 256.02, 347.58, 187.79]], "area": 12422.782250000006, "iscrowd": 0, "image_id": 219963, "bbox": [319.41, 148.35, 83.26, 343.68], "category_id": 25, "id": 596321, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "standing", "straight", "up", "next", "to", "a", "tree", "and", "a", "rock"], "raw": "A giraffe standing straight up next to a tree and a rock.", "sent_id": 91936, "sent": "a giraffe standing straight up next to a tree and a rock"}, {"tokens": ["a", "giraffe", "standing", "upright", "with", "its", "head", "raised"], "raw": "A giraffe standing upright with its head raised.", "sent_id": 91937, "sent": "a giraffe standing upright with its head raised"}], "file_name": "COCO_train2014_000000219963_596321.jpg", "ann_id": 596321, "sent_ids": [91936, 91937], "ref_id": 40353}, {"segmentation": [[126.97, 87.52, 275.21, 83.06, 318.12, 85.29, 379.98, 93.65, 418.43, 156.63, 228.95, 154.4, 83.5, 157.18, 106.35, 94.21]], "area": 20779.2846, "iscrowd": 0, "image_id": 502153, "bbox": [83.5, 83.06, 334.93, 74.12], "category_id": 3, "id": 1777506, "split": "val", "sentences": [{"tokens": ["the", "back", "window", "of", "a", "truck"], "raw": "The back window of a truck.", "sent_id": 91996, "sent": "the back window of a truck"}], "file_name": "COCO_train2014_000000502153_1777506.jpg", "ann_id": 1777506, "sent_ids": [91996], "ref_id": 40379}, {"segmentation": [[44.82, 367.13, 46.36, 362.0, 47.39, 349.17, 46.87, 341.47, 46.87, 334.29, 47.39, 328.14, 47.39, 324.54, 47.9, 317.87, 48.41, 312.23, 49.44, 304.54, 49.95, 296.33, 50.47, 286.07, 50.47, 277.86, 51.49, 262.98, 52.52, 251.18, 54.57, 240.92, 57.14, 228.09, 58.67, 216.8, 58.67, 214.75, 58.16, 211.16, 54.06, 208.59, 47.39, 206.03, 51.49, 195.25, 53.54, 190.64, 55.6, 187.04, 59.7, 177.81, 61.24, 173.7, 62.78, 169.09, 65.34, 158.83, 68.94, 151.13, 70.47, 147.03, 76.12, 142.92, 84.33, 140.36, 92.02, 140.36, 101.77, 140.36, 109.47, 144.97, 111.52, 144.46, 115.11, 140.36, 122.29, 143.95, 126.4, 149.08, 135.12, 149.59, 142.81, 151.13, 148.46, 151.64, 157.18, 157.29, 157.18, 162.93, 156.15, 173.19, 153.59, 181.4, 154.61, 187.56, 158.21, 195.25, 160.77, 198.84, 162.31, 203.46, 163.34, 208.08, 163.34, 212.18, 161.8, 218.34, 153.59, 220.91, 140.76, 220.39, 140.25, 220.39, 134.61, 216.8, 127.94, 212.18, 127.94, 218.34, 132.55, 221.93, 138.71, 230.14, 136.15, 232.19, 140.76, 239.89, 139.22, 245.53, 143.84, 260.92, 147.43, 268.62, 148.46, 275.8, 148.46, 282.47, 147.95, 288.63, 147.95, 293.76, 147.95, 296.84, 152.56, 300.43, 162.82, 297.35, 168.47, 294.27, 176.68, 293.76, 182.32, 293.76, 198.74, 293.76, 203.35, 296.32, 203.35, 302.48, 203.35, 307.1, 201.82, 309.66, 196.69, 311.72, 193.09, 312.23, 187.96, 312.23, 185.4, 318.9, 185.4, 318.9, 186.94, 317.11, 188.48, 322.24, 191.55, 325.83, 200.79, 327.37, 205.92, 331.47, 215.67, 335.06, 221.82, 340.19, 225.93, 346.35, 227.98, 350.45, 227.98, 354.05, 227.98, 358.66, 229.01, 359.18, 234.14, 364.31, 242.35, 368.92, 247.48, 373.54, 250.56, 378.16, 253.12, 380.72, 253.63, 382.78, 236.19, 392.01, 235.16, 395.09, 234.14, 396.63, 226.96, 397.14, 222.34, 396.63, 211.56, 393.04, 203.35, 393.04, 198.74, 394.06, 190.53, 397.66, 184.37, 399.19, 176.68, 399.19, 167.44, 402.27, 161.8, 404.32, 155.13, 404.84, 148.97, 405.86, 143.33, 407.92, 134.61, 413.05, 128.96, 415.1, 122.29, 411.51, 109.47, 407.92, 101.77, 407.92, 97.67, 406.89, 87.92, 404.84, 76.63, 402.27, 67.91, 399.19, 54.57, 396.12, 48.93, 396.63, 42.26, 395.6, 40.2, 389.45, 44.31, 370.46, 46.36, 367.39]], "area": 32865.756299999994, "iscrowd": 0, "image_id": 74945, "bbox": [40.2, 140.36, 213.43, 274.74], "category_id": 1, "id": 511549, "split": "val", "sentences": [{"tokens": ["a", "young", "girl", "in", "a", "pink", "dress", "and", "a", "pink", "bonnet"], "raw": "A young girl in a pink dress and a pink bonnet.", "sent_id": 92019, "sent": "a young girl in a pink dress and a pink bonnet"}, {"tokens": ["a", "woman", "in", "a", "pink", "dress", "and", "bonnet"], "raw": "A woman in a pink dress and bonnet.", "sent_id": 92020, "sent": "a woman in a pink dress and bonnet"}], "file_name": "COCO_train2014_000000074945_511549.jpg", "ann_id": 511549, "sent_ids": [92019, 92020], "ref_id": 40387}, {"segmentation": [[297.45, 331.4, 298.48, 323.19, 307.71, 313.96, 313.86, 305.76, 315.91, 292.42, 303.61, 269.86, 297.45, 264.73, 276.94, 248.32, 263.6, 233.96, 237.96, 219.6, 224.63, 214.47, 217.45, 223.7, 217.45, 229.85, 217.45, 243.19, 216.42, 257.55, 218.47, 268.83, 220.52, 277.04, 225.65, 289.35, 231.81, 316.01, 234.88, 327.3, 242.06, 336.53, 251.3, 344.73, 257.45, 344.73, 268.73, 342.68, 278.99, 337.55, 287.19, 336.53, 287.19, 345.76, 285.14, 349.86, 298.48, 346.78, 306.68, 362.17, 307.71, 347.81, 302.58, 343.71, 320.02, 342.68, 322.07, 341.66, 304.63, 335.5, 299.5, 331.4, 298.48, 331.4]], "area": 8683.939649999998, "iscrowd": 0, "image_id": 549377, "bbox": [216.42, 214.47, 105.65, 147.7], "category_id": 16, "id": 39570, "split": "val", "sentences": [{"tokens": ["the", "closest", "front", "facing", "pigeon"], "raw": "The closest front facing pigeon.", "sent_id": 92111, "sent": "the closest front facing pigeon"}, {"tokens": ["pigeon", "facing", "camera", "stands", "on", "pavement"], "raw": "Pigeon facing camera stands on pavement", "sent_id": 92112, "sent": "pigeon facing camera stands on pavement"}], "file_name": "COCO_train2014_000000549377_39570.jpg", "ann_id": 39570, "sent_ids": [92111, 92112], "ref_id": 40420}, {"segmentation": [[193.85, 112.85, 184.75, 94.65, 184.75, 81.0, 201.13, 68.26, 317.63, 30.03, 335.83, 20.02, 358.58, 34.58, 389.53, 58.25, 401.36, 69.17, 403.18, 86.46, 386.8, 95.56, 375.88, 97.38, 361.31, 65.53, 347.66, 60.07, 336.74, 58.25, 322.18, 65.53, 284.87, 69.17, 229.35, 80.09, 208.42, 83.73, 201.13, 104.66, 202.96, 119.22]], "area": 6632.84, "iscrowd": 0, "image_id": 524866, "bbox": [184.75, 20.02, 218.43, 99.2], "category_id": 77, "id": 1637559, "split": "val", "sentences": [{"tokens": ["the", "red", "flip", "phone", "under", "the", "smartphone"], "raw": "The red flip phone under the smartphone.", "sent_id": 92182, "sent": "the red flip phone under the smartphone"}, {"tokens": ["an", "unknown", "electronic", "device", "behind", "a", "mobile", "phone", "on", "an", "unknown", "surface"], "raw": "An unknown electronic device behind a mobile phone on an unknown surface.", "sent_id": 92183, "sent": "an unknown electronic device behind a mobile phone on an unknown surface"}], "file_name": "COCO_train2014_000000524866_1637559.jpg", "ann_id": 1637559, "sent_ids": [92182, 92183], "ref_id": 40447}, {"segmentation": [[41.17, 170.93, 35.76, 179.59, 30.34, 196.93, 48.76, 308.53, 31.42, 362.71, 10.84, 408.22, 0.0, 409.3, 0.0, 1.9, 303.39, 2.98, 313.14, 23.57, 315.3, 39.82, 314.22, 72.33, 295.8, 94.0, 274.13, 105.91, 255.71, 126.5, 250.29, 133.0, 237.29, 136.25, 226.46, 146.0, 214.54, 143.84, 200.45, 138.42, 177.7, 146.0, 171.2, 141.67, 144.11, 103.75, 135.44, 92.91, 128.94, 108.08, 124.6, 142.75, 124.6, 165.51, 128.94, 168.76, 127.86, 173.09, 107.27, 178.51, 102.93, 178.51, 93.18, 185.01, 81.26, 185.01, 70.43, 185.01]], "area": 52741.94395, "iscrowd": 0, "image_id": 100667, "bbox": [0.0, 1.9, 315.3, 407.4], "category_id": 1, "id": 506735, "split": "val", "sentences": [{"tokens": ["the", "man", "on", "the", "left", "wating", "a", "banana"], "raw": "The man on the left wating a banana.", "sent_id": 92220, "sent": "the man on the left wating a banana"}, {"tokens": ["a", "bald", "man", "eating", "a", "banana"], "raw": "A bald man eating a banana.", "sent_id": 92221, "sent": "a bald man eating a banana"}], "file_name": "COCO_train2014_000000100667_506735.jpg", "ann_id": 506735, "sent_ids": [92220, 92221], "ref_id": 40463}, {"segmentation": [[231.0, 289.69, 248.2, 259.41, 266.77, 233.27, 255.08, 214.01, 253.01, 196.12, 259.89, 170.67, 266.08, 159.66, 281.91, 151.4, 286.72, 150.71, 281.91, 128.01, 281.22, 117.0, 291.54, 110.12, 303.24, 108.75, 319.06, 112.88, 319.06, 132.14, 319.06, 141.08, 311.49, 147.27, 317.6, 155.14, 325.08, 153.64, 342.27, 161.12, 353.49, 184.3, 353.49, 195.51, 346.01, 201.49, 345.26, 222.43, 343.77, 227.66, 351.24, 235.14, 351.99, 247.1, 341.52, 249.34, 353.49, 274.76, 356.48, 294.95, 360.21, 299.44, 363.21, 313.64, 349.75, 312.89, 337.79, 303.92, 334.79, 282.99, 322.83, 284.48, 303.39, 255.33, 280.96, 280.0, 269.75, 279.25, 250.31, 291.96, 242.83, 306.91, 241.34, 320.37, 236.85, 327.1, 213.68, 331.59, 200.97, 331.59, 199.47, 324.11, 203.96, 317.38, 224.14, 313.64, 231.62, 294.95]], "area": 14552.376700000003, "iscrowd": 0, "image_id": 199331, "bbox": [199.47, 108.75, 163.74, 222.84], "category_id": 1, "id": 445066, "split": "val", "sentences": [{"tokens": ["man", "withyellow", "shirt", "with", "a", "blue", "vest", "on", "top", ",", "black", "shorts", "with", "the", "number", "79", "playing", "soccer"], "raw": "man withyellow shirt with a blue vest on top, black shorts with the number 79 playing soccer", "sent_id": 92238, "sent": "man withyellow shirt with a blue vest on top , black shorts with the number 79 playing soccer"}, {"tokens": ["a", "man", "with", "white", "and", "orange", "t", "-", "shirt", ",", "black", "trousers", "playing", "football"], "raw": "A man with white and orange t-shirt, black trousers playing football.", "sent_id": 92239, "sent": "a man with white and orange t - shirt , black trousers playing football"}], "file_name": "COCO_train2014_000000199331_445066.jpg", "ann_id": 445066, "sent_ids": [92238, 92239], "ref_id": 40470}, {"segmentation": [[154.93, 430.97, 234.17, 376.62, 240.27, 363.92, 251.95, 352.74, 277.35, 337.5, 259.06, 359.85, 277.86, 343.6, 264.14, 362.9, 280.91, 346.65, 265.67, 367.98, 284.97, 349.69, 253.48, 385.25, 236.71, 384.74, 170.17, 439.09, 145.79, 460.43, 137.16, 452.81, 136.14, 445.19]], "area": 2544.165649999999, "iscrowd": 0, "image_id": 212679, "bbox": [136.14, 337.5, 148.83, 122.93], "category_id": 48, "id": 688994, "split": "val", "sentences": [{"tokens": ["the", "fork", "in", "the", "side", "of", "green", "plate"], "raw": "the fork in the side of green plate", "sent_id": 92259, "sent": "the fork in the side of green plate"}, {"tokens": ["a", "steel", "fork", "on", "the", "right", "side", "of", "a", "green", "plate"], "raw": "A steel fork on the right side of a green plate", "sent_id": 92260, "sent": "a steel fork on the right side of a green plate"}], "file_name": "COCO_train2014_000000212679_688994.jpg", "ann_id": 688994, "sent_ids": [92259, 92260], "ref_id": 40480}, {"segmentation": [[222.97, 111.48, 172.04, 89.46, 108.73, 57.81, 103.23, 20.65, 194.06, 81.2, 229.85, 96.34, 268.39, 96.34, 297.29, 92.22, 349.59, 77.08, 390.88, 57.81, 363.35, 96.34, 286.28, 118.37, 295.91, 134.88, 271.14, 150.02, 269.76, 167.91, 253.25, 147.27, 239.48, 170.67, 232.6, 147.27, 213.33, 128.0, 231.23, 118.37]], "area": 8747.524150000001, "iscrowd": 0, "image_id": 354444, "bbox": [103.23, 20.65, 287.65, 150.02], "category_id": 16, "id": 41917, "split": "val", "sentences": [{"tokens": ["the", "flying", "seagull"], "raw": "the flying seagull", "sent_id": 92269, "sent": "the flying seagull"}, {"tokens": ["a", "seagul", "flying", "over", "seaguls", "sitting", "on", "an", "old", "car"], "raw": "A seagul flying over seaguls sitting on an old car.", "sent_id": 92270, "sent": "a seagul flying over seaguls sitting on an old car"}], "file_name": "COCO_train2014_000000354444_41917.jpg", "ann_id": 41917, "sent_ids": [92269, 92270], "ref_id": 40485}, {"segmentation": [[203.76, 149.71, 221.48, 132.0, 222.46, 100.5, 235.26, 70.97, 257.9, 60.14, 283.49, 64.08, 304.16, 101.48, 299.24, 133.97, 290.38, 153.65, 313.02, 169.4, 319.91, 193.03, 311.05, 320.99, 285.46, 282.6, 247.07, 271.77, 236.24, 255.04, 245.1, 233.38, 248.05, 221.57, 253.96, 209.76, 253.96, 194.99, 236.24, 169.4, 221.48, 158.57, 205.73, 163.5, 200.81, 165.46]], "area": 16370.060000000003, "iscrowd": 0, "image_id": 242090, "bbox": [200.81, 60.14, 119.1, 260.85], "category_id": 1, "id": 550623, "split": "val", "sentences": [{"tokens": ["a", "merchant", "in", "a", "red", "plaid", "shirt"], "raw": "A merchant in a red plaid shirt.", "sent_id": 92323, "sent": "a merchant in a red plaid shirt"}, {"tokens": ["a", "man", "in", "a", "red", "plaid", "shirt", "behind", "a", "counter"], "raw": "A man in a red plaid shirt behind a counter", "sent_id": 92324, "sent": "a man in a red plaid shirt behind a counter"}], "file_name": "COCO_train2014_000000242090_550623.jpg", "ann_id": 550623, "sent_ids": [92323, 92324], "ref_id": 40505}, {"segmentation": [[44.68, 260.9, 31.71, 289.73, 10.09, 350.27, 27.39, 438.2, 69.19, 498.74, 136.94, 546.31, 175.86, 562.16, 239.28, 552.07, 273.87, 523.24, 312.79, 480.0, 344.5, 410.81, 343.06, 345.95, 344.5, 317.12, 330.09, 270.99, 295.5, 229.19, 279.64, 219.1, 247.93, 209.01, 93.69, 201.8, 83.6, 226.31]], "area": 93840.91865000002, "iscrowd": 0, "image_id": 16836, "bbox": [10.09, 201.8, 334.41, 360.36], "category_id": 60, "id": 1080764, "split": "val", "sentences": [{"tokens": ["a", "round", "donut"], "raw": "A round donut.", "sent_id": 92336, "sent": "a round donut"}, {"tokens": ["the", "round", "donut"], "raw": "The round donut", "sent_id": 92337, "sent": "the round donut"}], "file_name": "COCO_train2014_000000016836_1080764.jpg", "ann_id": 1080764, "sent_ids": [92336, 92337], "ref_id": 40512}, {"segmentation": [[437.6, 204.1, 451.1, 247.48, 458.81, 293.74, 453.99, 313.98, 409.65, 308.2, 369.17, 309.17, 345.07, 304.35, 316.15, 289.89, 322.9, 269.65, 316.15, 265.79, 313.26, 243.62, 340.25, 214.7, 359.53, 205.07, 365.31, 203.14, 391.34, 202.17]], "area": 13176.250000000005, "iscrowd": 0, "image_id": 66518, "bbox": [313.26, 202.17, 145.55, 111.81], "category_id": 54, "id": 310554, "split": "val", "sentences": [{"tokens": ["the", "slightly", "smaller", "portion", "of", "a", "sandwich", ",", "with", "a", "darker", "crust"], "raw": "the slightly smaller portion of a sandwich, with a darker crust", "sent_id": 92405, "sent": "the slightly smaller portion of a sandwich , with a darker crust"}, {"tokens": ["the", "left", "half", "of", "the", "sandwhich"], "raw": "the left half of the sandwhich", "sent_id": 92406, "sent": "the left half of the sandwhich"}], "file_name": "COCO_train2014_000000066518_310554.jpg", "ann_id": 310554, "sent_ids": [92405, 92406], "ref_id": 40536}, {"segmentation": [[0.0, 514.34, 31.45, 425.56, 48.09, 309.03, 48.09, 277.58, 68.44, 251.68, 92.49, 235.04, 131.33, 231.34, 172.02, 229.49, 212.72, 233.19, 247.86, 264.63, 271.91, 283.13, 255.26, 314.57, 264.51, 329.37, 275.61, 353.42, 271.91, 412.61, 268.21, 457.0, 257.11, 497.7, 255.26, 551.34, 249.71, 584.63, 238.61, 597.58, 201.62, 590.18, 196.07, 567.98, 184.97, 521.74, 177.57, 492.15, 155.38, 477.35, 157.23, 519.89, 170.17, 595.73, 144.28, 599.43, 114.68, 599.43, 125.78, 579.08, 129.48, 560.59, 103.58, 412.61, 99.88, 384.86, 88.79, 388.56, 73.99, 434.81, 25.9, 542.09, 0.0, 569.83]], "area": 66416.16700000003, "iscrowd": 0, "image_id": 127214, "bbox": [0.0, 229.49, 275.61, 369.94], "category_id": 22, "id": 585447, "split": "val", "sentences": [{"tokens": ["the", "elephant", "that", "is", "most", "clearly", "visible", "in", "the", "picture"], "raw": "The elephant that is most clearly visible in the picture", "sent_id": 92569, "sent": "the elephant that is most clearly visible in the picture"}, {"tokens": ["the", "elephant", "with", "no", "tusks", "whose", "face", "is", "seen"], "raw": "The elephant with no tusks whose face is seen", "sent_id": 92570, "sent": "the elephant with no tusks whose face is seen"}], "file_name": "COCO_train2014_000000127214_585447.jpg", "ann_id": 585447, "sent_ids": [92569, 92570], "ref_id": 40598}, {"segmentation": [[595.42, 391.37, 640.0, 395.69, 638.9, 469.91, 439.34, 480.0, 450.46, 463.24, 457.88, 457.3, 502.4, 458.04, 589.94, 456.56, 593.64, 454.33, 598.1, 438.01, 600.32, 423.92, 607.74, 415.01, 620.35, 411.3, 605.51, 407.6, 596.61, 393.5]], "area": 5801.413000000001, "iscrowd": 0, "image_id": 220037, "bbox": [439.34, 391.37, 200.66, 88.63], "category_id": 62, "id": 376739, "split": "val", "sentences": [{"tokens": ["a", "white", "chair", "near", "by", "a", "eye", "glass", "wearing", "lady", "and", "holding", "a", "black", "color", "bag"], "raw": "A WHITE CHAIR NEAR BY A EYE GLASS WEARING LADY AND HOLDING A BLACK COLOR BAG", "sent_id": 92613, "sent": "a white chair near by a eye glass wearing lady and holding a black color bag"}, {"tokens": ["the", "chair", "with", "the", "bag", "on", "it", "in", "the", "right", "hand", "picture"], "raw": "the chair with the bag on it in the right hand picture", "sent_id": 92614, "sent": "the chair with the bag on it in the right hand picture"}], "file_name": "COCO_train2014_000000220037_376739.jpg", "ann_id": 376739, "sent_ids": [92613, 92614], "ref_id": 40616}, {"segmentation": [[0.96, 103.26, 11.46, 78.42, 19.11, 68.87, 34.39, 57.41, 64.0, 56.45, 102.21, 63.14, 118.45, 78.42, 124.18, 106.13, 130.87, 132.87, 121.32, 141.47, 119.41, 145.29, 123.23, 160.58, 126.09, 165.35, 124.18, 172.04, 124.18, 172.04, 140.42, 187.32, 152.84, 213.11, 161.44, 242.73, 162.39, 272.34, 165.26, 286.67, 170.99, 288.58, 174.81, 307.69, 175.77, 322.97, 175.77, 333.48, 173.86, 340.16, 165.26, 344.94, 149.02, 345.9, 132.78, 345.9, 127.05, 330.61, 124.18, 341.12, 120.36, 346.85, 77.38, 352.58, 68.78, 355.45, 63.05, 349.72, 48.72, 344.94, 12.42, 342.07, 0.96, 351.63, 0.0, 334.43, 29.61, 315.33, 30.57, 307.69, 12.42, 284.76, 0.0, 239.86, 0.96, 223.62, 9.55, 210.25, 3.82, 190.19, 0.96, 191.14]], "area": 39625.302, "iscrowd": 0, "image_id": 517492, "bbox": [0.0, 56.45, 175.77, 299.0], "category_id": 1, "id": 471291, "split": "val", "sentences": [{"tokens": ["chinese", "woman", "with", "black", "hair", "playing", "with", "her", "fingers", "looking", "of", "the", "screen"], "raw": "Chinese woman with black hair playing with her fingers looking of the screen.", "sent_id": 92653, "sent": "chinese woman with black hair playing with her fingers looking of the screen"}, {"tokens": ["a", "woman", "in", "black", "looks", "at", "a", "woman", "in", "a", "white", "shirt"], "raw": "A woman in black looks at a woman in a white shirt.", "sent_id": 92654, "sent": "a woman in black looks at a woman in a white shirt"}], "file_name": "COCO_train2014_000000517492_471291.jpg", "ann_id": 471291, "sent_ids": [92653, 92654], "ref_id": 40626}, {"segmentation": [[51.05, 64.39, 119.31, 89.31, 135.56, 104.48, 149.65, 125.07, 154.24, 132.14, 161.38, 128.57, 161.38, 128.57, 165.67, 123.57, 165.67, 132.86, 178.54, 132.14, 189.26, 140.01, 176.4, 148.59, 167.82, 145.01, 162.81, 153.59, 173.54, 155.74, 179.97, 152.16, 173.54, 161.45, 184.26, 159.31, 200.7, 165.03, 211.42, 175.04, 220.0, 196.48, 220.0, 209.35, 215.71, 202.2, 216.43, 212.21, 217.86, 220.07, 214.28, 232.22, 208.56, 237.23, 197.13, 241.52, 205.71, 282.98, 212.14, 320.15, 212.85, 335.88, 207.85, 365.9, 204.99, 383.06, 203.56, 404.51, 204.99, 418.09, 215.71, 430.24, 227.15, 435.96, 226.46, 454.81, 238.37, 456.98, 242.71, 465.64, 270.88, 479.73, 161.44, 480.0, 63.93, 480.0, 0.0, 479.73, 0.0, 137.34, 0.0, 66.91]], "area": 81153.69850000001, "iscrowd": 0, "image_id": 31187, "bbox": [0.0, 64.39, 270.88, 415.61], "category_id": 1, "id": 465027, "split": "val", "sentences": [{"tokens": ["the", "blonde", "girls", "head"], "raw": "the blonde girls head", "sent_id": 92682, "sent": "the blonde girls head"}, {"tokens": ["blonde", "hair", "with", "small", "green", "hairtie"], "raw": "blonde hair with small green hairtie", "sent_id": 92683, "sent": "blonde hair with small green hairtie"}], "file_name": "COCO_train2014_000000031187_465027.jpg", "ann_id": 465027, "sent_ids": [92682, 92683], "ref_id": 40639}, {"segmentation": [[640.0, 188.76, 627.78, 188.76, 628.85, 196.31, 362.43, 188.76, 362.43, 180.13, 347.33, 180.13, 349.48, 202.79, 354.88, 277.21, 353.8, 325.75, 372.13, 324.67, 369.98, 284.76, 386.16, 283.69, 388.31, 304.18, 394.79, 304.18, 394.79, 312.81, 388.31, 316.04, 394.79, 320.36, 404.49, 314.97, 404.49, 310.65, 403.42, 293.39, 404.49, 286.92, 485.39, 293.39, 487.55, 319.28, 509.12, 330.07, 518.83, 327.91, 523.15, 335.46, 530.7, 335.46, 530.7, 302.02, 546.88, 296.63, 633.17, 302.02, 631.01, 341.93, 639.64, 341.93]], "area": 32188.459099999996, "iscrowd": 0, "image_id": 366148, "bbox": [347.33, 180.13, 292.67, 161.8], "category_id": 15, "id": 578172, "split": "val", "sentences": [{"tokens": ["a", "wooden", "bench", "to", "the", "right", "of", "another", "wooden", "bench"], "raw": "A wooden bench to the right of another wooden bench.", "sent_id": 92750, "sent": "a wooden bench to the right of another wooden bench"}], "file_name": "COCO_train2014_000000366148_578172.jpg", "ann_id": 578172, "sent_ids": [92750], "ref_id": 40668}, {"segmentation": [[326.18, 159.07, 326.18, 149.0, 347.33, 141.95, 364.44, 125.84, 376.52, 142.96, 385.58, 150.0, 395.65, 170.14, 401.69, 186.25, 428.87, 201.35, 448.0, 210.41, 493.3, 222.49, 516.46, 252.69, 524.51, 270.81, 519.48, 280.88, 495.32, 276.85, 475.18, 267.79, 460.08, 254.71, 463.1, 267.79, 433.91, 274.84, 405.72, 266.79, 396.66, 265.78, 395.65, 300.01, 383.57, 327.19, 355.38, 331.22, 363.43, 314.1, 368.47, 299.0, 365.45, 261.75, 356.39, 227.52, 366.45, 203.36, 346.32, 182.22, 342.29, 177.19], [487.26, 338.27, 481.22, 369.47, 491.29, 379.54, 495.32, 368.47]], "area": 14818.668600000003, "iscrowd": 0, "image_id": 126447, "bbox": [326.18, 125.84, 198.33, 253.7], "category_id": 19, "id": 54819, "split": "val", "sentences": [{"tokens": ["horse", "getting", "ready", "to", "get", "behind", "the", "truck", "to", "travel", "long", "distance"], "raw": "horse getting ready to get behind the truck to travel long distance", "sent_id": 92785, "sent": "horse getting ready to get behind the truck to travel long distance"}, {"tokens": ["a", "horse", "being", "loaded", "into", "a", "truck"], "raw": "A horse being loaded into a truck.", "sent_id": 92786, "sent": "a horse being loaded into a truck"}], "file_name": "COCO_train2014_000000126447_54819.jpg", "ann_id": 54819, "sent_ids": [92785, 92786], "ref_id": 40683}, {"segmentation": [[22.48, 201.33, 53.96, 149.62, 101.17, 133.88, 139.39, 128.26, 148.38, 114.77, 148.38, 100.16, 150.63, 81.05, 158.5, 49.57, 165.25, 34.96, 175.36, 22.59, 207.96, 19.22, 228.2, 24.84, 236.07, 38.33, 240.56, 56.31, 248.43, 65.31, 247.31, 79.92, 243.93, 91.16, 239.44, 103.53, 213.58, 128.26, 211.33, 137.25, 216.96, 147.37, 249.56, 172.1, 265.29, 184.46, 279.91, 209.2, 291.15, 248.54, 296.77, 283.39, 299.02, 313.74, 310.26, 362.08, 317.0, 399.17, 322.62, 441.89, 326.0, 467.74, 290.02, 464.37, 281.03, 422.78, 269.79, 421.65, 278.78, 465.5, 55.08, 468.87, 58.45, 390.18, 58.45, 367.7, 32.6, 342.97, 1.12, 333.97, 2.25, 248.54, 17.99, 213.69]], "area": 95248.59525000001, "iscrowd": 0, "image_id": 492638, "bbox": [1.12, 19.22, 324.88, 449.65], "category_id": 1, "id": 502348, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "red", "shirt"], "raw": "The man in the red shirt", "sent_id": 92799, "sent": "the man in the red shirt"}, {"tokens": ["old", "man", "in", "red", "sweater", "playing", "wii"], "raw": "old man in red sweater playing wii", "sent_id": 92800, "sent": "old man in red sweater playing wii"}], "file_name": "COCO_train2014_000000492638_502348.jpg", "ann_id": 502348, "sent_ids": [92799, 92800], "ref_id": 40689}, {"segmentation": [[314.08, 167.14, 313.59, 163.83, 311.27, 160.53, 301.36, 159.7, 242.2, 166.47, 208.16, 170.11, 186.84, 173.25, 158.42, 177.22, 121.07, 181.68, 100.75, 183.66, 94.8, 187.96, 92.65, 192.91, 86.54, 195.06, 83.07, 198.04, 79.76, 210.6, 77.28, 223.98, 76.29, 231.58, 81.58, 236.7, 83.4, 249.59, 83.4, 254.72, 83.07, 257.03, 107.19, 277.69, 120.41, 290.25, 120.41, 301.65, 123.72, 307.6, 130.99, 306.6, 136.77, 297.35, 136.77, 292.56, 237.24, 273.56, 296.4, 262.81, 331.6, 256.04, 352.59, 251.25, 352.09, 256.2, 356.88, 259.67, 357.21, 255.05, 358.37, 249.1, 355.06, 243.98, 353.08, 233.9, 353.74, 223.98, 356.55, 222.66, 358.86, 219.02, 364.98, 213.07, 366.63, 188.12, 364.48, 186.8, 315.9, 166.97, 314.08, 166.97]], "area": 28086.792250000002, "iscrowd": 0, "image_id": 55226, "bbox": [76.29, 159.7, 290.34, 147.9], "category_id": 63, "id": 115384, "split": "val", "sentences": [{"tokens": ["the", "brown", "couch", "with", "the", "stool", "on", "it"], "raw": "The brown couch with the stool on it.", "sent_id": 92814, "sent": "the brown couch with the stool on it"}, {"tokens": ["a", "grey", "couch", "against", "the", "back", "wall", "with", "a", "bar", "stool", "lying", "on", "top", "of", "it"], "raw": "a grey couch against the back wall with a bar stool lying on top of it", "sent_id": 92815, "sent": "a grey couch against the back wall with a bar stool lying on top of it"}], "file_name": "COCO_train2014_000000055226_115384.jpg", "ann_id": 115384, "sent_ids": [92814, 92815], "ref_id": 40695}, {"segmentation": [[378.7, 252.84, 374.05, 245.86, 371.72, 223.74, 364.15, 191.14, 374.05, 184.73, 390.35, 184.15, 406.07, 240.62, 421.78, 202.78, 431.68, 180.66, 445.65, 180.08, 449.14, 181.24, 454.96, 192.88, 465.44, 193.47, 474.18, 200.45, 476.5, 191.72, 484.07, 178.91, 483.49, 146.89, 488.73, 140.49, 499.79, 137.0, 499.79, 186.48, 499.79, 199.87, 496.3, 195.79, 488.73, 218.5, 497.46, 219.66, 500.0, 216.75, 499.21, 247.6, 499.79, 287.77, 467.77, 294.18, 457.29, 294.76, 449.73, 286.61, 446.23, 290.68, 421.78, 284.86, 420.62, 283.7, 417.13, 278.46, 414.22, 275.55, 411.89, 276.13, 410.72, 277.88, 376.96, 253.43], [376.38, 173.09, 369.97, 165.52, 372.3, 159.12, 375.79, 152.72, 378.12, 150.39, 383.36, 150.39, 404.32, 145.15, 431.68, 136.42, 452.64, 127.1, 462.53, 126.52, 463.11, 127.1, 463.11, 128.85, 451.47, 130.01, 417.71, 145.15, 389.18, 158.54, 386.85, 159.7, 387.44, 169.02]], "area": 12365.393200000002, "iscrowd": 0, "image_id": 313209, "bbox": [364.15, 126.52, 135.85, 168.24], "category_id": 57, "id": 1062348, "split": "val", "sentences": [{"tokens": ["a", "corrot"], "raw": "A corrot", "sent_id": 92855, "sent": "a corrot"}], "file_name": "COCO_train2014_000000313209_1062348.jpg", "ann_id": 1062348, "sent_ids": [92855], "ref_id": 40712}, {"segmentation": [[272.33, 369.08, 261.74, 428.0, 109.14, 428.0, 0.0, 428.0, 0.0, 420.39, 0.0, 356.23, 1.16, 346.39, 9.74, 333.68, 34.83, 291.44, 50.07, 274.29, 49.44, 268.89, 49.12, 248.57, 55.47, 238.72, 79.93, 223.16, 71.99, 213.0, 75.16, 188.54, 69.13, 186.64, 56.43, 186.32, 53.57, 187.91, 44.36, 186.64, 34.51, 204.74, 28.16, 204.1, 25.62, 195.85, 24.98, 186.32, 25.62, 136.77, 27.21, 125.66, 32.92, 118.35, 42.77, 102.47, 46.58, 89.13, 51.03, 82.46, 63.1, 69.44, 68.81, 46.26, 77.71, 25.93, 72.94, 11.0, 81.83, 1.16, 127.25, 0.0, 171.71, 0.0, 225.39, 0.0, 238.41, 0.0, 253.65, 0.0, 273.03, 16.4, 263.18, 32.6, 260.01, 37.05, 250.48, 30.69, 238.41, 25.61, 255.24, 56.74, 261.59, 57.06, 273.03, 55.47, 291.13, 70.71, 291.77, 74.84, 277.16, 79.6, 264.45, 78.33, 262.55, 89.13, 264.14, 105.97, 261.01, 120.61, 260.59, 123.13, 249.48, 129.83, 250.53, 138.84, 248.85, 164.41, 248.01, 169.65, 250.13, 184.99, 235.84, 225.64, 238.38, 227.86, 261.56, 261.21, 256.16, 262.8, 245.68, 259.62, 258.39, 285.35, 271.41, 345.38]], "area": 94869.7276, "iscrowd": 0, "image_id": 473182, "bbox": [0.0, 0.0, 291.77, 428.0], "category_id": 4, "id": 1790525, "split": "val", "sentences": [{"tokens": ["a", "bike", "in", "the", "forest"], "raw": "a bike in the forest", "sent_id": 92900, "sent": "a bike in the forest"}, {"tokens": ["part", "of", "a", "bike", "on", "the", "ground", "surrounded", "by", "trees"], "raw": "Part of a bike on the ground surrounded by trees", "sent_id": 92901, "sent": "part of a bike on the ground surrounded by trees"}], "file_name": "COCO_train2014_000000473182_1790525.jpg", "ann_id": 1790525, "sent_ids": [92900, 92901], "ref_id": 40729}, {"segmentation": [[330.12, 190.81, 318.53, 191.29, 318.53, 211.09, 325.29, 246.83, 330.12, 258.9, 329.16, 272.42, 330.12, 284.97, 344.61, 310.57, 361.99, 332.3, 382.76, 336.16, 395.79, 325.54, 396.28, 309.12, 395.31, 291.73, 395.31, 280.63, 410.76, 276.28, 423.32, 260.35, 424.28, 234.75, 414.63, 213.99, 400.14, 198.54, 382.27, 184.05, 380.34, 185.02, 384.2, 192.26, 381.31, 196.12, 375.51, 200.95, 370.2, 196.12, 367.3, 188.4, 367.3, 186.46, 358.61, 186.95, 359.58, 190.81, 361.99, 195.64, 358.13, 199.02, 347.99, 197.57, 347.5, 192.74, 345.57, 190.81, 342.68, 190.81, 342.19, 198.54, 338.81, 204.33, 332.05, 200.47, 330.6, 192.26]], "area": 10686.214950000001, "iscrowd": 0, "image_id": 223023, "bbox": [318.53, 184.05, 105.75, 152.11], "category_id": 70, "id": 1967458, "split": "val", "sentences": [{"tokens": ["a", "bidet", "next", "to", "a", "toilet"], "raw": "A bidet next to a toilet.", "sent_id": 93034, "sent": "a bidet next to a toilet"}, {"tokens": ["a", "bidet", "beside", "a", "toilet"], "raw": "a bidet beside a toilet", "sent_id": 93035, "sent": "a bidet beside a toilet"}], "file_name": "COCO_train2014_000000223023_1967458.jpg", "ann_id": 1967458, "sent_ids": [93034, 93035], "ref_id": 40776}, {"segmentation": [[1.08, 184.26, 65.59, 165.98, 82.8, 314.37, 201.08, 371.36, 206.45, 488.56, 202.15, 498.24, 187.1, 500.0, 183.87, 495.01, 188.17, 489.64, 182.8, 421.89, 96.77, 497.16, 34.41, 500.0, 0.0, 461.68, 0.0, 348.78, 65.59, 315.44, 64.52, 228.35, 1.08, 261.68, 0.0, 228.35, 59.14, 210.07, 58.06, 187.49, 21.51, 204.69, 2.15, 215.44]], "area": 33462.09725, "iscrowd": 0, "image_id": 229678, "bbox": [0.0, 165.98, 206.45, 334.02], "category_id": 62, "id": 107983, "split": "val", "sentences": [{"tokens": ["a", "chair", "with", "a", "black", "seat"], "raw": "A chair with a black seat.", "sent_id": 93117, "sent": "a chair with a black seat"}, {"tokens": ["wooden", "chair", "with", "dark", "colored", "ripped", "padding", "on", "top"], "raw": "Wooden chair with dark colored ripped padding on top.", "sent_id": 93118, "sent": "wooden chair with dark colored ripped padding on top"}], "file_name": "COCO_train2014_000000229678_107983.jpg", "ann_id": 107983, "sent_ids": [93117, 93118], "ref_id": 40808}, {"segmentation": [[229.71, 143.46, 215.25, 154.04, 206.08, 170.26, 211.02, 184.72, 221.95, 197.41, 235.0, 221.4, 268.5, 222.81, 335.51, 224.22, 393.34, 223.16, 500.0, 222.45, 499.49, 143.46, 472.69, 148.75, 434.25, 157.21, 421.56, 158.97, 404.63, 165.32, 366.89, 167.09, 345.74, 165.32, 341.5, 164.26, 325.99, 153.69, 323.17, 143.81, 317.88, 137.46, 311.88, 136.76, 303.77, 131.12, 300.95, 129.7, 297.77, 134.99, 297.07, 140.28, 288.96, 126.18, 285.43, 122.3, 283.67, 123.71, 290.72, 144.16, 292.84, 158.97, 296.36, 164.62, 290.72, 172.73, 285.08, 173.43, 281.9, 171.32, 273.09, 164.26, 270.97, 158.62, 270.97, 155.45, 266.39, 155.1, 260.75, 153.33, 255.46, 147.69, 249.46, 144.16, 236.77, 140.99, 229.01, 142.4]], "area": 19370.3229, "iscrowd": 0, "image_id": 386211, "bbox": [206.08, 122.3, 293.92, 101.92], "category_id": 1, "id": 501665, "split": "val", "sentences": [{"tokens": ["woman", "wearing", "pink", "shirt"], "raw": "woman wearing pink shirt", "sent_id": 93177, "sent": "woman wearing pink shirt"}, {"tokens": ["a", "girl", "in", "a", "red", "and", "white", "shirt", "texting"], "raw": "A girl in a red and white shirt texting.", "sent_id": 93178, "sent": "a girl in a red and white shirt texting"}], "file_name": "COCO_train2014_000000386211_501665.jpg", "ann_id": 501665, "sent_ids": [93177, 93178], "ref_id": 40828}, {"segmentation": [[514.75, 543.66, 473.46, 560.17, 463.83, 556.04, 483.1, 536.77, 465.2, 478.97, 441.81, 439.05, 434.92, 377.12, 415.66, 342.71, 406.02, 348.22, 418.41, 295.91, 403.27, 260.13, 412.9, 236.73, 441.81, 235.35, 452.82, 265.63, 448.69, 273.89, 473.46, 291.78, 480.34, 357.85, 512.0, 400.52, 470.71, 455.57, 516.13, 543.66]], "area": 14379.887549999996, "iscrowd": 0, "image_id": 32533, "bbox": [403.27, 235.35, 112.86, 324.82], "category_id": 1, "id": 187829, "split": "val", "sentences": [{"tokens": ["motorcycle", "rider", "wearing", "dark", "clothing"], "raw": "Motorcycle rider wearing dark clothing.", "sent_id": 93202, "sent": "motorcycle rider wearing dark clothing"}, {"tokens": ["a", "police", "officer", "on", "a", "motorcycle"], "raw": "A police officer on a motorcycle.", "sent_id": 93203, "sent": "a police officer on a motorcycle"}], "file_name": "COCO_train2014_000000032533_187829.jpg", "ann_id": 187829, "sent_ids": [93202, 93203], "ref_id": 40838}, {"segmentation": [[615.55, 321.24, 580.93, 318.36, 565.54, 317.39, 516.49, 312.58, 511.68, 329.9, 482.82, 332.78, 473.2, 320.28, 463.59, 310.66, 457.82, 303.93, 453.97, 272.19, 453.01, 251.99, 417.42, 238.53, 401.07, 209.67, 397.22, 201.02, 390.49, 172.16, 394.34, 167.35, 528.99, 164.47, 554.96, 166.39, 552.07, 186.59, 559.77, 205.82, 576.12, 223.14, 586.7, 237.56, 617.47, 249.11, 627.09, 266.42, 628.05, 283.73, 628.05, 298.16, 624.21, 302.0, 619.4, 318.36]], "area": 25677.1905, "iscrowd": 0, "image_id": 277188, "bbox": [390.49, 164.47, 237.56, 168.31], "category_id": 8, "id": 401531, "split": "val", "sentences": [{"tokens": ["an", "ambulance", "located", "to", "the", "right", "of", "two", "other", "ambulances"], "raw": "An ambulance located to the right of two other ambulances.", "sent_id": 93254, "sent": "an ambulance located to the right of two other ambulances"}, {"tokens": ["a", "van", "stopped", "in", "the", "right", "corner", "of", "the", "picture"], "raw": "A van stopped in the right corner of the picture", "sent_id": 93255, "sent": "a van stopped in the right corner of the picture"}], "file_name": "COCO_train2014_000000277188_401531.jpg", "ann_id": 401531, "sent_ids": [93254, 93255], "ref_id": 40858}, {"segmentation": [[356.67, 499.06, 362.43, 384.0, 371.06, 312.09, 386.88, 309.21, 391.19, 280.45, 411.33, 283.33, 414.2, 309.21, 419.96, 320.72, 426.0, 330.79, 409.89, 504.81, 394.07, 499.06, 396.94, 412.76, 369.62, 513.44]], "area": 10529.377949999998, "iscrowd": 0, "image_id": 101503, "bbox": [356.67, 280.45, 69.33, 232.99], "category_id": 1, "id": 1727701, "split": "val", "sentences": [{"tokens": ["a", "bald", "man", "with", "a", "towel", "draped", "over", "his", "shoulder"], "raw": "A bald man with a towel draped over his shoulder.", "sent_id": 93262, "sent": "a bald man with a towel draped over his shoulder"}, {"tokens": ["the", "man", "in", "the", "background", "with", "a", "towel", "on", "his", "shoulder"], "raw": "The man in the background with a towel on his shoulder", "sent_id": 93263, "sent": "the man in the background with a towel on his shoulder"}], "file_name": "COCO_train2014_000000101503_1727701.jpg", "ann_id": 1727701, "sent_ids": [93262, 93263], "ref_id": 40861}, {"segmentation": [[5.76, 138.63, 31.67, 146.3, 35.5, 146.3, 53.73, 145.35, 61.41, 161.66, 69.09, 181.81, 82.52, 196.2, 131.46, 190.44, 142.01, 181.81, 166.0, 153.02, 183.27, 155.9, 173.68, 164.54, 161.2, 177.97, 146.81, 193.32, 95.96, 302.71, 95.96, 302.71, 99.79, 307.51, 108.43, 336.3, 116.11, 354.53, 149.69, 377.56, 166.96, 402.5, 184.23, 408.26, 215.9, 414.02, 226.45, 415.94, 252.36, 420.74, 242.77, 426.49, 233.17, 426.49, 215.9, 426.49, 183.27, 425.53, 147.77, 423.61, 101.71, 420.74, 71.97, 416.9, 53.73, 422.66, 41.26, 422.66, 34.54, 422.66, 29.75, 422.66, 26.87, 422.66, 11.51, 421.7, 3.84, 421.7], [491.29, 229.79, 510.48, 232.66, 546.94, 224.99, 570.93, 213.47, 579.57, 197.16, 601.64, 184.69, 630.42, 168.37, 639.06, 168.37, 640.0, 182.77, 639.06, 412.1, 631.38, 421.7, 615.07, 425.53, 453.87, 420.74, 400.13, 423.61, 399.17, 414.98, 458.67, 390.03, 483.61, 365.08, 495.13, 325.74, 508.56, 279.68, 502.8, 232.66]], "area": 66309.6877, "iscrowd": 0, "image_id": 239596, "bbox": [3.84, 138.63, 636.16, 287.86], "category_id": 67, "id": 420371, "split": "val", "sentences": [{"tokens": ["place", "mat", "under", "the", "food"], "raw": "Place mat under the food.", "sent_id": 93278, "sent": "place mat under the food"}, {"tokens": ["a", "table", "mat", "where", "plate", "of", "snacks", "are", "placed"], "raw": "A table mat where plate of snacks are placed", "sent_id": 93279, "sent": "a table mat where plate of snacks are placed"}], "file_name": "COCO_train2014_000000239596_420371.jpg", "ann_id": 420371, "sent_ids": [93278, 93279], "ref_id": 40869}, {"segmentation": [[414.2, 158.56, 423.1, 182.83, 440.09, 193.35, 461.12, 182.83, 463.55, 169.89, 459.51, 151.28, 460.31, 141.57, 495.1, 136.72, 521.8, 135.1, 542.02, 135.1, 561.44, 141.57, 586.52, 131.06, 594.61, 118.11, 606.74, 105.98, 605.12, 135.1, 620.49, 217.62, 612.4, 248.36, 602.7, 279.1, 596.22, 300.94, 532.31, 317.93, 438.47, 302.56, 416.63, 292.85, 397.21, 276.67, 381.03, 228.94, 369.71, 208.72, 361.62, 194.97, 366.47, 164.22, 381.84, 150.47]], "area": 36398.335450000006, "iscrowd": 0, "image_id": 411289, "bbox": [361.62, 105.98, 258.87, 211.95], "category_id": 9, "id": 176411, "split": "val", "sentences": [{"tokens": ["a", "boat", "with", "a", "fisherman", "standing", "in", "it"], "raw": "A boat with a fisherman standing in it.", "sent_id": 93293, "sent": "a boat with a fisherman standing in it"}, {"tokens": ["the", "boat", "on", "the", "right"], "raw": "The boat on the right.", "sent_id": 93294, "sent": "the boat on the right"}], "file_name": "COCO_train2014_000000411289_176411.jpg", "ann_id": 176411, "sent_ids": [93293, 93294], "ref_id": 40877}, {"segmentation": [[42.85, 210.25, 49.29, 205.96, 64.32, 198.44, 70.77, 182.33, 76.13, 181.26, 81.5, 174.82, 90.09, 169.45, 96.54, 166.23, 105.13, 159.78, 107.28, 157.64, 104.05, 151.19, 98.68, 147.97, 95.46, 138.31, 91.17, 131.87, 86.87, 125.42, 85.8, 113.61, 85.8, 97.5, 87.95, 84.62, 87.95, 70.66, 87.95, 57.77, 86.87, 50.25, 89.02, 32.0, 90.09, 26.63, 94.39, 20.19, 96.54, 11.6, 98.68, 4.08, 102.98, 0.0, 288.75, 0.0, 290.9, 6.23, 295.19, 15.89, 284.46, 26.63, 284.46, 32.0, 286.6, 35.22, 290.9, 43.81, 291.97, 45.96, 291.97, 51.33, 294.12, 56.7, 295.19, 64.21, 296.27, 67.44, 298.42, 73.88, 301.64, 81.4, 303.79, 84.62, 307.01, 95.36, 307.01, 99.65, 312.38, 112.54, 307.01, 117.91, 307.01, 127.57, 307.01, 137.23, 302.71, 152.27, 315.6, 158.71, 326.34, 174.82, 314.52, 179.11, 302.71, 180.19, 291.97, 180.19, 276.94, 180.19, 262.98, 180.19, 245.8, 183.41, 226.47, 188.78, 204.99, 188.78, 196.4, 188.78, 182.44, 188.78, 153.45, 194.15, 137.34, 194.15, 118.01, 194.15, 97.61, 197.37, 90.09, 197.37, 79.36, 204.89, 71.84, 214.55, 66.47, 214.55, 58.95, 212.4, 50.36, 211.33, 46.07, 210.25, 48.21, 211.33]], "area": 40613.14314999999, "iscrowd": 0, "image_id": 253238, "bbox": [42.85, 0.0, 283.49, 214.55], "category_id": 1, "id": 429816, "split": "val", "sentences": [{"tokens": ["a", "blonde", "-", "haired", "woman", "'", "s", "head"], "raw": "A blonde-haired woman's head.", "sent_id": 93339, "sent": "a blonde - haired woman ' s head"}, {"tokens": ["a", "blonde", "-", "haired", "middle", "-", "aged", "woman", "in", "glasses", "looking", "at", "a", "hot", "dog", "that", "is", "very", "close", "to", "the", "camera"], "raw": "a blonde-haired middle-aged woman in glasses looking at a hot dog that is very close to the camera.", "sent_id": 93340, "sent": "a blonde - haired middle - aged woman in glasses looking at a hot dog that is very close to the camera"}], "file_name": "COCO_train2014_000000253238_429816.jpg", "ann_id": 429816, "sent_ids": [93339, 93340], "ref_id": 40898}, {"segmentation": [[0.64, 310.37, 0.64, 164.13, 20.39, 149.72, 34.26, 143.85, 46.54, 141.18, 60.42, 143.85, 71.63, 147.05, 84.43, 149.72, 91.91, 152.92, 104.18, 154.52, 113.26, 155.59, 122.33, 161.99, 126.07, 171.07, 127.13, 182.81, 134.07, 196.69, 138.88, 204.69, 143.15, 219.64, 146.35, 226.04, 153.29, 228.71, 158.62, 221.24, 159.16, 211.1, 158.62, 198.29, 176.24, 204.16, 177.84, 213.77, 175.17, 223.91, 175.17, 240.99, 140.48, 249.53, 136.21, 248.46, 111.66, 235.12, 99.91, 231.38, 96.71, 248.46, 92.97, 264.47, 90.84, 275.15, 89.77, 288.49, 94.58, 306.1, 100.98, 324.78, 98.85, 327.45, 78.56, 327.98, 66.82, 322.65, 60.42, 318.38, 64.69, 301.83, 64.69, 276.21, 52.41, 257.53, 49.21, 265.0, 47.61, 280.48, 51.88, 289.02, 58.28, 300.76, 54.55, 310.37, 32.13, 310.91, 31.6, 290.09, 34.26, 263.4, 23.59, 242.05, 13.98, 253.26, 15.58, 277.81, 19.32, 299.7, 20.39, 309.3, 8.64, 313.57]], "area": 18617.62165000001, "iscrowd": 0, "image_id": 522834, "bbox": [0.64, 141.18, 177.2, 186.8], "category_id": 22, "id": 580402, "split": "val", "sentences": [{"tokens": ["a", "grey", "elephant", "to", "the", "left", "of", "another", "elephant"], "raw": "A grey elephant to the left of another elephant", "sent_id": 93346, "sent": "a grey elephant to the left of another elephant"}, {"tokens": ["elephant", "with", "the", "upturned", "trunk"], "raw": "Elephant with the upturned trunk", "sent_id": 93347, "sent": "elephant with the upturned trunk"}], "file_name": "COCO_train2014_000000522834_580402.jpg", "ann_id": 580402, "sent_ids": [93346, 93347], "ref_id": 40901}, {"segmentation": [[119.69, 295.02, 130.13, 269.31, 152.63, 242.79, 156.65, 160.84, 130.94, 157.63, 122.9, 138.35, 94.78, 138.35, 88.35, 150.4, 13.63, 138.35, 2.39, 135.94, 3.99, 273.33]], "area": 20292.972899999997, "iscrowd": 0, "image_id": 466825, "bbox": [2.39, 135.94, 154.26, 159.08], "category_id": 67, "id": 1615834, "split": "val", "sentences": [{"tokens": ["the", "table", "behind", "the", "cake", "holding", "food", "dishes"], "raw": "the table behind the cake holding food dishes", "sent_id": 93364, "sent": "the table behind the cake holding food dishes"}, {"tokens": ["a", "buffet", "table", "behind", "the", "wedding", "cake"], "raw": "A buffet table behind the wedding cake.", "sent_id": 93365, "sent": "a buffet table behind the wedding cake"}], "file_name": "COCO_train2014_000000466825_1615834.jpg", "ann_id": 1615834, "sent_ids": [93364, 93365], "ref_id": 40905}, {"segmentation": [[423.91, 381.84, 454.11, 401.26, 492.94, 412.04, 524.22, 396.94, 640.0, 229.75, 638.56, 168.27, 599.73, 142.38, 541.48, 120.81, 476.76, 114.34, 446.56, 120.81, 423.91, 136.99, 407.73, 311.73]], "area": 50464.34039999999, "iscrowd": 0, "image_id": 568840, "bbox": [407.73, 114.34, 232.27, 297.7], "category_id": 47, "id": 670389, "split": "val", "sentences": [{"tokens": ["a", "krispy", "creme", "coffee", "cup", "that", "is", "filled", "nearly", "to", "the", "brim"], "raw": "A Krispy Creme coffee cup that is filled nearly to the brim.", "sent_id": 93374, "sent": "a krispy creme coffee cup that is filled nearly to the brim"}, {"tokens": ["the", "coffee", "cup", "closest", "to", "the", "chocolate", "glazed", "donut", "with", "the", "spiderweb", "design"], "raw": "The coffee cup  closest to the chocolate glazed donut with the spiderweb design.", "sent_id": 93375, "sent": "the coffee cup closest to the chocolate glazed donut with the spiderweb design"}], "file_name": "COCO_train2014_000000568840_670389.jpg", "ann_id": 670389, "sent_ids": [93374, 93375], "ref_id": 40909}, {"segmentation": [[384.48, 433.3, 484.22, 427.07, 562.76, 402.13, 555.28, 412.11, 547.8, 444.52, 586.45, 478.19, 590.19, 479.43, 388.22, 480.0, 385.72, 452.0, 375.75, 434.55, 391.96, 433.3], [618.87, 372.21, 640.0, 377.2, 640.0, 407.12, 590.19, 394.65, 620.11, 370.97]], "area": 10894.909399999999, "iscrowd": 0, "image_id": 207543, "bbox": [375.75, 370.97, 264.25, 109.03], "category_id": 67, "id": 1962065, "split": "val", "sentences": [{"tokens": ["red", "and", "white", "checkered", "tablecloth"], "raw": "Red and white checkered tablecloth", "sent_id": 93388, "sent": "red and white checkered tablecloth"}, {"tokens": ["table", "with", "cloth"], "raw": "table with cloth", "sent_id": 93389, "sent": "table with cloth"}], "file_name": "COCO_train2014_000000207543_1962065.jpg", "ann_id": 1962065, "sent_ids": [93388, 93389], "ref_id": 40915}, {"segmentation": [[76.52, 280.08, 38.26, 277.22, 16.56, 272.65, 6.85, 254.66, 13.99, 226.39, 19.98, 212.69, 27.41, 196.12, 27.98, 189.27, 33.69, 175.85, 39.69, 165.57, 75.38, 152.43, 84.23, 151.29, 79.09, 144.72, 74.81, 141.58, 68.53, 131.59, 71.67, 114.74, 76.52, 108.46, 80.52, 104.46, 87.37, 99.61, 91.94, 99.61, 96.23, 92.18, 103.65, 91.9, 114.22, 96.47, 128.49, 111.89, 131.92, 119.88, 133.35, 122.45, 133.06, 132.16, 125.35, 144.72, 124.78, 147.01, 133.35, 148.44, 137.63, 147.87, 144.2, 152.43, 155.62, 170.14, 158.19, 175.85, 159.33, 181.28, 168.19, 196.98, 167.04, 198.98, 174.18, 212.4, 176.75, 223.54, 171.9, 238.39, 148.48, 244.38, 153.62, 234.96, 153.05, 219.25, 146.48, 208.4, 137.63, 203.26, 135.63, 222.11, 43.97, 240.1, 42.54, 246.95, 61.1, 255.8, 77.95, 259.52, 75.38, 261.23, 74.52, 268.65]], "area": 15546.202049999996, "iscrowd": 0, "image_id": 272155, "bbox": [6.85, 91.9, 169.9, 188.18], "category_id": 1, "id": 471140, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "a", "green", "short", "sleeved", "shirt"], "raw": "A man wearing a green short sleeved shirt.", "sent_id": 93398, "sent": "a man wearing a green short sleeved shirt"}, {"tokens": ["a", "man", "in", "a", "green", "shirt", "staring", "at", "his", "open", "laptop"], "raw": "a man in a green shirt staring at his open laptop", "sent_id": 93399, "sent": "a man in a green shirt staring at his open laptop"}], "file_name": "COCO_train2014_000000272155_471140.jpg", "ann_id": 471140, "sent_ids": [93398, 93399], "ref_id": 40920}, {"segmentation": [[248.1, 186.07, 238.48, 200.5, 225.98, 219.73, 220.21, 226.46, 209.63, 236.08, 210.6, 250.5, 221.17, 279.35, 235.6, 296.66, 252.91, 302.43, 267.33, 311.09, 302.91, 320.7, 316.37, 326.47, 325.99, 345.7, 339.45, 337.05, 365.42, 350.51, 376.0, 339.93, 384.65, 331.28, 385.61, 316.86, 385.61, 303.39, 388.5, 287.05, 398.11, 280.31, 422.15, 304.35, 432.73, 331.28, 467.35, 357.24, 525.05, 371.67, 560.63, 379.36, 640.0, 405.33, 640.0, 118.76, 615.44, 123.57, 610.63, 109.14, 532.74, 106.26, 493.31, 135.11, 466.39, 159.15, 456.77, 179.34, 451.0, 184.15, 436.58, 205.31, 433.69, 214.92, 433.69, 219.73, 408.69, 206.27, 407.73, 182.23, 394.27, 177.42, 383.69, 177.42, 373.11, 174.53, 361.57, 164.92, 345.22, 160.11, 325.99, 160.11, 311.57, 164.92, 299.07, 164.92, 281.76, 168.77, 269.26, 172.61, 248.1, 186.07]], "area": 79893.74059999998, "iscrowd": 0, "image_id": 419110, "bbox": [209.63, 106.26, 430.37, 299.07], "category_id": 1, "id": 422628, "split": "val", "sentences": [{"tokens": ["woman", "wearing", "green", "and", "brown", "dress"], "raw": "woman wearing green and brown dress", "sent_id": 93516, "sent": "woman wearing green and brown dress"}, {"tokens": ["the", "woman", "being", "touched", "by", "the", "elephant", "trunk"], "raw": "the woman being touched by the elephant trunk", "sent_id": 93517, "sent": "the woman being touched by the elephant trunk"}], "file_name": "COCO_train2014_000000419110_422628.jpg", "ann_id": 422628, "sent_ids": [93516, 93517], "ref_id": 40967}, {"segmentation": [[128.2, 186.12, 98.21, 188.43, 81.29, 198.43, 74.37, 287.62, 77.45, 314.53, 81.29, 316.07, 84.37, 301.46, 80.52, 284.54, 83.6, 275.32, 84.37, 259.94, 89.75, 278.39, 85.91, 289.16, 88.98, 319.91, 100.52, 312.99, 99.75, 282.24, 109.74, 309.15, 108.2, 322.22, 112.82, 316.07, 115.12, 293.77, 115.12, 288.39, 120.51, 295.31, 128.2, 286.08, 132.81, 281.47, 117.43, 252.25, 114.36, 229.18, 122.04, 204.58, 128.2, 194.58, 134.35, 186.89, 127.43, 184.59], [233.53, 187.66, 262.75, 188.43, 275.82, 191.51, 277.36, 185.36, 287.35, 187.66, 291.97, 189.97, 309.65, 180.74, 321.95, 186.89, 336.56, 185.36, 348.1, 186.12, 342.71, 199.2, 332.72, 202.27, 328.87, 223.8, 320.42, 248.4, 308.88, 248.4, 295.04, 266.86, 274.28, 294.54, 260.44, 295.31, 255.06, 306.07, 254.29, 316.84, 252.75, 329.91, 244.3, 328.37, 243.53, 308.38, 241.22, 308.38, 235.07, 333.75, 226.61, 331.44, 226.61, 293.77, 228.15, 288.39, 242.76, 260.71, 248.14, 240.72, 247.37, 221.49, 242.76, 203.04, 234.3, 189.2]], "area": 13848.04725, "iscrowd": 0, "image_id": 227198, "bbox": [74.37, 180.74, 273.73, 153.01], "category_id": 21, "id": 74318, "split": "val", "sentences": [{"tokens": ["the", "side", "of", "a", "cow", "looking", "towards", "the", "camera", "behind", "another", "cow"], "raw": "the side of a cow looking towards the camera behind another cow", "sent_id": 93567, "sent": "the side of a cow looking towards the camera behind another cow"}, {"tokens": ["all", "the", "cows", "except", "the", "first", "two", "from", "the", "front"], "raw": "all the cows except the first two from the front", "sent_id": 93568, "sent": "all the cows except the first two from the front"}], "file_name": "COCO_train2014_000000227198_74318.jpg", "ann_id": 74318, "sent_ids": [93567, 93568], "ref_id": 40988}, {"segmentation": [[37.67, 408.02, 154.98, 471.52, 636.05, 472.59, 638.21, 350.98, 608.07, 336.99, 619.91, 290.71, 615.61, 282.1, 554.26, 276.72, 543.5, 283.17, 543.5, 309.0, 506.91, 316.54, 486.46, 304.7, 471.39, 298.24, 472.47, 292.86, 471.39, 282.1, 461.7, 295.01, 439.1, 307.93, 375.61, 291.78, 355.16, 282.1, 356.23, 246.58, 346.55, 225.06, 326.1, 217.52, 311.03, 208.91, 294.89, 206.76, 277.67, 201.38, 269.06, 215.37, 265.83, 241.2, 266.91, 250.89, 271.21, 262.73, 270.13, 268.11, 245.38, 269.18, 224.93, 264.88, 205.56, 260.57, 192.65, 259.5, 178.65, 269.18, 177.58, 271.34, 188.34, 244.43, 166.82, 240.13, 145.29, 242.28, 139.91, 245.51, 135.61, 253.04, 134.53, 260.57, 144.22, 306.85, 145.29, 307.93, 131.3, 315.46, 127.0, 317.61, 132.38, 343.44, 145.29, 357.43, 142.06, 371.43, 128.07, 395.1, 116.23, 398.33, 62.42, 401.56]], "area": 102675.85559999995, "iscrowd": 0, "image_id": 151854, "bbox": [37.67, 201.38, 600.54, 271.21], "category_id": 67, "id": 392536, "split": "val", "sentences": [{"tokens": ["brown", "table"], "raw": "brown table", "sent_id": 93576, "sent": "brown table"}, {"tokens": ["the", "table", "top", "all", "the", "drinks", "are", "on"], "raw": "The table top all the drinks are on.", "sent_id": 93577, "sent": "the table top all the drinks are on"}], "file_name": "COCO_train2014_000000151854_392536.jpg", "ann_id": 392536, "sent_ids": [93576, 93577], "ref_id": 40991}, {"segmentation": [[66.35, 53.49, 80.1, 42.64, 80.82, 10.8, 80.1, 0.0, 0.0, 0.0, 9.91, 33.95, 1.22, 84.61, 40.3, 71.58, 51.88, 70.13, 54.77, 104.14, 60.56, 114.27, 85.89, 115.0, 98.19, 109.21, 100.36, 93.29, 83.0, 67.24, 72.14, 51.32]], "area": 7247.5962, "iscrowd": 0, "image_id": 447349, "bbox": [0.0, 0.0, 100.36, 115.0], "category_id": 62, "id": 1930521, "split": "val", "sentences": [{"tokens": ["wooden", "design", "to", "left", "of", "bears"], "raw": "Wooden design to left of bears", "sent_id": 93582, "sent": "wooden design to left of bears"}], "file_name": "COCO_train2014_000000447349_1930521.jpg", "ann_id": 1930521, "sent_ids": [93582], "ref_id": 40993}, {"segmentation": [[4.3, 297.95, 20.04, 283.63, 41.52, 287.92, 54.41, 290.79, 67.29, 279.33, 78.75, 270.74, 87.34, 253.56, 95.93, 239.24, 100.22, 233.52, 98.79, 220.63, 90.2, 203.45, 75.88, 194.86, 61.57, 189.13, 51.54, 187.7, 55.84, 177.68, 61.57, 176.25, 71.59, 170.52, 81.61, 164.79, 87.34, 161.93, 95.93, 157.63, 101.66, 156.2, 104.52, 147.61, 98.79, 139.02, 98.79, 133.29, 111.68, 139.02, 117.4, 139.02, 120.27, 131.86, 126.0, 121.84, 123.13, 106.09, 114.54, 100.36, 104.52, 94.63, 93.06, 94.63, 77.32, 96.07, 75.88, 98.93, 58.7, 96.07, 50.11, 93.2, 24.34, 90.34, 17.18, 90.34, 30.07, 80.32, 31.5, 68.86, 31.5, 58.84, 31.5, 41.66, 31.5, 23.05, 34.36, 11.59, 38.66, 0.14, 0.0, 4.43, 2.86, 293.65]], "area": 20348.624449999996, "iscrowd": 0, "image_id": 566301, "bbox": [0.0, 0.14, 126.0, 297.81], "category_id": 1, "id": 1732000, "split": "val", "sentences": [{"tokens": ["a", "kid", "looking", "down", "at", "something"], "raw": "A kid looking down at something.", "sent_id": 93682, "sent": "a kid looking down at something"}, {"tokens": ["hands", "holding", "pizza"], "raw": "Hands holding pizza.", "sent_id": 93683, "sent": "hands holding pizza"}], "file_name": "COCO_train2014_000000566301_1732000.jpg", "ann_id": 1732000, "sent_ids": [93682, 93683], "ref_id": 41029}, {"segmentation": [[505.83, 320.72, 491.84, 291.66, 499.37, 251.84, 529.51, 246.46, 559.64, 241.08, 552.11, 232.47, 537.04, 226.01, 512.29, 226.01, 495.07, 214.17, 519.82, 204.48, 542.42, 207.71, 541.35, 170.04, 551.03, 150.67, 572.56, 145.29, 585.47, 184.04, 599.46, 158.21, 611.3, 151.75, 613.45, 161.43, 610.22, 251.84, 611.3, 347.62, 554.26, 346.55, 552.11, 351.93, 547.8, 354.08, 544.57, 346.55, 517.67, 340.09, 517.67, 345.47, 513.36, 346.55, 511.21, 337.94, 503.68, 331.48, 503.68, 323.95], [625.29, 185.11, 637.13, 182.96, 637.13, 200.18, 627.44, 213.09, 630.67, 232.47, 630.67, 247.53, 640.0, 261.52, 639.28, 298.12, 636.05, 326.1, 633.9, 345.47, 624.22, 346.55, 620.99, 157.13]], "area": 19860.841949999998, "iscrowd": 0, "image_id": 268804, "bbox": [491.84, 145.29, 148.16, 208.79], "category_id": 64, "id": 1609975, "split": "val", "sentences": [{"tokens": ["a", "green", "planter", "holds", "pink", "flowers", "and", "a", "large", "leafed", "plant"], "raw": "A green planter holds pink flowers and a large leafed plant.", "sent_id": 93697, "sent": "a green planter holds pink flowers and a large leafed plant"}, {"tokens": ["a", "large", "plant", "in", "a", "grey", "planter", "directly", "behind", "a", "sign", "post"], "raw": "A large plant in a grey planter directly behind a sign post.", "sent_id": 93698, "sent": "a large plant in a grey planter directly behind a sign post"}], "file_name": "COCO_train2014_000000268804_1609975.jpg", "ann_id": 1609975, "sent_ids": [93697, 93698], "ref_id": 41035}, {"segmentation": [[1.43, 234.95, 50.11, 276.47, 41.52, 365.24, 31.5, 431.1, 12.89, 474.05, 0.0, 458.3], [68.72, 462.6, 88.77, 512.71, 84.47, 552.8, 67.29, 544.21, 57.27, 568.55, 7.16, 562.82, 52.98, 491.23, 64.43, 459.74]], "area": 12520.662349999999, "iscrowd": 0, "image_id": 127214, "bbox": [0.0, 234.95, 88.77, 333.6], "category_id": 22, "id": 585727, "split": "val", "sentences": [{"tokens": ["the", "elephant", "'", "s", "backside", "on", "the", "far", "left", "of", "the", "photo"], "raw": "the elephant's backside on the far left of the photo", "sent_id": 93707, "sent": "the elephant ' s backside on the far left of the photo"}, {"tokens": ["two", "back", "legs", "to", "a", "standing", "elephant"], "raw": "Two back legs to a standing elephant.", "sent_id": 93708, "sent": "two back legs to a standing elephant"}], "file_name": "COCO_train2014_000000127214_585727.jpg", "ann_id": 585727, "sent_ids": [93707, 93708], "ref_id": 41038}, {"segmentation": [[268.06, 276.92, 272.49, 252.55, 269.17, 219.32, 269.17, 201.6, 258.09, 209.35, 237.05, 213.78, 231.51, 199.38, 249.23, 177.23, 263.63, 162.83, 260.31, 151.75, 270.28, 128.49, 296.86, 78.65, 286.89, 62.03, 286.89, 48.74, 302.4, 39.88, 324.55, 36.55, 331.2, 45.42, 342.28, 54.28, 336.74, 63.14, 336.74, 84.18, 327.88, 94.15, 326.77, 104.12, 331.2, 122.95, 328.98, 140.68, 338.95, 147.32, 321.23, 159.51, 323.45, 167.26, 340.06, 182.77, 341.17, 183.88, 346.71, 191.63, 346.71, 200.49, 343.38, 206.03, 338.95, 208.25, 331.2, 212.68, 325.66, 214.89, 313.48, 217.11, 310.15, 219.32, 305.72, 231.51, 304.62, 240.37, 297.97, 258.09, 295.75, 264.74, 293.54, 278.03, 292.43, 283.57, 290.22, 297.97, 288.0, 305.72, 288.0, 312.37, 286.89, 321.23, 290.22, 327.88, 297.97, 331.2, 305.72, 336.74, 297.97, 341.17, 280.25, 342.28, 262.52, 342.28, 252.55, 338.95, 249.23, 331.2, 260.31, 293.54, 262.52, 276.92, 269.17, 263.63]], "area": 15483.9067, "iscrowd": 0, "image_id": 169653, "bbox": [231.51, 36.55, 115.2, 305.73], "category_id": 1, "id": 556937, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "in", "the", "batter", "'", "s", "box", "holding", "a", "bat", "and", "wearing", "a", "shin", "guard"], "raw": "A baseball player in the batter's box holding a bat and wearing a shin guard.", "sent_id": 93765, "sent": "a baseball player in the batter ' s box holding a bat and wearing a shin guard"}, {"tokens": ["a", "batter", "going", "to", "the", "mound"], "raw": "a batter going to the mound", "sent_id": 93766, "sent": "a batter going to the mound"}], "file_name": "COCO_train2014_000000169653_556937.jpg", "ann_id": 556937, "sent_ids": [93765, 93766], "ref_id": 41060}, {"segmentation": [[54.39, 444.3, 56.38, 448.67, 94.94, 449.87, 166.9, 456.62, 243.23, 466.96, 306.84, 470.14, 314.79, 466.17, 315.19, 449.47, 312.0, 440.32, 306.04, 436.35, 163.72, 434.36, 80.63, 431.98, 56.38, 429.59, 47.23, 415.28, 27.75, 393.02, 3.9, 382.68, 1.51, 383.87, 0.32, 476.1, 31.33, 453.84, 48.03, 444.7]], "area": 9688.170749999994, "iscrowd": 0, "image_id": 281464, "bbox": [0.32, 382.68, 314.87, 93.42], "category_id": 50, "id": 705247, "split": "val", "sentences": [{"tokens": ["spoon", "on", "the", "left"], "raw": "spoon on the left", "sent_id": 93819, "sent": "spoon on the left"}, {"tokens": ["the", "spoon", "the", "left"], "raw": "The spoon the left.", "sent_id": 93820, "sent": "the spoon the left"}], "file_name": "COCO_train2014_000000281464_705247.jpg", "ann_id": 705247, "sent_ids": [93819, 93820], "ref_id": 41081}, {"segmentation": [[245.14, 309.14, 259.2, 295.96, 211.76, 250.27, 216.15, 234.45, 224.93, 207.22, 243.39, 188.76, 224.06, 178.22, 216.15, 161.53, 210.0, 149.22, 203.85, 136.92, 190.67, 129.02, 188.03, 141.32, 164.31, 143.07, 150.25, 129.02, 159.91, 115.84, 188.03, 101.78, 194.18, 97.38, 181.0, 87.72, 182.76, 78.93, 188.03, 67.51, 192.42, 55.21, 209.12, 50.82, 225.81, 52.57, 236.36, 68.39, 239.87, 90.35, 238.99, 100.02, 266.23, 137.8, 288.2, 171.19, 298.74, 179.98, 290.83, 173.83, 258.32, 162.4, 243.39, 161.53, 210.88, 146.59, 219.66, 159.77, 252.17, 173.83, 299.62, 193.16, 303.13, 197.55, 325.98, 235.33, 358.49, 245.88, 389.24, 259.93, 401.54, 249.39, 412.97, 259.06, 421.75, 289.81, 422.63, 309.14, 413.84, 317.93, 398.03, 295.96, 389.24, 288.93, 373.43, 284.54, 311.04, 256.42, 268.87, 211.61, 258.32, 229.18, 246.9, 239.73, 245.14, 250.27, 276.78, 273.99, 282.93, 285.42, 295.23, 285.42, 300.5, 309.14, 277.65, 317.05, 251.29, 316.17, 245.14, 314.41, 241.63, 307.38]], "area": 18786.71145, "iscrowd": 0, "image_id": 347908, "bbox": [150.25, 50.82, 272.38, 267.11], "category_id": 1, "id": 477453, "split": "val", "sentences": [{"tokens": ["young", "person", "in", "red", "shirt", "and", "red", "safety", "helmet", "holds", "the", "bat", "in", "both", "hands", "as", "he", "is", "going", "to", "bunt", "the", "ball"], "raw": "Young person in red shirt and red safety helmet holds the bat in both hands as he is going to bunt the ball.", "sent_id": 93928, "sent": "young person in red shirt and red safety helmet holds the bat in both hands as he is going to bunt the ball"}, {"tokens": ["a", "boy", "with", "a", "red", "helmet", "is", "hodling", "a", "bat"], "raw": "A boy with a red helmet is hodling a bat", "sent_id": 93929, "sent": "a boy with a red helmet is hodling a bat"}], "file_name": "COCO_train2014_000000347908_477453.jpg", "ann_id": 477453, "sent_ids": [93928, 93929], "ref_id": 41117}, {"segmentation": [[82.25, 182.28, 90.4, 155.61, 88.18, 137.08, 88.92, 73.36, 97.81, 57.06, 113.37, 51.87, 107.44, 38.53, 121.52, 17.78, 137.08, 18.52, 144.49, 53.35, 197.1, 91.14, 186.73, 100.03, 163.02, 91.14, 152.64, 82.99, 152.64, 103.74, 144.49, 111.15, 134.12, 119.3, 112.63, 115.59, 116.34, 151.16, 108.18, 180.8, 110.41, 194.14, 120.78, 200.07, 90.4, 206.74]], "area": 7883.004400000001, "iscrowd": 0, "image_id": 177019, "bbox": [82.25, 17.78, 114.85, 188.96], "category_id": 1, "id": 203943, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "blue", "riding", "a", "motorcycle"], "raw": "A man in blue riding a motorcycle.", "sent_id": 93932, "sent": "a man in blue riding a motorcycle"}, {"tokens": ["man", "in", "blue", "shirt", "riding", "motorcycle"], "raw": "man in blue shirt riding motorcycle", "sent_id": 93933, "sent": "man in blue shirt riding motorcycle"}], "file_name": "COCO_train2014_000000177019_203943.jpg", "ann_id": 203943, "sent_ids": [93932, 93933], "ref_id": 41119}, {"segmentation": [[374.67, 355.38, 376.28, 498.49, 377.89, 572.46, 390.75, 572.46, 390.75, 530.65, 387.54, 435.78, 397.19, 426.13, 389.15, 418.09, 382.71, 321.61], [366.63, 281.41, 368.24, 260.5, 373.07, 244.42, 376.28, 247.64, 376.28, 274.97, 373.07, 279.8, 363.42, 283.02], [237.99, 553.17, 237.99, 498.49, 231.56, 480.8, 215.48, 402.01, 205.83, 377.89, 194.57, 376.28, 226.73, 514.57, 237.99, 549.95], [180.1, 291.06, 180.1, 266.93, 186.53, 268.54, 189.75, 294.27, 191.36, 299.1, 180.1, 294.27]], "area": 5574.801000000003, "iscrowd": 0, "image_id": 286132, "bbox": [180.1, 244.42, 217.09, 328.04], "category_id": 35, "id": 605858, "split": "val", "sentences": [{"tokens": ["a", "pair", "of", "red", "and", "blue", "skis", "being", "held", "by", "a", "child"], "raw": "A pair of red and blue skis being held by a child.", "sent_id": 94015, "sent": "a pair of red and blue skis being held by a child"}], "file_name": "COCO_train2014_000000286132_605858.jpg", "ann_id": 605858, "sent_ids": [94015], "ref_id": 41147}, {"segmentation": [[244.47, 244.47, 253.69, 241.01, 282.52, 243.32, 303.28, 236.4, 394.38, 221.41, 378.23, 335.57, 374.77, 345.95, 372.47, 326.34, 358.63, 281.37, 330.95, 295.21, 334.41, 357.48, 320.58, 352.86, 311.35, 295.21, 288.29, 366.7, 280.22, 334.41, 267.53, 294.05, 276.76, 280.22, 239.86, 285.98, 235.24, 253.69, 236.4, 243.32]], "area": 11590.92165, "iscrowd": 0, "image_id": 189836, "bbox": [235.24, 221.41, 159.14, 145.29], "category_id": 21, "id": 277915, "split": "val", "sentences": [{"tokens": ["the", "tan", "cow", "that", "is", "hidden", "behind", "the", "white", "lattice", "fencing"], "raw": "The tan cow that is hidden behind the white lattice fencing.", "sent_id": 94120, "sent": "the tan cow that is hidden behind the white lattice fencing"}, {"tokens": ["a", "brown", "cow", "standing", "behind", "the", "fence"], "raw": "A brown cow standing behind the fence", "sent_id": 94121, "sent": "a brown cow standing behind the fence"}], "file_name": "COCO_train2014_000000189836_277915.jpg", "ann_id": 277915, "sent_ids": [94120, 94121], "ref_id": 41189}, {"segmentation": [[11.99, 289.42, 6.0, 622.16, 292.27, 623.66, 172.37, 488.76, 293.77, 397.33, 80.94, 310.4, 43.47, 298.41, 11.99, 298.41]], "area": 66573.25749999998, "iscrowd": 0, "image_id": 209603, "bbox": [6.0, 289.42, 287.77, 334.24], "category_id": 67, "id": 120940, "split": "val", "sentences": [{"tokens": ["a", "wooden", "plank", "table", "with", "plates", "of", "food", "on", "it"], "raw": "A wooden plank table with plates of food on it", "sent_id": 94198, "sent": "a wooden plank table with plates of food on it"}, {"tokens": ["the", "table", "made", "of", "red", "wood", "lays", "beneath", "two", "black", "mats"], "raw": "The table made of red wood lays beneath two black mats.", "sent_id": 94199, "sent": "the table made of red wood lays beneath two black mats"}], "file_name": "COCO_train2014_000000209603_120940.jpg", "ann_id": 120940, "sent_ids": [94198, 94199], "ref_id": 41225}, {"segmentation": [[54.24, 154.98, 54.0, 161.64, 52.3, 163.21, 49.27, 161.16, 47.46, 158.73, 46.12, 151.34, 46.0, 150.86, 41.4, 149.65, 38.49, 149.65, 34.38, 149.04, 32.8, 147.95, 32.68, 146.14, 31.83, 140.08, 31.83, 135.48, 34.86, 124.82, 37.04, 120.7, 38.74, 117.67, 45.28, 108.59, 46.25, 107.38, 46.85, 106.77, 48.91, 107.38, 49.76, 128.82, 47.7, 133.78, 49.4, 135.48, 52.3, 146.98], [80.52, 155.34, 73.74, 155.95, 71.8, 160.19, 70.23, 158.37, 67.2, 152.92, 65.75, 146.5, 65.75, 146.38, 67.56, 145.29, 70.11, 142.5, 69.74, 140.32, 64.54, 138.87, 63.57, 128.45, 60.78, 123.97, 63.69, 120.7, 61.39, 111.74, 55.57, 111.01, 54.24, 107.01, 66.35, 106.17, 75.32, 106.04, 76.04, 108.59, 76.89, 103.62, 77.5, 102.29, 80.52, 101.44, 83.43, 100.84, 91.91, 94.78, 95.39, 91.83, 93.93, 85.9, 85.46, 84.93, 85.46, 80.81, 87.51, 79.96, 122.16, 79.36, 139.36, 79.72, 172.18, 78.99, 186.71, 78.99, 207.03, 78.27, 209.42, 81.94, 205.04, 84.73, 197.33, 84.18, 198.98, 87.48, 202.84, 87.67, 202.47, 124.38, 198.98, 143.11, 195.49, 137.05, 192.37, 137.79, 192.01, 146.6, 189.99, 147.52, 186.13, 150.82, 180.44, 153.58, 179.16, 148.25, 178.97, 142.74, 176.95, 139.07, 172.73, 134.11, 172.0, 126.4, 169.61, 119.98, 161.9, 114.29, 154.37, 113.19, 148.31, 116.67, 145.01, 124.57, 141.34, 140.54, 126.83, 148.99, 118.39, 153.76, 116.0, 155.59]], "area": 8929.98125, "iscrowd": 0, "image_id": 120782, "bbox": [31.83, 78.27, 177.59, 84.94], "category_id": 8, "id": 1797404, "split": "val", "sentences": [{"tokens": ["truck"], "raw": "truck", "sent_id": 94244, "sent": "truck"}, {"tokens": ["a", "truck", "with", "a", "white", "back", "area", "that", "is", "behind", "the", "woman", "in", "the", "black", "shirt", "near", "the", "cameraman"], "raw": "A truck with a white back area that is behind the woman in the black shirt near the cameraman.", "sent_id": 94245, "sent": "a truck with a white back area that is behind the woman in the black shirt near the cameraman"}], "file_name": "COCO_train2014_000000120782_1797404.jpg", "ann_id": 1797404, "sent_ids": [94244, 94245], "ref_id": 41241}, {"segmentation": [[365.0, 374.0, 310.0, 297.0, 304.0, 283.0, 286.0, 252.0, 271.0, 232.0, 270.0, 217.0, 281.0, 210.0, 293.0, 211.0, 299.0, 216.0, 338.0, 273.0, 358.0, 327.0, 372.0, 357.0, 377.0, 379.0, 374.0, 381.0]], "area": 5080.5, "iscrowd": 0, "image_id": 325545, "bbox": [270.0, 210.0, 107.0, 171.0], "category_id": 57, "id": 1066022, "split": "val", "sentences": [{"tokens": ["a", "carrot", "is", "to", "the", "left", "of", "the", "rest"], "raw": "A carrot is to the left of the rest", "sent_id": 94318, "sent": "a carrot is to the left of the rest"}, {"tokens": ["the", "first", "carrot", "nearer", "to", "ginger", "&", "garlic"], "raw": "THE FIRST CARROT NEARER TO GINGER & GARLIC", "sent_id": 94319, "sent": "the first carrot nearer to ginger & garlic"}], "file_name": "COCO_train2014_000000325545_1066022.jpg", "ann_id": 1066022, "sent_ids": [94318, 94319], "ref_id": 41269}, {"segmentation": [[43.82, 369.1, 43.82, 350.56, 52.25, 342.13, 53.09, 320.22, 64.04, 293.26, 75.84, 265.45, 88.48, 231.74, 107.87, 208.99, 128.09, 192.13, 150.0, 182.02, 182.02, 174.44, 189.61, 167.7, 189.61, 155.06, 196.35, 140.73, 185.39, 126.4, 187.08, 112.92, 199.72, 109.55, 208.99, 106.18, 216.57, 87.64, 220.79, 81.74, 219.1, 32.87, 230.06, 10.11, 247.75, 9.27, 257.87, 10.11, 278.09, 37.08, 288.2, 61.52, 287.36, 80.9, 306.74, 86.8, 316.01, 138.2, 301.69, 128.93, 285.67, 123.88, 292.42, 141.57, 294.94, 166.01, 284.83, 172.75, 273.03, 161.8, 273.88, 156.74, 258.71, 152.53, 251.12, 144.94, 230.06, 142.42, 210.67, 161.8, 203.93, 172.75, 214.89, 192.13, 237.64, 207.3, 241.01, 213.2, 221.63, 221.63, 213.2, 216.57, 172.75, 230.06, 185.39, 256.18, 186.24, 292.42, 195.51, 318.54, 203.09, 330.34, 183.71, 349.72, 166.01, 364.89, 146.63, 367.42, 142.42, 358.15, 160.11, 342.13, 169.38, 328.65, 166.85, 299.16, 152.53, 269.66, 139.04, 231.74, 123.88, 241.85, 118.82, 262.92, 102.81, 280.62, 85.11, 294.1, 75.0, 307.58, 80.9, 321.91, 71.63, 341.29, 64.89, 354.78, 46.35, 355.62]], "area": 25268.733299999993, "iscrowd": 0, "image_id": 386211, "bbox": [43.82, 9.27, 272.19, 359.83], "category_id": 1, "id": 490212, "split": "val", "sentences": [{"tokens": ["the", "girl", "sitting", "on", "the", "bench"], "raw": "The girl sitting on the bench.", "sent_id": 94352, "sent": "the girl sitting on the bench"}, {"tokens": ["the", "woman", "in", "black", "sitting", "on", "the", "bench"], "raw": "the woman in black sitting on the bench", "sent_id": 94353, "sent": "the woman in black sitting on the bench"}], "file_name": "COCO_train2014_000000386211_490212.jpg", "ann_id": 490212, "sent_ids": [94352, 94353], "ref_id": 41281}, {"segmentation": [[265.36, 310.03, 282.38, 288.65, 297.65, 272.07, 305.94, 264.65, 312.49, 276.43, 319.47, 280.8, 331.69, 286.9, 335.18, 296.07, 346.09, 301.31, 350.89, 301.31, 357.87, 294.76, 367.47, 289.96, 377.07, 288.65, 386.24, 299.56, 391.48, 298.69, 394.09, 294.76, 398.02, 294.76, 402.82, 302.18, 402.82, 304.8, 399.33, 317.02, 393.66, 329.0, 366.6, 329.0, 295.9, 329.0, 269.72, 329.0, 254.45, 329.0, 244.41, 329.0, 227.39, 325.74, 247.9, 316.14]], "area": 5740.281650000002, "iscrowd": 0, "image_id": 177019, "bbox": [227.39, 264.65, 175.43, 64.35], "category_id": 4, "id": 1789606, "split": "val", "sentences": [{"tokens": ["the", "control", "panel", "of", "a", "motorcycle"], "raw": "The control panel of a motorcycle.", "sent_id": 94389, "sent": "the control panel of a motorcycle"}], "file_name": "COCO_train2014_000000177019_1789606.jpg", "ann_id": 1789606, "sent_ids": [94389], "ref_id": 41300}, {"segmentation": [[251.12, 283.64, 238.41, 283.64, 235.69, 291.35, 231.15, 295.89, 203.47, 294.08, 197.57, 283.64, 194.84, 276.38, 190.76, 271.84, 185.77, 260.95, 185.31, 245.97, 187.58, 235.54, 191.67, 228.27, 203.01, 222.37, 217.99, 218.74, 234.33, 216.02, 242.04, 213.3, 250.66, 205.58, 268.36, 191.06, 280.61, 181.99, 295.14, 176.54, 321.46, 173.36, 335.98, 171.55, 337.34, 174.73, 331.89, 178.36, 331.89, 186.52, 312.83, 184.26, 298.31, 183.8, 284.24, 189.7, 273.35, 194.69, 262.92, 204.68, 254.75, 220.56, 249.3, 235.08, 247.94, 245.52, 247.03, 260.95, 247.94, 273.2, 250.21, 281.82], [347.78, 170.64, 362.3, 169.73, 362.3, 173.36, 349.14, 174.73, 347.32, 171.09], [384.54, 168.37, 402.23, 167.46, 397.7, 171.09, 384.08, 171.09, 384.08, 169.28], [412.67, 164.74, 419.48, 167.92, 467.58, 164.74, 479.84, 181.08, 478.47, 276.38, 468.04, 280.01, 464.41, 287.27, 455.33, 294.08, 458.05, 264.13, 457.6, 245.07, 454.42, 226.01, 448.52, 213.75, 439.9, 201.5, 432.19, 194.24, 423.11, 187.89, 414.03, 183.35]], "area": 9293.77275, "iscrowd": 0, "image_id": 19874, "bbox": [185.31, 164.74, 294.53, 131.15], "category_id": 3, "id": 1785837, "split": "val", "sentences": [{"tokens": ["the", "black", "car", "with", "one", "tire", "showing"], "raw": "The black car with one tire showing.", "sent_id": 94516, "sent": "the black car with one tire showing"}, {"tokens": ["black", "car", "that", "is", "behind", "the", "green", "car"], "raw": "Black car that is behind the green car.", "sent_id": 94517, "sent": "black car that is behind the green car"}], "file_name": "COCO_train2014_000000019874_1785837.jpg", "ann_id": 1785837, "sent_ids": [94516, 94517], "ref_id": 41352}, {"segmentation": [[444.01, 411.61, 459.25, 391.6, 452.58, 378.27, 463.07, 339.2, 460.21, 309.66, 458.3, 297.28, 468.78, 261.07, 482.12, 262.02, 476.4, 229.63, 488.79, 184.84, 489.74, 145.78, 486.89, 104.81, 474.5, 78.13, 456.4, 76.22, 459.25, 31.44, 445.91, 8.58, 411.61, 18.1, 404.94, 41.92, 417.33, 77.18, 392.56, 84.8, 390.65, 133.39, 343.01, 196.28, 364.93, 213.43, 398.27, 174.36, 375.41, 244.87, 373.5, 323.0, 389.7, 381.12, 363.02, 416.38, 391.6, 417.33, 416.38, 402.09, 402.09, 314.43, 419.24, 265.83, 429.72, 300.13, 438.29, 367.78, 417.33, 409.71]], "area": 31797.931350000003, "iscrowd": 0, "image_id": 360570, "bbox": [343.01, 8.58, 146.73, 408.75], "category_id": 1, "id": 220430, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "pink", "and", "black", "hair", "walking", "a", "dog"], "raw": "A woman with pink and black hair walking a dog.", "sent_id": 94539, "sent": "a woman with pink and black hair walking a dog"}, {"tokens": ["s", "woman", "walking", "her", "dog", "on", "sidewalk"], "raw": "s woman walking her dog on sidewalk", "sent_id": 94540, "sent": "s woman walking her dog on sidewalk"}], "file_name": "COCO_train2014_000000360570_220430.jpg", "ann_id": 220430, "sent_ids": [94539, 94540], "ref_id": 41361}, {"segmentation": [[491.1, 1.02, 534.18, 2.94, 558.11, 19.21, 561.94, 37.4, 569.6, 70.9, 568.64, 120.68, 558.11, 188.65, 555.24, 233.65, 554.28, 241.3, 500.67, 200.14, 490.14, 138.87, 494.93, 97.71]], "area": 14921.182750000004, "iscrowd": 0, "image_id": 555794, "bbox": [490.14, 1.02, 79.46, 240.28], "category_id": 1, "id": 488824, "split": "val", "sentences": [{"tokens": ["the", "standing", "surveyor"], "raw": "The standing surveyor", "sent_id": 94547, "sent": "the standing surveyor"}, {"tokens": ["blue", "colour", "dressed", "lady", "standing", "and", "watching"], "raw": "blue colour dressed lady standing and watching", "sent_id": 94548, "sent": "blue colour dressed lady standing and watching"}], "file_name": "COCO_train2014_000000555794_488824.jpg", "ann_id": 488824, "sent_ids": [94547, 94548], "ref_id": 41362}, {"segmentation": [[8.99, 414.26, 4.49, 380.56, 15.73, 346.85, 23.6, 298.53, 34.83, 260.33, 56.18, 234.49, 96.63, 206.4, 137.08, 189.54, 131.46, 173.81, 116.85, 151.34, 113.48, 141.23, 108.99, 126.62, 113.48, 121.0, 113.48, 121.0, 102.25, 83.93, 102.25, 58.08, 132.58, 32.24, 143.82, 34.49, 159.55, 31.12, 179.78, 31.12, 195.51, 45.72, 196.63, 65.95, 211.24, 95.16, 225.84, 104.15, 220.22, 142.35, 220.22, 153.59, 216.85, 147.97, 213.48, 158.08, 210.11, 172.69, 217.98, 189.54, 239.33, 204.15, 292.13, 222.13, 320.22, 250.22, 332.58, 292.92, 341.57, 323.25, 344.94, 346.85, 357.3, 378.31, 359.55, 403.03, 353.93, 407.52, 368.54, 408.65, 373.03, 419.88, 346.07, 423.25, 340.45, 458.08, 325.84, 473.81, 315.73, 473.81, 294.38, 473.81, 287.64, 489.54, 76.4, 491.79, 64.04, 470.44, 52.81, 467.07, 33.71, 467.07, 22.47, 452.47, 15.73, 440.11, 0.0, 428.87, 11.24, 427.75]], "area": 103034.48060000001, "iscrowd": 0, "image_id": 370727, "bbox": [0.0, 31.12, 373.03, 460.67], "category_id": 1, "id": 448334, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "red", "holding", "a", "coke", "and", "hot", "dog"], "raw": "A man in red holding a coke and hot dog.", "sent_id": 94668, "sent": "a man in red holding a coke and hot dog"}, {"tokens": ["the", "image", "of", "the", "man", "holding", "the", "food", "and", "drink", ",", "including", "the", "background", "up", "to", "the", "top", "of", "his", "head"], "raw": "The image of the man holding the food and drink, including the background up to the top of his head.", "sent_id": 94669, "sent": "the image of the man holding the food and drink , including the background up to the top of his head"}], "file_name": "COCO_train2014_000000370727_448334.jpg", "ann_id": 448334, "sent_ids": [94668, 94669], "ref_id": 41401}, {"segmentation": [[0.01, 302.99, 69.14, 301.7, 68.93, 328.33, 69.14, 369.55, 69.14, 372.98, 69.14, 399.61, 87.82, 399.82, 86.96, 324.46, 86.32, 300.84, 210.63, 299.13, 211.28, 299.13, 217.72, 288.6, 222.87, 280.45, 220.08, 281.3, 180.15, 279.16, 141.5, 274.43, 123.68, 269.93, 116.16, 273.36, 101.35, 272.07, 84.82, 271.21, 78.81, 267.56, 71.72, 268.85, 67.43, 275.29, 67.43, 277.01, 61.41, 277.65, 57.98, 271.43, 59.91, 263.7, 55.62, 266.49, 51.75, 270.35, 46.6, 272.29, 43.81, 270.78, 43.59, 265.85, 46.17, 261.55, 49.82, 257.69, 43.38, 259.19, 40.37, 259.19, 38.66, 254.9, 39.08, 251.46, 44.45, 241.37, 42.95, 238.15, 42.52, 233.85, 46.17, 227.84, 46.38, 222.69, 55.62, 214.1, 60.56, 210.88, 73.22, 211.53, 85.89, 214.32, 85.68, 201.65, 82.46, 194.99, 81.81, 191.99, 51.11, 191.99, 50.25, 193.06, 50.68, 194.35, 46.81, 201.86, 46.81, 218.61, 32.86, 218.83, 30.07, 220.33, 15.25, 216.89, 0.0, 212.38]], "area": 10757.024299999995, "iscrowd": 0, "image_id": 408266, "bbox": [0.0, 191.99, 222.87, 207.83], "category_id": 67, "id": 1621530, "split": "val", "sentences": [{"tokens": ["the", "table", "which", "is", "behind", "the", "boy"], "raw": "the table which is behind the boy", "sent_id": 94672, "sent": "the table which is behind the boy"}, {"tokens": ["a", "table", "with", "a", "wooden", "top", "and", "metal", "legs"], "raw": "A table with a wooden top and metal legs.", "sent_id": 94673, "sent": "a table with a wooden top and metal legs"}], "file_name": "COCO_train2014_000000408266_1621530.jpg", "ann_id": 1621530, "sent_ids": [94672, 94673], "ref_id": 41403}, {"segmentation": [[316.24, 323.68, 355.67, 305.08, 348.98, 284.24, 368.32, 263.41, 373.53, 255.22, 403.29, 241.83, 427.85, 215.04, 448.68, 187.51, 450.92, 183.05, 443.48, 178.58, 420.41, 197.18, 400.32, 223.23, 370.55, 235.88, 348.23, 221.74, 322.19, 215.78, 290.19, 218.76, 276.8, 225.46, 271.59, 218.76, 269.36, 198.67, 259.69, 179.32, 253.73, 183.05, 253.73, 193.46, 240.34, 196.44, 229.18, 205.37, 221.74, 208.34, 221.74, 209.83, 206.86, 220.25, 217.27, 229.92, 227.69, 224.71, 235.13, 229.18, 241.08, 244.06, 247.04, 266.38, 244.06, 286.47, 226.95, 309.54, 212.81, 318.47, 232.15, 327.4, 269.36, 288.71, 279.03, 283.5, 312.52, 281.26, 321.45, 297.63, 305.82, 306.56, 296.15, 303.59, 295.4, 308.8, 308.05, 323.68]], "area": 13330.539800000002, "iscrowd": 0, "image_id": 82484, "bbox": [206.86, 178.58, 244.06, 148.82], "category_id": 17, "id": 48681, "split": "val", "sentences": [{"tokens": ["a", "white", "cat", "with", "grey", "patterns"], "raw": "A white cat with grey patterns.", "sent_id": 94688, "sent": "a white cat with grey patterns"}, {"tokens": ["gray", "and", "whit", "cat", "playing", "inside"], "raw": "Gray and whit cat playing inside.", "sent_id": 94689, "sent": "gray and whit cat playing inside"}], "file_name": "COCO_train2014_000000082484_48681.jpg", "ann_id": 48681, "sent_ids": [94688, 94689], "ref_id": 41408}, {"segmentation": [[335.64, 173.11, 376.03, 191.38, 399.11, 210.61, 413.54, 241.39, 413.54, 272.16, 395.26, 303.9, 368.34, 345.25, 351.99, 360.64, 311.59, 381.8, 283.7, 384.68, 247.16, 380.84, 215.42, 368.34, 191.38, 354.87, 166.38, 330.83, 148.1, 314.48, 137.52, 296.21, 131.75, 271.2, 134.64, 249.08, 148.1, 219.27, 173.11, 199.07, 196.19, 184.65, 232.73, 172.15, 270.24, 168.3, 309.67, 166.38, 336.6, 122.14, 341.41, 118.29, 347.18, 118.29, 355.83, 122.14, 359.68, 126.95, 357.76, 132.72]], "area": 48005.01535000001, "iscrowd": 0, "image_id": 103778, "bbox": [131.75, 118.29, 281.79, 266.39], "category_id": 51, "id": 716694, "split": "val", "sentences": [{"tokens": ["a", "bowl", "of", "some", "sticky", "food", "possibly", "applesauce"], "raw": "a bowl of some sticky food possibly applesauce.", "sent_id": 94858, "sent": "a bowl of some sticky food possibly applesauce"}, {"tokens": ["bowl", "of", "food", "with", "white", "spoon", "in", "the", "bowl"], "raw": "Bowl of food with white spoon in the bowl.", "sent_id": 94859, "sent": "bowl of food with white spoon in the bowl"}], "file_name": "COCO_train2014_000000103778_716694.jpg", "ann_id": 716694, "sent_ids": [94858, 94859], "ref_id": 41475}, {"segmentation": [[4.31, 471.37, 17.26, 378.61, 25.89, 344.09, 71.19, 304.18, 67.96, 264.27, 98.16, 229.75, 78.74, 165.03, 84.13, 118.65, 85.21, 79.82, 97.08, 29.12, 124.04, 2.16, 272.9, 2.16, 294.47, 11.87, 326.83, 51.78, 357.03, 156.4, 352.72, 193.08, 399.1, 211.42, 424.99, 259.96, 448.72, 332.22, 455.19, 349.48, 482.16, 367.82, 518.83, 399.1, 531.78, 413.12, 557.66, 473.53]], "area": 164402.9496, "iscrowd": 0, "image_id": 407318, "bbox": [4.31, 2.16, 553.35, 471.37], "category_id": 1, "id": 461718, "split": "val", "sentences": [{"tokens": ["a", "woman", "eating", "food", "inside"], "raw": "A woman eating food inside.", "sent_id": 94868, "sent": "a woman eating food inside"}, {"tokens": ["dark", "haired", "girl", "with", "big", "eyes", "eating", "a", "donut", "with", "her", "left", "hand"], "raw": "Dark haired girl with big eyes eating a donut with her left hand.", "sent_id": 94869, "sent": "dark haired girl with big eyes eating a donut with her left hand"}], "file_name": "COCO_train2014_000000407318_461718.jpg", "ann_id": 461718, "sent_ids": [94868, 94869], "ref_id": 41478}, {"segmentation": [[398.33, 364.17, 343.33, 337.5, 331.67, 362.5, 330.0, 415.83, 340.0, 450.83, 356.67, 474.17, 366.67, 502.5, 371.67, 505.83, 435.0, 470.83, 436.67, 427.5, 425.0, 385.83], [305.0, 335.83, 250.0, 345.83, 215.0, 372.5, 205.0, 400.83, 196.67, 442.5, 201.67, 479.17, 275.0, 509.17, 298.33, 469.17, 301.67, 439.17, 305.0, 397.5]], "area": 26517.969450000004, "iscrowd": 0, "image_id": 143334, "bbox": [196.67, 335.83, 240.0, 173.34], "category_id": 47, "id": 1885686, "split": "val", "sentences": [{"tokens": ["cup"], "raw": "cup", "sent_id": 94899, "sent": "cup"}], "file_name": "COCO_train2014_000000143334_1885686.jpg", "ann_id": 1885686, "sent_ids": [94899], "ref_id": 41490}, {"segmentation": [[412.06, 74.12, 421.76, 99.71, 412.06, 112.06, 500.0, 157.94, 500.0, 225.88, 470.29, 187.94, 425.29, 182.65, 415.59, 195.88, 432.35, 207.35, 429.71, 229.41, 420.0, 219.71, 369.71, 197.65, 338.82, 183.53, 319.41, 151.76, 320.29, 150.0, 334.41, 126.18, 334.41, 126.18, 334.41, 83.82, 366.18, 57.35, 397.06, 62.65, 400.59, 64.41, 403.24, 65.29]], "area": 16458.5136, "iscrowd": 0, "image_id": 192891, "bbox": [319.41, 57.35, 180.59, 172.06], "category_id": 56, "id": 1056881, "split": "val", "sentences": [{"tokens": ["a", "blurry", "looking", "piece", "of", "broccoli", "sitting", "on", "a", "plate", "of", "other", "food"], "raw": "A blurry looking piece of broccoli sitting on a plate of other food.", "sent_id": 94905, "sent": "a blurry looking piece of broccoli sitting on a plate of other food"}, {"tokens": ["broccoli", "on", "a", "table", "plate", "to", "potatoes"], "raw": "Broccoli on a table plate to potatoes", "sent_id": 94906, "sent": "broccoli on a table plate to potatoes"}], "file_name": "COCO_train2014_000000192891_1056881.jpg", "ann_id": 1056881, "sent_ids": [94905, 94906], "ref_id": 41493}, {"segmentation": [[92.04, 205.66, 69.03, 185.53, 77.66, 174.02, 92.04, 163.96, 106.43, 149.57, 120.81, 136.63, 128.0, 123.69, 126.56, 109.3, 116.49, 97.8, 107.87, 90.61, 96.36, 89.17, 67.6, 84.85, 44.58, 84.85, 28.76, 93.48, 21.57, 93.48, 21.57, 77.66, 25.89, 64.72, 28.76, 38.83, 33.08, 23.01, 33.08, 8.63, 37.39, 0.0, 84.85, 1.44, 120.81, 1.44, 143.82, 0.0, 151.01, 8.63, 163.96, 40.27, 174.02, 61.84, 191.28, 63.28, 195.6, 71.91, 176.9, 93.48, 188.4, 133.75, 212.85, 159.64, 155.33, 169.71, 138.07, 189.84, 103.55, 205.66]], "area": 20342.918949999996, "iscrowd": 0, "image_id": 566301, "bbox": [21.57, 0.0, 191.28, 205.66], "category_id": 1, "id": 1262110, "split": "val", "sentences": [{"tokens": ["the", "person", "wearing", "all", "black", "that", "has", "a", "large", "blue", "ring", "on"], "raw": "The person wearing all black that has a large blue ring on.", "sent_id": 94915, "sent": "the person wearing all black that has a large blue ring on"}, {"tokens": ["a", "person", "in", "the", "background", "wearing", "a", "ring", "and", "on", "a", "phone"], "raw": "A person in the background wearing a ring and on a phone.", "sent_id": 94916, "sent": "a person in the background wearing a ring and on a phone"}], "file_name": "COCO_train2014_000000566301_1262110.jpg", "ann_id": 1262110, "sent_ids": [94915, 94916], "ref_id": 41496}, {"segmentation": [[266.15, 73.35, 270.74, 66.18, 273.61, 61.02, 274.47, 57.29, 275.04, 52.13, 274.75, 44.68, 273.61, 40.66, 276.47, 38.66, 281.35, 38.66, 285.08, 38.37, 290.81, 38.66, 289.95, 26.33, 289.66, 18.59, 296.26, 13.14, 298.84, 12.57, 300.56, 14.29, 300.56, 18.3, 300.56, 23.46, 301.99, 28.91, 304.57, 32.92, 310.31, 35.79, 316.62, 36.36, 318.62, 38.37, 324.07, 38.94, 332.1, 37.51, 334.97, 37.22, 330.95, 43.53, 327.51, 48.41, 329.23, 50.41, 341.27, 62.17, 349.3, 69.91, 353.6, 75.93, 356.18, 80.23, 374.25, 96.0, 396.61, 110.62, 431.02, 123.53, 447.36, 130.12, 476.32, 143.33, 478.49, 146.58, 508.87, 149.84, 538.17, 162.86, 554.44, 180.22, 559.87, 191.07, 560.95, 199.75, 539.25, 201.92, 409.05, 227.96, 391.69, 222.53, 387.35, 207.34, 394.94, 192.15, 401.45, 180.22, 389.52, 160.69, 379.75, 143.33, 379.75, 121.63, 375.41, 114.03, 372.16, 111.86, 373.24, 98.84, 365.65, 93.42, 353.71, 105.35, 345.03, 103.18, 329.84, 105.35, 326.59, 103.18, 317.91, 89.08, 311.4, 77.14, 285.36, 84.74, 270.17, 97.76, 258.23, 99.93, 253.89, 94.5, 258.23, 80.4, 259.32, 76.06]], "area": 17566.607399999997, "iscrowd": 0, "image_id": 177353, "bbox": [253.89, 12.57, 307.06, 215.39], "category_id": 25, "id": 601155, "split": "val", "sentences": [{"tokens": ["a", "graiffe", "on", "the", "right", "side", "of", "the", "jeep", "standing", "the", "closest"], "raw": "A graiffe on the right side of the jeep standing the closest", "sent_id": 94970, "sent": "a graiffe on the right side of the jeep standing the closest"}], "file_name": "COCO_train2014_000000177353_601155.jpg", "ann_id": 601155, "sent_ids": [94970], "ref_id": 41520}, {"segmentation": [[235.44, 199.89, 264.87, 168.0, 257.51, 120.18, 231.76, 79.71, 203.56, 71.13, 198.65, 65.0, 209.69, 28.21, 196.2, 4.91, 172.9, 8.59, 153.28, 24.53, 150.83, 41.7, 155.73, 62.55, 155.73, 72.36, 137.34, 77.26, 122.63, 89.52, 112.82, 115.28, 115.27, 160.65, 136.11, 180.27, 139.79, 183.95, 126.3, 203.57, 137.34, 279.59, 139.79, 327.42, 125.08, 334.78, 127.53, 351.94, 133.66, 361.75, 142.25, 356.85, 159.41, 344.59, 237.89, 240.35, 235.44, 230.54, 240.35, 213.38, 234.22, 201.11], [232.99, 262.43, 235.44, 414.48, 245.25, 431.65, 250.16, 439.0, 217.05, 439.0, 199.88, 435.33, 196.2, 431.65, 185.16, 436.55, 148.38, 439.0, 149.6, 424.29, 165.54, 413.26, 158.19, 385.05, 181.49, 372.79, 185.16, 354.4, 170.45, 348.26, 232.99, 261.2]], "area": 39847.66814999998, "iscrowd": 0, "image_id": 222977, "bbox": [112.82, 4.91, 152.05, 434.09], "category_id": 1, "id": 490735, "split": "val", "sentences": [{"tokens": ["the", "man", "wearing", "black", "shirt", "and", "with", "a", "letters", "nh"], "raw": "The man wearing black shirt and with a letters NH", "sent_id": 94973, "sent": "the man wearing black shirt and with a letters nh"}, {"tokens": ["a", "man", "having", "nh", "letters", "on", "his", "tea", "shirt"], "raw": "A man having NH letters on his tea shirt", "sent_id": 94974, "sent": "a man having nh letters on his tea shirt"}], "file_name": "COCO_train2014_000000222977_490735.jpg", "ann_id": 490735, "sent_ids": [94973, 94974], "ref_id": 41521}, {"segmentation": [[423.0, 539.41, 435.68, 544.35, 451.88, 538.01, 456.81, 527.44, 456.11, 514.76, 449.77, 497.85, 430.04, 468.97, 415.95, 457.69, 405.39, 452.06, 393.41, 449.94, 379.32, 452.06, 375.09, 459.81, 374.39, 471.78, 377.91, 479.53, 389.18, 485.17, 401.86, 495.03, 414.54, 511.94, 420.18, 528.14], [250.4, 530.96, 234.9, 533.07, 241.24, 521.1, 246.17, 524.62], [215.59, 511.97, 220.71, 509.61, 228.58, 506.46, 232.91, 505.68, 239.99, 515.12, 236.84, 521.02, 233.3, 526.93, 228.97, 532.04, 225.82, 534.8, 220.31, 535.59, 210.48, 534.8, 211.66, 527.71]], "area": 4630.994399999998, "iscrowd": 0, "image_id": 107425, "bbox": [210.48, 449.94, 246.33, 94.41], "category_id": 2, "id": 128414, "split": "val", "sentences": [{"tokens": ["cycle", "fell", "down", "in", "a", "floor"], "raw": "cycle fell down in a floor", "sent_id": 95219, "sent": "cycle fell down in a floor"}, {"tokens": ["the", "blue", "bicycle", "is", "laying", "on", "the", "ground", "next", "to", "the", "white", "bike", "that", "is", "standing", "up"], "raw": "The blue bicycle is laying on the ground next to the white bike that is standing up.", "sent_id": 95220, "sent": "the blue bicycle is laying on the ground next to the white bike that is standing up"}], "file_name": "COCO_train2014_000000107425_128414.jpg", "ann_id": 128414, "sent_ids": [95219, 95220], "ref_id": 41614}, {"segmentation": [[220.04, 188.76, 236.22, 186.61, 250.25, 187.69, 252.4, 184.45, 257.8, 184.45, 257.8, 208.18, 263.19, 207.1, 279.37, 209.26, 285.84, 213.57, 298.79, 216.81, 323.6, 218.97, 339.78, 218.97, 346.25, 221.12, 360.27, 224.36, 381.84, 228.67, 324.67, 252.4, 259.96, 276.13, 228.67, 266.43], [324.67, 264.27, 361.35, 248.09, 358.11, 284.76, 326.83, 306.34]], "area": 8550.211700000002, "iscrowd": 0, "image_id": 392098, "bbox": [220.04, 184.45, 161.8, 121.89], "category_id": 65, "id": 318258, "split": "val", "sentences": [{"tokens": ["bed", "furthest", "away", "with", "red", "decorated", "blanket", "and", "wooden", "head", "board"], "raw": "Bed furthest away with red decorated blanket and wooden head board.", "sent_id": 95221, "sent": "bed furthest away with red decorated blanket and wooden head board"}, {"tokens": ["bed", "close", "to", "window", "with", "dark", "red", "sheets"], "raw": "Bed close to window with dark red sheets", "sent_id": 95222, "sent": "bed close to window with dark red sheets"}], "file_name": "COCO_train2014_000000392098_318258.jpg", "ann_id": 318258, "sent_ids": [95221, 95222], "ref_id": 41615}, {"segmentation": [[0.0, 497.85, 259.41, 499.2, 216.13, 264.52, 177.42, 270.97, 160.22, 276.34, 151.61, 282.8, 120.43, 286.02, 93.55, 278.49, 126.88, 238.71, 97.85, 231.18, 79.57, 226.88, 43.01, 233.33, 0.53, 228.5]], "area": 58059.8041, "iscrowd": 0, "image_id": 475980, "bbox": [0.0, 226.88, 259.41, 272.32], "category_id": 63, "id": 115697, "split": "val", "sentences": [{"tokens": ["burlap", "fabric", "to", "the", "left", "of", "cat"], "raw": "Burlap fabric to the left of cat.", "sent_id": 95223, "sent": "burlap fabric to the left of cat"}, {"tokens": ["a", "brown", "sofa", "holds", "a", "cat"], "raw": "A brown sofa holds a cat.", "sent_id": 95224, "sent": "a brown sofa holds a cat"}], "file_name": "COCO_train2014_000000475980_115697.jpg", "ann_id": 115697, "sent_ids": [95223, 95224], "ref_id": 41616}, {"segmentation": [[197.12, 215.92, 194.31, 197.63, 195.72, 184.97, 190.09, 179.34, 206.97, 118.85, 226.67, 106.18, 250.58, 103.37, 270.28, 109.0, 287.16, 124.47, 294.19, 146.98, 295.6, 170.9, 285.75, 187.78, 278.72, 207.47, 302.64, 201.85, 337.81, 194.81, 318.11, 213.1, 301.23, 294.7, 299.82, 341.12, 311.08, 408.65, 315.3, 435.38, 278.72, 433.97, 257.62, 438.19, 250.58, 428.34, 221.04, 417.09, 187.28, 439.6, 128.19, 417.09, 129.6, 365.04, 115.53, 339.71, 125.38, 298.92, 153.51, 273.59, 177.43, 235.61], [135.22, 505.72, 129.6, 563.4, 139.45, 601.38, 264.65, 592.94, 364.53, 564.8, 340.62, 536.67, 333.58, 501.5, 278.72, 509.94, 261.84, 515.57, 240.74, 500.09, 145.07, 509.94]], "area": 64037.680049999995, "iscrowd": 0, "image_id": 119714, "bbox": [115.53, 103.37, 249.0, 498.01], "category_id": 1, "id": 2156457, "split": "val", "sentences": [{"tokens": ["the", "boy", "in", "the", "black", "t", "-", "shirt"], "raw": "the boy in the black t-shirt.", "sent_id": 95225, "sent": "the boy in the black t - shirt"}, {"tokens": ["a", "boy", "with", "long", "hair", "wearing", "a", "black", "shirt"], "raw": "a boy with long hair wearing a black shirt", "sent_id": 95226, "sent": "a boy with long hair wearing a black shirt"}], "file_name": "COCO_train2014_000000119714_2156457.jpg", "ann_id": 2156457, "sent_ids": [95225, 95226], "ref_id": 41617}, {"segmentation": [[317.91, 246.16, 309.93, 256.01, 298.68, 281.33, 294.93, 308.06, 290.24, 316.98, 278.98, 349.8, 274.29, 370.9, 257.88, 416.39, 261.16, 417.33, 276.17, 366.68, 278.05, 357.3, 282.74, 358.71, 285.55, 347.46, 291.18, 316.98, 293.99, 313.69, 292.11, 331.04, 297.27, 312.75, 309.47, 282.74, 317.91, 263.05, 320.72, 261.17, 317.91, 251.79], [242.41, 461.41, 240.53, 466.1, 240.53, 470.79, 241.94, 482.52, 243.81, 495.18, 245.69, 495.18, 258.35, 482.98, 262.57, 477.36, 267.26, 462.82, 253.19, 466.1, 244.75, 461.88]], "area": 1402.0934500000017, "iscrowd": 0, "image_id": 204294, "bbox": [240.53, 246.16, 80.19, 249.02], "category_id": 32, "id": 296505, "split": "val", "sentences": [{"tokens": ["blue", "striped", "tie", "worn", "by", "man", "with", "microphone", "and", "notepad"], "raw": "Blue striped tie worn by man with microphone and notepad.", "sent_id": 95245, "sent": "blue striped tie worn by man with microphone and notepad"}], "file_name": "COCO_train2014_000000204294_296505.jpg", "ann_id": 296505, "sent_ids": [95245], "ref_id": 41624}, {"segmentation": [[248.63, 180.39, 304.63, 205.77, 318.81, 211.75, 359.88, 225.19, 356.15, 194.57, 350.92, 172.17, 342.71, 149.78, 335.99, 138.58, 328.52, 131.86, 329.27, 113.94, 327.03, 105.72, 317.32, 99.75, 310.6, 96.76, 303.13, 97.51, 294.17, 103.48, 291.19, 134.84, 277.75, 143.06, 272.52, 137.08, 270.28, 135.59, 259.83, 132.6, 253.86, 134.84, 249.38, 137.83, 247.88, 151.27, 248.63, 159.48, 244.9, 168.44, 244.15, 173.67, 246.39, 180.39]], "area": 8154.627899999998, "iscrowd": 0, "image_id": 540211, "bbox": [244.15, 96.76, 115.73, 128.43], "category_id": 1, "id": 203854, "split": "val", "sentences": [{"tokens": ["older", "fat", "man"], "raw": "older fat man", "sent_id": 95313, "sent": "older fat man"}, {"tokens": ["old", "fat", "man"], "raw": "old fat man", "sent_id": 95314, "sent": "old fat man"}], "file_name": "COCO_train2014_000000540211_203854.jpg", "ann_id": 203854, "sent_ids": [95313, 95314], "ref_id": 41649}, {"segmentation": [[129.2, 313.09, 120.35, 336.92, 116.95, 358.71, 112.86, 368.24, 100.61, 373.01, 100.61, 366.2, 106.74, 343.73, 108.78, 321.26, 95.16, 323.99, 88.35, 321.26, 84.27, 331.48, 80.18, 347.82, 80.18, 359.39, 73.38, 371.65, 65.89, 371.65, 68.61, 351.9, 75.42, 339.65, 74.06, 331.48, 76.1, 314.46, 76.1, 306.97, 68.61, 305.61, 54.31, 305.61, 54.31, 296.07, 49.55, 283.82, 49.55, 279.05, 42.74, 278.37, 36.61, 273.61, 36.61, 267.48, 49.55, 266.12, 61.12, 261.35, 71.33, 260.67, 113.55, 247.05, 146.23, 244.33, 174.14, 241.61, 181.63, 239.56, 180.27, 255.9, 172.78, 257.27, 171.42, 270.88, 176.18, 287.22, 174.82, 300.16, 178.91, 307.65, 173.46, 312.41, 178.91, 323.99, 184.35, 334.2, 175.5, 355.99, 168.01, 365.52, 160.52, 364.84, 169.37, 334.88, 170.74, 322.63, 164.61, 299.48, 153.03, 303.56, 132.61, 306.97], [185.71, 240.25, 197.29, 244.33, 206.82, 256.59, 201.37, 254.54, 197.29, 259.31, 191.16, 255.9, 185.03, 257.95]], "area": 9884.715649999996, "iscrowd": 0, "image_id": 189836, "bbox": [36.61, 239.56, 170.21, 133.45], "category_id": 21, "id": 2191523, "split": "val", "sentences": [{"tokens": ["a", "white", "and", "brown", "cow", "standing", "slightly", "behind", "a", "fence"], "raw": "A white and brown cow standing slightly behind a fence.", "sent_id": 95327, "sent": "a white and brown cow standing slightly behind a fence"}, {"tokens": ["a", "cow", "eating", "grass"], "raw": "a cow eating grass", "sent_id": 95328, "sent": "a cow eating grass"}], "file_name": "COCO_train2014_000000189836_2191523.jpg", "ann_id": 2191523, "sent_ids": [95327, 95328], "ref_id": 41655}, {"segmentation": [[179.58, 376.56, 500.59, 381.05, 508.45, 393.4, 511.81, 421.46, 163.87, 424.83, 167.24, 386.67], [85.3, 378.81, 148.16, 383.3, 150.4, 418.09, 144.79, 425.95, 80.81, 423.7], [534.26, 385.54, 592.63, 384.42, 592.63, 424.83, 526.4, 425.95]], "area": 20548.486399999987, "iscrowd": 0, "image_id": 189330, "bbox": [80.81, 376.56, 511.82, 49.39], "category_id": 15, "id": 1810426, "split": "val", "sentences": [{"tokens": ["nearest", "bench"], "raw": "Nearest bench.", "sent_id": 95428, "sent": "nearest bench"}], "file_name": "COCO_train2014_000000189330_1810426.jpg", "ann_id": 1810426, "sent_ids": [95428], "ref_id": 41690}, {"segmentation": [[403.01, 346.4, 403.01, 264.84, 397.25, 223.58, 391.5, 176.56, 416.44, 135.3, 423.16, 61.41, 423.16, 36.46, 423.16, 21.11, 406.85, 3.84, 453.87, 0.0, 453.87, 8.64, 442.35, 20.15, 443.31, 97.87, 462.5, 177.52, 471.14, 215.9, 445.23, 265.8, 446.19, 355.99, 427.0, 362.71, 424.12, 334.88, 426.04, 254.28, 425.08, 232.21, 417.4, 258.12, 415.49, 352.16]], "area": 14222.681499999999, "iscrowd": 0, "image_id": 7393, "bbox": [391.5, 0.0, 79.64, 362.71], "category_id": 25, "id": 595444, "split": "val", "sentences": [{"tokens": ["the", "back", "profile", "of", "a", "giraffe"], "raw": "the back profile of a giraffe", "sent_id": 95466, "sent": "the back profile of a giraffe"}, {"tokens": ["giaraafe", "standing", "tall"], "raw": "giaraafe standing tall", "sent_id": 95467, "sent": "giaraafe standing tall"}], "file_name": "COCO_train2014_000000007393_595444.jpg", "ann_id": 595444, "sent_ids": [95466, 95467], "ref_id": 41706}, {"segmentation": [[190.7, 233.77, 69.35, 229.44, 123.52, 143.84, 100.77, 8.4, 315.3, 8.4, 319.64, 146.0, 183.12, 147.09, 192.87, 233.77]], "area": 36246.51975, "iscrowd": 0, "image_id": 344073, "bbox": [69.35, 8.4, 250.29, 225.37], "category_id": 73, "id": 1104230, "split": "val", "sentences": [{"tokens": ["the", "laptop", "in", "the", "back", "to", "the", "left"], "raw": "The laptop in the back to the left.", "sent_id": 95525, "sent": "the laptop in the back to the left"}, {"tokens": ["the", "computer", "on", "the", "back", "left"], "raw": "The computer on the back left.", "sent_id": 95526, "sent": "the computer on the back left"}], "file_name": "COCO_train2014_000000344073_1104230.jpg", "ann_id": 1104230, "sent_ids": [95525, 95526], "ref_id": 41732}, {"segmentation": [[208.97, 404.19, 229.5, 400.09, 243.87, 393.93, 231.55, 379.56, 231.55, 360.05, 232.58, 337.47, 245.92, 329.26, 273.64, 327.2, 293.14, 341.57, 293.14, 356.97, 292.12, 369.29, 290.06, 376.48, 282.88, 390.85, 279.8, 398.03, 273.64, 412.41, 299.3, 429.86, 308.54, 440.12, 309.57, 487.34, 317.78, 524.3, 315.73, 577.68, 302.38, 594.1, 304.44, 636.19, 273.64, 636.19, 229.5, 638.25, 217.18, 599.24, 212.05, 541.75, 206.91, 464.76, 207.94, 450.39, 204.86, 429.86]], "area": 26238.724049999997, "iscrowd": 0, "image_id": 205000, "bbox": [204.86, 327.2, 112.92, 311.05], "category_id": 1, "id": 446511, "split": "val", "sentences": [{"tokens": ["the", "reflection", "of", "a", "young", "woman", "in", "a", "green", "sweater", "in", "a", "mirror"], "raw": "The reflection of a young woman in a green sweater in a mirror.", "sent_id": 95542, "sent": "the reflection of a young woman in a green sweater in a mirror"}, {"tokens": ["a", "lady", "'", "s", "reflection", "in", "the", "mirror"], "raw": "A lady's reflection in the mirror", "sent_id": 95543, "sent": "a lady ' s reflection in the mirror"}], "file_name": "COCO_train2014_000000205000_446511.jpg", "ann_id": 446511, "sent_ids": [95542, 95543], "ref_id": 41741}, {"segmentation": [[250.25, 269.35, 219.98, 274.16, 219.5, 302.5, 221.9, 303.46, 214.7, 307.3, 216.62, 319.79, 221.9, 321.71, 216.62, 332.76, 221.9, 334.68, 236.32, 331.8, 237.76, 343.81, 244.48, 355.34, 253.13, 363.5, 262.26, 366.87, 273.78, 366.87, 289.64, 361.58, 301.65, 348.13, 366.02, 334.2, 357.85, 304.9, 368.42, 264.07, 372.74, 263.11, 371.3, 253.02, 377.54, 236.21, 377.54, 234.28, 368.42, 240.53, 360.73, 239.09, 358.33, 241.49, 367.46, 243.89, 372.26, 241.97, 370.34, 248.22, 365.05, 246.77, 348.72, 255.9, 333.35, 269.35, 322.78, 265.03, 305.97, 261.67, 300.2, 267.91, 276.19, 265.99, 249.77, 270.31], [422.22, 276.08, 412.13, 300.1, 409.25, 333.72, 419.82, 339.97, 433.27, 338.05, 444.8, 325.08, 445.28, 301.54, 434.23, 284.72, 438.07, 284.24, 429.42, 278.48, 422.22, 276.56], [344.88, 235.25, 348.72, 244.37, 336.71, 256.86, 328.07, 253.02, 342.96, 238.61, 333.35, 240.05, 327.11, 242.45, 323.26, 241.49, 323.74, 233.8, 327.11, 232.84, 334.31, 232.84, 336.23, 237.17]], "area": 14217.481399999995, "iscrowd": 0, "image_id": 274547, "bbox": [214.7, 232.84, 230.58, 134.03], "category_id": 4, "id": 152090, "split": "val", "sentences": [{"tokens": ["a", "motorcycle", "on", "a", "brick", "street"], "raw": "A motorcycle on a brick street.", "sent_id": 95590, "sent": "a motorcycle on a brick street"}, {"tokens": ["a", "white", "color", "big", "bike", "with", "helmet", "on", "his", "seat"], "raw": "A WHITE COLOR BIG BIKE WITH HELMET ON HIS SEAT", "sent_id": 95591, "sent": "a white color big bike with helmet on his seat"}], "file_name": "COCO_train2014_000000274547_152090.jpg", "ann_id": 152090, "sent_ids": [95590, 95591], "ref_id": 41758}, {"segmentation": [[273.1, 226.52, 296.0, 249.42, 318.9, 260.16, 367.57, 270.9, 434.85, 260.16, 456.32, 237.97, 464.91, 224.37, 460.61, 198.61, 441.29, 177.85, 407.65, 159.25, 374.01, 150.66, 328.21, 149.94, 299.58, 157.1, 278.82, 164.26, 265.23, 182.15, 263.08, 189.31, 263.79, 213.64]], "area": 18800.946750000003, "iscrowd": 0, "image_id": 444344, "bbox": [263.08, 149.94, 201.83, 120.96], "category_id": 59, "id": 1071649, "split": "val", "sentences": [{"tokens": ["a", "pizza", "with", "black", "olives"], "raw": "a pizza with black olives", "sent_id": 95656, "sent": "a pizza with black olives"}, {"tokens": ["pizza", "with", "black", "olives", "and", "pepperonis"], "raw": "pizza with black olives and pepperonis", "sent_id": 95657, "sent": "pizza with black olives and pepperonis"}], "file_name": "COCO_train2014_000000444344_1071649.jpg", "ann_id": 1071649, "sent_ids": [95656, 95657], "ref_id": 41784}, {"segmentation": [[486.44, 170.04, 473.13, 167.15, 465.04, 171.78, 460.41, 183.93, 452.31, 183.93, 422.23, 203.59, 396.78, 229.05, 397.36, 240.04, 416.45, 282.84, 409.5, 295.57, 395.62, 312.34, 384.63, 326.8, 407.19, 334.9, 415.87, 315.81, 427.44, 303.67, 434.38, 296.15, 431.49, 260.28, 426.86, 245.82, 443.05, 224.42, 450.0, 229.63, 453.47, 251.61, 459.25, 269.54, 464.46, 274.17, 467.35, 266.65, 459.25, 255.66, 457.52, 231.94, 455.2, 229.05, 463.88, 228.47, 473.13, 234.83, 479.5, 230.78, 476.6, 225.0, 466.77, 223.84, 456.36, 214.59, 466.19, 203.59, 469.08, 198.97, 477.18, 197.81, 482.97, 182.77, 485.28, 172.94]], "area": 5370.963099999999, "iscrowd": 0, "image_id": 513748, "bbox": [384.63, 167.15, 101.81, 167.75], "category_id": 1, "id": 436852, "split": "val", "sentences": [{"tokens": ["the", "person", "surfing"], "raw": "the person surfing", "sent_id": 95674, "sent": "the person surfing"}], "file_name": "COCO_train2014_000000513748_436852.jpg", "ann_id": 436852, "sent_ids": [95674], "ref_id": 41789}, {"segmentation": [[62.96, 301.82, 60.83, 295.43, 54.44, 293.84, 51.78, 284.25, 53.91, 265.09, 65.09, 242.74, 66.15, 236.35, 63.49, 221.98, 60.83, 207.61, 56.57, 194.83, 53.38, 184.72, 52.84, 173.01, 50.71, 166.09, 49.12, 157.04, 49.12, 151.18, 54.97, 150.65, 57.1, 148.52, 58.17, 143.2, 58.17, 132.55, 58.17, 130.43, 59.23, 116.59, 52.84, 108.07, 51.25, 96.89, 48.59, 90.5, 45.92, 86.25, 47.52, 79.33, 48.59, 75.6, 52.31, 76.13, 52.84, 74.0, 50.71, 70.28, 40.07, 60.7, 27.83, 55.91, 17.71, 59.1, 10.79, 64.96, 7.07, 76.67, 7.07, 92.1, 0.0, 103.81, 1.21, 160.23, 8.13, 159.17, 8.66, 167.69, 3.87, 181.52, 3.87, 192.17, 7.07, 200.15, 14.52, 217.72, 15.05, 237.95, 11.86, 255.51, 12.39, 272.01, 13.99, 283.19, 12.39, 293.3, 15.05, 302.35, 16.12, 309.27, 17.71, 313.0, 43.8, 317.79, 55.51, 314.59, 57.63, 312.47, 56.57, 307.14, 57.1, 303.42, 61.89, 302.88]], "area": 12135.469150000003, "iscrowd": 0, "image_id": 360570, "bbox": [0.0, 55.91, 66.15, 261.88], "category_id": 1, "id": 225970, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "black", "baseball", "cap", ",", "tight", "jeans", ",", "black", "shirt", "and", "purple", "ugg", "boots"], "raw": "A woman in black baseball cap, tight jeans, black shirt and purple ugg boots.", "sent_id": 95688, "sent": "a woman in black baseball cap , tight jeans , black shirt and purple ugg boots"}, {"tokens": ["a", "woman", "in", "tight", "jeans", "leaning", "against", "a", "storefront"], "raw": "a woman in tight jeans leaning against a storefront", "sent_id": 95689, "sent": "a woman in tight jeans leaning against a storefront"}], "file_name": "COCO_train2014_000000360570_225970.jpg", "ann_id": 225970, "sent_ids": [95688, 95689], "ref_id": 41794}, {"segmentation": [[424.83, 80.66, 433.28, 85.73, 434.12, 94.17, 434.97, 98.4, 449.32, 111.06, 451.01, 125.42, 452.7, 137.25, 455.24, 147.38, 466.22, 176.1, 474.66, 203.13, 467.91, 205.66, 461.99, 201.44, 455.24, 177.79, 444.26, 163.43, 434.97, 175.25, 431.59, 177.79, 427.36, 171.88, 424.83, 165.12, 418.92, 160.9, 412.16, 162.58, 400.34, 177.79, 391.05, 197.21, 385.14, 203.97, 377.53, 198.06, 391.89, 165.96, 406.25, 140.63, 398.65, 122.04, 402.03, 110.22, 416.39, 104.31, 417.23, 96.71, 418.07, 83.19]], "area": 4612.699650000002, "iscrowd": 0, "image_id": 513124, "bbox": [377.53, 80.66, 97.13, 125.0], "category_id": 1, "id": 495142, "split": "val", "sentences": [{"tokens": ["player", "bent", "over"], "raw": "player bent over", "sent_id": 95750, "sent": "player bent over"}, {"tokens": ["a", "baseball", "player", "stands", "in", "the", "outfield"], "raw": "A baseball player stands in the outfield.", "sent_id": 95751, "sent": "a baseball player stands in the outfield"}], "file_name": "COCO_train2014_000000513124_495142.jpg", "ann_id": 495142, "sent_ids": [95750, 95751], "ref_id": 41824}, {"segmentation": [[381.86, 207.24, 455.74, 223.55, 508.51, 235.07, 572.8, 253.3, 585.27, 257.14, 576.64, 309.91, 508.51, 286.88, 360.76, 246.58, 382.82, 204.36]], "area": 10514.211049999998, "iscrowd": 0, "image_id": 561479, "bbox": [360.76, 204.36, 224.51, 105.55], "category_id": 76, "id": 1117651, "split": "val", "sentences": [{"tokens": ["a", "white", "keyboard", "beneath", "a", "monitor"], "raw": "A white keyboard beneath a monitor.", "sent_id": 95778, "sent": "a white keyboard beneath a monitor"}, {"tokens": ["a", "narrow", ",", "white", "keyboard", "in", "front", "of", "a", "white", "apple", "computer", "monitor"], "raw": "A narrow, white keyboard in front of a white Apple computer monitor.", "sent_id": 95779, "sent": "a narrow , white keyboard in front of a white apple computer monitor"}], "file_name": "COCO_train2014_000000561479_1117651.jpg", "ann_id": 1117651, "sent_ids": [95778, 95779], "ref_id": 41837}, {"segmentation": [[2.24, 44.85, 2.24, 29.19, 13.42, 22.48, 32.44, 22.48, 32.44, 31.43, 31.32, 44.85, 32.44, 59.39, 34.68, 70.58, 51.45, 73.93, 50.34, 88.47, 45.86, 92.95, 36.91, 98.54, 50.34, 111.96, 58.17, 124.27, 58.17, 161.18, 66.0, 177.96, 66.0, 190.26, 50.34, 190.26, 48.1, 189.15, 49.22, 158.94, 49.22, 138.81, 43.62, 128.74, 11.19, 111.96, 2.24, 110.85, 0.0, 45.97]], "area": 4530.5699, "iscrowd": 0, "image_id": 55412, "bbox": [0.0, 22.48, 66.0, 167.78], "category_id": 1, "id": 206951, "split": "val", "sentences": [{"tokens": ["a", "blurry", "pick", "of", "a", "man", "with", "yellow", "on", "the", "back", "of", "a", "bike"], "raw": "a blurry pick of a man with yellow on the back of a bike", "sent_id": 95799, "sent": "a blurry pick of a man with yellow on the back of a bike"}], "file_name": "COCO_train2014_000000055412_206951.jpg", "ann_id": 206951, "sent_ids": [95799], "ref_id": 41846}, {"segmentation": [[313.26, 265.27, 352.88, 263.98, 391.21, 264.63, 424.69, 267.64, 429.86, 268.5, 442.35, 294.56, 450.31, 293.69, 454.62, 302.58, 456.77, 321.53, 455.05, 324.32, 454.62, 327.34, 452.04, 331.21, 451.61, 336.81, 447.3, 341.12, 430.51, 344.25, 428.35, 347.26, 428.35, 355.66, 425.55, 355.87, 423.19, 347.91, 419.74, 347.26, 420.6, 356.52, 415.22, 365.35, 403.38, 370.51, 388.74, 370.73, 382.28, 364.7, 377.75, 360.82, 369.79, 355.66, 368.28, 351.57, 366.99, 347.04, 258.52, 346.61, 258.52, 337.79, 265.84, 331.97, 270.58, 324.44, 272.51, 317.76, 274.24, 316.04, 293.18, 296.76, 296.41, 304.95, 303.52, 310.76, 309.76, 314.85, 319.45, 312.48, 323.97, 308.39, 324.19, 300.21, 319.88, 293.97, 317.3, 288.58, 316.44, 281.69, 316.44, 273.73, 315.36, 268.77]], "area": 13378.114900000006, "iscrowd": 0, "image_id": 493760, "bbox": [258.52, 263.98, 198.25, 106.75], "category_id": 3, "id": 134470, "split": "val", "sentences": [{"tokens": ["a", "green", "suv"], "raw": "a green SUV", "sent_id": 95827, "sent": "a green suv"}, {"tokens": ["green", "suv", "behind", "the", "white", "horse"], "raw": "green suv behind the white horse.", "sent_id": 95828, "sent": "green suv behind the white horse"}], "file_name": "COCO_train2014_000000493760_134470.jpg", "ann_id": 134470, "sent_ids": [95827, 95828], "ref_id": 41858}, {"segmentation": [[184.0, 47.95, 190.4, 44.02, 199.74, 33.68, 212.57, 34.51, 216.99, 42.87, 219.45, 58.62, 225.85, 69.44, 238.15, 85.67, 241.59, 116.66, 242.57, 122.57, 237.66, 130.93, 234.21, 134.37, 237.16, 140.28, 235.69, 145.69, 231.75, 164.38, 232.24, 174.22, 235.69, 191.93, 240.12, 215.05, 236.18, 233.74, 236.18, 241.61, 240.12, 250.47, 206.66, 256.37, 204.7, 251.95, 207.16, 248.01, 216.5, 243.09, 220.93, 235.71, 221.91, 224.89, 216.5, 204.23, 210.6, 187.01, 210.11, 184.06, 204.7, 191.44, 200.76, 209.64, 201.74, 228.33, 199.78, 235.22, 204.2, 248.01, 196.82, 250.96, 180.1, 254.4, 172.23, 249.49, 180.1, 246.53, 185.02, 234.24, 178.62, 186.52, 179.61, 180.12, 205.19, 180.12, 207.16, 174.22, 206.66, 147.66, 199.78, 147.16, 192.4, 145.69, 196.82, 136.83, 188.95, 131.91, 187.48, 124.04, 190.43, 105.84, 200.27, 81.74, 202.24, 71.9, 203.71, 68.45, 196.82, 67.96, 190.92, 55.17, 189.94, 49.76]], "area": 8319.162649999998, "iscrowd": 0, "image_id": 401982, "bbox": [172.23, 33.68, 70.34, 222.69], "category_id": 1, "id": 1732336, "split": "val", "sentences": [{"tokens": ["a", "wicket", "keeper", "wearing", "green", "t", "-", "shirt", "and", "green", "cap", "standing", "in", "the", "middle", "of", "other", "two", "playes"], "raw": "A wicket keeper wearing green t-shirt and green cap standing in the middle of other two playes", "sent_id": 95849, "sent": "a wicket keeper wearing green t - shirt and green cap standing in the middle of other two playes"}, {"tokens": ["a", "man", "dressed", "in", "green", ",", "playing", "baseball", ",", "with", "a", "mitt", "on", "his", "hand"], "raw": "A man dressed in green, playing baseball, with a mitt on his hand.", "sent_id": 95850, "sent": "a man dressed in green , playing baseball , with a mitt on his hand"}], "file_name": "COCO_train2014_000000401982_1732336.jpg", "ann_id": 1732336, "sent_ids": [95849, 95850], "ref_id": 41867}, {"segmentation": [[119.13, 459.12, 175.04, 410.5, 279.58, 269.49, 419.38, 290.15, 427.89, 331.48, 444.9, 369.17, 452.2, 382.54, 441.26, 415.36, 443.69, 445.75]], "area": 39840.62215, "iscrowd": 0, "image_id": 390474, "bbox": [119.13, 269.49, 333.07, 189.63], "category_id": 31, "id": 1837140, "split": "val", "sentences": [{"tokens": ["blue", "bag", "to", "the", "right", "of", "the", "black", "bag"], "raw": "Blue  bag to the right of the black bag", "sent_id": 95864, "sent": "blue bag to the right of the black bag"}, {"tokens": ["a", "blue", "duffel", "bag"], "raw": "a blue duffel bag", "sent_id": 95865, "sent": "a blue duffel bag"}], "file_name": "COCO_train2014_000000390474_1837140.jpg", "ann_id": 1837140, "sent_ids": [95864, 95865], "ref_id": 41875}, {"segmentation": [[381.62, 480.0, 579.46, 480.0, 608.65, 422.16, 609.73, 383.24, 597.84, 348.65, 587.03, 322.7, 589.19, 300.0, 568.65, 271.89, 537.3, 251.35, 504.86, 241.62, 461.62, 241.62, 422.7, 257.84, 387.03, 302.16, 366.49, 360.54, 365.41, 411.35, 369.73, 451.35]], "area": 49209.671449999994, "iscrowd": 0, "image_id": 323030, "bbox": [365.41, 241.62, 244.32, 238.38], "category_id": 43, "id": 655825, "split": "val", "sentences": [{"tokens": ["a", "tennis", "racket", "held", "by", "a", "bearded", "man"], "raw": "A tennis racket held by a bearded man.", "sent_id": 95876, "sent": "a tennis racket held by a bearded man"}, {"tokens": ["a", "yellow", "red", "and", "blue", "tennis", "racket"], "raw": "A yellow red and blue tennis racket.", "sent_id": 95877, "sent": "a yellow red and blue tennis racket"}], "file_name": "COCO_train2014_000000323030_655825.jpg", "ann_id": 655825, "sent_ids": [95876, 95877], "ref_id": 41878}, {"segmentation": [[168.37, 124.97, 157.89, 114.49, 160.89, 100.27, 169.12, 108.51, 172.86, 118.98, 180.34, 106.26, 189.32, 109.25, 200.55, 101.77, 202.04, 122.72, 198.3, 127.21, 235.72, 148.91, 282.11, 155.65, 277.62, 163.13, 290.35, 163.88, 302.32, 151.91, 345.72, 148.91, 384.63, 169.87, 387.63, 187.08, 368.92, 230.48, 373.41, 255.18, 374.91, 285.86, 370.42, 303.82, 361.44, 298.58, 337.49, 221.5, 286.6, 235.72, 249.94, 233.47, 246.2, 234.97, 255.92, 264.16, 258.92, 288.85, 270.14, 301.57, 248.44, 291.84, 247.69, 271.64, 242.45, 304.56, 221.5, 297.08, 215.51, 288.85, 223.0, 252.93, 224.49, 230.48, 199.8, 214.02, 200.55, 191.57, 193.07, 176.6, 181.84, 163.13, 178.1, 179.6, 161.64, 156.4, 167.62, 124.22]], "area": 20332.254100000006, "iscrowd": 0, "image_id": 523577, "bbox": [157.89, 100.27, 229.74, 204.29], "category_id": 24, "id": 590319, "split": "val", "sentences": [{"tokens": ["zebra", "in", "front"], "raw": "zebra in front", "sent_id": 96009, "sent": "zebra in front"}, {"tokens": ["the", "zebra", "which", "is", "in", "front", "of", "ua", "and", "facing", "to", "us"], "raw": "the zebra which is in front of ua and facing to us", "sent_id": 96010, "sent": "the zebra which is in front of ua and facing to us"}], "file_name": "COCO_train2014_000000523577_590319.jpg", "ann_id": 590319, "sent_ids": [96009, 96010], "ref_id": 41925}, {"segmentation": [[436.85, 209.53, 571.69, 217.08, 577.08, 368.09, 566.29, 376.72, 549.03, 388.58, 542.56, 390.74, 535.01, 403.69, 519.91, 397.21, 500.49, 377.8, 470.29, 365.93, 460.58, 362.7, 427.15, 228.94, 427.15, 218.16]], "area": 21958.71290000001, "iscrowd": 0, "image_id": 51965, "bbox": [427.15, 209.53, 149.93, 194.16], "category_id": 6, "id": 168185, "split": "val", "sentences": [{"tokens": ["a", "bus", "with", "the", "number", "17", "in", "its", "window"], "raw": "A bus with the number 17 in its window.", "sent_id": 96084, "sent": "a bus with the number 17 in its window"}, {"tokens": ["a", "passing", "bus", "with", "the", "number", "17", "on", "it"], "raw": "A passing bus with the number 17 on it.", "sent_id": 96085, "sent": "a passing bus with the number 17 on it"}], "file_name": "COCO_train2014_000000051965_168185.jpg", "ann_id": 168185, "sent_ids": [96084, 96085], "ref_id": 41958}, {"segmentation": [[432.47, 320.86, 421.74, 315.5, 415.3, 315.5, 409.93, 328.37, 404.57, 334.81, 394.91, 341.25, 389.54, 336.96, 385.25, 327.3, 379.88, 312.28, 387.4, 298.33, 401.35, 283.3, 418.52, 277.94, 442.12, 262.91, 458.22, 253.26, 474.32, 253.26, 501.15, 260.77, 507.58, 260.77, 529.05, 262.91, 533.34, 266.13, 543.0, 279.01, 551.58, 286.52, 561.24, 302.62, 580.56, 323.01, 564.46, 327.3, 551.58, 316.57, 548.36, 313.35, 547.29, 330.52, 524.75, 347.69, 520.46, 339.11, 511.88, 332.67, 492.56, 329.45, 477.54, 327.3, 476.46, 338.03, 455.0, 348.76, 445.34, 347.69, 442.12, 332.67, 444.27, 325.15, 442.12, 321.94]], "area": 11462.268400000003, "iscrowd": 0, "image_id": 331680, "bbox": [379.88, 253.26, 200.68, 95.5], "category_id": 19, "id": 58858, "split": "val", "sentences": [{"tokens": ["the", "horse", "closest", "to", "the", "boy"], "raw": "the horse closest to the boy", "sent_id": 96167, "sent": "the horse closest to the boy"}, {"tokens": ["the", "horse", "on", "the", "right"], "raw": "The horse on the right.", "sent_id": 96168, "sent": "the horse on the right"}], "file_name": "COCO_train2014_000000331680_58858.jpg", "ann_id": 58858, "sent_ids": [96167, 96168], "ref_id": 41991}, {"segmentation": [[416.17, 280.59, 371.47, 284.56, 315.85, 295.49, 303.93, 413.69, 301.95, 440.5, 372.47, 437.52, 383.39, 326.28, 417.16, 285.56]], "area": 11345.353449999997, "iscrowd": 0, "image_id": 333498, "bbox": [301.95, 280.59, 115.21, 159.91], "category_id": 33, "id": 1186548, "split": "val", "sentences": [{"tokens": ["a", "blue", "suitcase"], "raw": "A blue suitcase.", "sent_id": 96172, "sent": "a blue suitcase"}, {"tokens": ["a", "blue", "suitcase", "by", "a", "train"], "raw": "A blue suitcase by a train.", "sent_id": 96173, "sent": "a blue suitcase by a train"}], "file_name": "COCO_train2014_000000333498_1186548.jpg", "ann_id": 1186548, "sent_ids": [96172, 96173], "ref_id": 41993}, {"segmentation": [[349.68, 369.97, 346.75, 338.8, 343.83, 311.53, 354.55, 305.68, 374.03, 280.36, 366.23, 255.03, 339.94, 192.69, 334.09, 168.34, 322.4, 153.73, 308.77, 146.92, 294.16, 151.79, 281.49, 178.08, 281.49, 199.51, 275.65, 219.97, 261.04, 236.53, 245.45, 278.41, 243.51, 312.5, 256.17, 320.29, 254.22, 352.44, 254.22, 369.97]], "area": 19316.13135, "iscrowd": 0, "image_id": 377019, "bbox": [243.51, 146.92, 130.52, 223.05], "category_id": 1, "id": 2151014, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "brown", "shirt", "watching", "the", "tv"], "raw": "A woman wearing a brown shirt watching the TV.", "sent_id": 96246, "sent": "a woman wearing a brown shirt watching the tv"}], "file_name": "COCO_train2014_000000377019_2151014.jpg", "ann_id": 2151014, "sent_ids": [96246], "ref_id": 42020}, {"segmentation": [[161.18, 204.36, 161.18, 181.76, 157.07, 163.95, 150.22, 163.95, 149.54, 138.6, 163.24, 124.22, 193.38, 92.71, 228.31, 74.9, 250.23, 70.79, 266.67, 71.47, 276.26, 78.32, 250.92, 76.95, 224.2, 81.75, 202.97, 97.5, 187.9, 133.12, 175.57, 133.12, 172.83, 141.34, 187.9, 191.35, 187.21, 204.36, 180.36, 212.58, 169.4, 213.27], [222.83, 156.41, 222.83, 222.86, 233.11, 218.75, 236.53, 157.78], [255.03, 179.02, 268.73, 218.06, 283.11, 213.27, 259.82, 153.67], [338.6, 152.3, 349.56, 187.24, 339.28, 213.27, 349.56, 213.95, 360.52, 179.7, 356.41, 161.21, 370.79, 183.13, 372.16, 207.1, 385.18, 212.58, 381.75, 174.22, 367.37, 153.67, 352.98, 140.66]], "area": 6506.239599999999, "iscrowd": 0, "image_id": 127286, "bbox": [149.54, 70.79, 235.64, 152.07], "category_id": 24, "id": 593294, "split": "val", "sentences": [{"tokens": ["zebra", "standing", "behind", "a", "zebra"], "raw": "Zebra standing behind a zebra.", "sent_id": 96375, "sent": "zebra standing behind a zebra"}, {"tokens": ["the", "zebra", "standing", "behind", "the", "first", "zebra"], "raw": "The zebra standing behind the first zebra.", "sent_id": 96376, "sent": "the zebra standing behind the first zebra"}], "file_name": "COCO_train2014_000000127286_593294.jpg", "ann_id": 593294, "sent_ids": [96375, 96376], "ref_id": 42064}, {"segmentation": [[432.82, 308.35, 432.82, 269.92, 412.89, 259.96, 400.79, 234.34, 402.22, 195.91, 415.03, 141.11, 423.57, 133.99, 447.76, 131.86, 468.4, 133.99, 481.21, 143.25, 489.04, 201.6, 488.33, 232.91, 479.07, 257.82, 448.47, 274.19, 448.47, 309.77, 473.38, 324.71, 476.23, 333.25, 466.26, 344.64, 443.49, 349.62, 415.74, 347.49, 402.93, 335.39, 400.79, 320.44, 401.5, 315.46, 420.72, 311.91]], "area": 13295.1295, "iscrowd": 0, "image_id": 204529, "bbox": [400.79, 131.86, 88.25, 217.76], "category_id": 46, "id": 666622, "split": "val", "sentences": [{"tokens": ["a", "glass", "on", "white", "wine", "second", "from", "the", "right"], "raw": "A glass on white wine second from the right", "sent_id": 96391, "sent": "a glass on white wine second from the right"}], "file_name": "COCO_train2014_000000204529_666622.jpg", "ann_id": 666622, "sent_ids": [96391], "ref_id": 42069}, {"segmentation": [[199.39, 433.62, 296.94, 441.96, 271.93, 423.61, 273.6, 421.11, 276.1, 417.78, 324.46, 421.11, 321.12, 440.29, 312.79, 445.29, 301.95, 446.13, 319.46, 471.97, 355.31, 471.97, 391.16, 486.98, 408.67, 510.33, 421.18, 545.35, 421.18, 568.69, 402.0, 599.54, 361.98, 608.71, 321.12, 596.21, 298.61, 570.36, 291.11, 547.01, 287.77, 556.19, 279.44, 558.69, 271.1, 558.69, 264.43, 552.02, 254.42, 572.03, 253.59, 580.37, 246.08, 587.87, 241.08, 572.86, 251.92, 568.69, 259.42, 548.68, 253.59, 532.01, 195.22, 458.63, 191.05, 466.97, 205.23, 532.84, 188.55, 574.53, 172.71, 582.87, 154.37, 578.7, 139.36, 552.85, 131.02, 501.99, 142.69, 466.97, 157.7, 455.3, 184.38, 456.13, 186.89, 446.96, 180.21, 438.62, 182.72, 421.95, 184.38, 416.11, 146.86, 415.28, 150.2, 429.45, 161.04, 439.46, 156.87, 446.13, 142.69, 432.79, 142.69, 421.95, 136.86, 425.28, 143.53, 406.1, 166.87, 394.43, 149.37, 404.44, 151.87, 409.44, 183.55, 409.44, 197.72, 409.44, 196.89, 400.27, 212.73, 394.43, 213.57, 408.61, 220.24, 412.78, 221.9, 420.28, 217.74, 418.61, 206.9, 412.78]], "area": 32712.794650000003, "iscrowd": 0, "image_id": 107425, "bbox": [131.02, 394.43, 290.16, 214.28], "category_id": 2, "id": 126083, "split": "val", "sentences": [{"tokens": ["a", "bicycle", "upright", "and", "leaning", "against", "a", "metal", "sculpture", "with", "a", "pink", "water", "bottle", "attached", "to", "it"], "raw": "A bicycle upright and leaning against a metal sculpture with a pink water bottle attached to it.", "sent_id": 96422, "sent": "a bicycle upright and leaning against a metal sculpture with a pink water bottle attached to it"}, {"tokens": ["a", "white", "road", "bike"], "raw": "A white road bike.", "sent_id": 96423, "sent": "a white road bike"}], "file_name": "COCO_train2014_000000107425_126083.jpg", "ann_id": 126083, "sent_ids": [96422, 96423], "ref_id": 42081}, {"segmentation": [[64.57, 240.0, 53.81, 228.16, 50.58, 226.01, 68.88, 208.79, 57.04, 198.03, 40.9, 189.42, 54.89, 180.81, 61.35, 179.73, 68.88, 177.58, 73.18, 150.67, 75.34, 147.44, 99.01, 144.22, 349.78, 154.98, 370.22, 162.51, 370.22, 198.03, 376.68, 210.94, 376.68, 237.85, 367.0, 251.84, 348.7, 249.69, 333.63, 249.69, 304.57, 252.91, 273.36, 256.14, 247.53, 257.22, 215.25, 258.3, 176.5, 260.45, 158.21, 260.45, 129.15, 256.14, 82.87, 243.23]], "area": 32365.289350000014, "iscrowd": 0, "image_id": 510027, "bbox": [40.9, 144.22, 335.78, 116.23], "category_id": 54, "id": 310948, "split": "val", "sentences": [{"tokens": ["the", "half", "part", "of", "the", "sandwich", "nearest", "to", "the", "carrots"], "raw": "the half part of the sandwich nearest to the carrots", "sent_id": 96471, "sent": "the half part of the sandwich nearest to the carrots"}, {"tokens": ["the", "bottom", "half", "of", "a", "sandwich", "packed", "in", "a", "lunchbox"], "raw": "The bottom half of a sandwich packed in a lunchbox.", "sent_id": 96472, "sent": "the bottom half of a sandwich packed in a lunchbox"}], "file_name": "COCO_train2014_000000510027_310948.jpg", "ann_id": 310948, "sent_ids": [96471, 96472], "ref_id": 42102}, {"segmentation": [[175.48, 401.67, 175.48, 322.19, 164.74, 294.27, 126.08, 285.68, 88.49, 282.45, 90.64, 271.71, 98.16, 268.49, 107.82, 267.42, 121.79, 267.42, 167.97, 266.34, 177.63, 262.05, 203.41, 265.27, 213.07, 272.79, 213.07, 278.16, 212.0, 282.45, 202.33, 285.68, 194.82, 296.42, 201.26, 390.93, 193.74, 402.74, 188.37, 414.55, 185.15, 415.63, 173.34, 405.96]], "area": 5496.9145499999995, "iscrowd": 0, "image_id": 5587, "bbox": [88.49, 262.05, 124.58, 153.58], "category_id": 67, "id": 392590, "split": "val", "sentences": [{"tokens": ["the", "square", "table", "the", "people", "are", "sitting", "at"], "raw": "The square table the people are sitting at", "sent_id": 96550, "sent": "the square table the people are sitting at"}], "file_name": "COCO_train2014_000000005587_392590.jpg", "ann_id": 392590, "sent_ids": [96550], "ref_id": 42132}, {"segmentation": [[435.49, 213.61, 389.85, 217.03, 388.92, 219.82, 390.47, 231.31, 393.27, 251.8, 394.51, 273.22, 394.82, 273.84, 396.37, 275.7, 410.96, 278.81, 421.52, 285.02, 422.45, 289.05, 422.14, 292.78, 422.45, 303.33, 425.25, 318.55, 424.62, 323.2, 423.38, 329.1, 417.79, 331.27, 411.9, 335.0, 416.24, 344.94, 421.52, 361.08, 428.04, 373.19, 430.83, 373.19, 432.7, 371.32, 430.83, 364.8, 430.52, 358.28, 462.19, 348.35, 469.64, 358.28, 473.99, 356.73, 473.37, 349.59, 467.47, 336.86, 463.12, 327.86, 460.95, 326.31, 464.98, 322.89, 472.44, 320.41, 481.75, 315.75, 485.79, 309.85, 489.2, 304.89, 487.34, 301.78, 484.54, 302.71, 481.75, 288.74, 480.82, 280.05, 486.1, 280.05, 487.65, 280.05, 487.96, 277.57, 486.41, 274.46, 472.44, 269.18, 457.22, 265.77, 451.01, 265.77, 444.8, 265.77, 444.18, 253.35, 439.84, 231.62, 436.42, 213.61], [396.06, 281.6, 394.82, 281.6, 397.93, 299.61, 401.34, 308.3, 414.38, 313.89, 418.11, 310.16, 415.93, 294.95, 411.9, 288.43, 403.82, 284.4]], "area": 8402.543700000002, "iscrowd": 0, "image_id": 36574, "bbox": [388.92, 213.61, 100.28, 159.58], "category_id": 62, "id": 374030, "split": "val", "sentences": [{"tokens": ["a", "wooden", "chair", "sitting", "between", "two", "other", "wooden", "chairs", "on", "a", "patio"], "raw": "A wooden chair sitting between two other wooden chairs on a patio.", "sent_id": 96628, "sent": "a wooden chair sitting between two other wooden chairs on a patio"}, {"tokens": ["a", "wooden", "chair", "at", "the", "middle", "of", "two", "other", "wooden", "chairs"], "raw": "A WOODEN CHAIR AT THE MIDDLE OF TWO OTHER WOODEN CHAIRS.", "sent_id": 96629, "sent": "a wooden chair at the middle of two other wooden chairs"}], "file_name": "COCO_train2014_000000036574_374030.jpg", "ann_id": 374030, "sent_ids": [96628, 96629], "ref_id": 42167}, {"segmentation": [[527.38, 121.64, 510.44, 91.62, 495.04, 78.53, 424.21, 46.19, 428.83, 59.28, 419.59, 56.2, 424.21, 60.05, 417.28, 63.13, 424.98, 67.75, 423.44, 71.6, 434.22, 76.22, 427.29, 76.99, 434.99, 87.0, 445.0, 88.54, 446.54, 96.24, 488.11, 154.75, 491.96, 158.6, 485.03, 167.84, 451.93, 185.54, 462.71, 212.49, 489.65, 220.96, 507.36, 181.69, 513.52, 178.62, 535.08, 194.01, 564.33, 204.79, 579.73, 210.95, 593.59, 221.73, 596.67, 229.43, 623.61, 237.9, 623.61, 229.43, 628.23, 229.43, 590.51, 161.68, 575.11, 152.44, 548.93, 140.12, 555.09, 125.49, 559.71, 111.63, 546.62, 111.63, 538.92, 120.87, 532.77, 120.87]], "area": 13919.382649999996, "iscrowd": 0, "image_id": 37122, "bbox": [417.28, 46.19, 210.95, 191.71], "category_id": 16, "id": 37568, "split": "val", "sentences": [{"tokens": ["a", "bird", "flying", "to", "the", "right", "of", "another", "bird"], "raw": "A bird flying to the right of another bird.", "sent_id": 96638, "sent": "a bird flying to the right of another bird"}, {"tokens": ["the", "bird", "on", "the", "right"], "raw": "the bird on the right", "sent_id": 96639, "sent": "the bird on the right"}], "file_name": "COCO_train2014_000000037122_37568.jpg", "ann_id": 37568, "sent_ids": [96638, 96639], "ref_id": 42172}, {"segmentation": [[386.75, 220.02, 361.86, 218.11, 358.99, 195.13, 365.69, 190.34, 354.2, 179.81, 327.4, 179.81, 326.44, 207.58, 347.5, 213.32, 339.84, 241.08, 327.4, 243.95, 302.51, 243.95, 301.55, 242.04, 317.82, 181.73, 330.27, 156.84, 337.93, 120.46, 339.84, 75.47, 337.93, 41.96, 354.2, 29.52, 379.09, 31.43, 377.18, 64.94, 381.01, 78.34, 393.45, 100.36, 403.02, 169.28, 387.71, 180.77, 393.45, 200.87, 394.41, 224.81], [386.75, 229.59, 396.32, 265.01, 400.15, 305.22, 384.84, 310.01, 381.01, 310.01, 379.09, 288.95, 388.67, 281.29, 380.05, 269.8, 371.43, 265.97, 361.86, 231.51]], "area": 12591.768349999997, "iscrowd": 0, "image_id": 97936, "bbox": [301.55, 29.52, 101.47, 280.49], "category_id": 1, "id": 210777, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "white", "gloves"], "raw": "a woman wearing white gloves", "sent_id": 96663, "sent": "a woman wearing white gloves"}, {"tokens": ["two", "lovely", "ladies", "conversing", "while", "walking", "a", "dog", ",", "behind", "a", "bicycle"], "raw": "Two lovely ladies conversing while walking a dog, behind a bicycle.", "sent_id": 96664, "sent": "two lovely ladies conversing while walking a dog , behind a bicycle"}], "file_name": "COCO_train2014_000000097936_210777.jpg", "ann_id": 210777, "sent_ids": [96663, 96664], "ref_id": 42180}, {"segmentation": [[221.37, 93.76, 254.84, 45.07, 296.68, 35.94, 298.96, 12.36, 305.05, 0.19, 354.5, 4.75, 361.34, 15.4, 343.85, 57.24, 359.06, 58.01, 385.69, 108.21, 414.59, 143.21, 426.77, 162.98, 445.02, 175.92, 426.77, 182.76, 354.5, 115.06, 347.65, 131.03, 352.98, 176.68, 397.1, 246.66, 412.31, 268.73, 409.27, 281.66, 394.05, 306.76, 384.93, 317.41, 376.56, 311.33, 375.04, 286.98, 370.47, 264.92, 333.96, 248.19, 314.94, 251.23, 306.57, 239.82, 268.53, 210.91, 260.93, 195.7, 245.71, 158.42, 234.3, 145.49, 216.81, 127.99, 225.93, 112.78]], "area": 30442.41725, "iscrowd": 0, "image_id": 190732, "bbox": [216.81, 0.19, 228.21, 317.22], "category_id": 1, "id": 492542, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "red", "shirt"], "raw": "A man in a red shirt.", "sent_id": 96670, "sent": "a man in a red shirt"}, {"tokens": ["soccer", "player", "in", "red"], "raw": "soccer player in red", "sent_id": 96671, "sent": "soccer player in red"}], "file_name": "COCO_train2014_000000190732_492542.jpg", "ann_id": 492542, "sent_ids": [96670, 96671], "ref_id": 42182}, {"segmentation": [[325.47, 7.11, 541.85, 7.11, 523.98, 147.06, 532.92, 158.97, 570.63, 236.39, 452.52, 241.36, 447.56, 230.44, 450.53, 147.06, 448.55, 144.09, 327.46, 139.12, 321.5, 8.11, 322.49, 5.13, 362.2, 6.12]], "area": 37726.562750000005, "iscrowd": 0, "image_id": 344073, "bbox": [321.5, 5.13, 249.13, 236.23], "category_id": 73, "id": 1103981, "split": "val", "sentences": [{"tokens": ["the", "top", "and", "rightmost", "of", "three", "open", "laptops"], "raw": "The top and rightmost of three open laptops.", "sent_id": 96731, "sent": "the top and rightmost of three open laptops"}], "file_name": "COCO_train2014_000000344073_1103981.jpg", "ann_id": 1103981, "sent_ids": [96731], "ref_id": 42208}, {"segmentation": [[5.51, 221.01, 102.25, 220.22, 104.61, 206.85, 165.96, 204.49, 201.35, 230.45, 213.93, 234.38, 244.61, 266.63, 237.53, 297.3, 195.84, 301.24, 179.33, 296.52, 165.17, 276.85, 125.84, 272.13, 84.16, 272.92, 64.49, 279.21, 49.55, 291.8, 0.0, 278.43]], "area": 15298.885300000004, "iscrowd": 0, "image_id": 234516, "bbox": [0.0, 204.49, 244.61, 96.75], "category_id": 8, "id": 398279, "split": "val", "sentences": [{"tokens": ["an", "old", "truck", "in", "front", "of", "other", "trucks", "and", "cars"], "raw": "An old truck in front of other trucks and cars", "sent_id": 96734, "sent": "an old truck in front of other trucks and cars"}, {"tokens": ["the", "truck", "furthest", "to", "the", "left"], "raw": "The truck furthest to the left.", "sent_id": 96735, "sent": "the truck furthest to the left"}], "file_name": "COCO_train2014_000000234516_398279.jpg", "ann_id": 398279, "sent_ids": [96734, 96735], "ref_id": 42210}, {"segmentation": [[257.72, 614.5, 249.13, 565.82, 251.99, 511.41, 272.04, 468.46, 289.22, 441.25, 273.47, 383.98, 260.58, 318.12, 267.74, 308.1, 257.72, 266.58, 256.29, 242.24, 286.35, 220.76, 336.47, 232.21, 335.03, 269.44, 330.74, 316.69, 367.96, 331.01, 399.46, 369.66, 425.23, 394.0, 425.23, 446.98, 399.46, 520.0, 382.28, 530.02, 386.58, 591.59, 386.58, 604.47, 372.26, 591.59, 365.1, 640.0, 260.58, 638.84]], "area": 48960.43015, "iscrowd": 0, "image_id": 153749, "bbox": [249.13, 220.76, 176.1, 419.24], "category_id": 1, "id": 467404, "split": "val", "sentences": [{"tokens": ["a", "women", "standing", "wearing", "a", "green", "shirt", "and", "blue", "vest", "with", "her", "left", "hand", "on", "her", "hip"], "raw": "A women standing wearing a green shirt and blue vest with her left hand on her hip", "sent_id": 96742, "sent": "a women standing wearing a green shirt and blue vest with her left hand on her hip"}, {"tokens": ["lady", "with", "a", "green", "guest", "with", "her", "husband"], "raw": "Lady with a green guest with her husband.", "sent_id": 96743, "sent": "lady with a green guest with her husband"}], "file_name": "COCO_train2014_000000153749_467404.jpg", "ann_id": 467404, "sent_ids": [96742, 96743], "ref_id": 42213}, {"segmentation": [[4.04, 305.91, 35.54, 296.31, 45.13, 268.93, 17.73, 208.65, 8.15, 170.3, 25.96, 123.73, 61.57, 86.75, 109.5, 79.91, 151.97, 114.15, 171.15, 145.65, 172.51, 229.21, 136.9, 296.31, 147.86, 336.04, 173.88, 353.84, 206.76, 383.99, 206.76, 431.92, 227.31, 631.9, 0.0, 629.16, 1.29, 308.64]], "area": 94667.01249999998, "iscrowd": 0, "image_id": 205000, "bbox": [0.0, 79.91, 227.31, 551.99], "category_id": 1, "id": 481130, "split": "val", "sentences": [{"tokens": ["back", "image", "of", "a", "woman", "in", "a", "green", "shirt"], "raw": "back image of a woman in a green shirt", "sent_id": 96754, "sent": "back image of a woman in a green shirt"}, {"tokens": ["a", "green", "colour", "dressed", "young", "lady", "is", "standing", "infront", "of", "the", "mirror"], "raw": "A GREEN COLOUR DRESSED YOUNG LADY IS STANDING INFRONT OF THE MIRROR", "sent_id": 96755, "sent": "a green colour dressed young lady is standing infront of the mirror"}], "file_name": "COCO_train2014_000000205000_481130.jpg", "ann_id": 481130, "sent_ids": [96754, 96755], "ref_id": 42219}, {"segmentation": [[27.03, 336.22, 23.78, 351.35, 30.27, 362.16, 37.84, 366.49, 42.16, 375.14, 62.7, 375.14, 132.97, 365.41, 170.81, 353.51, 178.38, 362.16, 179.46, 375.14, 109.19, 405.41, 107.03, 480.0, 2.16, 480.0, 0.0, 342.7], [357.84, 292.97, 356.76, 307.03, 341.62, 307.03, 327.57, 302.7, 313.51, 305.95, 312.43, 317.84, 314.59, 323.24, 322.16, 390.27, 329.73, 392.43, 337.3, 385.95, 341.62, 323.24, 371.89, 299.46, 366.49, 288.65]], "area": 16723.2177, "iscrowd": 0, "image_id": 439325, "bbox": [0.0, 288.65, 371.89, 191.35], "category_id": 15, "id": 574532, "split": "val", "sentences": [{"tokens": ["a", "bench", "with", "a", "man", "in", "a", "suit", "on", "it"], "raw": "A bench with a man in a suit on it.", "sent_id": 96756, "sent": "a bench with a man in a suit on it"}, {"tokens": ["bench", "on", "sidewalk"], "raw": "Bench on sidewalk.", "sent_id": 96757, "sent": "bench on sidewalk"}], "file_name": "COCO_train2014_000000439325_574532.jpg", "ann_id": 574532, "sent_ids": [96756, 96757], "ref_id": 42220}, {"segmentation": [[102.66, 457.62, 121.18, 461.54, 110.49, 445.51, 117.26, 426.28, 142.91, 400.28, 161.79, 374.99, 155.0, 339.94, 141.07, 316.33, 134.49, 289.62, 125.97, 279.17, 114.36, 285.75, 104.3, 299.68, 107.01, 313.62, 137.97, 339.17, 145.33, 344.97, 152.29, 356.97, 147.26, 367.04, 137.2, 367.04, 119.0, 386.0, 103.91, 411.55, 96.55, 422.0, 87.26, 439.03], [120.55, 425.48, 137.58, 432.45, 150.75, 444.06, 164.68, 447.94, 160.81, 439.42, 152.29, 428.58, 148.04, 418.13, 165.84, 394.91, 198.74, 368.97, 199.52, 355.42, 193.71, 330.65, 182.1, 295.04, 169.33, 288.46, 165.84, 279.17, 169.71, 249.36, 183.65, 209.49, 191.78, 220.33, 196.81, 204.08, 199.13, 183.56, 188.68, 169.24, 175.13, 164.21, 172.42, 150.66, 182.49, 145.63, 186.74, 140.59, 199.9, 135.18, 198.36, 131.69, 187.13, 131.69, 179.0, 124.34, 177.45, 105.76, 171.26, 106.92, 168.55, 108.47, 159.26, 103.82, 145.33, 108.47, 136.42, 116.6, 132.94, 133.63, 122.1, 164.59, 119.39, 187.43, 117.46, 193.24, 115.91, 195.95, 120.55, 214.14, 125.57, 213.13, 131.61, 210.98, 139.79, 211.59, 148.07, 215.07, 154.42, 221.0, 157.28, 226.12, 162.09, 231.23, 164.13, 233.18, 169.55, 241.87, 169.96, 244.63, 167.1, 245.96, 154.72, 247.09, 154.62, 250.46, 147.82, 254.75, 153.81, 287.14, 155.52, 290.71, 159.52, 305.4, 165.65, 319.67, 168.22, 337.36, 170.07, 347.77, 179.21, 352.91, 173.36, 361.32, 175.5, 375.02, 167.65, 383.87, 167.36, 370.74, 165.51, 368.46, 153.53, 387.43, 145.39, 398.42]], "area": 15576.943550000004, "iscrowd": 0, "image_id": 233841, "bbox": [87.26, 103.82, 112.64, 357.72], "category_id": 1, "id": 2156311, "split": "val", "sentences": [{"tokens": ["girl", "in", "green", "shirt", "and", "blue", "shorts"], "raw": "Girl in green shirt and blue shorts.", "sent_id": 96803, "sent": "girl in green shirt and blue shorts"}], "file_name": "COCO_train2014_000000233841_2156311.jpg", "ann_id": 2156311, "sent_ids": [96803], "ref_id": 42239}, {"segmentation": [[29.6, 81.45, 25.93, 82.58, 20.72, 85.82, 19.87, 90.47, 22.41, 96.67, 22.27, 100.47, 18.18, 105.91, 11.42, 110.0, 9.3, 112.33, 8.88, 121.77, 7.89, 129.54, 7.89, 129.54, 10.85, 132.5, 10.01, 137.01, 13.11, 141.24, 14.66, 143.63, 17.05, 143.91, 17.9, 146.17, 18.04, 148.14, 16.63, 151.95, 27.25, 180.88, 29.7, 189.71, 28.23, 203.94, 31.17, 217.83, 33.63, 234.03, 37.06, 237.62, 40.5, 240.07, 40.5, 240.07, 53.75, 236.64, 48.35, 231.24, 47.37, 219.46, 48.35, 202.29, 50.31, 187.07, 56.56, 167.01, 62.72, 156.97, 59.8, 144.02, 58.51, 137.24, 51.71, 121.7, 46.53, 107.48, 37.46, 105.54, 34.87, 100.69, 39.08, 92.92, 37.79, 89.68, 37.14, 84.45, 30.99, 81.53, 29.69, 81.86]], "area": 4437.06685, "iscrowd": 0, "image_id": 266369, "bbox": [7.89, 81.45, 54.83, 158.62], "category_id": 1, "id": 483616, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "black", "watches", "wildlife"], "raw": "A woman wearing black watches wildlife.", "sent_id": 96842, "sent": "a woman wearing black watches wildlife"}, {"tokens": ["a", "woman", "in", "a", "blue", "skirt", "standing", "next", "to", "a", "man"], "raw": "A woman in a blue skirt standing next to a man.", "sent_id": 96843, "sent": "a woman in a blue skirt standing next to a man"}], "file_name": "COCO_train2014_000000266369_483616.jpg", "ann_id": 483616, "sent_ids": [96842, 96843], "ref_id": 42255}, {"segmentation": [[94.57, 340.16, 162.39, 317.24, 207.29, 310.55, 243.59, 336.34, 227.35, 372.64, 178.63, 419.45, 176.72, 420.41, 127.05, 421.36], [77.38, 354.49, 85.97, 386.02, 107.94, 421.36, 3.82, 420.41, 0.96, 404.17, 33.43, 375.51]], "area": 15251.647100000002, "iscrowd": 0, "image_id": 206062, "bbox": [0.96, 310.55, 242.63, 110.81], "category_id": 42, "id": 653118, "split": "val", "sentences": [{"tokens": ["a", "yellow", "surfboard", "with", "swell", "written", "on", "it"], "raw": "A yellow surfboard with Swell written on it.", "sent_id": 96852, "sent": "a yellow surfboard with swell written on it"}, {"tokens": ["a", "yellow", "surfboard", "being", "held", "by", "a", "man"], "raw": "A yellow surfboard being held by a man.", "sent_id": 96853, "sent": "a yellow surfboard being held by a man"}], "file_name": "COCO_train2014_000000206062_653118.jpg", "ann_id": 653118, "sent_ids": [96852, 96853], "ref_id": 42260}, {"segmentation": [[35.5, 173.74, 33.58, 131.52, 57.57, 103.7, 71.97, 95.06, 79.64, 90.26, 75.8, 74.91, 93.08, 40.37, 111.31, 29.81, 139.13, 45.16, 147.77, 76.83, 148.73, 96.98, 147.77, 113.29, 163.12, 117.13, 173.68, 139.2, 182.31, 169.9, 184.23, 200.61, 192.87, 224.6, 189.99, 257.22, 204.38, 306.16, 204.38, 326.31, 170.8, 334.95, 130.5, 333.03, 88.28, 333.99, 85.4, 303.28, 45.1, 249.55]], "area": 35183.07169999999, "iscrowd": 0, "image_id": 549599, "bbox": [33.58, 29.81, 170.8, 305.14], "category_id": 1, "id": 474137, "split": "val", "sentences": [{"tokens": ["a", "lady", "on", "a", "bench", "holding", "an", "orange", "bag"], "raw": "A lady on a bench holding an orange bag.", "sent_id": 96880, "sent": "a lady on a bench holding an orange bag"}, {"tokens": ["woman", "holding", "a", "jacket", "in", "her", "lap"], "raw": "Woman holding a jacket in her lap.", "sent_id": 96881, "sent": "woman holding a jacket in her lap"}], "file_name": "COCO_train2014_000000549599_474137.jpg", "ann_id": 474137, "sent_ids": [96880, 96881], "ref_id": 42271}, {"segmentation": [[71.84, 134.14, 80.82, 124.41, 98.78, 117.67, 122.72, 129.65, 124.97, 146.86, 123.47, 159.58, 129.46, 175.29, 137.69, 191.01, 152.66, 215.7, 156.4, 233.66, 148.17, 241.89, 126.47, 242.64, 124.97, 251.62, 122.72, 258.36, 143.68, 264.34, 160.14, 283.05, 167.62, 294.27, 166.87, 307.0, 161.64, 312.23, 138.44, 314.48, 110.0, 319.72, 93.54, 326.45, 59.12, 329.45, 43.4, 288.29, 35.17, 237.4, 38.91, 208.97, 47.14, 188.76, 63.61, 167.81, 68.84, 158.83, 69.59, 144.61]], "area": 18313.4684, "iscrowd": 0, "image_id": 540211, "bbox": [35.17, 117.67, 132.45, 211.78], "category_id": 1, "id": 183132, "split": "val", "sentences": [{"tokens": ["the", "boy", "in", "the", "jersey"], "raw": "The boy in the jersey.", "sent_id": 96892, "sent": "the boy in the jersey"}, {"tokens": ["a", "man", "in", "a", "white", "shirt", "holding", "a", "phone", "to", "his", "ear"], "raw": "A man in a white shirt holding a phone to his ear.", "sent_id": 96893, "sent": "a man in a white shirt holding a phone to his ear"}], "file_name": "COCO_train2014_000000540211_183132.jpg", "ann_id": 183132, "sent_ids": [96892, 96893], "ref_id": 42278}, {"segmentation": [[2.75, 379.58, 148.53, 341.07, 177.41, 312.19, 148.53, 268.18, 99.02, 220.04, 116.9, 144.4, 66.01, 83.89, 4.13, 83.89]], "area": 33433.17105, "iscrowd": 0, "image_id": 501177, "bbox": [2.75, 83.89, 174.66, 295.69], "category_id": 1, "id": 513015, "split": "val", "sentences": [{"tokens": ["it", "'", "s", "a", "man", "who", "is", "behind", "another", "man", "who", "'", "s", "on", "his", "phone"], "raw": "It's a man who is behind another man who's on his phone.", "sent_id": 97022, "sent": "it ' s a man who is behind another man who ' s on his phone"}, {"tokens": ["man", "on", "left", "with", "low", "cut", "hair"], "raw": "Man on left with low cut hair", "sent_id": 97023, "sent": "man on left with low cut hair"}], "file_name": "COCO_train2014_000000501177_513015.jpg", "ann_id": 513015, "sent_ids": [97022, 97023], "ref_id": 42331}, {"segmentation": [[13.0, 311.69, 66.46, 300.14, 80.9, 291.47, 83.79, 326.14, 92.46, 360.81, 95.35, 394.04, 99.68, 427.27, 93.91, 441.72, 83.79, 425.82, 83.79, 401.26, 69.35, 369.48, 54.9, 368.04, 11.56, 368.04, 5.78, 346.37, 5.78, 318.92], [348.17, 275.58, 348.17, 298.69, 339.5, 331.92, 345.28, 378.15, 343.84, 401.26, 323.61, 420.05, 316.39, 394.04, 314.94, 355.03, 314.94, 333.36, 314.94, 307.36, 316.39, 278.47]], "area": 9967.87785, "iscrowd": 0, "image_id": 566488, "bbox": [5.78, 275.58, 342.39, 166.14], "category_id": 15, "id": 571281, "split": "val", "sentences": [{"tokens": ["a", "bench", "the", "skateboarder", "is", "sitting", "on"], "raw": "A bench the skateboarder is sitting on", "sent_id": 97036, "sent": "a bench the skateboarder is sitting on"}], "file_name": "COCO_train2014_000000566488_571281.jpg", "ann_id": 571281, "sent_ids": [97036], "ref_id": 42338}, {"segmentation": [[199.55, 432.21, 269.66, 422.5, 350.56, 412.79, 415.28, 421.42, 461.66, 376.12, 423.91, 224.03, 413.12, 163.63, 381.84, 137.74, 286.92, 164.7, 226.52, 159.31, 199.55, 149.6, 146.7, 175.49, 98.16, 222.95, 93.84, 288.75, 101.39, 378.28, 113.26, 400.93, 153.17, 408.48, 179.06, 425.74, 179.06, 425.74, 192.0, 426.82]], "area": 86288.47970000001, "iscrowd": 0, "image_id": 51965, "bbox": [93.84, 137.74, 367.82, 294.47], "category_id": 6, "id": 165853, "split": "val", "sentences": [{"tokens": ["bus", "reading", "nis", "training", "vehicle"], "raw": "bus reading NIS TRAINING VEHICLE", "sent_id": 97255, "sent": "bus reading nis training vehicle"}, {"tokens": ["nis", "training", "vehicle", "bus", "number", "2565"], "raw": "NIS Training Vehicle bus number 2565.", "sent_id": 97256, "sent": "nis training vehicle bus number 2565"}], "file_name": "COCO_train2014_000000051965_165853.jpg", "ann_id": 165853, "sent_ids": [97255, 97256], "ref_id": 42430}, {"segmentation": [[640.0, 99.95, 640.0, 99.95, 637.11, 99.95, 605.69, 93.45, 598.1, 93.45, 595.94, 91.29, 590.52, 93.45, 587.27, 97.79, 582.93, 105.37, 579.68, 110.79, 572.1, 132.46, 572.1, 132.46, 573.18, 141.13, 573.18, 144.38, 573.18, 150.88, 572.1, 150.88, 572.1, 151.96, 577.52, 170.38, 579.68, 170.38, 579.68, 181.22, 551.51, 205.06, 551.51, 205.06, 551.51, 219.14, 551.51, 222.39, 551.51, 223.48, 545.01, 231.06, 540.68, 240.81, 538.51, 259.23, 538.51, 262.48, 529.84, 288.49, 527.67, 290.65, 519.01, 309.07, 515.76, 318.83, 515.76, 343.75, 519.01, 355.67, 523.34, 370.84, 523.34, 376.25, 523.34, 387.09, 523.34, 391.42, 527.67, 405.51, 527.67, 412.01, 533.09, 427.18, 536.34, 427.18, 555.85, 441.26, 568.85, 434.76, 573.18, 430.43, 587.27, 419.59, 601.35, 413.09, 602.44, 413.09, 604.6, 416.34, 604.6, 422.84, 607.86, 428.26, 613.27, 458.6, 616.52, 464.02, 618.69, 466.19, 624.11, 470.52, 634.94, 470.52, 634.94, 469.44, 638.19, 439.1, 640.0, 412.01, 640.0, 380.59, 640.0, 366.5, 640.0, 332.91, 638.19, 132.46]], "area": 32646.391150000014, "iscrowd": 0, "image_id": 72396, "bbox": [515.76, 91.29, 124.24, 379.23], "category_id": 1, "id": 499781, "split": "val", "sentences": [{"tokens": ["the", "woman", "who", "is", "not", "standing", "at", "the", "lap", "top", "computer"], "raw": "The woman who is not standing at the lap top computer.", "sent_id": 97315, "sent": "the woman who is not standing at the lap top computer"}, {"tokens": ["the", "woman", "on", "the", "right"], "raw": "the woman on the right", "sent_id": 97316, "sent": "the woman on the right"}], "file_name": "COCO_train2014_000000072396_499781.jpg", "ann_id": 499781, "sent_ids": [97315, 97316], "ref_id": 42450}, {"segmentation": [[523.24, 225.41, 538.38, 36.22, 497.3, 41.62, 457.3, 47.03, 405.41, 39.46, 382.7, 35.14, 357.84, 25.41, 368.65, 2.7, 640.0, 1.62, 638.92, 41.62, 607.57, 31.89, 571.89, 39.46, 544.86, 39.46, 536.22, 228.65]], "area": 12117.137750000002, "iscrowd": 0, "image_id": 516106, "bbox": [357.84, 1.62, 282.16, 227.03], "category_id": 28, "id": 285409, "split": "val", "sentences": [{"tokens": ["pole", "on", "a", "green", "umbrella"], "raw": "Pole on a green umbrella", "sent_id": 97317, "sent": "pole on a green umbrella"}, {"tokens": ["green", "umbrella", "and", "its", "pole"], "raw": "Green umbrella and its pole.", "sent_id": 97318, "sent": "green umbrella and its pole"}], "file_name": "COCO_train2014_000000516106_285409.jpg", "ann_id": 285409, "sent_ids": [97317, 97318], "ref_id": 42451}, {"segmentation": [[114.54, 320.5, 87.41, 289.36, 82.39, 255.2, 93.44, 232.09, 99.47, 215.01, 118.56, 198.93, 138.65, 189.89, 157.74, 185.87, 201.95, 195.92, 213.0, 215.01, 224.05, 244.14, 226.06, 262.23, 213.0, 261.22, 180.85, 250.17, 167.79, 255.2, 145.68, 263.23, 133.63, 272.28, 121.57, 299.4]], "area": 9923.0267, "iscrowd": 0, "image_id": 504744, "bbox": [82.39, 185.87, 143.67, 134.63], "category_id": 55, "id": 1053688, "split": "val", "sentences": [{"tokens": ["an", "orange", "placed", "behind", "an", "apple", "on", "the", "left", "side", "of", "a", "fruit", "bowl"], "raw": "An orange placed behind an apple on the left side of a fruit bowl.", "sent_id": 97319, "sent": "an orange placed behind an apple on the left side of a fruit bowl"}, {"tokens": ["a", "orange", "in", "a", "bowl", "of", "fruit"], "raw": "A orange in a bowl of fruit", "sent_id": 97320, "sent": "a orange in a bowl of fruit"}], "file_name": "COCO_train2014_000000504744_1053688.jpg", "ann_id": 1053688, "sent_ids": [97319, 97320], "ref_id": 42452}, {"segmentation": [[127.25, 28.99, 127.25, 28.99, 139.67, 66.65, 148.08, 79.87, 159.7, 94.29, 180.54, 120.74, 180.54, 120.74, 205.78, 150.78, 223.81, 182.04, 262.67, 227.31, 267.08, 231.72, 268.68, 224.91, 274.69, 216.89, 277.5, 214.89, 278.3, 204.47, 283.1, 202.47, 280.3, 194.46, 284.71, 192.45, 301.13, 187.24, 324.77, 169.21, 351.62, 180.03, 384.87, 199.26, 380.86, 239.73, 391.68, 262.17, 401.7, 315.05, 427.74, 292.62, 457.79, 259.76, 468.61, 256.16, 472.09, 253.71, 472.09, 253.71, 472.49, 243.29, 488.51, 244.1, 483.71, 257.72, 477.3, 265.73, 486.11, 273.74, 490.52, 279.35, 469.28, 282.16, 442.84, 314.21, 427.62, 332.24, 405.18, 352.27, 404.38, 388.33, 391.16, 408.36, 373.53, 410.37, 353.09, 345.46, 335.87, 369.5, 319.04, 392.74, 317.03, 413.17, 327.85, 425.99, 226.09, 426.39, 220.88, 399.15, 221.28, 398.35, 220.48, 356.68, 218.87, 338.25, 224.48, 318.22, 239.71, 300.19, 240.51, 298.99, 238.11, 259.32, 220.08, 237.28, 192.03, 192.81, 180.01, 178.79, 168.39, 157.15, 143.95, 113.88, 128.73, 85.04, 128.73, 85.04, 113.1, 84.23, 95.07, 72.62, 80.25, 67.41, 84.25, 60.2, 107.49, 66.61, 109.9, 63.0, 98.68, 19.33, 102.68, 16.12, 106.69, 10.91, 111.1, 13.32, 116.31, 18.13, 123.92, 38.56, 121.92, 25.34, 124.72, 24.14, 126.72, 26.14]], "area": 45961.744550000025, "iscrowd": 0, "image_id": 103556, "bbox": [80.25, 10.91, 410.27, 415.48], "category_id": 1, "id": 1204361, "split": "val", "sentences": [{"tokens": ["a", "girl", "in", "a", "black", "sports", "top", "with", "a", "tennis", "racquet", "in", "her", "right", "hand"], "raw": "A girl in a black sports top with a tennis racquet in her right hand.", "sent_id": 97346, "sent": "a girl in a black sports top with a tennis racquet in her right hand"}, {"tokens": ["a", "woman", "wearing", "a", "black", "tank", "top", "swinging", "a", "tennis", "racket"], "raw": "a woman wearing a black tank top swinging a tennis racket", "sent_id": 97347, "sent": "a woman wearing a black tank top swinging a tennis racket"}], "file_name": "COCO_train2014_000000103556_1204361.jpg", "ann_id": 1204361, "sent_ids": [97346, 97347], "ref_id": 42463}, {"segmentation": [[95.25, 4.51, 60.16, 13.54, 39.1, 30.58, 27.07, 51.64, 19.05, 80.72, 27.07, 108.79, 38.1, 125.84, 63.17, 135.86, 92.25, 133.86, 112.3, 118.82, 131.35, 105.78, 152.41, 62.67, 145.39, 31.58, 136.36, 13.54, 98.26, 3.51]], "area": 13024.2737, "iscrowd": 0, "image_id": 234699, "bbox": [19.05, 3.51, 133.36, 132.35], "category_id": 60, "id": 1078552, "split": "val", "sentences": [{"tokens": ["black", "grapes", "on", "a", "bread"], "raw": "BLACK GRAPES ON A BREAD.", "sent_id": 97418, "sent": "black grapes on a bread"}, {"tokens": ["a", "powdered", "blackberry", "donut", "with", "real", "blackberries", "on", "top"], "raw": "A powdered blackberry donut with real blackberries on top.", "sent_id": 97419, "sent": "a powdered blackberry donut with real blackberries on top"}], "file_name": "COCO_train2014_000000234699_1078552.jpg", "ann_id": 1078552, "sent_ids": [97418, 97419], "ref_id": 42493}, {"segmentation": [[195.56, 2.37, 167.11, 149.33, 175.41, 165.93, 170.67, 195.56, 200.3, 195.56, 202.67, 128.0, 225.19, 69.93, 226.37, 1.19], [271.41, 1.19, 276.15, 43.85, 297.48, 112.59, 298.67, 55.7, 324.74, 29.63, 324.74, 2.37], [384.0, 48.59, 393.48, 146.96, 406.52, 114.96, 395.85, 54.52]], "area": 10699.51935, "iscrowd": 0, "image_id": 204529, "bbox": [167.11, 1.19, 239.41, 194.37], "category_id": 1, "id": 1755762, "split": "val", "sentences": [{"tokens": ["a", "guy", "who", "is", "wearing", "orange", "color", "shirt"], "raw": "A guy who is wearing orange color shirt", "sent_id": 97469, "sent": "a guy who is wearing orange color shirt"}, {"tokens": ["the", "left", "most", "person"], "raw": "The left most person", "sent_id": 97470, "sent": "the left most person"}], "file_name": "COCO_train2014_000000204529_1755762.jpg", "ann_id": 1755762, "sent_ids": [97469, 97470], "ref_id": 42515}, {"segmentation": [[356.1, 112.56, 495.04, 109.22, 499.48, 113.11, 508.37, 133.12, 508.93, 160.91, 501.71, 161.46, 493.37, 159.24, 486.7, 159.8, 476.7, 159.8, 470.03, 160.91, 462.8, 145.9, 458.36, 146.46, 458.91, 160.35, 454.47, 158.69, 445.58, 159.8, 445.02, 160.91, 436.13, 143.12, 428.35, 139.23, 428.9, 147.57, 437.24, 165.35, 433.91, 178.69, 391.67, 174.8, 390.0, 167.02, 385.56, 164.24, 380.0, 164.8, 377.22, 162.02, 376.66, 155.35, 387.22, 159.24, 391.11, 154.24, 387.22, 145.35, 394.45, 142.57, 395.56, 137.57, 385.56, 132.57, 375.0, 137.01, 355.55, 130.9, 339.43, 130.9, 333.32, 136.46, 336.1, 140.9, 333.32, 140.35, 324.98, 136.46, 321.65, 137.57, 328.31, 141.46, 333.87, 148.13, 337.21, 175.36, 332.76, 179.8, 331.65, 186.47, 324.98, 194.25, 319.42, 188.7, 315.53, 182.03, 303.86, 178.14, 296.08, 173.13, 294.97, 168.69, 299.42, 167.58, 294.97, 149.24, 297.19, 144.24, 319.42, 140.35, 318.87, 132.01, 329.98, 134.23, 343.32, 118.12]], "area": 9002.597600000001, "iscrowd": 0, "image_id": 380820, "bbox": [294.97, 109.22, 213.96, 85.03], "category_id": 8, "id": 1372692, "split": "val", "sentences": [{"tokens": ["a", "van"], "raw": "a van", "sent_id": 97649, "sent": "a van"}, {"tokens": ["a", "silver", "van", "with", "no", "windows"], "raw": "a silver van with no windows", "sent_id": 97650, "sent": "a silver van with no windows"}], "file_name": "COCO_train2014_000000380820_1372692.jpg", "ann_id": 1372692, "sent_ids": [97649, 97650], "ref_id": 42586}, {"segmentation": [[34.08, 162.24, 42.15, 184.16, 39.84, 210.11, 39.84, 225.11, 54.84, 242.41, 80.79, 255.67, 94.06, 249.33, 97.52, 238.95, 110.21, 229.14, 125.2, 219.34, 140.2, 207.81, 151.73, 207.23, 156.92, 186.47, 140.2, 159.36, 121.74, 140.9, 99.82, 132.83, 75.03, 128.22, 54.84, 133.98, 36.96, 147.25, 35.23, 161.09]], "area": 10544.0321, "iscrowd": 0, "image_id": 391703, "bbox": [34.08, 128.22, 122.84, 127.45], "category_id": 51, "id": 712653, "split": "val", "sentences": [{"tokens": ["cream", "colored", "dipping", "sauce"], "raw": "Cream colored dipping sauce.", "sent_id": 97733, "sent": "cream colored dipping sauce"}, {"tokens": ["dip", "in", "cup", "on", "left", "of", "the", "plate"], "raw": "dip in cup on left of the plate", "sent_id": 97734, "sent": "dip in cup on left of the plate"}], "file_name": "COCO_train2014_000000391703_712653.jpg", "ann_id": 712653, "sent_ids": [97733, 97734], "ref_id": 42619}, {"segmentation": [[118.11, 292.88, 125.8, 292.18, 128.59, 290.78, 132.09, 290.78, 139.78, 287.98, 145.37, 286.59, 147.46, 279.6, 142.57, 271.21, 140.47, 262.13, 135.58, 243.95, 133.49, 232.77, 130.69, 218.79, 127.89, 213.9, 127.2, 211.81, 127.2, 208.31, 126.5, 204.12, 131.39, 191.54, 139.78, 179.66, 148.86, 165.68, 153.05, 159.39, 155.15, 150.31, 155.15, 144.02, 157.95, 139.12, 157.25, 128.64, 160.04, 112.57, 159.34, 106.28, 157.25, 99.29, 151.66, 80.42, 150.26, 70.63, 146.76, 63.64, 140.47, 53.16, 136.98, 46.17, 132.09, 41.28, 129.29, 39.18, 120.21, 29.4, 113.92, 18.92, 106.93, 14.72, 101.34, 14.02, 92.25, 14.72, 85.26, 17.52, 81.07, 20.31, 78.97, 23.11, 77.58, 30.1, 78.27, 34.29, 81.07, 41.28, 79.67, 51.76, 86.66, 57.35, 87.36, 58.05, 94.35, 58.75, 95.05, 59.45, 97.84, 61.55, 93.65, 72.03, 92.25, 79.02, 92.25, 88.11, 92.95, 93.0, 93.65, 93.7, 94.35, 97.19, 95.75, 99.99, 95.75, 120.25, 95.75, 120.25, 98.54, 132.13, 102.04, 134.23, 103.43, 144.71, 102.04, 148.91, 100.64, 156.59, 98.54, 170.57, 95.75, 180.36, 95.75, 188.04, 92.95, 202.02, 92.95, 213.9, 92.95, 227.88, 97.14, 236.97, 97.84, 244.65, 99.24, 254.44, 100.64, 260.03, 100.64, 265.62, 104.13, 272.61, 100.64, 279.6, 92.25, 283.79, 87.36, 287.28, 87.36, 287.98, 81.77, 292.88, 90.85, 294.27, 91.55, 294.27, 92.95, 294.27, 95.05, 294.27, 97.14, 294.27, 106.23, 294.27, 108.33, 294.27, 111.12, 293.57, 114.62, 293.57, 117.41, 293.57, 118.11, 293.57]], "area": 13393.799499999994, "iscrowd": 0, "image_id": 141121, "bbox": [77.58, 14.02, 82.46, 280.25], "category_id": 1, "id": 431700, "split": "val", "sentences": [{"tokens": ["man", "in", "blue", "jacket", "with", "red", "gloves"], "raw": "man in blue jacket with red gloves", "sent_id": 97762, "sent": "man in blue jacket with red gloves"}, {"tokens": ["father", "on", "ski", "'", "s"], "raw": "Father on ski's", "sent_id": 97763, "sent": "father on ski ' s"}], "file_name": "COCO_train2014_000000141121_431700.jpg", "ann_id": 431700, "sent_ids": [97762, 97763], "ref_id": 42630}, {"segmentation": [[593.75, 68.19, 582.19, 71.09, 574.47, 77.83, 568.69, 84.58, 559.05, 98.08, 549.41, 126.99, 537.85, 142.41, 526.28, 153.02, 515.68, 169.4, 499.29, 191.57, 486.76, 207.96, 482.91, 233.02, 482.91, 259.04, 494.47, 295.67, 501.22, 302.42, 513.75, 316.88, 519.53, 316.88, 531.1, 314.95, 537.85, 305.31, 539.77, 275.43, 542.67, 262.9, 554.23, 248.44, 572.55, 248.44, 581.22, 249.4, 593.75, 249.4, 612.07, 252.3, 624.6, 247.48, 632.31, 242.66, 636.16, 223.38, 637.13, 198.32, 637.13, 145.31, 637.13, 109.64, 635.2, 83.62, 611.1, 63.38, 603.39, 61.45, 602.43, 61.45]], "area": 23370.480799999998, "iscrowd": 0, "image_id": 235582, "bbox": [482.91, 61.45, 154.22, 255.43], "category_id": 1, "id": 557819, "split": "val", "sentences": [{"tokens": ["man", "on", "right"], "raw": "MAN ON RIGHT", "sent_id": 97871, "sent": "man on right"}, {"tokens": ["a", "man", "wearing", "a", "black", "shirt", "at", "dinner"], "raw": "a man wearing a black shirt at dinner", "sent_id": 97872, "sent": "a man wearing a black shirt at dinner"}], "file_name": "COCO_train2014_000000235582_557819.jpg", "ann_id": 557819, "sent_ids": [97871, 97872], "ref_id": 42673}, {"segmentation": [[261.84, 77.8, 300.7, 82.44, 354.64, 70.84, 391.18, 81.86, 405.68, 98.68, 414.96, 132.32, 416.7, 161.32, 412.64, 171.19, 414.96, 181.63, 419.03, 212.95, 416.12, 221.07, 413.8, 208.31, 406.26, 186.27, 399.3, 167.12, 396.4, 188.59, 390.02, 221.07, 386.54, 182.21, 371.46, 157.84, 354.06, 139.28, 332.6, 157.26, 293.16, 155.52, 257.78, 150.3, 257.78, 150.3, 254.88, 188.59, 254.88, 215.27, 249.08, 210.05, 246.18, 185.69, 240.38, 196.13, 232.84, 218.17, 235.16, 178.73, 234.58, 159.58, 224.14, 150.3, 210.22, 156.68, 211.38, 171.19, 214.28, 189.75, 206.74, 211.79, 197.45, 224.55, 196.29, 217.01, 187.01, 179.31, 185.27, 170.61, 181.21, 161.32, 172.51, 137.54, 174.83, 132.9, 189.33, 134.64, 195.71, 118.4, 203.84, 99.84, 211.38, 89.4, 229.36, 80.12, 241.54, 77.22]], "area": 19912.591999999997, "iscrowd": 0, "image_id": 127286, "bbox": [172.51, 70.84, 246.52, 153.71], "category_id": 24, "id": 588185, "split": "val", "sentences": [{"tokens": ["the", "zebra", "in", "full", "view"], "raw": "The zebra in full view.", "sent_id": 97887, "sent": "the zebra in full view"}, {"tokens": ["zebra", "in", "front"], "raw": "zebra in front", "sent_id": 97888, "sent": "zebra in front"}], "file_name": "COCO_train2014_000000127286_588185.jpg", "ann_id": 588185, "sent_ids": [97887, 97888], "ref_id": 42679}, {"segmentation": [[522.91, 419.28, 513.31, 380.91, 519.07, 311.82, 529.62, 281.12, 523.86, 253.3, 476.85, 236.03, 471.09, 220.68, 493.16, 209.16, 507.55, 184.22, 527.7, 186.14, 514.27, 219.72, 548.81, 213.96, 548.81, 189.97, 556.49, 171.74, 600.62, 183.26, 592.95, 213.0, 639.0, 242.74, 637.08, 273.45, 606.38, 279.2, 603.5, 333.89, 606.38, 421.2, 575.68, 414.49, 571.84, 390.5, 557.45, 361.72, 542.09, 383.78, 537.3, 382.82, 542.09, 407.77, 520.03, 406.81]], "area": 20832.232, "iscrowd": 0, "image_id": 156170, "bbox": [471.09, 171.74, 167.91, 249.46], "category_id": 1, "id": 491976, "split": "val", "sentences": [{"tokens": ["man", "on", "right", "wearing", "white", "shirt", "and", "orange", "shorts"], "raw": "Man on right wearing white shirt and orange shorts.", "sent_id": 97949, "sent": "man on right wearing white shirt and orange shorts"}, {"tokens": ["a", "fat", "person", "with", "white", "tshirt", "throwing", "an", "yellow", "disk"], "raw": "a fat person with white tshirt throwing an yellow disk.", "sent_id": 97950, "sent": "a fat person with white tshirt throwing an yellow disk"}], "file_name": "COCO_train2014_000000156170_491976.jpg", "ann_id": 491976, "sent_ids": [97949, 97950], "ref_id": 42706}, {"segmentation": [[56.08, 119.16, 113.65, 94.69, 118.68, 91.82, 125.88, 78.15, 136.67, 89.66, 139.55, 111.24, 156.82, 143.62, 154.66, 159.45, 184.16, 163.77, 207.18, 172.4, 228.77, 195.43, 254.67, 238.6, 276.26, 263.06, 269.06, 303.36, 282.01, 342.21, 273.38, 362.36, 251.79, 373.15, 230.21, 363.8, 227.33, 336.45, 223.01, 299.04, 223.73, 285.37, 190.63, 303.36, 176.96, 309.83, 174.09, 329.26, 184.16, 350.13, 204.31, 383.22, 190.63, 426.39, 174.81, 435.03, 148.18, 426.39, 129.48, 396.89, 125.16, 383.22, 93.5, 333.58, 65.44, 337.17, 32.34, 281.05, 35.22, 262.34, 44.57, 216.29, 61.84, 202.62, 63.28, 191.11, 78.39, 184.64, 56.08, 160.17, 48.89, 155.85, 33.06, 147.22, 26.58, 128.51, 56.08, 120.6]], "area": 48089.38649999998, "iscrowd": 0, "image_id": 443916, "bbox": [26.58, 78.15, 255.43, 356.88], "category_id": 23, "id": 2210352, "split": "val", "sentences": [{"tokens": ["a", "teddy", "bear", "in", "a", "yellow", "shirt", "with", "an", "orange", "pumpkin", "basket"], "raw": "A teddy bear in a yellow shirt with an orange pumpkin basket.", "sent_id": 97966, "sent": "a teddy bear in a yellow shirt with an orange pumpkin basket"}, {"tokens": ["a", "black", "bear", "with", "a", "candy", "bowl"], "raw": "A black bear with a candy bowl.", "sent_id": 97967, "sent": "a black bear with a candy bowl"}], "file_name": "COCO_train2014_000000443916_2210352.jpg", "ann_id": 2210352, "sent_ids": [97966, 97967], "ref_id": 42712}, {"segmentation": [[464.32, 252.57, 458.52, 250.91, 465.98, 246.22, 468.74, 243.18, 467.91, 229.09, 465.98, 220.53, 462.94, 208.38, 455.49, 204.51, 451.34, 199.82, 451.07, 193.47, 452.72, 190.43, 473.44, 179.93, 493.6, 173.3, 509.06, 172.2, 522.04, 177.45, 533.92, 184.35, 539.44, 192.64, 541.65, 200.09, 540.27, 210.04, 540.82, 216.94, 536.96, 223.29, 533.92, 229.09, 525.91, 237.65, 523.7, 237.93, 523.43, 243.18, 527.29, 242.63, 528.67, 246.22, 527.02, 247.6, 532.54, 247.87, 535.3, 252.29, 538.89, 253.67, 549.11, 255.88, 560.71, 263.06, 570.38, 283.5, 577.83, 299.24, 539.17, 297.03, 538.89, 290.68, 534.47, 290.13, 520.11, 287.37, 511.83, 286.54, 511.83, 279.08, 500.23, 279.63, 493.87, 280.74, 481.72, 282.95, 466.81, 282.4, 467.09, 267.76, 466.26, 257.26]], "area": 8978.015399999993, "iscrowd": 0, "image_id": 24689, "bbox": [451.07, 172.2, 126.76, 127.04], "category_id": 1, "id": 482497, "split": "val", "sentences": [{"tokens": ["a", "small", "boy", "wearing", "a", "plaid", "cap", "eating", "pizza"], "raw": "A small boy wearing a plaid cap eating pizza.", "sent_id": 97973, "sent": "a small boy wearing a plaid cap eating pizza"}, {"tokens": ["dirty", "blonde", "hair", "child", "wearing", "a", "plaid", "cap", "taking", "a", "bite", "of", "his", "pizza", "with", "his", "eyes", "closed"], "raw": "Dirty blonde hair child wearing a plaid cap taking a bite of his pizza with his eyes closed.", "sent_id": 97974, "sent": "dirty blonde hair child wearing a plaid cap taking a bite of his pizza with his eyes closed"}], "file_name": "COCO_train2014_000000024689_482497.jpg", "ann_id": 482497, "sent_ids": [97973, 97974], "ref_id": 42716}, {"segmentation": [[128.28, 0.0, 93.46, 68.54, 96.21, 82.28, 91.63, 85.95, 100.79, 135.43, 105.38, 134.51, 108.12, 142.76, 111.79, 142.76, 111.79, 129.02, 170.43, 127.18, 172.27, 135.43, 176.85, 134.51, 174.1, 124.43, 179.6, 107.02, 193.34, 72.21, 183.26, 66.71, 163.1, 67.62, 153.94, 57.54, 155.77, 44.72, 162.19, 35.55, 162.19, 30.05, 150.27, 31.89, 147.53, 21.81, 150.27, 10.81, 146.61, 2.57, 133.78, 2.57]], "area": 8310.604699999998, "iscrowd": 0, "image_id": 332158, "bbox": [91.63, 0.0, 101.71, 142.76], "category_id": 63, "id": 111555, "split": "val", "sentences": [{"tokens": ["a", "green", "couch", "with", "a", "person", "sitting", "on", "it"], "raw": "A green couch with a person sitting on it", "sent_id": 98019, "sent": "a green couch with a person sitting on it"}, {"tokens": ["the", "grey", "and", "green", "sofa", "with", "a", "woman", "using", "a", "laptop", "sitting", "on", "it"], "raw": "The grey and green sofa with a woman using a laptop sitting on it.", "sent_id": 98020, "sent": "the grey and green sofa with a woman using a laptop sitting on it"}], "file_name": "COCO_train2014_000000332158_111555.jpg", "ann_id": 111555, "sent_ids": [98019, 98020], "ref_id": 42733}, {"segmentation": [[383.02, 356.08, 433.41, 343.25, 481.98, 346.0, 557.12, 367.99, 602.02, 418.39, 501.22, 422.97, 276.73, 421.14, 301.47, 401.89, 355.53, 382.65], [213.5, 272.69, 201.59, 247.04, 204.34, 212.22, 226.33, 234.21, 269.39, 227.79, 262.06, 251.62, 264.81, 302.93, 269.39, 320.34, 276.73, 334.09, 219.0, 366.16, 207.09, 373.49, 198.84, 361.58, 206.17, 329.5, 203.42, 307.51, 203.42, 281.86]], "area": 24745.220000000005, "iscrowd": 0, "image_id": 64092, "bbox": [198.84, 212.22, 403.18, 210.75], "category_id": 19, "id": 58314, "split": "val", "sentences": [{"tokens": ["the", "brown", "horse", "the", "woman", "is", "sitting", "on"], "raw": "The brown horse the woman is sitting on.", "sent_id": 98032, "sent": "the brown horse the woman is sitting on"}, {"tokens": ["the", "horse", "the", "woman", "is", "riding"], "raw": "The horse the woman is riding", "sent_id": 98033, "sent": "the horse the woman is riding"}], "file_name": "COCO_train2014_000000064092_58314.jpg", "ann_id": 58314, "sent_ids": [98032, 98033], "ref_id": 42739}, {"segmentation": [[64.64, 426.43, 169.16, 320.53, 167.78, 180.25, 162.28, 90.86, 251.68, 45.48, 341.07, 22.1, 416.71, 66.11, 394.71, 110.11, 415.33, 178.88, 408.46, 183.0, 471.72, 187.13, 563.87, 243.52, 612.0, 271.02, 612.0, 513.07, 607.87, 548.83, 612.0, 573.58, 500.6, 533.7, 493.73, 601.09, 33.01, 601.09, 67.39, 434.68]], "area": 231636.01920000004, "iscrowd": 0, "image_id": 501177, "bbox": [33.01, 22.1, 578.99, 578.99], "category_id": 1, "id": 513811, "split": "val", "sentences": [{"tokens": ["a", "boy", "wearing", "a", "hat", "and", "talking", "on", "a", "mobile", "phone"], "raw": "A boy wearing a hat and talking on a mobile phone.", "sent_id": 98172, "sent": "a boy wearing a hat and talking on a mobile phone"}, {"tokens": ["a", "man", "smiling", "on", "his", "phone"], "raw": "a man smiling on his phone", "sent_id": 98173, "sent": "a man smiling on his phone"}], "file_name": "COCO_train2014_000000501177_513811.jpg", "ann_id": 513811, "sent_ids": [98172, 98173], "ref_id": 42797}, {"segmentation": [[366.61, 205.72, 382.22, 232.24, 389.0, 252.37, 390.88, 274.95, 387.68, 290.56, 395.2, 326.31, 395.02, 362.05, 393.32, 370.52, 388.24, 375.22, 394.07, 397.61, 399.91, 424.0, 373.76, 424.0, 283.26, 423.76, 246.2, 424.0, 246.2, 420.0, 247.33, 408.9, 249.96, 397.99, 260.88, 376.73, 263.62, 371.77, 261.55, 366.88, 245.18, 381.18, 234.46, 382.5, 226.37, 381.74, 221.48, 379.86, 214.71, 378.92, 209.06, 377.04, 209.06, 371.96, 208.69, 368.39, 196.65, 359.36, 196.65, 356.16, 194.01, 352.96, 193.26, 349.38, 197.02, 346.56, 201.73, 346.19, 204.55, 342.8, 213.01, 340.54, 232.02, 336.78, 242.36, 336.59, 260.61, 340.54, 270.96, 332.08, 284.69, 315.71, 284.5, 313.64, 276.79, 301.41, 268.89, 287.49, 268.89, 281.66, 270.96, 269.8, 272.84, 266.04, 273.22, 256.07, 283.0, 241.21, 287.89, 222.39, 289.21, 215.06, 285.82, 205.27, 273.78, 214.12, 270.39, 212.8, 262.87, 209.79, 258.92, 209.79, 255.53, 208.28, 252.9, 207.16, 246.13, 204.33, 243.3, 202.83, 236.15, 203.96, 233.14, 197.75, 228.44, 184.58, 222.42, 184.02, 214.52, 175.93, 207.56, 165.58, 203.23, 161.63, 198.53, 156.36, 198.15, 151.28, 203.98, 130.21, 210.0, 117.23, 225.43, 103.87, 230.32, 100.3, 230.32, 94.09, 225.99, 90.14, 222.98, 85.62, 222.42, 79.98, 226.75, 75.46, 236.53, 67.75, 243.68, 66.62, 251.96, 66.62, 271.34, 80.92, 291.47, 108.2, 295.98, 121.18, 301.62, 142.63, 301.81, 150.34, 313.1, 157.86, 330.22, 168.4, 350.92, 182.32, 358.82, 192.11, 355.81, 196.43]], "area": 41399.37740000002, "iscrowd": 0, "image_id": 577240, "bbox": [193.26, 66.62, 206.65, 357.38], "category_id": 1, "id": 1206502, "split": "val", "sentences": [{"tokens": ["a", "woman", "with", "earbuds", "in", "looking", "at", "her", "phone"], "raw": "A woman with earbuds in looking at her phone.", "sent_id": 98271, "sent": "a woman with earbuds in looking at her phone"}, {"tokens": ["a", "woman", "wearing", "a", "halter", "dress", "with", "her", "hair", "pinned", "up", "and", "earbuds", "in", "her", "ears", ",", "looking", "downward"], "raw": "A woman wearing a halter dress with her hair pinned up and earbuds in her ears, looking downward.", "sent_id": 98272, "sent": "a woman wearing a halter dress with her hair pinned up and earbuds in her ears , looking downward"}], "file_name": "COCO_train2014_000000577240_1206502.jpg", "ann_id": 1206502, "sent_ids": [98271, 98272], "ref_id": 42836}, {"segmentation": [[211.73, 291.58, 233.5, 304.98, 229.31, 326.75, 221.78, 341.82, 207.54, 357.73, 153.12, 382.01, 86.97, 395.41, 26.68, 395.41, 0.0, 392.06, 0.0, 324.24, 4.91, 313.35, 14.12, 314.19, 25.01, 306.65, 30.87, 306.65, 36.73, 289.91, 53.48, 285.72, 85.29, 285.72, 95.34, 285.72, 122.14, 281.54, 127.16, 287.4, 117.11, 286.56, 117.11, 300.79, 99.53, 311.68, 115.44, 311.68, 139.72, 307.49, 171.54, 299.96, 181.58, 293.26, 203.35, 289.91]], "area": 19688.024050000007, "iscrowd": 0, "image_id": 566301, "bbox": [0.0, 281.54, 233.5, 113.87], "category_id": 59, "id": 1076423, "split": "val", "sentences": [{"tokens": ["the", "middle", "pizza", "with", "a", "piece", "missing"], "raw": "The middle pizza with a piece missing.", "sent_id": 98282, "sent": "the middle pizza with a piece missing"}, {"tokens": ["pizza", "on", "a", "white", "plate", "in", "between", "two", "other", "pizzas", "on", "plates"], "raw": "Pizza on a white plate in between two other pizzas on plates.", "sent_id": 98283, "sent": "pizza on a white plate in between two other pizzas on plates"}], "file_name": "COCO_train2014_000000566301_1076423.jpg", "ann_id": 1076423, "sent_ids": [98282, 98283], "ref_id": 42841}, {"segmentation": [[131.11, 492.62, 142.67, 477.19, 140.1, 461.77, 143.96, 442.49, 147.81, 433.49, 147.81, 419.35, 142.67, 402.64, 140.1, 388.51, 134.96, 379.51, 134.96, 367.94, 138.39, 360.84, 135.51, 355.38, 135.51, 349.34, 138.96, 342.43, 144.71, 338.12, 150.18, 338.12, 151.04, 337.54, 150.18, 334.96, 150.75, 332.08, 152.48, 329.2, 152.48, 326.62, 154.49, 324.03, 155.93, 320.29, 158.52, 317.99, 158.52, 310.22, 158.52, 301.59, 159.67, 299.01, 163.69, 296.99, 166.57, 296.99, 167.43, 299.58, 168.01, 306.77, 168.01, 309.93, 169.73, 310.8, 171.75, 308.5, 176.64, 308.21, 176.92, 310.22, 172.32, 313.39, 168.87, 315.97, 165.71, 317.99, 164.85, 321.15, 165.42, 325.47, 165.71, 329.78, 164.56, 334.38, 163.69, 338.69, 163.12, 346.46, 163.12, 352.5, 165.42, 354.23, 163.12, 357.39, 162.83, 360.84, 165.42, 362.57, 166.57, 366.59, 168.01, 366.88, 179.23, 373.5, 182.96, 377.23, 185.55, 378.96, 191.3, 378.67, 195.04, 377.81, 199.36, 376.37, 200.22, 376.37, 203.38, 373.78, 207.41, 373.78, 209.42, 373.5, 212.01, 371.77, 215.18, 368.61, 218.91, 367.46, 218.63, 377.81, 210.86, 384.71, 208.27, 387.59, 200.8, 390.75, 194.76, 393.63, 189.87, 395.35, 186.99, 394.2, 182.68, 394.49, 180.38, 394.2, 179.23, 394.49, 179.23, 400.53, 180.09, 407.43, 181.24, 414.33, 181.24, 424.4, 180.38, 426.99, 179.23, 430.44, 178.36, 435.33, 180.09, 439.93, 179.51, 444.25, 181.81, 452.01, 181.81, 452.87, 182.96, 459.78, 182.96, 465.53, 182.96, 470.99, 182.96, 489.69]], "area": 6637.206749999999, "iscrowd": 0, "image_id": 565018, "bbox": [131.11, 296.99, 87.8, 195.63], "category_id": 1, "id": 2150281, "split": "val", "sentences": [{"tokens": ["the", "shorter", "guy", "in", "yellow", "shirt", "trying", "to", "catch", "frisbee"], "raw": "The shorter guy in yellow shirt trying to catch frisbee.", "sent_id": 98381, "sent": "the shorter guy in yellow shirt trying to catch frisbee"}, {"tokens": ["a", "man", "in", "a", "yellow", "t", "-", "shirt", "reaching", "for", "a", "frisbee"], "raw": "A man in a yellow t-shirt reaching for a Frisbee.", "sent_id": 98382, "sent": "a man in a yellow t - shirt reaching for a frisbee"}], "file_name": "COCO_train2014_000000565018_2150281.jpg", "ann_id": 2150281, "sent_ids": [98381, 98382], "ref_id": 42875}, {"segmentation": [[1.44, 463.1, 40.27, 524.94, 47.46, 535.01, 140.94, 576.72, 186.97, 629.93, 1.44, 628.49]], "area": 14010.704499999994, "iscrowd": 0, "image_id": 28988, "bbox": [1.44, 463.1, 185.53, 166.83], "category_id": 21, "id": 1408066, "split": "val", "sentences": [{"tokens": ["a", "blurry", "part", "of", "an", "animal", "that", "is", "not", "completely", "visible"], "raw": "A blurry part of an animal that is not completely visible.", "sent_id": 98389, "sent": "a blurry part of an animal that is not completely visible"}, {"tokens": ["ear", "of", "an", "animal", "not", "in", "the", "picture"], "raw": "ear of an animal not in the picture", "sent_id": 98390, "sent": "ear of an animal not in the picture"}], "file_name": "COCO_train2014_000000028988_1408066.jpg", "ann_id": 1408066, "sent_ids": [98389, 98390], "ref_id": 42878}, {"segmentation": [[83.06, 400.33, 69.85, 383.81, 67.37, 363.16, 68.61, 354.9, 71.91, 345.4, 76.04, 333.84, 76.04, 316.08, 78.11, 290.88, 82.65, 276.43, 84.72, 269.82, 84.72, 262.8, 88.02, 251.65, 92.15, 244.21, 99.17, 244.21, 122.71, 238.87, 145.02, 230.2, 151.62, 224.42, 154.51, 217.39, 157.41, 209.55, 158.23, 206.24, 152.45, 199.22, 152.45, 191.79, 151.21, 183.53, 148.73, 174.85, 148.73, 169.9, 150.38, 167.83, 151.21, 163.29, 148.32, 148.86, 152.04, 126.56, 163.19, 110.86, 184.66, 101.78, 202.01, 104.26, 219.77, 110.86, 231.34, 124.91, 238.36, 137.3, 240.83, 144.73, 241.25, 156.3, 242.49, 165.79, 247.86, 174.06, 246.2, 194.29, 245.79, 200.08, 247.86, 203.38, 265.2, 217.42, 270.16, 224.44, 329.46, 244.24, 340.2, 341.95, 343.5, 361.77, 366.22, 490.31, 373.65, 559.82, 372.41, 563.12, 372.0, 565.6, 372.0, 570.97, 372.41, 575.1, 377.37, 586.25, 380.67, 592.45, 381.5, 596.99, 377.37, 602.77, 374.48, 608.14, 372.41, 613.92, 370.76, 615.99, 369.11, 615.99, 362.5, 605.66, 360.85, 600.29, 357.54, 599.05, 354.24, 600.71, 353.41, 606.08, 353.83, 611.86, 353.0, 616.81, 348.87, 620.12, 346.39, 620.53, 340.61, 620.12, 340.61, 610.62, 341.02, 600.29, 340.61, 591.62, 339.78, 579.64, 341.44, 570.56, 341.44, 569.32, 334.41, 565.19, 334.0, 563.12, 324.09, 523.47, 321.2, 512.32, 321.2, 516.86, 322.02, 524.71, 324.09, 534.62, 324.91, 544.95, 325.33, 563.95, 326.57, 596.58, 324.5, 605.66, 318.31, 601.12, 315.42, 593.27, 311.7, 610.62, 310.87, 639.09, 144.84, 637.85, 143.19, 623.81, 140.71, 611.42, 140.3, 606.05, 138.64, 599.44, 111.8, 597.37, 93.63, 589.53, 81.24, 587.88, 98.17, 510.55, 106.02, 482.05, 106.02, 477.92, 106.02, 470.07, 109.32, 458.51, 118.82, 443.64, 129.97, 408.83, 130.38, 398.5, 130.38, 394.37, 125.43, 393.55, 120.89, 398.09, 115.93, 402.63, 109.73, 408.42, 108.91, 409.66, 102.71, 410.89, 98.58, 410.89, 94.45, 410.07, 89.91, 407.18, 82.89, 401.81]], "area": 113566.26360000002, "iscrowd": 0, "image_id": 512282, "bbox": [67.37, 101.78, 314.13, 537.31], "category_id": 1, "id": 448727, "split": "val", "sentences": [{"tokens": ["a", "man", "talking", "on", "a", "mobile", "phone", "wearing", "an", "open", "suit", "coat", ",", "jeans", "and", "a", "blue", "shirt", "carrying", "a", "bag"], "raw": "A man talking on a mobile phone wearing an open suit coat, jeans and a blue shirt carrying a bag", "sent_id": 98420, "sent": "a man talking on a mobile phone wearing an open suit coat , jeans and a blue shirt carrying a bag"}, {"tokens": ["a", "man", "in", "a", "blue", "shirt", "and", "black", "jacket", "using", "a", "red", "mobile", "phone"], "raw": "A man in a blue shirt and black jacket using a red mobile phone", "sent_id": 98421, "sent": "a man in a blue shirt and black jacket using a red mobile phone"}], "file_name": "COCO_train2014_000000512282_448727.jpg", "ann_id": 448727, "sent_ids": [98420, 98421], "ref_id": 42890}, {"segmentation": [[110.92, 425.0, 119.7, 389.96, 148.26, 340.55, 193.28, 214.25, 222.93, 120.91, 229.52, 103.34, 236.11, 53.92, 240.5, 51.72, 259.17, 67.1, 264.66, 108.83, 214.15, 239.51, 136.18, 425.0]], "area": 10891.029050000001, "iscrowd": 0, "image_id": 54282, "bbox": [110.92, 51.72, 153.74, 373.28], "category_id": 35, "id": 2201924, "split": "val", "sentences": [{"tokens": ["one", "ski"], "raw": "One ski", "sent_id": 98471, "sent": "one ski"}, {"tokens": ["a", "black", "ski"], "raw": "A black ski.", "sent_id": 98472, "sent": "a black ski"}], "file_name": "COCO_train2014_000000054282_2201924.jpg", "ann_id": 2201924, "sent_ids": [98471, 98472], "ref_id": 42909}, {"segmentation": [[524.22, 230.5, 554.43, 205.69, 569.53, 199.22, 596.49, 191.67, 611.6, 207.85, 631.01, 232.66, 633.17, 252.07, 627.78, 273.65, 601.89, 335.13, 591.1, 342.68, 547.96, 340.52, 523.15, 309.24, 529.62, 274.73]], "area": 12494.183099999995, "iscrowd": 0, "image_id": 17962, "bbox": [523.15, 191.67, 110.02, 151.01], "category_id": 27, "id": 1421511, "split": "val", "sentences": [{"tokens": ["a", "red", "color", "backpack"], "raw": "A red color backpack", "sent_id": 98680, "sent": "a red color backpack"}, {"tokens": ["a", "red", "backpack", "is", "worn", "by", "a", "person", "going", "skiing"], "raw": "A red backpack is worn by a person going skiing.", "sent_id": 98681, "sent": "a red backpack is worn by a person going skiing"}], "file_name": "COCO_train2014_000000017962_1421511.jpg", "ann_id": 1421511, "sent_ids": [98680, 98681], "ref_id": 42994}, {"segmentation": [[253.54, 263.02, 260.05, 246.77, 265.46, 233.77, 268.71, 225.1, 275.21, 216.43, 282.8, 207.77, 296.88, 198.01, 312.05, 190.43, 328.31, 183.93, 351.06, 181.76, 400.9, 178.51, 427.99, 180.68, 391.15, 225.1, 455.08, 270.61, 475.67, 248.94, 444.24, 212.1, 464.83, 191.51, 509.26, 208.85, 525.51, 218.6, 535.26, 230.52, 539.59, 250.02, 539.59, 259.77, 539.59, 270.61, 530.93, 286.86, 519.01, 308.53, 508.17, 320.45, 507.09, 325.87, 508.17, 338.87, 513.59, 352.96, 508.17, 364.88, 496.25, 389.8, 476.75, 396.3, 461.58, 400.63, 409.57, 406.05, 390.07, 413.63, 366.23, 423.39, 356.48, 423.39, 322.89, 423.39, 314.22, 412.55, 302.3, 397.38, 293.63, 390.88, 280.63, 389.8, 265.46, 374.63, 260.05, 359.46, 258.96, 347.54, 249.21, 332.37, 234.04, 316.12, 237.29, 299.86, 247.04, 287.95, 249.21, 271.69, 252.46, 256.52]], "area": 52842.52445000002, "iscrowd": 0, "image_id": 226046, "bbox": [234.04, 178.51, 305.55, 244.88], "category_id": 54, "id": 309730, "split": "val", "sentences": [{"tokens": ["a", "sandwich", "with", "a", "knife", "embedded", "on", "it"], "raw": "a sandwich with a knife embedded on it", "sent_id": 98706, "sent": "a sandwich with a knife embedded on it"}, {"tokens": ["a", "sandwich", "with", "a", "knife", "in", "it"], "raw": "A sandwich with a knife in it.", "sent_id": 98707, "sent": "a sandwich with a knife in it"}], "file_name": "COCO_train2014_000000226046_309730.jpg", "ann_id": 309730, "sent_ids": [98706, 98707], "ref_id": 43002}, {"segmentation": [[325.03, 563.34, 330.79, 536.01, 310.65, 466.98, 306.34, 389.31, 337.98, 347.61, 336.54, 324.59, 352.36, 290.08, 371.06, 298.71, 388.31, 314.53, 389.75, 353.36, 389.75, 363.43, 408.45, 377.81, 418.52, 405.13, 421.39, 409.45, 418.52, 439.65, 404.13, 449.72, 418.52, 454.03, 424.0, 458.35, 419.96, 504.37, 395.51, 557.58]], "area": 22469.601800000004, "iscrowd": 0, "image_id": 193682, "bbox": [306.34, 290.08, 117.66, 273.26], "category_id": 1, "id": 476678, "split": "val", "sentences": [{"tokens": ["a", "male", "spectator", "in", "a", "blue", "shirt"], "raw": "a male spectator in a blue shirt", "sent_id": 98714, "sent": "a male spectator in a blue shirt"}, {"tokens": ["the", "man", "in", "the", "blue", "shirt", "is", "a", "spectator", "at", "the", "tennis", "match"], "raw": "The man in the blue shirt is a spectator at the tennis match.", "sent_id": 98715, "sent": "the man in the blue shirt is a spectator at the tennis match"}], "file_name": "COCO_train2014_000000193682_476678.jpg", "ann_id": 476678, "sent_ids": [98714, 98715], "ref_id": 43006}, {"segmentation": [[304.9, 258.88, 300.58, 234.43, 309.21, 225.8, 320.72, 221.48, 345.17, 227.24, 352.36, 240.18, 353.8, 271.82, 369.62, 290.52, 391.19, 290.52, 399.82, 306.34, 408.45, 358.11, 422.83, 404.13, 396.94, 405.57, 384.0, 343.73, 376.81, 384.0, 382.56, 404.13, 287.64, 404.13, 297.71, 339.42, 286.2, 359.55, 274.7, 343.73, 281.89, 327.91, 290.52, 293.39, 294.83, 276.13, 296.27, 266.07, 302.02, 263.19, 304.9, 261.75, 303.46, 254.56]], "area": 16707.166, "iscrowd": 0, "image_id": 529624, "bbox": [274.7, 221.48, 148.13, 184.09], "category_id": 1, "id": 558035, "split": "val", "sentences": [{"tokens": ["the", "girl", "who", "is", "smiling"], "raw": "The girl who is smiling.", "sent_id": 98749, "sent": "the girl who is smiling"}, {"tokens": ["a", "tennis", "player", "facing", "the", "camera", "and", "shaking", "another", "player", "'", "s", "hand"], "raw": "A tennis player facing the camera and shaking another player's hand.", "sent_id": 98750, "sent": "a tennis player facing the camera and shaking another player ' s hand"}], "file_name": "COCO_train2014_000000529624_558035.jpg", "ann_id": 558035, "sent_ids": [98749, 98750], "ref_id": 43021}, {"segmentation": [[263.19, 464.54, 264.63, 394.07, 332.22, 389.75, 335.1, 339.42, 418.52, 343.73, 409.89, 447.28, 411.33, 581.03, 394.07, 576.72, 389.75, 509.12, 303.46, 503.37, 304.9, 581.03, 289.08, 581.03, 284.76, 506.25]], "area": 23271.53704999999, "iscrowd": 0, "image_id": 71796, "bbox": [263.19, 339.42, 155.33, 241.61], "category_id": 15, "id": 575695, "split": "val", "sentences": [{"tokens": ["the", "closest", "bench"], "raw": "the closest bench.", "sent_id": 98770, "sent": "the closest bench"}], "file_name": "COCO_train2014_000000071796_575695.jpg", "ann_id": 575695, "sent_ids": [98770], "ref_id": 43030}, {"segmentation": [[239.64, 536.68, 195.16, 506.55, 177.94, 463.5, 170.76, 427.62, 175.07, 403.23, 187.98, 378.83, 198.03, 365.92, 210.94, 357.31, 223.86, 348.7, 241.08, 345.83, 252.56, 345.83, 281.26, 350.13, 301.35, 355.87, 321.43, 371.66, 331.48, 388.88, 350.13, 421.88, 357.31, 452.02, 353.0, 495.07, 335.78, 520.9, 304.22, 536.68, 249.69, 543.86, 241.08, 542.42]], "area": 28481.187599999994, "iscrowd": 0, "image_id": 369509, "bbox": [170.76, 345.83, 186.55, 198.03], "category_id": 85, "id": 335095, "split": "val", "sentences": [{"tokens": ["a", "clock", "that", "has", "the", "time", "12", ":", "10", "on", "it"], "raw": "a clock that has the time 12:10 on it", "sent_id": 98773, "sent": "a clock that has the time 12 : 10 on it"}, {"tokens": ["a", "clock", "on", "the", "watch", "tower", "showing", "12", ":", "10", "pm"], "raw": "A clock on the watch tower showing 12:10 pm", "sent_id": 98774, "sent": "a clock on the watch tower showing 12 : 10 pm"}], "file_name": "COCO_train2014_000000369509_335095.jpg", "ann_id": 335095, "sent_ids": [98773, 98774], "ref_id": 43032}, {"segmentation": [[299.28, 303.64, 233.39, 315.27, 194.63, 347.56, 168.8, 387.61, 164.92, 449.62, 188.18, 471.58, 195.93, 476.75, 189.47, 437.99, 206.26, 385.03, 252.77, 341.1, 299.28, 330.77], [339.33, 301.05, 400.04, 325.6, 440.09, 374.69, 451.72, 443.16, 438.8, 463.83, 433.63, 406.99, 393.58, 357.9, 345.78, 335.94, 327.7, 329.48]], "area": 11056.607799999994, "iscrowd": 0, "image_id": 143334, "bbox": [164.92, 301.05, 286.8, 175.7], "category_id": 47, "id": 1885324, "split": "val", "sentences": [{"tokens": ["the", "second", "to", "largest", "measuring", "cup"], "raw": "The second to largest measuring cup", "sent_id": 98798, "sent": "the second to largest measuring cup"}, {"tokens": ["the", "second", "largest", "measuring", "cup"], "raw": "The second largest measuring cup.", "sent_id": 98799, "sent": "the second largest measuring cup"}], "file_name": "COCO_train2014_000000143334_1885324.jpg", "ann_id": 1885324, "sent_ids": [98798, 98799], "ref_id": 43042}, {"segmentation": [[1.44, 316.4, 57.53, 337.98, 81.98, 381.12, 119.37, 386.88, 146.7, 401.26, 250.25, 418.52, 307.78, 476.04, 326.47, 500.49, 316.4, 524.94, 339.42, 535.01, 382.56, 530.7, 396.94, 592.54, 378.25, 632.81, 4.31, 631.37]], "area": 81501.65709999998, "iscrowd": 0, "image_id": 219966, "bbox": [1.44, 316.4, 395.5, 316.41], "category_id": 1, "id": 503968, "split": "val", "sentences": [{"tokens": ["woman", "in", "white", "shirt", "holding", "baby"], "raw": "woman in white shirt holding baby", "sent_id": 98805, "sent": "woman in white shirt holding baby"}, {"tokens": ["a", "person", "in", "a", "white", "shirt"], "raw": "A person in a white shirt.", "sent_id": 98806, "sent": "a person in a white shirt"}], "file_name": "COCO_train2014_000000219966_503968.jpg", "ann_id": 503968, "sent_ids": [98805, 98806], "ref_id": 43045}, {"segmentation": [[217.77, 283.35, 466.18, 277.82, 471.71, 236.32, 450.13, 223.6, 460.09, 183.76, 483.88, 77.54, 628.83, 0.0, 640.0, 0.0, 640.0, 195.38, 640.0, 199.81, 640.0, 301.05, 640.0, 316.54, 640.0, 416.13, 640.0, 424.42, 640.0, 480.0, 51.24, 480.0, 32.99, 479.75, 202.28, 302.71]], "area": 143676.44939999998, "iscrowd": 0, "image_id": 338242, "bbox": [32.99, 0.0, 607.01, 480.0], "category_id": 15, "id": 574945, "split": "val", "sentences": [{"tokens": ["bench", "closest", "to", "camera"], "raw": "bench closest to camera", "sent_id": 98835, "sent": "bench closest to camera"}, {"tokens": ["the", "bench", "that", "is", "first"], "raw": "The bench that is first.", "sent_id": 98836, "sent": "the bench that is first"}], "file_name": "COCO_train2014_000000338242_574945.jpg", "ann_id": 574945, "sent_ids": [98835, 98836], "ref_id": 43060}, {"segmentation": [[234.32, 185.88, 253.94, 155.94, 269.42, 134.26, 283.87, 130.13, 259.1, 120.84, 275.61, 111.55, 303.48, 132.2, 329.29, 133.23, 363.35, 119.81, 388.13, 106.39, 416.0, 99.17, 444.9, 90.91, 454.19, 84.71, 472.77, 83.68, 499.61, 101.23, 524.39, 129.1, 530.58, 166.26, 521.29, 183.81, 515.1, 190.0, 482.06, 187.94, 454.19, 178.65, 418.06, 181.75, 407.74, 195.17, 388.13, 207.55, 380.9, 222.0, 352.0, 212.71, 335.48, 209.62, 305.55, 205.49, 292.13, 205.49, 273.55, 203.42, 265.29, 199.29, 248.77, 201.36, 234.32, 194.13]], "area": 23966.288049999996, "iscrowd": 0, "image_id": 397760, "bbox": [234.32, 83.68, 296.26, 138.32], "category_id": 20, "id": 64851, "split": "val", "sentences": [{"tokens": ["beer", "in", "the", "middle"], "raw": "beer in the middle", "sent_id": 98855, "sent": "beer in the middle"}, {"tokens": ["sheep", "facing", "left"], "raw": "sheep facing left", "sent_id": 98856, "sent": "sheep facing left"}], "file_name": "COCO_train2014_000000397760_64851.jpg", "ann_id": 64851, "sent_ids": [98855, 98856], "ref_id": 43068}, {"segmentation": [[133.31, 419.18, 100.37, 424.01, 36.09, 432.04, 85.91, 432.04, 35.29, 448.11, 34.49, 454.54, 113.22, 433.65, 120.45, 436.06, 203.21, 400.71, 255.43, 399.1, 258.65, 395.88, 202.41, 390.26]], "area": 2309.4817, "iscrowd": 0, "image_id": 101573, "bbox": [34.49, 390.26, 224.16, 64.28], "category_id": 84, "id": 1146258, "split": "val", "sentences": [{"tokens": ["notebook", "with", "papaer"], "raw": "notebook with papaer", "sent_id": 98867, "sent": "notebook with papaer"}, {"tokens": ["a", "notebook", "being", "held", "by", "one", "of", "the", "women"], "raw": "A notebook being held by one of the women.", "sent_id": 98868, "sent": "a notebook being held by one of the women"}], "file_name": "COCO_train2014_000000101573_1146258.jpg", "ann_id": 1146258, "sent_ids": [98867, 98868], "ref_id": 43074}, {"segmentation": [[308.49, 141.3, 295.55, 151.01, 285.84, 155.33, 276.13, 160.72, 272.9, 163.96, 268.58, 166.11, 265.35, 173.66, 262.11, 177.98, 256.72, 182.29, 254.56, 197.39, 253.48, 202.79, 256.72, 209.26, 254.56, 217.89, 256.72, 224.36, 259.96, 235.15, 264.27, 247.01, 272.9, 264.27, 275.06, 269.66, 280.45, 275.06, 297.71, 285.84, 309.57, 293.39, 319.28, 295.55, 335.46, 300.94, 358.11, 296.63, 394.79, 291.24, 406.65, 283.69, 417.44, 270.74, 431.46, 258.88, 435.78, 243.78, 444.4, 226.52, 443.33, 221.12, 441.17, 206.02, 441.17, 193.08, 440.09, 183.37, 436.85, 154.25, 432.54, 149.93, 409.89, 135.91, 400.18, 128.36, 381.84, 121.89, 323.6, 126.2, 281.53, 141.3, 258.88, 161.8, 277.21, 158.56, 284.76, 151.01]], "area": 26955.227399999992, "iscrowd": 0, "image_id": 74201, "bbox": [253.48, 121.89, 190.92, 179.05], "category_id": 51, "id": 710917, "split": "val", "sentences": [{"tokens": ["the", "plate", "with", "the", "orange", "food"], "raw": "the plate with the orange food", "sent_id": 98941, "sent": "the plate with the orange food"}, {"tokens": ["a", "bowl", "of", "carrots"], "raw": "a bowl of carrots", "sent_id": 98942, "sent": "a bowl of carrots"}], "file_name": "COCO_train2014_000000074201_710917.jpg", "ann_id": 710917, "sent_ids": [98941, 98942], "ref_id": 43104}, {"segmentation": [[290.38, 157.92, 277.38, 186.09, 276.3, 206.68, 241.63, 229.44, 210.2, 251.11, 173.36, 287.95, 151.69, 320.45, 140.86, 351.87, 144.11, 370.29, 171.2, 377.88, 203.7, 350.79, 214.54, 318.28, 219.95, 308.53, 237.29, 339.95, 232.96, 361.63, 288.22, 359.46, 333.72, 361.63, 360.81, 362.71, 362.98, 335.62, 367.31, 285.78, 385.73, 261.94, 395.49, 239.19, 399.82, 186.09, 401.99, 148.17, 401.99, 114.58, 384.65, 80.99, 371.65, 36.57, 362.98, 15.98, 341.31, 15.98, 334.81, 31.15, 334.81, 33.32, 349.98, 66.91, 358.65, 72.33, 362.98, 109.16, 357.56, 164.42, 336.98, 150.34, 320.72, 144.92, 292.55, 152.51]], "area": 39530.43915, "iscrowd": 0, "image_id": 524227, "bbox": [140.86, 15.98, 261.13, 361.9], "category_id": 1, "id": 433188, "split": "val", "sentences": [{"tokens": ["the", "kid", "with", "his", "arm", "up", "in", "the", "air"], "raw": "The kid with his arm up in the air.", "sent_id": 98983, "sent": "the kid with his arm up in the air"}, {"tokens": ["a", "child", "with", "grey", "dress"], "raw": "A child with grey dress", "sent_id": 98984, "sent": "a child with grey dress"}], "file_name": "COCO_train2014_000000524227_433188.jpg", "ann_id": 433188, "sent_ids": [98983, 98984], "ref_id": 43122}, {"segmentation": [[640.0, 479.93, 566.33, 480.0, 565.74, 468.32, 564.85, 441.82, 564.85, 413.24, 563.95, 410.27, 563.95, 406.1, 563.65, 400.14, 565.44, 398.36, 568.72, 363.23, 573.48, 354.59, 578.24, 346.55, 578.24, 344.77, 592.83, 320.95, 592.83, 318.27, 588.66, 315.89, 584.2, 314.4, 560.38, 309.04, 558.3, 307.55, 558.0, 307.26, 558.3, 300.41, 562.46, 286.42, 574.67, 285.52, 592.83, 287.01, 594.02, 289.69, 596.11, 295.64, 597.0, 300.11, 600.27, 301.6, 602.66, 301.6, 615.46, 272.12, 628.86, 249.8, 639.28, 235.51, 640.0, 234.61]], "area": 14431.563999999995, "iscrowd": 0, "image_id": 98038, "bbox": [558.0, 234.61, 82.0, 245.39], "category_id": 3, "id": 134761, "split": "val", "sentences": [{"tokens": ["a", "silver", "four", "door", "car", "is", "closely", "behind", "a", "large", "truck"], "raw": "A silver four door car is closely behind a large truck.", "sent_id": 98990, "sent": "a silver four door car is closely behind a large truck"}, {"tokens": ["a", "silver", "car", "stuck", "in", "traffic", "behind", "an", "orange", "and", "yellow", "truck", ",", "next", "to", "a", "man", "on", "a", "motorcycle", "and", "a", "herd", "of", "oxen"], "raw": "A silver car stuck in traffic behind an orange and yellow truck, next to a man on a motorcycle and a herd of oxen.", "sent_id": 98991, "sent": "a silver car stuck in traffic behind an orange and yellow truck , next to a man on a motorcycle and a herd of oxen"}], "file_name": "COCO_train2014_000000098038_134761.jpg", "ann_id": 134761, "sent_ids": [98990, 98991], "ref_id": 43126}, {"segmentation": [[526.24, 84.71, 542.47, 89.48, 559.66, 98.08, 622.7, 70.38, 637.02, 62.74, 640.0, 65.61, 639.89, 211.73, 628.43, 212.69, 628.43, 241.34, 625.56, 251.84, 616.97, 271.9, 605.51, 265.21, 608.37, 235.61, 607.42, 208.87, 594.04, 194.54, 565.39, 169.71, 550.11, 159.2, 538.65, 169.71, 532.92, 89.48, 528.15, 87.57]], "area": 12140.674499999996, "iscrowd": 0, "image_id": 547055, "bbox": [526.24, 62.74, 113.76, 209.16], "category_id": 21, "id": 278088, "split": "val", "sentences": [{"tokens": ["black", "and", "white", "cow", "behind", "mostly", "black", "cow"], "raw": "black and white cow behind mostly black cow", "sent_id": 99119, "sent": "black and white cow behind mostly black cow"}, {"tokens": ["part", "of", "a", "white", "cow", "with", "a", "black", "spot", "around", "it", "'", "s", "neck", "area"], "raw": "Part of a white cow with a black spot around it's neck area", "sent_id": 99120, "sent": "part of a white cow with a black spot around it ' s neck area"}], "file_name": "COCO_train2014_000000547055_278088.jpg", "ann_id": 278088, "sent_ids": [99119, 99120], "ref_id": 43175}, {"segmentation": [[2.16, 103.55, 18.34, 59.33, 34.52, 37.75, 53.93, 25.89, 72.27, 24.81, 90.61, 24.81, 108.94, 26.97, 122.97, 26.97, 129.44, 22.65, 144.54, 15.1, 162.88, 8.63, 182.29, 4.31, 330.07, 1.08, 358.11, 9.71, 412.04, 42.07, 441.17, 94.92, 442.25, 139.15, 435.78, 187.69, 418.52, 196.31, 408.81, 201.71, 391.55, 210.34, 365.66, 222.2, 350.56, 227.6, 333.3, 238.38, 305.26, 251.33, 295.55, 263.19, 247.01, 263.19, 227.6, 277.21, 217.89, 283.69, 200.63, 307.42, 214.65, 407.73, 224.36, 431.46, 201.71, 436.85, 182.29, 442.25, 159.64, 444.4, 155.33, 437.93, 160.72, 422.83, 165.03, 404.49, 161.8, 379.69, 149.93, 379.69, 148.85, 408.81, 135.91, 450.88, 138.07, 461.66, 121.89, 472.45, 113.26, 472.45, 102.47, 473.53, 106.79, 406.65, 101.39, 384.0, 101.39, 375.37, 134.83, 273.98, 130.52, 255.64, 128.36, 241.62, 100.31, 245.93, 97.08, 177.98, 78.74, 166.11, 55.01, 163.96, 39.91, 171.51, 34.52, 185.53, 32.36, 225.44, 36.67, 437.93, 36.67, 451.96, 32.36, 462.74, 26.97, 463.82, 26.97, 460.58, 32.36, 433.62, 23.73, 414.2, 15.1, 406.65, 5.39, 348.4, 1.08, 352.72, 0.0, 250.25, 2.16, 200.63, 2.16, 106.79]], "area": 115802.61475, "iscrowd": 0, "image_id": 475651, "bbox": [0.0, 1.08, 442.25, 472.45], "category_id": 22, "id": 585873, "split": "val", "sentences": [{"tokens": ["a", "big", "elephant", "walking", "with", "the", "small", "elephant"], "raw": "A big elephant walking with the small elephant.", "sent_id": 99142, "sent": "a big elephant walking with the small elephant"}, {"tokens": ["the", "adult", "elephant"], "raw": "the adult elephant", "sent_id": 99143, "sent": "the adult elephant"}], "file_name": "COCO_train2014_000000475651_585873.jpg", "ann_id": 585873, "sent_ids": [99142, 99143], "ref_id": 43185}, {"segmentation": [[289.04, 345.51, 271.35, 325.28, 272.19, 211.52, 277.25, 176.12, 289.04, 163.48, 398.6, 168.54, 410.39, 184.55, 414.61, 192.13, 417.13, 236.8, 423.03, 321.91, 411.24, 337.92, 401.97, 344.66, 290.73, 342.98]], "area": 25353.8151, "iscrowd": 0, "image_id": 174892, "bbox": [271.35, 163.48, 151.68, 182.03], "category_id": 51, "id": 1534224, "split": "val", "sentences": [{"tokens": ["peeled", "nectarines", "sitting", "inside", "a", "green", "plastic", "container"], "raw": "Peeled nectarines sitting inside a green plastic container.", "sent_id": 99154, "sent": "peeled nectarines sitting inside a green plastic container"}, {"tokens": ["a", "green", "cup", "with", "oranges", "in", "it"], "raw": "A green cup with oranges in it.", "sent_id": 99155, "sent": "a green cup with oranges in it"}], "file_name": "COCO_train2014_000000174892_1534224.jpg", "ann_id": 1534224, "sent_ids": [99154, 99155], "ref_id": 43191}, {"segmentation": [[306.02, 253.39, 304.2, 241.03, 298.75, 241.03, 274.57, 240.67, 253.48, 240.49, 235.48, 239.21, 226.94, 235.94, 224.76, 228.85, 220.58, 225.58, 219.67, 229.4, 220.03, 241.94, 220.58, 247.94, 213.49, 295.93, 200.94, 423.2, 204.58, 426.47, 206.58, 425.92, 208.4, 423.92, 209.67, 420.1, 218.03, 333.39, 232.21, 335.2, 235.12, 335.93, 237.3, 356.11, 242.76, 355.93, 241.48, 338.48, 253.12, 341.93, 264.39, 348.48, 274.93, 360.11, 277.48, 362.66, 276.57, 426.83, 285.66, 427.0, 288.21, 358.47, 296.39, 355.93, 297.3, 388.11, 301.84, 387.93, 302.75, 354.11, 340.38, 339.57, 338.93, 371.75, 343.37, 373.75, 345.35, 372.16, 347.12, 337.39, 364.4, 330.48, 371.67, 424.29, 373.12, 427.0, 380.76, 426.84, 374.21, 344.66, 372.39, 317.58, 376.58, 315.21, 376.76, 313.94, 373.49, 310.3, 354.94, 309.76, 338.4, 304.67, 307.47, 292.27, 296.01, 286.74, 288.3, 289.51, 287.76, 255.33, 300.85, 254.42]], "area": 14406.552949999996, "iscrowd": 0, "image_id": 257102, "bbox": [200.94, 225.58, 179.82, 201.42], "category_id": 62, "id": 1595469, "split": "val", "sentences": [{"tokens": ["the", "chair", "closest", "to", "the", "camera"], "raw": "The chair closest to the camera.", "sent_id": 99220, "sent": "the chair closest to the camera"}, {"tokens": ["the", "chair", "on", "the", "closest", "side", "of", "the", "table", "that", "is", "on", "the", "right"], "raw": "the chair on the closest side of the table that is on the right", "sent_id": 99221, "sent": "the chair on the closest side of the table that is on the right"}], "file_name": "COCO_train2014_000000257102_1595469.jpg", "ann_id": 1595469, "sent_ids": [99220, 99221], "ref_id": 43219}, {"segmentation": [[74.12, 145.01, 83.78, 164.35, 60.15, 170.79, 54.78, 182.61, 52.63, 193.35, 44.04, 203.02, 38.67, 214.83, 34.37, 230.94, 32.22, 243.83, 34.37, 258.87, 31.15, 271.76, 27.93, 292.17, 26.85, 300.76, 26.85, 310.43, 26.85, 321.17, 26.85, 334.06, 26.85, 349.1, 26.85, 359.84, 33.3, 373.81, 51.56, 374.88, 55.86, 379.18, 65.52, 385.62, 78.41, 387.77, 109.56, 394.22, 142.86, 396.36, 167.57, 373.81, 170.79, 352.32, 166.49, 334.06, 155.75, 315.8, 149.31, 299.69, 148.23, 276.06, 149.31, 255.65, 141.79, 224.5, 134.27, 201.94, 126.75, 180.46, 121.38, 164.35, 120.31, 140.71, 118.16, 132.12, 108.49, 140.71, 104.19, 141.79, 91.3, 140.71, 80.56, 136.42, 79.49, 141.79]], "area": 26520.44595, "iscrowd": 0, "image_id": 543838, "bbox": [26.85, 132.12, 143.94, 264.24], "category_id": 86, "id": 1154063, "split": "val", "sentences": [{"tokens": ["a", "thin", "flower", "vase", "place", "beside", "other", "fat", "flower", "vase"], "raw": "A thin flower vase place beside other fat flower vase", "sent_id": 99274, "sent": "a thin flower vase place beside other fat flower vase"}], "file_name": "COCO_train2014_000000543838_1154063.jpg", "ann_id": 1154063, "sent_ids": [99274], "ref_id": 43239}, {"segmentation": [[449.09, 462.27, 440.68, 453.86, 438.43, 451.62, 437.31, 444.89, 435.07, 438.17, 432.83, 435.36, 429.46, 429.76, 437.87, 388.83, 445.16, 372.01, 458.06, 372.57, 481.6, 373.13, 500.1, 374.26, 514.12, 375.38, 541.59, 378.74, 561.21, 378.74, 571.3, 383.79, 576.91, 396.12, 566.82, 401.73, 562.89, 412.94, 562.89, 429.2, 564.01, 440.97, 562.33, 449.38, 561.21, 458.91, 558.41, 470.68, 550.0, 476.29, 542.15, 476.29, 528.13, 476.29, 519.16, 470.68, 499.54, 470.12, 490.01, 469.0, 483.84, 469.0, 473.75, 469.0, 461.98, 464.52, 456.93, 463.4], [611.67, 458.35, 608.86, 442.09, 606.62, 433.68, 598.21, 425.27, 594.85, 419.67, 595.97, 419.67, 597.65, 414.06, 606.06, 425.83, 612.23, 432.56, 616.71, 433.68, 619.52, 439.29, 622.88, 450.5, 620.64, 454.99, 618.4, 465.08, 616.15, 468.44, 609.43, 460.59]], "area": 12601.9311, "iscrowd": 0, "image_id": 383639, "bbox": [429.46, 372.01, 193.42, 104.28], "category_id": 8, "id": 2209371, "split": "val", "sentences": [{"tokens": ["blue", "van"], "raw": "blue van", "sent_id": 99352, "sent": "blue van"}, {"tokens": ["a", "blue", "van"], "raw": "A blue van", "sent_id": 99353, "sent": "a blue van"}], "file_name": "COCO_train2014_000000383639_2209371.jpg", "ann_id": 2209371, "sent_ids": [99352, 99353], "ref_id": 43272}, {"segmentation": [[58.87, 173.14, 76.61, 170.72, 100.81, 176.37, 124.19, 189.27, 150.81, 220.72, 163.71, 229.59, 181.45, 229.59, 237.9, 232.01, 239.52, 236.85, 236.29, 252.17, 237.1, 286.85, 238.71, 293.3, 213.71, 319.91, 206.45, 340.88, 204.03, 352.98, 200.0, 358.62, 205.65, 361.04, 203.23, 369.11, 198.39, 369.91, 87.1, 369.11, 84.68, 368.3, 57.26, 178.79]], "area": 24945.897000000008, "iscrowd": 0, "image_id": 523484, "bbox": [57.26, 170.72, 182.26, 199.19], "category_id": 62, "id": 106278, "split": "val", "sentences": [{"tokens": ["brown", "and", "white", "cat"], "raw": "brown and white cat", "sent_id": 99354, "sent": "brown and white cat"}, {"tokens": ["a", "white", "chair", "the", "cat", "is", "laying", "in"], "raw": "A white chair the cat is laying in.", "sent_id": 99355, "sent": "a white chair the cat is laying in"}], "file_name": "COCO_train2014_000000523484_106278.jpg", "ann_id": 106278, "sent_ids": [99354, 99355], "ref_id": 43273}, {"segmentation": [[213.57, 421.75, 202.79, 415.28, 202.79, 384.0, 211.42, 331.15, 196.31, 249.17, 210.34, 238.38, 217.89, 210.34, 222.2, 208.18, 217.89, 184.45, 204.94, 167.19, 192.0, 159.64, 179.06, 159.64, 177.98, 155.33, 169.35, 154.25, 163.96, 149.93, 166.11, 145.62, 174.74, 146.7, 187.69, 140.22, 181.21, 139.15, 175.82, 134.83, 170.43, 132.67, 166.11, 126.2, 157.48, 129.44, 138.07, 102.47, 126.2, 94.92, 108.94, 87.37, 51.78, 67.96, 44.22, 3.24, 336.54, 2.16, 344.09, 67.96, 349.48, 102.47, 330.07, 224.36, 340.85, 292.31, 333.3, 305.26, 310.65, 316.04, 297.71, 316.04, 279.37, 312.81, 280.45, 365.66, 261.03, 382.92, 223.28, 413.12]], "area": 63719.49180000001, "iscrowd": 0, "image_id": 31187, "bbox": [44.22, 2.16, 305.26, 419.59], "category_id": 1, "id": 1732500, "split": "val", "sentences": [{"tokens": ["a", "knife", "cutting", "a", "cake"], "raw": "A knife cutting a cake.", "sent_id": 99374, "sent": "a knife cutting a cake"}, {"tokens": ["person", "wearing", "jacket", "cutting", "the", "cake"], "raw": "Person wearing jacket cutting the cake.", "sent_id": 99375, "sent": "person wearing jacket cutting the cake"}], "file_name": "COCO_train2014_000000031187_1732500.jpg", "ann_id": 1732500, "sent_ids": [99374, 99375], "ref_id": 43280}, {"segmentation": [[149.2, 78.62, 155.07, 59.21, 156.87, 47.47, 159.13, 35.28, 154.62, 29.87, 153.71, 21.29, 168.16, 14.97, 156.87, 0.08, 163.19, 0.0, 205.17, 0.0, 231.81, 0.0, 246.7, 0.0, 397.47, 0.0, 506.26, 0.0, 534.24, 5.94, 532.89, 21.74, 524.76, 35.74, 520.7, 43.86, 520.7, 58.31, 504.45, 78.17, 490.91, 76.36, 463.83, 75.01, 444.42, 75.46, 426.81, 70.04, 422.75, 68.24, 406.05, 65.08, 382.57, 63.27, 355.49, 62.82, 335.63, 64.63, 301.77, 67.33, 260.7, 70.04, 234.06, 74.56, 193.89, 84.04, 148.75, 89.45]], "area": 26593.729599999995, "iscrowd": 0, "image_id": 468117, "bbox": [148.75, 0.0, 385.49, 89.45], "category_id": 1, "id": 1735572, "split": "val", "sentences": [{"tokens": ["hands", "with", "a", "fork", "in", "background"], "raw": "HANDS WITH A FORK IN BACKGROUND", "sent_id": 99388, "sent": "hands with a fork in background"}, {"tokens": ["a", "person", "in", "a", "blue", "sweatshirt", "eating", "pizza", "with", "a", "fork"], "raw": "a person in a blue sweatshirt eating pizza with a fork", "sent_id": 99389, "sent": "a person in a blue sweatshirt eating pizza with a fork"}], "file_name": "COCO_train2014_000000468117_1735572.jpg", "ann_id": 1735572, "sent_ids": [99388, 99389], "ref_id": 43287}, {"segmentation": [[220.79, 287.37, 201.43, 335.79, 212.08, 393.9, 203.36, 409.39, 227.57, 411.33, 241.13, 403.58, 230.48, 334.82, 267.28, 291.25, 274.06, 329.98, 288.58, 358.06, 293.42, 392.93, 285.68, 403.58, 289.55, 411.33, 310.86, 418.11, 325.38, 406.48, 324.41, 393.9, 319.57, 380.34, 295.36, 316.42, 291.49, 305.77, 301.17, 271.88, 299.23, 247.67, 290.52, 218.62, 261.47, 183.75, 267.28, 176.97, 265.34, 166.32, 251.78, 161.48, 240.16, 147.92, 230.48, 146.95, 225.64, 133.4, 209.17, 115.97, 197.55, 115.97, 182.06, 123.71, 188.84, 147.92, 207.24, 162.45, 207.24, 184.72, 214.02, 208.93, 217.89, 225.39, 208.21, 252.51]], "area": 18518.112999999994, "iscrowd": 0, "image_id": 317149, "bbox": [182.06, 115.97, 143.32, 302.14], "category_id": 1, "id": 520579, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "baseball", "mit", "throwing", "a", "baseball", "to", "someone"], "raw": "A man with a baseball mit throwing a baseball to someone.", "sent_id": 99400, "sent": "a man with a baseball mit throwing a baseball to someone"}, {"tokens": ["a", "man", "wearing", "a", "black", "jacket", "begins", "to", "throw", "a", "ball"], "raw": "A man wearing a black jacket begins to throw a ball.", "sent_id": 99401, "sent": "a man wearing a black jacket begins to throw a ball"}], "file_name": "COCO_train2014_000000317149_520579.jpg", "ann_id": 520579, "sent_ids": [99400, 99401], "ref_id": 43293}, {"segmentation": [[316.62, 217.22, 322.55, 202.38, 327.0, 197.44, 330.95, 189.53, 334.91, 187.06, 338.87, 172.72, 343.32, 164.81, 351.72, 161.34, 364.08, 164.31, 371.99, 177.17, 370.51, 184.09, 387.32, 197.44, 399.68, 216.23, 406.6, 249.85, 400.67, 270.62, 392.27, 282.98, 376.44, 279.02, 355.18, 273.58, 343.81, 268.14, 319.09, 267.16, 311.18, 269.13, 314.64, 260.73, 324.53, 258.75, 330.46, 257.27, 339.36, 255.78, 341.34, 255.29, 344.3, 253.81, 351.23, 244.41, 363.59, 243.92, 346.28, 237.98, 327.0, 235.02, 313.65, 231.06, 308.21, 229.08, 307.22, 224.63, 310.19, 220.68, 313.15, 219.19]], "area": 7005.407800000001, "iscrowd": 0, "image_id": 454923, "bbox": [307.22, 161.34, 99.38, 121.64], "category_id": 1, "id": 441457, "split": "val", "sentences": [{"tokens": ["man", "in", "striped", "shirt", "wearing", "glasses"], "raw": "Man in striped shirt wearing glasses.", "sent_id": 99520, "sent": "man in striped shirt wearing glasses"}, {"tokens": ["this", "is", "a", "man", "sitting", "in", "a", "striped", "shirt"], "raw": "This is a man sitting in a striped shirt.", "sent_id": 99521, "sent": "this is a man sitting in a striped shirt"}], "file_name": "COCO_train2014_000000454923_441457.jpg", "ann_id": 441457, "sent_ids": [99520, 99521], "ref_id": 43344}, {"segmentation": [[385.9, 458.99, 343.06, 438.59, 310.42, 438.59, 258.39, 407.99, 240.03, 361.07, 236.97, 294.76, 264.51, 242.74, 342.04, 149.91, 401.2, 116.25, 413.45, 115.23, 431.81, 97.88, 455.27, 89.72, 475.67, 93.8, 479.75, 115.23, 491.99, 121.35, 513.41, 127.47, 533.81, 105.03, 563.4, 127.47, 562.38, 159.09, 532.79, 222.33, 500.15, 286.6, 460.37, 369.23, 434.87, 418.19, 414.47, 451.85]], "area": 74401.15144999999, "iscrowd": 0, "image_id": 319192, "bbox": [236.97, 89.72, 326.43, 369.27], "category_id": 58, "id": 1068293, "split": "val", "sentences": [{"tokens": ["the", "piece", "with", "sauce", "in", "the", "right", "side", "of", "the", "image"], "raw": "the piece with sauce in the right side of the image", "sent_id": 99567, "sent": "the piece with sauce in the right side of the image"}], "file_name": "COCO_train2014_000000319192_1068293.jpg", "ann_id": 1068293, "sent_ids": [99567], "ref_id": 43360}, {"segmentation": [[189.99, 312.81, 163.12, 330.09, 161.2, 327.21, 148.73, 314.73, 140.09, 312.81, 109.39, 313.77, 107.47, 308.02, 102.67, 269.63, 107.47, 257.16, 112.27, 246.6, 118.98, 232.21, 120.9, 213.02, 124.74, 172.72, 133.38, 149.69, 139.13, 141.05, 155.45, 134.34, 158.33, 131.46, 161.2, 118.02, 161.2, 115.15, 165.04, 86.36, 171.76, 71.97, 180.4, 67.17, 200.55, 67.17, 213.02, 67.17, 220.7, 72.93, 227.41, 83.48, 228.37, 87.32, 229.33, 93.08, 229.33, 97.87, 222.62, 113.23, 217.82, 134.34, 216.86, 138.18, 214.94, 145.85, 214.94, 145.85, 235.09, 154.49, 245.64, 154.49, 251.4, 154.49, 264.84, 158.33, 275.39, 158.33, 283.07, 158.33, 289.78, 160.24, 295.54, 161.2, 301.3, 163.12, 322.41, 181.36, 321.45, 185.19, 316.65, 188.07, 301.3, 195.75, 283.07, 199.59, 285.95, 186.15, 278.27, 183.27, 250.44, 179.44, 244.69, 183.27, 239.89, 189.03, 238.93, 217.82, 245.64, 224.53, 246.6, 224.53, 261.96, 217.82, 279.23, 221.66, 269.63, 235.09, 261.96, 243.73, 252.36, 243.73, 245.64, 243.73, 240.85, 247.56, 230.29, 258.12, 227.41, 261.96, 231.25, 270.59, 235.09, 279.23, 237.01, 280.19, 242.77, 287.87, 241.81, 291.7, 217.82, 303.22, 205.34, 311.85, 210.14, 302.26, 216.86, 289.78, 217.82, 276.35, 214.94, 261.96, 211.1, 249.48, 203.42, 240.85, 195.75, 237.97, 188.07, 241.81, 180.4, 241.81, 175.6, 251.4, 174.64, 256.2, 172.72, 265.8, 167.92, 280.19, 166.96, 288.82, 168.88, 292.66, 174.64, 297.46, 183.27, 305.14]], "area": 25173.73975, "iscrowd": 0, "image_id": 438071, "bbox": [102.67, 67.17, 219.74, 262.92], "category_id": 1, "id": 474256, "split": "val", "sentences": [{"tokens": ["a", "woman", "pouring", "wine", ",", "a", "wine", "glass", ",", "and", "a", "basket", "are", "all", "within", "the", "red", "square", ".", "the", "woman", "is", "wearing", "an", "apron"], "raw": "A woman pouring wine, a wine glass, and a basket are all within the red square. The woman is wearing an apron.", "sent_id": 99611, "sent": "a woman pouring wine , a wine glass , and a basket are all within the red square . the woman is wearing an apron"}, {"tokens": ["the", "lady", "is", "giving", "alcohol", "to", "man"], "raw": "the lady is giving alcohol to man", "sent_id": 99612, "sent": "the lady is giving alcohol to man"}], "file_name": "COCO_train2014_000000438071_474256.jpg", "ann_id": 474256, "sent_ids": [99611, 99612], "ref_id": 43379}, {"segmentation": [[341.61, 270.55, 321.66, 302.96, 347.84, 341.61, 410.18, 361.56, 458.81, 351.58, 561.04, 263.06, 583.48, 243.12, 497.45, 266.81, 433.87, 270.55, 407.69, 270.55, 354.08, 270.55]], "area": 15092.873899999999, "iscrowd": 0, "image_id": 187537, "bbox": [321.66, 243.12, 261.82, 118.44], "category_id": 58, "id": 2220421, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "hot", "dog", "that", "is", "in", "between", "two", "pieces", "of", "bread"], "raw": "A piece of hot dog that is in between two pieces of bread.", "sent_id": 99688, "sent": "a piece of hot dog that is in between two pieces of bread"}, {"tokens": ["the", "hot", "dog", "to", "the", "right", "of", "the", "pickle"], "raw": "The hot dog to the right of the pickle.", "sent_id": 99689, "sent": "the hot dog to the right of the pickle"}], "file_name": "COCO_train2014_000000187537_2220421.jpg", "ann_id": 2220421, "sent_ids": [99688, 99689], "ref_id": 43411}, {"segmentation": [[130.18, 172.36, 111.09, 163.68, 107.62, 166.28, 69.43, 145.46, 2.6, 114.21, 0.87, 70.82, 61.62, 46.52, 142.33, 25.69, 121.5, 53.46, 111.96, 62.14, 86.79, 50.86, 86.79, 76.89, 104.15, 103.8, 100.67, 117.68, 108.48, 124.63, 113.69, 144.59, 127.58, 161.08], [472.99, 220.09, 451.3, 186.25, 426.99, 166.28, 426.99, 145.46, 406.17, 148.06, 378.39, 122.89, 367.98, 122.89, 368.85, 101.19, 357.56, 90.78, 343.68, 88.18, 332.4, 94.25, 323.72, 82.97, 323.72, 67.35, 307.23, 47.39, 283.8, 49.99, 274.25, 39.58, 263.83, 38.71, 256.02, 20.48, 323.72, 32.63, 380.13, 49.12, 447.82, 77.76, 484.27, 102.06, 500.0, 123.76, 500.0, 266.09, 474.73, 251.34, 466.05, 233.98, 475.6, 218.36], [444.35, 270.43, 468.65, 279.98, 498.16, 273.9, 499.03, 327.71, 365.38, 330.31, 369.72, 317.3, 407.03, 292.99, 418.32, 302.54, 433.94, 290.39, 433.94, 279.11]], "area": 32284.68669999999, "iscrowd": 0, "image_id": 226966, "bbox": [0.87, 20.48, 499.13, 309.83], "category_id": 67, "id": 1959317, "split": "val", "sentences": [{"tokens": ["the", "blue", "plate"], "raw": "The blue plate", "sent_id": 99777, "sent": "the blue plate"}, {"tokens": ["a", "blue", "serving", "plate", "is", "decorated", "with", "food"], "raw": "A blue serving plate is decorated with food", "sent_id": 99778, "sent": "a blue serving plate is decorated with food"}], "file_name": "COCO_train2014_000000226966_1959317.jpg", "ann_id": 1959317, "sent_ids": [99777, 99778], "ref_id": 43447}, {"segmentation": [[541.92, 14.43, 540.05, 17.57, 529.69, 18.44, 517.52, 19.11, 509.36, 19.04, 506.02, 18.51, 498.87, 30.01, 508.16, 38.03, 519.93, 45.99, 527.15, 55.88, 523.67, 68.88, 515.18, 102.7, 511.65, 148.57, 511.3, 181.03, 512.35, 190.21, 527.88, 219.85, 540.94, 237.49, 569.87, 238.0, 572.69, 191.62, 567.75, 155.63, 556.81, 99.17, 547.64, 68.47, 541.99, 55.41, 542.35, 42.71, 543.41, 28.95, 544.46, 25.07, 549.76, 19.78]], "area": 9442.751550000003, "iscrowd": 0, "image_id": 205223, "bbox": [498.87, 14.43, 73.82, 223.57], "category_id": 32, "id": 296797, "split": "val", "sentences": [{"tokens": ["the", "fourth", "image", "of", "a", "grey", "tie", "in", "a", "series", "of", "four"], "raw": "The fourth image of a grey tie in a series of four", "sent_id": 99785, "sent": "the fourth image of a grey tie in a series of four"}, {"tokens": ["the", "mans", "gray", "tie", "on", "the", "right", "side", "of", "the", "picture"], "raw": "The mans gray tie on the right side of the picture.", "sent_id": 99786, "sent": "the mans gray tie on the right side of the picture"}], "file_name": "COCO_train2014_000000205223_296797.jpg", "ann_id": 296797, "sent_ids": [99785, 99786], "ref_id": 43451}, {"segmentation": [[288.14, 225.37, 310.09, 229.51, 341.98, 232.82, 355.23, 222.88, 360.61, 214.18, 374.28, 210.46, 375.0, 192.24, 361.03, 186.85, 350.26, 189.34, 343.64, 193.06, 341.98, 203.83, 337.42, 200.1, 325.41, 196.38, 305.95, 197.62, 295.18, 197.21, 287.73, 202.59, 287.73, 212.53, 279.03, 215.43, 263.71, 212.53, 259.98, 202.17, 242.59, 198.45, 233.07, 193.06, 212.36, 191.82, 205.73, 191.41, 213.19, 207.97, 229.34, 222.47, 259.57, 234.06, 268.68, 229.92, 278.62, 221.22, 290.63, 227.02], [192.48, 185.2, 185.44, 175.26, 178.82, 160.35, 170.53, 168.63, 163.08, 178.16, 166.81, 196.79, 167.22, 205.07, 175.92, 203.83, 181.3, 193.89]], "area": 5134.71635, "iscrowd": 0, "image_id": 141952, "bbox": [163.08, 160.35, 211.92, 73.71], "category_id": 1, "id": 1260816, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "hat", "relaxing", "in", "a", "lawn", "chair"], "raw": "A man in a white hat relaxing in a lawn chair.", "sent_id": 99822, "sent": "a man in a white hat relaxing in a lawn chair"}, {"tokens": ["a", "man", "with", "a", "white", "hat", "reclining", "in", "a", "chair"], "raw": "A man with a white hat reclining in a chair.", "sent_id": 99823, "sent": "a man with a white hat reclining in a chair"}], "file_name": "COCO_train2014_000000141952_1260816.jpg", "ann_id": 1260816, "sent_ids": [99822, 99823], "ref_id": 43465}, {"segmentation": [[39.25, 456.62, 43.54, 444.37, 34.96, 428.43, 33.12, 405.76, 45.99, 392.9, 88.88, 384.93, 130.54, 387.38, 166.7, 379.42, 184.46, 388.61, 184.46, 402.09, 172.82, 407.6, 163.02, 409.44, 150.15, 414.95, 141.57, 425.98, 128.71, 433.34, 128.71, 442.53, 131.16, 449.88, 136.06, 453.56, 126.87, 457.23, 112.16, 456.62, 112.77, 450.49, 112.77, 441.91, 100.52, 438.85, 88.27, 433.34, 79.07, 438.24, 72.33, 438.85, 64.37, 440.08, 62.53, 443.75, 61.31, 450.49, 64.98, 458.46, 57.02, 458.46, 45.99, 460.91, 40.47, 461.52]], "area": 7181.488400000001, "iscrowd": 0, "image_id": 244875, "bbox": [33.12, 379.42, 151.34, 82.1], "category_id": 17, "id": 2066730, "split": "val", "sentences": [{"tokens": ["a", "cat", "standing", "sideways", "under", "a", "car"], "raw": "A cat standing sideways under a car.", "sent_id": 99901, "sent": "a cat standing sideways under a car"}], "file_name": "COCO_train2014_000000244875_2066730.jpg", "ann_id": 2066730, "sent_ids": [99901], "ref_id": 43495}, {"segmentation": [[519.91, 473.2, 511.28, 368.57, 515.6, 320.03, 530.7, 299.54, 522.07, 240.21, 511.28, 228.34, 490.79, 213.24, 487.55, 185.2, 477.84, 174.41, 470.29, 174.41, 461.66, 185.2, 463.82, 205.69, 470.29, 222.95, 460.58, 232.66, 445.48, 271.49, 442.25, 300.61, 432.54, 314.64, 416.36, 324.34, 421.75, 330.82, 436.85, 330.82, 447.64, 326.5, 449.8, 371.81, 450.88, 437.6, 470.29, 466.73, 463.82, 472.12]], "area": 18351.706550000003, "iscrowd": 0, "image_id": 496053, "bbox": [416.36, 174.41, 114.34, 298.79], "category_id": 1, "id": 186964, "split": "val", "sentences": [{"tokens": ["a", "man", "holding", "a", "tv", "remote", "control"], "raw": "A man holding a TV remote control.", "sent_id": 99905, "sent": "a man holding a tv remote control"}, {"tokens": ["a", "man", "with", "khaki", "pants", "holding", "television", "remotes"], "raw": "A man with khaki pants holding television remotes.", "sent_id": 99906, "sent": "a man with khaki pants holding television remotes"}], "file_name": "COCO_train2014_000000496053_186964.jpg", "ann_id": 186964, "sent_ids": [99905, 99906], "ref_id": 43497}, {"segmentation": [[131.17, 471.35, 149.91, 410.81, 191.71, 357.48, 219.1, 324.32, 236.4, 314.23, 220.54, 252.25, 210.45, 203.24, 221.98, 148.47, 229.19, 126.85, 243.6, 134.05, 249.37, 145.59, 237.84, 183.06, 245.05, 236.4, 263.78, 281.08, 281.08, 296.94, 292.61, 288.29, 304.14, 272.43, 317.12, 265.23, 334.41, 268.11, 343.06, 288.29, 340.18, 304.14, 334.41, 320.0, 330.09, 324.32, 308.47, 335.86, 311.35, 353.15, 309.91, 370.45, 279.64, 393.51, 270.99, 392.07, 262.34, 410.81, 259.46, 420.9, 266.67, 429.55, 243.6, 468.47, 234.95, 531.89, 242.16, 552.07, 243.6, 640.0, 219.1, 640.0, 217.66, 614.05, 200.36, 527.57, 204.68, 467.03, 174.41, 452.61, 157.12, 482.88, 148.47, 563.6, 152.79, 573.69, 172.97, 586.67, 151.35, 614.05, 147.03, 637.12, 151.35, 638.56, 121.08, 638.56, 121.08, 524.68, 121.08, 497.3, 128.29, 465.59]], "area": 36630.360250000005, "iscrowd": 0, "image_id": 193682, "bbox": [121.08, 126.85, 221.98, 513.15], "category_id": 1, "id": 427803, "split": "val", "sentences": [{"tokens": ["the", "tennis", "player", "on", "the", "court"], "raw": "The tennis player on the court.", "sent_id": 99914, "sent": "the tennis player on the court"}, {"tokens": ["woman", "hitting", "a", "tennis", "ball", "with", "racket"], "raw": "woman hitting a tennis ball with racket", "sent_id": 99915, "sent": "woman hitting a tennis ball with racket"}], "file_name": "COCO_train2014_000000193682_427803.jpg", "ann_id": 427803, "sent_ids": [99914, 99915], "ref_id": 43501}, {"segmentation": [[32.55, 264.91, 24.51, 271.61, 21.83, 295.74, 49.98, 386.89, 80.81, 390.91, 99.58, 364.1, 94.21, 330.59, 104.94, 318.53, 127.73, 301.1, 139.79, 298.42, 141.13, 298.42, 198.77, 279.65, 224.24, 280.99, 186.71, 212.63, 151.85, 211.29, 130.41, 215.31, 129.07, 236.76, 90.19, 252.84, 91.53, 274.29, 70.09, 282.33, 64.72, 267.59, 43.28, 275.63, 36.57, 270.27]], "area": 15392.782899999998, "iscrowd": 0, "image_id": 142431, "bbox": [21.83, 211.29, 202.41, 179.62], "category_id": 75, "id": 1974866, "split": "val", "sentences": [{"tokens": ["a", "playstation", "controller"], "raw": "A Playstation controller.", "sent_id": 99924, "sent": "a playstation controller"}, {"tokens": ["sony", "playstation", "controller", "on", "the", "top", "right", "of", "the", "collection"], "raw": "SONY Playstation controller on the top right of the collection", "sent_id": 99925, "sent": "sony playstation controller on the top right of the collection"}], "file_name": "COCO_train2014_000000142431_1974866.jpg", "ann_id": 1974866, "sent_ids": [99924, 99925], "ref_id": 43505}, {"segmentation": [[408.77, 262.92, 384.78, 261.96, 384.78, 261.96, 362.71, 268.67, 341.6, 294.58, 337.76, 316.65, 355.03, 337.76, 379.98, 340.64, 400.13, 331.04, 420.28, 332.96, 432.76, 328.17, 538.31, 231.25, 590.12, 154.49, 595.88, 182.31, 639.06, 216.86, 640.0, 1.92, 640.0, 1.92, 575.73, 0.0, 572.85, 14.39, 573.81, 28.79, 574.77, 47.98, 510.48, 117.07, 474.98, 170.8, 460.58, 206.3]], "area": 36322.73699999999, "iscrowd": 0, "image_id": 90569, "bbox": [337.76, 0.0, 302.24, 340.64], "category_id": 1, "id": 446196, "split": "val", "sentences": [{"tokens": ["the", "woman", "on", "the", "right"], "raw": "the woman on the right", "sent_id": 99937, "sent": "the woman on the right"}, {"tokens": ["woman", "holding", "a", "glass"], "raw": "woman holding a glass.", "sent_id": 99938, "sent": "woman holding a glass"}], "file_name": "COCO_train2014_000000090569_446196.jpg", "ann_id": 446196, "sent_ids": [99937, 99938], "ref_id": 43511}, {"segmentation": [[544.27, 318.15, 517.66, 273.19, 535.09, 228.23, 537.85, 188.78, 507.57, 230.07, 491.05, 193.37, 509.4, 164.93, 525.92, 88.77, 536.01, 51.16, 542.43, 16.29, 567.21, 4.37, 599.32, 13.54, 613.08, 0.0, 638.77, 2.53, 639.69, 262.18, 639.69, 380.54, 616.75, 367.69, 576.38, 355.76, 560.78, 325.49]], "area": 39477.099600000016, "iscrowd": 0, "image_id": 527925, "bbox": [491.05, 0.0, 148.64, 380.54], "category_id": 27, "id": 1421159, "split": "val", "sentences": [{"tokens": ["grey", "/", "black", "bag", "touching", "striped", "cat"], "raw": "Grey/black bag touching striped cat.", "sent_id": 99963, "sent": "grey / black bag touching striped cat"}, {"tokens": ["the", "black", "bag", "next", "to", "the", "lighter", "cat"], "raw": "The black bag next to the lighter cat.", "sent_id": 99964, "sent": "the black bag next to the lighter cat"}], "file_name": "COCO_train2014_000000527925_1421159.jpg", "ann_id": 1421159, "sent_ids": [99963, 99964], "ref_id": 43521}, {"segmentation": [[269.0, 118.71, 278.58, 107.22, 272.83, 87.11, 262.3, 87.11, 248.9, 84.24, 210.61, 84.24, 221.14, 110.09, 219.22, 149.34, 200.08, 147.42, 190.5, 154.13, 185.72, 174.23, 192.42, 196.25, 192.42, 216.35, 149.34, 217.31, 138.81, 220.18, 131.15, 240.28, 124.45, 269.0, 128.28, 294.85, 136.89, 307.29, 166.57, 314.0, 189.55, 314.95, 215.39, 313.04, 235.5, 303.47, 235.5, 287.19, 231.67, 275.7, 228.8, 263.26, 225.92, 254.64, 222.09, 241.24, 222.09, 221.14, 224.01, 220.18, 226.88, 221.14, 236.45, 229.75, 236.45, 242.2, 240.28, 265.17, 247.94, 278.58, 258.47, 290.06, 271.87, 292.93, 313.04, 294.85, 305.38, 285.28, 297.72, 264.22, 283.36, 244.11, 286.23, 224.01, 305.38, 213.48, 309.21, 196.25, 309.21, 179.97, 298.68, 171.36, 280.49, 159.87, 260.39, 154.13, 256.56, 154.13, 247.94, 142.64, 244.11, 140.72, 237.41, 140.72, 229.75, 126.36, 237.41, 122.53, 249.86, 120.62, 260.39, 117.75], [368.56, 184.76, 380.05, 176.14, 407.81, 177.1, 441.32, 167.53, 475.78, 170.4, 466.21, 184.76, 453.76, 188.59, 455.68, 203.91, 446.1, 211.56, 454.72, 225.92, 470.99, 236.45, 471.95, 256.56, 477.69, 269.0, 477.69, 277.62, 469.08, 290.06, 462.38, 295.81, 416.43, 318.78, 398.24, 318.78, 372.39, 311.12, 351.33, 293.89, 343.67, 293.89, 336.97, 292.93, 330.27, 284.32, 321.65, 259.43, 318.78, 254.64, 327.4, 246.03, 343.67, 221.14]], "area": 39961.87700000001, "iscrowd": 0, "image_id": 11690, "bbox": [124.45, 84.24, 353.24, 234.54], "category_id": 4, "id": 151401, "split": "val", "sentences": [{"tokens": ["the", "motorcycle", "the", "man", "is", "riding"], "raw": "The motorcycle the man is riding.", "sent_id": 99965, "sent": "the motorcycle the man is riding"}, {"tokens": ["the", "red", "motor", "cycle"], "raw": "The red motor cycle.", "sent_id": 99966, "sent": "the red motor cycle"}], "file_name": "COCO_train2014_000000011690_151401.jpg", "ann_id": 151401, "sent_ids": [99965, 99966], "ref_id": 43522}, {"segmentation": [[314.38, 251.87, 310.13, 264.61, 310.13, 270.99, 306.95, 276.3, 303.76, 279.48, 302.7, 284.79, 302.7, 292.23, 302.7, 312.41, 305.88, 330.46, 309.07, 348.52, 312.26, 367.64, 319.69, 375.07, 322.88, 369.76, 320.75, 355.95, 318.63, 338.96, 319.69, 323.03, 327.13, 323.03, 331.37, 327.28, 336.69, 334.71, 348.37, 338.96, 367.49, 342.15, 377.04, 343.21, 380.23, 345.33, 378.11, 360.2, 385.54, 375.07, 394.04, 378.26, 394.04, 353.83, 392.98, 345.33, 400.41, 336.84, 417.4, 338.96, 415.28, 346.4, 414.22, 353.83, 416.34, 364.45, 426.96, 377.2, 431.21, 370.82, 429.09, 345.33, 428.03, 341.09, 433.34, 328.34, 437.58, 313.47, 440.77, 301.79, 443.96, 289.04, 447.14, 277.36, 451.39, 268.86, 455.64, 260.37, 457.76, 258.24, 464.14, 249.74, 468.39, 235.94, 459.89, 223.19, 455.64, 217.88, 448.21, 213.63, 435.46, 214.7, 422.72, 218.94, 416.34, 221.07, 406.78, 223.19, 399.35, 223.19, 399.35, 227.44, 401.47, 235.94, 401.47, 239.12, 398.29, 243.37, 391.91, 243.37, 380.23, 239.12, 369.61, 234.88, 355.8, 233.81, 345.18, 233.81, 322.88, 238.06]], "area": 16454.110899999992, "iscrowd": 0, "image_id": 124694, "bbox": [302.7, 213.63, 165.69, 164.63], "category_id": 20, "id": 62794, "split": "val", "sentences": [{"tokens": ["the", "sheep", "on", "the", "right"], "raw": "The sheep on the right.", "sent_id": 99988, "sent": "the sheep on the right"}, {"tokens": ["the", "sheep", "on", "the", "right", "side", "with", "the", "woman", "in", "white", "top"], "raw": "The sheep on the right side with the woman in white top", "sent_id": 99989, "sent": "the sheep on the right side with the woman in white top"}], "file_name": "COCO_train2014_000000124694_62794.jpg", "ann_id": 62794, "sent_ids": [99988, 99989], "ref_id": 43529}, {"segmentation": [[288.04, 357.9, 251.13, 347.45, 200.98, 353.72, 173.12, 327.95, 161.98, 295.91, 174.51, 269.45, 200.28, 250.64, 220.48, 242.28, 232.32, 219.3, 218.39, 218.6, 203.77, 232.53, 203.77, 201.89, 234.41, 193.53, 258.09, 183.78, 288.74, 185.17, 294.31, 206.76, 306.85, 229.05, 306.15, 236.02, 285.95, 241.59, 274.81, 249.25, 256.7, 259.7, 253.91, 275.02, 283.86, 291.74, 312.42, 302.88, 320.78, 320.99, 348.64, 308.45, 354.9, 322.38, 311.72, 340.49, 305.45, 358.6, 296.4, 359.29]], "area": 17455.215700000004, "iscrowd": 0, "image_id": 470977, "bbox": [161.98, 183.78, 192.92, 175.51], "category_id": 20, "id": 1817840, "split": "val", "sentences": [{"tokens": ["the", "lamb", "in", "between", "the", "other", "lamb", "and", "the", "mother", "sheep"], "raw": "The lamb in between the other lamb and the mother sheep", "sent_id": 100106, "sent": "the lamb in between the other lamb and the mother sheep"}, {"tokens": ["a", "baby", "lamb", "sitting", "closer", "to", "the", "older", "lamb", "in", "the", "photo"], "raw": "A baby lamb sitting closer to the older lamb in the photo.", "sent_id": 100107, "sent": "a baby lamb sitting closer to the older lamb in the photo"}], "file_name": "COCO_train2014_000000470977_1817840.jpg", "ann_id": 1817840, "sent_ids": [100106, 100107], "ref_id": 43575}, {"segmentation": [[553.25, 246.25, 527.74, 359.22, 567.55, 381.22, 570.27, 423.03, 531.2, 426.0, 409.98, 374.33, 413.98, 313.96, 417.99, 278.83, 425.08, 225.37]], "area": 22408.05334999999, "iscrowd": 0, "image_id": 454144, "bbox": [409.98, 225.37, 160.29, 200.63], "category_id": 63, "id": 111263, "split": "val", "sentences": [{"tokens": ["a", "black", "sofa", "with", "a", "brown", "or", "gold", "pattern"], "raw": "A black sofa with a brown or gold pattern.", "sent_id": 100161, "sent": "a black sofa with a brown or gold pattern"}, {"tokens": ["the", "long", "black", "couch"], "raw": "The long black couch", "sent_id": 100162, "sent": "the long black couch"}], "file_name": "COCO_train2014_000000454144_111263.jpg", "ann_id": 111263, "sent_ids": [100161, 100162], "ref_id": 43595}, {"segmentation": [[355.51, 313.41, 352.78, 364.59, 431.94, 468.33, 475.62, 473.79, 468.79, 418.51, 475.62, 406.9, 485.17, 402.13, 489.95, 398.72, 494.04, 378.92, 507.01, 378.92, 508.38, 387.8, 509.74, 398.72, 509.74, 400.08, 531.58, 408.95, 527.48, 395.3, 527.48, 391.89, 511.79, 382.34, 519.98, 374.15, 529.53, 370.73, 541.82, 365.27, 577.99, 378.24, 555.47, 361.86, 552.74, 352.99, 433.31, 305.9, 427.16, 300.44, 384.85, 297.03, 384.85, 301.81], [486.79, 442.35, 481.33, 473.06, 515.45, 470.33, 516.82, 449.86, 495.66, 445.77, 488.16, 439.62], [540.7, 455.32, 538.66, 474.43, 575.51, 466.92, 574.15, 458.05, 541.39, 456.69]], "area": 20576.9835, "iscrowd": 0, "image_id": 320611, "bbox": [352.78, 297.03, 225.21, 177.4], "category_id": 63, "id": 113723, "split": "val", "sentences": [{"tokens": ["a", "white", "sofa", "with", "patterned", "pillows", "upon", "it"], "raw": "A white sofa with patterned pillows upon it.", "sent_id": 100201, "sent": "a white sofa with patterned pillows upon it"}, {"tokens": ["a", "white", "sofa", "that", "is", "right", "in", "front", "of", "a", "window", ";", "there", "is", "also", "an", "end", "table", "on", "each", "side"], "raw": "A white sofa that is right in front of a window; there is also an end table on each side.", "sent_id": 100202, "sent": "a white sofa that is right in front of a window ; there is also an end table on each side"}], "file_name": "COCO_train2014_000000320611_113723.jpg", "ann_id": 113723, "sent_ids": [100201, 100202], "ref_id": 43611}, {"segmentation": [[408.83, 36.66, 374.68, 49.72, 349.57, 86.89, 349.57, 118.03, 360.62, 136.11, 356.6, 157.2, 364.64, 156.2, 368.65, 176.29, 383.72, 191.36, 406.82, 190.35, 341.53, 249.62, 335.5, 311.9, 311.4, 289.8, 290.3, 277.75, 274.23, 281.76, 287.29, 320.94, 327.47, 330.98, 312.4, 360.11, 269.21, 327.97, 264.18, 287.79, 245.1, 304.87, 241.08, 292.81, 227.02, 306.88, 238.07, 343.04, 264.18, 398.29, 313.41, 441.48, 367.65, 440.48, 552.48, 440.48, 552.48, 374.18, 553.48, 307.88, 560.51, 258.66, 537.41, 209.44, 488.19, 172.27, 469.1, 150.17, 460.06, 133.1, 458.05, 61.78, 422.9, 37.67]], "area": 77266.66940000001, "iscrowd": 0, "image_id": 468219, "bbox": [227.02, 36.66, 333.49, 404.82], "category_id": 1, "id": 1718200, "split": "val", "sentences": [{"tokens": ["a", "tall", "man", "fixing", "another", "man", "'", "s", "tie"], "raw": "A tall man fixing another man's tie", "sent_id": 100203, "sent": "a tall man fixing another man ' s tie"}, {"tokens": ["a", "man", "with", "a", "shaved", "head", "and", "white", "jacket", "on", "helps", "another", "man", "with", "his", "tie"], "raw": "A man with a shaved head and white jacket on helps another man with his tie.", "sent_id": 100204, "sent": "a man with a shaved head and white jacket on helps another man with his tie"}], "file_name": "COCO_train2014_000000468219_1718200.jpg", "ann_id": 1718200, "sent_ids": [100203, 100204], "ref_id": 43612}, {"segmentation": [[400.55, 185.24, 328.14, 155.28, 336.46, 110.33, 368.51, 98.68, 397.22, 103.26, 436.34, 117.41, 445.49, 133.64, 439.25, 143.63, 439.25, 179.83]], "area": 7439.683000000001, "iscrowd": 0, "image_id": 157190, "bbox": [328.14, 98.68, 117.35, 86.56], "category_id": 79, "id": 2139380, "split": "val", "sentences": [{"tokens": ["a", "black", "microwave"], "raw": "a black microwave", "sent_id": 100244, "sent": "a black microwave"}, {"tokens": ["a", "black", "microwave", "on", "the", "counter", "to", "the", "right", "of", "a", "man", "wearing", "a", "grey", "shirt"], "raw": "a black microwave on the counter to the right of a man wearing a grey shirt", "sent_id": 100245, "sent": "a black microwave on the counter to the right of a man wearing a grey shirt"}], "file_name": "COCO_train2014_000000157190_2139380.jpg", "ann_id": 2139380, "sent_ids": [100244, 100245], "ref_id": 43627}, {"segmentation": [[373.6, 139.78, 371.63, 131.42, 377.04, 126.49, 374.58, 121.57, 377.54, 95.98, 383.93, 83.68, 428.22, 53.66, 430.68, 48.74, 431.18, 43.33, 438.07, 41.85, 443.97, 39.39, 454.31, 40.87, 451.35, 54.15, 463.16, 52.19, 475.47, 36.93, 482.36, 41.85, 477.93, 62.03, 477.93, 70.39, 482.85, 84.17, 495.64, 65.97, 521.72, 57.11, 526.15, 61.54, 510.41, 92.54, 492.69, 97.46, 487.28, 109.27, 550.76, 150.61, 569.46, 170.29, 588.65, 199.33, 588.65, 203.26, 613.75, 216.55, 623.49, 223.05, 633.94, 259.6, 632.44, 290.93, 623.49, 320.02, 616.78, 346.12, 617.53, 371.48, 613.8, 388.64, 617.53, 425.93, 608.58, 425.19, 598.13, 357.31, 594.4, 385.65, 595.15, 410.27, 601.12, 425.93, 569.04, 425.93, 571.22, 412.57, 567.47, 367.99, 563.72, 358.4, 564.14, 349.24, 558.3, 325.07, 555.39, 334.65, 558.72, 349.65, 560.8, 385.91, 564.14, 402.57, 566.22, 412.99, 562.89, 425.07, 547.05, 425.91, 544.13, 405.07, 547.05, 399.24, 543.3, 377.16, 540.52, 360.9, 523.41, 322.39, 520.2, 303.68, 518.15, 256.05, 525.63, 220.75, 530.45, 206.31, 480.71, 173.15, 476.43, 163.53, 455.58, 151.76, 413.33, 152.3, 403.76, 146.34, 387.91, 149.96, 375.69, 144.98, 374.78, 137.73]], "area": 36076.102100000004, "iscrowd": 0, "image_id": 367715, "bbox": [371.63, 36.93, 262.31, 389.0], "category_id": 25, "id": 595340, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "at", "a", "zoo", "being", "fed", "by", "a", "man"], "raw": "A giraffe at a zoo being fed by a man.", "sent_id": 100314, "sent": "a giraffe at a zoo being fed by a man"}, {"tokens": ["giraffe", "standing", "in", "field"], "raw": "Giraffe standing in field", "sent_id": 100315, "sent": "giraffe standing in field"}], "file_name": "COCO_train2014_000000367715_595340.jpg", "ann_id": 595340, "sent_ids": [100314, 100315], "ref_id": 43654}, {"segmentation": [[63.64, 469.68, 112.67, 369.65, 159.74, 308.86, 210.73, 302.97, 273.49, 278.45, 307.8, 264.73, 349.97, 258.84, 345.07, 249.04, 328.4, 242.18, 350.95, 226.48, 342.13, 209.82, 266.62, 193.14, 204.85, 180.4, 174.45, 174.52, 164.65, 182.36, 85.21, 174.52, 84.23, 193.14, 110.71, 215.7, 117.57, 227.47, 54.82, 304.93, 14.62, 371.62, 0.0, 401.03, 0.0, 462.81, 0.0, 480.0, 47.95, 480.0]], "area": 41966.75050000001, "iscrowd": 0, "image_id": 304408, "bbox": [0.0, 174.52, 350.95, 305.48], "category_id": 25, "id": 597602, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "looking", "at", "a", "kid", "and", "older", "man"], "raw": "A giraffe looking at a kid and older man.", "sent_id": 100328, "sent": "a giraffe looking at a kid and older man"}, {"tokens": ["a", "giraffe", "looking", "at", "a", "man", "and", "child"], "raw": "A giraffe looking at a man and child.", "sent_id": 100329, "sent": "a giraffe looking at a man and child"}], "file_name": "COCO_train2014_000000304408_597602.jpg", "ann_id": 597602, "sent_ids": [100328, 100329], "ref_id": 43659}, {"segmentation": [[168.27, 120.81, 168.27, 143.82, 106.43, 161.08, 86.29, 179.78, 61.84, 184.09, 27.33, 172.58, 27.33, 142.38, 24.45, 60.4, 100.67, 60.4]], "area": 13026.037, "iscrowd": 0, "image_id": 529689, "bbox": [24.45, 60.4, 143.82, 123.69], "category_id": 7, "id": 172937, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "train", "that", "has", "red", ",", "green", "and", "white", "compartments"], "raw": "The back of train that has red, green and white compartments.", "sent_id": 100409, "sent": "the back of train that has red , green and white compartments"}, {"tokens": ["this", "is", "the", "train", "on", "the", "far", "left"], "raw": "This is the train on the far left.", "sent_id": 100410, "sent": "this is the train on the far left"}], "file_name": "COCO_train2014_000000529689_172937.jpg", "ann_id": 172937, "sent_ids": [100409, 100410], "ref_id": 43689}, {"segmentation": [[283.73, 263.24, 250.07, 299.79, 159.66, 322.87, 80.79, 329.6, 34.62, 305.56, 29.82, 263.24, 87.52, 215.15, 169.28, 208.42, 248.14, 203.61, 266.42, 213.23, 267.38, 227.65, 216.4, 246.89, 252.95, 251.7, 280.84, 251.7]], "area": 23216.398300000004, "iscrowd": 0, "image_id": 132889, "bbox": [29.82, 203.61, 253.91, 125.99], "category_id": 59, "id": 1076885, "split": "val", "sentences": [{"tokens": ["the", "deep", "dish", "pizza", "pie", "with", "the", "slice", "missing"], "raw": "The deep dish pizza pie with the slice missing.", "sent_id": 100427, "sent": "the deep dish pizza pie with the slice missing"}, {"tokens": ["the", "pizza", "sitting", "up", "on", "a", "stand"], "raw": "The pizza sitting up on a stand.", "sent_id": 100428, "sent": "the pizza sitting up on a stand"}], "file_name": "COCO_train2014_000000132889_1076885.jpg", "ann_id": 1076885, "sent_ids": [100427, 100428], "ref_id": 43694}, {"segmentation": [[104.3, 507.26, 47.41, 410.86, 22.12, 339.75, 25.28, 311.31, 47.41, 238.62, 55.31, 210.17, 50.57, 181.73, 44.25, 169.09, 71.11, 169.09, 83.75, 161.19, 102.72, 120.1, 140.64, 121.68, 151.7, 109.04, 158.02, 129.58, 195.95, 131.16, 211.75, 124.84, 214.91, 135.9, 244.94, 146.96, 304.99, 346.07, 336.59, 442.47, 363.46, 480.4, 327.11, 504.1, 309.73, 491.46, 281.28, 499.36, 278.12, 500.94, 289.19, 518.32, 330.27, 532.54, 316.05, 548.35, 292.35, 537.28, 287.6, 546.77, 252.84, 519.9, 248.1, 512.0, 243.36, 493.04, 235.46, 496.2, 238.62, 523.06, 224.4, 512.0, 195.95, 543.6, 165.93, 551.51, 143.8, 543.6]], "area": 97025.60615, "iscrowd": 0, "image_id": 564823, "bbox": [22.12, 109.04, 341.34, 442.47], "category_id": 54, "id": 2219649, "split": "val", "sentences": [{"tokens": ["a", "sandwich", "filled", "with", "lettuce", ",", "tomato", ",", "and", "crumbled", "cheese"], "raw": "A sandwich filled with lettuce, tomato, and crumbled cheese.", "sent_id": 100612, "sent": "a sandwich filled with lettuce , tomato , and crumbled cheese"}, {"tokens": ["a", "huge", "sandwich", "with", "lots", "of", "veggies", "piled", "on", "a", "blue", "plate"], "raw": "A huge sandwich with lots of veggies piled on a blue plate", "sent_id": 100613, "sent": "a huge sandwich with lots of veggies piled on a blue plate"}], "file_name": "COCO_train2014_000000564823_2219649.jpg", "ann_id": 2219649, "sent_ids": [100612, 100613], "ref_id": 43759}, {"segmentation": [[239.7, 292.62, 245.85, 289.63, 252.49, 289.3, 261.45, 289.96, 277.73, 293.45, 293.0, 297.27, 307.78, 303.24, 308.28, 303.41, 312.6, 293.95, 326.54, 270.04, 341.49, 242.14, 347.8, 232.18, 356.93, 216.9, 359.92, 212.42, 362.41, 209.93, 364.74, 210.09, 371.71, 213.91, 371.05, 218.73, 363.57, 238.82, 357.6, 250.77, 356.27, 257.08, 354.44, 264.06, 352.12, 271.7, 350.46, 276.35, 350.29, 279.5, 348.13, 287.64, 345.64, 295.11, 342.82, 303.91, 340.16, 310.72, 337.5, 320.18, 334.35, 328.82, 334.02, 329.48, 335.35, 330.64, 334.85, 338.28, 334.68, 345.42, 333.19, 352.23, 327.38, 364.35, 329.04, 370.83, 329.04, 375.0, 321.4, 375.0, 320.9, 372.65, 319.9, 373.48, 319.9, 375.0, 249.67, 375.0, 239.37, 371.66, 226.42, 366.18, 224.26, 365.35, 219.11, 374.98, 209.32, 374.98, 215.13, 360.03, 211.64, 357.38, 207.99, 350.9, 206.66, 345.42, 206.16, 336.79, 206.99, 333.47, 213.97, 320.85, 222.6, 309.39, 230.74, 299.76]], "area": 11494.163599999998, "iscrowd": 0, "image_id": 523484, "bbox": [206.16, 209.93, 165.55, 165.07], "category_id": 62, "id": 100670, "split": "val", "sentences": [{"tokens": ["a", "simple", "wooden", "chair", "in", "front", "of", "a", "cat"], "raw": "A simple wooden chair in front of a cat.", "sent_id": 100616, "sent": "a simple wooden chair in front of a cat"}, {"tokens": ["the", "wooden", "chair", "that", "is", "empty"], "raw": "the wooden chair that is empty", "sent_id": 100617, "sent": "the wooden chair that is empty"}], "file_name": "COCO_train2014_000000523484_100670.jpg", "ann_id": 100670, "sent_ids": [100616, 100617], "ref_id": 43761}, {"segmentation": [[27.38, 1.01, 28.79, 13.69, 45.69, 37.63, 56.02, 56.41, 55.55, 61.11, 71.52, 61.11, 76.68, 67.68, 93.11, 67.21, 94.99, 58.76, 125.98, 56.41, 132.55, 73.79, 139.6, 70.97, 134.9, 49.37, 253.22, 65.34, 257.91, 38.57, 245.24, 34.35, 255.09, 18.38, 262.61, 11.81, 261.67, 1.01, 259.79, 0.54], [338.67, 0.07, 334.91, 12.28, 339.14, 16.51, 353.22, 28.24, 354.16, 34.35, 384.21, 39.04, 397.36, 13.69, 404.4, 0.0], [332.09, 30.59, 330.69, 43.27, 345.71, 49.84, 348.53, 45.62, 333.03, 33.41], [330.69, 58.76, 332.56, 81.3, 341.95, 79.89, 336.79, 62.52]], "area": 14797.5894, "iscrowd": 0, "image_id": 226046, "bbox": [27.38, 0.0, 377.02, 81.3], "category_id": 1, "id": 1727876, "split": "val", "sentences": [{"tokens": ["the", "person", "sitting", "at", "the", "table", "of", "food"], "raw": "The person sitting at the table of food.", "sent_id": 100637, "sent": "the person sitting at the table of food"}, {"tokens": ["a", "person", "touching", "a", "sandwich"], "raw": "A person touching a sandwich", "sent_id": 100638, "sent": "a person touching a sandwich"}], "file_name": "COCO_train2014_000000226046_1727876.jpg", "ann_id": 1727876, "sent_ids": [100637, 100638], "ref_id": 43770}, {"segmentation": [[287.75, 275.96, 287.75, 266.07, 285.4, 259.47, 282.1, 239.67, 279.27, 226.01, 269.37, 214.22, 269.37, 188.3, 274.56, 169.92, 272.67, 163.79, 274.56, 156.25, 276.44, 147.77, 271.73, 149.18, 268.9, 122.32, 272.2, 109.59, 260.42, 114.78, 252.88, 111.95, 252.88, 106.29, 254.29, 97.81, 254.76, 91.68, 257.59, 88.39, 259.95, 88.39, 269.37, 80.37, 284.93, 71.89, 295.96, 69.46, 296.3, 64.73, 292.92, 63.04, 292.92, 53.58, 294.95, 50.54, 294.95, 49.19, 298.33, 42.77, 298.66, 39.73, 306.44, 38.71, 316.57, 41.75, 316.91, 55.95, 319.62, 56.62, 315.9, 64.39, 317.59, 73.52, 333.13, 82.3, 340.9, 110.69, 343.61, 127.25, 337.19, 127.92, 334.82, 132.31, 328.4, 136.71, 320.97, 145.15, 324.35, 175.57, 322.66, 196.18, 319.95, 202.94, 322.66, 203.95, 323.67, 212.74, 325.36, 229.63, 326.37, 237.07, 326.71, 247.21, 321.64, 248.89, 316.57, 253.96, 313.53, 272.55, 311.17, 282.01, 310.83, 287.75, 296.3, 284.38, 297.65, 276.27, 303.73, 276.6, 307.11, 267.82, 308.46, 254.3, 306.1, 242.81, 308.46, 226.59, 303.06, 207.67, 299.68, 189.42, 296.98, 143.77, 295.96, 142.08, 299.0, 137.69, 295.62, 139.04, 294.27, 140.4, 295.96, 189.73, 296.3, 197.84, 293.6, 202.57, 292.92, 206.96, 291.57, 218.79, 292.92, 234.0, 292.92, 248.19, 293.6, 256.64, 292.92, 263.4, 295.29, 277.93, 288.53, 277.59], [280.08, 279.28, 279.74, 271.17, 276.36, 261.37, 270.28, 266.78, 269.27, 271.84, 265.55, 276.91, 275.01, 279.62]], "area": 10845.756500000001, "iscrowd": 0, "image_id": 575768, "bbox": [252.88, 38.71, 90.73, 249.04], "category_id": 1, "id": 207728, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", "and", "jeans", "holding", "a", "shepherd", "'", "s", "crook", ",", "with", "four", "goats", "running", "around", "him"], "raw": "A man in a white shirt and jeans holding a shepherd's crook, with four goats running around him.", "sent_id": 100655, "sent": "a man in a white shirt and jeans holding a shepherd ' s crook , with four goats running around him"}, {"tokens": ["dog", "trainer"], "raw": "DOG TRAINER", "sent_id": 100656, "sent": "dog trainer"}], "file_name": "COCO_train2014_000000575768_207728.jpg", "ann_id": 207728, "sent_ids": [100655, 100656], "ref_id": 43775}, {"segmentation": [[150.21, 432.56, 145.69, 443.86, 118.59, 444.99, 96.0, 446.12, 77.93, 439.34, 75.67, 428.05, 54.21, 428.05, 51.95, 409.98, 32.75, 409.98, 19.2, 385.13, 31.62, 346.73, 45.18, 330.92, 46.31, 281.22, 59.86, 275.58, 62.12, 255.25, 89.22, 248.47, 106.16, 243.95, 110.68, 238.31, 124.24, 211.2, 173.93, 211.2, 214.59, 227.01, 238.31, 240.56, 264.28, 257.51, 267.67, 282.35, 258.64, 281.22, 211.2, 281.22, 195.39, 285.74, 184.09, 300.42, 180.71, 333.18, 171.67, 342.21, 144.56, 347.86, 123.11, 353.51, 123.11, 360.28, 126.49, 390.78, 135.53, 404.33, 147.95, 424.66]], "area": 28838.0485, "iscrowd": 0, "image_id": 29473, "bbox": [19.2, 211.2, 248.47, 234.92], "category_id": 57, "id": 1065794, "split": "val", "sentences": [{"tokens": ["a", "white", "container", "with", "steamed", "carrots", "in", "it"], "raw": "A white container with steamed carrots in it.", "sent_id": 100799, "sent": "a white container with steamed carrots in it"}, {"tokens": ["white", "plastic", "bowl", "of", "carrots", "and", "hummus", "next", "to", "white", "bowls", "of", "other", "food"], "raw": "White plastic bowl of carrots and hummus next to white bowls of other food.", "sent_id": 100800, "sent": "white plastic bowl of carrots and hummus next to white bowls of other food"}], "file_name": "COCO_train2014_000000029473_1065794.jpg", "ann_id": 1065794, "sent_ids": [100799, 100800], "ref_id": 43829}, {"segmentation": [[207.71, 0.0, 207.71, 14.64, 176.5, 45.85, 136.68, 93.2, 118.39, 191.14, 114.08, 219.12, 127.0, 256.79, 161.43, 321.36, 164.66, 342.89, 162.51, 369.79, 167.89, 377.33, 182.96, 381.63, 195.87, 374.1, 200.18, 357.96, 203.41, 346.12, 198.03, 335.35, 226.01, 347.19, 266.91, 363.34, 248.61, 300.91, 247.53, 278.31, 232.47, 260.02, 224.93, 212.66, 236.77, 164.23, 257.22, 119.03, 278.74, 80.29, 273.36, 54.46, 278.74, 36.16, 286.28, 12.48, 294.89, 0.0, 213.09, 0.65]], "area": 38840.3496, "iscrowd": 0, "image_id": 329502, "bbox": [114.08, 0.0, 180.81, 381.63], "category_id": 1, "id": 453886, "split": "val", "sentences": [{"tokens": ["man", "kneeling", "on", "floor"], "raw": "man kneeling on floor", "sent_id": 101181, "sent": "man kneeling on floor"}, {"tokens": ["a", "man", "in", "a", "black", "t", "-", "shirt"], "raw": "a man in a black t-shirt", "sent_id": 101182, "sent": "a man in a black t - shirt"}], "file_name": "COCO_train2014_000000329502_453886.jpg", "ann_id": 453886, "sent_ids": [101181, 101182], "ref_id": 43971}, {"segmentation": [[378.05, 479.31, 376.68, 464.94, 382.16, 458.79, 395.83, 457.42, 407.46, 458.1, 409.51, 433.48, 409.51, 409.54, 411.57, 386.97, 418.41, 361.66, 435.51, 330.2, 464.92, 298.05, 456.02, 300.79, 423.88, 281.64, 417.72, 271.38, 414.99, 261.8, 418.41, 254.96, 427.3, 254.28, 452.61, 270.01, 465.6, 274.8, 475.18, 274.8, 471.07, 254.96, 469.7, 237.18, 471.76, 229.66, 477.91, 222.13, 468.34, 213.92, 455.34, 213.92, 418.41, 220.76, 403.13, 232.32, 387.55, 237.08, 379.12, 237.08, 369.98, 231.69, 363.75, 227.12, 359.6, 222.97, 356.28, 215.91, 355.45, 212.58, 358.36, 194.31, 367.49, 176.04, 386.59, 148.22, 415.24, 115.83, 412.34, 113.76, 404.03, 111.27, 399.47, 107.53, 410.26, 97.98, 422.72, 91.75, 425.63, 82.61, 428.53, 76.8, 431.02, 71.4, 438.08, 70.16, 452.62, 67.25, 462.17, 59.78, 465.07, 57.7, 473.38, 53.96, 481.27, 53.55, 489.57, 56.87, 495.39, 58.53, 499.95, 58.95, 508.58, 64.24, 509.95, 64.51, 517.34, 63.14, 522.28, 65.88, 528.3, 67.25, 530.22, 65.61, 537.62, 64.51, 541.45, 61.5, 544.19, 62.05, 547.48, 65.88, 548.03, 68.9, 548.03, 72.46, 548.58, 76.57, 552.96, 73.01, 554.88, 72.73, 557.62, 74.38, 568.03, 79.03, 574.05, 76.84, 577.61, 76.57, 578.98, 81.77, 580.35, 87.25, 579.81, 93.0, 579.81, 94.65, 584.19, 91.91, 584.19, 97.11, 583.64, 99.58, 587.75, 97.11, 588.3, 102.87, 588.3, 104.24, 594.6, 103.14, 596.79, 107.25, 597.61, 112.73, 597.61, 113.83, 597.89, 117.93, 604.46, 119.85, 604.46, 122.87, 607.2, 125.61, 607.2, 131.91, 610.22, 133.28, 612.96, 136.56, 617.06, 143.14, 617.34, 147.25, 615.42, 151.63, 622.27, 156.84, 622.54, 162.04, 624.19, 168.89, 626.65, 170.26, 634.87, 164.51, 640.0, 165.33, 640.0, 479.19]], "area": 89965.86405, "iscrowd": 0, "image_id": 470977, "bbox": [355.45, 53.55, 284.55, 425.76], "category_id": 20, "id": 61926, "split": "val", "sentences": [{"tokens": ["a", "mother", "sheep", "laying", "in", "hay", "watching", "over", "her", "two", "babies"], "raw": "A mother sheep laying in hay watching over her two babies.", "sent_id": 101327, "sent": "a mother sheep laying in hay watching over her two babies"}, {"tokens": ["an", "adult", "sheep", "looking", "backwards"], "raw": "An adult sheep looking backwards", "sent_id": 101328, "sent": "an adult sheep looking backwards"}], "file_name": "COCO_train2014_000000470977_61926.jpg", "ann_id": 61926, "sent_ids": [101327, 101328], "ref_id": 44028}, {"segmentation": [[449.68, 53.56, 445.35, 79.58, 454.45, 76.54, 457.05, 68.3, 463.56, 79.58, 473.96, 80.88, 489.57, 88.25, 507.78, 93.88, 506.48, 108.19, 509.51, 113.82, 517.31, 93.45, 537.69, 97.35, 522.52, 136.8, 536.39, 129.0, 566.74, 56.17, 555.47, 47.06, 542.46, 41.86, 535.09, 38.82, 535.09, 27.55, 529.89, 20.62, 533.79, 18.01, 536.82, 16.28, 532.92, 11.51, 494.34, 7.18, 478.3, 51.83, 450.99, 52.26], [564.57, 14.98, 581.48, 16.28, 576.27, 33.19, 555.9, 12.38, 565.44, 14.55]], "area": 7118.387749999998, "iscrowd": 0, "image_id": 444344, "bbox": [445.35, 7.18, 136.13, 129.62], "category_id": 62, "id": 372972, "split": "val", "sentences": [{"tokens": ["an", "empty", "chair"], "raw": "an empty chair", "sent_id": 101342, "sent": "an empty chair"}, {"tokens": ["a", "black", "bar", "chair", "in", "the", "background"], "raw": "A black bar chair in the background.", "sent_id": 101343, "sent": "a black bar chair in the background"}], "file_name": "COCO_train2014_000000444344_372972.jpg", "ann_id": 372972, "sent_ids": [101342, 101343], "ref_id": 44035}, {"segmentation": [[20.83, 149.62, 21.08, 133.94, 27.66, 104.84, 35.25, 86.12, 37.27, 78.28, 32.97, 57.53, 34.74, 50.45, 39.3, 48.68, 52.45, 44.63, 63.33, 51.97, 51.44, 70.44, 53.72, 83.85, 65.86, 111.67, 67.63, 122.55, 65.61, 135.46, 61.31, 162.27, 60.55, 185.8, 60.8, 197.44, 54.48, 225.77, 52.2, 237.16, 52.2, 238.0, 41.07, 237.16, 38.79, 229.31, 29.94, 191.87, 25.38, 178.46, 20.83, 150.89]], "area": 5760.914249999999, "iscrowd": 0, "image_id": 205223, "bbox": [20.83, 44.63, 46.8, 193.37], "category_id": 32, "id": 297341, "split": "val", "sentences": [{"tokens": ["a", "dark", "grey", "tie", "to", "the", "left", "of", "three", "other", "ties"], "raw": "A dark grey tie to the left of three other ties.", "sent_id": 101381, "sent": "a dark grey tie to the left of three other ties"}, {"tokens": ["the", "tie", "on", "the", "left"], "raw": "the tie on the left", "sent_id": 101382, "sent": "the tie on the left"}], "file_name": "COCO_train2014_000000205223_297341.jpg", "ann_id": 297341, "sent_ids": [101381, 101382], "ref_id": 44052}, {"segmentation": [[146.81, 207.1, 143.93, 191.75, 122.82, 184.07, 113.23, 171.6, 120.9, 147.61, 143.93, 116.91, 145.85, 103.47, 145.85, 91.0, 148.73, 81.4, 159.29, 86.2, 162.16, 93.88, 173.68, 79.48, 253.32, 43.98, 347.36, 0.8, 522.96, 1.76, 527.75, 22.87, 519.12, 35.34, 499.93, 54.53, 493.21, 86.2, 490.33, 113.07, 507.6, 132.26, 525.83, 131.3, 545.02, 96.75, 562.3, 90.04, 583.41, 80.44, 604.52, 84.28, 617.95, 104.43, 633.3, 90.04, 634.26, 90.04, 638.1, 92.92, 640.0, 226.29, 632.34, 247.4, 618.91, 263.72, 585.33, 304.02, 552.7, 350.08, 534.47, 382.7, 514.32, 397.09, 489.37, 402.85, 487.45, 385.58, 486.49, 382.7, 479.78, 374.06, 460.58, 368.31, 458.67, 381.74, 454.83, 395.17, 452.91, 404.77, 440.43, 402.85, 427.0, 391.34, 425.08, 374.06, 415.49, 369.27, 387.66, 375.98, 354.07, 375.98, 354.07, 382.7, 362.71, 392.3, 364.63, 395.17, 347.36, 395.17, 344.48, 394.22, 317.61, 399.97, 299.38, 401.89, 257.16, 405.73, 217.82, 399.97, 208.22, 385.58, 203.42, 378.86, 181.36, 372.15, 166.0, 361.59, 147.77, 331.84, 143.93, 281.95, 126.66, 274.27, 116.11, 271.39, 127.62, 250.28]], "area": 162031.38025000007, "iscrowd": 0, "image_id": 541255, "bbox": [113.23, 0.8, 526.77, 404.93], "category_id": 54, "id": 308549, "split": "val", "sentences": [{"tokens": ["a", "sandwich", "with", "green", "stuff", "on", "it", "that", "is", "clear", "and", "not", "blurry"], "raw": "a sandwich with green stuff on it that is clear and not blurry", "sent_id": 101393, "sent": "a sandwich with green stuff on it that is clear and not blurry"}], "file_name": "COCO_train2014_000000541255_308549.jpg", "ann_id": 308549, "sent_ids": [101393], "ref_id": 44057}, {"segmentation": [[52.24, 163.01, 229.07, 160.0, 270.27, 153.97, 181.85, 184.11, 164.77, 200.19, 147.69, 198.18, 123.58, 210.23, 127.6, 227.31, 138.65, 228.32, 157.74, 228.32, 193.91, 223.3, 192.9, 237.36, 203.96, 238.37, 222.04, 228.32, 364.71, 172.06, 404.9, 162.01, 554.6, 334.82, 636.98, 420.22, 16.08, 427.0, 0.0, 427.0, 3.01, 263.48]], "area": 123773.48935000002, "iscrowd": 0, "image_id": 197525, "bbox": [0.0, 153.97, 636.98, 273.03], "category_id": 67, "id": 120300, "split": "val", "sentences": [{"tokens": ["a", "large", "pizza", "on", "a", "table", "with", "a", "woman", "'", "s", "hand", "above", "it"], "raw": "A large pizza on a table with a woman's hand above it.", "sent_id": 101412, "sent": "a large pizza on a table with a woman ' s hand above it"}, {"tokens": ["a", "pizza", "that", "is", "wider", "than", "an", "arm"], "raw": "A pizza that is wider than an arm.", "sent_id": 101413, "sent": "a pizza that is wider than an arm"}], "file_name": "COCO_train2014_000000197525_120300.jpg", "ann_id": 120300, "sent_ids": [101412, 101413], "ref_id": 44065}, {"segmentation": [[411.34, 184.53, 435.61, 173.07, 476.73, 191.95, 500.0, 266.1, 500.0, 315.99, 489.54, 313.29, 469.99, 290.37, 450.44, 264.75, 446.4, 250.6, 450.44, 236.44, 451.12, 224.98, 413.37, 186.55]], "area": 5489.088300000003, "iscrowd": 0, "image_id": 192891, "bbox": [411.34, 173.07, 88.66, 142.92], "category_id": 56, "id": 2114191, "split": "val", "sentences": [{"tokens": ["the", "broccoli", "under", "the", "other", "broccoli"], "raw": "The broccoli under the other broccoli.", "sent_id": 101461, "sent": "the broccoli under the other broccoli"}, {"tokens": ["the", "small", "bit", "of", "broccoli", "that", "is", "pointing", "downwards", ",", "under", "the", "larger", "bit", "of", "broccoli"], "raw": "The small bit of broccoli that is pointing downwards, under the larger bit of broccoli", "sent_id": 101462, "sent": "the small bit of broccoli that is pointing downwards , under the larger bit of broccoli"}], "file_name": "COCO_train2014_000000192891_2114191.jpg", "ann_id": 2114191, "sent_ids": [101461, 101462], "ref_id": 44084}, {"segmentation": [[121.62, 272.35, 154.32, 253.72, 164.96, 252.2, 182.45, 245.36, 187.77, 236.61, 194.62, 233.57, 204.12, 230.53, 199.94, 225.59, 200.32, 221.79, 200.7, 210.38, 202.98, 205.06, 204.12, 201.63, 207.93, 197.45, 211.73, 194.03, 218.95, 192.13, 219.71, 192.51, 229.6, 198.59, 232.64, 200.49, 235.68, 203.92, 237.2, 207.72, 241.0, 214.18, 241.0, 216.84, 237.2, 224.45, 242.53, 231.67, 252.03, 232.43, 254.69, 233.19, 262.68, 235.85, 269.9, 247.26, 279.79, 263.99, 306.4, 303.88, 300.32, 309.96, 292.71, 314.52, 271.42, 286.39, 287.39, 334.3, 288.53, 346.46, 287.39, 350.65, 307.54, 358.63, 322.37, 370.77, 324.65, 378.76, 321.61, 388.64, 320.85, 393.97, 318.19, 400.05, 315.91, 403.09, 312.48, 403.47, 310.58, 401.95, 307.92, 395.87, 305.64, 385.22, 303.74, 381.42, 296.9, 379.52, 285.87, 376.1, 280.55, 370.39, 264.58, 363.93, 262.3, 358.99, 256.59, 341.12, 252.41, 335.79, 253.17, 344.16, 253.93, 348.72, 256.59, 357.85, 261.54, 366.21, 266.48, 371.91, 270.28, 378.38, 276.74, 385.6, 280.55, 389.02, 282.07, 394.35, 282.83, 399.29, 278.65, 405.37, 272.94, 408.47, 272.94, 413.03, 264.96, 417.6, 260.02, 416.84, 256.59, 409.23, 254.69, 404.67, 255.07, 399.35, 251.65, 391.36, 245.57, 382.62, 240.62, 371.59, 234.16, 354.86, 233.78, 352.2, 232.64, 364.37, 228.84, 372.73, 228.84, 373.49, 226.18, 373.49, 217.43, 366.27, 215.15, 361.32, 210.97, 352.2, 205.26, 306.19, 204.5, 295.98, 193.48, 267.47, 192.72, 265.19, 134.54, 283.82, 128.46, 283.82, 123.9, 284.2, 123.9, 284.2]], "area": 16055.677599999983, "iscrowd": 0, "image_id": 298017, "bbox": [121.62, 192.13, 203.03, 225.47], "category_id": 1, "id": 185390, "split": "val", "sentences": [{"tokens": ["woman", "holding", "umbrella"], "raw": "woman holding umbrella", "sent_id": 101501, "sent": "woman holding umbrella"}, {"tokens": ["a", "woman", "in", "a", "long", ",", "unhooded", "coat", ",", "poses", "with", "her", "upside", "-", "down", "umbrella", "on", "a", "sidewalk"], "raw": "A woman in a long, unhooded coat, poses with her upside-down umbrella on a sidewalk.", "sent_id": 101502, "sent": "a woman in a long , unhooded coat , poses with her upside - down umbrella on a sidewalk"}], "file_name": "COCO_train2014_000000298017_185390.jpg", "ann_id": 185390, "sent_ids": [101501, 101502], "ref_id": 44098}, {"segmentation": [[159.95, 330.58, 181.58, 336.76, 187.15, 329.96, 183.44, 324.4, 189.0, 305.85, 192.71, 271.24, 185.91, 266.91, 196.42, 255.17, 201.37, 258.26, 237.17, 245.79, 237.46, 241.4, 231.61, 240.23, 218.16, 246.08, 208.51, 247.25, 200.33, 241.99, 201.2, 231.75, 205.0, 224.44, 204.13, 222.1, 203.38, 220.67, 205.96, 216.69, 208.07, 218.68, 210.06, 227.11, 213.22, 228.52, 212.63, 223.25, 216.5, 213.53, 217.9, 208.73, 217.2, 203.92, 219.19, 198.77, 215.68, 192.92, 207.95, 189.29, 201.39, 190.57, 194.72, 192.56, 191.09, 198.77, 190.5, 201.93, 180.66, 203.34, 166.14, 212.24, 152.55, 222.66, 147.4, 227.58, 141.66, 234.61, 137.45, 245.5, 138.38, 250.07, 138.5, 251.94, 142.37, 261.43, 145.29, 264.0, 145.18, 272.79, 149.98, 273.26, 155.83, 272.44, 159.58, 274.66, 154.66, 287.19, 154.66, 291.76, 160.4, 294.34, 168.6, 291.18, 167.9, 297.97, 168.13, 299.14, 159.46, 321.63, 158.29, 329.24]], "area": 6046.761799999999, "iscrowd": 0, "image_id": 119693, "bbox": [137.45, 189.29, 100.01, 147.47], "category_id": 1, "id": 2191446, "split": "val", "sentences": [{"tokens": ["a", "baseball", "umpire", "in", "position", "in", "baseball", "match"], "raw": "a baseball umpire in position in baseball match.", "sent_id": 101521, "sent": "a baseball umpire in position in baseball match"}, {"tokens": ["umpire", "crouching", "behind", "the", "catcher", "and", "watching", "the", "batter"], "raw": "umpire crouching behind the catcher and watching the batter", "sent_id": 101522, "sent": "umpire crouching behind the catcher and watching the batter"}], "file_name": "COCO_train2014_000000119693_2191446.jpg", "ann_id": 2191446, "sent_ids": [101521, 101522], "ref_id": 44107}, {"segmentation": [[197.39, 171.38, 194.16, 167.07, 188.76, 149.81, 188.76, 141.18, 203.87, 113.13, 273.98, 64.59, 300.94, 53.81, 311.73, 149.81, 244.85, 159.51, 225.44, 167.07, 192.0, 172.46], [327.91, 44.1, 371.06, 43.02, 372.13, 2.03, 378.61, 2.03, 374.29, 46.26, 432.54, 50.57, 508.04, 63.51, 558.74, 86.17, 564.13, 87.24, 555.51, 96.95, 557.66, 105.58, 555.51, 112.05, 552.27, 117.45, 536.09, 113.13, 524.22, 106.66, 526.38, 113.13, 498.34, 116.37, 473.53, 122.84, 404.49, 132.55, 330.07, 146.57, 319.28, 150.89, 309.57, 51.65, 332.22, 44.1]], "area": 26814.044000000005, "iscrowd": 0, "image_id": 291493, "bbox": [188.76, 2.03, 375.37, 170.43], "category_id": 54, "id": 310658, "split": "val", "sentences": [{"tokens": ["half", "of", "a", "club", "sandwich", "with", "its", "filling", "obscured", "by", "the", "other", "half"], "raw": "Half of a club sandwich with its filling obscured by the other half.", "sent_id": 101540, "sent": "half of a club sandwich with its filling obscured by the other half"}, {"tokens": ["half", "of", "a", "sandwich", "at", "top", "of", "a", "plate"], "raw": "Half of a sandwich at top of a plate", "sent_id": 101541, "sent": "half of a sandwich at top of a plate"}], "file_name": "COCO_train2014_000000291493_310658.jpg", "ann_id": 310658, "sent_ids": [101540, 101541], "ref_id": 44115}, {"segmentation": [[159.64, 66.27, 177.05, 88.04, 152.38, 150.45, 159.64, 167.86, 171.25, 172.21, 195.92, 182.37, 207.53, 214.3, 206.08, 243.33, 200.27, 276.7, 184.31, 308.63, 178.5, 330.4, 181.41, 344.91, 181.41, 366.68, 178.5, 389.9, 178.5, 407.32, 169.8, 431.99, 159.64, 458.11, 156.73, 472.62, 162.54, 506.0, 116.1, 537.93, 40.63, 540.83, 39.18, 535.03, 60.95, 506.0, 82.72, 450.85, 72.56, 417.48, 55.15, 375.39, 43.54, 359.43, 26.12, 337.66, 24.67, 327.5, 17.41, 301.38, 14.51, 269.45, 29.02, 223.01, 40.63, 189.63, 50.79, 148.99, 69.66, 105.46, 76.92, 80.79, 111.75, 44.5, 133.51, 47.41, 171.25, 70.63]], "area": 60808.028900000005, "iscrowd": 0, "image_id": 527267, "bbox": [14.51, 44.5, 193.02, 496.33], "category_id": 1, "id": 521181, "split": "val", "sentences": [{"tokens": ["a", "person", "wearing", "green", "and", "holding", "bananas"], "raw": "A person wearing green and holding bananas.", "sent_id": 101564, "sent": "a person wearing green and holding bananas"}, {"tokens": ["a", "lady", "holding", "bananas"], "raw": "A lady holding bananas.", "sent_id": 101565, "sent": "a lady holding bananas"}], "file_name": "COCO_train2014_000000527267_521181.jpg", "ann_id": 521181, "sent_ids": [101564, 101565], "ref_id": 44124}, {"segmentation": [[368.78, 285.45, 347.24, 227.99, 331.09, 224.41, 322.11, 210.94, 319.41, 225.31, 328.39, 284.55, 332.88, 310.58, 338.27, 313.27, 329.29, 320.45, 331.09, 357.25, 331.09, 360.85, 326.6, 403.93, 330.19, 394.05, 331.09, 393.16, 334.68, 360.85, 358.02, 369.83, 364.29, 378.8, 340.95, 393.16, 335.58, 394.05, 348.14, 404.83, 364.29, 407.53, 374.17, 411.12, 376.87, 400.34, 407.38, 381.49, 404.69, 374.31, 390.33, 373.41, 367.89, 378.8, 372.38, 368.03, 395.72, 360.85, 401.1, 349.18, 397.51, 327.64, 358.92, 322.25, 366.09, 310.58, 379.56, 306.1, 366.99, 276.47]], "area": 7939.1381999999985, "iscrowd": 0, "image_id": 77332, "bbox": [319.41, 210.94, 87.97, 200.18], "category_id": 62, "id": 105478, "split": "val", "sentences": [{"tokens": ["a", "tall", "wooden", "chair", "with", "a", "green", "cushion"], "raw": "A TALL WOODEN CHAIR WITH A GREEN CUSHION.", "sent_id": 101581, "sent": "a tall wooden chair with a green cushion"}, {"tokens": ["the", "chair", "the", "woman", "is", "leaning", "on"], "raw": "the chair the woman is leaning on", "sent_id": 101582, "sent": "the chair the woman is leaning on"}], "file_name": "COCO_train2014_000000077332_105478.jpg", "ann_id": 105478, "sent_ids": [101581, 101582], "ref_id": 44130}, {"segmentation": [[94.77, 411.48, 89.03, 381.8, 101.47, 344.47, 92.86, 314.79, 89.99, 268.84, 93.82, 227.68, 118.71, 204.7, 155.08, 179.81, 205.82, 150.14, 242.2, 113.76, 269.96, 96.53, 360.9, 97.49, 441.32, 88.87, 491.1, 79.3, 509.29, 73.55, 509.29, 63.02, 529.39, 57.28, 529.39, 81.21, 548.53, 106.1, 562.89, 166.41, 537.05, 166.41, 515.03, 141.52, 489.18, 130.03, 433.66, 141.52, 363.78, 163.54, 305.38, 195.13, 312.08, 226.72, 311.12, 251.61, 291.02, 310.01, 278.58, 356.91, 275.7, 378.93, 267.09, 419.14, 246.03, 419.14, 246.03, 404.78, 242.2, 401.91, 242.2, 417.22, 224.01, 420.1, 226.88, 392.33, 233.58, 361.7, 239.33, 316.71, 241.24, 287.99, 226.88, 299.48, 205.82, 307.13, 188.59, 314.79, 170.4, 298.52, 165.61, 321.49, 159.87, 349.26, 158.91, 377.98, 157.96, 399.04, 162.74, 419.14, 144.55, 417.22, 123.49, 395.21, 123.49, 386.59, 117.75, 394.25, 116.79, 408.61, 116.79, 417.22, 101.47, 422.01, 90.94, 419.14, 95.73, 409.57]], "area": 61681.87640000004, "iscrowd": 0, "image_id": 418989, "bbox": [89.03, 57.28, 473.86, 364.73], "category_id": 25, "id": 599935, "split": "val", "sentences": [{"tokens": ["a", "tall", "giraffe", "eating"], "raw": "A tall giraffe eating.", "sent_id": 101611, "sent": "a tall giraffe eating"}, {"tokens": ["a", "giraffe", "eating", "leaves", "from", "a", "tree", "along", "side", "another", "giraffe"], "raw": "a giraffe eating leaves from a tree along side another giraffe", "sent_id": 101612, "sent": "a giraffe eating leaves from a tree along side another giraffe"}], "file_name": "COCO_train2014_000000418989_599935.jpg", "ann_id": 599935, "sent_ids": [101611, 101612], "ref_id": 44140}, {"segmentation": [[339.78, 475.51, 318.2, 424.81, 324.67, 403.24, 408.81, 393.53, 456.27, 405.39, 506.97, 384.9, 524.22, 395.69, 526.38, 417.26, 567.37, 445.3, 607.28, 451.78, 640.0, 471.19]], "area": 18342.748500000005, "iscrowd": 0, "image_id": 182406, "bbox": [318.2, 384.9, 321.8, 90.61], "category_id": 27, "id": 1421499, "split": "val", "sentences": [{"tokens": ["blue", "and", "black", "backpack", "in", "front", "of", "a", "man", "on", "the", "phone"], "raw": "Blue and black backpack in front of a man on the phone.", "sent_id": 101680, "sent": "blue and black backpack in front of a man on the phone"}, {"tokens": ["a", "blue", "and", "black", "booksack", "or", "duffel", "bag", "next", "to", "a", "guy", "on", "the", "phone"], "raw": "A blue and black booksack or duffel bag next to a guy on the phone.", "sent_id": 101681, "sent": "a blue and black booksack or duffel bag next to a guy on the phone"}], "file_name": "COCO_train2014_000000182406_1421499.jpg", "ann_id": 1421499, "sent_ids": [101680, 101681], "ref_id": 44162}, {"segmentation": [[119.37, 319.38, 117.93, 309.31, 117.93, 276.23, 117.93, 256.1, 132.31, 233.08, 151.01, 215.83, 163.96, 210.07, 181.21, 192.81, 185.53, 187.06, 185.53, 145.35, 185.53, 125.22, 176.9, 96.46, 176.9, 76.32, 204.22, 40.37, 214.29, 30.3, 248.81, 30.3, 270.38, 36.05, 287.64, 43.24, 299.15, 54.75, 297.71, 90.7, 300.58, 113.71, 309.21, 136.73, 330.79, 158.3, 382.56, 225.89, 388.31, 237.4, 396.94, 248.9, 411.33, 271.92, 412.76, 302.12, 414.2, 332.32, 414.2, 332.32, 414.2, 332.32]], "area": 55310.168999999994, "iscrowd": 0, "image_id": 131030, "bbox": [117.93, 30.3, 296.27, 302.02], "category_id": 1, "id": 428628, "split": "val", "sentences": [{"tokens": ["a", "male", "smiling", "with", "spikey", "hair", "and", "glasses"], "raw": "A male smiling with spikey hair and glasses.", "sent_id": 101690, "sent": "a male smiling with spikey hair and glasses"}, {"tokens": ["a", "man", "sitting", "in", "front", "of", "a", "larger", "pizza", "with", "pineapple", "on", "it"], "raw": "A man sitting in front of a larger pizza with pineapple on it.", "sent_id": 101691, "sent": "a man sitting in front of a larger pizza with pineapple on it"}], "file_name": "COCO_train2014_000000131030_428628.jpg", "ann_id": 428628, "sent_ids": [101690, 101691], "ref_id": 44166}, {"segmentation": [[67.66, 105.88, 56.23, 97.3, 38.12, 96.35, 21.92, 90.63, 10.48, 86.82, 0.0, 81.1, 0.95, 57.27, 3.81, 50.6, 3.81, 41.07, 0.0, 30.59, 1.91, 5.81, 6.67, 1.05, 126.75, 0.0, 131.52, 22.01, 119.13, 23.92, 116.27, 28.68, 114.36, 31.54, 121.99, 36.31, 128.66, 37.26, 133.42, 49.65, 129.61, 56.32, 122.94, 63.94, 88.63, 95.39, 74.34, 101.11, 67.66, 104.92]], "area": 11208.628800000002, "iscrowd": 0, "image_id": 155268, "bbox": [0.0, 0.0, 133.42, 105.88], "category_id": 1, "id": 492123, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "on", "a", "green", "sofa"], "raw": "A man sitting on a green sofa.", "sent_id": 101738, "sent": "a man sitting on a green sofa"}, {"tokens": ["a", "man"], "raw": "a man", "sent_id": 101739, "sent": "a man"}], "file_name": "COCO_train2014_000000155268_492123.jpg", "ann_id": 492123, "sent_ids": [101738, 101739], "ref_id": 44186}, {"segmentation": [[275.91, 259.0, 264.43, 234.53, 263.67, 201.65, 283.55, 196.29, 301.91, 198.59, 323.32, 198.59, 330.97, 199.35, 349.33, 208.53, 364.62, 224.59, 373.03, 239.88, 360.8, 308.72, 359.27, 340.07, 357.74, 346.19, 343.21, 348.48, 349.33, 328.6, 345.5, 311.77, 336.32, 309.48, 332.5, 330.13, 330.21, 341.6, 318.73, 324.78, 312.62, 316.36, 308.79, 301.83, 304.2, 293.42, 297.32, 288.07, 308.03, 330.89, 301.14, 332.42, 296.56, 330.13, 288.91, 320.95, 287.38, 333.95, 277.44, 337.01, 276.67, 287.3, 279.73, 269.71, 272.85, 271.24, 274.38, 262.06]], "area": 11645.307149999995, "iscrowd": 0, "image_id": 300047, "bbox": [263.67, 196.29, 109.36, 152.19], "category_id": 22, "id": 1821386, "split": "val", "sentences": [{"tokens": ["a", "large", "elephant"], "raw": "A large elephant.", "sent_id": 101869, "sent": "a large elephant"}, {"tokens": ["elephant", "and", "with", "its", "child", "elephant"], "raw": "elephant and with its child elephant", "sent_id": 101870, "sent": "elephant and with its child elephant"}], "file_name": "COCO_train2014_000000300047_1821386.jpg", "ann_id": 1821386, "sent_ids": [101869, 101870], "ref_id": 44234}, {"segmentation": [[74.16, 57.13, 74.16, 167.0, 49.44, 183.48, 52.19, 311.21, 63.18, 458.16, 85.15, 478.76, 152.45, 463.66, 162.06, 444.43, 157.94, 194.47, 123.61, 149.15, 115.36, 53.01, 81.03, 46.15]], "area": 36838.69625000001, "iscrowd": 0, "image_id": 56032, "bbox": [49.44, 46.15, 112.62, 432.61], "category_id": 44, "id": 89147, "split": "val", "sentences": [{"tokens": ["a", "wine", "bottle", "with", "a", "white", "label"], "raw": "A wine bottle with a white label.", "sent_id": 101874, "sent": "a wine bottle with a white label"}, {"tokens": ["a", "sample", "bottle", "of", "wine", "opened", "and", "emptied"], "raw": "A sample bottle of wine opened and emptied.", "sent_id": 101875, "sent": "a sample bottle of wine opened and emptied"}], "file_name": "COCO_train2014_000000056032_89147.jpg", "ann_id": 89147, "sent_ids": [101874, 101875], "ref_id": 44237}, {"segmentation": [[205.0, 227.0, 1.5, 253.5, 0.5, 233.5, 185.0, 215.5, 185.5, 228.0, 190.5, 227.0, 190.0, 211.0, 218.5, 209.0, 217.0, 227.0]], "area": 3641.25, "iscrowd": 0, "image_id": 311706, "bbox": [0.5, 209.0, 218.0, 44.5], "category_id": 67, "id": 1965493, "split": "val", "sentences": [{"tokens": ["the", "part", "of", "the", "table", "in", "front", "of", "the", "garbage", "can"], "raw": "The part of the table in front of the garbage can.", "sent_id": 101919, "sent": "the part of the table in front of the garbage can"}, {"tokens": ["the", "table", "next", "to", "the", "men", "with", "a", "beer", "bottle", "on", "it"], "raw": "The table next to the men with a beer bottle on it.", "sent_id": 101920, "sent": "the table next to the men with a beer bottle on it"}], "file_name": "COCO_train2014_000000311706_1965493.jpg", "ann_id": 1965493, "sent_ids": [101919, 101920], "ref_id": 44252}, {"segmentation": [[259.07, 249.42, 266.1, 235.37, 280.62, 229.28, 305.45, 227.4, 329.81, 229.75, 349.49, 228.81, 359.32, 239.11, 369.16, 239.11, 386.96, 248.02, 392.59, 268.16, 402.42, 261.6, 408.51, 261.6, 409.92, 270.03, 401.95, 278.93, 401.95, 297.67, 398.21, 313.13, 398.68, 325.31, 397.74, 330.93, 389.77, 334.21, 386.5, 334.21, 381.34, 327.18, 371.5, 306.1, 368.23, 296.73, 368.23, 283.62, 359.79, 280.81, 358.86, 293.92, 352.77, 305.64, 352.3, 323.44, 351.36, 344.52, 346.21, 344.52, 343.4, 326.72, 343.4, 303.76, 342.93, 293.46, 337.31, 291.58, 333.09, 300.95, 331.69, 320.63, 329.81, 329.06, 329.81, 345.92, 319.97, 345.92, 323.72, 326.25, 321.38, 316.41, 321.38, 293.46, 292.34, 291.11, 282.97, 300.95, 288.12, 329.06, 290.46, 340.3, 282.5, 347.8, 282.5, 339.83, 276.88, 339.83, 276.41, 330.93, 270.79, 328.59, 269.85, 303.29, 267.51, 289.24, 259.07, 270.97, 245.49, 273.31, 242.21, 260.2, 247.36, 248.02, 248.3, 257.85, 249.71, 268.63, 255.8, 263.94, 259.07, 250.36]], "area": 10889.367749999992, "iscrowd": 0, "image_id": 504187, "bbox": [242.21, 227.4, 167.71, 120.4], "category_id": 24, "id": 588612, "split": "val", "sentences": [{"tokens": ["a", "zebra", "eating", "hay", "standing", "next", "to", "another", "zebra"], "raw": "A zebra eating hay standing next to another zebra.", "sent_id": 101958, "sent": "a zebra eating hay standing next to another zebra"}], "file_name": "COCO_train2014_000000504187_588612.jpg", "ann_id": 588612, "sent_ids": [101958], "ref_id": 44268}, {"segmentation": [[131.89, 42.16, 163.24, 29.19, 198.92, 24.86, 237.84, 31.35, 268.11, 42.16, 287.57, 59.46, 300.54, 98.38, 292.97, 135.14, 284.32, 164.32, 268.11, 178.38, 252.97, 188.11, 235.68, 189.19, 203.24, 190.27, 167.57, 191.35, 149.19, 191.35, 120.0, 175.14, 97.3, 149.19, 87.57, 124.32, 90.81, 91.89, 100.54, 64.86, 109.19, 49.73, 138.38, 38.92, 154.59, 32.43]], "area": 28896.017699999997, "iscrowd": 0, "image_id": 9822, "bbox": [87.57, 24.86, 212.97, 166.49], "category_id": 60, "id": 1081134, "split": "val", "sentences": [{"tokens": ["the", "single", "donnet", "on", "the", "top"], "raw": "THE SINGLE DONNET ON THE TOP", "sent_id": 101961, "sent": "the single donnet on the top"}, {"tokens": ["farthest", "donut"], "raw": "farthest donut", "sent_id": 101962, "sent": "farthest donut"}], "file_name": "COCO_train2014_000000009822_1081134.jpg", "ann_id": 1081134, "sent_ids": [101961, 101962], "ref_id": 44269}, {"segmentation": [[15.1, 441.17, 58.25, 419.6, 111.1, 401.26, 138.07, 382.92, 155.33, 373.21, 154.25, 340.85, 149.93, 320.36, 146.7, 286.92, 144.54, 265.35, 136.99, 224.36, 161.8, 165.03, 202.79, 122.97, 252.4, 107.87, 302.02, 111.1, 341.93, 127.28, 373.21, 155.33, 392.63, 194.16, 399.1, 235.15, 396.94, 261.03, 390.47, 279.37, 380.76, 292.31, 379.69, 316.04, 369.98, 341.93, 363.51, 367.82, 359.19, 388.31, 350.56, 403.42, 345.17, 419.6, 337.62, 428.22, 326.83, 432.54, 306.34, 447.64, 300.94, 453.03, 293.39, 459.51, 294.47, 472.45, 1.08, 473.53, 4.31, 449.8, 11.87, 445.48]], "area": 84867.96489999998, "iscrowd": 0, "image_id": 87214, "bbox": [1.08, 107.87, 398.02, 365.66], "category_id": 1, "id": 541905, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "black", "helmet", "and", "brown", "shirt", "smiling", "on", "a", "snowy", "mountaintop"], "raw": "A person in a black helmet and brown shirt smiling on a snowy mountaintop.", "sent_id": 101992, "sent": "a person in a black helmet and brown shirt smiling on a snowy mountaintop"}, {"tokens": ["person", "with", "glasses", "looking", "at", "the", "camera"], "raw": "Person with glasses looking at the camera.", "sent_id": 101993, "sent": "person with glasses looking at the camera"}], "file_name": "COCO_train2014_000000087214_541905.jpg", "ann_id": 541905, "sent_ids": [101992, 101993], "ref_id": 44281}, {"segmentation": [[305.59, 498.02, 318.56, 460.54, 321.44, 436.04, 343.06, 382.7, 351.71, 349.55, 383.42, 339.46, 396.4, 314.95, 392.07, 281.8, 374.77, 250.09, 363.24, 227.03, 351.71, 224.14, 351.71, 201.08, 335.86, 182.34, 322.88, 169.37, 291.17, 160.72, 255.14, 166.49, 229.19, 185.23, 224.86, 222.7, 219.1, 258.74, 233.51, 281.8, 213.33, 291.89, 209.01, 310.63, 223.42, 313.51, 230.63, 340.9, 259.46, 307.75, 266.67, 306.31, 262.34, 323.6, 246.49, 348.11, 233.51, 363.96, 220.54, 379.82, 240.72, 424.5, 269.55, 461.98, 296.94, 490.81], [190.27, 405.77, 177.3, 460.54, 184.5, 505.23, 183.06, 544.14, 203.24, 549.91, 217.66, 549.91, 223.42, 565.77, 252.25, 557.12, 256.58, 539.82, 250.81, 502.34, 223.42, 446.13, 206.13, 436.04, 206.13, 418.74]], "area": 45167.04175, "iscrowd": 0, "image_id": 33991, "bbox": [177.3, 160.72, 219.1, 405.05], "category_id": 1, "id": 1227109, "split": "val", "sentences": [{"tokens": ["a", "baby", "looks", "at", "an", "elephant"], "raw": "A baby looks at an elephant.", "sent_id": 102046, "sent": "a baby looks at an elephant"}, {"tokens": ["a", "small", "child", "in", "an", "orange", "shirt"], "raw": "a small child in an orange shirt", "sent_id": 102047, "sent": "a small child in an orange shirt"}], "file_name": "COCO_train2014_000000033991_1227109.jpg", "ann_id": 1227109, "sent_ids": [102046, 102047], "ref_id": 44301}, {"segmentation": [[248.81, 312.09, 327.91, 304.9, 362.43, 291.96, 372.49, 279.01, 365.3, 250.25, 348.04, 228.67, 337.98, 218.61, 291.96, 225.8, 220.04, 230.11, 178.34, 231.55, 155.33, 270.38, 158.2, 286.2, 201.35, 306.34, 254.56, 310.65]], "area": 15476.820399999997, "iscrowd": 0, "image_id": 209603, "bbox": [155.33, 218.61, 217.16, 93.48], "category_id": 59, "id": 1072452, "split": "val", "sentences": [{"tokens": ["the", "calzone", "in", "the", "middle", "of", "the", "picture"], "raw": "The calzone in the middle of the picture.", "sent_id": 102052, "sent": "the calzone in the middle of the picture"}], "file_name": "COCO_train2014_000000209603_1072452.jpg", "ann_id": 1072452, "sent_ids": [102052], "ref_id": 44304}, {"segmentation": [[148.54, 265.81, 161.94, 242.36, 190.98, 233.42, 217.79, 233.42, 237.89, 246.82, 233.42, 257.99, 231.19, 302.67, 239.01, 323.89, 246.82, 321.65, 261.34, 313.84, 263.58, 314.95, 255.76, 325.0, 241.24, 336.17, 223.37, 333.94, 221.14, 365.21, 208.85, 381.96, 199.92, 383.08, 193.22, 377.5, 180.93, 371.91, 170.88, 371.91, 164.18, 364.09, 159.71, 328.36, 151.89, 302.67, 146.31, 284.8]], "area": 10540.308149999999, "iscrowd": 0, "image_id": 363331, "bbox": [146.31, 233.42, 117.27, 149.66], "category_id": 22, "id": 580829, "split": "val", "sentences": [{"tokens": ["elephant", "in", "back"], "raw": "Elephant in back.", "sent_id": 102061, "sent": "elephant in back"}, {"tokens": ["elephant", "following", "another", "elephant"], "raw": "elephant following another elephant", "sent_id": 102062, "sent": "elephant following another elephant"}], "file_name": "COCO_train2014_000000363331_580829.jpg", "ann_id": 580829, "sent_ids": [102061, 102062], "ref_id": 44310}, {"segmentation": [[92.27, 273.21, 134.59, 279.13, 159.99, 268.98, 173.53, 246.97, 151.52, 213.11, 159.14, 147.93, 167.61, 72.59, 164.7, 28.34, 153.63, 0.0, 64.33, 0.63, 63.49, 46.35, 59.26, 75.97, 66.03, 158.93, 68.57, 235.12, 83.8, 271.52, 93.12, 275.75]], "area": 26248.10795, "iscrowd": 0, "image_id": 80590, "bbox": [59.26, 0.0, 114.27, 279.13], "category_id": 44, "id": 288317, "split": "val", "sentences": [{"tokens": ["the", "bottle", "with", "the", "2006", "sticker"], "raw": "The bottle with the 2006 sticker", "sent_id": 102104, "sent": "the bottle with the 2006 sticker"}, {"tokens": ["bottle", "of", "wine", "with", "green", "label"], "raw": "bottle of wine with green label", "sent_id": 102105, "sent": "bottle of wine with green label"}], "file_name": "COCO_train2014_000000080590_288317.jpg", "ann_id": 288317, "sent_ids": [102104, 102105], "ref_id": 44326}, {"segmentation": [[31.29, 406.74, 34.19, 390.52, 29.59, 382.29, 30.56, 368.73, 33.95, 365.59, 34.43, 356.15, 35.4, 315.96, 34.43, 308.94, 33.47, 304.1, 29.83, 279.65, 30.8, 276.5, 32.74, 270.94, 34.19, 264.4, 35.64, 258.35, 39.03, 241.65, 36.37, 219.62, 35.64, 208.48, 34.84, 160.28, 39.82, 133.4, 70.68, 93.58, 127.42, 66.7, 147.33, 51.77, 170.23, 42.81, 223.99, 88.6, 273.76, 109.51, 277.75, 92.58, 277.75, 89.6, 302.63, 91.59, 311.59, 91.59, 325.53, 97.56, 336.48, 107.51, 338.47, 119.46, 329.51, 126.43, 318.56, 131.41, 271.77, 149.33, 241.91, 150.32, 242.9, 319.56, 252.86, 371.32, 247.88, 377.3, 231.95, 380.28, 230.96, 380.28, 225.98, 380.28, 228.97, 357.39, 227.97, 352.41, 227.97, 343.45, 227.97, 329.51, 225.98, 260.82, 221.0, 351.41, 214.03, 361.37, 213.04, 364.36, 215.03, 376.3, 211.05, 381.28, 199.1, 384.27, 190.14, 383.27, 181.18, 381.28, 179.19, 377.3, 196.11, 350.42, 209.06, 241.91, 201.09, 183.17, 202.09, 163.26, 194.12, 205.07, 172.22, 245.89, 164.26, 308.61, 162.27, 327.52, 167.24, 367.34, 169.24, 384.27, 171.23, 394.22, 153.31, 400.19, 148.33, 400.19, 145.34, 385.26, 145.34, 379.29, 141.36, 369.33, 142.36, 363.36, 143.35, 353.4, 144.35, 350.42, 144.35, 313.58, 140.37, 292.68, 133.4, 279.74, 133.4, 257.84, 133.4, 238.92, 131.41, 205.07, 126.43, 199.1, 114.48, 202.09, 84.62, 247.88, 53.76, 326.53, 47.78, 389.24, 60.73, 412.14]], "area": 50102.018249999994, "iscrowd": 0, "image_id": 3178, "bbox": [29.59, 42.81, 308.88, 369.33], "category_id": 25, "id": 594525, "split": "val", "sentences": [{"tokens": ["a", "baby", "giraffe", "nurses", "from", "its", "mother"], "raw": "A baby giraffe nurses from its mother.", "sent_id": 102106, "sent": "a baby giraffe nurses from its mother"}], "file_name": "COCO_train2014_000000003178_594525.jpg", "ann_id": 594525, "sent_ids": [102106], "ref_id": 44327}, {"segmentation": [[102.66, 142.37, 106.3, 172.92, 102.66, 192.55, 99.75, 202.37, 92.48, 211.46, 89.94, 217.64, 90.66, 254.0, 93.21, 281.63, 92.48, 287.81, 83.39, 323.08, 79.39, 343.44, 82.3, 361.26, 76.12, 420.16, 69.21, 427.8, 66.67, 433.25, 39.4, 437.98, 33.58, 432.89, 19.04, 436.16, 5.22, 434.71, 5.22, 412.89, 0.0, 388.89, 1.22, 93.28, 12.13, 85.28, 12.85, 81.65, 10.67, 76.92, 9.58, 75.1, 3.4, 68.19, 1.22, 62.74, 0.0, 57.28, 3.04, 34.74, 6.31, 26.38, 15.76, 22.74, 24.13, 21.29, 33.58, 23.11, 43.76, 30.38, 47.76, 36.56, 53.58, 42.38, 56.12, 47.1, 59.4, 44.92, 59.4, 50.38, 57.94, 55.1, 54.67, 59.47, 51.76, 64.92, 49.21, 69.65, 47.4, 71.1, 43.76, 72.56, 42.67, 71.46, 43.76, 81.28, 44.12, 87.83, 45.58, 92.19, 59.4, 94.73, 68.48, 99.83, 85.21, 103.46, 85.21, 112.55, 88.85, 118.0]], "area": 33000.09885000002, "iscrowd": 0, "image_id": 222977, "bbox": [0.0, 21.29, 106.3, 416.69], "category_id": 1, "id": 1205053, "split": "val", "sentences": [{"tokens": ["an", "old", "man", "wearing", "a", "tie", "and", "spectacles"], "raw": "An old man wearing a tie and spectacles", "sent_id": 102111, "sent": "an old man wearing a tie and spectacles"}, {"tokens": ["a", "man", "wearing", "a", "tie", "and", "glasses"], "raw": "A man wearing a tie and glasses.", "sent_id": 102112, "sent": "a man wearing a tie and glasses"}], "file_name": "COCO_train2014_000000222977_1205053.jpg", "ann_id": 1205053, "sent_ids": [102111, 102112], "ref_id": 44330}, {"segmentation": [[254.11, 230.82, 633.94, 249.41, 639.25, 377.79, 463.06, 377.79, 246.14, 317.59, 254.11, 231.7]], "area": 46926.717800000006, "iscrowd": 0, "image_id": 252277, "bbox": [246.14, 230.82, 393.11, 146.97], "category_id": 84, "id": 1138586, "split": "val", "sentences": [{"tokens": ["1", ",", "000", "places", "to", "see", "before", "you", "die"], "raw": "1,000 Places to See Before You Die", "sent_id": 102298, "sent": "1 , 000 places to see before you die"}, {"tokens": ["a", "book", "of", "1000", "places", "to", "see", "before", "you", "die", "on", "the", "laptop"], "raw": "A book of 1000 Places To See Before You Die on the laptop.", "sent_id": 102299, "sent": "a book of 1000 places to see before you die on the laptop"}], "file_name": "COCO_train2014_000000252277_1138586.jpg", "ann_id": 1138586, "sent_ids": [102298, 102299], "ref_id": 44411}, {"segmentation": [[1.08, 306.37, 2.15, 228.88, 35.52, 194.44, 66.73, 178.3, 80.72, 175.07, 88.25, 133.09, 96.86, 127.71, 94.71, 48.07, 136.68, 8.25, 178.65, 109.42, 186.19, 198.74, 186.19, 225.65, 209.87, 233.18, 232.47, 228.88, 237.85, 267.62, 198.03, 250.4, 191.57, 252.56, 173.27, 228.88, 94.71, 285.92, 37.67, 295.61, 23.68, 298.83]], "area": 29612.72215, "iscrowd": 0, "image_id": 135539, "bbox": [1.08, 8.25, 236.77, 298.12], "category_id": 1, "id": 476249, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "a", "mans", "head"], "raw": "the back of a mans head", "sent_id": 102320, "sent": "the back of a mans head"}, {"tokens": ["a", "person", "with", "a", "brown", "jacket", "on"], "raw": "A person with a brown jacket on.", "sent_id": 102321, "sent": "a person with a brown jacket on"}], "file_name": "COCO_train2014_000000135539_476249.jpg", "ann_id": 476249, "sent_ids": [102320, 102321], "ref_id": 44419}, {"segmentation": [[35.0, 1.67, 58.33, 40.0, 81.67, 50.0, 93.33, 80.0, 110.0, 95.0, 113.33, 148.33, 66.67, 193.33, 60.0, 290.0, 1.67, 360.0, 1.67, 311.67, 1.67, 3.33]], "area": 24298.70835, "iscrowd": 0, "image_id": 20188, "bbox": [1.67, 1.67, 111.66, 358.33], "category_id": 1, "id": 2161230, "split": "val", "sentences": [{"tokens": ["a", "man", "is", "standing"], "raw": "A MAN IS STANDING", "sent_id": 102409, "sent": "a man is standing"}, {"tokens": ["a", "man", "is", "standing", "wearing", "a", "blue", "jeans"], "raw": "A MAN IS STANDING WEARING A BLUE JEANS", "sent_id": 102410, "sent": "a man is standing wearing a blue jeans"}], "file_name": "COCO_train2014_000000020188_2161230.jpg", "ann_id": 2161230, "sent_ids": [102409, 102410], "ref_id": 44456}, {"segmentation": [[350.45, 250.35, 318.28, 140.31, 324.21, 113.22, 414.79, 89.52, 443.57, 104.75, 479.12, 221.57, 462.19, 242.73, 379.23, 264.74, 350.45, 254.59]], "area": 20207.385550000006, "iscrowd": 0, "image_id": 520100, "bbox": [318.28, 89.52, 160.84, 175.22], "category_id": 51, "id": 1041210, "split": "val", "sentences": [{"tokens": ["a", "clear", "glass", "bowl", "with", "slices", "of", "cucumber"], "raw": "A clear glass bowl with slices of cucumber.", "sent_id": 102484, "sent": "a clear glass bowl with slices of cucumber"}, {"tokens": ["the", "smallest", "bowl"], "raw": "the smallest bowl", "sent_id": 102485, "sent": "the smallest bowl"}], "file_name": "COCO_train2014_000000520100_1041210.jpg", "ann_id": 1041210, "sent_ids": [102484, 102485], "ref_id": 44481}, {"segmentation": [[265.35, 369.98, 261.03, 343.01, 259.96, 323.6, 254.56, 314.97, 244.85, 303.1, 234.07, 293.39, 230.83, 288.0, 230.83, 279.37, 227.6, 267.51, 218.97, 250.25, 204.94, 236.22, 177.98, 223.28, 183.37, 208.18, 179.06, 196.31, 166.11, 188.76, 148.85, 190.92, 139.15, 203.87, 134.83, 221.12, 139.15, 226.52, 131.6, 234.07, 119.73, 244.85, 118.65, 255.64, 118.65, 266.43, 118.65, 284.76, 122.97, 306.34, 132.67, 312.81, 126.2, 322.52, 127.28, 341.93, 148.85, 353.8, 173.66, 365.66, 186.61, 374.29, 192.0, 380.76, 218.97, 379.69, 238.38, 373.21]], "area": 17722.492599999998, "iscrowd": 0, "image_id": 443410, "bbox": [118.65, 188.76, 146.7, 192.0], "category_id": 1, "id": 1213241, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "blue", "shirt"], "raw": "A woman in a blue shirt.", "sent_id": 102582, "sent": "a woman in a blue shirt"}, {"tokens": ["woman", "in", "blue", "shirt", "sitting", "on", "couch"], "raw": "Woman in blue shirt sitting on couch.", "sent_id": 102583, "sent": "woman in blue shirt sitting on couch"}], "file_name": "COCO_train2014_000000443410_1213241.jpg", "ann_id": 1213241, "sent_ids": [102582, 102583], "ref_id": 44518}, {"segmentation": [[387.3, 236.7, 383.78, 225.1, 384.84, 215.25, 390.11, 208.57, 392.92, 205.76, 393.27, 193.45, 397.14, 182.56, 408.74, 168.49, 436.16, 160.41, 477.65, 162.52, 491.36, 161.11, 498.04, 156.89, 511.75, 155.84, 534.95, 155.49, 535.3, 163.22, 535.66, 165.68, 566.59, 166.38, 585.58, 169.2, 601.4, 178.69, 610.19, 193.81, 612.65, 216.31, 618.98, 246.89, 611.24, 248.65, 575.38, 249.35, 550.77, 250.76, 543.04, 253.92, 531.79, 257.44, 525.11, 254.63, 520.19, 247.95, 510.34, 247.95, 504.72, 251.81, 496.98, 252.17, 493.12, 244.43, 450.23, 243.73, 433.0, 242.67, 415.77, 240.56, 400.66, 240.56, 391.16, 239.86]], "area": 18195.142050000002, "iscrowd": 0, "image_id": 466523, "bbox": [383.78, 155.49, 235.2, 101.95], "category_id": 8, "id": 1799738, "split": "val", "sentences": [{"tokens": ["silver", "camper", "towed", "by", "red", "car"], "raw": "silver camper towed by red car", "sent_id": 102711, "sent": "silver camper towed by red car"}, {"tokens": ["a", "silver", "van", "in", "the", "road"], "raw": "a silver van in the road", "sent_id": 102712, "sent": "a silver van in the road"}], "file_name": "COCO_train2014_000000466523_1799738.jpg", "ann_id": 1799738, "sent_ids": [102711, 102712], "ref_id": 44574}, {"segmentation": [[48.2, 222.05, 46.48, 207.42, 47.34, 197.96, 54.22, 191.93, 61.97, 191.93, 62.83, 186.77, 58.53, 173.86, 54.22, 160.95, 58.53, 143.73, 70.58, 130.82, 81.76, 118.77, 73.16, 99.84, 74.02, 92.09, 90.37, 72.3, 102.42, 69.71, 118.77, 68.85, 135.99, 74.02, 154.06, 71.44, 171.27, 61.97, 185.91, 62.83, 191.07, 64.55, 199.68, 69.71, 211.73, 71.44, 218.61, 76.6, 218.61, 86.93, 234.1, 87.79, 241.85, 82.62, 261.64, 88.65, 262.51, 101.56, 270.25, 105.86, 273.69, 111.03, 270.25, 132.54, 263.37, 140.29, 265.95, 147.18, 277.14, 157.5, 275.42, 167.83, 271.97, 177.3, 278.86, 185.91, 282.3, 191.07, 275.42, 196.23, 266.81, 201.4, 259.06, 208.28, 244.43, 200.54, 210.87, 202.26, 207.42, 225.5, 205.7, 233.24, 197.09, 237.55, 189.35, 247.01, 179.88, 250.46, 167.83, 253.04, 150.62, 254.76, 145.45, 252.18, 142.01, 247.87, 129.96, 240.99, 121.36, 241.85, 122.22, 253.04, 113.61, 261.64, 95.53, 264.23, 78.32, 259.92, 56.8, 241.85, 50.78, 229.8]], "area": 33973.19435, "iscrowd": 0, "image_id": 265235, "bbox": [46.48, 61.97, 235.82, 202.26], "category_id": 61, "id": 1086451, "split": "val", "sentences": [{"tokens": ["the", "cupcakes", "with", "a", "baseball", "desing", "over", "them"], "raw": "The cupcakes with a baseball desing over them", "sent_id": 102770, "sent": "the cupcakes with a baseball desing over them"}, {"tokens": ["cupcakes", "in", "the", "shape", "of", "a", "baseball"], "raw": "Cupcakes in  the shape of a baseball.", "sent_id": 102771, "sent": "cupcakes in the shape of a baseball"}], "file_name": "COCO_train2014_000000265235_1086451.jpg", "ann_id": 1086451, "sent_ids": [102770, 102771], "ref_id": 44594}, {"segmentation": [[442.39, 165.63, 465.43, 145.48, 477.9, 128.21, 506.69, 120.53, 547.96, 120.53, 573.87, 132.05, 596.9, 159.88, 609.37, 201.14, 617.05, 209.78, 616.09, 232.81, 616.09, 250.08, 602.65, 278.87, 599.78, 312.46, 611.29, 331.65, 559.47, 331.65, 492.3, 327.81, 483.66, 329.73, 475.02, 327.81, 469.26, 303.82, 463.51, 282.71, 476.94, 277.91, 476.94, 250.08, 472.14, 235.69, 451.03, 235.69, 439.52, 231.85, 436.64, 214.58, 439.52, 189.63, 436.64, 170.43]], "area": 29801.807450000004, "iscrowd": 0, "image_id": 331419, "bbox": [436.64, 120.53, 180.41, 211.12], "category_id": 18, "id": 17989, "split": "val", "sentences": [{"tokens": ["a", "dark", "brown", "dog", "beside", "two", "other", "dogs"], "raw": "A  dark brown dog beside two other dogs", "sent_id": 102772, "sent": "a dark brown dog beside two other dogs"}, {"tokens": ["the", "dog", "on", "the", "far", "right"], "raw": "The dog on the far right.", "sent_id": 102773, "sent": "the dog on the far right"}], "file_name": "COCO_train2014_000000331419_17989.jpg", "ann_id": 17989, "sent_ids": [102772, 102773], "ref_id": 44595}, {"segmentation": [[343.11, 270.16, 358.94, 251.8, 361.47, 241.04, 377.3, 229.01, 398.82, 217.61, 422.25, 196.72, 444.4, 179.63, 462.76, 160.01, 465.93, 158.11, 460.23, 148.61, 467.19, 146.08, 470.99, 145.45, 480.49, 151.14, 484.29, 147.98, 480.49, 142.91, 486.82, 139.11, 493.78, 146.08, 499.48, 150.51, 503.91, 161.91, 517.21, 172.03, 521.01, 183.43, 514.04, 183.43, 503.91, 180.9, 498.85, 179.63, 487.45, 175.2, 483.65, 172.67, 469.73, 180.26, 441.24, 224.58, 417.18, 249.9, 410.85, 265.73, 417.18, 277.76, 406.42, 294.85, 405.15, 305.61, 426.68, 331.57, 436.17, 341.06, 436.81, 350.56, 415.92, 373.35, 403.89, 391.71, 408.32, 407.54, 421.61, 416.4, 425.41, 422.73, 407.69, 421.46, 402.62, 414.5, 400.09, 409.43, 398.82, 397.41, 389.96, 405.64, 386.16, 405.64, 388.69, 388.54, 393.13, 389.18, 412.75, 365.75, 424.78, 346.76, 422.88, 339.16, 406.42, 326.5, 399.46, 322.7, 399.46, 350.56, 400.72, 368.92, 400.72, 378.41, 395.03, 385.38, 387.43, 352.46, 386.16, 329.03, 388.69, 313.21, 381.1, 316.37, 367.8, 322.07, 360.21, 324.6, 361.47, 306.24, 351.34, 298.65, 336.78, 285.35, 334.88, 280.29, 336.78, 273.32, 338.05, 269.53], [322.22, 293.58, 341.85, 316.37, 348.81, 323.34, 350.08, 331.57, 332.35, 346.13, 323.49, 360.69, 324.75, 387.28, 326.02, 408.8, 332.98, 417.66, 334.25, 423.36, 319.69, 422.1, 318.42, 410.07, 315.89, 371.45, 313.36, 366.39, 305.13, 395.51, 299.43, 403.74, 293.73, 393.61, 304.5, 366.39, 312.09, 349.29, 320.32, 336.0, 320.32, 322.7, 315.26, 300.55]], "area": 13668.297100000003, "iscrowd": 0, "image_id": 395432, "bbox": [293.73, 139.11, 227.28, 284.25], "category_id": 25, "id": 600294, "split": "val", "sentences": [{"tokens": ["small", "giraffe", "on", "the", "right"], "raw": "small giraffe on the right", "sent_id": 102780, "sent": "small giraffe on the right"}, {"tokens": ["there", "is", "a", "shorter", "giraffe", "shown", "in", "the", "picture"], "raw": "There is a shorter giraffe shown in the picture.", "sent_id": 102781, "sent": "there is a shorter giraffe shown in the picture"}], "file_name": "COCO_train2014_000000395432_600294.jpg", "ann_id": 600294, "sent_ids": [102780, 102781], "ref_id": 44597}, {"segmentation": [[93.99, 329.01, 92.1, 278.72, 82.61, 265.44, 69.32, 260.7, 83.56, 251.21, 88.3, 241.72, 94.94, 235.08, 93.05, 229.38, 92.1, 218.95, 112.97, 183.84, 62.68, 144.94, 44.65, 140.19, 7.65, 140.19, 0.06, 145.88, 1.95, 212.3, 2.9, 222.74, 2.9, 298.65, 3.85, 353.68, 1.01, 374.56, 1.95, 376.46, 53.19, 347.04, 90.2, 329.01]], "area": 18651.614049999996, "iscrowd": 0, "image_id": 131030, "bbox": [0.06, 140.19, 112.91, 236.27], "category_id": 1, "id": 493291, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "with", "curly", "hair", "looking", "over", "his", "shoulder"], "raw": "A young boy with curly hair looking over his shoulder.", "sent_id": 102869, "sent": "a young boy with curly hair looking over his shoulder"}, {"tokens": ["a", "little", "boy", "in", "green", "stands", "near", "a", "man"], "raw": "A little boy in green stands near a man.", "sent_id": 102870, "sent": "a little boy in green stands near a man"}], "file_name": "COCO_train2014_000000131030_493291.jpg", "ann_id": 493291, "sent_ids": [102869, 102870], "ref_id": 44635}, {"segmentation": [[640.0, 216.93, 518.38, 192.35, 509.44, 225.86, 489.33, 243.74, 636.8, 277.25], [6.7, 304.07, 35.75, 290.66, 40.22, 239.27, 40.22, 232.57, 2.23, 250.44]], "area": 9613.74385, "iscrowd": 0, "image_id": 569214, "bbox": [2.23, 192.35, 637.77, 111.72], "category_id": 67, "id": 1960472, "split": "val", "sentences": [{"tokens": ["the", "edges", "of", "a", "table"], "raw": "The edges of a table.", "sent_id": 102955, "sent": "the edges of a table"}], "file_name": "COCO_train2014_000000569214_1960472.jpg", "ann_id": 1960472, "sent_ids": [102955], "ref_id": 44667}, {"segmentation": [[60.67, 171.07, 74.16, 169.38, 83.43, 168.54, 91.01, 170.22, 101.97, 163.48, 112.92, 155.9, 117.98, 152.53, 121.35, 150.0, 129.78, 148.31, 130.62, 154.21, 140.73, 154.21, 148.31, 155.06, 150.84, 155.9, 160.11, 160.96, 174.44, 161.8, 178.65, 161.8, 193.82, 160.11, 202.25, 158.43, 209.83, 156.74, 224.16, 157.58, 238.48, 160.11, 242.7, 161.8, 248.6, 171.91, 248.6, 182.02, 246.91, 194.66, 248.6, 200.56, 251.12, 207.3, 252.81, 215.73, 255.34, 222.47, 256.18, 228.37, 256.18, 233.43, 260.39, 242.7, 262.08, 246.91, 265.45, 253.65, 263.76, 267.13, 262.92, 276.4, 268.82, 294.94, 247.75, 289.04, 233.43, 287.36, 235.96, 294.1, 239.33, 305.06, 240.17, 312.64, 241.85, 323.6, 246.07, 339.61, 245.22, 342.13, 211.52, 336.24, 202.25, 332.87, 183.71, 326.12, 159.27, 315.17, 150.84, 310.96, 141.57, 301.69, 129.78, 289.89, 114.61, 281.46, 106.18, 273.88, 97.75, 267.98, 83.43, 251.12, 80.06, 244.38, 75.0, 235.96, 67.42, 229.21, 63.2, 216.57, 56.46, 201.4, 53.93, 192.13, 53.93, 182.02, 53.93, 176.97]], "area": 27174.6357, "iscrowd": 0, "image_id": 335376, "bbox": [53.93, 148.31, 214.89, 193.82], "category_id": 59, "id": 1073722, "split": "val", "sentences": [{"tokens": ["the", "two", "slices", "of", "pizza", "that", "are", "more", "towards", "the", "left", "side", "of", "the", "photo", ",", "they", "are", "also", "closer", "to", "the", "camera", "than", "the", "other", "two", "slices"], "raw": "The two slices of pizza that are more towards the left side of the photo, they are also closer to the camera than the other two slices.", "sent_id": 102966, "sent": "the two slices of pizza that are more towards the left side of the photo , they are also closer to the camera than the other two slices"}, {"tokens": ["two", "closest", "pizza", "slices"], "raw": "two closest pizza slices", "sent_id": 102967, "sent": "two closest pizza slices"}], "file_name": "COCO_train2014_000000335376_1073722.jpg", "ann_id": 1073722, "sent_ids": [102966, 102967], "ref_id": 44672}, {"segmentation": [[372.31, 250.15, 427.96, 267.42, 491.29, 252.07, 572.85, 227.12, 580.53, 213.69, 554.62, 184.9, 499.93, 160.91, 435.64, 144.6, 404.93, 146.52, 361.75, 146.52, 320.49, 154.19, 302.26, 183.94, 321.45, 218.48, 361.75, 252.07]], "area": 23556.528399999996, "iscrowd": 0, "image_id": 135694, "bbox": [302.26, 144.6, 278.27, 122.82], "category_id": 59, "id": 1073904, "split": "val", "sentences": [{"tokens": ["a", "pizza", "closest", "to", "the", "hanging", "utencils"], "raw": "a pizza closest to the hanging utencils.", "sent_id": 103034, "sent": "a pizza closest to the hanging utencils"}, {"tokens": ["the", "pizza", "in", "the", "right"], "raw": "the pizza in the right", "sent_id": 103035, "sent": "the pizza in the right"}], "file_name": "COCO_train2014_000000135694_1073904.jpg", "ann_id": 1073904, "sent_ids": [103034, 103035], "ref_id": 44698}, {"segmentation": [[548.47, 209.04, 524.99, 266.6, 534.08, 271.9, 534.84, 314.31, 527.26, 325.67, 510.6, 332.49, 488.63, 339.31, 471.21, 343.85, 459.1, 345.37, 448.49, 354.45, 445.46, 361.27, 441.68, 368.09, 441.68, 389.29, 460.61, 396.87, 479.55, 399.14, 515.14, 404.44, 518.17, 405.96, 530.29, 405.96, 543.17, 405.96, 554.53, 405.96, 575.73, 404.44, 587.09, 403.68, 599.97, 401.41, 607.54, 401.41, 609.06, 398.38, 612.09, 395.35, 619.66, 390.05, 621.93, 387.02, 625.72, 383.24, 630.27, 375.66, 618.15, 354.45, 624.21, 346.88, 627.24, 344.61, 614.36, 309.77, 609.06, 299.17, 611.33, 287.05, 609.82, 232.52, 593.15, 203.74, 590.88, 195.4, 584.82, 190.86, 579.52, 186.32, 584.82, 172.68, 581.79, 159.05, 587.85, 155.26, 588.61, 149.96, 587.09, 143.14, 575.73, 140.87, 571.99, 120.06, 509.13, 124.61, 506.85, 148.84, 497.77, 153.39, 500.8, 160.96, 505.34, 160.96, 510.64, 160.96, 517.46, 182.17, 523.52, 196.56, 526.55, 198.83, 533.36, 204.13, 535.64, 204.89, 537.91, 204.89, 540.18, 207.16]], "area": 27248.644500000002, "iscrowd": 0, "image_id": 74945, "bbox": [441.68, 120.06, 188.59, 285.9], "category_id": 1, "id": 503407, "split": "val", "sentences": [{"tokens": ["a", "kneeling", "person", "in", "a", "black", "top", "hat"], "raw": "A kneeling person in a black top hat.", "sent_id": 103057, "sent": "a kneeling person in a black top hat"}, {"tokens": ["the", "woman", "in", "black", "sitting", "down"], "raw": "The woman in black sitting down.", "sent_id": 103058, "sent": "the woman in black sitting down"}], "file_name": "COCO_train2014_000000074945_503407.jpg", "ann_id": 503407, "sent_ids": [103057, 103058], "ref_id": 44708}, {"segmentation": [[238.31, 127.06, 245.5, 125.75, 252.69, 129.67, 254.0, 135.55, 259.23, 140.13, 259.23, 147.32, 257.27, 152.55, 255.31, 156.47, 254.0, 159.09, 265.76, 170.85, 266.42, 177.39, 265.76, 183.27, 260.54, 188.5, 259.88, 195.04, 258.57, 211.38, 257.92, 221.84, 254.65, 235.56, 253.35, 247.98, 250.08, 261.71, 249.42, 272.82, 248.77, 281.97, 250.08, 295.7, 254.0, 307.47, 257.92, 314.66, 255.96, 323.81, 250.08, 323.81, 240.27, 325.77, 237.66, 332.31, 236.35, 336.23, 229.16, 339.5, 225.89, 340.15, 221.97, 343.42, 220.66, 350.61, 214.13, 351.26, 206.94, 351.26, 204.32, 350.61, 204.32, 344.73, 209.55, 337.54, 213.47, 327.73, 215.43, 318.58, 218.05, 309.43, 213.47, 229.68, 214.78, 218.57, 217.39, 209.42, 218.05, 202.88, 219.35, 200.27, 208.9, 206.8, 204.32, 209.42, 201.05, 210.07, 197.13, 209.42, 189.29, 207.46, 188.63, 206.8, 183.4, 201.57, 183.4, 196.34, 194.52, 195.04, 202.36, 195.04, 208.9, 191.77, 213.47, 183.27, 213.47, 173.47, 216.09, 167.58, 225.24, 162.35, 235.04, 158.43, 235.04, 155.16, 233.74, 153.2, 233.08, 148.63, 233.08, 144.05, 233.08, 139.48, 232.43, 133.59]], "area": 8340.451200000001, "iscrowd": 0, "image_id": 311706, "bbox": [183.4, 125.75, 83.02, 225.51], "category_id": 1, "id": 196401, "split": "val", "sentences": [{"tokens": ["a", "man", "walking", "with", "long", "hair"], "raw": "a man walking with long hair", "sent_id": 103263, "sent": "a man walking with long hair"}, {"tokens": ["a", "man", "with", "longer", "hair", "past", "his", "ears", ",", "standing", "to", "the", "right", "of", "another", "man"], "raw": "A man with longer hair past his ears, standing to the right of another man", "sent_id": 103264, "sent": "a man with longer hair past his ears , standing to the right of another man"}], "file_name": "COCO_train2014_000000311706_196401.jpg", "ann_id": 196401, "sent_ids": [103263, 103264], "ref_id": 44783}, {"segmentation": [[151.32, 201.99, 132.55, 226.82, 134.36, 284.34, 119.23, 409.07, 127.7, 438.13, 139.81, 534.4, 131.33, 557.41, 87.74, 601.61, 93.19, 615.53, 164.64, 617.35, 248.8, 616.14, 245.16, 535.61, 243.95, 478.09, 233.66, 424.2, 254.85, 392.11, 257.27, 300.69, 243.95, 252.85, 191.28, 222.58, 171.9, 204.42, 152.53, 178.99, 155.55, 166.27, 146.47, 152.35], [153.13, 121.47, 169.48, 106.93, 205.2, 129.34, 203.99, 149.92, 202.18, 148.11, 173.72, 143.26, 164.03, 142.66]], "area": 49379.761999999995, "iscrowd": 0, "image_id": 451842, "bbox": [87.74, 106.93, 169.53, 510.42], "category_id": 1, "id": 522834, "split": "val", "sentences": [{"tokens": ["a", "person", "on", "a", "tennis", "court", "near", "green", "wall"], "raw": "A person on a tennis court near green wall.", "sent_id": 103284, "sent": "a person on a tennis court near green wall"}, {"tokens": ["a", "tennis", "official", "holding", "a", "tennis", "ball"], "raw": "A tennis official holding a tennis ball", "sent_id": 103285, "sent": "a tennis official holding a tennis ball"}], "file_name": "COCO_train2014_000000451842_522834.jpg", "ann_id": 522834, "sent_ids": [103284, 103285], "ref_id": 44788}, {"segmentation": [[49.09, 152.55, 49.95, 173.22, 55.11, 186.14, 59.42, 199.05, 58.56, 207.66, 59.42, 211.97, 69.75, 207.66, 72.34, 202.5, 73.2, 199.91, 77.51, 211.11, 78.37, 222.3, 81.81, 229.19, 83.53, 236.94, 83.53, 253.31, 83.53, 267.95, 82.67, 276.56, 79.23, 290.34, 79.23, 297.23, 77.51, 307.56, 89.56, 313.59, 93.87, 313.59, 100.76, 317.89, 107.65, 319.62, 113.67, 320.48, 466.75, 329.09, 465.03, 317.89, 462.45, 285.17, 459.0, 280.0, 459.86, 273.11, 466.75, 280.0, 474.5, 275.7, 477.09, 264.5, 477.95, 253.31, 477.95, 243.83, 463.31, 235.22, 438.33, 236.94, 417.67, 242.11, 395.28, 246.42, 376.33, 249.0, 359.11, 250.72, 350.49, 249.0, 339.3, 245.56, 321.22, 240.39, 300.55, 236.94, 273.85, 235.22, 256.63, 234.36, 251.46, 231.78, 249.74, 227.47, 251.46, 224.89, 265.24, 210.25, 265.24, 208.53, 269.55, 201.64, 272.99, 187.86, 270.41, 163.74, 264.38, 157.72, 255.77, 154.27, 227.35, 143.08, 217.88, 143.08, 204.96, 143.94, 194.62, 143.08, 175.68, 137.91, 157.59, 134.47, 148.98, 133.6, 124.01, 132.74, 92.14, 128.44, 80.95, 129.3, 53.39, 138.77, 46.5, 143.94, 43.06, 156.86, 41.34, 163.74, 45.64, 162.88, 45.64, 162.88]], "area": 53094.20264999996, "iscrowd": 0, "image_id": 331419, "bbox": [41.34, 128.44, 436.61, 200.65], "category_id": 18, "id": 11817, "split": "val", "sentences": [{"tokens": ["a", "dog", "with", "a", "black", "band", "around", "it", "'", "s", "snout"], "raw": "A dog with a black band around it's snout.", "sent_id": 103290, "sent": "a dog with a black band around it ' s snout"}, {"tokens": ["a", "dog", "wearing", "a", "muzzle"], "raw": "A dog wearing a muzzle.", "sent_id": 103291, "sent": "a dog wearing a muzzle"}], "file_name": "COCO_train2014_000000331419_11817.jpg", "ann_id": 11817, "sent_ids": [103290, 103291], "ref_id": 44790}, {"segmentation": [[382.11, 287.05, 480.0, 289.34, 480.0, 444.83, 329.52, 404.81, 263.21, 381.95, 256.35, 384.23, 250.63, 353.36, 291.79, 353.36, 343.24, 361.37, 364.96, 357.94, 352.39, 353.36, 363.82, 331.64, 348.96, 313.35, 367.25, 290.48]], "area": 21330.55215, "iscrowd": 0, "image_id": 171808, "bbox": [250.63, 287.05, 229.37, 157.78], "category_id": 63, "id": 1949707, "split": "val", "sentences": [{"tokens": ["the", "long", "brown", "ottoman"], "raw": "The long brown ottoman", "sent_id": 103303, "sent": "the long brown ottoman"}, {"tokens": ["a", "dark", "brown", "couch", "in", "front", "of", "a", "fireplace"], "raw": "A dark brown couch in front of a fireplace.", "sent_id": 103304, "sent": "a dark brown couch in front of a fireplace"}], "file_name": "COCO_train2014_000000171808_1949707.jpg", "ann_id": 1949707, "sent_ids": [103303, 103304], "ref_id": 44794}, {"segmentation": [[218.74, 221.56, 303.42, 135.48, 303.42, 103.02, 309.06, 86.09, 331.64, 86.09, 347.16, 94.55, 345.75, 138.3, 369.74, 146.77, 381.03, 180.64, 388.09, 213.1, 393.73, 245.56, 395.15, 256.84, 378.21, 273.78, 359.87, 259.67, 348.58, 214.51, 331.64, 187.69, 299.18, 176.4, 278.01, 187.69, 259.67, 211.69, 259.67, 225.8, 296.36, 266.72, 314.71, 289.3, 320.35, 314.71, 326.0, 351.4, 314.71, 365.51, 317.53, 399.38, 300.59, 416.31, 280.84, 412.08, 293.54, 395.15, 299.18, 365.51, 282.25, 328.82, 280.84, 307.65, 262.49, 282.25, 245.56, 245.56, 218.74, 263.9, 193.34, 252.61, 191.93, 228.62, 198.98, 215.92, 221.56, 224.39, 227.21, 215.92]], "area": 18828.215699999997, "iscrowd": 0, "image_id": 100034, "bbox": [191.93, 86.09, 203.22, 330.22], "category_id": 1, "id": 488870, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "the", "white", "shirt", "in", "the", "back", "holding", "a", "tennis", "racket"], "raw": "The man with the white shirt in the back holding a tennis racket", "sent_id": 103309, "sent": "the man with the white shirt in the back holding a tennis racket"}, {"tokens": ["the", "boy", "in", "the", "back", "wearing", "a", "white", "shirt"], "raw": "the boy in the back wearing a white shirt", "sent_id": 103310, "sent": "the boy in the back wearing a white shirt"}], "file_name": "COCO_train2014_000000100034_488870.jpg", "ann_id": 488870, "sent_ids": [103309, 103310], "ref_id": 44797}, {"segmentation": [[444.4, 193.08, 441.17, 166.11, 444.4, 121.89, 454.11, 77.66, 464.9, 65.8, 497.26, 64.72, 541.48, 78.74, 546.88, 102.47, 528.54, 160.72, 502.65, 211.42, 495.1, 211.42, 468.13, 198.47]], "area": 11599.341699999997, "iscrowd": 0, "image_id": 447574, "bbox": [441.17, 64.72, 105.71, 146.7], "category_id": 47, "id": 674038, "split": "val", "sentences": [{"tokens": ["glass", "of", "water", "on", "a", "table"], "raw": "Glass of water on a table", "sent_id": 103337, "sent": "glass of water on a table"}, {"tokens": ["clear", "glass", "full", "of", "water"], "raw": "Clear glass full of water.", "sent_id": 103338, "sent": "clear glass full of water"}], "file_name": "COCO_train2014_000000447574_674038.jpg", "ann_id": 674038, "sent_ids": [103337, 103338], "ref_id": 44807}, {"segmentation": [[422.98, 517.82, 398.97, 528.11, 380.68, 522.4, 370.39, 502.96, 372.67, 465.23, 378.39, 451.51, 360.1, 445.79, 362.38, 430.93, 377.25, 419.5, 398.97, 388.63, 413.83, 371.48, 418.4, 344.04, 426.41, 334.89, 413.83, 326.89, 409.26, 316.6, 469.85, 269.72, 518.26, 292.77, 479.95, 316.82, 449.66, 360.47, 429.17, 425.47, 422.05, 473.57]], "area": 12799.712350000005, "iscrowd": 0, "image_id": 490887, "bbox": [360.1, 269.72, 158.16, 258.39], "category_id": 2, "id": 2168493, "split": "val", "sentences": [{"tokens": ["a", "white", "bicycle", "on", "the", "left", "side", "of", "a", "pole"], "raw": "a white bicycle on the left side of a pole", "sent_id": 103341, "sent": "a white bicycle on the left side of a pole"}, {"tokens": ["the", "back", "wheel", "of", "a", "bicycle", "that", "is", "next", "to", "a", "blue", "bicycle"], "raw": "The back wheel of a bicycle that is next to a blue bicycle.", "sent_id": 103342, "sent": "the back wheel of a bicycle that is next to a blue bicycle"}], "file_name": "COCO_train2014_000000490887_2168493.jpg", "ann_id": 2168493, "sent_ids": [103341, 103342], "ref_id": 44809}, {"segmentation": [[547.9, 276.35, 540.23, 234.13, 543.11, 214.94, 541.19, 185.19, 541.19, 166.96, 545.98, 153.53, 553.66, 149.69, 554.62, 133.38, 559.42, 116.11, 575.73, 109.39, 590.12, 120.9, 593.0, 138.18, 599.72, 147.77, 604.52, 166.0, 605.48, 196.71, 604.52, 225.49, 595.88, 269.63, 595.88, 308.98, 603.56, 339.68, 593.96, 350.24, 581.49, 339.68, 570.93, 256.2, 566.13, 298.42]], "area": 10452.011949999998, "iscrowd": 0, "image_id": 502134, "bbox": [540.23, 109.39, 65.25, 240.85], "category_id": 1, "id": 235786, "split": "val", "sentences": [{"tokens": ["a", "woman", "taking", "a", "picture", "with", "a", "light", "blue", "phone"], "raw": "A woman taking a picture with a light blue phone.", "sent_id": 103368, "sent": "a woman taking a picture with a light blue phone"}, {"tokens": ["a", "woman", "wearing", "a", "santa", "hat", "holding", "up", "her", "blue", "phone"], "raw": "A woman wearing a Santa hat holding up her blue phone.", "sent_id": 103369, "sent": "a woman wearing a santa hat holding up her blue phone"}], "file_name": "COCO_train2014_000000502134_235786.jpg", "ann_id": 235786, "sent_ids": [103368, 103369], "ref_id": 44818}, {"segmentation": [[480.0, 170.74, 448.21, 165.48, 424.76, 161.04, 411.83, 169.12, 387.58, 173.16, 371.41, 166.29, 350.79, 157.4, 329.77, 149.31, 318.05, 142.44, 290.97, 146.48, 255.4, 129.1, 255.4, 115.36, 259.44, 109.3, 273.18, 104.04, 298.24, 104.85, 321.28, 108.89, 324.92, 92.72, 291.78, 63.62, 266.71, 52.3, 248.93, 50.68, 242.06, 54.73, 237.21, 56.75, 234.38, 65.24, 237.21, 73.32, 241.65, 81.0, 248.93, 94.34, 242.06, 108.89, 231.55, 100.0, 222.25, 94.34, 209.72, 54.32, 219.02, 37.75, 247.72, 7.03, 252.16, 2.99, 284.9, 17.94, 307.95, 32.9, 321.69, 38.15, 330.58, 38.96, 335.84, 45.83, 349.58, 50.28, 357.26, 59.98, 370.19, 65.64, 405.77, 85.04, 435.68, 91.51, 463.97, 93.13, 480.0, 96.36]], "area": 21714.77970000001, "iscrowd": 0, "image_id": 179618, "bbox": [209.72, 2.99, 270.28, 170.17], "category_id": 1, "id": 2166291, "split": "val", "sentences": [{"tokens": ["a", "right", "hand", "grasping", "a", "handle", "at", "the", "top", "of", "a", "blender"], "raw": "A right hand grasping a handle at the top of a blender.", "sent_id": 103375, "sent": "a right hand grasping a handle at the top of a blender"}, {"tokens": ["a", "mans", "hand", "reaching", "for", "the", "handle"], "raw": "A mans hand reaching for the handle", "sent_id": 103376, "sent": "a mans hand reaching for the handle"}], "file_name": "COCO_train2014_000000179618_2166291.jpg", "ann_id": 2166291, "sent_ids": [103375, 103376], "ref_id": 44822}, {"segmentation": [[95.69, 0.33, 95.69, 0.33, 102.95, 14.85, 103.61, 27.39, 103.61, 38.6, 100.31, 51.8, 101.63, 62.36, 108.89, 70.28, 120.76, 91.4, 127.36, 98.66, 139.9, 96.68, 148.48, 94.04, 161.68, 93.38, 170.92, 97.34, 174.88, 109.88, 185.43, 123.73, 198.63, 127.69, 209.85, 123.73, 211.83, 115.15, 199.95, 100.64, 192.69, 92.06, 194.67, 85.46, 204.57, 88.76, 218.43, 101.3, 227.67, 107.9, 236.25, 111.19, 238.89, 118.45, 245.49, 118.45, 248.79, 113.17, 252.09, 112.51, 256.7, 115.15, 267.26, 116.47, 271.88, 105.26, 276.5, 98.0, 283.1, 92.06, 287.72, 86.12, 285.08, 82.82, 281.78, 70.28, 281.78, 61.04, 283.1, 28.05, 284.42, 8.91, 378.13, 6.27, 382.75, 11.55, 382.09, 84.14, 362.29, 86.78, 372.85, 96.02, 377.47, 103.94, 378.79, 117.13, 384.07, 124.39, 390.0, 125.71, 390.0, 0.99], [360.97, 197.64, 326.66, 195.66, 304.22, 195.66, 289.04, 201.6, 267.92, 216.12, 255.39, 233.94, 238.23, 254.4, 236.25, 257.03, 240.87, 264.29, 252.75, 268.25, 261.32, 268.91, 262.64, 272.21, 250.11, 284.75, 246.81, 288.71, 246.81, 289.37, 362.95, 288.71, 362.29, 261.65, 362.29, 237.9, 362.29, 231.3, 373.51, 227.34, 382.75, 220.74, 390.0, 212.16, 390.0, 175.87, 385.39, 184.44, 378.13, 194.34, 370.87, 193.02, 365.59, 192.36]], "area": 31036.6098, "iscrowd": 0, "image_id": 79883, "bbox": [95.69, 0.33, 294.31, 289.04], "category_id": 1, "id": 442094, "split": "val", "sentences": [{"tokens": ["the", "hands", ".", "of", "a", "woman", "holding", "a", "puppy"], "raw": "The hands. Of a woman holding a puppy", "sent_id": 103438, "sent": "the hands . of a woman holding a puppy"}, {"tokens": ["hands", "placed", "on", "lap", "with", "a", "silver", "ring", "on", "the", "right", "hand"], "raw": "Hands placed on lap with a silver ring on the right hand", "sent_id": 103439, "sent": "hands placed on lap with a silver ring on the right hand"}], "file_name": "COCO_train2014_000000079883_442094.jpg", "ann_id": 442094, "sent_ids": [103438, 103439], "ref_id": 44845}, {"segmentation": [[447.11, 232.74, 566.78, 233.7, 556.25, 340.93, 437.53, 328.48]], "area": 12163.923350000001, "iscrowd": 0, "image_id": 373727, "bbox": [437.53, 232.74, 129.25, 108.19], "category_id": 79, "id": 1124524, "split": "val", "sentences": [{"tokens": ["a", "bottom", "oven"], "raw": "A bottom oven.", "sent_id": 103457, "sent": "a bottom oven"}, {"tokens": ["a", "silver", "oven", "beneath", "another", "smaller", "oven"], "raw": "A silver oven beneath another smaller oven", "sent_id": 103458, "sent": "a silver oven beneath another smaller oven"}], "file_name": "COCO_train2014_000000373727_1124524.jpg", "ann_id": 1124524, "sent_ids": [103457, 103458], "ref_id": 44851}, {"segmentation": [[176.49, 122.5, 114.72, 144.96, 36.1, 175.45, 20.06, 189.09, 18.45, 204.33, 34.5, 210.75, 69.8, 211.55, 129.16, 201.12, 179.7, 177.85, 224.63, 156.19, 258.32, 137.74, 268.75, 131.32, 242.28, 122.5, 204.57, 122.5, 193.34, 116.08]], "area": 11043.25785, "iscrowd": 0, "image_id": 88425, "bbox": [18.45, 116.08, 250.3, 95.47], "category_id": 42, "id": 651102, "split": "val", "sentences": [{"tokens": ["a", "red", "color", "surf", "board"], "raw": "a red color surf board", "sent_id": 103571, "sent": "a red color surf board"}, {"tokens": ["the", "shorter", "surf", "board", "is", "bright", "pink"], "raw": "The shorter surf board is bright pink.", "sent_id": 103572, "sent": "the shorter surf board is bright pink"}], "file_name": "COCO_train2014_000000088425_651102.jpg", "ann_id": 651102, "sent_ids": [103571, 103572], "ref_id": 44899}, {"segmentation": [[427.12, 585.04, 422.55, 492.43, 425.98, 440.98, 425.98, 440.98, 424.84, 405.54, 412.26, 390.68, 367.67, 373.53, 327.65, 342.66, 295.64, 306.07, 276.21, 259.19, 276.21, 192.7, 264.77, 167.46, 283.07, 175.46, 265.92, 160.6, 283.07, 145.74, 257.91, 142.31, 238.48, 134.3, 193.89, 114.87, 206.46, 150.31, 236.19, 177.75, 246.48, 237.2, 246.48, 238.34, 243.05, 304.65, 256.77, 358.39, 257.91, 400.69, 260.2, 414.41, 252.2, 405.45, 259.06, 424.88, 271.63, 448.89, 272.78, 474.05, 277.35, 500.34, 283.07, 549.5, 284.21, 618.28, 279.64, 640.0, 299.07, 632.0, 295.64, 546.26, 294.5, 462.61, 301.36, 522.06, 310.51, 580.37, 316.22, 632.97, 316.22, 635.25, 316.22, 635.25, 316.22, 640.0, 331.08, 636.4, 309.36, 477.48, 332.23, 483.19, 337.94, 477.48, 357.38, 477.48, 367.67, 477.48, 374.53, 476.33, 424.84, 581.52]], "area": 35801.81949999998, "iscrowd": 0, "image_id": 96586, "bbox": [193.89, 114.87, 233.23, 525.13], "category_id": 25, "id": 1823321, "split": "val", "sentences": [{"tokens": ["giraffe", "stretching", "tall", "to", "eat"], "raw": "giraffe stretching tall to eat", "sent_id": 103594, "sent": "giraffe stretching tall to eat"}, {"tokens": ["a", "giraffe", "with", "its", "head", "up"], "raw": "A giraffe with its head up.", "sent_id": 103595, "sent": "a giraffe with its head up"}], "file_name": "COCO_train2014_000000096586_1823321.jpg", "ann_id": 1823321, "sent_ids": [103594, 103595], "ref_id": 44908}, {"segmentation": [[190.15, 232.57, 189.78, 219.77, 189.78, 216.61, 191.26, 213.65, 193.3, 211.61, 196.83, 211.61, 213.71, 210.49, 229.29, 209.94, 237.82, 209.57, 248.03, 198.62, 250.44, 195.84, 250.99, 193.98, 255.08, 193.43, 284.76, 191.76, 305.9, 192.5, 326.12, 193.24, 340.59, 195.1, 345.79, 197.51, 351.16, 200.48, 351.16, 202.52, 361.37, 214.2, 363.78, 214.95, 378.8, 215.69, 379.18, 217.54, 379.73, 218.84, 380.47, 219.4, 380.47, 221.81, 379.92, 223.48, 379.55, 224.78, 378.06, 227.19, 377.13, 228.49, 378.25, 232.94, 378.99, 234.24, 378.99, 235.54, 379.73, 238.32, 380.29, 239.62, 378.43, 240.92, 372.5, 241.84, 364.15, 241.84, 356.73, 241.84, 354.87, 241.29, 353.39, 238.5, 349.31, 239.06, 349.68, 245.0, 347.08, 250.75, 342.26, 255.38, 334.66, 255.01, 328.9, 254.09, 326.68, 253.34, 322.78, 250.01, 320.37, 246.3, 318.89, 245.37, 266.39, 246.67, 244.87, 246.48, 243.2, 244.63, 239.49, 240.92, 237.27, 239.06, 234.86, 236.09, 234.48, 238.69, 234.48, 244.81, 230.4, 251.3, 225.95, 253.53, 215.75, 254.83, 208.89, 252.05, 205.55, 248.34, 202.76, 244.81, 199.24, 241.47, 197.94, 242.03, 189.96, 241.66, 184.77, 240.92, 184.03, 239.06, 183.29, 237.21, 184.03, 235.17, 185.51, 233.12]], "area": 8673.867949999996, "iscrowd": 0, "image_id": 466523, "bbox": [183.29, 191.76, 197.18, 63.62], "category_id": 3, "id": 349020, "split": "val", "sentences": [{"tokens": ["a", "red", "car", "with", "a", "white", "roof", "inbetween", "two", "other", "cars"], "raw": "A red car with a white roof inbetween two other cars.", "sent_id": 103624, "sent": "a red car with a white roof inbetween two other cars"}, {"tokens": ["a", "classic", "car", "attached", "to", "a", "silver", "trailer"], "raw": "A classic car attached to a silver trailer.", "sent_id": 103625, "sent": "a classic car attached to a silver trailer"}], "file_name": "COCO_train2014_000000466523_349020.jpg", "ann_id": 349020, "sent_ids": [103624, 103625], "ref_id": 44922}, {"segmentation": [[408.86, 13.33, 497.74, 156.39, 498.59, 368.02, 500.0, 368.86, 3.39, 370.56, 2.54, 6.56, 405.47, 4.02]], "area": 173316.3197, "iscrowd": 0, "image_id": 554706, "bbox": [2.54, 4.02, 497.46, 366.54], "category_id": 67, "id": 391456, "split": "val", "sentences": [{"tokens": ["a", "fast", "food", "meal", "on", "a", "red", "tray"], "raw": "A fast food meal on a red tray.", "sent_id": 103628, "sent": "a fast food meal on a red tray"}, {"tokens": ["a", "meal", "of", "hot", "dogs", ",", "french", "fries", ",", "sauces", "and", "a", "beverage"], "raw": "A meal of hot dogs, french fries, sauces and a beverage.", "sent_id": 103629, "sent": "a meal of hot dogs , french fries , sauces and a beverage"}], "file_name": "COCO_train2014_000000554706_391456.jpg", "ann_id": 391456, "sent_ids": [103628, 103629], "ref_id": 44924}, {"segmentation": [[208.54, 258.85, 225.59, 229.62, 220.72, 194.31, 218.28, 157.77, 224.37, 126.11, 229.24, 111.5, 232.9, 101.76, 228.02, 74.96, 242.64, 49.39, 280.39, 39.65, 304.74, 65.22, 321.79, 106.63, 333.97, 143.16, 318.14, 217.45, 304.74, 249.11, 326.67, 257.63, 326.67, 267.37, 309.62, 267.37, 301.09, 271.03, 286.48, 274.68, 281.61, 274.68, 273.08, 274.68, 271.86, 263.72, 268.21, 251.54, 263.34, 252.76, 266.99, 266.16, 268.21, 273.46, 263.34, 279.55, 251.16, 281.99, 246.29, 286.86, 241.42, 292.95, 238.98, 301.47, 236.55, 308.78, 228.02, 308.78, 223.15, 301.47, 223.15, 296.6, 224.37, 291.73, 225.59, 289.3, 228.02, 283.21, 229.24, 274.68, 217.06, 266.16, 209.76, 258.85], [203.67, 292.95, 229.24, 322.18, 192.71, 323.39, 201.23, 296.6], [196.36, 334.35, 238.98, 338.01, 210.97, 350.18, 196.36, 368.45, 198.8, 385.5, 198.8, 403.77, 200.01, 420.82, 202.45, 434.21, 198.8, 446.39, 195.14, 456.13, 181.75, 462.22, 173.22, 462.22, 168.35, 451.26, 168.35, 439.08, 168.35, 424.47, 172.01, 412.29, 175.66, 400.11, 178.09, 390.37, 180.53, 376.98, 185.4, 361.14, 195.14, 346.53]], "area": 25804.641450000003, "iscrowd": 0, "image_id": 198785, "bbox": [168.35, 39.65, 165.62, 422.57], "category_id": 1, "id": 214165, "split": "val", "sentences": [{"tokens": ["a", "pretty", "woman", "with", "silver", "hoop", "earings", "sitting", "on", "a", "motorcycle", "between", "her", "two", "friends"], "raw": "A pretty woman with silver hoop earings sitting on a motorcycle between her two friends.", "sent_id": 103718, "sent": "a pretty woman with silver hoop earings sitting on a motorcycle between her two friends"}, {"tokens": ["a", "woman", "sitting", "on", "top", "of", "a", "motorcycle"], "raw": "A woman sitting on top of a motorcycle.", "sent_id": 103719, "sent": "a woman sitting on top of a motorcycle"}], "file_name": "COCO_train2014_000000198785_214165.jpg", "ann_id": 214165, "sent_ids": [103718, 103719], "ref_id": 44962}, {"segmentation": [[31.57, 619.84, 45.92, 500.74, 30.13, 464.86, 10.04, 459.12, 7.17, 365.85, 21.52, 317.06, 73.18, 266.83, 113.36, 245.31, 100.45, 190.78, 117.67, 150.6, 139.19, 131.95, 167.89, 130.51, 199.46, 156.34, 210.94, 183.61, 210.94, 222.35, 209.51, 253.92, 231.03, 279.75, 253.99, 294.1, 256.86, 304.14, 274.08, 355.8, 282.69, 407.46, 294.17, 447.64, 271.21, 480.65, 251.12, 510.78, 252.56, 573.92, 269.78, 614.1, 265.47, 627.01, 265.47, 631.32]], "area": 98247.09205, "iscrowd": 0, "image_id": 153749, "bbox": [7.17, 130.51, 287.0, 500.81], "category_id": 1, "id": 461323, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "hat", "holding", "a", "hotdog"], "raw": "A man in hat holding a hotdog.", "sent_id": 103736, "sent": "a man in hat holding a hotdog"}, {"tokens": ["an", "old", "man", "eating", "a", "hot", "dog"], "raw": "An old man eating a hot dog.", "sent_id": 103737, "sent": "an old man eating a hot dog"}], "file_name": "COCO_train2014_000000153749_461323.jpg", "ann_id": 461323, "sent_ids": [103736, 103737], "ref_id": 44970}, {"segmentation": [[164.02, 212.96, 310.08, 204.68, 287.61, 150.87, 214.29, 150.87, 210.15, 140.82, 197.73, 143.77, 199.5, 156.19, 198.32, 159.74, 191.82, 162.1, 210.15, 161.51, 209.56, 168.02, 201.28, 174.52, 179.99, 176.89]], "area": 6702.687249999998, "iscrowd": 0, "image_id": 554031, "bbox": [164.02, 140.82, 146.06, 72.14], "category_id": 67, "id": 1964562, "split": "val", "sentences": [{"tokens": ["the", "far", "side", "of", "a", "table", "with", "glasses", "on", "it"], "raw": "The far side of a table with glasses on it.", "sent_id": 103840, "sent": "the far side of a table with glasses on it"}], "file_name": "COCO_train2014_000000554031_1964562.jpg", "ann_id": 1964562, "sent_ids": [103840], "ref_id": 45013}, {"segmentation": [[89.45, 351.93, 62.36, 316.34, 43.02, 267.59, 37.6, 231.22, 41.47, 201.04, 46.89, 177.82, 55.4, 152.29, 80.16, 109.73, 81.71, 122.88, 67.01, 161.57, 67.01, 179.37, 63.91, 225.03, 69.33, 242.83, 81.71, 278.42, 97.96, 308.6, 116.53, 326.4, 152.13, 355.8, 197.01, 377.47, 264.33, 381.34, 311.54, 368.18, 344.81, 352.71, 361.83, 334.91, 381.18, 303.18, 388.92, 283.84, 418.06, 315.14, 391.08, 345.36, 363.01, 372.34, 318.76, 399.32, 272.36, 410.11, 230.26, 411.19, 182.77, 404.72, 135.29, 385.29, 89.96, 350.75], [426.8, 231.93, 402.68, 213.24, 401.48, 197.56, 441.27, 216.25, 440.06, 228.91, 439.46, 242.78, 425.59, 231.32], [401.48, 176.46, 388.81, 146.91, 374.95, 118.57, 363.49, 98.68, 319.48, 62.5, 321.89, 59.49, 358.06, 80.59, 384.59, 103.5, 406.9, 128.22, 421.98, 152.34, 431.02, 170.43, 438.86, 199.97, 397.86, 177.66]], "area": 21029.264249999997, "iscrowd": 0, "image_id": 79111, "bbox": [37.6, 59.49, 403.67, 351.7], "category_id": 51, "id": 1902616, "split": "val", "sentences": [{"tokens": ["a", "wooden", "bowl", "containing", "another", "wooden", "bowl"], "raw": "A wooden bowl containing another wooden bowl.", "sent_id": 103861, "sent": "a wooden bowl containing another wooden bowl"}, {"tokens": ["a", "brown", "bowl", "on", "the", "ground"], "raw": "a Brown bowl on the ground", "sent_id": 103862, "sent": "a brown bowl on the ground"}], "file_name": "COCO_train2014_000000079111_1902616.jpg", "ann_id": 1902616, "sent_ids": [103861, 103862], "ref_id": 45020}, {"segmentation": [[325.52, 194.3, 327.43, 187.6, 321.69, 182.82, 325.52, 172.28, 342.75, 168.45, 359.02, 159.84, 365.73, 141.65, 377.22, 133.99, 511.25, 154.09, 483.49, 194.3, 472.0, 220.15, 417.43, 226.86, 401.15, 239.3, 384.87, 259.41, 374.34, 260.36, 379.13, 236.43, 369.56, 226.86, 366.68, 239.3, 359.02, 229.73, 366.68, 220.15, 359.02, 214.41, 352.32, 224.94, 347.54, 214.41, 353.28, 211.54, 350.41, 207.71, 340.83, 217.28, 340.83, 207.71, 346.58, 198.13, 337.96, 198.13, 335.09, 205.79, 334.13, 201.96, 337.0, 192.39, 336.05, 192.39, 332.22, 200.05, 327.43, 196.22]], "area": 12895.160050000004, "iscrowd": 0, "image_id": 346026, "bbox": [321.69, 133.99, 189.56, 126.37], "category_id": 15, "id": 579376, "split": "val", "sentences": [{"tokens": ["the", "second", "bench", "in", "the", "right"], "raw": "the second bench in the right", "sent_id": 104010, "sent": "the second bench in the right"}, {"tokens": ["a", "green", "bench", "closest", "to", "top", "right", "corner"], "raw": "a green bench closest to top right corner", "sent_id": 104011, "sent": "a green bench closest to top right corner"}], "file_name": "COCO_train2014_000000346026_579376.jpg", "ann_id": 579376, "sent_ids": [104010, 104011], "ref_id": 45082}, {"segmentation": [[139.44, 390.62, 72.58, 382.98, 43.93, 370.56, 40.11, 348.6, 24.83, 320.9, 21.01, 290.34, 15.28, 277.92, 22.92, 224.44, 37.25, 210.11, 56.35, 167.13, 61.12, 149.94, 67.81, 145.17, 149.94, 138.48, 159.49, 148.03, 154.72, 165.22, 170.96, 201.52, 172.87, 273.15, 159.49, 306.57, 178.6, 320.9, 177.64, 334.27, 155.67, 355.28, 146.12, 372.47, 146.12, 384.89, 146.12, 391.57]], "area": 31720.704800000003, "iscrowd": 0, "image_id": 79611, "bbox": [15.28, 138.48, 163.32, 253.09], "category_id": 85, "id": 1666607, "split": "val", "sentences": [{"tokens": ["reflection", "of", "clock"], "raw": "reflection of clock", "sent_id": 104019, "sent": "reflection of clock"}, {"tokens": ["reflection", "of", "the", "clock"], "raw": "Reflection of the clock.", "sent_id": 104020, "sent": "reflection of the clock"}], "file_name": "COCO_train2014_000000079611_1666607.jpg", "ann_id": 1666607, "sent_ids": [104019, 104020], "ref_id": 45087}, {"segmentation": [[220.64, 194.8, 276.04, 226.32, 236.88, 266.44, 264.58, 291.28, 268.4, 316.11, 308.52, 336.17, 341.95, 331.39, 330.48, 311.33, 319.02, 286.5, 328.57, 254.98, 356.27, 196.71, 341.95, 163.28, 320.93, 148.0, 337.17, 126.03, 368.69, 128.9, 383.97, 146.09, 388.75, 138.45, 390.66, 113.62, 400.21, 104.06, 390.66, 75.41, 370.6, 64.9, 352.45, 63.95, 327.62, 59.17, 298.96, 59.17, 287.5, 63.95, 262.67, 95.47, 219.69, 118.39, 206.31, 157.55, 215.87, 191.94]], "area": 28137.523850000005, "iscrowd": 0, "image_id": 433723, "bbox": [206.31, 59.17, 193.9, 277.0], "category_id": 1, "id": 495291, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "in", "a", "colorful", "hat", "jumping", "a", "skateboard"], "raw": "A young boy in a colorful hat jumping a skateboard.", "sent_id": 104037, "sent": "a young boy in a colorful hat jumping a skateboard"}, {"tokens": ["a", "boy", "with", "a", "colorful", "hat", "is", "doing", "tricks", "on", "top", "of", "a", "skateboard"], "raw": "A boy with a colorful hat is doing tricks on top of a skateboard", "sent_id": 104038, "sent": "a boy with a colorful hat is doing tricks on top of a skateboard"}], "file_name": "COCO_train2014_000000433723_495291.jpg", "ann_id": 495291, "sent_ids": [104037, 104038], "ref_id": 45094}, {"segmentation": [[283.65, 228.37, 268.16, 242.62, 247.1, 241.38, 243.38, 230.85, 248.96, 214.74, 245.24, 206.06, 233.47, 210.4, 222.31, 201.1, 185.14, 213.5, 213.02, 182.52, 224.17, 177.56, 256.39, 181.28, 292.33, 178.8, 353.05, 178.8, 366.06, 188.09, 369.16, 202.34, 369.16, 209.16, 343.13, 237.04, 330.74, 271.74, 304.1, 259.97]], "area": 9021.357399999999, "iscrowd": 0, "image_id": 26421, "bbox": [185.14, 177.56, 184.02, 94.18], "category_id": 24, "id": 1822778, "split": "val", "sentences": [{"tokens": ["middle", "zebra"], "raw": "Middle zebra", "sent_id": 104050, "sent": "middle zebra"}, {"tokens": ["the", "zebra", "back", "in", "the", "bushes"], "raw": "The zebra back in the bushes.", "sent_id": 104051, "sent": "the zebra back in the bushes"}], "file_name": "COCO_train2014_000000026421_1822778.jpg", "ann_id": 1822778, "sent_ids": [104050, 104051], "ref_id": 45098}, {"segmentation": [[0.71, 103.93, 2.09, 42.12, 2.09, 4.3, 2.55, 2.91, 32.54, 0.61, 37.15, 4.76, 52.83, 23.21, 66.67, 45.81, 58.83, 67.49, 39.46, 78.1, 49.61, 81.33, 51.91, 95.17, 58.37, 124.23, 57.91, 131.15, 58.37, 138.53, 42.22, 138.99, 41.3, 138.53, 40.38, 124.69, 37.61, 111.32, 9.01, 109.93, 3.02, 109.01]], "area": 6147.779899999999, "iscrowd": 0, "image_id": 488073, "bbox": [0.71, 0.61, 65.96, 138.38], "category_id": 1, "id": 527379, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "blue", "pant"], "raw": "A MAN IN BLUE PANT.", "sent_id": 104109, "sent": "a man in blue pant"}, {"tokens": ["a", "spectator", "sitting", "in", "the", "stands", ",", "wearing", "blue", "jeans", "and", "a", "dark", "jacket"], "raw": "A spectator sitting in the stands, wearing blue jeans and a dark jacket.", "sent_id": 104110, "sent": "a spectator sitting in the stands , wearing blue jeans and a dark jacket"}], "file_name": "COCO_train2014_000000488073_527379.jpg", "ann_id": 527379, "sent_ids": [104109, 104110], "ref_id": 45120}, {"segmentation": [[339.42, 568.09, 327.91, 428.58, 369.62, 441.53, 414.2, 451.6, 450.16, 493.3, 473.17, 530.7, 480.0, 546.52]], "area": 13578.6327, "iscrowd": 0, "image_id": 498854, "bbox": [327.91, 428.58, 152.09, 139.51], "category_id": 62, "id": 1598075, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "the", "seat", "to", "the", "right", "of", "the", "window", "pane"], "raw": "the back of the seat to the right of the window pane", "sent_id": 104124, "sent": "the back of the seat to the right of the window pane"}], "file_name": "COCO_train2014_000000498854_1598075.jpg", "ann_id": 1598075, "sent_ids": [104124], "ref_id": 45127}, {"segmentation": [[273.04, 362.69, 292.48, 367.86, 296.08, 368.76, 293.83, 363.36, 296.98, 359.76, 300.59, 355.26, 306.89, 349.41, 313.19, 345.36, 334.34, 350.76, 360.0, 334.11, 360.0, 367.41, 345.14, 377.76, 315.89, 382.71, 302.39, 382.26, 280.78, 374.61, 267.28, 365.16, 266.38, 361.56, 269.53, 361.56, 272.23, 361.56], [360.0, 376.32, 316.34, 391.17, 307.79, 401.52, 307.34, 414.57, 314.99, 432.58, 336.14, 445.18, 355.04, 451.93, 360.0, 453.28], [360.0, 459.13, 337.04, 478.0, 328.94, 486.1, 328.49, 497.8, 330.29, 500.0, 359.99, 500.0]], "area": 6109.87485, "iscrowd": 0, "image_id": 358921, "bbox": [266.38, 334.11, 93.62, 165.89], "category_id": 1, "id": 1681391, "split": "val", "sentences": [{"tokens": ["the", "person", "whose", "face", "is", "not", "shown"], "raw": "The person whose face is not shown", "sent_id": 104137, "sent": "the person whose face is not shown"}, {"tokens": ["the", "hand", "with", "one", "finger", "pointing", "from", "the", "side"], "raw": "The hand with one finger pointing from the side.", "sent_id": 104138, "sent": "the hand with one finger pointing from the side"}], "file_name": "COCO_train2014_000000358921_1681391.jpg", "ann_id": 1681391, "sent_ids": [104137, 104138], "ref_id": 45135}, {"segmentation": [[398.15, 244.76, 382.76, 255.33, 371.22, 261.1, 361.6, 266.88, 353.91, 275.53, 350.06, 279.38, 348.14, 284.19, 347.18, 287.07, 334.68, 287.07, 326.02, 285.15, 313.52, 283.22, 306.79, 281.3, 302.94, 279.38, 309.67, 276.49, 316.4, 274.57, 322.17, 272.65, 327.94, 265.91, 337.56, 254.37, 345.25, 238.02, 345.25, 237.06, 344.29, 231.29, 331.79, 232.25, 319.29, 231.29, 294.28, 224.56, 284.67, 223.6, 272.16, 220.71, 256.78, 212.06, 249.08, 208.21, 251.97, 205.33, 272.16, 200.52, 295.25, 201.48, 316.4, 201.48, 357.76, 202.44, 362.57, 202.44, 376.03, 196.67, 399.11, 188.98, 402.96, 173.59, 402.96, 168.78, 398.15, 164.93, 395.26, 163.97, 393.34, 159.16, 399.11, 159.16, 422.19, 158.2, 437.58, 160.13, 439.5, 165.9, 441.43, 167.82, 434.69, 172.63, 429.89, 177.44, 426.04, 185.13, 423.15, 194.75, 422.19, 201.48, 424.11, 206.29, 427.0, 204.36, 444.31, 195.71, 450.08, 188.98, 455.85, 185.13, 475.09, 185.13, 471.24, 191.86, 465.47, 201.48, 464.51, 206.29, 476.05, 199.56, 481.82, 192.82, 484.7, 193.78, 488.55, 196.67, 490.47, 209.17, 480.86, 223.6, 474.12, 231.29, 467.39, 241.87, 457.77, 251.49, 452.0, 254.37, 449.12, 254.37, 441.43, 250.53, 437.58, 247.64, 441.43, 236.1, 420.27, 239.95, 405.84, 239.95, 400.07, 240.91, 397.19, 240.91, 395.26, 240.91]], "area": 11636.21075, "iscrowd": 0, "image_id": 171478, "bbox": [249.08, 158.2, 241.39, 128.87], "category_id": 5, "id": 160441, "split": "val", "sentences": [{"tokens": ["a", "blue", "and", "yellow", "jet", "fighter", "plane", "emitting", "grey", "smoke"], "raw": "a blue and yellow jet fighter plane emitting grey smoke", "sent_id": 104171, "sent": "a blue and yellow jet fighter plane emitting grey smoke"}, {"tokens": ["plane", "in", "the", "middle"], "raw": "plane in the middle", "sent_id": 104172, "sent": "plane in the middle"}], "file_name": "COCO_train2014_000000171478_160441.jpg", "ann_id": 160441, "sent_ids": [104171, 104172], "ref_id": 45148}, {"segmentation": [[317.76, 68.95, 322.62, 69.85, 322.62, 73.99, 317.76, 78.86, 331.63, 104.8, 347.3, 132.18, 353.97, 143.89, 360.99, 155.42, 364.96, 152.17, 370.0, 148.21, 377.75, 147.85, 381.71, 149.29, 382.61, 155.6, 385.13, 160.46, 383.69, 181.0, 395.76, 181.0, 401.35, 181.0, 402.07, 177.75, 404.05, 175.05, 405.49, 173.07, 405.85, 169.29, 406.93, 166.95, 409.45, 164.96, 410.71, 167.85, 411.97, 171.63, 415.04, 173.07, 415.94, 175.95, 421.92, 179.79, 441.85, 179.52, 441.85, 189.62, 426.56, 189.35, 427.38, 200.54, 459.05, 200.0, 474.07, 201.91, 479.22, 221.04, 481.2, 242.66, 485.7, 273.82, 488.4, 302.46, 485.52, 308.59, 485.16, 311.29, 484.8, 348.04, 478.68, 349.66, 467.33, 349.3, 459.76, 359.21, 453.82, 363.53, 415.09, 364.79, 406.26, 364.97, 398.15, 359.57, 392.75, 345.88, 351.86, 346.06, 347.72, 346.6, 337.63, 354.88, 326.46, 354.88, 285.75, 358.67, 266.65, 366.41, 261.43, 367.49, 253.32, 365.69, 249.36, 359.57, 247.2, 351.64, 243.23, 331.65, 242.69, 318.86, 204.32, 319.4, 203.42, 319.94, 203.6, 324.62, 199.28, 322.64, 199.28, 328.4, 199.1, 333.99, 197.12, 337.05, 194.06, 337.05, 191.53, 334.89, 191.35, 332.55, 191.71, 329.66, 191.89, 328.4, 188.65, 325.16, 188.29, 318.86, 186.13, 299.76, 184.15, 294.36, 180.01, 290.57, 171.36, 277.6, 167.94, 256.53, 161.09, 231.31, 152.26, 216.0, 143.44, 207.53, 144.16, 192.04, 145.42, 164.66, 143.8, 163.94, 142.0, 161.05, 135.51, 159.61, 127.22, 158.71, 126.5, 160.87, 131.73, 162.13, 131.19, 173.66, 134.25, 189.88, 134.25, 198.34, 125.78, 200.14, 120.74, 196.72, 118.58, 165.38, 119.84, 163.22, 123.08, 162.13, 123.98, 158.35, 126.5, 157.09, 129.93, 156.37, 139.11, 157.27, 142.9, 157.81, 146.5, 148.98, 148.3, 144.48, 156.95, 122.14, 163.97, 109.53, 170.46, 100.71, 175.86, 90.98, 179.47, 87.74, 194.6, 86.84, 194.6, 81.97, 191.71, 80.71, 189.91, 74.05, 192.07, 71.16, 195.32, 69.36, 193.15, 65.22, 195.34, 59.21, 198.34, 57.85, 311.65, 58.12, 314.11, 58.67, 316.3, 61.94, 315.2, 66.04]], "area": 75171.24735, "iscrowd": 0, "image_id": 257867, "bbox": [118.58, 57.85, 369.82, 309.64], "category_id": 8, "id": 399113, "split": "val", "sentences": [{"tokens": ["a", "white", "tow", "truck", "with", "yellow", "and", "red", "stripes"], "raw": "A white tow truck with yellow and red stripes.", "sent_id": 104202, "sent": "a white tow truck with yellow and red stripes"}], "file_name": "COCO_train2014_000000257867_399113.jpg", "ann_id": 399113, "sent_ids": [104202], "ref_id": 45161}, {"segmentation": [[208.3, 228.61, 205.46, 179.51, 196.96, 153.07, 199.8, 135.13, 171.47, 124.75, 151.64, 110.58, 140.31, 85.09, 151.64, 54.88, 179.03, 24.66, 235.68, 19.0, 251.73, 23.72, 278.17, 10.5, 309.32, 15.22, 329.15, 24.66, 356.53, 19.0, 389.58, 35.05, 415.07, 55.82, 419.79, 69.98, 413.19, 89.81, 419.79, 101.14, 415.07, 108.69, 410.35, 119.08, 379.19, 130.41, 365.03, 138.91, 358.42, 139.85, 348.98, 147.41, 331.98, 151.18, 332.93, 166.29, 347.09, 152.13, 356.53, 159.68, 352.76, 171.96, 352.76, 178.56, 347.09, 192.73, 338.59, 193.67, 342.37, 231.44, 353.7, 320.19, 353.7, 331.52, 361.25, 342.85, 362.2, 348.52, 352.76, 351.35, 335.76, 351.35, 327.26, 349.46, 326.32, 338.13, 330.1, 301.31, 315.93, 247.49, 309.32, 225.77, 309.32, 217.28, 298.94, 237.1, 291.38, 237.1, 285.72, 265.43, 283.83, 298.48, 293.27, 323.97, 290.44, 334.36, 273.44, 337.19, 268.72, 336.25, 261.17, 323.03, 259.28, 282.43, 255.5, 259.77, 246.06, 238.99, 245.12, 265.43, 252.67, 295.64, 259.28, 310.75, 248.9, 318.31, 235.68, 314.53, 230.96, 312.64, 230.01, 293.76, 218.68, 247.49, 213.02, 235.22]], "area": 50746.34854999998, "iscrowd": 0, "image_id": 516889, "bbox": [140.31, 10.5, 279.48, 340.85], "category_id": 22, "id": 580333, "split": "val", "sentences": [{"tokens": ["elephant", "about", "to", "charge"], "raw": "elephant about to charge", "sent_id": 104265, "sent": "elephant about to charge"}, {"tokens": ["there", "is", "a", "large", "elephant", "standing", "outside"], "raw": "There is a large elephant standing outside.", "sent_id": 104266, "sent": "there is a large elephant standing outside"}], "file_name": "COCO_train2014_000000516889_580333.jpg", "ann_id": 580333, "sent_ids": [104265, 104266], "ref_id": 45188}, {"segmentation": [[142.75, 222.3, 139.48, 249.54, 156.91, 289.86, 153.65, 302.93, 137.3, 367.22, 152.56, 428.25, 140.57, 444.59, 152.56, 451.13, 161.27, 455.49, 178.71, 453.31, 186.34, 448.95, 192.87, 448.95, 196.14, 453.31, 197.23, 459.85, 198.32, 464.21, 191.78, 474.01, 222.3, 479.46, 222.3, 474.01, 227.74, 464.21, 238.64, 462.03, 240.82, 460.94, 245.18, 459.85, 246.27, 455.49, 213.58, 351.97, 237.55, 269.15, 213.58, 181.98, 195.05, 155.83, 190.7, 149.29, 186.34, 143.84, 186.34, 137.3, 174.35, 127.49, 158.0, 119.87, 150.38, 126.4, 144.93, 128.58, 141.66, 134.03, 135.12, 138.39, 130.76, 128.58, 124.22, 136.21, 117.69, 144.93, 113.33, 155.83, 117.69, 165.63, 120.96, 169.99, 130.76, 175.44, 141.66, 175.44, 128.58, 196.14, 119.87, 177.62, 115.51, 169.99, 105.7, 162.36, 101.34, 162.36, 95.89, 166.72, 95.89, 172.17, 95.89, 180.89, 98.07, 211.4, 117.69, 225.57, 124.22, 228.83, 128.58, 228.83, 134.03, 227.74]], "area": 29037.259049999997, "iscrowd": 0, "image_id": 222676, "bbox": [95.89, 119.87, 150.38, 359.59], "category_id": 1, "id": 531118, "split": "val", "sentences": [{"tokens": ["a", "guy", "scared", "of", "balls"], "raw": "A guy scared of balls.", "sent_id": 104306, "sent": "a guy scared of balls"}, {"tokens": ["guy", "with", "teeth", "showing", "swinging", "at", "a", "tennis", "ball"], "raw": "Guy with teeth showing swinging at a tennis ball.", "sent_id": 104307, "sent": "guy with teeth showing swinging at a tennis ball"}], "file_name": "COCO_train2014_000000222676_531118.jpg", "ann_id": 531118, "sent_ids": [104306, 104307], "ref_id": 45202}, {"segmentation": [[465.17, 111.03, 311.46, 41.46, 249.17, 40.65, 190.92, 64.92, 177.98, 304.38, 242.7, 310.85, 252.4, 318.13, 267.78, 321.37, 293.66, 318.13, 355.15, 321.37, 381.03, 328.65, 381.03, 328.65, 381.84, 327.03, 401.26, 312.47, 486.2, 301.15, 495.1, 309.24, 502.38, 297.1, 518.56, 301.15, 525.03, 294.67, 536.36, 290.63, 556.58, 286.58, 546.88, 167.66, 534.74, 181.42, 478.11, 154.72]], "area": 82302.23644999998, "iscrowd": 0, "image_id": 388935, "bbox": [177.98, 40.65, 378.6, 288.0], "category_id": 6, "id": 162931, "split": "val", "sentences": [{"tokens": ["a", "red", "and", "white", "double", "decker", "sight", "seeing", "bus"], "raw": "a red and white double decker sight seeing bus", "sent_id": 104355, "sent": "a red and white double decker sight seeing bus"}, {"tokens": ["a", "red", "double", "decker", "tour", "bus", "on", "a", "city", "street"], "raw": "A red double decker tour bus on a city street.", "sent_id": 104356, "sent": "a red double decker tour bus on a city street"}], "file_name": "COCO_train2014_000000388935_162931.jpg", "ann_id": 162931, "sent_ids": [104355, 104356], "ref_id": 45221}, {"segmentation": [[167.2, 555.12, 132.58, 578.86, 102.91, 605.56, 131.59, 628.31, 155.33, 624.36, 187.98, 594.68, 226.55, 586.77, 266.12, 594.68, 296.78, 612.49, 317.55, 630.29, 259.19, 621.39, 227.54, 614.47, 168.19, 623.37, 147.93, 626.02, 129.24, 638.75, 52.46, 638.79, 1.03, 639.19, 2.01, 565.01, 157.31, 560.06]], "area": 12896.622850000009, "iscrowd": 0, "image_id": 537196, "bbox": [1.03, 555.12, 316.52, 84.07], "category_id": 1, "id": 566228, "split": "val", "sentences": [{"tokens": ["fingers", "holding", "the", "pizza", "box", "up"], "raw": "Fingers holding the pizza box up.", "sent_id": 104436, "sent": "fingers holding the pizza box up"}, {"tokens": ["the", "left", "hands", "fingers", "of", "the", "person", "holding", "the", "box"], "raw": "The left hands fingers of the person holding the box", "sent_id": 104437, "sent": "the left hands fingers of the person holding the box"}], "file_name": "COCO_train2014_000000537196_566228.jpg", "ann_id": 566228, "sent_ids": [104436, 104437], "ref_id": 45250}, {"segmentation": [[96.45, 348.47, 57.27, 293.21, 31.15, 273.11, 35.16, 245.99, 38.18, 223.88, 114.54, 203.79, 185.87, 200.77, 244.14, 204.79, 274.28, 213.83, 303.42, 232.92, 340.6, 257.04, 347.63, 283.16, 326.53, 300.24, 284.33, 332.39, 168.79, 358.51, 130.61, 351.48]], "area": 36743.888399999996, "iscrowd": 0, "image_id": 135694, "bbox": [31.15, 200.77, 316.48, 157.74], "category_id": 59, "id": 1070935, "split": "val", "sentences": [{"tokens": ["the", "pizza", "to", "the", "far", "left"], "raw": "the pizza to the far left", "sent_id": 104456, "sent": "the pizza to the far left"}, {"tokens": ["the", "pizza", "that", "has", "olives", "on", "it", "on", "the", "left", "burner"], "raw": "The pizza that has olives on it on the left burner", "sent_id": 104457, "sent": "the pizza that has olives on it on the left burner"}], "file_name": "COCO_train2014_000000135694_1070935.jpg", "ann_id": 1070935, "sent_ids": [104456, 104457], "ref_id": 45258}, {"segmentation": [[156.68, 16.27, 206.34, 8.56, 295.38, 17.98, 308.22, 23.97, 306.51, 357.88, 245.72, 371.58, 193.5, 372.44, 139.56, 360.45, 148.98, 325.35]], "area": 55078.06025, "iscrowd": 0, "image_id": 118413, "bbox": [139.56, 8.56, 168.66, 363.88], "category_id": 77, "id": 321776, "split": "val", "sentences": [{"tokens": ["the", "front", "portion", "of", "an", "old", ",", "grey", "cell", "phone"], "raw": "The front portion of an old, grey cell phone.", "sent_id": 104478, "sent": "the front portion of an old , grey cell phone"}, {"tokens": ["motorola", "c350", "phone"], "raw": "Motorola C350 phone.", "sent_id": 104479, "sent": "motorola c350 phone"}], "file_name": "COCO_train2014_000000118413_321776.jpg", "ann_id": 321776, "sent_ids": [104478, 104479], "ref_id": 45267}, {"segmentation": [[361.75, 216.57, 424.12, 198.33, 448.11, 198.33, 441.39, 304.84, 432.76, 327.87, 406.85, 314.44, 408.77, 349.94, 409.73, 400.8, 412.61, 415.19, 379.98, 416.15, 376.14, 384.49, 368.47, 358.58, 375.18, 396.96, 370.39, 418.07, 347.36, 413.27, 333.92, 370.09, 318.57, 348.98, 312.81, 323.08, 295.54, 300.05, 313.77, 299.09, 326.25, 292.37, 342.56, 240.55], [498.97, 195.46, 534.47, 203.13, 557.5, 232.88, 567.09, 253.03, 558.46, 285.65, 552.7, 307.72, 559.42, 348.02, 566.13, 399.84, 564.22, 410.39, 545.02, 399.84, 547.9, 375.85, 542.15, 359.54, 525.83, 328.83, 515.28, 320.2, 530.63, 384.49, 510.48, 378.73, 500.89, 333.63, 485.53, 309.64, 471.14, 317.32, 494.17, 243.43, 498.97, 216.57, 498.97, 196.41], [461.54, 200.25, 474.02, 196.41, 470.18, 229.04, 465.38, 242.47, 458.67, 203.13]], "area": 31489.58155, "iscrowd": 0, "image_id": 26421, "bbox": [295.54, 195.46, 271.55, 222.61], "category_id": 24, "id": 591422, "split": "val", "sentences": [{"tokens": ["zebra", "behind", "a", "tree", "with", "its", "mouth", "to", "the", "ground"], "raw": "Zebra behind a tree with its mouth to the ground.", "sent_id": 104511, "sent": "zebra behind a tree with its mouth to the ground"}], "file_name": "COCO_train2014_000000026421_591422.jpg", "ann_id": 591422, "sent_ids": [104511], "ref_id": 45283}, {"segmentation": [[355.03, 265.5, 345.44, 253.03, 337.76, 229.04, 341.6, 188.74, 350.24, 151.32, 355.03, 115.81, 355.03, 104.3, 356.95, 78.39, 369.43, 49.6, 384.78, 1.63, 522.96, 2.59, 533.51, 19.86, 543.11, 48.64, 541.19, 59.2, 514.32, 61.12, 481.69, 83.19, 480.73, 99.5, 513.36, 128.29, 499.93, 171.47, 467.3, 214.65, 456.75, 236.72, 447.15, 251.11, 467.3, 281.81, 447.15, 272.22, 434.68, 263.58, 441.39, 252.07, 423.16, 246.31, 413.57, 238.63, 429.88, 206.01, 451.95, 175.3, 472.1, 137.88, 461.54, 127.33, 437.56, 107.18, 427.0, 115.81, 413.57, 117.73, 401.09, 121.57, 389.58, 147.48, 389.58, 173.39, 381.9, 200.25, 381.9, 236.72, 385.74, 264.54, 390.54, 276.06, 356.95, 267.42]], "area": 29317.15364999999, "iscrowd": 0, "image_id": 156608, "bbox": [337.76, 1.63, 205.35, 280.18], "category_id": 1, "id": 191852, "split": "val", "sentences": [{"tokens": ["a", "man", "drinking", "beer"], "raw": "a man drinking beer", "sent_id": 104535, "sent": "a man drinking beer"}, {"tokens": ["a", "man", "holding", "beer", "bottle", "and", "sitting", "in", "sofa"], "raw": "A MAN HOLDING BEER BOTTLE AND SITTING IN SOFA", "sent_id": 104536, "sent": "a man holding beer bottle and sitting in sofa"}], "file_name": "COCO_train2014_000000156608_191852.jpg", "ann_id": 191852, "sent_ids": [104535, 104536], "ref_id": 45293}, {"segmentation": [[449.93, 194.01, 382.1, 217.89, 370.64, 225.53, 370.64, 239.86, 365.86, 237.0, 369.68, 251.32, 363.0, 261.83, 364.91, 277.12, 360.13, 277.12, 355.36, 290.49, 357.27, 291.45, 362.04, 291.45, 362.04, 305.77, 365.86, 323.92, 384.01, 322.01, 385.92, 303.86, 428.91, 301.0, 435.6, 322.01, 440.37, 329.66, 452.79, 330.61, 451.84, 337.3, 454.7, 337.3, 459.48, 333.48, 466.17, 325.84, 458.52, 307.69, 478.58, 300.04, 487.18, 288.58, 518.7, 279.03, 515.84, 289.54, 529.21, 294.31, 555.0, 278.07, 533.03, 241.77, 554.05, 230.31, 541.63, 203.56, 472.85, 225.53, 460.43, 194.01, 449.93, 191.14, 446.11, 194.01]], "area": 17007.338249999993, "iscrowd": 0, "image_id": 307082, "bbox": [355.36, 191.14, 199.64, 146.16], "category_id": 8, "id": 401571, "split": "val", "sentences": [{"tokens": ["a", "truck", "number", "14", "on", "a", "snow", "bank"], "raw": "a truck number 14 on a snow bank.", "sent_id": 29, "sent": "a truck number 14 on a snow bank"}, {"tokens": ["a", "truck", "with", "the", "number", "14", "painted", "on", "it"], "raw": "A truck with the number 14 painted on it.", "sent_id": 30, "sent": "a truck with the number 14 painted on it"}], "file_name": "COCO_train2014_000000307082_401571.jpg", "ann_id": 401571, "sent_ids": [29, 30], "ref_id": 45305}, {"segmentation": [[435.15, 324.04, 374.0, 396.51, 367.96, 410.86, 374.0, 419.92, 417.79, 430.49, 432.13, 446.34, 439.68, 457.66, 430.62, 477.29, 436.66, 480.0, 445.72, 480.0, 446.47, 459.17, 438.92, 438.04, 432.88, 425.2, 495.54, 332.34, 473.65, 327.81, 469.12, 324.04, 440.43, 324.04]], "area": 7746.115900000001, "iscrowd": 0, "image_id": 149921, "bbox": [367.96, 324.04, 127.58, 155.96], "category_id": 15, "id": 2061563, "split": "val", "sentences": [{"tokens": ["an", "empty", "seat", "at", "on", "a", "bench"], "raw": "An empty seat at on a bench.", "sent_id": 1071, "sent": "an empty seat at on a bench"}, {"tokens": ["the", "table", "bench", "with", "two", "people", "on"], "raw": "the table bench with two people on.", "sent_id": 1072, "sent": "the table bench with two people on"}], "file_name": "COCO_train2014_000000149921_2061563.jpg", "ann_id": 2061563, "sent_ids": [1071, 1072], "ref_id": 45360}, {"segmentation": [[3.24, 445.48, 24.81, 432.54, 49.62, 422.83, 75.51, 415.28, 90.61, 414.2, 116.49, 396.94, 126.2, 392.63, 129.44, 384.0, 124.04, 367.82, 118.65, 347.33, 151.01, 350.56, 149.93, 321.44, 145.62, 313.89, 136.99, 304.18, 141.3, 295.55, 136.99, 289.08, 130.52, 268.58, 122.97, 265.35, 115.42, 240.54, 110.02, 218.97, 103.55, 211.42, 99.24, 193.08, 105.71, 188.76, 104.63, 176.9, 110.02, 167.19, 118.65, 166.11, 114.34, 154.25, 117.57, 144.54, 122.97, 140.22, 116.49, 116.49, 102.47, 104.63, 80.9, 99.24, 48.54, 103.55, 37.75, 119.73, 36.67, 141.3, 38.83, 149.93, 39.91, 157.48, 44.22, 159.64, 31.28, 163.96, 25.89, 174.74, 31.28, 180.13, 30.2, 184.45, 11.87, 196.31, 2.16, 208.18, 0.0, 444.4, 3.24, 446.56]], "area": 35473.15290000001, "iscrowd": 0, "image_id": 87214, "bbox": [0.0, 99.24, 151.01, 347.32], "category_id": 1, "id": 524467, "split": "val", "sentences": [{"tokens": ["man", "with", "black", "helmet", "and", "blue", "jacket"], "raw": "man with black helmet and blue jacket", "sent_id": 1509, "sent": "man with black helmet and blue jacket"}, {"tokens": ["the", "man", "facing", "away", "in", "the", "helmet"], "raw": "The man facing away in the helmet", "sent_id": 1510, "sent": "the man facing away in the helmet"}], "file_name": "COCO_train2014_000000087214_524467.jpg", "ann_id": 524467, "sent_ids": [1509, 1510], "ref_id": 45383}, {"segmentation": [[43.22, 424.76, 12.97, 327.51, 16.21, 296.17, 20.53, 284.29, 30.26, 270.24, 39.98, 267.0, 81.04, 256.19, 101.57, 252.95, 116.7, 251.87, 105.89, 284.29, 103.73, 303.74, 109.13, 376.13, 43.22, 420.43]], "area": 11966.7806, "iscrowd": 0, "image_id": 205202, "bbox": [12.97, 251.87, 103.73, 172.89], "category_id": 62, "id": 385941, "split": "val", "sentences": [{"tokens": ["a", "back", "rest", "of", "a", "wooden", "chair", "which", "was", "occupied", "by", "a", "man"], "raw": "A back rest of a wooden chair which was occupied by a man", "sent_id": 1583, "sent": "a back rest of a wooden chair which was occupied by a man"}, {"tokens": ["a", "chair", "with", "a", "boy", "sitting", "in", "it", "and", "a", "boy", "leaning", "on", "it"], "raw": "A chair with a boy sitting in it and a boy leaning on it", "sent_id": 1584, "sent": "a chair with a boy sitting in it and a boy leaning on it"}], "file_name": "COCO_train2014_000000205202_385941.jpg", "ann_id": 385941, "sent_ids": [1583, 1584], "ref_id": 45386}, {"segmentation": [[84.52, 378.67, 70.77, 378.67, 67.33, 401.89, 73.35, 411.34, 77.64, 413.92, 92.26, 405.32, 101.72, 398.45, 131.81, 405.32, 138.68, 414.78, 143.84, 414.78, 147.28, 408.76, 142.12, 393.29, 135.25, 388.13, 135.25, 380.39, 134.39, 376.95, 118.05, 376.09, 100.0, 376.09, 94.84, 350.3, 139.54, 346.0, 142.12, 334.83, 137.82, 322.79, 139.54, 305.6, 140.4, 299.58, 140.4, 290.98, 140.4, 274.65, 145.56, 261.75, 145.56, 253.15, 139.54, 247.14, 129.23, 240.26, 109.45, 241.12, 95.7, 252.29, 87.96, 266.91, 85.38, 268.63, 74.21, 270.35, 57.87, 274.65, 46.7, 284.96, 51.85, 297.86, 63.89, 317.63, 43.26, 317.63, 59.59, 363.2, 86.24, 355.46]], "area": 10940.1861, "iscrowd": 0, "image_id": 485014, "bbox": [43.26, 240.26, 104.02, 174.52], "category_id": 62, "id": 1938820, "split": "val", "sentences": [{"tokens": ["an", "office", "chair", "closest", "to", "the", "corner"], "raw": "An office chair closest to the corner.", "sent_id": 2406, "sent": "an office chair closest to the corner"}], "file_name": "COCO_train2014_000000485014_1938820.jpg", "ann_id": 1938820, "sent_ids": [2406], "ref_id": 45430}, {"segmentation": [[223.7, 179.99, 243.11, 158.91, 353.45, 158.36, 360.1, 176.1, 362.32, 181.65, 362.87, 208.26, 360.66, 292.55, 226.47, 295.87]], "area": 18283.283400000004, "iscrowd": 0, "image_id": 365351, "bbox": [223.7, 158.36, 139.17, 137.51], "category_id": 79, "id": 1121366, "split": "val", "sentences": [{"tokens": ["two", "hand", "towels", "hanging", "in", "the", "rod"], "raw": "Two hand towels hanging in the rod", "sent_id": 2603, "sent": "two hand towels hanging in the rod"}, {"tokens": ["silver", "oven", "with", "two", "towels", "hanging", "on", "it"], "raw": "silver oven with two towels hanging on it", "sent_id": 2604, "sent": "silver oven with two towels hanging on it"}], "file_name": "COCO_train2014_000000365351_1121366.jpg", "ann_id": 1121366, "sent_ids": [2603, 2604], "ref_id": 45438}, {"segmentation": [[23.58, 396.88, 53.37, 389.68, 90.35, 418.45, 93.43, 432.83, 118.09, 443.11, 128.36, 414.34, 132.47, 395.85, 93.43, 377.36, 164.31, 351.67, 173.56, 406.12, 204.38, 396.88, 204.38, 352.71, 211.57, 339.34, 229.03, 335.24, 237.25, 360.92, 245.47, 379.42, 239.31, 391.74, 255.75, 403.04, 261.91, 388.66, 297.86, 396.88, 354.36, 415.37, 367.71, 396.88, 300.94, 370.17, 297.86, 358.87, 323.54, 361.95, 333.82, 347.56, 312.25, 321.88, 325.6, 315.72, 342.04, 312.64, 346.14, 355.78, 363.61, 356.82, 369.77, 309.56, 399.56, 318.81, 400.59, 330.1, 431.41, 336.27, 432.43, 330.1, 501.26, 347.56, 508.45, 351.67, 391.35, 416.39, 283.48, 472.89, 111.92, 472.89, 19.47, 405.1]], "area": 34016.0496, "iscrowd": 0, "image_id": 220037, "bbox": [19.47, 309.56, 488.98, 163.33], "category_id": 67, "id": 413149, "split": "val", "sentences": [{"tokens": ["table", "with", "drinks", "in", "front", "of", "ladies"], "raw": "table with drinks in front of ladies", "sent_id": 3610, "sent": "table with drinks in front of ladies"}, {"tokens": ["a", "table", "with", "2", "females", "sitting", "at", "it"], "raw": "A table with 2 females sitting at it", "sent_id": 3611, "sent": "a table with 2 females sitting at it"}], "file_name": "COCO_train2014_000000220037_413149.jpg", "ann_id": 413149, "sent_ids": [3610, 3611], "ref_id": 45471}, {"segmentation": [[113.26, 208.93, 157.48, 205.69, 267.51, 206.77, 375.37, 205.69, 442.25, 205.69, 485.39, 225.11, 508.04, 266.1, 514.52, 328.66, 512.36, 372.88, 491.87, 406.32, 464.9, 424.66, 429.3, 440.84, 230.83, 444.07, 142.38, 434.37, 104.63, 430.05, 70.11, 413.87, 46.38, 389.06, 39.91, 369.65, 37.75, 341.6, 44.22, 288.75, 60.4, 243.45, 87.37, 216.48, 105.71, 210.01]], "area": 102965.78349999998, "iscrowd": 0, "image_id": 41730, "bbox": [37.75, 205.69, 476.77, 238.38], "category_id": 51, "id": 718077, "split": "val", "sentences": [{"tokens": ["a", "container", "of", "various", "foods", "sitting", "on", "a", "table", "next", "to", "other", "foods"], "raw": "A container of various foods sitting on a table next to other foods.", "sent_id": 3911, "sent": "a container of various foods sitting on a table next to other foods"}, {"tokens": ["the", "plate", "of", "food", "that", "contains", "broccoli", "and", "others"], "raw": "the plate of food that contains broccoli and others.", "sent_id": 3912, "sent": "the plate of food that contains broccoli and others"}], "file_name": "COCO_train2014_000000041730_718077.jpg", "ann_id": 718077, "sent_ids": [3911, 3912], "ref_id": 45487}, {"segmentation": [[407.81, 222.62, 424.12, 182.31, 418.36, 131.46, 413.57, 106.51, 426.04, 89.24, 444.27, 55.65, 462.5, 37.42, 458.67, 21.11, 468.26, 0.96, 640.0, 2.88, 640.0, 271.55, 626.59, 268.67, 611.23, 274.43, 589.16, 284.99, 571.89, 295.54, 563.26, 298.42, 541.19, 309.93, 530.63, 330.09, 524.87, 339.68, 517.2, 346.4, 521.04, 352.16, 541.19, 351.2, 575.73, 345.44, 614.11, 343.52, 611.23, 335.84, 598.76, 323.37, 612.19, 302.26, 630.42, 299.38, 640.0, 307.06, 626.59, 387.66, 596.84, 399.17, 567.09, 404.93, 535.43, 408.77, 500.89, 401.09, 445.23, 382.86, 408.77, 332.96, 426.04, 328.17, 471.14, 307.06, 494.17, 295.54, 507.6, 285.95, 500.89, 267.71, 488.41, 258.12, 450.99, 269.63, 404.93, 275.39, 395.33, 273.47]], "area": 75755.72240000001, "iscrowd": 0, "image_id": 470085, "bbox": [395.33, 0.96, 244.67, 407.81], "category_id": 22, "id": 581063, "split": "val", "sentences": [{"tokens": ["an", "elephant", "with", "it", "'", "s", "trunk", "curled", "under", "itself", "and", "no", "tusk", "showing"], "raw": "An elephant with it's trunk curled under itself and no tusk showing.", "sent_id": 4229, "sent": "an elephant with it ' s trunk curled under itself and no tusk showing"}, {"tokens": ["the", "elephant", "on", "the", "right"], "raw": "the elephant on the right", "sent_id": 4230, "sent": "the elephant on the right"}], "file_name": "COCO_train2014_000000470085_581063.jpg", "ann_id": 581063, "sent_ids": [4229, 4230], "ref_id": 45500}, {"segmentation": [[60.84, 310.39, 131.61, 243.35, 137.81, 204.86, 189.96, 163.89, 209.82, 126.64, 184.99, 84.43, 158.92, 73.25, 76.98, 74.49, 88.15, 124.16, 79.46, 140.3, 55.87, 131.61, 29.8, 163.89, 1.24, 213.55, 0.0, 237.14, 23.59, 266.94, 44.7, 274.38, 37.25, 302.94, 47.18, 314.11]], "area": 26824.77645, "iscrowd": 0, "image_id": 174700, "bbox": [0.0, 73.25, 209.82, 240.86], "category_id": 17, "id": 1816336, "split": "val", "sentences": [{"tokens": ["cat", "on", "left", "side"], "raw": "cat on left side", "sent_id": 4475, "sent": "cat on left side"}, {"tokens": ["a", "black", "and", "white", "cat", "sleeping", "to", "the", "left", "of", "two", "other", "cats"], "raw": "A black and white cat sleeping to the left of two other cats.", "sent_id": 4476, "sent": "a black and white cat sleeping to the left of two other cats"}], "file_name": "COCO_train2014_000000174700_1816336.jpg", "ann_id": 1816336, "sent_ids": [4475, 4476], "ref_id": 45507}, {"segmentation": [[137.85, 342.71, 113.92, 287.19, 101.47, 340.8, 87.11, 340.8, 101.47, 290.06, 99.56, 249.86, 79.46, 206.78, 90.94, 184.76, 64.14, 89.99, 51.69, 85.2, 39.25, 94.77, 28.72, 97.64, 27.76, 88.07, 36.38, 72.76, 40.21, 62.22, 46.91, 55.52, 59.35, 45.95, 64.14, 55.52, 73.71, 67.97, 90.94, 122.53, 115.83, 150.3, 142.64, 185.72, 164.66, 193.38, 152.21, 208.69, 167.53, 226.88, 175.19, 247.94, 168.49, 270.92, 167.53, 291.02, 166.57, 340.8, 159.87, 345.59, 148.38, 316.87, 149.34, 271.87, 129.24, 238.37, 118.71, 246.03, 150.3, 336.97]], "area": 13318.088150000001, "iscrowd": 0, "image_id": 526713, "bbox": [27.76, 45.95, 147.43, 299.64], "category_id": 25, "id": 600764, "split": "val", "sentences": [{"tokens": ["giraffe", "to", "the", "far", "left"], "raw": "Giraffe to the far left.", "sent_id": 5525, "sent": "giraffe to the far left"}, {"tokens": ["the", "giraffe", "furthest", "left", "walking", "toward", "the", "photographer"], "raw": "The giraffe furthest left walking toward the photographer.", "sent_id": 5526, "sent": "the giraffe furthest left walking toward the photographer"}], "file_name": "COCO_train2014_000000526713_600764.jpg", "ann_id": 600764, "sent_ids": [5525, 5526], "ref_id": 45553}, {"segmentation": [[81.17, 349.99, 30.56, 337.58, 28.65, 310.84, 66.85, 259.27, 88.81, 234.44, 78.31, 179.05, 89.77, 120.8, 131.78, 93.11, 176.67, 93.11, 194.81, 128.44, 222.5, 178.1, 209.14, 223.94, 243.51, 239.22, 286.49, 310.84, 262.61, 326.12, 293.17, 322.3, 292.22, 347.13, 227.28, 361.45, 202.45, 354.77, 174.76, 357.63, 160.43, 339.49, 132.74, 343.31, 98.36, 350.95, 87.86, 341.4, 72.58, 347.13]], "area": 42201.58854999999, "iscrowd": 0, "image_id": 258071, "bbox": [28.65, 93.11, 264.52, 268.34], "category_id": 1, "id": 498436, "split": "val", "sentences": [{"tokens": ["a", "child", "cutting", "paper", "with", "safety", "scissors", "next", "to", "her", "mom"], "raw": "A child cutting paper with safety scissors next to her mom", "sent_id": 5795, "sent": "a child cutting paper with safety scissors next to her mom"}, {"tokens": ["a", "young", "girl", "with", "a", "white", "shirt", "using", "scissors", "beside", "her", "mom"], "raw": "A young girl with a white shirt using scissors beside her mom.", "sent_id": 5796, "sent": "a young girl with a white shirt using scissors beside her mom"}], "file_name": "COCO_train2014_000000258071_498436.jpg", "ann_id": 498436, "sent_ids": [5795, 5796], "ref_id": 45562}, {"segmentation": [[192.72, 388.31, 188.4, 428.58, 174.02, 471.73, 169.71, 516.31, 165.39, 562.34, 146.7, 547.96, 132.31, 506.25, 128.0, 471.73, 104.99, 513.44, 97.8, 542.2, 73.35, 540.76, 44.58, 520.63, 43.15, 503.37, 69.03, 484.67, 87.73, 458.79, 102.11, 418.52, 100.67, 399.82, 81.98, 330.79, 87.73, 289.08, 93.48, 264.63, 92.04, 224.36, 86.29, 166.83, 102.11, 152.45, 94.92, 76.22, 120.81, 37.39, 140.94, 38.83, 161.08, 47.46, 184.09, 60.4, 195.6, 96.36, 197.03, 145.26, 227.24, 153.89, 234.43, 189.84, 235.87, 212.85, 221.48, 230.11, 207.1, 254.56, 201.35, 266.07, 182.65, 280.45, 171.15, 299.15, 171.15, 339.42, 179.78, 343.73, 186.97, 356.67, 189.84, 392.63]], "area": 50514.47785000001, "iscrowd": 0, "image_id": 490610, "bbox": [43.15, 37.39, 192.72, 524.95], "category_id": 1, "id": 214754, "split": "val", "sentences": [{"tokens": ["a", "lady", "wearing", "a", "black", "dress", "side", "of", "the", "baby", "sitting", "in", "the", "ship"], "raw": "A lady wearing a black dress side of the baby sitting in the ship.", "sent_id": 5834, "sent": "a lady wearing a black dress side of the baby sitting in the ship"}, {"tokens": ["a", "woman", "wearing", "glasses"], "raw": "a woman wearing glasses", "sent_id": 5835, "sent": "a woman wearing glasses"}], "file_name": "COCO_train2014_000000490610_214754.jpg", "ann_id": 214754, "sent_ids": [5834, 5835], "ref_id": 45564}, {"segmentation": [[341.35, 248.51, 591.89, 231.49, 612.16, 238.78, 616.22, 276.89, 603.24, 305.27, 566.76, 306.08, 562.7, 310.95, 544.86, 311.76, 537.57, 308.51, 424.86, 316.62, 403.78, 319.05, 354.32, 317.43, 335.68, 303.65, 340.54, 246.89]], "area": 19974.00385, "iscrowd": 0, "image_id": 147303, "bbox": [335.68, 231.49, 280.54, 87.56], "category_id": 6, "id": 165363, "split": "val", "sentences": [{"tokens": ["a", "bus", "in", "front", "of", "others"], "raw": "a bus in front of others", "sent_id": 5878, "sent": "a bus in front of others"}, {"tokens": ["the", "bus", "has", "a", "violet", "colour", "only", "in", "bottom"], "raw": "The bus has a violet colour only in bottom", "sent_id": 5879, "sent": "the bus has a violet colour only in bottom"}], "file_name": "COCO_train2014_000000147303_165363.jpg", "ann_id": 165363, "sent_ids": [5878, 5879], "ref_id": 45566}, {"segmentation": [[516.67, 254.4, 502.71, 230.76, 509.15, 182.43, 496.26, 169.54, 503.78, 113.68, 640.0, 126.57, 640.0, 273.73]], "area": 19463.193400000004, "iscrowd": 0, "image_id": 155107, "bbox": [496.26, 113.68, 143.74, 160.05], "category_id": 73, "id": 1102106, "split": "val", "sentences": [{"tokens": ["a", "white", "color", "laptop", "is", "on", "a", "table"], "raw": "a white color laptop is on a table", "sent_id": 8360, "sent": "a white color laptop is on a table"}, {"tokens": ["a", "small", "white", "laptop"], "raw": "A small white laptop.", "sent_id": 8361, "sent": "a small white laptop"}], "file_name": "COCO_train2014_000000155107_1102106.jpg", "ann_id": 1102106, "sent_ids": [8360, 8361], "ref_id": 45659}, {"segmentation": [[178.5, 194.76, 195.55, 216.58, 203.05, 226.12, 213.96, 227.49, 224.87, 242.49, 237.82, 252.72, 243.96, 252.72, 269.19, 260.22, 292.37, 285.44, 298.51, 292.26, 306.69, 305.9, 316.92, 314.08, 329.87, 313.4, 327.83, 291.58, 319.65, 275.9, 306.01, 253.4, 282.83, 230.21, 280.1, 218.62, 269.19, 208.4, 261.69, 189.99, 256.92, 170.89, 252.82, 147.71, 250.78, 140.21, 253.51, 135.44, 254.87, 130.67, 266.46, 128.62, 275.33, 114.98, 280.1, 107.48, 276.01, 97.94, 275.33, 91.8, 266.46, 74.07, 258.96, 62.48, 239.19, 60.44, 226.23, 64.53, 216.69, 78.85, 213.28, 94.53, 222.82, 113.62, 213.28, 123.17, 205.1, 127.26, 186.0, 149.76, 179.87, 183.85, 178.5, 190.67], [158.05, 293.63, 160.09, 307.26, 171.69, 350.22, 177.14, 411.59, 178.5, 425.9, 172.37, 457.95, 166.91, 480.45, 161.46, 500.22, 158.73, 509.09, 161.46, 523.41, 180.55, 522.73, 177.82, 528.18, 180.55, 535.0, 203.05, 538.41, 235.1, 542.5, 258.96, 537.04, 265.1, 526.82, 262.37, 516.59, 235.1, 506.36, 232.37, 498.86, 220.1, 493.41, 220.78, 476.36, 239.19, 420.45, 242.6, 393.18, 237.82, 376.13, 239.19, 369.31, 215.32, 328.4, 190.78, 306.58, 188.05, 296.35, 168.28, 291.58]], "area": 29434.91809999999, "iscrowd": 0, "image_id": 316557, "bbox": [158.05, 60.44, 171.82, 482.06], "category_id": 1, "id": 511142, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "middle", "of", "the", "group", "of", "3"], "raw": "The man in the middle of the group of 3.", "sent_id": 8529, "sent": "the man in the middle of the group of 3"}, {"tokens": ["the", "person", "standing", "second", "from", "left"], "raw": "The person standing second from left.", "sent_id": 8530, "sent": "the person standing second from left"}], "file_name": "COCO_train2014_000000316557_511142.jpg", "ann_id": 511142, "sent_ids": [8529, 8530], "ref_id": 45666}, {"segmentation": [[478.92, 314.97, 581.39, 345.17, 594.34, 313.89, 594.34, 248.09, 593.26, 236.22, 605.12, 249.17, 610.52, 230.83, 582.47, 192.0, 555.51, 173.66, 549.03, 151.01, 533.93, 119.73, 525.3, 118.65, 506.97, 81.98, 486.47, 67.96, 458.43, 70.11, 434.7, 90.61, 419.6, 135.91, 427.15, 183.37, 436.85, 187.69, 410.97, 193.08, 378.61, 238.38, 375.37, 277.21, 384.0, 271.82, 409.89, 266.43, 450.88, 266.43, 472.45, 276.13, 475.69, 305.26, 475.69, 318.2]], "area": 36425.12545, "iscrowd": 0, "image_id": 159768, "bbox": [375.37, 67.96, 235.15, 277.21], "category_id": 1, "id": 427914, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "green", "and", "blue", "striped", "shirt"], "raw": "A woman in a green and blue striped shirt.", "sent_id": 8574, "sent": "a woman in a green and blue striped shirt"}, {"tokens": ["a", "woman", "in", "a", "green", "shirt", "sitting", "at", "the", "table"], "raw": "A woman in a green shirt sitting at the table.", "sent_id": 8575, "sent": "a woman in a green shirt sitting at the table"}], "file_name": "COCO_train2014_000000159768_427914.jpg", "ann_id": 427914, "sent_ids": [8574, 8575], "ref_id": 45669}, {"segmentation": [[164.74, 148.01, 168.07, 175.18, 172.51, 196.8, 174.17, 217.87, 174.72, 236.73, 177.5, 250.59, 153.76, 267.22, 122.15, 266.67, 92.26, 260.57, 75.63, 252.81, 55.21, 221.2, 43.02, 211.78, 56.88, 265.56, 48.01, 263.9, 33.59, 207.89, 37.47, 175.73, 41.91, 152.45, 51.89, 122.05, 63.53, 117.62, 89.04, 116.56, 105.12, 118.22, 147.26, 129.87]], "area": 17374.928399999997, "iscrowd": 0, "image_id": 252373, "bbox": [33.59, 116.56, 143.91, 150.66], "category_id": 27, "id": 1167087, "split": "val", "sentences": [{"tokens": ["the", "backpack", "with", "the", "water", "bottle", "in", "a", "side", "pocket"], "raw": "The backpack with the water bottle in a side pocket", "sent_id": 10070, "sent": "the backpack with the water bottle in a side pocket"}, {"tokens": ["the", "black", "luggage", "on", "the", "far", "-", "right", "with", "the", "water", "bottle"], "raw": "The black luggage on the far-right with the water bottle.", "sent_id": 10071, "sent": "the black luggage on the far - right with the water bottle"}], "file_name": "COCO_train2014_000000252373_1167087.jpg", "ann_id": 1167087, "sent_ids": [10070, 10071], "ref_id": 45722}, {"segmentation": [[201.86, 320.52, 218.75, 308.7, 223.82, 281.67, 213.68, 273.23, 207.77, 263.94, 202.7, 173.56, 19.43, 173.56, 46.45, 304.48, 49.83, 306.17, 49.83, 317.15, 55.74, 321.37, 202.7, 323.06]], "area": 25951.825100000002, "iscrowd": 0, "image_id": 304757, "bbox": [19.43, 173.56, 204.39, 149.5], "category_id": 73, "id": 1103622, "split": "val", "sentences": [{"tokens": ["a", "laptop", "with", "a", "black", "back"], "raw": "A laptop with a black back.", "sent_id": 10130, "sent": "a laptop with a black back"}, {"tokens": ["a", "large", "dell", "laptop", "silver", "with", "a", "dark", "cover"], "raw": "A large dell laptop silver with a dark cover.", "sent_id": 10131, "sent": "a large dell laptop silver with a dark cover"}], "file_name": "COCO_train2014_000000304757_1103622.jpg", "ann_id": 1103622, "sent_ids": [10130, 10131], "ref_id": 45726}, {"segmentation": [[467.3, 154.85, 478.39, 175.71, 484.61, 185.48, 498.37, 193.91, 503.7, 209.0, 503.7, 214.77, 503.25, 221.43, 486.38, 244.51, 483.28, 261.38, 481.06, 280.47, 480.61, 296.01, 477.95, 310.21, 479.73, 335.52, 467.3, 331.52, 468.18, 311.54, 467.74, 295.56, 470.4, 277.81, 473.07, 261.83, 468.63, 253.84, 465.96, 248.51, 463.3, 247.62, 459.75, 258.28, 461.97, 283.58, 461.97, 292.46, 456.2, 314.65, 456.2, 342.17, 448.21, 344.84, 446.43, 336.85, 450.87, 288.02, 450.43, 270.71, 445.1, 252.95, 441.55, 234.75, 443.33, 211.22, 448.21, 195.24, 448.21, 188.58, 449.1, 181.48, 451.32, 157.07, 451.76, 137.98, 453.98, 125.55, 455.31, 118.45, 452.65, 110.01, 442.88, 112.23, 429.12, 112.23, 422.02, 113.56, 412.7, 114.45, 414.03, 107.79, 420.24, 101.13, 424.68, 97.14, 435.78, 81.16, 437.55, 78.05, 444.21, 78.94, 444.66, 72.28, 447.76, 68.28, 449.1, 66.06, 451.32, 66.51, 452.2, 73.17, 458.42, 66.51, 461.97, 71.39, 460.19, 75.83, 458.86, 80.27, 464.63, 89.15, 468.63, 107.35, 468.18, 133.54]], "area": 8283.401200000004, "iscrowd": 0, "image_id": 171484, "bbox": [412.7, 66.06, 91.0, 278.78], "category_id": 25, "id": 597940, "split": "val", "sentences": [{"tokens": ["the", "giraffe", "standing", "to", "the", "right", "of", "two", "giraffes", "and", "to", "the", "left", "of", "one", "giraffe"], "raw": "The giraffe standing to the right of two giraffes and to the left of one giraffe.", "sent_id": 10138, "sent": "the giraffe standing to the right of two giraffes and to the left of one giraffe"}, {"tokens": ["tallest", "giraffe"], "raw": "tallest giraffe", "sent_id": 10139, "sent": "tallest giraffe"}], "file_name": "COCO_train2014_000000171484_597940.jpg", "ann_id": 597940, "sent_ids": [10138, 10139], "ref_id": 45727}, {"segmentation": [[5.4, 63.12, 28.05, 62.04, 60.42, 245.47, 173.72, 270.29, 231.99, 294.03, 6.47, 434.3]], "area": 30338.856949999998, "iscrowd": 0, "image_id": 155107, "bbox": [5.4, 62.04, 226.59, 372.26], "category_id": 73, "id": 1099755, "split": "val", "sentences": [{"tokens": ["a", "gray", "laptop", "next", "a", "white", "mac", "computer"], "raw": "A gray laptop next a white Mac computer.", "sent_id": 10442, "sent": "a gray laptop next a white mac computer"}, {"tokens": ["silver", "laptop", "computer"], "raw": "Silver laptop computer.", "sent_id": 10443, "sent": "silver laptop computer"}], "file_name": "COCO_train2014_000000155107_1099755.jpg", "ann_id": 1099755, "sent_ids": [10442, 10443], "ref_id": 45735}, {"segmentation": [[231.56, 325.46, 210.93, 338.99, 185.42, 358.3, 161.24, 354.08, 89.58, 331.89, 77.6, 326.57, 80.04, 320.8, 136.39, 283.97, 146.59, 287.3, 189.63, 308.16, 228.68, 316.59, 233.78, 317.7, 233.78, 321.25]], "area": 6228.092899999998, "iscrowd": 0, "image_id": 523309, "bbox": [77.6, 283.97, 156.18, 74.33], "category_id": 84, "id": 1652763, "split": "val", "sentences": [{"tokens": ["the", "top", "newspaper", ",", "on", "the", "table"], "raw": "The top newspaper, on the table.", "sent_id": 10959, "sent": "the top newspaper , on the table"}, {"tokens": ["a", "newspaper", "with", "tv", "remotes", "on", "top", "of", "it"], "raw": "A newspaper with tv remotes on top of it", "sent_id": 10960, "sent": "a newspaper with tv remotes on top of it"}], "file_name": "COCO_train2014_000000523309_1652763.jpg", "ann_id": 1652763, "sent_ids": [10959, 10960], "ref_id": 45753}, {"segmentation": [[171.18, 210.51, 171.64, 203.72, 177.52, 205.08, 184.31, 206.89, 187.48, 205.98, 188.39, 201.46, 192.01, 197.83, 196.09, 191.49, 201.07, 187.42, 200.16, 177.91, 201.52, 170.66, 201.52, 163.42, 195.18, 153.91, 185.67, 149.83, 180.69, 149.38, 169.37, 151.19, 161.67, 157.53, 157.14, 168.85, 152.62, 175.64, 150.35, 179.27, 146.73, 180.17, 129.97, 180.17, 118.65, 182.44, 105.52, 186.97, 92.84, 192.85, 80.16, 208.7, 64.31, 222.74, 57.52, 236.32, 56.62, 251.72, 57.97, 259.87, 61.14, 266.66, 63.41, 269.83, 66.58, 272.55, 64.31, 280.25, 60.24, 286.14, 58.88, 292.02, 57.97, 295.19, 61.14, 301.08, 64.77, 307.42, 65.67, 308.78, 62.5, 311.04, 57.97, 316.02, 52.99, 321.13, 51.18, 333.94, 57.07, 343.9, 57.07, 349.79, 76.54, 352.96, 85.14, 352.05, 82.88, 346.16, 77.45, 337.56, 77.9, 333.48, 82.43, 333.03, 88.77, 330.31, 89.22, 329.41, 102.8, 319.9, 115.03, 311.3, 118.65, 309.48, 118.2, 314.92, 116.39, 319.45, 115.48, 324.88, 115.94, 327.6, 118.65, 329.41, 112.77, 331.22, 111.86, 333.48, 112.31, 340.28, 117.75, 345.71, 117.75, 349.79, 125.45, 350.24, 140.84, 349.33, 143.11, 347.52, 139.94, 342.09, 139.94, 337.56, 139.94, 333.94, 141.75, 328.05, 142.2, 321.26, 140.39, 315.82, 140.39, 313.11, 146.73, 305.86, 154.88, 278.69, 154.88, 257.86, 152.62, 247.9, 148.54, 245.18, 146.93, 243.31, 152.12, 236.17, 157.32, 227.4, 165.43, 221.56, 171.28, 211.49, 171.6, 206.3]], "area": 15882.64795, "iscrowd": 0, "image_id": 536244, "bbox": [51.18, 149.38, 150.34, 203.58], "category_id": 1, "id": 428131, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "purple", "shirt", "is", "riding", "on", "a", "skateboard", "as", "his", "picture", "is", "being", "taken"], "raw": "A man in a purple shirt is riding on a skateboard as his picture is being taken", "sent_id": 11239, "sent": "a man in a purple shirt is riding on a skateboard as his picture is being taken"}, {"tokens": ["a", "man", "in", "a", "purple", "t", "-", "shirt", "is", "crouching", "down"], "raw": "A man in a purple t-shirt is crouching down.", "sent_id": 11240, "sent": "a man in a purple t - shirt is crouching down"}], "file_name": "COCO_train2014_000000536244_428131.jpg", "ann_id": 428131, "sent_ids": [11239, 11240], "ref_id": 45769}, {"segmentation": [[106.43, 404.49, 222.92, 371.42, 286.2, 369.98, 401.26, 428.94, 382.56, 449.08, 263.19, 444.76, 155.33, 433.26]], "area": 14780.291949999995, "iscrowd": 0, "image_id": 101892, "bbox": [106.43, 369.98, 294.83, 79.1], "category_id": 28, "id": 280255, "split": "val", "sentences": [{"tokens": ["beach", "umbrella", "on", "the", "beach", ","], "raw": "Beach umbrella on the beach,", "sent_id": 12278, "sent": "beach umbrella on the beach ,"}], "file_name": "COCO_train2014_000000101892_280255.jpg", "ann_id": 280255, "sent_ids": [12278], "ref_id": 45819}, {"segmentation": [[0.0, 169.13, 96.0, 167.63, 98.25, 151.13, 108.0, 137.63, 111.75, 133.13, 116.25, 124.88, 126.0, 127.13, 132.0, 125.62, 136.5, 115.13, 176.25, 118.13, 175.5, 133.13, 187.5, 142.13, 194.25, 142.13, 196.5, 166.88, 197.25, 178.13, 195.0, 189.38, 0.0, 199.88], [207.0, 140.63, 219.0, 142.13, 220.5, 172.88, 217.5, 175.88, 212.25, 174.38, 207.0, 169.87, 208.5, 163.13, 210.75, 154.88, 205.5, 153.38, 207.75, 148.13, 206.25, 145.88]], "area": 9578.0025, "iscrowd": 0, "image_id": 393394, "bbox": [0.0, 115.13, 220.5, 84.75], "category_id": 65, "id": 316230, "split": "val", "sentences": [{"tokens": ["bed", "on", "the", "other", "side", "of", "the", "lamp"], "raw": "bed on the other side of the lamp", "sent_id": 13214, "sent": "bed on the other side of the lamp"}, {"tokens": ["the", "bed", "that", "is", "farthest", "away", "from", "the", "flower", "vase"], "raw": "the bed that is farthest away from the flower vase", "sent_id": 13215, "sent": "the bed that is farthest away from the flower vase"}], "file_name": "COCO_train2014_000000393394_316230.jpg", "ann_id": 316230, "sent_ids": [13214, 13215], "ref_id": 45857}, {"segmentation": [[380.87, 410.69, 400.11, 385.68, 410.69, 326.05, 415.5, 284.69, 415.5, 257.76, 408.76, 229.87, 414.53, 206.79, 406.84, 192.36, 408.76, 174.09, 413.57, 165.43, 434.73, 177.93, 442.43, 210.63, 455.89, 231.79, 453.97, 274.11, 448.2, 335.67, 439.54, 400.11, 441.47, 414.53, 421.27, 408.76, 406.84, 416.46, 383.76, 416.46, 382.8, 415.5]], "area": 9471.172300000004, "iscrowd": 0, "image_id": 476651, "bbox": [380.87, 165.43, 75.02, 251.03], "category_id": 1, "id": 1709086, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "sports", "dress", "and", "a", "bat", "in", "his", "hand"], "raw": "A man wearing sports dress and a bat in his hand", "sent_id": 13297, "sent": "a man wearing sports dress and a bat in his hand"}, {"tokens": ["a", "man", "wearing", "a", "yellow", "sweatband", "on", "his", "head"], "raw": "A man wearing a yellow sweatband on his head.", "sent_id": 13298, "sent": "a man wearing a yellow sweatband on his head"}], "file_name": "COCO_train2014_000000476651_1709086.jpg", "ann_id": 1709086, "sent_ids": [13297, 13298], "ref_id": 45864}, {"segmentation": [[121.21, 119.93, 113.51, 143.01, 117.36, 148.78, 117.36, 162.25, 111.59, 179.57, 121.21, 205.54, 123.13, 225.74, 119.28, 231.51, 36.55, 233.44, 27.9, 235.36, 28.86, 226.7, 22.13, 226.7, 1.92, 256.52, 0.0, 104.53, 27.9, 61.25, 7.7, 55.47, 5.77, 54.51, 4.81, 47.78, 13.47, 46.82, 17.32, 40.08, 32.71, 42.97, 36.55, 41.04, 17.32, 23.73, 26.94, 15.07, 40.4, 27.58, 38.48, 34.31, 47.14, 44.89, 70.22, 29.5, 86.58, 28.54, 117.36, 42.97, 126.98, 79.52, 92.35, 87.22, 74.07, 92.03, 75.03, 104.53, 80.81, 114.15, 90.43, 118.0]], "area": 21351.80455, "iscrowd": 0, "image_id": 268428, "bbox": [0.0, 15.07, 126.98, 241.45], "category_id": 4, "id": 153648, "split": "val", "sentences": [{"tokens": ["a", "blue", "motercycle"], "raw": "a blue motercycle", "sent_id": 13754, "sent": "a blue motercycle"}, {"tokens": ["the", "front", "of", "the", "bright", "blue", "motorcycle"], "raw": "The front of the bright blue motorcycle.", "sent_id": 13755, "sent": "the front of the bright blue motorcycle"}], "file_name": "COCO_train2014_000000268428_153648.jpg", "ann_id": 153648, "sent_ids": [13754, 13755], "ref_id": 45885}, {"segmentation": [[480.43, 379.16, 465.12, 362.68, 455.95, 353.26, 433.58, 333.25, 424.16, 327.36, 422.98, 315.58, 422.98, 301.45, 420.62, 293.21, 419.45, 289.68, 412.38, 288.5, 408.85, 296.74, 406.49, 303.81, 401.78, 315.58, 401.78, 316.76, 378.23, 302.63, 368.81, 303.81, 387.65, 323.83, 387.65, 323.83, 397.07, 332.07, 399.43, 334.42, 417.09, 356.8, 427.69, 363.86, 454.77, 394.48, 499.52, 426.27, 495.99, 409.79]], "area": 4162.355950000002, "iscrowd": 0, "image_id": 223459, "bbox": [368.81, 288.5, 130.71, 137.77], "category_id": 5, "id": 160922, "split": "val", "sentences": [{"tokens": ["four", "blue", "jets", "flying", "close", "to", "each", "other"], "raw": "Four blue jets flying close to each other.", "sent_id": 13949, "sent": "four blue jets flying close to each other"}, {"tokens": ["a", "second", "plane", "which", "is", "not", "forming", "foam"], "raw": "A second plane which is not forming foam.", "sent_id": 13950, "sent": "a second plane which is not forming foam"}], "file_name": "COCO_train2014_000000223459_160922.jpg", "ann_id": 160922, "sent_ids": [13949, 13950], "ref_id": 45888}, {"segmentation": [[130.55, 237.39, 139.13, 233.58, 145.8, 232.62, 150.56, 231.67, 163.9, 232.62, 165.81, 232.62, 171.52, 238.34, 174.38, 240.25, 235.37, 246.92, 236.32, 242.15, 240.13, 238.34, 245.85, 232.62, 249.66, 229.76, 259.19, 225.95, 264.91, 225.95, 265.86, 225.0, 248.71, 217.38, 241.09, 210.71, 237.28, 206.89, 238.23, 202.13, 241.09, 189.74, 237.28, 165.92, 224.89, 148.77, 217.26, 138.28, 211.55, 128.75, 205.83, 125.9, 196.3, 125.9, 191.54, 125.9, 175.34, 130.66, 165.81, 141.14, 155.33, 152.58, 150.56, 164.01, 150.56, 168.78, 142.94, 189.74, 142.94, 204.99, 141.03, 215.47, 140.08, 219.28, 140.08, 221.19]], "area": 9856.3278, "iscrowd": 0, "image_id": 342374, "bbox": [130.55, 125.9, 135.31, 121.02], "category_id": 1, "id": 467796, "split": "val", "sentences": [{"tokens": ["smallest", "girl", "in", "blue", "smock", "across", "the", "table"], "raw": "smallest girl in blue smock across the table", "sent_id": 14494, "sent": "smallest girl in blue smock across the table"}, {"tokens": ["little", "girl", "wuth", "blue", "vest"], "raw": "little girl wuth blue vest", "sent_id": 14495, "sent": "little girl wuth blue vest"}], "file_name": "COCO_train2014_000000342374_467796.jpg", "ann_id": 467796, "sent_ids": [14494, 14495], "ref_id": 45909}, {"segmentation": [[66.96, 261.5, 46.08, 266.24, 32.8, 256.76, 31.85, 249.16, 35.64, 235.88, 39.44, 227.34, 63.16, 218.8, 97.32, 206.47, 129.58, 194.13, 159.0, 187.49, 169.43, 181.8, 177.02, 175.15, 199.8, 181.8, 214.98, 185.59, 230.16, 195.08, 238.7, 215.01, 226.37, 221.65, 214.98, 230.19, 201.7, 229.24, 191.26, 228.29, 179.87, 230.19, 171.33, 233.03, 166.59, 245.37, 160.89, 250.11, 144.76, 252.01, 132.43, 260.55, 119.14, 260.55, 85.93, 264.35]], "area": 10233.20575, "iscrowd": 0, "image_id": 209603, "bbox": [31.85, 175.15, 206.85, 91.09], "category_id": 59, "id": 1075744, "split": "val", "sentences": [{"tokens": ["the", "pizza", "on", "the", "upper", "left", "looks", "hot"], "raw": "The pizza on the upper left looks hot.", "sent_id": 15262, "sent": "the pizza on the upper left looks hot"}, {"tokens": ["a", "calzone", "sitting", "on", "a", "pan", "to", "the", "left", "of", "another", "calzone", "and", "it", "is", "by", "the", "edge", "of", "the", "table"], "raw": "A calzone sitting on a pan to the left of another calzone and it is by the edge of the table.", "sent_id": 15263, "sent": "a calzone sitting on a pan to the left of another calzone and it is by the edge of the table"}], "file_name": "COCO_train2014_000000209603_1075744.jpg", "ann_id": 1075744, "sent_ids": [15262, 15263], "ref_id": 45942}, {"segmentation": [[480.0, 368.29, 468.47, 348.11, 448.29, 329.37, 428.11, 327.93, 370.45, 356.76, 366.13, 397.12, 357.48, 415.86, 337.3, 437.48, 321.44, 450.45, 318.56, 474.95, 325.77, 505.23, 348.83, 541.26, 360.36, 568.65, 369.01, 604.68, 377.66, 633.51, 472.79, 633.51, 480.0, 632.07]], "area": 37790.08625, "iscrowd": 0, "image_id": 339051, "bbox": [318.56, 327.93, 161.44, 305.58], "category_id": 1, "id": 1240840, "split": "val", "sentences": [{"tokens": ["a", "woman", "or", "girl", "in", "a", "red", "shirt", "with", "brown", "hair"], "raw": "A woman or girl in a red shirt with brown hair", "sent_id": 15309, "sent": "a woman or girl in a red shirt with brown hair"}, {"tokens": ["a", "person", "in", "a", "red", "shirt", "by", "the", "refridgerator"], "raw": "A person in a red shirt by the refridgerator.", "sent_id": 15310, "sent": "a person in a red shirt by the refridgerator"}], "file_name": "COCO_train2014_000000339051_1240840.jpg", "ann_id": 1240840, "sent_ids": [15309, 15310], "ref_id": 45944}, {"segmentation": [[147.19, 211.03, 172.01, 202.76, 207.19, 197.24, 238.22, 200.69, 263.74, 215.17, 268.56, 222.07, 268.56, 231.03, 265.81, 244.83, 253.39, 285.52, 242.36, 299.31, 219.6, 307.58, 192.01, 311.03, 173.39, 311.03, 155.46, 296.55, 144.43, 284.14, 136.15, 257.93, 128.57, 246.9, 127.19, 235.86, 129.26, 224.14, 149.26, 211.03]], "area": 12448.562399999999, "iscrowd": 0, "image_id": 16243, "bbox": [127.19, 197.24, 141.37, 113.79], "category_id": 51, "id": 710147, "split": "val", "sentences": [{"tokens": ["a", "clear", "mixing", "bowl", "full", "of", "chocolate", "mix"], "raw": "A clear mixing bowl full of  chocolate mix", "sent_id": 15382, "sent": "a clear mixing bowl full of chocolate mix"}, {"tokens": ["the", "bowl", "with", "a", "spoon", "sticking", "out", "of", "it", "with", "brown", "frosting", "in", "it"], "raw": "The bowl with a spoon sticking out of it with brown frosting in it.", "sent_id": 15383, "sent": "the bowl with a spoon sticking out of it with brown frosting in it"}], "file_name": "COCO_train2014_000000016243_710147.jpg", "ann_id": 710147, "sent_ids": [15382, 15383], "ref_id": 45948}, {"segmentation": [[461.65, 293.37, 454.83, 276.31, 442.32, 228.55, 452.56, 201.26, 467.34, 194.44, 493.49, 197.85, 524.19, 189.89, 565.13, 187.62, 617.43, 187.62, 639.04, 200.13, 639.04, 355.91, 635.63, 355.91, 631.08, 333.16, 595.83, 325.2, 592.42, 279.72, 573.09, 243.33, 548.07, 228.55, 531.02, 233.1, 528.74, 244.47, 534.43, 307.01, 524.19, 346.81, 500.31, 345.67, 499.18, 310.42, 498.04, 271.76, 492.36, 268.35, 479.85, 293.37, 471.89, 299.05, 457.11, 274.04]], "area": 19121.386199999994, "iscrowd": 0, "image_id": 4477, "bbox": [442.32, 187.62, 196.72, 168.29], "category_id": 22, "id": 582924, "split": "val", "sentences": [{"tokens": ["the", "elephant", "behind", "the", "trunk"], "raw": "the elephant behind the trunk", "sent_id": 16917, "sent": "the elephant behind the trunk"}, {"tokens": ["the", "elephant", "behind", "the", "front", "one"], "raw": "The elephant behind the front one.", "sent_id": 16918, "sent": "the elephant behind the front one"}], "file_name": "COCO_train2014_000000004477_582924.jpg", "ann_id": 582924, "sent_ids": [16917, 16918], "ref_id": 46009}, {"segmentation": [[0.96, 17.29, 84.06, 74.6, 106.99, 83.2, 155.71, 135.74, 203.47, 192.1, 238.81, 232.22, 254.1, 258.97, 269.38, 276.16, 282.76, 248.46, 302.82, 252.28, 304.73, 260.88, 279.89, 294.31, 274.16, 327.75, 274.16, 362.13, 260.79, 367.87, 245.5, 411.81, 191.05, 420.41, 177.68, 377.42, 165.26, 333.48, 165.26, 297.18, 121.32, 237.95, 64.96, 184.46, 39.17, 165.35, 19.11, 154.84, 0.0, 145.29]], "area": 42943.1896, "iscrowd": 0, "image_id": 427461, "bbox": [0.0, 17.29, 304.73, 403.12], "category_id": 25, "id": 599153, "split": "val", "sentences": [{"tokens": ["a", "giraffe", "bends", "over", "to", "stick", "its", "nose", "into", "a", "cage"], "raw": "A giraffe bends over to stick its nose into a cage.", "sent_id": 17868, "sent": "a giraffe bends over to stick its nose into a cage"}, {"tokens": ["the", "neck", "and", "face", "of", "a", "giraffe", "with", "its", "head", "in", "a", "feeding", "trough"], "raw": "The neck and face of a giraffe with its head in a feeding trough.", "sent_id": 17869, "sent": "the neck and face of a giraffe with its head in a feeding trough"}], "file_name": "COCO_train2014_000000427461_599153.jpg", "ann_id": 599153, "sent_ids": [17868, 17869], "ref_id": 46051}, {"segmentation": [[20.15, 341.6, 20.15, 332.96, 11.51, 323.37, 14.39, 309.93, 30.71, 303.22, 34.54, 256.2, 60.45, 212.06, 145.85, 211.1, 222.62, 222.62, 356.95, 254.28, 369.43, 261.0, 377.1, 265.8, 447.15, 282.11, 452.91, 286.91, 462.5, 325.29, 457.71, 337.76, 376.14, 346.4, 267.71, 354.07, 163.12, 364.63, 125.7, 360.79, 67.17, 357.91, 29.75, 351.2, 16.31, 345.44]], "area": 50320.76345, "iscrowd": 0, "image_id": 240911, "bbox": [11.51, 211.1, 450.99, 153.53], "category_id": 7, "id": 171692, "split": "val", "sentences": [{"tokens": ["the", "front", "train", "cart", "that", "'", "s", "yellow", "and", "gray", "with", "a", "navy", "blue", "wavy", "banner", "painted", "on", "it"], "raw": "The front train cart that's yellow and gray with a navy blue wavy banner painted on it.", "sent_id": 18403, "sent": "the front train cart that ' s yellow and gray with a navy blue wavy banner painted on it"}, {"tokens": ["a", "large", "train", "with", "moving", "europe", "painted", "on", "the", "side"], "raw": "A large train with Moving Europe painted on the side.", "sent_id": 18404, "sent": "a large train with moving europe painted on the side"}], "file_name": "COCO_train2014_000000240911_171692.jpg", "ann_id": 171692, "sent_ids": [18403, 18404], "ref_id": 46071}, {"segmentation": [[610.27, 421.24, 581.49, 377.1, 579.57, 365.59, 554.62, 331.04, 539.27, 327.21, 526.79, 308.98, 512.88, 291.66, 512.88, 286.65, 497.84, 269.94, 489.91, 267.02, 481.55, 249.06, 481.13, 234.86, 473.62, 226.51, 469.02, 221.91, 470.69, 215.23, 456.91, 171.79, 456.91, 160.51, 446.28, 151.94, 440.38, 151.49, 436.75, 136.51, 432.21, 130.61, 429.94, 119.26, 422.68, 113.36, 409.97, 111.09, 406.33, 107.46, 401.34, 129.25, 399.07, 136.06, 391.81, 144.68, 384.55, 154.21, 375.02, 154.21, 375.02, 157.84, 367.3, 158.75, 356.86, 161.47, 350.51, 173.73, 350.05, 177.82, 360.04, 180.99, 368.66, 213.22, 374.11, 241.36, 387.27, 278.13, 387.01, 296.92, 398.4, 329.2, 416.89, 356.15, 410.99, 363.41, 413.26, 373.4, 403.73, 399.72, 396.47, 426.96, 612.52, 427.0]], "area": 38428.07244999999, "iscrowd": 0, "image_id": 538737, "bbox": [350.05, 107.46, 262.47, 319.54], "category_id": 23, "id": 587134, "split": "val", "sentences": [{"tokens": ["polar", "bear", "on", "right"], "raw": "polar bear on right", "sent_id": 18503, "sent": "polar bear on right"}, {"tokens": ["the", "polar", "bear", "on", "the", "right"], "raw": "The polar bear on the right.", "sent_id": 18504, "sent": "the polar bear on the right"}], "file_name": "COCO_train2014_000000538737_587134.jpg", "ann_id": 587134, "sent_ids": [18503, 18504], "ref_id": 46077}, {"segmentation": [[99.79, 389.58, 92.12, 363.67, 72.93, 342.56, 84.44, 208.22, 89.24, 164.08, 103.63, 142.01, 182.31, 114.19, 206.3, 69.09, 265.8, 43.18, 301.3, 88.28, 306.1, 136.26, 296.5, 163.12, 262.92, 165.04, 244.69, 197.67, 237.01, 215.9, 242.77, 263.88, 265.8, 290.74, 283.07, 275.39, 334.88, 348.32, 300.34, 327.21, 261.96, 312.81, 213.02, 318.57, 218.78, 353.11, 168.88, 360.79, 147.77, 383.82, 117.07, 388.62]], "area": 49652.386750000005, "iscrowd": 0, "image_id": 511930, "bbox": [72.93, 43.18, 261.95, 346.4], "category_id": 1, "id": 500620, "split": "val", "sentences": [{"tokens": ["a", "man", "serving", "soup"], "raw": "A man serving soup", "sent_id": 19308, "sent": "a man serving soup"}, {"tokens": ["a", "man", "with", "a", "white", "shirt", "and", "navy", "apron", "preparing", "food"], "raw": "A man with a white shirt and navy apron preparing food.", "sent_id": 19309, "sent": "a man with a white shirt and navy apron preparing food"}], "file_name": "COCO_train2014_000000511930_500620.jpg", "ann_id": 500620, "sent_ids": [19308, 19309], "ref_id": 46114}, {"segmentation": [[278.29, 338.7, 282.61, 333.3, 283.69, 320.36, 284.76, 303.1, 283.69, 268.58, 289.08, 244.85, 299.87, 224.36, 308.49, 217.89, 332.22, 225.44, 357.03, 237.3, 367.82, 240.54, 380.76, 243.78, 390.47, 247.01, 389.39, 238.38, 415.28, 258.88, 424.99, 243.78, 416.36, 226.52, 417.44, 221.12, 428.22, 214.65, 449.8, 195.24, 444.4, 181.21, 457.35, 157.48, 458.43, 147.78, 448.72, 134.83, 448.72, 121.89, 451.96, 112.18, 464.9, 96.0, 478.92, 86.29, 490.79, 84.13, 503.73, 88.45, 523.15, 100.31, 532.85, 128.36, 545.8, 185.53, 553.35, 217.89, 557.66, 229.75, 551.19, 252.4, 518.83, 312.81, 403.42, 278.29, 380.76, 266.43, 361.35, 269.66, 353.8, 269.66, 367.82, 277.21, 368.9, 289.08, 366.74, 295.55, 363.51, 308.49, 353.8, 324.67, 351.64, 331.15, 334.38, 323.6, 328.99, 328.99, 326.83, 358.11, 324.67, 360.27, 307.42, 360.27, 311.73, 395.87, 304.18, 417.44, 302.02, 419.6, 295.55, 421.75, 285.84, 402.34, 279.37, 391.55, 273.98, 382.92, 271.82, 374.29, 271.82, 363.51, 271.82, 339.78, 282.61, 327.91], [373.21, 334.38, 401.26, 353.8, 428.22, 371.06, 486.47, 364.58, 502.65, 352.72, 496.18, 339.78, 463.82, 319.28, 399.1, 290.16, 376.45, 334.38]], "area": 39953.7936, "iscrowd": 0, "image_id": 337808, "bbox": [271.82, 84.13, 285.84, 337.62], "category_id": 1, "id": 522626, "split": "val", "sentences": [{"tokens": ["girl", "in", "a", "white", "coat", "with", "her", "hood", "up", ",", "sits", "in", "a", "rocking", "chair", "reading"], "raw": "girl in a white coat with her hood up, sits in a rocking chair reading", "sent_id": 19523, "sent": "girl in a white coat with her hood up , sits in a rocking chair reading"}, {"tokens": ["a", "woman", "wearing", "a", "beige", "coat", "with", "a", "hood"], "raw": "A woman wearing a beige coat with a hood.", "sent_id": 19524, "sent": "a woman wearing a beige coat with a hood"}], "file_name": "COCO_train2014_000000337808_522626.jpg", "ann_id": 522626, "sent_ids": [19523, 19524], "ref_id": 46123}, {"segmentation": [[624.4, 381.07, 627.48, 447.83, 405.65, 450.91, 278.31, 450.91, 138.64, 449.88, 81.13, 444.74, 135.56, 371.83, 149.94, 353.34, 167.4, 354.37, 193.07, 380.05, 302.96, 372.86, 363.55, 363.61, 442.62, 385.18, 498.08, 380.05, 602.83, 369.78]], "area": 39542.57175000002, "iscrowd": 0, "image_id": 210187, "bbox": [81.13, 353.34, 546.35, 97.57], "category_id": 67, "id": 392289, "split": "val", "sentences": [{"tokens": ["a", "book", "on", "table"], "raw": "a book on table", "sent_id": 19766, "sent": "a book on table"}, {"tokens": ["a", "fine", "wooden", "table", "in", "front", "of", "a", "girl"], "raw": "A fine wooden table in front of a girl", "sent_id": 19767, "sent": "a fine wooden table in front of a girl"}], "file_name": "COCO_train2014_000000210187_392289.jpg", "ann_id": 392289, "sent_ids": [19766, 19767], "ref_id": 46132}, {"segmentation": [[544.18, 163.99, 623.88, 18.32, 640.0, 24.74, 640.0, 258.35, 606.48, 327.06, 584.49, 341.72, 556.09, 420.5, 538.68, 417.75, 541.43, 409.51, 448.9, 419.59, 474.55, 344.46, 588.15, 323.39], [467.23, 249.19, 498.37, 329.81, 481.88, 336.22, 480.97, 345.38, 587.24, 321.56, 565.77, 233.56, 544.59, 304.73, 532.34, 295.89, 547.85, 264.76, 536.85, 230.86, 530.44, 259.26, 513.03, 282.17, 502.04, 284.0, 507.66, 268.89, 524.53, 249.53, 509.37, 227.2, 493.79, 219.87, 483.72, 220.79, 469.97, 233.61, 466.31, 246.44, 470.89, 255.6], [455.32, 225.37, 446.15, 210.71, 465.39, 211.63, 468.14, 218.95, 456.23, 229.95]], "area": 36475.55630000002, "iscrowd": 0, "image_id": 322121, "bbox": [446.15, 18.32, 193.85, 402.18], "category_id": 62, "id": 105901, "split": "val", "sentences": [{"tokens": ["a", "brown", "chair", "with", "a", "white", "padding", ",", "on", "which", "a", "grey", "cat", "is", "standing", "on"], "raw": "A brown chair with a white padding, on which a grey cat is standing on.", "sent_id": 20173, "sent": "a brown chair with a white padding , on which a grey cat is standing on"}, {"tokens": ["the", "chair", "that", "the", "cat", "is", "standing", "on"], "raw": "The chair that the cat is standing on.", "sent_id": 20174, "sent": "the chair that the cat is standing on"}], "file_name": "COCO_train2014_000000322121_105901.jpg", "ann_id": 105901, "sent_ids": [20173, 20174], "ref_id": 46146}, {"segmentation": [[468.45, 33.49, 461.7, 39.28, 453.99, 43.13, 437.6, 46.03, 428.93, 49.88, 423.14, 53.74, 425.07, 60.48, 432.78, 70.12, 437.6, 76.87, 453.99, 76.87, 458.81, 83.62, 463.63, 92.29, 463.63, 97.11, 458.81, 102.89, 456.88, 112.53, 452.06, 126.03, 451.1, 141.45, 448.21, 151.09, 438.57, 154.94, 431.82, 159.76, 424.11, 158.8, 413.51, 150.12, 403.87, 151.09, 399.05, 152.05, 391.34, 163.62, 394.23, 165.55, 404.83, 166.51, 410.61, 171.33, 419.29, 171.33, 420.25, 171.33, 439.53, 183.86, 455.92, 183.86, 466.52, 175.19, 472.3, 163.62, 480.01, 164.58, 482.91, 184.82, 495.44, 208.92, 491.58, 213.74, 470.37, 255.19, 453.02, 280.25, 449.17, 289.89, 449.17, 290.85, 499.29, 357.36, 489.65, 359.29, 477.12, 363.14, 473.27, 370.85, 475.19, 375.67, 486.76, 375.67, 506.04, 371.82, 500.26, 377.6, 500.26, 381.46, 507.0, 381.46, 524.35, 381.46, 548.45, 387.24, 564.84, 386.28, 574.47, 377.6, 574.47, 371.82, 558.09, 341.94, 530.14, 279.28, 574.47, 229.16, 574.47, 207.96, 567.73, 180.01, 540.74, 116.39, 526.28, 91.33, 504.11, 79.76, 500.26, 63.38, 492.54, 38.31, 480.98, 31.57, 470.37, 33.49]], "area": 29280.25975, "iscrowd": 0, "image_id": 95676, "bbox": [391.34, 31.57, 183.13, 355.67], "category_id": 1, "id": 505325, "split": "val", "sentences": [{"tokens": ["baseball", "player", "with", "glove"], "raw": "baseball player with glove", "sent_id": 20326, "sent": "baseball player with glove"}, {"tokens": ["a", "baseball", "player", "in", "a", "blue", "shirt", "with", "a", "mitt", "on"], "raw": "A baseball player in a blue shirt with a mitt on.", "sent_id": 20327, "sent": "a baseball player in a blue shirt with a mitt on"}], "file_name": "COCO_train2014_000000095676_505325.jpg", "ann_id": 505325, "sent_ids": [20326, 20327], "ref_id": 46158}, {"segmentation": [[165.03, 265.43, 178.79, 224.17, 181.54, 196.67, 188.41, 167.78, 211.79, 151.28, 215.92, 143.03, 215.92, 125.15, 210.42, 88.02, 224.17, 71.51, 244.8, 53.64, 270.93, 45.38, 291.56, 52.26, 302.56, 63.26, 309.44, 82.52, 309.44, 97.64, 323.19, 115.52, 334.19, 126.53, 349.32, 140.28, 372.7, 154.03, 372.7, 176.04, 372.7, 210.42, 371.33, 243.42, 358.95, 283.31, 356.2, 308.06, 365.82, 335.57, 363.07, 368.58, 354.82, 385.08, 346.57, 409.83, 336.94, 536.36, 330.07, 481.35, 308.06, 416.71, 310.81, 382.33, 302.56, 364.45, 279.18, 354.82, 248.93, 345.2, 222.8, 346.57, 222.8, 338.32, 213.17, 323.19, 203.54, 309.44, 189.79, 279.18, 177.41, 261.3], [138.9, 336.94, 123.78, 358.95, 137.53, 398.83, 163.66, 433.21]], "area": 51733.05015, "iscrowd": 0, "image_id": 313873, "bbox": [123.78, 45.38, 248.92, 490.98], "category_id": 1, "id": 487838, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "a", "red", "sweatshirt"], "raw": "A boy in a red sweatshirt.", "sent_id": 21023, "sent": "a boy in a red sweatshirt"}, {"tokens": ["the", "girl", "wearing", "the", "red", "shirt"], "raw": "The girl wearing the red shirt.", "sent_id": 21024, "sent": "the girl wearing the red shirt"}], "file_name": "COCO_train2014_000000313873_487838.jpg", "ann_id": 487838, "sent_ids": [21023, 21024], "ref_id": 46184}, {"segmentation": [[118.84, 198.54, 131.72, 172.77, 126.0, 141.27, 117.4, 122.65, 151.77, 101.18, 180.4, 98.31, 206.17, 135.54, 234.81, 175.63, 241.97, 220.01, 216.2, 272.99, 236.24, 334.56, 229.08, 356.03, 249.13, 411.87, 300.67, 464.85, 367.96, 502.07, 369.4, 527.84, 312.13, 555.05, 309.26, 553.62, 312.13, 533.57, 323.58, 519.25, 263.45, 477.73, 214.77, 457.69, 170.38, 384.67, 134.59, 407.58, 123.13, 416.17, 154.63, 497.78, 156.06, 527.84, 91.63, 540.73, 65.86, 542.16, 101.66, 504.94, 110.25, 477.73, 80.18, 417.6, 78.75, 390.4, 114.54, 347.44, 138.88, 333.12, 153.2, 301.63, 150.34, 293.04]], "area": 45460.31075, "iscrowd": 0, "image_id": 480240, "bbox": [65.86, 98.31, 303.54, 456.74], "category_id": 1, "id": 1729111, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "blue", "jersey", "number", "26", "is", "playing", "with", "baseball", "bat"], "raw": "a boy in blue jersey number 26 is playing with baseball bat.", "sent_id": 21253, "sent": "a boy in blue jersey number 26 is playing with baseball bat"}, {"tokens": ["the", "batter"], "raw": "the batter.", "sent_id": 21254, "sent": "the batter"}], "file_name": "COCO_train2014_000000480240_1729111.jpg", "ann_id": 1729111, "sent_ids": [21253, 21254], "ref_id": 46191}, {"segmentation": [[357.93, 323.56, 374.52, 269.04, 376.89, 231.11, 395.85, 224.0, 386.37, 162.37, 417.19, 124.44, 465.78, 137.48, 488.3, 195.56, 534.52, 242.96, 535.7, 324.74, 527.41, 350.81, 507.26, 359.11, 517.93, 399.41, 528.59, 448.0, 519.11, 471.7, 466.96, 471.7, 466.96, 433.78, 490.67, 427.85, 508.44, 404.15, 484.74, 395.85, 475.26, 341.33]], "area": 31727.190800000008, "iscrowd": 0, "image_id": 323728, "bbox": [357.93, 124.44, 177.77, 347.26], "category_id": 1, "id": 1745688, "split": "val", "sentences": [{"tokens": ["a", "lady", "sitting", "outside", "on", "her", "laptop"], "raw": "A lady sitting outside on her laptop.", "sent_id": 21280, "sent": "a lady sitting outside on her laptop"}, {"tokens": ["a", "smiling", "blonde", "lady", "with", "her", "shades", "set", "against", "her", "hair"], "raw": "A smiling blonde lady with her shades set against her hair.", "sent_id": 21281, "sent": "a smiling blonde lady with her shades set against her hair"}], "file_name": "COCO_train2014_000000323728_1745688.jpg", "ann_id": 1745688, "sent_ids": [21280, 21281], "ref_id": 46192}, {"segmentation": [[246.92, 265.93, 248.37, 209.0, 228.67, 209.73, 219.91, 202.43, 204.58, 201.7, 191.44, 211.92, 172.46, 213.38, 148.38, 201.7, 119.92, 196.59, 161.52, 163.02, 210.42, 148.42, 226.48, 144.77, 236.7, 142.58, 273.93, 144.04, 305.31, 151.34, 319.18, 157.18, 341.08, 168.85, 373.19, 203.89, 361.51, 203.16, 320.64, 206.81, 311.88, 186.38, 258.59, 184.92, 258.59, 195.87, 266.62, 200.97, 264.44, 210.46, 251.3, 210.46, 252.76, 266.66]], "area": 10718.550049999998, "iscrowd": 0, "image_id": 383929, "bbox": [119.92, 142.58, 253.27, 124.08], "category_id": 28, "id": 285302, "split": "val", "sentences": [{"tokens": ["pink", "umbrella", "carried", "by", "a", "girl", "with", "a", "boy"], "raw": "pink umbrella carried by a girl with a boy", "sent_id": 22027, "sent": "pink umbrella carried by a girl with a boy"}, {"tokens": ["a", "umbrella", "over", "some", "peoples", "heads"], "raw": "A umbrella over some peoples heads.", "sent_id": 22028, "sent": "a umbrella over some peoples heads"}], "file_name": "COCO_train2014_000000383929_285302.jpg", "ann_id": 285302, "sent_ids": [22027, 22028], "ref_id": 46221}, {"segmentation": [[33.97, 483.53, 37.89, 499.2, 78.39, 466.54, 87.53, 435.19, 116.28, 411.67, 121.5, 373.78, 105.83, 307.15, 197.28, 275.8, 194.67, 107.26, 135.87, 2.74, 20.9, 1.43, 0.0, 4.05, 0.0, 308.46, 23.52, 320.22, 15.68, 364.64, 13.06, 435.19, 26.13, 491.37]], "area": 70653.88525, "iscrowd": 0, "image_id": 438663, "bbox": [0.0, 1.43, 197.28, 497.77], "category_id": 8, "id": 398837, "split": "val", "sentences": [{"tokens": ["a", "food", "truck", "parked", "next", "to", "a", "smashed", "truck"], "raw": "A food truck parked next to a smashed truck.", "sent_id": 22150, "sent": "a food truck parked next to a smashed truck"}, {"tokens": ["truck", "on", "left", "hand", "side"], "raw": "truck on left hand side", "sent_id": 22151, "sent": "truck on left hand side"}], "file_name": "COCO_train2014_000000438663_398837.jpg", "ann_id": 398837, "sent_ids": [22150, 22151], "ref_id": 46228}, {"segmentation": [[36.92, 326.86, 35.0, 315.34, 39.8, 304.79, 55.15, 300.95, 85.85, 293.27, 108.88, 289.44, 120.4, 292.31, 152.06, 296.15, 188.53, 297.11, 221.15, 297.11, 238.42, 298.07, 249.94, 298.07, 275.84, 299.99, 300.79, 312.47, 305.59, 324.94, 291.2, 325.9, 261.45, 334.53, 239.38, 333.58, 225.95, 332.62, 187.57, 334.53, 159.74, 342.21, 143.43, 349.89, 125.2, 351.81, 116.56, 385.39, 116.56, 405.54, 111.76, 418.02, 90.65, 417.06, 61.87, 401.7, 55.15, 396.91, 46.51, 361.4, 39.8, 338.37, 34.04, 323.98]], "area": 15630.814399999994, "iscrowd": 0, "image_id": 50601, "bbox": [34.04, 289.44, 271.55, 128.58], "category_id": 23, "id": 1411540, "split": "val", "sentences": [{"tokens": ["water", "tub", "in", "zoo"], "raw": "water tub in zoo", "sent_id": 22234, "sent": "water tub in zoo"}, {"tokens": ["the", "black", "animal", "on", "the", "bottom", "left", "of", "the", "photo"], "raw": "the black animal on the bottom left of the photo", "sent_id": 22235, "sent": "the black animal on the bottom left of the photo"}], "file_name": "COCO_train2014_000000050601_1411540.jpg", "ann_id": 1411540, "sent_ids": [22234, 22235], "ref_id": 46233}, {"segmentation": [[313.82, 110.3, 316.45, 120.8, 316.45, 135.25, 329.58, 147.06, 347.96, 172.01, 355.84, 183.83, 375.54, 194.33, 389.98, 195.65, 399.17, 162.82, 409.68, 153.63, 424.12, 157.57, 433.31, 160.19, 439.88, 166.76, 442.5, 175.95, 442.5, 186.45, 435.94, 200.9, 429.37, 214.03, 435.94, 221.91, 439.88, 224.53, 447.75, 225.85, 454.32, 235.04, 453.01, 266.55, 464.82, 278.37, 476.64, 298.07, 481.89, 300.69, 489.77, 302.0, 495.02, 302.0, 501.59, 308.57, 504.22, 316.45, 498.96, 320.39, 491.09, 320.39, 489.77, 330.89, 479.27, 328.27, 430.68, 270.49, 422.81, 299.38, 425.43, 324.33, 435.94, 349.27, 442.5, 368.97, 462.2, 432.0, 470.08, 443.82, 485.83, 463.51, 512.09, 513.41, 525.23, 531.79, 535.73, 550.17, 534.42, 561.99, 530.48, 565.93, 521.29, 564.62, 510.78, 560.68, 497.65, 531.79, 451.69, 466.14, 438.56, 442.5, 425.43, 432.0, 409.68, 432.0, 392.61, 382.1, 387.35, 400.48, 393.92, 428.06, 393.92, 449.07, 392.61, 470.08, 397.86, 498.96, 397.86, 523.91, 405.74, 537.04, 400.48, 552.8, 395.23, 571.18, 388.67, 571.18, 376.85, 569.87, 371.6, 512.09, 366.34, 474.02, 363.72, 435.94, 345.34, 430.68, 338.77, 379.48, 334.83, 358.47, 351.9, 220.59, 292.81, 133.93, 290.19, 118.18, 296.75, 108.98, 311.2, 110.3]], "area": 36204.67454999998, "iscrowd": 0, "image_id": 382707, "bbox": [290.19, 108.98, 245.54, 462.2], "category_id": 1, "id": 463977, "split": "val", "sentences": [{"tokens": ["a", "tennis", "player", "in", "blue", "t", "-", "shirt", "and", "black", "shorts", "just", "after", "serving"], "raw": "A tennis player in blue t-shirt and black shorts just after serving.", "sent_id": 22727, "sent": "a tennis player in blue t - shirt and black shorts just after serving"}, {"tokens": ["a", "player", "with", "blue", "teashirt", "and", "black", "shorts", "is", "looking", "somewhere"], "raw": "A player with blue teashirt and black shorts is looking somewhere", "sent_id": 22728, "sent": "a player with blue teashirt and black shorts is looking somewhere"}], "file_name": "COCO_train2014_000000382707_463977.jpg", "ann_id": 463977, "sent_ids": [22727, 22728], "ref_id": 46251}, {"segmentation": [[361.89, 232.06, 372.77, 205.53, 384.34, 175.59, 401.35, 151.1, 414.27, 127.97, 421.08, 113.68, 429.92, 106.2, 438.08, 97.36, 437.4, 87.15, 431.28, 72.87, 438.08, 65.38, 445.57, 52.46, 453.05, 45.65, 467.34, 45.65, 474.82, 53.14, 478.22, 63.34, 480.26, 73.55, 478.9, 84.43, 476.86, 91.91, 481.62, 104.16, 511.56, 111.64, 529.93, 146.34, 544.89, 198.04, 544.89, 215.05, 549.66, 229.34, 553.06, 236.14, 546.93, 239.54, 535.37, 227.98, 526.53, 206.89, 519.72, 192.6, 514.28, 187.16, 515.64, 208.93, 519.72, 226.62, 507.48, 228.66, 499.31, 234.1, 495.23, 237.5, 494.55, 242.94, 498.63, 251.11, 488.43, 257.91, 481.62, 244.3, 478.22, 232.74, 471.42, 226.62, 460.54, 238.18, 449.65, 242.94, 440.13, 247.02, 435.36, 254.51, 428.56, 266.75, 414.95, 250.43, 420.4, 238.86, 424.48, 230.02, 429.24, 217.09, 435.36, 209.61, 440.13, 198.72, 441.49, 196.0, 438.08, 183.76, 436.04, 176.27, 426.52, 161.31, 426.52, 161.31, 408.15, 189.2, 387.06, 216.41, 379.58, 225.94, 377.54, 231.38, 370.05, 234.78]], "area": 18662.913499999995, "iscrowd": 0, "image_id": 269532, "bbox": [361.89, 45.65, 191.17, 221.1], "category_id": 1, "id": 217947, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "work", "shirt", "and", "jeans", "holding", "his", "hat", "and", "herding", "sheep"], "raw": "A man in a work shirt and jeans holding his hat and herding sheep.", "sent_id": 22739, "sent": "a man in a work shirt and jeans holding his hat and herding sheep"}, {"tokens": ["a", "man", "herding", "some", "sheep", "into", "a", "pen"], "raw": "A man herding some sheep into a pen.", "sent_id": 22740, "sent": "a man herding some sheep into a pen"}], "file_name": "COCO_train2014_000000269532_217947.jpg", "ann_id": 217947, "sent_ids": [22739, 22740], "ref_id": 46252}, {"segmentation": [[294.06, 55.93, 295.86, 30.07, 277.22, 61.95, 260.37, 70.37, 238.72, 74.58, 228.5, 66.16, 232.1, 52.32, 221.28, 45.71, 225.49, 2.4, 307.29, 0.0, 390.3, 0.6, 369.85, 22.38, 313.31, 66.89, 300.07, 71.7]], "area": 8335.658650000003, "iscrowd": 0, "image_id": 39288, "bbox": [221.28, 0.0, 169.02, 74.58], "category_id": 52, "id": 1042423, "split": "val", "sentences": [{"tokens": ["the", "bananas", "in", "the", "back"], "raw": "The bananas in the back .", "sent_id": 23939, "sent": "the bananas in the back"}], "file_name": "COCO_train2014_000000039288_1042423.jpg", "ann_id": 1042423, "sent_ids": [23939], "ref_id": 46298}, {"segmentation": [[266.37, 167.61, 239.13, 164.58, 239.13, 168.62, 233.07, 174.67, 229.04, 180.72, 222.98, 191.82, 217.94, 200.9, 212.89, 208.97, 204.82, 216.04, 197.76, 239.24, 187.67, 248.32, 181.61, 255.39, 221.97, 252.36, 244.17, 250.34, 251.23, 248.32, 264.35, 240.25, 276.46, 233.19, 286.55, 225.12, 292.6, 209.98, 277.47, 194.85, 276.46, 180.72, 276.46, 175.68, 267.38, 167.61, 262.33, 165.59], [211.88, 276.58, 193.72, 285.66, 183.63, 297.76, 173.54, 306.84, 169.51, 313.91, 164.46, 321.98, 153.36, 336.1, 142.26, 358.3, 141.26, 369.4, 141.26, 398.66, 145.29, 410.77, 156.39, 433.97, 157.4, 433.97, 169.51, 442.05, 189.69, 444.06, 196.75, 444.06, 200.78, 439.02, 200.78, 425.9, 197.76, 413.79, 193.72, 403.71, 191.7, 389.58, 191.7, 379.49, 193.72, 367.38, 202.8, 360.32, 220.96, 353.26, 228.03, 349.22, 250.22, 339.13, 254.26, 334.09, 266.37, 325.01, 273.43, 314.92, 278.48, 308.86, 286.55, 297.76, 288.57, 290.7, 280.49, 291.71, 276.46, 291.71, 266.37, 291.71, 253.25, 291.71, 242.15, 290.7, 216.93, 285.66, 208.86, 278.59], [283.52, 437.0, 290.58, 418.84, 304.71, 400.68, 313.79, 396.64, 320.85, 391.6, 334.98, 383.53, 346.08, 377.47, 363.23, 379.49, 375.34, 379.49, 390.47, 379.49, 402.58, 379.49, 421.75, 375.45, 440.92, 364.36, 441.93, 362.34, 450.0, 358.3, 460.09, 358.3, 480.27, 367.38, 496.41, 373.44, 505.49, 377.47, 508.52, 377.47, 524.66, 383.53, 537.78, 388.57, 545.85, 394.62, 551.91, 403.71, 552.91, 407.74, 547.87, 416.82, 538.79, 425.9, 531.73, 428.93, 517.6, 440.03, 515.58, 443.05, 282.51, 442.05, 281.5, 439.02]], "area": 32643.012150000002, "iscrowd": 0, "image_id": 440689, "bbox": [141.26, 164.58, 411.65, 279.48], "category_id": 4, "id": 148665, "split": "val", "sentences": [{"tokens": ["maroon", "scooter", "with", "silver", "back"], "raw": "maroon scooter with silver back", "sent_id": 24388, "sent": "maroon scooter with silver back"}, {"tokens": ["motor", "bike", "the", "man", "with", "a", "backpack", "is", "riding"], "raw": "motor bike the man with a backpack is riding", "sent_id": 24389, "sent": "motor bike the man with a backpack is riding"}], "file_name": "COCO_train2014_000000440689_148665.jpg", "ann_id": 148665, "sent_ids": [24388, 24389], "ref_id": 46318}, {"segmentation": [[268.71, 361.74, 265.25, 342.73, 262.66, 324.58, 263.52, 307.3, 263.52, 300.38, 266.98, 282.24, 264.38, 281.37, 264.38, 268.41, 266.98, 246.81, 270.43, 235.57, 279.94, 216.56, 290.31, 213.97, 324.01, 194.96, 324.88, 194.96, 328.33, 190.63, 330.06, 176.81, 326.91, 176.28, 323.24, 173.14, 322.19, 165.27, 321.67, 160.54, 324.29, 158.45, 321.14, 157.4, 321.14, 156.35, 323.77, 153.2, 323.77, 145.33, 325.34, 134.31, 337.93, 123.3, 351.57, 119.39, 367.83, 124.64, 373.61, 132.51, 376.75, 148.25, 379.38, 150.87, 378.85, 152.44, 377.8, 158.74, 380.43, 161.89, 379.38, 173.43, 372.56, 178.15, 370.98, 178.15, 366.26, 190.51, 365.74, 201.53, 370.46, 207.3, 372.03, 209.4, 376.75, 208.88, 389.34, 216.74, 395.12, 221.24, 400.36, 231.73, 402.46, 244.84, 402.98, 255.86, 405.08, 266.88, 404.03, 278.95, 407.18, 289.96, 399.84, 294.68, 405.61, 310.42, 408.23, 317.24, 408.23, 337.7, 412.95, 367.61, 414.0, 372.85, 415.05, 378.1, 418.72, 400.14, 414.0, 417.97, 401.94, 422.69, 400.36, 420.6, 397.74, 420.6, 397.21, 426.89, 277.07, 426.89, 281.27, 396.99, 271.3, 388.59, 269.73, 378.1, 271.83, 373.9, 267.63, 367.08, 267.63, 362.89]], "area": 34078.40469999999, "iscrowd": 0, "image_id": 340129, "bbox": [262.66, 119.39, 156.06, 307.5], "category_id": 1, "id": 2204746, "split": "val", "sentences": [{"tokens": ["a", "short", "man", "stands", "next", "to", "a", "taller", "man"], "raw": "A short man stands next to a taller man.", "sent_id": 24782, "sent": "a short man stands next to a taller man"}, {"tokens": ["a", "man", "wearing", "a", "blue", "tshirt", "and", "blue", "baseball", "cap"], "raw": "a man wearing a blue tshirt and blue baseball cap", "sent_id": 24783, "sent": "a man wearing a blue tshirt and blue baseball cap"}], "file_name": "COCO_train2014_000000340129_2204746.jpg", "ann_id": 2204746, "sent_ids": [24782, 24783], "ref_id": 46329}, {"segmentation": [[11.87, 473.53, 28.04, 415.28, 79.82, 393.71, 80.9, 372.13, 50.7, 385.08, 40.99, 375.37, 40.99, 354.88, 58.25, 347.33, 51.78, 324.67, 48.54, 314.97, 22.65, 307.42, 32.36, 277.21, 52.85, 269.66, 77.66, 276.13, 80.9, 250.25, 80.9, 237.3, 53.93, 229.75, 34.52, 266.43, 9.71, 244.85, 5.39, 229.75, 7.55, 214.65, 15.1, 212.49, 28.04, 208.18, 42.07, 209.26, 51.78, 212.49, 62.56, 209.26, 62.56, 187.69, 72.27, 156.4, 87.37, 119.73, 98.16, 99.24, 126.2, 86.29, 177.98, 80.9, 235.15, 98.16, 267.51, 159.64, 273.98, 192.0, 275.06, 209.26, 291.24, 210.34, 302.02, 188.76, 318.2, 184.45, 331.15, 173.66, 361.35, 169.35, 376.45, 172.58, 379.69, 186.61, 371.06, 199.55, 354.88, 200.63, 324.67, 192.0, 307.42, 193.08, 300.94, 210.34, 311.73, 222.2, 323.6, 231.91, 335.46, 244.85, 373.21, 261.03, 326.83, 249.17, 318.2, 241.62, 302.02, 232.99, 289.08, 227.6, 278.29, 228.67, 276.13, 236.22, 276.13, 253.48, 276.13, 264.27, 273.98, 277.21, 265.35, 294.47, 257.8, 304.18, 251.33, 312.81, 249.17, 324.67, 248.09, 331.15, 259.96, 334.38, 264.27, 341.93, 259.96, 355.96, 257.8, 364.58, 259.96, 379.69, 286.92, 390.47, 297.71, 395.87, 310.65, 404.49, 319.28, 413.12, 325.75, 431.46, 328.99, 457.35, 328.99, 472.45]], "area": 89106.53114999998, "iscrowd": 0, "image_id": 489695, "bbox": [5.39, 80.9, 374.3, 392.63], "category_id": 4, "id": 149590, "split": "val", "sentences": [{"tokens": ["bike", "with", "three", "lights"], "raw": "bike with three lights", "sent_id": 25335, "sent": "bike with three lights"}, {"tokens": ["bike", "in", "front", "left", "side"], "raw": "bike in front left side", "sent_id": 25336, "sent": "bike in front left side"}], "file_name": "COCO_train2014_000000489695_149590.jpg", "ann_id": 149590, "sent_ids": [25335, 25336], "ref_id": 46357}, {"segmentation": [[455.06, 311.8, 460.96, 284.83, 443.26, 267.98, 442.42, 232.58, 452.53, 166.01, 471.07, 139.89, 487.92, 110.39, 500.0, 100.28, 498.03, 370.79, 486.24, 370.79, 470.22, 340.45, 458.43, 321.07]], "area": 10609.620749999995, "iscrowd": 0, "image_id": 574563, "bbox": [442.42, 100.28, 57.58, 270.51], "category_id": 1, "id": 481916, "split": "val", "sentences": [{"tokens": ["the", "person", "with", "their", "back", "to", "the", "camera"], "raw": "The person with their back to the camera", "sent_id": 25478, "sent": "the person with their back to the camera"}, {"tokens": ["back", "of", "a", "person", "wearing", "a", "plaid", "shirt"], "raw": "back of a person wearing a plaid shirt", "sent_id": 25479, "sent": "back of a person wearing a plaid shirt"}], "file_name": "COCO_train2014_000000574563_481916.jpg", "ann_id": 481916, "sent_ids": [25478, 25479], "ref_id": 46369}, {"segmentation": [[403.65, 1.69, 362.36, 28.65, 329.49, 52.25, 306.74, 78.37, 281.46, 103.65, 269.66, 141.57, 288.2, 151.69, 300.84, 139.04, 325.28, 125.56, 349.72, 123.88, 387.64, 96.91, 444.94, 50.56, 476.97, 32.02, 487.92, 14.33, 486.24, 1.69]], "area": 13482.65345, "iscrowd": 0, "image_id": 39288, "bbox": [269.66, 1.69, 218.26, 150.0], "category_id": 52, "id": 1041486, "split": "val", "sentences": [{"tokens": ["a", "whole", "banana", "with", "small", "blemishes"], "raw": "A whole banana with small blemishes.", "sent_id": 25970, "sent": "a whole banana with small blemishes"}, {"tokens": ["a", "banana", "with", "a", "triangle", "shaped", "bruise"], "raw": "A banana with a triangle shaped bruise.", "sent_id": 25971, "sent": "a banana with a triangle shaped bruise"}], "file_name": "COCO_train2014_000000039288_1041486.jpg", "ann_id": 1041486, "sent_ids": [25970, 25971], "ref_id": 46394}, {"segmentation": [[320.72, 331.79, 327.91, 331.79, 327.91, 317.4, 319.28, 310.21, 303.46, 292.95, 280.45, 303.02, 263.19, 311.65, 250.25, 318.84, 244.49, 321.72, 234.43, 327.47, 209.98, 349.04, 202.79, 353.36, 192.72, 357.67, 188.4, 360.55, 175.46, 357.67, 161.08, 347.61, 161.08, 336.1, 155.33, 334.66, 151.01, 331.79, 139.51, 323.16, 143.82, 317.4, 146.7, 310.21, 153.89, 294.39, 163.96, 281.45, 158.2, 275.7, 162.52, 262.75, 162.52, 262.75, 136.63, 274.26, 76.22, 274.26, 81.98, 292.95, 81.98, 298.71, 77.66, 310.21, 76.22, 317.4, 60.4, 327.47, 18.7, 347.61, 21.57, 579.16, 48.9, 584.91, 53.21, 626.62, 204.22, 625.18, 207.1, 605.04, 204.22, 579.16, 197.03, 564.77, 189.84, 559.02, 197.03, 548.95, 198.47, 541.76, 202.79, 533.13, 195.6, 527.38, 192.72, 515.88, 184.09, 508.68, 176.9, 508.68, 172.58, 500.05, 166.83, 489.99, 165.39, 472.73, 163.96, 461.22, 162.52, 446.84, 162.52, 442.53, 159.64, 425.27, 165.39, 418.08, 175.46, 418.08, 201.35, 415.2, 221.48, 409.45, 251.69, 395.07, 263.19, 379.25, 267.51, 360.55, 277.57, 353.36, 284.76, 346.17, 293.39, 336.1, 312.09, 328.91, 320.72, 327.47]], "area": 58573.27865000001, "iscrowd": 0, "image_id": 505885, "bbox": [18.7, 262.75, 309.21, 363.87], "category_id": 1, "id": 506679, "split": "val", "sentences": [{"tokens": ["the", "man", "with", "his", "arm", "around", "the", "woman"], "raw": "The man with his arm around the woman.", "sent_id": 26003, "sent": "the man with his arm around the woman"}, {"tokens": ["a", "couple", "under", "an", "umbrella"], "raw": "a couple under an umbrella", "sent_id": 26004, "sent": "a couple under an umbrella"}], "file_name": "COCO_train2014_000000505885_506679.jpg", "ann_id": 506679, "sent_ids": [26003, 26004], "ref_id": 46395}, {"segmentation": [[61.4, 357.52, 77.86, 359.42, 99.38, 351.83, 111.41, 339.8, 111.41, 328.4, 103.81, 315.74, 108.25, 315.11, 114.58, 310.68, 116.48, 301.81, 110.78, 290.42, 89.89, 268.89, 90.52, 253.07, 102.55, 249.27, 103.18, 234.71, 100.65, 232.18, 102.55, 225.21, 108.88, 223.95, 107.61, 214.45, 113.31, 194.82, 113.31, 187.86, 108.88, 151.14, 98.12, 137.85, 94.32, 125.19, 87.35, 126.45, 79.12, 115.06, 80.39, 104.93, 75.33, 92.9, 59.5, 84.67, 40.51, 82.77, 31.01, 89.1, 32.28, 108.09, 37.34, 125.82, 30.38, 127.09, 43.67, 132.78, 43.04, 137.85, 35.44, 145.45, 32.91, 161.91, 30.38, 185.96, 24.05, 209.39, 24.68, 216.35, 19.62, 234.71, 29.11, 245.47, 43.67, 241.67, 39.87, 232.81, 43.67, 231.54, 44.31, 260.66, 49.37, 276.49, 50.0, 287.89, 63.93, 301.81, 66.46, 320.17, 73.43, 331.57, 56.33, 344.86, 57.6, 359.42, 63.93, 360.69]], "area": 16356.580300000001, "iscrowd": 0, "image_id": 544595, "bbox": [19.62, 82.77, 96.86, 277.92], "category_id": 1, "id": 467277, "split": "val", "sentences": [{"tokens": ["the", "snow", "boarder", "in", "the", "blue", "jacket"], "raw": "The snow boarder in the blue jacket.", "sent_id": 26035, "sent": "the snow boarder in the blue jacket"}, {"tokens": ["a", "man", "snowboarding", "in", "a", "blue", "jacket"], "raw": "a man snowboarding in a blue jacket.", "sent_id": 26036, "sent": "a man snowboarding in a blue jacket"}], "file_name": "COCO_train2014_000000544595_467277.jpg", "ann_id": 467277, "sent_ids": [26035, 26036], "ref_id": 46397}, {"segmentation": [[166.88, 52.97, 163.13, 37.97, 163.13, 19.22, 155.63, 2.34, 0.94, 1.41, 0.94, 97.97, 105.0, 71.72]], "area": 12145.47305, "iscrowd": 0, "image_id": 246641, "bbox": [0.94, 1.41, 165.94, 96.56], "category_id": 1, "id": 2157540, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "red", "and", "white", "shirt"], "raw": "A person in a red and white shirt.", "sent_id": 26538, "sent": "a person in a red and white shirt"}, {"tokens": ["a", "red", "and", "white", "blouse"], "raw": "A red and white blouse.", "sent_id": 26539, "sent": "a red and white blouse"}], "file_name": "COCO_train2014_000000246641_2157540.jpg", "ann_id": 2157540, "sent_ids": [26538, 26539], "ref_id": 46423}, {"segmentation": [[84.96, 6.62, 81.65, 191.99, 281.36, 201.92, 303.43, 153.37, 306.74, 120.27, 307.84, 6.62]], "area": 41973.00675, "iscrowd": 0, "image_id": 56699, "bbox": [81.65, 6.62, 226.19, 195.3], "category_id": 6, "id": 168234, "split": "val", "sentences": [{"tokens": ["front", "of", "the", "big", "red", "tram", "in", "the", "other", "lane", "on", "the", "highway"], "raw": "Front of the big red tram in the other lane on the highway", "sent_id": 26912, "sent": "front of the big red tram in the other lane on the highway"}, {"tokens": ["a", "red", "bus", "with", "the", "licence", "number", "j322bsh", "on", "it"], "raw": "A red bus with the licence number J322BSH on it", "sent_id": 26913, "sent": "a red bus with the licence number j322bsh on it"}], "file_name": "COCO_train2014_000000056699_168234.jpg", "ann_id": 168234, "sent_ids": [26912, 26913], "ref_id": 46444}, {"segmentation": [[50.13, 324.51, 74.37, 309.16, 85.68, 297.85, 107.5, 278.46, 111.54, 258.25, 128.51, 244.52, 156.79, 231.59, 186.69, 223.51, 229.52, 223.51, 262.65, 219.47, 294.97, 215.43, 312.74, 216.24, 322.44, 211.39, 331.33, 219.47, 348.3, 225.12, 362.04, 242.9, 375.77, 250.98, 366.88, 263.1, 360.42, 264.72, 360.42, 284.11, 342.64, 292.19, 376.58, 309.16, 389.51, 320.47, 385.47, 330.98, 376.58, 331.79, 361.23, 328.55, 344.26, 318.86, 336.99, 327.75, 336.99, 339.87, 324.87, 335.83, 316.79, 324.51, 316.79, 314.82, 290.93, 303.51, 270.73, 302.7, 252.14, 302.7, 219.01, 314.01, 203.66, 321.28, 191.54, 329.36, 193.15, 339.87, 201.23, 350.37, 212.55, 360.88, 210.12, 371.38, 193.96, 371.38, 184.26, 368.15, 180.22, 378.65, 169.72, 380.27, 157.6, 377.85, 151.94, 366.53, 151.94, 356.84, 153.56, 330.98, 139.01, 320.47, 130.93, 314.82, 127.7, 332.59, 106.69, 343.1, 84.07, 351.99, 62.25, 351.99, 40.43, 348.76, 34.77, 340.68, 37.2, 329.36, 37.2, 329.36]], "area": 29433.42095, "iscrowd": 0, "image_id": 37862, "bbox": [34.77, 211.39, 354.74, 168.88], "category_id": 18, "id": 11754, "split": "val", "sentences": [{"tokens": ["the", "biggest", "dog", "laying", "on", "the", "floor"], "raw": "The biggest dog laying on the floor.", "sent_id": 27043, "sent": "the biggest dog laying on the floor"}], "file_name": "COCO_train2014_000000037862_11754.jpg", "ann_id": 11754, "sent_ids": [27043], "ref_id": 46448}, {"segmentation": [[297.75, 164.29, 314.98, 140.35, 349.45, 122.16, 367.64, 110.68, 430.83, 105.89, 482.53, 103.97, 528.48, 106.85, 554.33, 116.42, 550.5, 127.91, 503.59, 149.93, 516.04, 151.84, 534.23, 149.93, 539.97, 158.55, 541.89, 180.57, 541.89, 186.31, 554.33, 187.27, 572.52, 187.27, 575.4, 193.97, 568.7, 203.54, 574.44, 214.07, 579.23, 217.9, 561.99, 214.07, 571.57, 222.69, 583.06, 236.09, 584.01, 250.46, 573.48, 263.86, 434.66, 344.28, 404.98, 350.98, 384.87, 350.98, 354.24, 333.75, 345.62, 321.3, 338.92, 325.13, 330.3, 319.39, 335.09, 314.6, 323.6, 298.33, 320.73, 267.69, 324.56, 253.33, 324.56, 237.05, 307.33, 192.05, 292.96, 165.25]], "area": 51311.592549999994, "iscrowd": 0, "image_id": 67356, "bbox": [292.96, 103.97, 291.05, 247.01], "category_id": 54, "id": 308558, "split": "val", "sentences": [{"tokens": ["half", "of", "sandwich", "with", "more", "visible", "meat"], "raw": "Half of sandwich with more visible meat.", "sent_id": 28420, "sent": "half of sandwich with more visible meat"}, {"tokens": ["half", "of", "a", "sandwich", "to", "the", "right", "of", "another", "half", "of", "sandwich"], "raw": "Half of a sandwich to the right of another half of sandwich.", "sent_id": 28421, "sent": "half of a sandwich to the right of another half of sandwich"}], "file_name": "COCO_train2014_000000067356_308558.jpg", "ann_id": 308558, "sent_ids": [28420, 28421], "ref_id": 46513}, {"segmentation": [[67.65, 326.38, 135.74, 401.7, 138.15, 411.95, 142.97, 425.81, 141.77, 429.42, 111.64, 472.21, 45.96, 465.58, 11.01, 355.91, 19.45, 343.86, 24.27, 342.05, 26.68, 355.91, 29.09, 387.84, 31.5, 392.67, 45.96, 369.77, 52.59, 375.79, 53.19, 392.67, 53.79, 407.73, 59.82, 417.37, 72.47, 408.33, 79.7, 398.09, 79.7, 377.6, 79.7, 363.74]], "area": 9255.87935, "iscrowd": 0, "image_id": 451283, "bbox": [11.01, 326.38, 131.96, 145.83], "category_id": 31, "id": 1438006, "split": "val", "sentences": [{"tokens": ["a", "red", "bag", "that", "is", "hanging", "on", "the", "arm", "of", "a", "woman"], "raw": "A red bag that is hanging on the arm of a woman.", "sent_id": 28957, "sent": "a red bag that is hanging on the arm of a woman"}], "file_name": "COCO_train2014_000000451283_1438006.jpg", "ann_id": 1438006, "sent_ids": [28957], "ref_id": 46534}, {"segmentation": [[479.4, 290.69, 476.75, 260.86, 461.5, 254.9, 461.5, 254.23, 473.44, 227.72, 486.03, 214.46, 504.59, 206.5, 515.86, 200.54, 526.47, 189.93, 515.86, 181.31, 512.55, 168.05, 520.5, 135.57, 549.01, 131.59, 577.52, 134.24, 580.17, 170.7, 580.17, 201.86, 603.37, 209.82, 619.28, 233.68, 625.91, 278.1, 623.92, 323.18, 612.65, 323.18, 597.4, 316.55, 598.73, 343.07, 615.97, 349.69, 619.28, 355.66, 639.17, 372.23, 622.6, 396.1, 605.36, 405.38, 582.82, 422.62, 588.79, 396.76, 562.27, 382.84, 536.42, 360.96, 512.55, 364.28, 480.73, 357.65, 476.09, 342.4, 482.72, 317.21, 480.07, 297.32]], "area": 29073.495099999993, "iscrowd": 0, "image_id": 533220, "bbox": [461.5, 131.59, 177.67, 291.03], "category_id": 1, "id": 535147, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "purple", "shirt"], "raw": "A man with a purple shirt.", "sent_id": 29146, "sent": "a man with a purple shirt"}, {"tokens": ["a", "smiley", "man", "with", "a", "purple", "shirt", "and", "khaki", "pants", "sitting", "down", "with", "his", "hands", "together"], "raw": "A smiley man with a purple shirt and khaki pants sitting down with his hands together.", "sent_id": 29147, "sent": "a smiley man with a purple shirt and khaki pants sitting down with his hands together"}], "file_name": "COCO_train2014_000000533220_535147.jpg", "ann_id": 535147, "sent_ids": [29146, 29147], "ref_id": 46543}, {"segmentation": [[525.3, 203.87, 550.11, 161.8, 559.82, 120.81, 556.58, 97.08, 504.81, 29.12, 483.24, 16.18, 447.64, 5.39, 429.3, 3.24, 410.97, 3.24, 388.31, 9.71, 344.09, 47.46, 293.39, 112.18, 321.44, 125.12, 325.75, 168.27, 350.56, 214.65, 381.84, 235.15, 414.2, 244.85, 446.56, 247.01, 501.57, 225.44]], "area": 45378.457850000006, "iscrowd": 0, "image_id": 87792, "bbox": [293.39, 3.24, 266.43, 243.77], "category_id": 60, "id": 1081224, "split": "val", "sentences": [{"tokens": ["glazed", "cake", "donut", "on", "upper", "right"], "raw": "Glazed cake donut on upper right.", "sent_id": 29980, "sent": "glazed cake donut on upper right"}, {"tokens": ["light", "color", "glazed", "donut", "in", "the", "upper", "right"], "raw": "Light color glazed donut in the upper right", "sent_id": 29981, "sent": "light color glazed donut in the upper right"}], "file_name": "COCO_train2014_000000087792_1081224.jpg", "ann_id": 1081224, "sent_ids": [29980, 29981], "ref_id": 46575}, {"segmentation": [[405.55, 421.39, 398.36, 398.38, 409.87, 388.31, 419.93, 375.37, 435.75, 375.37, 442.94, 369.62, 450.13, 369.62, 435.75, 359.55, 427.12, 349.48, 415.62, 343.73, 399.8, 343.73, 378.22, 339.41, 366.72, 322.15, 360.97, 322.15, 352.34, 329.35, 356.65, 339.41, 353.78, 346.6, 346.58, 345.17, 342.27, 335.1, 329.33, 319.28, 346.58, 302.02, 355.21, 289.08, 371.03, 290.51, 378.22, 290.51, 389.73, 277.57, 391.17, 264.63, 389.73, 247.37, 386.85, 228.67, 394.04, 214.29, 395.48, 211.41, 398.36, 207.1, 395.48, 198.47, 395.48, 192.72, 398.36, 184.09, 398.36, 184.09, 394.04, 182.65, 391.17, 175.46, 399.8, 158.2, 422.81, 146.69, 441.51, 152.45, 451.57, 153.89, 454.45, 156.76, 460.0, 504.81, 460.0, 532.13, 441.51, 533.57, 428.56, 533.57, 424.25, 533.57, 419.93, 522.07, 427.12, 517.75, 428.56, 513.44, 434.31, 504.81, 434.31, 501.93, 432.88, 499.05, 418.49, 499.05, 409.87, 499.05, 391.17, 497.62, 379.66, 486.11, 378.22, 474.6, 383.98, 457.35, 389.73, 448.72, 394.04, 442.96, 405.55, 432.9]], "area": 24244.965899999996, "iscrowd": 0, "image_id": 480240, "bbox": [329.33, 146.69, 130.67, 386.88], "category_id": 1, "id": 518912, "split": "val", "sentences": [{"tokens": ["a", "catcher", "watching", "as", "a", "batter", "hits", "the", "ball"], "raw": "A catcher watching as a batter hits the ball.", "sent_id": 30012, "sent": "a catcher watching as a batter hits the ball"}, {"tokens": ["catcher", "behind", "the", "batter"], "raw": "Catcher behind the batter", "sent_id": 30013, "sent": "catcher behind the batter"}], "file_name": "COCO_train2014_000000480240_518912.jpg", "ann_id": 518912, "sent_ids": [30012, 30013], "ref_id": 46577}, {"segmentation": [[461.03, 41.28, 498.09, 27.58, 506.81, 34.12, 517.71, 57.48, 501.51, 77.72, 491.24, 75.23, 496.22, 63.71, 496.22, 63.71, 482.83, 44.08, 470.99, 45.64, 470.99, 45.64, 465.39, 49.38, 457.91, 43.77, 457.91, 43.77, 457.91, 43.77], [420.13, 66.11, 417.01, 70.66, 425.46, 92.5, 425.46, 92.5, 425.46, 92.5, 428.06, 97.32, 428.19, 97.32, 433.0, 90.03, 430.66, 81.58, 426.76, 79.63, 420.65, 66.76], [509.94, 141.27, 501.8, 175.55, 501.8, 175.55, 520.98, 182.53, 552.95, 232.51, 540.74, 244.13, 491.34, 257.5, 473.33, 233.67, 472.74, 225.54, 485.53, 217.98, 486.11, 216.24, 485.53, 204.03, 500.06, 185.43, 500.06, 185.43, 487.27, 152.89, 493.09, 144.17, 493.09, 144.17], [398.33, 168.65, 415.12, 169.85, 415.92, 169.85, 427.51, 174.65, 426.71, 195.84, 411.52, 188.64, 399.53, 180.65, 396.73, 172.65]], "area": 6247.962550000005, "iscrowd": 0, "image_id": 310457, "bbox": [396.73, 27.58, 156.22, 229.92], "category_id": 62, "id": 1590005, "split": "val", "sentences": [{"tokens": ["off", "colored", "green", "arm", "chair", "sitting", "next", "to", "a", "black", "leather", "chair"], "raw": "Off colored green arm chair sitting next to a black leather chair.", "sent_id": 30936, "sent": "off colored green arm chair sitting next to a black leather chair"}], "file_name": "COCO_train2014_000000310457_1590005.jpg", "ann_id": 1590005, "sent_ids": [30936], "ref_id": 46610}, {"segmentation": [[405.91, 417.88, 366.33, 420.64, 206.18, 419.72, 184.09, 403.15, 263.24, 264.16, 352.52, 259.56, 376.46, 342.4, 406.83, 385.66, 406.83, 404.07, 400.39, 416.95]], "area": 25265.584199999998, "iscrowd": 0, "image_id": 64259, "bbox": [184.09, 259.56, 222.74, 161.08], "category_id": 63, "id": 98010, "split": "val", "sentences": [{"tokens": ["a", "long", "white", "couch", "with", "three", "pillows", "facing", "a", "television"], "raw": "A long white couch with three pillows facing a television.", "sent_id": 31443, "sent": "a long white couch with three pillows facing a television"}, {"tokens": ["white", "couch", "with", "a", "remote", "on", "one", "of", "the", "arms"], "raw": "White couch with a remote on one of the arms.", "sent_id": 31444, "sent": "white couch with a remote on one of the arms"}], "file_name": "COCO_train2014_000000064259_98010.jpg", "ann_id": 98010, "sent_ids": [31443, 31444], "ref_id": 46630}, {"segmentation": [[110.26, 453.7, 111.73, 435.35, 117.61, 416.99, 119.08, 403.03, 118.71, 393.12, 115.04, 394.95, 113.94, 385.04, 112.1, 378.43, 108.43, 364.48, 111.0, 345.38, 116.87, 328.86, 129.72, 322.98, 133.76, 317.84, 127.89, 314.17, 128.26, 306.09, 131.19, 298.75, 148.08, 296.55, 150.29, 307.56, 149.55, 316.01, 145.88, 321.15, 160.57, 329.96, 174.52, 359.7, 184.8, 378.06, 191.78, 383.94, 181.87, 390.91, 173.42, 377.33, 162.77, 363.37, 156.16, 351.99, 155.8, 349.05, 157.26, 368.88, 159.47, 385.04, 169.01, 403.03, 170.48, 416.62, 162.77, 451.87, 162.41, 452.6, 176.36, 471.33, 155.43, 469.49, 144.78, 464.72, 146.62, 460.68, 150.65, 448.2, 153.59, 436.08, 157.26, 421.76, 140.74, 400.09, 134.87, 408.91, 135.6, 416.62, 127.52, 424.33, 124.95, 439.02, 116.51, 451.87, 120.18, 458.85, 120.18, 465.82, 107.33, 470.23, 107.33, 463.62, 109.53, 452.97]], "area": 6730.199100000002, "iscrowd": 0, "image_id": 275297, "bbox": [107.33, 296.55, 84.45, 174.78], "category_id": 1, "id": 501154, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "a", "yellow", "bandana", ",", "gray", "shirt", ",", "red", "shorts", ",", "and", "tennis", "shoes", "playing", "frisbee", "on", "the", "beach"], "raw": "A man with a yellow bandana, gray shirt, red shorts, and tennis shoes playing frisbee on the beach.", "sent_id": 31509, "sent": "a man with a yellow bandana , gray shirt , red shorts , and tennis shoes playing frisbee on the beach"}, {"tokens": ["a", "man", "with", "a", "green", "bandana"], "raw": "a man with a green bandana.", "sent_id": 31510, "sent": "a man with a green bandana"}], "file_name": "COCO_train2014_000000275297_501154.jpg", "ann_id": 501154, "sent_ids": [31509, 31510], "ref_id": 46632}, {"segmentation": [[244.28, 167.19, 233.83, 162.71, 227.87, 162.71, 224.88, 154.51, 231.6, 145.56, 230.85, 134.37, 224.88, 126.91, 230.85, 119.45, 224.14, 114.98, 208.47, 115.72, 209.22, 125.42, 206.98, 131.39, 201.01, 140.34, 209.22, 147.05, 218.92, 153.02, 225.63, 165.7, 229.36, 170.17, 244.28, 170.17], [126.43, 150.03, 116.73, 147.05, 123.44, 142.58, 122.7, 133.62, 122.7, 127.66, 126.43, 123.18, 127.17, 111.99, 116.73, 98.57, 102.56, 97.08, 90.62, 100.81, 77.2, 115.72, 76.45, 123.18, 81.67, 135.12, 85.4, 142.58, 84.65, 150.03, 86.89, 156.0, 80.18, 157.49, 72.72, 160.48, 68.25, 169.43, 64.52, 179.12, 67.5, 187.33, 71.23, 205.23, 71.97, 220.89, 76.45, 221.64, 79.43, 223.13, 83.16, 223.13, 83.91, 222.39, 84.65, 199.26, 86.15, 179.12, 123.44, 174.65]], "area": 5142.921100000001, "iscrowd": 0, "image_id": 441972, "bbox": [64.52, 97.08, 179.76, 126.05], "category_id": 1, "id": 230830, "split": "val", "sentences": [{"tokens": ["the", "two", "adults", "that", "are", "sitting", "behind", "the", "driver", "and", "the", "child", "in", "the", "carriage", ".", "one", "is", "facing", "away", "from", "the", "camera", "and", "has", "brown", "hair", ",", "the", "other", "one", "is", "facing", "the", "camera"], "raw": "The two adults that are sitting behind the driver and the child in the carriage. One is facing away from the camera and has brown hair, the other one is facing the camera.", "sent_id": 31553, "sent": "the two adults that are sitting behind the driver and the child in the carriage . one is facing away from the camera and has brown hair , the other one is facing the camera"}], "file_name": "COCO_train2014_000000441972_230830.jpg", "ann_id": 230830, "sent_ids": [31553], "ref_id": 46634}, {"segmentation": [[177.51, 355.09, 168.55, 328.19, 177.51, 294.58, 197.68, 274.4, 221.22, 266.56, 241.39, 265.44, 261.56, 272.16, 281.73, 295.7, 286.21, 330.43, 276.13, 368.53, 245.87, 383.1, 207.77, 383.1]], "area": 10909.352, "iscrowd": 0, "image_id": 581042, "bbox": [168.55, 265.44, 117.66, 117.66], "category_id": 85, "id": 335596, "split": "val", "sentences": [{"tokens": ["clock", "face", "sitting", "on", "top", "a", "gold", "stand"], "raw": "Clock face sitting on top a gold stand.", "sent_id": 32211, "sent": "clock face sitting on top a gold stand"}, {"tokens": ["a", "wall", "clock"], "raw": "a wall clock", "sent_id": 32212, "sent": "a wall clock"}], "file_name": "COCO_train2014_000000581042_335596.jpg", "ann_id": 335596, "sent_ids": [32211, 32212], "ref_id": 46659}, {"segmentation": [[104.52, 70.29, 136.02, 33.07, 181.83, 1.57, 223.36, 1.57, 200.45, 33.07, 174.68, 40.23, 120.27, 67.43], [2.86, 203.45, 52.98, 146.18, 38.66, 186.27, 7.16, 210.61]], "area": 3627.8589, "iscrowd": 0, "image_id": 74549, "bbox": [2.86, 1.57, 220.5, 209.04], "category_id": 49, "id": 693074, "split": "val", "sentences": [{"tokens": ["a", "brown", "and", "yellow", "wrapper"], "raw": "A Brown and Yellow wrapper", "sent_id": 32646, "sent": "a brown and yellow wrapper"}, {"tokens": ["the", "langer", "wrapper", "in", "the", "right", "hand", "picture"], "raw": "the langer wrapper in the right hand picture", "sent_id": 32647, "sent": "the langer wrapper in the right hand picture"}], "file_name": "COCO_train2014_000000074549_693074.jpg", "ann_id": 693074, "sent_ids": [32646, 32647], "ref_id": 46681}, {"segmentation": [[352.43, 217.3, 357.84, 201.08, 364.32, 184.86, 369.73, 177.3, 371.89, 167.57, 371.89, 147.03, 377.3, 132.97, 473.51, 120.0, 507.03, 132.97, 518.92, 147.03, 527.57, 165.41, 530.81, 172.97, 532.97, 193.51, 536.22, 206.49, 540.54, 233.51, 540.54, 237.84, 537.3, 252.97, 526.49, 267.03, 487.57, 285.41, 425.95, 278.92, 403.24, 270.27, 394.59, 268.11, 388.11, 255.14, 387.03, 246.49, 383.78, 241.08, 372.97, 231.35, 360.0, 220.54, 360.0, 219.46]], "area": 23742.54475, "iscrowd": 0, "image_id": 149202, "bbox": [352.43, 120.0, 188.11, 165.41], "category_id": 61, "id": 1088030, "split": "val", "sentences": [{"tokens": ["a", "cupcake", "that", "looks", "like", "a", "hat", "with", "a", "bow", "in", "front"], "raw": "A cupcake that looks like a hat with a bow in front.", "sent_id": 32696, "sent": "a cupcake that looks like a hat with a bow in front"}, {"tokens": ["hat", "in", "the", "right", "most", "side", "of", "the", "image"], "raw": "hat in the right most side of the image", "sent_id": 32697, "sent": "hat in the right most side of the image"}], "file_name": "COCO_train2014_000000149202_1088030.jpg", "ann_id": 1088030, "sent_ids": [32696, 32697], "ref_id": 46686}, {"segmentation": [[37.67, 222.91, 8.61, 326.22, 32.29, 466.13, 122.69, 469.36, 145.29, 429.54, 179.73, 415.55, 216.32, 412.32, 245.38, 416.63, 258.3, 427.39, 271.21, 436.0, 280.9, 452.14, 283.05, 454.3, 288.43, 437.08, 256.14, 400.48, 200.18, 342.37, 195.87, 328.38, 195.87, 324.07, 193.72, 301.47, 181.88, 290.71, 158.21, 277.79, 151.75, 245.51, 149.6, 225.06, 132.38, 215.37, 138.83, 185.24, 134.53, 165.87, 131.3, 155.1, 125.92, 148.65, 116.23, 143.26, 102.24, 140.04, 93.63, 138.96, 71.03, 138.96, 62.42, 140.04, 51.66, 145.42, 45.2, 151.87, 33.36, 161.56, 26.91, 175.55, 19.37, 191.7, 16.14, 206.76, 16.14, 222.91, 16.14, 227.21, 21.52, 229.36, 22.6, 229.36]], "area": 49320.62265000001, "iscrowd": 0, "image_id": 492040, "bbox": [8.61, 138.96, 279.82, 330.4], "category_id": 1, "id": 485421, "split": "val", "sentences": [{"tokens": ["a", "lady", "sitting", "on", "a", "stool", "wrapped", "in", "a", "red", "blanket"], "raw": "A lady sitting on a stool wrapped in a red blanket.", "sent_id": 33416, "sent": "a lady sitting on a stool wrapped in a red blanket"}, {"tokens": ["a", "woman", "sitting", "on", "a", "chair", "wrapped", "in", "a", "red", "blanket"], "raw": "A woman sitting on a chair wrapped in a red blanket.", "sent_id": 33417, "sent": "a woman sitting on a chair wrapped in a red blanket"}], "file_name": "COCO_train2014_000000492040_485421.jpg", "ann_id": 485421, "sent_ids": [33416, 33417], "ref_id": 46709}, {"segmentation": [[194.16, 509.12, 204.22, 488.99, 199.91, 442.97, 220.04, 432.9, 253.12, 343.73, 243.06, 266.07, 230.11, 247.37, 231.55, 181.21, 241.62, 136.63, 232.99, 107.87, 231.55, 103.55, 271.82, 77.66, 365.3, 64.72, 427.0, 63.28, 427.0, 631.37, 303.46, 632.81, 279.01, 592.54, 225.8, 536.45]], "area": 106410.6388, "iscrowd": 0, "image_id": 517920, "bbox": [194.16, 63.28, 232.84, 569.53], "category_id": 3, "id": 347641, "split": "val", "sentences": [{"tokens": ["a", "carp", "arked", "next", "to", "a", "parking", "meter"], "raw": "a carp arked next to a parking meter", "sent_id": 33776, "sent": "a carp arked next to a parking meter"}, {"tokens": ["the", "car", "closes", "to", "the", "parking", "meter"], "raw": "The car closes to the parking meter", "sent_id": 33777, "sent": "the car closes to the parking meter"}], "file_name": "COCO_train2014_000000517920_347641.jpg", "ann_id": 347641, "sent_ids": [33776, 33777], "ref_id": 46725}, {"segmentation": [[3.24, 363.33, 252.4, 357.93, 640.0, 353.62, 640.0, 467.96, 640.0, 480.0, 3.24, 477.66]], "area": 77146.83000000002, "iscrowd": 0, "image_id": 27679, "bbox": [3.24, 353.62, 636.76, 126.38], "category_id": 79, "id": 1127893, "split": "val", "sentences": [{"tokens": ["the", "bottom", "portion", "of", "the", "oven", "door"], "raw": "The bottom portion of the oven door.", "sent_id": 34072, "sent": "the bottom portion of the oven door"}, {"tokens": ["a", "lower", "front", "panel", "of", "a", "prince", "oven"], "raw": "a lower front panel of a prince oven.", "sent_id": 34073, "sent": "a lower front panel of a prince oven"}], "file_name": "COCO_train2014_000000027679_1127893.jpg", "ann_id": 1127893, "sent_ids": [34072, 34073], "ref_id": 46737}, {"segmentation": [[86.52, 285.05, 110.11, 355.84, 96.63, 463.7, 125.84, 488.42, 174.16, 474.94, 193.26, 455.84, 166.29, 344.6, 175.28, 279.43]], "area": 15064.496200000001, "iscrowd": 0, "image_id": 388823, "bbox": [86.52, 279.43, 106.74, 208.99], "category_id": 86, "id": 1155752, "split": "val", "sentences": [{"tokens": ["a", "glass", "model", "flower", "pot", "with", "flowers"], "raw": "A GLASS MODEL FLOWER POT WITH FLOWERS", "sent_id": 34364, "sent": "a glass model flower pot with flowers"}, {"tokens": ["glass", "vase", "with", "three", "flowers", "in", "it"], "raw": "Glass vase with three flowers in it.", "sent_id": 34365, "sent": "glass vase with three flowers in it"}], "file_name": "COCO_train2014_000000388823_1155752.jpg", "ann_id": 1155752, "sent_ids": [34364, 34365], "ref_id": 46751}, {"segmentation": [[255.91, 307.38, 255.07, 332.07, 245.87, 354.66, 296.49, 359.27, 440.42, 359.68, 446.28, 355.92, 443.35, 342.95, 447.54, 335.0, 448.79, 310.31, 367.62, 265.96, 278.92, 272.66, 253.81, 278.1, 251.3, 290.23, 253.81, 307.38]], "area": 15769.503150000002, "iscrowd": 0, "image_id": 78274, "bbox": [245.87, 265.96, 202.92, 93.72], "category_id": 63, "id": 2223643, "split": "val", "sentences": [{"tokens": ["the", "ottoman", "on", "front", "of", "the", "couch"], "raw": "The ottoman on front of the couch.", "sent_id": 34823, "sent": "the ottoman on front of the couch"}, {"tokens": ["a", "rectangular", "ottoman", "in", "front", "of", "the", "tv"], "raw": "A rectangular ottoman in front of the tv.", "sent_id": 34824, "sent": "a rectangular ottoman in front of the tv"}], "file_name": "COCO_train2014_000000078274_2223643.jpg", "ann_id": 2223643, "sent_ids": [34823, 34824], "ref_id": 46766}, {"segmentation": [[125.5, 123.0, 127.72, 152.99, 132.16, 160.76, 119.95, 177.42, 93.29, 190.75, 75.52, 236.28, 92.18, 262.94, 106.62, 262.94, 115.5, 278.49, 114.39, 305.14, 132.16, 340.68, 122.17, 375.11, 106.62, 417.31, 99.95, 439.52, 121.06, 445.08, 127.72, 423.98, 137.72, 417.31, 137.72, 411.76, 165.48, 355.12, 175.48, 355.12, 178.81, 368.44, 161.04, 451.74, 177.7, 452.85, 208.79, 450.63, 204.35, 436.19, 197.69, 428.42, 209.91, 350.67, 205.46, 312.91, 188.8, 285.15, 183.25, 236.28, 195.47, 262.94, 206.57, 306.25, 215.46, 316.25, 226.56, 311.8, 217.68, 267.38, 216.81, 267.38, 207.3, 227.57, 199.51, 190.36, 177.01, 178.25, 164.03, 169.59, 160.57, 154.88, 168.35, 137.58, 160.57, 123.73, 152.78, 113.35, 146.72, 112.48, 135.47, 119.4]], "area": 26264.695549999997, "iscrowd": 0, "image_id": 289425, "bbox": [75.52, 112.48, 151.04, 340.37], "category_id": 1, "id": 476344, "split": "val", "sentences": [{"tokens": ["there", "is", "one", "person", "wearing", "white", "dress", "and", "helmet", "looking", "at", "somewhere"], "raw": "There is one person wearing white dress and helmet looking at somewhere", "sent_id": 36061, "sent": "there is one person wearing white dress and helmet looking at somewhere"}, {"tokens": ["#", "25", "is", "attempting", "to", "steal", "a", "base"], "raw": "#25 is attempting to steal a base.", "sent_id": 36062, "sent": "# 25 is attempting to steal a base"}], "file_name": "COCO_train2014_000000289425_476344.jpg", "ann_id": 476344, "sent_ids": [36061, 36062], "ref_id": 46832}, {"segmentation": [[436.42, 417.24, 582.97, 434.35, 595.8, 467.51, 59.9, 465.37, 36.37, 465.37, 100.55, 419.38, 154.03, 371.24, 194.68, 377.66, 207.51, 391.57, 251.37, 433.28, 278.11, 430.08, 289.88, 403.33, 320.9, 436.49, 329.46, 441.84, 371.17, 429.01, 388.29, 392.64, 395.78, 361.62, 417.17, 357.34, 419.31, 385.15, 424.66, 405.47, 425.73, 412.96]], "area": 28225.75805, "iscrowd": 0, "image_id": 290185, "bbox": [36.37, 357.34, 559.43, 110.17], "category_id": 67, "id": 412777, "split": "val", "sentences": [{"tokens": ["a", "colorful", "bouquet", "on", "a", "table", "with", "a", "bottle", "of", "beer", "on", "a", "table", "before", "a", "beautiful", ",", "smiling", "woman"], "raw": "A colorful bouquet on a table with a bottle of beer on a table before a beautiful, smiling woman.", "sent_id": 36127, "sent": "a colorful bouquet on a table with a bottle of beer on a table before a beautiful , smiling woman"}, {"tokens": ["a", "table", "with", "a", "beer", "and", "a", "flower", "bouquet", "on", "it"], "raw": "A table with a beer and a flower bouquet on it.", "sent_id": 36128, "sent": "a table with a beer and a flower bouquet on it"}], "file_name": "COCO_train2014_000000290185_412777.jpg", "ann_id": 412777, "sent_ids": [36127, 36128], "ref_id": 46838}, {"segmentation": [[311.48, 128.34, 328.9, 106.96, 359.79, 95.47, 386.71, 99.04, 408.89, 111.31, 420.37, 129.13, 427.5, 150.51, 425.91, 174.27, 416.02, 196.05, 400.18, 208.72, 381.57, 216.64, 351.08, 216.24, 333.66, 211.89, 319.8, 202.78, 310.29, 185.75, 303.56, 167.93, 302.77, 148.14, 307.13, 129.13]], "area": 11949.1892, "iscrowd": 0, "image_id": 7504, "bbox": [302.77, 95.47, 124.73, 121.17], "category_id": 85, "id": 336426, "split": "val", "sentences": [{"tokens": ["a", "black", ",", "brown", ",", "gold", ",", "and", "white", "clock", "that", "says", "it", "'", "s", "7", ":", "30", "in", "ha", "noi"], "raw": "A black, brown, gold, and white clock that says it's 7:30 in Ha Noi.", "sent_id": 36214, "sent": "a black , brown , gold , and white clock that says it ' s 7 : 30 in ha noi"}, {"tokens": ["a", "clock", "on", "a", "pink", "wall", "with", "the", "characters", "'", "ha", "noi", "'", "printed", "beneath", "it"], "raw": "A clock on a pink wall with the characters 'HA NOI' printed beneath it", "sent_id": 36215, "sent": "a clock on a pink wall with the characters ' ha noi ' printed beneath it"}], "file_name": "COCO_train2014_000000007504_336426.jpg", "ann_id": 336426, "sent_ids": [36214, 36215], "ref_id": 46841}, {"segmentation": [[74.8, 128.58, 72.68, 142.4, 67.9, 147.19, 63.11, 154.1, 59.92, 161.54, 59.39, 170.57, 61.52, 175.89, 62.05, 181.73, 62.05, 191.83, 66.83, 201.4, 67.36, 202.99, 63.11, 210.97, 56.2, 215.75, 50.89, 220.0, 34.94, 233.29, 24.31, 246.04, 20.06, 252.42, 12.09, 280.59, 4.65, 310.89, 2.52, 318.86, 0.4, 381.57, 4.12, 378.39, 11.56, 352.87, 13.68, 335.34, 16.34, 320.45, 19.0, 302.38, 23.25, 279.53, 39.73, 248.7, 67.36, 223.72, 95.53, 210.97, 114.67, 198.21, 133.27, 190.77, 129.55, 184.39, 126.89, 171.1, 126.36, 167.38, 124.23, 165.79, 115.73, 161.01, 114.14, 156.22, 114.14, 150.38, 114.14, 141.87, 110.95, 136.03, 108.82, 128.58, 102.97, 123.8, 85.97, 122.74]], "area": 6864.8930500000015, "iscrowd": 0, "image_id": 370727, "bbox": [0.4, 122.74, 132.87, 258.83], "category_id": 1, "id": 469556, "split": "val", "sentences": [{"tokens": ["a", "man", "wearing", "glasses", "behind", "the", "left", "shoulder", "of", "the", "man", "in", "the", "red", "shirt"], "raw": "A man wearing glasses behind the left shoulder of the man in the red shirt.", "sent_id": 36397, "sent": "a man wearing glasses behind the left shoulder of the man in the red shirt"}, {"tokens": ["a", "man", "in", "a", "black", "jacket", "with", "dark", "hair", "and", "glasses"], "raw": "A man in a black jacket with dark hair and glasses.", "sent_id": 36398, "sent": "a man in a black jacket with dark hair and glasses"}], "file_name": "COCO_train2014_000000370727_469556.jpg", "ann_id": 469556, "sent_ids": [36397, 36398], "ref_id": 46850}, {"segmentation": [[98.32, 206.22, 23.17, 257.84, 8.79, 274.83, 17.29, 304.9, 56.5, 317.96, 94.4, 319.93, 143.41, 312.08, 153.87, 310.12, 153.21, 291.83, 166.94, 285.29, 188.5, 303.59, 189.81, 307.51, 176.74, 314.7, 187.85, 335.61, 197.0, 335.61, 192.42, 346.72, 189.81, 355.87, 179.35, 362.4, 164.32, 419.26, 166.94, 485.91, 168.9, 536.23, 166.28, 563.68, 168.24, 584.59, 205.49, 566.94, 237.51, 538.19, 274.11, 487.22, 302.86, 445.39, 296.33, 422.52, 300.9, 385.93, 300.9, 343.45, 292.41, 316.66, 292.41, 286.6, 296.33, 273.53, 300.25, 255.88, 298.29, 242.81, 194.38, 297.05, 190.46, 291.83, 185.89, 275.49, 185.89, 264.38, 279.34, 207.53, 265.61, 189.23, 268.23, 171.58, 261.04, 167.01, 246.01, 170.93, 255.16, 156.55, 265.61, 126.49, 274.11, 109.5, 270.19, 87.94, 255.81, 68.99, 238.17, 53.96, 210.07, 53.96, 187.85, 70.95, 178.7, 92.51, 175.43, 120.61, 170.2, 144.79, 166.28, 155.9, 173.47, 161.13, 164.98, 166.36, 136.22, 181.39], [326.78, 523.11, 342.96, 560.86, 351.95, 581.09, 347.46, 612.0, 244.98, 612.0, 259.37, 597.27, 258.02, 582.88, 262.96, 567.6, 286.78, 548.73]], "area": 71357.24805000002, "iscrowd": 0, "image_id": 541949, "bbox": [8.79, 53.96, 343.16, 558.04], "category_id": 1, "id": 525892, "split": "val", "sentences": [{"tokens": ["woman", "in", "an", "all", "black", "dress"], "raw": "woman in an all black dress", "sent_id": 36451, "sent": "woman in an all black dress"}, {"tokens": ["girl", "in", "black", "dress"], "raw": "girl in black dress", "sent_id": 36452, "sent": "girl in black dress"}], "file_name": "COCO_train2014_000000541949_525892.jpg", "ann_id": 525892, "sent_ids": [36451, 36452], "ref_id": 46854}, {"segmentation": [[312.11, 259.55, 316.9, 227.0, 337.96, 218.38, 359.02, 220.3, 374.34, 227.96, 376.26, 244.23, 369.56, 268.17, 369.56, 292.1, 388.7, 334.23, 388.7, 372.52, 374.34, 409.86, 365.73, 423.27, 294.88, 421.35, 274.77, 390.71, 249.88, 415.61, 225.95, 423.27, 187.65, 423.27, 185.74, 384.97, 186.69, 371.57, 208.71, 372.52, 219.24, 392.63, 234.56, 375.4, 256.58, 356.25, 246.05, 329.44, 253.71, 312.21, 279.56, 321.78, 305.41, 325.61]], "area": 21817.7879, "iscrowd": 0, "image_id": 314319, "bbox": [185.74, 218.38, 202.96, 204.89], "category_id": 1, "id": 494745, "split": "val", "sentences": [{"tokens": ["baby", "being", "worn", "in", "an", "orange", "printed", "sling"], "raw": "baby being worn in an orange printed sling", "sent_id": 36632, "sent": "baby being worn in an orange printed sling"}, {"tokens": ["the", "baby", "in", "the", "right", "hand", "picture"], "raw": "the baby in the right hand picture", "sent_id": 36633, "sent": "the baby in the right hand picture"}], "file_name": "COCO_train2014_000000314319_494745.jpg", "ann_id": 494745, "sent_ids": [36632, 36633], "ref_id": 46863}, {"segmentation": [[198.47, 223.15, 231.28, 246.12, 250.14, 251.86, 269.82, 290.4, 294.43, 281.38, 282.12, 241.2, 344.45, 246.94, 347.73, 228.9, 341.99, 182.15, 304.27, 153.44, 260.8, 145.24, 213.23, 155.9, 188.63, 199.37]], "area": 14088.30965, "iscrowd": 0, "image_id": 43655, "bbox": [188.63, 145.24, 159.1, 145.16], "category_id": 17, "id": 46622, "split": "val", "sentences": [{"tokens": ["cat", "with", "one", "paw", "outside", "his", "bed"], "raw": "cat with one paw outside his bed", "sent_id": 36873, "sent": "cat with one paw outside his bed"}, {"tokens": ["a", "cat", "on", "the", "left", "side", "sitting", "next", "to", "another", "cat"], "raw": "A cat on the left side sitting next to another cat.", "sent_id": 36874, "sent": "a cat on the left side sitting next to another cat"}], "file_name": "COCO_train2014_000000043655_46622.jpg", "ann_id": 46622, "sent_ids": [36873, 36874], "ref_id": 46872}, {"segmentation": [[77.15, 238.9, 80.19, 229.77, 81.2, 228.25, 78.16, 226.22, 63.96, 224.19, 44.17, 224.7, 28.95, 227.23, 30.48, 216.58, 63.96, 206.43, 54.32, 188.68, 57.36, 174.98, 50.77, 170.42, 52.29, 153.17, 59.39, 143.53, 70.55, 133.39, 84.75, 136.94, 85.77, 154.19, 97.44, 126.28, 118.74, 107.01, 135.99, 98.38, 149.69, 98.38, 150.19, 103.96, 145.12, 114.62, 135.48, 130.34, 127.87, 137.95, 139.03, 149.62, 148.16, 161.29, 146.64, 169.91, 139.54, 169.91, 131.93, 161.79, 125.84, 161.29, 126.35, 184.11, 124.83, 200.35, 118.74, 212.01, 99.47, 220.64, 98.96, 229.26, 105.05, 237.89, 111.13, 244.99, 103.02, 246.0, 96.93, 243.47, 91.35, 232.81, 91.35, 224.19, 82.73, 222.67, 89.83, 229.26, 90.84, 241.94, 88.31, 244.48, 75.12, 243.47, 78.16, 236.87]], "area": 8217.516599999999, "iscrowd": 0, "image_id": 354444, "bbox": [28.95, 98.38, 121.24, 147.62], "category_id": 16, "id": 41000, "split": "val", "sentences": [{"tokens": ["a", "bird", "with", "its", "wings", "spread", "standing", "on", "top", "of", "the", "vehicle"], "raw": "A bird with its wings spread standing on top of the vehicle.", "sent_id": 36879, "sent": "a bird with its wings spread standing on top of the vehicle"}, {"tokens": ["the", "seagull", "on", "the", "vehicle", "to", "the", "left", "of", "two", "other", "seagulls"], "raw": "The seagull on the vehicle to the left of two other seagulls.", "sent_id": 36880, "sent": "the seagull on the vehicle to the left of two other seagulls"}], "file_name": "COCO_train2014_000000354444_41000.jpg", "ann_id": 41000, "sent_ids": [36879, 36880], "ref_id": 46873}, {"segmentation": [[456.02, 182.41, 450.01, 201.45, 451.01, 216.49, 453.02, 227.51, 460.03, 240.54, 485.09, 247.56, 502.13, 253.57, 506.13, 263.59, 506.13, 274.62, 494.11, 273.61, 483.08, 269.6, 475.07, 266.6, 479.07, 285.64, 480.08, 293.66, 419.94, 278.62, 417.94, 275.62, 385.87, 245.55, 383.86, 213.48, 337.76, 192.43, 292.66, 185.42, 273.61, 193.43, 257.58, 207.47, 246.55, 228.51, 251.56, 244.55, 259.58, 265.6, 268.6, 276.62, 288.65, 284.64, 315.71, 294.66, 328.74, 295.66, 343.77, 310.7, 378.85, 334.75, 382.86, 339.76, 391.88, 357.8, 418.94, 375.84, 453.02, 390.88, 458.03, 389.87, 480.08, 387.87, 500.12, 385.87, 503.13, 380.85, 486.09, 333.75, 475.07, 317.71, 489.1, 332.75, 511.15, 366.82, 534.2, 369.83, 546.22, 375.84, 568.27, 390.88, 586.31, 377.85, 584.31, 338.76, 548.23, 309.69, 543.22, 305.69, 534.2, 294.66, 524.18, 270.61, 524.18, 260.58, 530.19, 240.54, 521.17, 229.51, 509.14, 215.48, 498.12, 212.48, 495.11, 212.48, 497.11, 202.45, 468.05, 173.39, 465.04, 171.38, 456.02, 146.33, 436.98, 115.26, 415.93, 51.11, 400.9, 64.14, 390.88, 83.19, 424.95, 143.32, 448.0, 162.36, 465.04, 199.45, 470.05, 221.5, 470.05, 236.53]], "area": 38536.77525, "iscrowd": 0, "image_id": 515309, "bbox": [246.55, 51.11, 339.76, 339.77], "category_id": 4, "id": 148421, "split": "val", "sentences": [{"tokens": ["a", "red", "and", "white", "motorcycle", "tilted", "to", "the", "side"], "raw": "a red and white motorcycle tilted to the side", "sent_id": 36916, "sent": "a red and white motorcycle tilted to the side"}, {"tokens": ["bike", "on", "the", "road", "with", "rider"], "raw": "bike on the road with rider", "sent_id": 36917, "sent": "bike on the road with rider"}], "file_name": "COCO_train2014_000000515309_148421.jpg", "ann_id": 148421, "sent_ids": [36916, 36917], "ref_id": 46876}, {"segmentation": [[413.39, 250.15, 508.14, 250.92, 515.02, 260.09, 495.15, 283.77, 484.46, 287.59, 447.01, 260.85, 406.51, 255.5, 408.04, 251.68], [197.14, 415.2, 279.67, 376.23, 312.53, 345.67, 339.27, 351.78, 377.48, 334.97, 382.83, 332.68, 423.33, 330.38, 440.9, 321.98, 447.01, 348.72, 453.89, 365.53, 409.57, 396.1, 395.05, 408.33, 392.76, 415.97, 197.14, 421.32]], "area": 15099.021149999999, "iscrowd": 0, "image_id": 86654, "bbox": [197.14, 250.15, 317.88, 171.17], "category_id": 67, "id": 392240, "split": "val", "sentences": [{"tokens": ["the", "table", "cloth", "that", "is", "underneath", "the", "man", "and", "kids", "arms"], "raw": "The table cloth that is underneath the man and kids arms", "sent_id": 37333, "sent": "the table cloth that is underneath the man and kids arms"}], "file_name": "COCO_train2014_000000086654_392240.jpg", "ann_id": 392240, "sent_ids": [37333], "ref_id": 46892}, {"segmentation": [[374.51, 312.65, 377.31, 274.32, 384.79, 270.58, 410.5, 269.18, 443.22, 268.71, 457.71, 270.58, 467.99, 275.72, 471.26, 280.86, 475.47, 320.59, 475.47, 371.07, 469.39, 393.98, 457.24, 409.4, 438.08, 424.83, 439.01, 451.0, 454.9, 453.34, 469.86, 459.88, 481.08, 476.24, 481.08, 480.0, 418.91, 480.0, 388.53, 480.0, 384.79, 479.51, 383.86, 472.97, 389.0, 462.69, 399.75, 453.34, 411.43, 445.86, 423.12, 443.52, 423.12, 422.02, 409.56, 415.94, 392.74, 399.12, 380.58, 382.29, 375.91, 361.26]], "area": 16412.117850000002, "iscrowd": 0, "image_id": 159768, "bbox": [374.51, 268.71, 106.57, 211.29], "category_id": 46, "id": 665702, "split": "val", "sentences": [{"tokens": ["clear", "goblet", "with", "ice", "in", "it", "but", "no", "wtaer"], "raw": "clear goblet with ice in it but no wtaer", "sent_id": 37785, "sent": "clear goblet with ice in it but no wtaer"}, {"tokens": ["a", "glass", "with", "a", "lot", "of", "ice", "and", "a", "little", "bit", "of", "water", "to", "the", "right", "of", "the", "salt"], "raw": "A glass with a lot of ice and a little bit of water to the right of the salt.", "sent_id": 37786, "sent": "a glass with a lot of ice and a little bit of water to the right of the salt"}], "file_name": "COCO_train2014_000000159768_665702.jpg", "ann_id": 665702, "sent_ids": [37785, 37786], "ref_id": 46910}, {"segmentation": [[214.94, 207.26, 198.63, 229.33, 189.03, 234.13, 185.19, 221.66, 179.44, 213.98, 188.07, 202.47, 166.96, 189.99, 153.53, 185.19, 152.57, 197.67, 143.93, 204.38, 119.94, 203.42, 119.94, 186.15, 119.94, 170.8, 126.66, 157.37, 136.26, 153.53, 147.77, 155.45, 162.16, 157.37, 177.52, 171.76, 181.36, 182.31, 199.59, 184.23, 206.3, 194.79, 215.9, 206.3, 217.82, 209.18], [259.08, 57.57, 260.04, 70.05, 263.88, 86.36, 270.59, 99.79, 276.35, 109.39, 279.23, 123.78, 272.51, 132.42, 259.08, 139.13, 247.56, 140.09, 233.17, 156.41, 244.69, 172.72, 253.32, 189.03, 237.97, 193.83, 224.53, 190.95, 213.98, 189.03, 204.38, 185.19, 214.94, 174.64, 201.51, 166.0, 219.74, 149.69, 226.45, 150.65, 229.33, 127.62, 237.97, 105.55, 231.25, 89.24, 237.97, 76.76, 256.2, 57.57]], "area": 7591.61915, "iscrowd": 0, "image_id": 233746, "bbox": [119.94, 57.57, 159.29, 176.56], "category_id": 56, "id": 1559867, "split": "val", "sentences": [{"tokens": ["2", "pieces", "of", "broccoli", "closest", "to", "the", "left", "side", "of", "the", "plate"], "raw": "2 Pieces of broccoli closest to the left side of the plate", "sent_id": 38116, "sent": "2 pieces of broccoli closest to the left side of the plate"}], "file_name": "COCO_train2014_000000233746_1559867.jpg", "ann_id": 1559867, "sent_ids": [38116], "ref_id": 46928}, {"segmentation": [[204.69, 253.21, 292.45, 297.09, 460.67, 297.09, 587.93, 267.84, 612.0, 240.05, 609.87, 210.79, 506.01, 196.16, 446.04, 178.61, 393.38, 165.45, 384.61, 188.85, 333.41, 204.94, 282.22, 218.1, 226.63, 222.49, 184.21, 235.66, 184.21, 254.67]], "area": 35047.751849999986, "iscrowd": 0, "image_id": 5587, "bbox": [184.21, 165.45, 427.79, 131.64], "category_id": 51, "id": 1901672, "split": "val", "sentences": [{"tokens": ["top", "plate", "holding", "sandwiches"], "raw": "top plate holding sandwiches", "sent_id": 38503, "sent": "top plate holding sandwiches"}, {"tokens": ["the", "topmost", "plate", "of", "pastries", "on", "the", "pastry", "rack"], "raw": "The topmost plate of pastries on the pastry rack.", "sent_id": 38504, "sent": "the topmost plate of pastries on the pastry rack"}], "file_name": "COCO_train2014_000000005587_1901672.jpg", "ann_id": 1901672, "sent_ids": [38503, 38504], "ref_id": 46943}, {"segmentation": [[140.31, 300.81, 177.54, 309.4, 176.11, 267.88, 170.38, 229.22, 143.18, 253.56, 107.38, 260.72, 94.5, 276.47, 80.18, 236.38, 87.34, 226.36, 146.04, 196.29, 168.95, 173.38, 181.83, 146.18, 183.27, 113.25, 209.04, 103.23, 231.95, 117.54, 239.11, 141.88, 277.76, 150.47, 336.47, 156.2, 369.4, 184.84, 395.17, 212.04, 376.55, 219.2, 349.35, 226.36, 332.17, 209.18, 287.79, 209.18, 297.81, 287.92, 300.67, 306.54, 279.19, 316.56, 247.7, 388.15, 224.79, 455.44, 200.45, 472.62, 168.95, 489.8, 167.52, 433.96, 204.74, 386.72, 204.74, 352.35, 171.81, 362.38, 151.77, 358.08, 114.54, 372.4, 93.06, 346.63, 121.7, 316.56]], "area": 45327.85305, "iscrowd": 0, "image_id": 62295, "bbox": [80.18, 103.23, 314.99, 386.57], "category_id": 1, "id": 469914, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "red", "pants", "doing", "a", "trick", "with", "a", "snowboard"], "raw": "A man in red pants doing a trick with a snowboard.", "sent_id": 38863, "sent": "a man in red pants doing a trick with a snowboard"}, {"tokens": ["a", "person", "in", "a", "black", "coat", "and", "red", "snow", "pants", "snow", "boarding"], "raw": "A person in a black coat and red snow pants snow boarding.", "sent_id": 38864, "sent": "a person in a black coat and red snow pants snow boarding"}], "file_name": "COCO_train2014_000000062295_469914.jpg", "ann_id": 469914, "sent_ids": [38863, 38864], "ref_id": 46959}, {"segmentation": [[217.14, 340.53, 239.37, 347.36, 225.69, 323.43, 236.8, 272.14, 235.95, 317.44, 234.24, 337.11, 265.01, 340.53, 250.48, 325.99, 260.74, 272.99, 257.32, 225.12, 260.74, 165.28, 251.33, 151.6, 256.46, 136.21, 256.46, 128.52, 254.75, 113.98, 253.9, 108.85, 225.69, 124.24, 230.82, 131.08, 230.82, 139.63, 218.85, 156.73, 209.44, 165.28]], "area": 8998.710450000004, "iscrowd": 0, "image_id": 376838, "bbox": [209.44, 108.85, 55.57, 238.51], "category_id": 1, "id": 209587, "split": "val", "sentences": [{"tokens": ["soldier", "without", "coat"], "raw": "soldier without coat", "sent_id": 39312, "sent": "soldier without coat"}, {"tokens": ["the", "man", "in", "the", "middle", "wearing", "black"], "raw": "The man in the middle wearing black.", "sent_id": 39313, "sent": "the man in the middle wearing black"}], "file_name": "COCO_train2014_000000376838_209587.jpg", "ann_id": 209587, "sent_ids": [39312, 39313], "ref_id": 46985}, {"segmentation": [[168.16, 317.78, 134.53, 269.02, 119.39, 258.93, 112.67, 278.27, 97.53, 273.22, 103.42, 255.56, 125.28, 223.61, 118.55, 205.96, 116.87, 186.62, 127.8, 176.53, 204.32, 154.67, 243.83, 131.96, 332.12, 100.85, 353.98, 107.58, 369.96, 126.08, 374.16, 140.37, 382.57, 143.74, 392.66, 151.3, 390.98, 163.07, 364.07, 171.48, 386.77, 184.94, 350.62, 223.61, 316.98, 250.52, 247.2, 292.56, 178.25, 325.35]], "area": 36414.773550000005, "iscrowd": 0, "image_id": 581670, "bbox": [97.53, 100.85, 295.13, 224.5], "category_id": 54, "id": 311586, "split": "val", "sentences": [{"tokens": ["the", "large", "sandwich", "that", "is", "on", "the", "plate", "next", "to", "the", "knife"], "raw": "The large sandwich that is on the plate next to the knife", "sent_id": 39679, "sent": "the large sandwich that is on the plate next to the knife"}, {"tokens": ["a", "sandwich", "on", "a", "plate", "next", "to", "a", "cutting", "knife"], "raw": "A sandwich on a plate next to a cutting knife.", "sent_id": 39680, "sent": "a sandwich on a plate next to a cutting knife"}], "file_name": "COCO_train2014_000000581670_311586.jpg", "ann_id": 311586, "sent_ids": [39679, 39680], "ref_id": 46999}, {"segmentation": [[4.23, 257.18, 4.23, 274.44, 24.63, 271.31, 30.91, 265.03, 91.33, 265.03, 101.53, 280.72, 115.66, 278.37, 118.8, 268.95, 158.82, 262.67, 169.02, 272.09, 183.93, 266.6, 185.5, 252.47, 186.28, 230.5, 171.37, 182.63, 50.53, 186.56, 31.69, 208.53, 27.77, 206.96, 24.63, 209.31, 23.06, 215.59, 6.58, 219.51, 1.09, 227.36, 1.09, 257.97, 3.44, 261.89]], "area": 13927.656299999999, "iscrowd": 0, "image_id": 19874, "bbox": [1.09, 182.63, 185.19, 98.09], "category_id": 3, "id": 1784540, "split": "val", "sentences": [{"tokens": ["a", "gold", "mid", "-", "sized", "vehicle"], "raw": "A gold mid-sized vehicle", "sent_id": 39733, "sent": "a gold mid - sized vehicle"}, {"tokens": ["a", "light", "green", "car"], "raw": "a light green car", "sent_id": 39734, "sent": "a light green car"}], "file_name": "COCO_train2014_000000019874_1784540.jpg", "ann_id": 1784540, "sent_ids": [39733, 39734], "ref_id": 47001}, {"segmentation": [[101.2, 215.89, 98.31, 211.07, 90.6, 193.72, 87.71, 182.16, 92.52, 176.38, 95.42, 153.24, 110.84, 144.57, 136.86, 143.61, 148.43, 152.28, 159.03, 175.41, 157.1, 189.87, 159.03, 208.18, 168.67, 234.2, 165.77, 242.88, 156.14, 247.7, 135.9, 257.33, 125.29, 263.12, 119.51, 274.68, 113.73, 292.03, 104.09, 303.6, 87.71, 311.31, 83.85, 311.31, 78.07, 311.31, 72.29, 300.71, 72.29, 291.07, 76.14, 282.39, 79.03, 276.61, 87.71, 257.33, 92.52, 239.02, 104.09, 215.89]], "area": 9086.849399999997, "iscrowd": 0, "image_id": 181929, "bbox": [72.29, 143.61, 96.38, 167.7], "category_id": 1, "id": 529741, "split": "val", "sentences": [{"tokens": ["an", "asian", "girl", "with", "glasses"], "raw": "An Asian girl with glasses.", "sent_id": 39968, "sent": "an asian girl with glasses"}, {"tokens": ["a", "woman", "with", "glasses", "standing", "beside", "a", "man", "with", "glasses"], "raw": "a woman with glasses standing beside a man with glasses", "sent_id": 39969, "sent": "a woman with glasses standing beside a man with glasses"}], "file_name": "COCO_train2014_000000181929_529741.jpg", "ann_id": 529741, "sent_ids": [39968, 39969], "ref_id": 47008}, {"segmentation": [[245.41, 180.69, 256.41, 202.69, 255.03, 216.89, 247.7, 227.89, 245.86, 240.27, 244.95, 262.73, 247.7, 267.77, 253.2, 267.31, 252.28, 248.06, 256.41, 239.35, 261.91, 226.06, 262.36, 233.39, 260.99, 246.69, 269.7, 265.94, 274.28, 267.77, 276.11, 262.73, 271.53, 249.44, 269.7, 242.1, 272.91, 221.02, 278.86, 197.19, 299.03, 210.94, 330.65, 210.94, 321.03, 241.19, 317.36, 265.02, 321.95, 268.69, 326.53, 264.56, 321.95, 256.31, 330.2, 240.27, 339.36, 220.56, 341.2, 214.6, 357.7, 212.31, 374.19, 263.19, 381.53, 269.6, 382.9, 265.94, 374.65, 235.23, 379.69, 232.02, 378.32, 243.94, 384.28, 267.31, 401.69, 267.77, 407.19, 266.85, 406.28, 248.06, 404.9, 230.64, 409.03, 220.1, 412.69, 212.77, 388.86, 174.73, 352.65, 152.27, 329.74, 155.02, 307.74, 155.48, 278.41, 151.35, 263.74, 154.1, 247.7, 163.27, 242.66, 173.81, 236.7, 203.6, 243.11, 204.98, 247.7, 204.52, 247.7, 199.94]], "area": 11793.668750000003, "iscrowd": 0, "image_id": 292271, "bbox": [236.7, 151.35, 175.99, 118.25], "category_id": 24, "id": 1822777, "split": "val", "sentences": [{"tokens": ["the", "big", "zebra", "in", "the", "biddle"], "raw": "The big zebra in the biddle.", "sent_id": 40203, "sent": "the big zebra in the biddle"}, {"tokens": ["a", "zebra", "that", "is", "dead", "center", "in", "the", "camera", "'", "s", "frame"], "raw": "A zebra that is dead center in the camera's frame.", "sent_id": 40204, "sent": "a zebra that is dead center in the camera ' s frame"}], "file_name": "COCO_train2014_000000292271_1822777.jpg", "ann_id": 1822777, "sent_ids": [40203, 40204], "ref_id": 47019}, {"segmentation": [[178.33, 130.9, 210.68, 129.49, 251.93, 174.5, 326.46, 173.56, 343.34, 167.93, 348.5, 157.62, 411.78, 150.12, 418.34, 156.21, 441.78, 157.62, 430.53, 164.65, 448.82, 170.28, 490.07, 172.15, 491.47, 151.06, 494.76, 145.9, 491.47, 175.9, 492.88, 172.15, 503.19, 177.31, 488.19, 184.81, 478.82, 197.47, 447.41, 196.06, 434.75, 198.4, 423.5, 199.34, 416.94, 200.28, 412.25, 202.15, 392.09, 206.84, 234.12, 200.75, 231.77, 204.03, 231.77, 199.34, 190.52, 201.68, 204.58, 192.31, 179.27, 132.77]], "area": 12067.86595, "iscrowd": 0, "image_id": 524925, "bbox": [178.33, 129.49, 324.86, 77.35], "category_id": 5, "id": 160998, "split": "val", "sentences": [{"tokens": ["the", "small", "aeroplane", "have", "5", "colours"], "raw": "The small aeroplane have 5 colours", "sent_id": 41188, "sent": "the small aeroplane have 5 colours"}, {"tokens": ["a", "airoplan", "with", "number", "n177xy"], "raw": "A airoplan with number N177XY", "sent_id": 41189, "sent": "a airoplan with number n177xy"}], "file_name": "COCO_train2014_000000524925_160998.jpg", "ann_id": 160998, "sent_ids": [41188, 41189], "ref_id": 47056}, {"segmentation": [[500.0, 290.58, 457.4, 312.44, 405.27, 320.85, 327.91, 315.81, 292.6, 284.7, 284.19, 267.04, 296.8, 219.96, 285.03, 200.62, 290.92, 176.23, 332.96, 150.17, 475.9, 115.7, 499.44, 126.63]], "area": 36362.164650000006, "iscrowd": 0, "image_id": 421298, "bbox": [284.19, 115.7, 215.81, 205.15], "category_id": 54, "id": 310176, "split": "val", "sentences": [{"tokens": ["the", "sandwich"], "raw": "The sandwich", "sent_id": 41209, "sent": "the sandwich"}, {"tokens": ["a", "wheat", "bread", "sandwhich"], "raw": "a wheat bread sandwhich", "sent_id": 41210, "sent": "a wheat bread sandwhich"}], "file_name": "COCO_train2014_000000421298_310176.jpg", "ann_id": 310176, "sent_ids": [41209, 41210], "ref_id": 47057}, {"segmentation": [[4.8, 68.13, 36.46, 67.17, 86.36, 71.97, 109.39, 88.28, 127.62, 139.13, 113.23, 202.47, 117.07, 272.51, 105.55, 291.7, 93.08, 324.33, 68.13, 322.41, 32.62, 327.21, 2.88, 335.84, 0.0, 71.97]], "area": 28817.828649999996, "iscrowd": 0, "image_id": 197289, "bbox": [0.0, 67.17, 127.62, 268.67], "category_id": 54, "id": 1552435, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "bread", "on", "top", "of", "some", "kind", "of", "meat", "which", "is", "half", "cut", "off", "from", "the", "picture"], "raw": "A piece of bread on top of some kind of meat which is half cut off from the picture", "sent_id": 41961, "sent": "a piece of bread on top of some kind of meat which is half cut off from the picture"}, {"tokens": ["a", "burger", "slider", "that", "is", "to", "the", "left", "of", "all", "the", "other", "burgers"], "raw": "a burger slider that is to the left of all the other burgers", "sent_id": 41962, "sent": "a burger slider that is to the left of all the other burgers"}], "file_name": "COCO_train2014_000000197289_1552435.jpg", "ann_id": 1552435, "sent_ids": [41961, 41962], "ref_id": 47086}, {"segmentation": [[78.55, 327.9, 100.99, 304.21, 109.71, 297.97, 103.48, 290.49, 100.99, 269.3, 97.25, 250.6, 91.01, 220.68, 83.53, 214.44, 73.56, 182.03, 71.06, 165.82, 82.29, 149.61, 88.52, 139.64, 78.55, 127.17, 73.56, 123.43, 72.31, 104.73, 86.03, 98.49, 100.99, 98.49, 108.47, 104.73, 115.95, 125.92, 115.95, 130.91, 137.14, 135.9, 187.01, 157.09, 200.73, 177.04, 213.19, 180.78, 218.18, 189.51, 214.44, 201.97, 204.47, 199.48, 193.25, 184.52, 182.03, 174.55, 159.58, 162.08, 148.36, 158.34, 140.88, 155.84, 138.39, 160.83, 145.87, 177.04, 148.36, 189.51, 155.84, 190.75, 150.86, 199.48, 147.12, 209.45, 149.61, 228.16, 153.35, 284.26, 149.61, 294.23, 135.9, 305.45, 130.91, 312.94, 134.65, 350.34, 145.87, 374.03, 159.58, 391.48, 152.1, 400.21, 138.39, 393.97, 130.91, 381.51, 129.66, 371.53, 122.18, 350.34, 113.45, 330.39, 113.45, 315.43, 98.49, 329.14, 107.22, 341.61, 114.7, 352.83, 115.95, 356.57, 108.47, 356.57, 92.26, 339.12]], "area": 15151.872599999999, "iscrowd": 0, "image_id": 418569, "bbox": [71.06, 98.49, 147.12, 301.72], "category_id": 1, "id": 2198624, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "air", "throwing", "frisbee", "weraing", "a", "light", "yellow", "tea", "shirt"], "raw": "A man in air throwing frisbee weraing a light yellow tea shirt", "sent_id": 42088, "sent": "a man in air throwing frisbee weraing a light yellow tea shirt"}, {"tokens": ["a", "man", "wearing", "an", "orange", "shirt", ",", "jumping"], "raw": "A man wearing an orange shirt, jumping.", "sent_id": 42089, "sent": "a man wearing an orange shirt , jumping"}], "file_name": "COCO_train2014_000000418569_2198624.jpg", "ann_id": 2198624, "sent_ids": [42088, 42089], "ref_id": 47091}, {"segmentation": [[408.81, 152.09, 433.62, 193.08, 475.69, 230.83, 525.3, 267.51, 610.52, 317.12, 640.0, 320.36, 637.48, 4.31, 550.11, 1.08, 520.99, 3.24, 461.66, 21.57, 406.65, 37.75, 399.1, 46.38, 398.02, 45.3, 420.67, 78.74, 432.54, 93.84, 412.04, 151.01]], "area": 55855.31145000002, "iscrowd": 0, "image_id": 213652, "bbox": [398.02, 1.08, 241.98, 319.28], "category_id": 54, "id": 312884, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "on", "the", "right"], "raw": "The sandwich on the right.", "sent_id": 42219, "sent": "the sandwich on the right"}, {"tokens": ["half", "of", "a", "sandwich", "on", "the", "right", "side", "of", "a", "plate"], "raw": "half of a sandwich on the right side of a plate", "sent_id": 42220, "sent": "half of a sandwich on the right side of a plate"}], "file_name": "COCO_train2014_000000213652_312884.jpg", "ann_id": 312884, "sent_ids": [42219, 42220], "ref_id": 47099}, {"segmentation": [[215.83, 224.21, 196.9, 260.56, 182.51, 280.25, 179.48, 299.19, 205.23, 331.75, 153.73, 330.23, 141.62, 300.7, 149.19, 275.71, 143.89, 259.81, 145.4, 226.48, 151.46, 200.74, 145.4, 181.8, 132.53, 166.66, 112.84, 149.24, 113.6, 209.07, 112.08, 253.75, 118.14, 257.53, 106.02, 274.95, 100.72, 295.4, 99.21, 297.67, 99.21, 290.85, 99.21, 286.31, 93.91, 295.4, 85.58, 296.16, 85.58, 291.61, 81.79, 293.13, 97.69, 256.78, 87.85, 203.01, 84.82, 186.35, 71.19, 187.1, 78.0, 152.27, 77.24, 118.95, 91.63, 92.44, 92.39, 87.14, 84.82, 71.24, 80.27, 62.15, 78.0, 54.58, 81.79, 33.37, 87.85, 28.83, 99.96, 28.07, 121.17, 37.16, 136.31, 51.55, 138.59, 65.94, 159.03, 65.94, 187.05, 59.88, 211.29, 65.18, 231.73, 71.24, 224.16, 93.96, 224.92, 110.62, 217.35, 134.09, 217.35, 142.42, 247.64, 162.87, 265.06, 196.19, 268.84, 204.52, 311.25, 246.93, 328.67, 289.34, 334.73, 289.34, 344.57, 284.04, 359.72, 288.58, 353.66, 310.54, 349.12, 323.42, 343.06, 332.51, 320.34, 303.73, 297.62, 281.01, 255.97, 237.84, 237.04, 231.03, 231.73, 238.6]], "area": 35445.865650000014, "iscrowd": 0, "image_id": 190732, "bbox": [71.19, 28.07, 288.53, 304.44], "category_id": 1, "id": 494799, "split": "val", "sentences": [{"tokens": ["two", "soccer", "player", "battling", "for", "the", "ball"], "raw": "Two soccer player battling for the ball.", "sent_id": 42225, "sent": "two soccer player battling for the ball"}, {"tokens": ["soccer", "referee", "fight"], "raw": "Soccer referee fight", "sent_id": 42226, "sent": "soccer referee fight"}], "file_name": "COCO_train2014_000000190732_494799.jpg", "ann_id": 494799, "sent_ids": [42225, 42226], "ref_id": 47100}, {"segmentation": [[412.04, 85.21, 408.81, 101.39, 406.65, 130.52, 403.42, 146.7, 404.49, 158.56, 390.47, 170.43, 377.53, 174.74, 369.98, 193.08, 363.51, 201.71, 359.19, 211.42, 347.33, 228.67, 331.15, 272.9, 335.46, 294.47, 346.25, 307.42, 319.28, 322.52, 286.92, 328.99, 251.33, 335.46, 225.44, 364.58, 207.1, 380.76, 165.03, 435.78, 108.94, 465.98, 99.24, 474.61, 291.24, 472.45, 347.33, 441.17, 416.36, 444.4, 491.87, 376.45, 517.75, 357.03, 524.22, 355.96, 530.7, 351.64, 542.56, 340.85, 546.88, 317.12, 552.27, 290.16, 552.27, 277.21, 552.27, 256.72, 554.43, 243.78, 551.19, 222.2, 549.03, 210.34, 543.64, 166.11, 533.93, 157.48, 525.3, 142.38, 520.99, 99.24, 499.42, 92.76, 491.87, 78.74, 467.06, 65.8, 456.27, 63.64, 430.38, 61.48, 421.75, 61.48, 410.97, 66.88]], "area": 81383.932, "iscrowd": 0, "image_id": 201897, "bbox": [99.24, 61.48, 455.19, 413.13], "category_id": 1, "id": 197895, "split": "val", "sentences": [{"tokens": ["asian", "girl", "in", "long", "sleeve", "brown", "hoodie", "and", "holding", "wii", "remote"], "raw": "asian girl in long sleeve brown hoodie and holding Wii remote", "sent_id": 42302, "sent": "asian girl in long sleeve brown hoodie and holding wii remote"}, {"tokens": ["girl", "in", "brown", "sweatshirt", "with", "wii", "controller"], "raw": "Girl in brown sweatshirt with Wii controller.", "sent_id": 42303, "sent": "girl in brown sweatshirt with wii controller"}], "file_name": "COCO_train2014_000000201897_197895.jpg", "ann_id": 197895, "sent_ids": [42302, 42303], "ref_id": 47103}, {"segmentation": [[544.04, 121.14, 593.6, 64.98, 617.83, 1.1, 222.46, 4.41, 269.82, 55.06, 300.65, 49.56, 313.87, 78.19, 349.11, 75.99, 375.54, 88.1, 378.85, 107.93, 390.96, 106.83, 429.51, 105.72, 459.24, 114.54, 453.74, 125.55, 482.37, 136.56, 515.41, 136.56]], "area": 33362.50644999999, "iscrowd": 0, "image_id": 100485, "bbox": [222.46, 1.1, 395.37, 135.46], "category_id": 18, "id": 1817165, "split": "val", "sentences": [{"tokens": ["the", "brown", "part", "of", "the", "dogs", "face"], "raw": "The brown part of the dogs face.", "sent_id": 44116, "sent": "the brown part of the dogs face"}, {"tokens": ["a", "dog", "is", "trying", "to", "chew", "on", "an", "empty", "water", "bottle"], "raw": "A dog is trying to chew on an empty water bottle.", "sent_id": 44117, "sent": "a dog is trying to chew on an empty water bottle"}], "file_name": "COCO_train2014_000000100485_1817165.jpg", "ann_id": 1817165, "sent_ids": [44116, 44117], "ref_id": 47174}, {"segmentation": [[122.42, 29.1, 149.26, 6.55, 210.47, 2.25, 241.61, 16.21, 262.01, 25.88, 296.38, 26.95, 358.66, 41.98, 393.02, 61.31, 430.6, 90.31, 444.56, 96.75, 495.03, 156.88, 524.03, 197.69, 544.43, 241.71, 547.65, 261.04, 536.91, 270.71, 524.03, 264.26, 525.1, 314.73, 539.06, 389.9, 530.47, 400.64, 518.66, 402.79, 488.59, 409.23, 446.71, 360.91, 440.27, 349.1, 418.79, 326.55, 428.46, 295.41, 430.6, 285.74, 415.57, 262.12, 408.05, 240.64, 398.39, 227.75, 386.58, 225.61, 364.03, 209.5, 355.44, 238.49, 347.92, 256.75, 343.62, 276.08, 343.62, 305.07, 338.26, 323.33, 339.33, 357.69, 339.33, 360.91, 340.4, 394.2, 352.21, 411.38, 359.73, 418.9, 333.96, 421.04, 325.37, 421.04, 317.85, 396.35, 314.63, 385.61, 317.85, 367.35, 316.78, 312.59, 313.56, 275.0, 311.41, 236.35, 289.93, 233.12, 284.56, 228.83, 260.94, 161.18, 255.57, 136.48, 239.46, 130.04, 265.23, 88.16, 252.35, 79.57, 238.39, 81.71, 207.25, 65.61, 154.63, 35.54, 125.64, 30.17], [131.01, 204.13, 146.04, 239.57, 139.6, 253.53, 136.38, 323.33, 139.6, 336.21, 162.15, 311.51, 167.52, 339.43, 162.15, 372.72, 162.15, 398.49, 162.15, 411.38, 178.26, 413.53, 185.77, 419.97, 215.84, 419.97, 222.28, 372.72, 248.05, 310.44, 250.2, 293.26, 237.32, 278.22, 228.72, 262.12, 222.28, 316.88, 208.32, 364.13, 204.03, 375.94, 199.73, 380.24, 191.14, 368.43, 182.55, 336.21, 183.62, 297.55, 186.85, 262.12, 199.73, 250.31, 164.3, 218.09, 168.59, 215.94, 161.07, 206.28, 153.56, 197.69, 137.45, 199.84]], "area": 79570.27899999998, "iscrowd": 0, "image_id": 306837, "bbox": [122.42, 2.25, 425.23, 418.79], "category_id": 24, "id": 592693, "split": "val", "sentences": [{"tokens": ["a", "zebra", "that", "is", "eating", "while", "standing", "to", "the", "right", "of", "another", "zebra"], "raw": "A zebra that is eating while standing to the right of another zebra.", "sent_id": 44324, "sent": "a zebra that is eating while standing to the right of another zebra"}, {"tokens": ["the", "zebra", "with", "its", "head", "in", "the", "grass"], "raw": "The zebra with its head in the grass.", "sent_id": 44325, "sent": "the zebra with its head in the grass"}], "file_name": "COCO_train2014_000000306837_592693.jpg", "ann_id": 592693, "sent_ids": [44324, 44325], "ref_id": 47186}, {"segmentation": [[97.11, 337.14, 229.03, 350.88, 253.77, 360.95, 265.68, 421.42, 159.41, 421.42, 100.77, 420.5, 85.2, 387.52, 79.7, 369.2, 80.62, 349.96]], "area": 12998.710750000004, "iscrowd": 0, "image_id": 454144, "bbox": [79.7, 337.14, 185.98, 84.28], "category_id": 63, "id": 99283, "split": "val", "sentences": [{"tokens": ["there", "is", "a", "grey", "colored", "sofa", "chair", "in", "front", "of", "three", "people"], "raw": "There is a grey colored sofa chair in front of three people", "sent_id": 46024, "sent": "there is a grey colored sofa chair in front of three people"}, {"tokens": ["steal", "blue", "chair", "headrest", "in", "room"], "raw": "Steal blue chair headrest in room", "sent_id": 46025, "sent": "steal blue chair headrest in room"}], "file_name": "COCO_train2014_000000454144_99283.jpg", "ann_id": 99283, "sent_ids": [46024, 46025], "ref_id": 47257}, {"segmentation": [[581.39, 1.08, 517.75, 264.27, 494.02, 371.06, 496.18, 398.02, 564.13, 449.8, 608.36, 460.58, 637.48, 458.43, 639.64, 12.94]], "area": 47268.24985000001, "iscrowd": 0, "image_id": 522229, "bbox": [494.02, 1.08, 145.62, 459.5], "category_id": 47, "id": 678765, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "water", "on", "a", "table", "near", "a", "plate", "of", "food"], "raw": "A glass of water on a table near a plate of food.", "sent_id": 46708, "sent": "a glass of water on a table near a plate of food"}, {"tokens": ["a", "glass", "full", "of", "honey", "-", "colored", "beer", "on", "a", "table"], "raw": "A glass full of honey-colored beer on a table.", "sent_id": 46709, "sent": "a glass full of honey - colored beer on a table"}], "file_name": "COCO_train2014_000000522229_678765.jpg", "ann_id": 678765, "sent_ids": [46708, 46709], "ref_id": 47294}, {"segmentation": [[292.49, 369.52, 305.52, 373.36, 315.49, 365.69, 336.96, 335.79, 331.59, 292.85, 326.99, 278.29, 320.86, 250.68, 320.86, 236.88, 322.39, 222.32, 323.16, 216.95, 307.82, 213.88, 296.32, 211.58, 290.19, 201.62, 284.82, 182.45, 287.89, 157.15, 298.62, 125.71, 307.82, 106.54, 323.16, 95.81, 348.46, 88.14, 396.0, 81.24, 421.3, 86.61, 437.4, 101.18, 445.83, 149.48, 429.73, 174.01, 409.03, 205.45, 440.46, 239.95, 445.83, 258.35, 503.33, 312.79, 513.3, 351.89, 513.3, 412.46, 506.4, 433.93, 514.07, 454.63, 537.84, 478.0, 456.56, 478.0, 446.6, 447.73, 435.86, 446.96, 439.7, 478.0, 395.23, 476.86, 394.46, 457.69, 393.7, 452.33, 385.26, 442.36, 391.4, 396.36, 392.16, 363.39, 366.09, 333.49, 351.53, 349.59, 344.63, 364.92, 333.89, 377.19, 317.79, 389.46, 310.89, 398.66, 298.62, 404.02, 282.52, 409.39, 274.09, 409.39, 267.96, 404.79, 257.22, 395.59, 255.69, 373.36, 265.66, 369.52]], "area": 54705.86034999999, "iscrowd": 0, "image_id": 151729, "bbox": [255.69, 81.24, 282.15, 396.76], "category_id": 1, "id": 443886, "split": "val", "sentences": [{"tokens": ["little", "girl", "in", "green", "shorts", "on", "the", "right", "of", "the", "other", "girl"], "raw": "Little girl in green shorts on the right of the other girl", "sent_id": 47085, "sent": "little girl in green shorts on the right of the other girl"}, {"tokens": ["a", "little", "girl", "with", "brown", "hair", ",", "green", "shorts", "and", "a", "white", "shirt", "leaning", "in", "to", "give", "a", "kiss"], "raw": "A little girl with brown hair, green shorts and a white shirt leaning in to give a kiss.", "sent_id": 47086, "sent": "a little girl with brown hair , green shorts and a white shirt leaning in to give a kiss"}], "file_name": "COCO_train2014_000000151729_443886.jpg", "ann_id": 443886, "sent_ids": [47085, 47086], "ref_id": 47314}, {"segmentation": [[323.14, 282.26, 314.48, 299.57, 301.98, 299.57, 309.67, 285.15, 320.25, 275.53, 335.64, 272.65, 339.48, 261.1, 334.68, 254.37, 372.18, 227.44, 401.03, 202.44, 409.69, 180.32, 448.16, 141.85, 533.75, 122.62, 541.44, 120.69, 588.57, 138.97, 618.38, 138.97, 635.69, 138.97, 640.0, 272.65, 629.92, 249.56, 617.42, 247.64, 609.73, 242.83, 601.07, 245.72, 600.11, 246.68, 604.92, 324.58, 617.42, 354.39, 615.5, 363.05, 598.18, 363.05, 586.64, 364.97, 583.76, 362.08, 577.99, 348.62, 579.91, 334.19, 577.03, 321.69, 573.18, 313.04, 565.49, 335.16, 566.45, 345.74, 572.22, 373.63, 553.95, 372.66, 535.67, 373.63, 532.79, 368.82, 536.64, 344.77, 541.44, 308.23, 547.21, 284.19, 544.33, 276.49, 511.63, 293.8, 494.32, 316.88, 489.51, 313.04, 483.74, 253.41, 481.82, 243.79, 477.97, 243.79, 472.2, 255.33, 473.16, 322.65, 470.28, 339.97, 465.47, 351.51, 466.43, 364.97, 470.28, 373.63, 454.89, 383.24, 435.66, 375.55, 419.31, 366.89, 412.57, 352.47, 421.23, 335.16, 428.92, 330.35, 428.92, 314.0, 405.84, 238.02, 402.0, 229.37, 342.37, 268.8]], "area": 43932.189150000035, "iscrowd": 0, "image_id": 489167, "bbox": [301.98, 120.69, 338.02, 262.55], "category_id": 22, "id": 583674, "split": "val", "sentences": [{"tokens": ["the", "back", "of", "an", "elephant", "whose", "tail", "is", "being", "held", "by", "the", "trunk", "of", "another", "elephant"], "raw": "The back of an elephant whose tail is being held by the trunk of another elephant.", "sent_id": 47439, "sent": "the back of an elephant whose tail is being held by the trunk of another elephant"}, {"tokens": ["an", "elephant", "with", "a", "star", "on", "its", "back"], "raw": "An elephant with a star on its back.", "sent_id": 47440, "sent": "an elephant with a star on its back"}], "file_name": "COCO_train2014_000000489167_583674.jpg", "ann_id": 583674, "sent_ids": [47439, 47440], "ref_id": 47327}, {"segmentation": [[391.55, 386.16, 399.1, 351.64, 415.28, 306.34, 417.44, 258.88, 429.3, 226.52, 449.8, 206.02, 431.46, 200.63, 426.07, 172.58, 445.48, 142.38, 472.45, 139.15, 494.02, 149.93, 517.75, 161.8, 502.65, 190.92, 509.12, 210.34, 541.48, 237.3, 550.11, 309.57, 558.74, 361.35, 520.99, 363.51, 484.31, 379.69, 484.31, 400.18, 505.89, 413.12, 464.9, 414.2, 457.35, 405.57, 429.3, 388.31]], "area": 28241.3483, "iscrowd": 0, "image_id": 492040, "bbox": [391.55, 139.15, 167.19, 275.05], "category_id": 1, "id": 479005, "split": "val", "sentences": [{"tokens": ["woman", "in", "grey", "plaid", "shirt"], "raw": "Woman in grey plaid shirt.", "sent_id": 47512, "sent": "woman in grey plaid shirt"}, {"tokens": ["a", "woman", "wearing", "checked", "shirt"], "raw": "A woman wearing checked shirt", "sent_id": 47513, "sent": "a woman wearing checked shirt"}], "file_name": "COCO_train2014_000000492040_479005.jpg", "ann_id": 479005, "sent_ids": [47512, 47513], "ref_id": 47329}, {"segmentation": [[290.43, 331.19, 300.36, 322.15, 310.36, 311.32, 309.94, 307.15, 308.69, 292.57, 301.61, 273.82, 301.61, 273.82, 292.86, 253.4, 289.11, 244.23, 289.11, 237.15, 290.78, 232.98, 306.19, 197.98, 312.03, 190.06, 313.28, 187.15, 310.78, 182.56, 311.61, 172.98, 315.36, 165.89, 317.03, 149.64, 318.28, 138.39, 303.69, 146.73, 286.61, 144.64, 273.69, 140.89, 260.78, 134.23, 256.19, 134.64, 249.94, 133.81, 244.94, 137.14, 240.77, 138.39, 237.02, 135.89, 234.94, 129.23, 237.86, 123.39, 243.69, 120.47, 245.77, 118.81, 256.19, 124.22, 259.11, 124.22, 265.78, 120.47, 279.11, 115.89, 297.03, 107.56, 313.28, 103.39, 327.86, 94.22, 330.36, 90.47, 324.53, 90.06, 319.53, 89.22, 317.86, 84.64, 315.78, 82.97, 315.21, 79.83, 315.57, 76.57, 315.93, 76.2, 312.12, 74.94, 312.67, 71.85, 314.66, 69.31, 314.48, 66.95, 315.03, 63.51, 305.96, 62.78, 292.65, 59.24, 302.71, 45.54, 314.92, 39.97, 317.92, 38.25, 321.35, 38.68, 336.77, 34.61, 344.91, 37.61, 349.19, 41.25, 355.84, 45.96, 358.83, 49.6, 358.62, 55.17, 360.12, 58.82, 359.48, 65.67, 357.98, 70.17, 350.48, 75.95, 351.98, 79.16, 359.69, 84.09, 367.83, 92.02, 370.88, 106.15, 370.88, 110.04, 376.07, 126.92, 375.75, 145.11, 369.26, 166.21, 370.55, 173.35, 370.23, 175.95, 370.88, 180.49, 369.91, 183.42, 370.55, 190.56, 361.46, 201.27, 350.43, 209.7, 340.36, 214.24, 333.54, 224.96, 325.1, 243.14, 321.53, 250.28, 318.28, 251.25, 322.83, 263.59, 324.78, 283.07, 328.35, 299.31, 329.65, 304.5, 334.19, 306.12, 338.74, 315.54, 343.61, 320.73, 327.7, 332.1, 327.05, 330.8, 316.66, 338.27, 303.35, 340.21, 290.25, 338.27, 289.63, 334.21, 289.71, 331.77]], "area": 15155.083050000005, "iscrowd": 0, "image_id": 11690, "bbox": [234.94, 34.61, 141.13, 305.6], "category_id": 1, "id": 192307, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "white", "shirt", ",", "riding", "a", "motorcycle", ",", "with", "red", "helmet"], "raw": "A man in a white shirt, riding a motorcycle, with red helmet.", "sent_id": 47842, "sent": "a man in a white shirt , riding a motorcycle , with red helmet"}, {"tokens": ["a", "male", "in", "a", "burgundy", "helmet", "sits", "on", "a", "like", "-", "colored", "motorcycle"], "raw": "A male in a burgundy helmet sits on a like-colored motorcycle.", "sent_id": 47843, "sent": "a male in a burgundy helmet sits on a like - colored motorcycle"}], "file_name": "COCO_train2014_000000011690_192307.jpg", "ann_id": 192307, "sent_ids": [47842, 47843], "ref_id": 47344}, {"segmentation": [[222.2, 2.16, 520.99, 1.08, 526.38, 49.62, 638.56, 122.97, 640.0, 225.44, 497.26, 371.06, 324.67, 217.89, 319.28, 207.1]], "area": 94146.3691, "iscrowd": 0, "image_id": 187939, "bbox": [222.2, 1.08, 417.8, 369.98], "category_id": 73, "id": 1104182, "split": "val", "sentences": [{"tokens": ["a", "black", "laptop", "on", "a", "desk", "sitting", "beside", "a", "silver", "laptop"], "raw": "A black laptop on a desk sitting beside a silver laptop", "sent_id": 48255, "sent": "a black laptop on a desk sitting beside a silver laptop"}, {"tokens": ["this", "is", "the", "black", "laptop", "next", "to", "a", "white", "laptop"], "raw": "This is the black laptop next to a white laptop.", "sent_id": 48256, "sent": "this is the black laptop next to a white laptop"}], "file_name": "COCO_train2014_000000187939_1104182.jpg", "ann_id": 1104182, "sent_ids": [48255, 48256], "ref_id": 47365}, {"segmentation": [[1.92, 387.62, 35.5, 409.69, 54.69, 418.32, 90.19, 417.36, 118.97, 399.14, 140.08, 387.62, 140.08, 377.07, 114.18, 373.23, 96.91, 367.47, 107.46, 364.59, 141.04, 364.59, 163.11, 355.96, 182.3, 345.41, 192.85, 332.93, 188.05, 325.26, 174.62, 324.3, 155.43, 326.22, 147.76, 326.22, 139.12, 323.34, 134.32, 314.7, 126.65, 308.95, 108.42, 303.19, 109.38, 291.68, 151.59, 240.82, 189.01, 205.32, 209.16, 167.91, 216.84, 157.35, 241.78, 149.68, 253.3, 146.8, 262.89, 156.39, 255.22, 166.95, 252.34, 174.62, 257.14, 183.26, 261.93, 185.18, 274.41, 183.26, 287.84, 180.38, 294.55, 171.74, 298.39, 164.07, 303.19, 161.19, 310.86, 172.7, 316.62, 179.42, 323.34, 179.42, 322.38, 170.78, 316.62, 157.35, 324.3, 165.03, 327.18, 167.91, 396.26, 186.14, 423.12, 197.65, 438.47, 197.65, 439.43, 188.05, 434.64, 180.38, 452.86, 180.38, 459.58, 174.62, 457.66, 167.91, 434.64, 164.07, 392.42, 157.35, 335.81, 122.81, 285.92, 91.15, 258.09, 86.35, 224.51, 64.28, 160.23, 0.96, 1.92, 0.96]], "area": 83557.42399999998, "iscrowd": 0, "image_id": 347655, "bbox": [1.92, 0.96, 457.66, 417.36], "category_id": 1, "id": 462284, "split": "val", "sentences": [{"tokens": ["a", "female", "holding", "a", "knife", "crouched", "down", "and", "cutting", "a", "designer", "cake"], "raw": "A female holding a knife crouched down and cutting a designer cake", "sent_id": 48772, "sent": "a female holding a knife crouched down and cutting a designer cake"}, {"tokens": ["a", "woman", "holding", "a", "knife", ",", "cutting", "in", "to", "something"], "raw": "A woman holding a knife, cutting in to something.", "sent_id": 48773, "sent": "a woman holding a knife , cutting in to something"}], "file_name": "COCO_train2014_000000347655_462284.jpg", "ann_id": 462284, "sent_ids": [48772, 48773], "ref_id": 47388}, {"segmentation": [[50.51, 185.38, 20.35, 186.93, 13.39, 176.87, 19.58, 166.82, 26.54, 155.99, 28.86, 138.98, 59.02, 104.95, 73.71, 105.72, 109.29, 101.86, 115.48, 95.67, 120.89, 94.12, 130.17, 79.43, 144.09, 56.23, 175.03, 54.68, 199.0, 76.34, 195.13, 100.31, 193.59, 107.27, 188.95, 116.55, 193.59, 121.96, 176.57, 129.7, 167.29, 133.56, 197.45, 155.99, 209.83, 189.25, 230.71, 200.07, 240.76, 201.62, 265.51, 200.07, 304.95, 200.85, 321.97, 203.17, 311.91, 219.41, 309.59, 222.5, 229.75, 239.46, 206.02, 222.2, 177.98, 207.1, 163.96, 227.6, 155.33, 237.3, 144.54, 234.07, 126.2, 221.12, 104.63, 214.65, 77.66, 197.39, 59.33, 188.76, 49.62, 184.45]], "area": 23990.278599999998, "iscrowd": 0, "image_id": 27149, "bbox": [13.39, 54.68, 308.58, 184.78], "category_id": 1, "id": 194720, "split": "val", "sentences": [{"tokens": ["man", "in", "brown", "shirt", "and", "gray", "pants", "playing", "wii"], "raw": "man in brown shirt and gray pants playing Wii", "sent_id": 51139, "sent": "man in brown shirt and gray pants playing wii"}, {"tokens": ["the", "man", "playing", "wii"], "raw": "The man playing Wii.", "sent_id": 51140, "sent": "the man playing wii"}], "file_name": "COCO_train2014_000000027149_194720.jpg", "ann_id": 194720, "sent_ids": [51139, 51140], "ref_id": 47496}, {"segmentation": [[445.4, 250.78, 468.63, 249.81, 504.46, 222.7, 526.73, 188.81, 538.35, 165.57, 530.6, 156.86, 519.95, 157.83, 516.08, 137.49, 511.24, 137.49, 509.3, 131.68, 515.11, 123.94, 515.11, 111.35, 526.73, 94.89, 574.17, 94.89, 585.79, 141.37, 606.13, 157.83, 640.0, 231.41, 635.17, 369.87, 592.57, 320.49, 562.56, 335.98, 542.22, 333.08, 534.48, 333.08, 539.32, 366.0, 530.6, 397.95, 531.57, 420.22, 488.0, 418.29, 509.3, 401.83, 497.68, 364.06, 493.81, 331.14, 508.33, 305.97, 554.81, 265.3, 567.4, 263.37, 550.94, 236.25, 538.35, 222.7, 499.62, 249.81, 462.83, 265.3, 447.33, 290.48, 423.13, 276.92, 420.22, 255.62, 433.78, 247.87]], "area": 28046.0445, "iscrowd": 0, "image_id": 105714, "bbox": [420.22, 94.89, 219.78, 325.33], "category_id": 1, "id": 483544, "split": "val", "sentences": [{"tokens": ["the", "person", "in", "black"], "raw": "The person in black.", "sent_id": 51698, "sent": "the person in black"}, {"tokens": ["the", "man", "in", "the", "black", "gym", "clothes", "who", "is", "playing", "frisbee", "has", "long", "black", "hair"], "raw": "The man in the black gym clothes who is playing frisbee has long black hair.", "sent_id": 51699, "sent": "the man in the black gym clothes who is playing frisbee has long black hair"}], "file_name": "COCO_train2014_000000105714_483544.jpg", "ann_id": 483544, "sent_ids": [51698, 51699], "ref_id": 47521}, {"segmentation": [[227.71, 303.42, 208.73, 309.11, 192.6, 308.16, 185.96, 302.47, 166.03, 297.73, 149.9, 280.65, 155.59, 270.21, 164.13, 255.03, 174.57, 242.69, 191.65, 238.9, 225.81, 243.64, 228.66, 239.85, 230.55, 221.82, 242.89, 211.38, 249.53, 201.89, 257.12, 191.45, 267.56, 175.32, 277.05, 153.5, 291.28, 137.37, 350.11, 123.14, 360.55, 103.21, 378.58, 101.31, 390.91, 93.72, 409.89, 107.95, 413.68, 122.19, 446.89, 131.68, 463.97, 146.86, 474.41, 173.42, 495.29, 211.38, 507.62, 247.44, 516.31, 329.35, 509.12, 339.42, 491.87, 363.87, 478.92, 398.38, 463.1, 408.45, 438.65, 425.71, 428.58, 431.46, 419.96, 447.28, 419.96, 477.48, 419.96, 487.55, 401.26, 496.18, 379.69, 512.0, 376.81, 581.03, 375.37, 614.11, 378.25, 628.49, 332.22, 629.93, 336.54, 602.61, 337.98, 569.53, 333.66, 552.27, 333.66, 527.82, 346.61, 490.43, 352.36, 474.61, 329.35, 490.43, 313.53, 487.55, 327.91, 530.7, 322.16, 547.96, 317.84, 563.78, 317.84, 576.72, 317.84, 609.8, 320.72, 621.3, 323.6, 631.37, 284.76, 632.81, 279.01, 619.87, 283.33, 588.22, 281.89, 569.53, 276.13, 533.57, 274.7, 516.31, 263.19, 486.11, 258.88, 468.85, 256.0, 453.03, 251.69, 422.83, 250.25, 402.7, 244.49, 371.06, 237.3, 349.48, 232.99, 333.66, 231.55, 317.84, 231.55, 307.78, 225.8, 304.9]], "area": 101275.59214999995, "iscrowd": 0, "image_id": 28988, "bbox": [149.9, 93.72, 366.41, 539.09], "category_id": 21, "id": 73373, "split": "val", "sentences": [{"tokens": ["a", "cow", "standing", "next", "to", "a", "tub"], "raw": "A cow standing next to a tub", "sent_id": 52775, "sent": "a cow standing next to a tub"}, {"tokens": ["a", "brown", "cow", "on", "the", "right", "next", "to", "the", "building"], "raw": "A brown cow on the right next to the building.", "sent_id": 52776, "sent": "a brown cow on the right next to the building"}], "file_name": "COCO_train2014_000000028988_73373.jpg", "ann_id": 73373, "sent_ids": [52775, 52776], "ref_id": 47564}, {"segmentation": [[107.33, 288.74, 105.08, 191.91, 109.58, 140.88, 170.38, 137.87, 196.65, 143.13, 199.65, 220.44, 200.4, 287.24, 111.08, 293.24]], "area": 13906.733050000003, "iscrowd": 0, "image_id": 81768, "bbox": [105.08, 137.87, 95.32, 155.37], "category_id": 6, "id": 162957, "split": "val", "sentences": [{"tokens": ["the", "red", "and", "blue", "189", "bus", "stopping", "for", "pedestrians"], "raw": "The red and blue 189 bus stopping for pedestrians.", "sent_id": 52932, "sent": "the red and blue 189 bus stopping for pedestrians"}, {"tokens": ["the", "back", "of", "the", "red", "bus", "that", "is", "driving", "away", "from", "the", "camera"], "raw": "The back of the red bus that is driving away from the camera.", "sent_id": 52933, "sent": "the back of the red bus that is driving away from the camera"}], "file_name": "COCO_train2014_000000081768_162957.jpg", "ann_id": 162957, "sent_ids": [52932, 52933], "ref_id": 47569}, {"segmentation": [[46.38, 430.05, 116.49, 432.21, 131.6, 403.09, 131.6, 391.22, 110.02, 392.3, 100.31, 390.14, 99.24, 372.88, 122.97, 354.55, 133.75, 328.66, 135.91, 299.54, 145.62, 288.75, 142.38, 267.18, 133.75, 259.63, 146.7, 211.09, 143.46, 190.59, 124.04, 180.88, 108.94, 180.88, 104.63, 190.59, 104.63, 197.06, 57.17, 201.38, 55.01, 181.96, 35.6, 177.65, 22.65, 190.59, 22.65, 211.09, 30.2, 239.13, 30.2, 263.94, 23.73, 279.04, 24.81, 296.3, 34.52, 297.38, 40.99, 342.68, 60.4, 367.49, 75.51, 376.12, 79.82, 380.43, 78.74, 393.38, 64.72, 390.14, 46.38, 416.03]], "area": 22109.659000000003, "iscrowd": 0, "image_id": 419028, "bbox": [22.65, 177.65, 124.05, 254.56], "category_id": 86, "id": 1151457, "split": "val", "sentences": [{"tokens": ["a", "gold", ",", "intricate", "vase", "to", "the", "left", "of", "three", "other", "vases"], "raw": "A gold, intricate vase to the left of three other vases.", "sent_id": 53867, "sent": "a gold , intricate vase to the left of three other vases"}, {"tokens": ["a", "golden", "piece", "of", "pottery"], "raw": "A golden piece of pottery.", "sent_id": 53868, "sent": "a golden piece of pottery"}], "file_name": "COCO_train2014_000000419028_1151457.jpg", "ann_id": 1151457, "sent_ids": [53867, 53868], "ref_id": 47603}, {"segmentation": [[19.38, 327.81, 84.27, 330.34, 207.3, 335.39, 249.44, 337.08, 264.61, 334.55, 269.66, 321.91, 267.98, 182.02, 261.24, 172.75, 253.65, 171.07, 56.46, 172.75, 40.45, 173.6, 26.12, 177.81, 13.48, 268.82, 10.11, 325.28, 16.01, 333.71]], "area": 40348.80695, "iscrowd": 0, "image_id": 174892, "bbox": [10.11, 171.07, 259.55, 166.01], "category_id": 51, "id": 1538918, "split": "val", "sentences": [{"tokens": ["food", "in", "an", "orange", "container"], "raw": "Food in an orange container", "sent_id": 53901, "sent": "food in an orange container"}, {"tokens": ["food", "in", "an", "orange", "contaier"], "raw": "Food in an orange contaier", "sent_id": 53902, "sent": "food in an orange contaier"}], "file_name": "COCO_train2014_000000174892_1538918.jpg", "ann_id": 1538918, "sent_ids": [53901, 53902], "ref_id": 47604}, {"segmentation": [[533.03, 116.26, 516.84, 135.69, 497.42, 151.87, 480.16, 173.45, 474.76, 189.64, 478.0, 206.9, 489.87, 226.32, 494.19, 287.83, 497.42, 315.88, 508.21, 352.57, 500.66, 366.59, 462.89, 429.17, 452.1, 427.02, 438.08, 417.31, 427.29, 425.94, 402.47, 471.26, 640.0, 471.26, 640.0, 168.06, 616.11, 131.37, 593.45, 118.42, 569.72, 113.03, 556.77, 107.63, 545.98, 110.87, 535.19, 118.42]], "area": 55008.927299999996, "iscrowd": 0, "image_id": 39812, "bbox": [402.47, 107.63, 237.53, 363.63], "category_id": 1, "id": 505810, "split": "val", "sentences": [{"tokens": ["a", "blonde", "woman"], "raw": "A blonde woman.", "sent_id": 53978, "sent": "a blonde woman"}, {"tokens": ["blonde", "woman"], "raw": "Blonde woman.", "sent_id": 53979, "sent": "blonde woman"}], "file_name": "COCO_train2014_000000039812_505810.jpg", "ann_id": 505810, "sent_ids": [53978, 53979], "ref_id": 47606}, {"segmentation": [[174.38, 30.26, 168.45, 46.35, 167.61, 55.66, 165.07, 86.13, 173.53, 91.21, 170.15, 103.06, 156.6, 108.14, 139.67, 119.99, 131.21, 128.46, 119.36, 140.31, 91.42, 190.25, 78.72, 229.19, 87.19, 234.27, 137.98, 235.12, 207.39, 237.66, 222.63, 234.27, 219.24, 205.49, 225.17, 145.39, 235.33, 129.3, 248.02, 127.61, 279.35, 119.99, 270.88, 109.83, 253.95, 105.6, 231.94, 103.06, 235.33, 91.21, 237.87, 77.67, 237.02, 50.58, 229.4, 22.64, 218.4, 14.18, 205.7, 9.95, 190.46, 18.41, 182.84, 20.95, 176.92, 31.11]], "area": 21934.2272, "iscrowd": 0, "image_id": 122259, "bbox": [78.72, 9.95, 200.63, 227.71], "category_id": 1, "id": 459042, "split": "val", "sentences": [{"tokens": ["a", "blurry", "mans", "face", "wearing", "a", "diamond", "patterned", "sweater"], "raw": "A blurry mans face wearing a diamond patterned sweater.", "sent_id": 54678, "sent": "a blurry mans face wearing a diamond patterned sweater"}, {"tokens": ["a", "guy", "with", "blue", "on", "his", "sweater"], "raw": "A guy with blue on his sweater.", "sent_id": 54679, "sent": "a guy with blue on his sweater"}], "file_name": "COCO_train2014_000000122259_459042.jpg", "ann_id": 459042, "sent_ids": [54678, 54679], "ref_id": 47630}, {"segmentation": [[103.56, 147.59, 105.04, 162.89, 104.05, 178.18, 132.66, 189.52, 162.75, 196.92, 158.31, 208.76, 126.74, 197.91, 134.64, 229.48, 144.99, 253.65, 148.94, 270.91, 155.35, 280.78, 157.82, 288.67, 146.97, 290.64, 130.2, 263.02, 121.32, 258.58, 106.03, 222.08, 91.72, 219.61, 67.55, 223.06, 57.19, 206.79, 52.75, 191.0, 47.82, 180.15, 59.66, 165.84, 65.09, 154.99, 58.18, 137.73, 50.78, 129.34, 46.34, 119.48, 42.89, 114.05, 47.33, 112.57, 49.79, 116.03, 53.74, 119.97, 60.15, 129.34, 56.7, 131.32, 63.61, 135.26, 69.03, 136.74, 79.88, 139.21, 82.84, 141.18, 91.23, 145.62, 91.72, 154.01, 92.21, 155.98, 92.21, 145.13, 92.21, 139.21, 89.75, 133.29, 86.79, 127.37, 94.19, 117.5, 94.19, 122.44, 100.11, 113.56, 97.64, 122.93, 100.11, 121.94, 101.09, 127.37, 102.57, 125.89, 102.57, 130.82, 104.05, 128.36, 101.09, 136.74, 103.56, 142.66]], "area": 6964.4460500000005, "iscrowd": 0, "image_id": 224734, "bbox": [42.89, 112.57, 119.86, 178.07], "category_id": 1, "id": 533995, "split": "val", "sentences": [{"tokens": ["sitting", "person", "in", "background"], "raw": "sitting person in background", "sent_id": 54717, "sent": "sitting person in background"}, {"tokens": ["person", "in", "back", "sitting"], "raw": "person in back sitting", "sent_id": 54718, "sent": "person in back sitting"}], "file_name": "COCO_train2014_000000224734_533995.jpg", "ann_id": 533995, "sent_ids": [54717, 54718], "ref_id": 47632}, {"segmentation": [[135.75, 4.89, 131.68, 33.39, 149.33, 59.19, 146.61, 70.05, 120.82, 61.9, 105.89, 105.34, 76.02, 171.86, 70.59, 199.01, 36.65, 232.95, 16.29, 257.38, 0.0, 254.67, 0.0, 15.75, 0.0, 0.0]], "area": 23694.1427, "iscrowd": 0, "image_id": 527925, "bbox": [0.0, 0.0, 149.33, 257.38], "category_id": 27, "id": 1827181, "split": "val", "sentences": [{"tokens": ["the", "back", "pack", "on", "left", "side"], "raw": "the back pack on left side", "sent_id": 56154, "sent": "the back pack on left side"}, {"tokens": ["blue", "backpack", "near", "the", "black", "cat"], "raw": "Blue backpack near the black cat.", "sent_id": 56155, "sent": "blue backpack near the black cat"}], "file_name": "COCO_train2014_000000527925_1827181.jpg", "ann_id": 1827181, "sent_ids": [56154, 56155], "ref_id": 47703}, {"segmentation": [[44.04, 277.62, 14.36, 253.69, 10.53, 234.54, 23.93, 226.88, 57.44, 232.62, 63.18, 234.54, 68.93, 213.48, 68.93, 190.5, 69.88, 179.02, 78.5, 169.44, 92.86, 164.66, 103.39, 162.74, 104.35, 153.17, 104.35, 143.6, 105.3, 136.89, 118.71, 133.07, 137.85, 138.81, 140.72, 153.17, 142.64, 165.61, 150.3, 177.1, 170.4, 205.82, 173.27, 220.18, 166.57, 221.14, 141.68, 210.61, 133.07, 247.94, 155.08, 259.43, 170.4, 266.13, 174.23, 271.87, 167.53, 290.06, 146.47, 293.89, 123.49, 292.93, 110.09, 291.98, 83.29, 291.02, 70.84, 289.11, 60.31, 289.11, 48.82, 289.11, 37.33, 289.11, 31.59, 286.23, 35.42, 277.62]], "area": 14575.08955, "iscrowd": 0, "image_id": 176229, "bbox": [10.53, 133.07, 163.7, 160.82], "category_id": 1, "id": 260509, "split": "val", "sentences": [{"tokens": ["a", "man", "sitting", "on", "the", "road", "taking", "a", "photo", "of", "a", "man", "skateboarding"], "raw": "A man sitting on the road taking a photo of a man skateboarding.", "sent_id": 56265, "sent": "a man sitting on the road taking a photo of a man skateboarding"}, {"tokens": ["the", "person", "holding", "the", "a", "camera", ",", "taking", "a", "photo"], "raw": "The person holding the a camera, taking a photo.", "sent_id": 56266, "sent": "the person holding the a camera , taking a photo"}], "file_name": "COCO_train2014_000000176229_260509.jpg", "ann_id": 260509, "sent_ids": [56265, 56266], "ref_id": 47704}, {"segmentation": [[214.77, 400.64, 214.77, 418.9, 214.77, 423.19, 172.89, 425.34, 208.32, 360.91, 184.7, 300.77, 178.26, 253.53, 179.33, 215.94, 182.55, 211.65, 171.81, 184.8, 183.62, 175.14, 196.51, 175.14, 212.62, 196.61, 213.69, 209.5, 273.83, 149.37, 265.23, 182.65, 258.79, 204.13, 231.95, 264.26, 234.09, 300.77, 227.65, 307.22, 246.98, 379.16, 243.76, 437.15, 256.64, 433.93, 260.94, 441.45, 258.79, 457.55, 219.06, 457.55, 217.99, 423.19]], "area": 14685.580100000003, "iscrowd": 0, "image_id": 404139, "bbox": [171.81, 149.37, 102.02, 308.18], "category_id": 1, "id": 445560, "split": "val", "sentences": [{"tokens": ["man", "with", "a", "beard", "in", "black", "shirt", "and", "blue", "jeans"], "raw": "Man with a beard in black shirt and blue jeans.", "sent_id": 57422, "sent": "man with a beard in black shirt and blue jeans"}, {"tokens": ["man", "holding", "kite"], "raw": "MAN HOLDING KITE", "sent_id": 57423, "sent": "man holding kite"}], "file_name": "COCO_train2014_000000404139_445560.jpg", "ann_id": 445560, "sent_ids": [57422, 57423], "ref_id": 47757}, {"segmentation": [[240.6, 231.08, 219.22, 256.75, 224.56, 297.38, 245.95, 356.2, 257.71, 382.93, 286.59, 377.58, 287.66, 328.39, 272.68, 301.66, 271.62, 281.34, 280.17, 280.27, 288.72, 289.9, 279.1, 302.73, 288.72, 327.32, 317.6, 325.19, 325.08, 314.49, 327.22, 302.73, 342.19, 315.56, 363.58, 308.08, 374.27, 288.83, 381.76, 256.75, 376.41, 239.64, 391.38, 231.08, 393.52, 213.97, 371.06, 195.79, 373.2, 185.1, 402.08, 141.26, 403.15, 123.08, 387.11, 105.97, 350.75, 102.76, 317.6, 101.69, 303.7, 104.9, 295.14, 128.43, 266.27, 166.92, 253.44, 195.79]], "area": 30503.11085, "iscrowd": 0, "image_id": 174700, "bbox": [219.22, 101.69, 183.93, 281.24], "category_id": 17, "id": 48301, "split": "val", "sentences": [{"tokens": ["a", "grey", "cat", "on", "a", "red", "suitcase", "between", "two", "black", "cats"], "raw": "a grey cat on a red suitcase between two black cats.", "sent_id": 57526, "sent": "a grey cat on a red suitcase between two black cats"}, {"tokens": ["a", "grey", "and", "white", "cat", "on", "a", "red", "luggage"], "raw": "A grey and white cat on a red luggage", "sent_id": 57527, "sent": "a grey and white cat on a red luggage"}], "file_name": "COCO_train2014_000000174700_48301.jpg", "ann_id": 48301, "sent_ids": [57526, 57527], "ref_id": 47764}, {"segmentation": [[148.41, 422.35, 124.47, 346.71, 109.15, 335.22, 110.11, 306.49, 113.94, 277.77, 112.98, 239.47, 170.43, 169.57, 201.07, 154.25, 187.67, 96.8, 202.03, 88.18, 225.97, 82.44, 247.03, 87.22, 261.4, 94.88, 265.23, 119.78, 260.44, 152.33, 257.57, 161.91, 242.25, 173.4, 247.03, 188.72, 258.52, 204.04, 263.31, 232.76, 270.97, 261.49, 304.48, 303.62, 296.82, 314.15, 279.59, 312.24, 243.2, 275.85, 238.42, 299.79, 231.71, 333.3, 228.84, 346.71, 243.2, 395.54, 249.91, 420.43]], "area": 37129.78305, "iscrowd": 0, "image_id": 435029, "bbox": [109.15, 82.44, 195.33, 339.91], "category_id": 1, "id": 507789, "split": "val", "sentences": [{"tokens": ["man", "with", "black", "shorts"], "raw": "man with black shorts.", "sent_id": 57957, "sent": "man with black shorts"}, {"tokens": ["a", "man", "with", "a", "blue", "and", "white", "t", "-", "shirt", "wearing", "black", "pants"], "raw": "A man with a blue and white t-shirt wearing black pants.", "sent_id": 57958, "sent": "a man with a blue and white t - shirt wearing black pants"}], "file_name": "COCO_train2014_000000435029_507789.jpg", "ann_id": 507789, "sent_ids": [57957, 57958], "ref_id": 47784}, {"segmentation": [[127.52, 360.9, 108.22, 340.76, 101.51, 353.35, 89.77, 346.63, 90.6, 329.86, 45.3, 261.9, 0.0, 182.2, 0.0, 11.9, 28.52, 0.0, 109.9, 1.84, 78.02, 27.84, 67.95, 47.14, 62.92, 60.56, 62.08, 77.34, 68.79, 102.51, 75.5, 115.09, 86.41, 134.39, 109.9, 157.04, 121.64, 175.49, 126.68, 182.2, 120.81, 197.3, 119.13, 206.53, 119.97, 209.05, 101.51, 236.73, 98.99, 262.74]], "area": 25480.599400000003, "iscrowd": 0, "image_id": 401962, "bbox": [0.0, 0.0, 127.52, 360.9], "category_id": 62, "id": 377598, "split": "val", "sentences": [{"tokens": ["the", "blue", "chair", "with", "a", "boy", "sitting", "in", "it"], "raw": "the Blue Chair with a boy sitting in it", "sent_id": 58840, "sent": "the blue chair with a boy sitting in it"}, {"tokens": ["a", "purple", "chair", "being", "occupied", "by", "a", "boy", "in", "an", "orange", "shirt"], "raw": "A purple chair being occupied by a boy in an orange shirt.", "sent_id": 58841, "sent": "a purple chair being occupied by a boy in an orange shirt"}], "file_name": "COCO_train2014_000000401962_377598.jpg", "ann_id": 377598, "sent_ids": [58840, 58841], "ref_id": 47825}, {"segmentation": [[3.84, 355.58, 27.73, 392.8, 46.06, 392.25, 70.5, 396.69, 96.06, 413.91, 125.5, 444.47, 128.28, 450.02, 131.61, 441.14, 88.28, 367.8, 42.73, 322.25, 36.62, 311.69, 37.17, 297.8, 32.17, 279.47, 17.17, 265.58, 2.73, 240.58, 0.0, 242.25, 0.51, 347.25]], "area": 7962.468750000002, "iscrowd": 0, "image_id": 174700, "bbox": [0.0, 240.58, 131.61, 209.44], "category_id": 62, "id": 2222413, "split": "val", "sentences": [{"tokens": ["the", "wooden", "chair", "leg", "on", "the", "far", "left", "by", "the", "black", "and", "white", "cat"], "raw": "the wooden chair leg on the far left by the black and white cat", "sent_id": 59042, "sent": "the wooden chair leg on the far left by the black and white cat"}], "file_name": "COCO_train2014_000000174700_2222413.jpg", "ann_id": 2222413, "sent_ids": [59042], "ref_id": 47837}, {"segmentation": [[163.24, 296.06, 185.39, 281.52, 214.47, 281.52, 229.01, 301.6, 242.85, 327.91, 262.93, 347.29, 303.08, 370.83, 310.01, 399.91, 294.77, 415.14, 270.54, 433.83, 231.78, 450.44, 218.62, 439.37, 200.62, 417.21, 176.39, 390.21, 160.47, 370.14, 147.31, 356.29, 117.55, 347.98, 103.01, 341.75, 105.78, 331.37, 118.93, 312.68, 141.08, 306.45, 156.31, 298.14]], "area": 17574.045000000006, "iscrowd": 0, "image_id": 142431, "bbox": [103.01, 281.52, 207.0, 168.92], "category_id": 75, "id": 1974597, "split": "val", "sentences": [{"tokens": ["an", "xbox", "video", "game", "controller"], "raw": "an xbox video game controller", "sent_id": 59325, "sent": "an xbox video game controller"}, {"tokens": ["the", "game", "controller", "in", "the", "middle"], "raw": "the game controller in the middle", "sent_id": 59326, "sent": "the game controller in the middle"}], "file_name": "COCO_train2014_000000142431_1974597.jpg", "ann_id": 1974597, "sent_ids": [59325, 59326], "ref_id": 47851}, {"segmentation": [[182.03, 122.44, 210.93, 119.55, 222.48, 89.21, 231.15, 77.65, 254.27, 57.43, 287.49, 31.42, 296.16, 12.64, 307.72, 0.0, 314.94, 27.09, 332.28, 27.09, 336.61, 40.09, 330.84, 53.09, 309.16, 63.21, 290.38, 68.98, 268.71, 110.88, 228.26, 136.88, 215.26, 158.56, 215.26, 194.67, 218.15, 251.02, 222.48, 266.91, 235.49, 284.24, 216.7, 308.8, 202.26, 350.7, 203.7, 368.04, 192.14, 379.59, 157.47, 375.26, 131.47, 375.26, 109.8, 370.93, 112.69, 344.92, 88.13, 327.58, 88.13, 310.25, 79.46, 285.69, 69.35, 295.8, 63.57, 305.91, 47.67, 316.03, 47.67, 292.91, 52.01, 274.13, 62.12, 256.79, 73.68, 240.9, 83.79, 229.35, 95.35, 209.12, 101.13, 197.56, 102.57, 171.56, 112.69, 164.33, 98.24, 148.44, 80.9, 129.66, 80.9, 125.33, 76.57, 103.66, 83.79, 84.88, 99.68, 77.65, 115.58, 70.43, 138.69, 68.98, 151.69, 71.87, 182.03, 77.65, 184.92, 83.43, 195.03, 105.1, 216.7, 103.66]], "area": 44205.948749999996, "iscrowd": 0, "image_id": 508780, "bbox": [47.67, 0.0, 288.94, 379.59], "category_id": 1, "id": 425724, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "the", "air", "with", "his", "arm", "out", ",", "the", "arm", "has", "tattoos", ",", "with", "a", "corner", "of", "a", "skateboard", "in", "it"], "raw": "A person in the air with his arm out, the arm has tattoos, with a corner of a skateboard in it", "sent_id": 59353, "sent": "a person in the air with his arm out , the arm has tattoos , with a corner of a skateboard in it"}, {"tokens": ["shaggy", "haired", "man", "with", "tattoo", "on", "forearm", "in", "mid", "air", "doing", "a", "skateboard", "trick"], "raw": "shaggy haired man with tattoo on forearm in mid air doing a skateboard trick", "sent_id": 59354, "sent": "shaggy haired man with tattoo on forearm in mid air doing a skateboard trick"}], "file_name": "COCO_train2014_000000508780_425724.jpg", "ann_id": 425724, "sent_ids": [59353, 59354], "ref_id": 47853}, {"segmentation": [[297.29, 334.83, 288.05, 321.63, 299.93, 295.23, 313.13, 262.89, 312.47, 237.81, 304.55, 224.62, 295.97, 215.38, 285.41, 212.08, 286.07, 201.52, 286.07, 200.86, 271.55, 198.88, 245.81, 198.22, 215.46, 198.88, 201.6, 202.18, 202.26, 212.74, 190.38, 225.28, 180.48, 237.15, 176.52, 245.07, 173.88, 254.97, 182.46, 284.01, 200.28, 313.71, 202.92, 325.59, 196.32, 338.13, 299.27, 334.83]], "area": 15392.5828, "iscrowd": 0, "image_id": 368659, "bbox": [173.88, 198.22, 139.25, 139.91], "category_id": 86, "id": 1154136, "split": "val", "sentences": [{"tokens": ["a", "cream", "colored", "urn", "with", "burgundy", "floral", "designs"], "raw": "A cream colored urn with burgundy floral designs.", "sent_id": 59689, "sent": "a cream colored urn with burgundy floral designs"}, {"tokens": ["a", "white", "and", "red", "vas", "on", "the", "wood", "crate"], "raw": "A white and red vas on the wood crate.", "sent_id": 59690, "sent": "a white and red vas on the wood crate"}], "file_name": "COCO_train2014_000000368659_1154136.jpg", "ann_id": 1154136, "sent_ids": [59689, 59690], "ref_id": 47871}, {"segmentation": [[383.77, 369.16, 99.35, 368.18, 100.32, 360.39, 119.81, 363.31, 131.49, 355.52, 159.74, 294.16, 176.3, 290.26, 199.68, 299.03, 199.68, 256.17, 203.57, 242.53, 189.94, 225.0, 161.69, 226.95, 167.53, 213.31, 309.74, 204.55, 319.48, 219.16, 318.51, 227.92, 289.29, 239.61, 277.6, 247.4, 267.86, 252.27, 265.91, 263.96, 277.6, 274.68, 310.71, 293.18, 345.78, 302.92, 357.47, 297.08]], "area": 25448.68565000001, "iscrowd": 0, "image_id": 554031, "bbox": [99.35, 204.55, 284.42, 164.61], "category_id": 67, "id": 1960645, "split": "val", "sentences": [{"tokens": ["white", "table", "in", "front", "of", "other", "tables", "which", "the", "group", "of", "three", "women", "are", "resting", "their", "hands", "on"], "raw": "White table in front of other tables which the group of three women are resting their hands on", "sent_id": 59862, "sent": "white table in front of other tables which the group of three women are resting their hands on"}, {"tokens": ["the", "white", "table", "between", "two", "women", "in", "pony", "tails"], "raw": "The white table between two women in pony tails", "sent_id": 59863, "sent": "the white table between two women in pony tails"}], "file_name": "COCO_train2014_000000554031_1960645.jpg", "ann_id": 1960645, "sent_ids": [59862, 59863], "ref_id": 47880}, {"segmentation": [[409.15, 160.79, 389.8, 283.39, 394.41, 355.3, 375.97, 406.0, 377.81, 432.63, 381.5, 461.11, 407.31, 456.5, 400.86, 433.46, 420.22, 415.94, 430.36, 375.38, 436.81, 334.82, 462.62, 380.91, 481.98, 446.36, 509.63, 455.58, 533.6, 447.29, 513.32, 425.16, 511.48, 393.82, 499.49, 344.96, 469.07, 283.2, 475.53, 245.41, 470.92, 229.73, 503.18, 232.5, 522.54, 224.2, 515.16, 209.55, 508.71, 203.1, 485.67, 204.02, 489.35, 195.72, 495.81, 191.11, 492.12, 180.05, 492.12, 179.13, 478.29, 180.05, 474.6, 185.58, 470.92, 186.5, 459.85, 163.56, 473.68, 115.72, 446.03, 103.83, 431.28, 113.97, 430.36, 125.95, 429.43, 133.33, 411.0, 160.98]], "area": 27459.72415000001, "iscrowd": 0, "image_id": 222676, "bbox": [375.97, 103.83, 157.63, 357.28], "category_id": 1, "id": 523278, "split": "val", "sentences": [{"tokens": ["the", "person", "to", "the", "right", "of", "the", "man", "not", "swinging", "his", "tennis", "racket"], "raw": "The person to the right of the man not swinging his tennis racket.", "sent_id": 59984, "sent": "the person to the right of the man not swinging his tennis racket"}, {"tokens": ["a", "man", "in", "a", "blue", "jacket", "playing", "tennis"], "raw": "A man in a blue jacket playing tennis.", "sent_id": 59985, "sent": "a man in a blue jacket playing tennis"}], "file_name": "COCO_train2014_000000222676_523278.jpg", "ann_id": 523278, "sent_ids": [59984, 59985], "ref_id": 47884}, {"segmentation": [[99.36, 627.99, 99.36, 636.43, 86.69, 611.1, 106.39, 599.84, 90.91, 574.5, 97.95, 560.43, 130.32, 567.46, 165.51, 611.1, 210.55, 636.43, 209.15, 620.95, 155.66, 578.72, 133.14, 551.98, 127.51, 533.68, 145.81, 522.42, 175.36, 542.13, 195.07, 571.69, 240.11, 592.8, 295.01, 609.69, 314.71, 577.32, 302.05, 535.09, 302.05, 508.35, 309.08, 505.53, 342.87, 532.27, 345.68, 594.21, 348.5, 635.03, 337.24, 627.99, 302.05, 635.03, 186.63, 637.84, 120.47, 639.25]], "area": 16484.4729, "iscrowd": 0, "image_id": 179618, "bbox": [86.69, 505.53, 261.81, 133.72], "category_id": 1, "id": 2159127, "split": "val", "sentences": [{"tokens": ["someone", "holding", "the", "base", "of", "a", "blender"], "raw": "someone holding the base of a blender.", "sent_id": 59996, "sent": "someone holding the base of a blender"}, {"tokens": ["a", "person", "holding", "blender", "with", "left", "hand"], "raw": "A person holding blender with left hand.", "sent_id": 59997, "sent": "a person holding blender with left hand"}], "file_name": "COCO_train2014_000000179618_2159127.jpg", "ann_id": 2159127, "sent_ids": [59996, 59997], "ref_id": 47886}, {"segmentation": [[487.55, 266.43, 445.48, 229.75, 453.03, 211.42, 473.53, 193.08, 473.53, 167.19, 470.29, 143.46, 467.06, 129.44, 474.61, 113.26, 484.31, 113.26, 546.88, 94.92, 583.55, 103.55, 613.75, 127.28, 616.99, 176.9, 618.07, 202.79, 607.28, 259.96, 594.34, 284.76, 580.31, 289.08, 578.16, 289.08, 542.56, 277.21, 520.99, 280.45]], "area": 25125.623550000008, "iscrowd": 0, "image_id": 252373, "bbox": [445.48, 94.92, 172.59, 194.16], "category_id": 27, "id": 1169423, "split": "val", "sentences": [{"tokens": ["a", "black", "suitcase", "that", "is", "only", "next", "to", "a", "white", "bag", "not", "another", "black", "bag"], "raw": "A black suitcase that is only next to a white bag not another black bag", "sent_id": 60830, "sent": "a black suitcase that is only next to a white bag not another black bag"}], "file_name": "COCO_train2014_000000252373_1169423.jpg", "ann_id": 1169423, "sent_ids": [60830], "ref_id": 47922}, {"segmentation": [[68.24, 239.21, 66.4, 136.84, 49.26, 134.39, 63.95, 169.29, 53.55, 193.78, 46.81, 208.47, 47.42, 215.82, 40.08, 223.16, 38.85, 229.9], [48.04, 79.9, 73.14, 79.9, 79.26, 79.9, 84.16, 73.78, 98.24, 71.33, 112.93, 73.78, 117.22, 75.01, 117.83, 67.66, 114.77, 57.87, 105.58, 45.01, 89.05, 7.05, 85.99, 0.0, 47.42, 0.0, 44.97, 7.66, 39.46, 17.46, 37.02, 27.87, 36.4, 38.89, 64.56, 38.27, 61.5, 46.23, 61.5, 54.19, 51.1, 54.19, 44.36, 54.8, 57.22, 62.76, 55.38, 69.5]], "area": 5622.68255, "iscrowd": 0, "image_id": 496732, "bbox": [36.4, 0.0, 81.43, 239.21], "category_id": 1, "id": 439544, "split": "val", "sentences": [{"tokens": ["person", "outside"], "raw": "person outside", "sent_id": 61041, "sent": "person outside"}], "file_name": "COCO_train2014_000000496732_439544.jpg", "ann_id": 439544, "sent_ids": [61041], "ref_id": 47931}, {"segmentation": [[97.48, 105.38, 103.75, 100.98, 116.93, 97.85, 136.38, 95.34, 153.32, 95.96, 169.0, 99.1, 185.94, 103.49, 190.96, 110.4, 190.96, 146.16, 189.08, 161.22, 185.32, 175.65, 183.43, 185.06, 175.91, 210.78, 175.28, 213.92, 174.02, 219.57, 173.4, 235.25, 175.91, 252.82, 175.91, 264.11, 172.14, 274.15, 161.47, 282.94, 148.3, 286.07, 128.85, 284.19, 119.44, 281.68, 111.28, 276.04, 109.4, 272.9, 110.65, 255.96, 112.54, 244.04, 115.67, 234.63, 116.93, 226.47, 115.04, 213.92, 111.91, 200.12, 106.89, 188.82, 104.38, 173.14, 100.61, 159.33, 96.85, 144.9, 96.85, 133.61, 96.85, 122.32]], "area": 13960.692350000003, "iscrowd": 0, "image_id": 551244, "bbox": [96.85, 95.34, 94.11, 190.73], "category_id": 47, "id": 668393, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "juice", "is", "placed", "on", "the", "table", "near", "pizza"], "raw": "a glass of juice is placed on the table near pizza", "sent_id": 62133, "sent": "a glass of juice is placed on the table near pizza"}, {"tokens": ["a", "coca", "-", "cola", "glass", "sitting", "on", "a", "table", "half", "filled", "with", "an", "orange", "drink"], "raw": "A Coca-Cola glass sitting on a table half filled with an orange drink", "sent_id": 62134, "sent": "a coca - cola glass sitting on a table half filled with an orange drink"}], "file_name": "COCO_train2014_000000551244_668393.jpg", "ann_id": 668393, "sent_ids": [62133, 62134], "ref_id": 47971}, {"segmentation": [[182.21, 297.74, 187.81, 262.99, 201.26, 241.69, 205.75, 196.84, 209.11, 164.33, 212.48, 156.48, 251.71, 156.48, 211.35, 222.63, 200.14, 265.23, 192.3, 295.5, 186.69, 299.98]], "area": 2357.6132, "iscrowd": 0, "image_id": 45680, "bbox": [182.21, 156.48, 69.5, 143.5], "category_id": 38, "id": 624428, "split": "val", "sentences": [{"tokens": ["the", "pink", "dorsal", "fin", "part", "of", "the", "kite", "that", "looks", "like", "a", "fish"], "raw": "The pink dorsal fin part of the kite that looks like a fish.", "sent_id": 62792, "sent": "the pink dorsal fin part of the kite that looks like a fish"}, {"tokens": ["the", "pink", "back", "stripe", "of", "a", "flying", "fish", "windsock"], "raw": "The pink back stripe of a flying fish windsock.", "sent_id": 62793, "sent": "the pink back stripe of a flying fish windsock"}], "file_name": "COCO_train2014_000000045680_624428.jpg", "ann_id": 624428, "sent_ids": [62792, 62793], "ref_id": 48007}, {"segmentation": [[333.51, 428.0, 390.2, 367.97, 371.3, 353.52, 393.54, 323.5, 452.46, 300.16, 525.83, 290.15, 591.42, 294.6, 578.08, 422.44]], "area": 26301.13845, "iscrowd": 0, "image_id": 8063, "bbox": [333.51, 290.15, 257.91, 137.85], "category_id": 27, "id": 2072001, "split": "val", "sentences": [{"tokens": ["black", "jacket", "on", "the", "bag"], "raw": "black jacket on the bag", "sent_id": 63045, "sent": "black jacket on the bag"}, {"tokens": ["a", "piece", "of", "luggage", "with", "a", "piece", "of", "black", "clothing", "folded", "on", "top", "of", "it"], "raw": "A piece of luggage with a piece of black clothing folded on top of it.", "sent_id": 63046, "sent": "a piece of luggage with a piece of black clothing folded on top of it"}], "file_name": "COCO_train2014_000000008063_2072001.jpg", "ann_id": 2072001, "sent_ids": [63045, 63046], "ref_id": 48020}, {"segmentation": [[409.1, 365.75, 415.77, 333.51, 421.33, 312.38, 429.11, 302.38, 445.79, 322.39, 454.68, 335.73, 459.13, 364.63, 471.36, 363.52, 470.24, 336.84, 482.47, 336.84, 482.47, 337.95, 505.82, 367.97, 637.0, 355.74, 637.0, 233.45, 612.54, 222.34, 592.53, 191.21, 558.07, 168.98, 532.5, 163.42, 494.7, 167.86, 470.24, 162.31, 446.9, 154.52, 424.66, 176.76, 416.88, 202.33, 413.55, 255.69, 407.99, 292.37, 406.88, 319.05, 404.65, 341.29, 399.1, 364.63]], "area": 39111.379300000015, "iscrowd": 0, "image_id": 351025, "bbox": [399.1, 154.52, 237.9, 213.45], "category_id": 21, "id": 1819824, "split": "val", "sentences": [{"tokens": ["cow", "in", "the", "front", "that", "is", "darkened", "by", "shadow"], "raw": "Cow in the front that is darkened by shadow.", "sent_id": 63114, "sent": "cow in the front that is darkened by shadow"}, {"tokens": ["the", "cow", "in", "the", "shadows", "in", "the", "foreground", "of", "the", "picture"], "raw": "The cow in the shadows in the foreground of the picture", "sent_id": 63115, "sent": "the cow in the shadows in the foreground of the picture"}], "file_name": "COCO_train2014_000000351025_1819824.jpg", "ann_id": 1819824, "sent_ids": [63114, 63115], "ref_id": 48024}, {"segmentation": [[42.41, 313.97, 91.03, 316.03, 107.59, 306.72, 128.28, 300.52, 154.14, 280.86, 175.86, 268.45, 192.41, 255.0, 220.34, 238.45, 246.21, 222.93, 284.48, 211.55, 308.28, 206.38, 328.97, 193.97, 345.52, 183.62, 369.31, 180.52, 397.24, 182.59, 413.79, 185.69, 401.38, 153.62, 404.48, 131.9, 408.62, 125.69, 418.97, 139.14, 428.28, 156.72, 441.72, 189.83, 451.03, 225.0, 456.21, 238.45, 481.03, 233.28, 505.86, 226.03, 533.79, 219.83, 553.45, 207.41, 546.21, 192.93, 538.97, 174.31, 546.21, 168.1, 571.03, 187.76, 582.41, 214.66, 578.28, 240.52, 517.24, 257.07, 524.48, 268.45, 527.59, 287.07, 503.79, 302.59, 470.69, 302.59, 453.1, 316.03, 422.07, 317.07, 391.03, 324.31, 361.03, 324.31, 332.07, 324.31, 316.55, 324.31, 336.21, 342.93, 344.48, 360.52, 344.48, 381.21, 326.9, 395.69, 316.55, 395.69, 303.1, 381.21, 289.66, 380.17, 296.9, 387.41, 298.97, 399.83, 305.17, 417.41, 296.9, 435.0, 286.55, 441.21, 268.97, 438.1, 257.59, 427.76, 264.83, 418.45, 264.83, 402.93, 258.62, 385.34, 255.52, 367.76, 242.07, 362.59, 234.83, 376.03, 220.34, 377.07, 204.83, 378.1, 194.48, 392.59, 189.31, 406.03, 175.86, 417.41, 157.24, 419.48, 136.55, 413.28, 114.83, 400.86, 99.31, 390.52, 84.83, 367.76, 79.66, 354.31, 70.34, 332.59]], "area": 63508.66394999997, "iscrowd": 0, "image_id": 69231, "bbox": [42.41, 125.69, 540.0, 315.52], "category_id": 17, "id": 47368, "split": "val", "sentences": [{"tokens": ["a", "cat", "is", "lying", "on", "a", "white", "cover", "on", "a", "bed"], "raw": "A cat is lying on a white cover on a bed", "sent_id": 63168, "sent": "a cat is lying on a white cover on a bed"}, {"tokens": ["stripped", "cat", "with", "white", "tummy", "laying", "on", "white", "blanket"], "raw": "stripped cat with white tummy laying on white blanket", "sent_id": 63169, "sent": "stripped cat with white tummy laying on white blanket"}], "file_name": "COCO_train2014_000000069231_47368.jpg", "ann_id": 47368, "sent_ids": [63168, 63169], "ref_id": 48025}, {"segmentation": [[269.75, 297.73, 245.74, 309.73, 240.93, 311.33, 218.52, 302.53, 190.51, 302.53, 175.3, 300.93, 162.49, 296.13, 151.28, 288.92, 149.68, 282.52, 153.69, 282.52, 190.51, 279.32, 209.72, 268.91, 231.33, 260.11, 241.74, 252.9, 240.13, 236.09, 244.94, 216.08, 246.54, 210.48, 241.74, 206.48, 236.93, 201.67, 233.73, 196.07, 234.53, 184.86, 240.13, 176.86, 228.13, 172.86, 218.52, 158.45, 225.73, 152.05, 235.33, 152.85, 245.74, 156.85, 272.15, 157.65, 291.36, 162.45, 296.17, 185.66, 298.57, 194.47, 298.57, 220.88, 298.57, 232.89, 300.17, 247.3, 300.97, 264.91, 292.96, 282.52, 287.36, 294.53]], "area": 10986.74745, "iscrowd": 0, "image_id": 535234, "bbox": [149.68, 152.05, 151.29, 159.28], "category_id": 1, "id": 475148, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "sliding", "into", "a", "base"], "raw": "A baseball player sliding into a base.", "sent_id": 63345, "sent": "a baseball player sliding into a base"}, {"tokens": ["baseball", "player", "stealing", "base", ",", "wearing", "the", "number", "12", "sliding", "into", "2nd", "base"], "raw": "Baseball player stealing base, wearing the number 12 sliding into 2nd base.", "sent_id": 63346, "sent": "baseball player stealing base , wearing the number 12 sliding into 2nd base"}], "file_name": "COCO_train2014_000000535234_475148.jpg", "ann_id": 475148, "sent_ids": [63345, 63346], "ref_id": 48032}, {"segmentation": [[172.72, 200.86, 159.13, 191.15, 176.6, 173.69, 186.3, 140.7, 207.65, 121.29, 229.0, 130.99, 238.7, 146.52, 256.16, 165.92, 260.05, 195.03, 256.16, 204.74, 236.76, 228.03, 240.64, 259.08, 256.16, 292.07, 263.93, 311.47, 261.99, 323.12, 254.22, 365.81, 248.4, 400.74, 244.52, 412.39, 223.17, 416.27, 188.24, 420.15, 159.13, 414.33, 100.91, 420.15, 98.97, 420.15, 104.79, 385.22, 98.97, 350.29, 100.91, 334.76, 118.38, 278.48, 122.26, 274.6, 130.02, 251.31, 155.25, 272.66, 172.72, 274.6, 172.72, 266.84, 180.48, 261.02, 174.66, 233.85, 174.66, 222.2, 161.07, 216.38, 157.19, 208.62, 157.19, 198.92]], "area": 32266.4329, "iscrowd": 0, "image_id": 203994, "bbox": [98.97, 121.29, 164.96, 298.86], "category_id": 1, "id": 535209, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "blue", "tank", "top", "smiles", "beside", "a", "taller", "man"], "raw": "A woman in a blue tank top smiles beside a taller man.", "sent_id": 63470, "sent": "a woman in a blue tank top smiles beside a taller man"}, {"tokens": ["smiling", "woman", "wearing", "a", "black", "top", "stands", "with", "a", "man", "near", "the", "sea", "shore"], "raw": "Smiling woman wearing a black top stands with a man near the sea shore", "sent_id": 63471, "sent": "smiling woman wearing a black top stands with a man near the sea shore"}], "file_name": "COCO_train2014_000000203994_535209.jpg", "ann_id": 535209, "sent_ids": [63470, 63471], "ref_id": 48037}, {"segmentation": [[130.88, 133.85, 103.55, 168.37, 97.8, 217.26, 92.04, 231.65, 46.02, 251.78, 35.96, 279.11, 28.76, 290.61, 24.45, 302.12, 17.26, 319.38, 17.26, 338.07, 21.57, 362.52, 23.01, 389.85, 21.57, 417.17, 23.01, 441.62, 24.45, 477.58, 20.13, 516.41, 12.94, 553.8, 12.94, 575.38, 35.96, 607.02, 63.28, 617.08, 188.4, 602.7, 192.72, 573.94, 195.6, 526.48, 197.03, 496.28, 168.27, 451.69, 163.96, 397.04, 197.03, 333.76, 214.29, 309.31, 228.67, 276.23, 238.74, 231.65, 250.25, 182.75, 251.69, 149.67, 222.92, 125.22, 188.4, 112.28, 155.33, 109.4, 140.94, 118.03]], "area": 79307.27475000001, "iscrowd": 0, "image_id": 354391, "bbox": [12.94, 109.4, 238.75, 507.68], "category_id": 1, "id": 529710, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "fedora", "is", "hugging", "a", "girl"], "raw": "A man in a fedora is hugging a girl.", "sent_id": 63616, "sent": "a man in a fedora is hugging a girl"}, {"tokens": ["man", "wearing", "hat", "holding", "child"], "raw": "Man wearing hat holding child.", "sent_id": 63617, "sent": "man wearing hat holding child"}], "file_name": "COCO_train2014_000000354391_529710.jpg", "ann_id": 529710, "sent_ids": [63616, 63617], "ref_id": 48046}, {"segmentation": [[557.04, 152.89, 566.52, 167.11, 623.41, 165.93, 640.0, 161.19, 640.0, 425.48, 632.89, 461.04, 632.89, 461.04, 631.7, 469.33, 407.7, 472.89, 289.19, 471.7, 283.26, 470.52, 277.33, 459.85, 245.33, 442.07, 232.3, 417.19, 242.96, 417.19, 250.07, 419.56, 253.63, 419.56, 216.89, 370.96, 216.89, 363.85, 219.26, 363.85, 229.93, 361.48, 305.78, 414.81, 315.26, 424.3, 304.59, 404.15, 277.33, 354.37, 259.56, 321.19, 259.56, 310.52, 259.56, 308.15, 259.56, 308.15, 257.19, 305.78, 195.56, 284.44, 192.0, 256.0, 194.37, 248.89, 210.96, 231.11, 210.96, 231.11, 188.44, 168.3, 188.44, 117.33, 169.48, 69.93, 169.48, 69.93, 150.52, 43.85, 143.41, 20.15, 143.41, 1.19, 146.96, 0.0, 341.33, 3.56, 457.48, 3.56, 457.48, 3.56, 506.07, 2.37, 508.44, 2.37, 528.59, 18.96, 541.63, 79.41, 541.63, 103.11, 542.81, 126.81, 552.3, 144.59, 557.04, 152.89]], "area": 184279.80469999992, "iscrowd": 0, "image_id": 135539, "bbox": [143.41, 0.0, 496.59, 472.89], "category_id": 1, "id": 1739621, "split": "val", "sentences": [{"tokens": ["a", "man", "with", "facial", "hair", "wearing", "glasses", "eating", "a", "piece", "of", "bread"], "raw": "A man with facial hair wearing glasses eating a piece of bread.", "sent_id": 63905, "sent": "a man with facial hair wearing glasses eating a piece of bread"}, {"tokens": ["a", "man", "with", "glasses", "eating"], "raw": "A man with glasses eating.", "sent_id": 63906, "sent": "a man with glasses eating"}], "file_name": "COCO_train2014_000000135539_1739621.jpg", "ann_id": 1739621, "sent_ids": [63905, 63906], "ref_id": 48057}, {"segmentation": [[143.76, 382.34, 140.33, 313.74, 148.91, 306.88, 184.06, 331.75, 201.21, 325.75, 208.07, 313.74, 274.1, 299.17, 262.95, 293.16, 263.81, 285.45, 273.24, 282.02, 292.1, 293.16, 294.68, 294.02, 323.83, 288.02, 331.55, 298.31, 333.26, 313.74, 346.13, 320.6, 343.55, 399.49, 341.84, 400.35, 341.84, 433.79, 338.41, 437.22, 330.69, 433.79, 327.26, 413.21, 212.36, 444.94, 209.79, 460.37, 210.64, 480.0, 204.64, 479.24, 197.78, 444.08, 191.78, 438.08]], "area": 24460.438099999996, "iscrowd": 0, "image_id": 55226, "bbox": [140.33, 282.02, 205.8, 197.98], "category_id": 62, "id": 1936786, "split": "val", "sentences": [{"tokens": ["a", "white", "chair", "in", "a", "living", "room", "near", "a", "grey", "couch", "and", "two", "recliners"], "raw": "A white chair in a living room near a grey couch and two recliners.", "sent_id": 64525, "sent": "a white chair in a living room near a grey couch and two recliners"}, {"tokens": ["a", "single", "-", "seat", "white", "sofa"], "raw": "A single-seat white sofa.", "sent_id": 64526, "sent": "a single - seat white sofa"}], "file_name": "COCO_train2014_000000055226_1936786.jpg", "ann_id": 1936786, "sent_ids": [64525, 64526], "ref_id": 48084}, {"segmentation": [[303.17, 222.25, 292.12, 224.46, 277.4, 208.26, 242.79, 188.38, 246.47, 175.86, 243.52, 153.02, 301.69, 136.83, 329.68, 143.45, 358.4, 159.66, 386.39, 182.48, 390.06, 212.67, 391.54, 220.77, 359.87, 226.67, 352.51, 236.98, 307.59, 227.41, 305.38, 243.6, 311.27, 246.55, 317.16, 236.98, 318.64, 242.87, 310.53, 250.97, 298.02, 245.82, 302.43, 225.2]], "area": 10217.403250000001, "iscrowd": 0, "image_id": 24808, "bbox": [242.79, 136.83, 148.75, 114.14], "category_id": 28, "id": 283834, "split": "val", "sentences": [{"tokens": ["umbrella", "white", "orange", "and", "black"], "raw": "umbrella white orange and black", "sent_id": 64791, "sent": "umbrella white orange and black"}, {"tokens": ["the", "umbrella", "of", "the", "woman", "in", "front"], "raw": "The umbrella of the woman in front", "sent_id": 64792, "sent": "the umbrella of the woman in front"}], "file_name": "COCO_train2014_000000024808_283834.jpg", "ann_id": 283834, "sent_ids": [64791, 64792], "ref_id": 48095}, {"segmentation": [[286.62, 262.63, 278.92, 244.36, 277.96, 222.24, 276.04, 219.35, 271.23, 198.19, 284.69, 127.98, 285.65, 103.94, 286.62, 93.36, 299.12, 85.66, 345.29, 88.55, 387.6, 86.63, 428.0, 78.93, 488.59, 87.59, 534.76, 112.59, 564.58, 139.52, 580.93, 175.11, 575.16, 287.64, 573.23, 301.11, 566.5, 303.99, 569.38, 293.41, 572.27, 208.77, 570.35, 190.5, 566.5, 208.77, 564.58, 219.35, 559.77, 227.05, 559.77, 279.95, 562.65, 312.65, 562.65, 325.15, 562.65, 335.73, 484.75, 344.39, 504.94, 317.46, 503.98, 283.79, 506.87, 265.52, 498.21, 256.86, 494.36, 246.28, 492.44, 244.36, 414.53, 228.97, 405.88, 242.44, 398.18, 244.36, 392.41, 283.79, 395.3, 314.57, 400.11, 328.04, 401.07, 333.81, 378.95, 335.73, 355.87, 329.0, 349.13, 322.27, 361.64, 321.3, 369.33, 310.72, 359.71, 283.79, 364.52, 266.48, 359.71, 248.21, 363.56, 214.55, 363.56, 201.08, 358.75, 196.27, 346.25, 186.65, 336.63, 183.77, 322.2, 189.54, 315.47, 191.46, 310.66, 191.46, 302.97, 204.93, 300.08, 205.89, 293.35, 213.58, 302.97, 274.18, 301.04, 297.26, 301.04, 314.57, 310.66, 314.57, 310.66, 320.34, 296.23, 312.65, 291.42, 302.07]], "area": 50138.43385, "iscrowd": 0, "image_id": 356535, "bbox": [271.23, 78.93, 309.7, 265.46], "category_id": 22, "id": 580419, "split": "val", "sentences": [{"tokens": ["larger", "elephant"], "raw": "larger elephant", "sent_id": 64826, "sent": "larger elephant"}, {"tokens": ["larger", "elephant"], "raw": "larger elephant", "sent_id": 64827, "sent": "larger elephant"}], "file_name": "COCO_train2014_000000356535_580419.jpg", "ann_id": 580419, "sent_ids": [64826, 64827], "ref_id": 48097}, {"segmentation": [[194.62, 90.17, 202.4, 60.98, 197.54, 42.49, 165.43, 40.55, 141.1, 69.74, 109.96, 95.04, 135.26, 114.5, 126.5, 144.67, 128.45, 166.07, 109.96, 205.0, 120.66, 226.41, 131.37, 206.94, 145.96, 192.35, 109.96, 267.28, 116.77, 343.18, 124.56, 357.77, 112.88, 371.4, 97.31, 386.32, 119.69, 393.13, 160.56, 376.59, 145.96, 353.23, 139.15, 280.25, 168.35, 245.22, 189.75, 243.27, 272.47, 364.91, 302.63, 393.13, 312.36, 371.72, 289.01, 348.37, 264.68, 289.01, 253.0, 274.41, 234.52, 194.62, 230.62, 161.53, 299.71, 147.91, 309.44, 129.42, 292.9, 127.48, 275.39, 129.42, 267.6, 141.1, 236.46, 139.15, 217.97, 94.39]], "area": 31030.189500000008, "iscrowd": 0, "image_id": 333546, "bbox": [97.31, 40.55, 215.05, 352.58], "category_id": 1, "id": 428051, "split": "val", "sentences": [{"tokens": ["the", "woman", "on", "the", "left"], "raw": "The woman on the left.", "sent_id": 65397, "sent": "the woman on the left"}], "file_name": "COCO_train2014_000000333546_428051.jpg", "ann_id": 428051, "sent_ids": [65397], "ref_id": 48122}, {"segmentation": [[427.0, 318.57, 347.36, 312.81, 335.84, 306.1, 328.17, 300.34, 313.77, 291.7, 298.42, 250.44, 296.5, 216.86, 298.42, 183.27, 298.42, 179.44, 300.34, 163.12, 308.98, 145.85, 311.85, 141.05, 276.35, 118.02, 273.47, 105.55, 272.51, 89.24, 264.84, 85.4, 256.2, 85.4, 255.24, 40.3, 257.16, 25.91, 261.96, 21.11, 269.63, 20.15, 283.07, 23.03, 284.99, 21.11, 303.22, 9.6, 338.72, 13.43, 386.7, 46.06, 403.97, 45.1, 428.92, 56.61, 462.5, 61.41, 477.86, 53.73, 489.37, 46.06, 510.48, 38.38, 522.96, 36.46, 552.7, 47.02, 565.18, 50.86, 569.01, 73.89, 562.3, 104.59, 529.67, 176.56, 519.12, 236.05, 496.09, 290.74]], "area": 66675.24979999999, "iscrowd": 0, "image_id": 330716, "bbox": [255.24, 9.6, 313.77, 308.97], "category_id": 86, "id": 1667690, "split": "val", "sentences": [{"tokens": ["a", "pitcher", "with", "gold", "handle"], "raw": "A pitcher with gold handle.", "sent_id": 65556, "sent": "a pitcher with gold handle"}, {"tokens": ["a", "pitcher", "with", "white", "men", "on", "it"], "raw": "A pitcher with white men on it.", "sent_id": 65557, "sent": "a pitcher with white men on it"}], "file_name": "COCO_train2014_000000330716_1667690.jpg", "ann_id": 1667690, "sent_ids": [65556, 65557], "ref_id": 48127}, {"segmentation": [[354.32, 271.34, 383.23, 290.39, 441.06, 300.25, 453.54, 305.51, 458.14, 343.62, 434.49, 351.5, 431.2, 365.3, 458.8, 362.02, 461.43, 384.36, 470.63, 408.67, 496.91, 408.02, 474.57, 358.73, 497.57, 336.39, 485.74, 298.28, 510.71, 281.2, 519.25, 254.91, 540.28, 222.71, 572.48, 258.92, 594.82, 255.64, 590.88, 209.64, 586.28, 182.04, 568.54, 151.82, 561.97, 167.59, 514.0, 168.9, 479.17, 186.64, 445.0, 201.1, 414.78, 203.07, 365.49, 197.81, 327.38, 192.56, 290.58, 207.67, 278.76, 238.55, 279.41, 270.75, 259.04, 327.26, 263.64, 357.49, 284.01, 344.35, 285.98, 300.32, 295.84, 368.0, 316.21, 379.83, 349.07, 385.09, 322.12, 323.32, 350.38, 272.72]], "area": 36911.62614999999, "iscrowd": 0, "image_id": 182706, "bbox": [259.04, 151.82, 335.78, 256.85], "category_id": 19, "id": 55177, "split": "val", "sentences": [{"tokens": ["the", "horse", "that", "is", "fully", "visible"], "raw": "The horse that is fully visible", "sent_id": 66610, "sent": "the horse that is fully visible"}, {"tokens": ["horse", "in", "front", ",", "whose", "body", "is", "fully", "visible"], "raw": "Horse in front, whose body is fully visible", "sent_id": 66611, "sent": "horse in front , whose body is fully visible"}], "file_name": "COCO_train2014_000000182706_55177.jpg", "ann_id": 55177, "sent_ids": [66610, 66611], "ref_id": 48169}, {"segmentation": [[307.42, 310.32, 314.97, 261.78, 350.56, 211.09, 394.79, 184.12, 457.35, 175.49, 519.91, 175.49, 586.79, 211.09, 621.3, 260.7, 631.01, 314.64, 611.6, 381.51, 568.45, 447.31, 530.7, 469.96, 447.64, 471.04, 394.79, 464.57, 361.35, 439.76, 348.4, 422.5, 336.54, 402.01, 312.81, 363.18]], "area": 76838.58914999999, "iscrowd": 0, "image_id": 29473, "bbox": [307.42, 175.49, 323.59, 295.55], "category_id": 51, "id": 715541, "split": "val", "sentences": [{"tokens": ["a", "bowl", "filled", "with", "fried", "greens"], "raw": "A bowl filled with fried greens.", "sent_id": 66618, "sent": "a bowl filled with fried greens"}, {"tokens": ["cooked", "zucchini"], "raw": "cooked zucchini", "sent_id": 66619, "sent": "cooked zucchini"}], "file_name": "COCO_train2014_000000029473_715541.jpg", "ann_id": 715541, "sent_ids": [66618, 66619], "ref_id": 48170}, {"segmentation": [[529.29, 113.66, 439.03, 100.29, 361.03, 94.71, 362.14, 3.34, 596.14, 5.57, 605.06, 23.4, 587.23, 63.51, 551.57, 81.34, 530.4, 85.8]], "area": 21271.824900000003, "iscrowd": 0, "image_id": 48707, "bbox": [361.03, 3.34, 244.03, 110.32], "category_id": 47, "id": 1882562, "split": "val", "sentences": [{"tokens": ["a", "tea", "cup", "with", "blue", "pattern", "on", "saucer", "next", "to", "a", "bowl", "full", "of", "edibles"], "raw": "A tea cup with blue pattern on saucer next to a bowl full of edibles.", "sent_id": 66975, "sent": "a tea cup with blue pattern on saucer next to a bowl full of edibles"}, {"tokens": ["blurred", "white", "coffee", "cup"], "raw": "blurred white coffee cup", "sent_id": 66976, "sent": "blurred white coffee cup"}], "file_name": "COCO_train2014_000000048707_1882562.jpg", "ann_id": 1882562, "sent_ids": [66975, 66976], "ref_id": 48188}, {"segmentation": [[333.0, 221.22, 326.73, 202.39, 324.84, 186.7, 320.45, 173.52, 309.78, 166.61, 297.22, 170.38, 286.55, 187.95, 280.9, 220.59, 271.49, 223.73, 262.07, 228.75, 247.01, 283.99, 250.15, 290.27, 268.35, 291.52, 265.84, 321.15, 260.19, 343.12, 263.96, 366.97, 269.61, 383.92, 267.72, 400.87, 271.49, 408.4, 270.86, 414.05, 332.37, 413.42, 331.75, 245.2, 332.37, 221.35]], "area": 15497.94515, "iscrowd": 0, "image_id": 522062, "bbox": [247.01, 166.61, 85.99, 247.44], "category_id": 1, "id": 541602, "split": "val", "sentences": [{"tokens": ["the", "woman", "with", "black", "hair", "and", "a", "black", "shirt"], "raw": "The woman with black hair and a black shirt", "sent_id": 67144, "sent": "the woman with black hair and a black shirt"}, {"tokens": ["women", "in", "all", "black"], "raw": "Women in all black", "sent_id": 67145, "sent": "women in all black"}], "file_name": "COCO_train2014_000000522062_541602.jpg", "ann_id": 541602, "sent_ids": [67144, 67145], "ref_id": 48199}, {"segmentation": [[491.24, 219.31, 492.37, 184.46, 503.61, 167.6, 508.1, 159.73, 500.23, 147.37, 485.62, 146.24, 478.88, 137.25, 472.13, 123.76, 468.76, 102.4, 472.13, 87.79, 476.63, 72.05, 493.49, 63.06, 510.35, 64.18, 520.47, 67.56, 535.08, 75.42, 542.95, 85.54, 548.57, 113.64, 546.32, 126.01, 541.83, 133.88, 555.32, 140.62, 568.81, 144.0, 575.55, 148.49, 585.67, 165.35, 595.78, 211.44, 598.03, 247.42, 604.78, 291.26, 611.52, 319.36, 592.41, 381.19, 583.42, 409.29, 584.54, 432.9, 591.29, 457.63, 600.28, 475.61, 502.48, 477.86, 515.97, 429.52, 522.72, 391.3, 518.22, 367.7, 509.23, 341.84, 509.23, 314.86, 506.98, 276.64, 500.23, 247.42, 488.99, 256.41, 467.63, 263.15, 458.64, 256.41, 441.78, 242.92, 445.15, 228.31, 456.39, 229.43, 480.0, 228.31, 485.62, 226.06]], "area": 36311.60824999999, "iscrowd": 0, "image_id": 436025, "bbox": [441.78, 63.06, 169.74, 414.8], "category_id": 1, "id": 503701, "split": "val", "sentences": [{"tokens": ["a", "woman", "playing", "wii"], "raw": "A woman playing wii", "sent_id": 67397, "sent": "a woman playing wii"}, {"tokens": ["a", "woman", "playing", "wii"], "raw": "A woman playing Wii.", "sent_id": 67398, "sent": "a woman playing wii"}], "file_name": "COCO_train2014_000000436025_503701.jpg", "ann_id": 503701, "sent_ids": [67397, 67398], "ref_id": 48208}, {"segmentation": [[87.9, 238.13, 87.9, 251.84, 94.35, 288.13, 100.0, 300.23, 137.1, 309.1, 137.1, 371.2, 0.81, 369.58, 0.0, 232.49, 48.39, 228.45, 75.0, 233.29]], "area": 15681.146699999998, "iscrowd": 0, "image_id": 479396, "bbox": [0.0, 228.45, 137.1, 142.75], "category_id": 63, "id": 113877, "split": "val", "sentences": [{"tokens": ["a", "maroon", "velvet", "chair", "with", "matching", "pillow", "in", "a", "livingroom"], "raw": "a maroon velvet chair with matching pillow in a livingroom", "sent_id": 67904, "sent": "a maroon velvet chair with matching pillow in a livingroom"}, {"tokens": ["a", "maroon", "couch", "with", "a", "video", "game", "system", "box", "on", "top"], "raw": "A maroon couch with a video game system box on top.", "sent_id": 67905, "sent": "a maroon couch with a video game system box on top"}], "file_name": "COCO_train2014_000000479396_113877.jpg", "ann_id": 113877, "sent_ids": [67904, 67905], "ref_id": 48229}, {"segmentation": [[1.68, 193.48, 81.56, 157.33, 132.01, 145.56, 181.61, 132.1, 220.29, 125.38, 252.24, 122.86, 266.54, 126.22, 265.7, 137.99, 279.15, 142.19, 285.03, 148.08, 286.72, 162.37, 287.56, 174.99, 287.56, 190.12, 287.56, 205.26, 283.35, 230.48, 290.92, 264.11, 278.31, 292.7, 270.74, 333.9, 279.99, 350.71, 282.51, 352.4, 279.99, 365.01, 282.51, 367.53, 1.68, 369.21]], "area": 62011.02464999999, "iscrowd": 0, "image_id": 421298, "bbox": [1.68, 122.86, 289.24, 246.35], "category_id": 67, "id": 390502, "split": "val", "sentences": [{"tokens": ["salad", "on", "a", "plate"], "raw": "Salad on a plate", "sent_id": 69031, "sent": "salad on a plate"}, {"tokens": ["a", "side", "dish", "consisting", "of", "radishes", "and", "lettuce"], "raw": "A side dish consisting of radishes and lettuce", "sent_id": 69032, "sent": "a side dish consisting of radishes and lettuce"}], "file_name": "COCO_train2014_000000421298_390502.jpg", "ann_id": 390502, "sent_ids": [69031, 69032], "ref_id": 48280}, {"segmentation": [[404.49, 97.08, 408.81, 85.21, 426.07, 86.29, 436.85, 90.61, 445.48, 96.0, 445.48, 96.0, 461.66, 96.0, 508.04, 94.92, 520.99, 88.45, 547.96, 93.84, 559.82, 94.92, 573.84, 98.16, 587.87, 96.0, 598.65, 101.39, 614.83, 107.87, 629.93, 113.26, 638.56, 117.57, 640.0, 140.22, 640.0, 160.72, 631.01, 170.43, 634.25, 198.47, 632.09, 223.28, 612.67, 244.85, 597.57, 255.64, 586.79, 266.43, 601.89, 259.96, 613.75, 262.11, 612.67, 258.88, 621.3, 252.4, 629.93, 241.62, 639.64, 230.83, 640.0, 227.6, 640.0, 473.53, 602.97, 474.61, 557.66, 473.53, 535.01, 465.98, 531.78, 460.58, 506.97, 434.7, 485.39, 423.91, 473.53, 423.91, 461.66, 420.67, 459.51, 409.89, 441.17, 395.87, 434.7, 398.02, 434.7, 387.24, 408.81, 372.13, 381.84, 354.88, 376.45, 354.88, 376.45, 343.01, 384.0, 324.67, 385.08, 299.87, 387.24, 282.61, 387.24, 267.51, 392.63, 250.25, 394.79, 238.38, 394.79, 220.04, 401.26, 209.26, 403.42, 209.26, 421.75, 211.42, 422.83, 203.87, 439.01, 203.87, 446.56, 196.31, 449.8, 190.92, 453.03, 180.13, 455.19, 176.9, 456.27, 166.11, 475.69, 162.88, 486.47, 154.25, 486.47, 145.62, 467.06, 124.04, 415.28, 106.79, 404.49, 104.63]], "area": 77151.19544999997, "iscrowd": 0, "image_id": 186336, "bbox": [376.45, 85.21, 263.55, 389.4], "category_id": 88, "id": 1159213, "split": "val", "sentences": [{"tokens": ["the", "gray", "stuffed", "animal", "in", "the", "red", "and", "white", "stripes"], "raw": "The gray stuffed animal in the red and white stripes.", "sent_id": 69371, "sent": "the gray stuffed animal in the red and white stripes"}, {"tokens": ["a", "light", "brown", "teddy", "bear", "wearing", "a", "red", "and", "white", "striped", "shirt"], "raw": "A light brown teddy bear wearing a red and white striped shirt.", "sent_id": 69372, "sent": "a light brown teddy bear wearing a red and white striped shirt"}], "file_name": "COCO_train2014_000000186336_1159213.jpg", "ann_id": 1159213, "sent_ids": [69371, 69372], "ref_id": 48300}, {"segmentation": [[521.88, 251.76, 527.57, 230.41, 546.08, 195.54, 543.23, 180.59, 528.29, 144.3, 499.11, 122.95, 503.38, 86.65, 484.16, 65.31, 457.12, 67.44, 442.18, 78.11, 440.75, 98.75, 451.43, 120.81, 454.99, 129.35, 460.68, 135.76, 446.45, 154.97, 433.64, 194.11, 432.21, 214.04, 423.67, 221.16, 441.46, 221.87, 444.31, 212.62, 447.87, 194.82, 454.99, 190.55, 477.05, 197.67, 501.95, 198.38, 520.46, 194.11, 521.88, 177.74, 529.0, 191.27, 511.92, 233.25, 510.49, 231.83, 509.07, 231.12, 506.22, 238.95, 505.51, 251.04, 520.46, 252.47, 520.46, 254.6]], "area": 10420.920200000002, "iscrowd": 0, "image_id": 304408, "bbox": [423.67, 65.31, 122.41, 189.29], "category_id": 1, "id": 444486, "split": "val", "sentences": [{"tokens": ["the", "child", "looking", "at", "the", "giraffe"], "raw": "The child looking at the giraffe.", "sent_id": 69960, "sent": "the child looking at the giraffe"}, {"tokens": ["a", "young", "girl", "wearing", "a", "brown", "shirt", ",", "held", "up", "by", "an", "older", "man", "wearing", "glasses"], "raw": "A young girl wearing a brown shirt, held up by an older man wearing glasses.", "sent_id": 69961, "sent": "a young girl wearing a brown shirt , held up by an older man wearing glasses"}], "file_name": "COCO_train2014_000000304408_444486.jpg", "ann_id": 444486, "sent_ids": [69960, 69961], "ref_id": 48319}, {"segmentation": [[256.72, 286.92, 238.38, 225.44, 229.75, 202.79, 225.44, 171.51, 222.2, 147.78, 198.47, 136.99, 175.82, 141.3, 152.09, 146.7, 106.79, 151.01, 73.35, 145.62, 43.15, 143.46, 3.24, 144.54, 1.08, 303.1, 252.4, 288.0]], "area": 35403.49865000001, "iscrowd": 0, "image_id": 421086, "bbox": [1.08, 136.99, 255.64, 166.11], "category_id": 59, "id": 1077251, "split": "val", "sentences": [{"tokens": ["pizza", "in", "front", "of", "white", "apron"], "raw": "Pizza in front of white apron.", "sent_id": 70177, "sent": "pizza in front of white apron"}, {"tokens": ["cheese", "pizza", "on", "a", "pan"], "raw": "Cheese pizza on a pan", "sent_id": 70178, "sent": "cheese pizza on a pan"}], "file_name": "COCO_train2014_000000421086_1077251.jpg", "ann_id": 1077251, "sent_ids": [70177, 70178], "ref_id": 48326}, {"segmentation": [[234.66, 143.85, 245.84, 125.97, 251.05, 114.05, 262.23, 105.86, 277.87, 90.96, 286.81, 92.45, 295.01, 108.84, 301.71, 130.44, 300.22, 151.3, 294.26, 161.73, 280.11, 156.51, 280.11, 152.79, 266.7, 151.3, 248.82, 152.05], [136.33, 135.66, 108.02, 143.85, 92.38, 156.51, 81.2, 170.67, 95.36, 181.1, 103.55, 195.25, 109.51, 209.41, 111.0, 221.33, 107.28, 232.5, 104.3, 248.15, 107.28, 264.54, 109.51, 277.94, 111.0, 289.12, 118.45, 275.71, 117.7, 242.93, 129.62, 263.05, 133.35, 285.39, 138.56, 292.84, 142.29, 270.49, 135.58, 243.68, 137.07, 227.29, 144.52, 211.64, 173.58, 229.52, 209.34, 222.82, 197.42, 198.98, 192.95, 181.1, 184.75, 169.92, 169.85, 171.41, 163.89, 154.28, 163.15, 147.58]], "area": 11584.254649999999, "iscrowd": 0, "image_id": 523577, "bbox": [81.2, 90.96, 220.51, 201.88], "category_id": 24, "id": 590860, "split": "val", "sentences": [{"tokens": ["a", "zebra", "resting", "its", "head", "on", "another", "zebra", "'", "s", "back"], "raw": "A zebra resting its head on another zebra's back.", "sent_id": 70765, "sent": "a zebra resting its head on another zebra ' s back"}, {"tokens": ["a", "zebra", "with", "it", "'", "s", "head", "draped", "over", "the", "back", "of", "another", "zebra"], "raw": "A zebra with it's head draped over the back of another zebra.", "sent_id": 70766, "sent": "a zebra with it ' s head draped over the back of another zebra"}], "file_name": "COCO_train2014_000000523577_590860.jpg", "ann_id": 590860, "sent_ids": [70765, 70766], "ref_id": 48352}, {"segmentation": [[545.91, 308.33, 639.17, 267.3, 639.17, 472.48, 387.98, 480.0, 405.39, 467.5, 499.9, 392.89]], "area": 27747.81565, "iscrowd": 0, "image_id": 55873, "bbox": [387.98, 267.3, 251.19, 212.7], "category_id": 67, "id": 1963610, "split": "val", "sentences": [{"tokens": ["the", "green", "granite", "table", "top"], "raw": "The green granite table top", "sent_id": 71523, "sent": "the green granite table top"}, {"tokens": ["the", "portion", "of", "granite", "counter", "under", "the", "cutting", "board"], "raw": "The portion of granite counter under the cutting board.", "sent_id": 71524, "sent": "the portion of granite counter under the cutting board"}], "file_name": "COCO_train2014_000000055873_1963610.jpg", "ann_id": 1963610, "sent_ids": [71523, 71524], "ref_id": 48387}, {"segmentation": [[269.33, 378.98, 301.07, 325.12, 311.65, 312.61, 378.98, 302.99, 462.67, 291.45, 569.43, 274.14, 564.63, 267.4, 569.43, 259.71, 565.59, 255.86, 569.43, 245.28, 592.52, 229.89, 601.18, 219.31, 608.87, 126.01, 637.73, 133.7, 640.0, 421.3, 265.48, 421.3, 278.95, 396.3, 280.87, 386.68, 265.48, 379.94, 273.17, 371.29]], "area": 52567.058700000016, "iscrowd": 0, "image_id": 54318, "bbox": [265.48, 126.01, 374.52, 295.29], "category_id": 65, "id": 1612459, "split": "val", "sentences": [{"tokens": ["the", "bed", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the bed on the right in the right hand picture", "sent_id": 71580, "sent": "the bed on the right in the right hand picture"}], "file_name": "COCO_train2014_000000054318_1612459.jpg", "ann_id": 1612459, "sent_ids": [71580], "ref_id": 48391}, {"segmentation": [[2.49, 58.6, 117.19, 1.25, 640.0, 1.25, 637.09, 265.56, 549.82, 304.21, 514.91, 374.03, 381.51, 480.0, 150.86, 480.0, 0.0, 480.0]], "area": 272420.9357, "iscrowd": 0, "image_id": 55873, "bbox": [0.0, 1.25, 640.0, 478.75], "category_id": 67, "id": 1961301, "split": "val", "sentences": [{"tokens": ["plate", "with", "fruit"], "raw": "plate with fruit", "sent_id": 72893, "sent": "plate with fruit"}, {"tokens": ["a", "white", "and", "blue", "bowl", "full", "of", "fruit"], "raw": "A white and blue bowl full of fruit", "sent_id": 72894, "sent": "a white and blue bowl full of fruit"}], "file_name": "COCO_train2014_000000055873_1961301.jpg", "ann_id": 1961301, "sent_ids": [72893, 72894], "ref_id": 48437}, {"segmentation": [[503.54, 226.88, 499.71, 197.2, 491.1, 180.93, 483.44, 163.7, 478.65, 155.08, 474.82, 149.34, 460.46, 162.74, 453.76, 155.08, 460.46, 135.94, 462.38, 118.71, 459.51, 107.22, 466.21, 103.39, 477.69, 112.96, 482.48, 106.26, 515.03, 132.11, 517.9, 135.94, 527.47, 138.81, 552.36, 132.11, 568.64, 128.28, 583.0, 133.07, 593.53, 146.47, 598.31, 140.72, 610.76, 149.34, 605.97, 159.87, 602.14, 158.91, 594.49, 180.93, 599.27, 197.2, 601.19, 215.39, 610.76, 242.2, 595.44, 234.54, 596.4, 219.22, 582.04, 187.63, 585.87, 205.82, 583.96, 237.41, 577.25, 232.62, 577.25, 207.73, 567.68, 191.46, 554.28, 196.25, 529.39, 197.2, 517.9, 190.5, 517.9, 220.18, 517.9, 235.5, 513.11, 230.71, 508.33, 206.78, 508.33, 229.75]], "area": 9784.834099999998, "iscrowd": 0, "image_id": 253942, "bbox": [453.76, 103.39, 157.0, 138.81], "category_id": 24, "id": 593570, "split": "val", "sentences": [{"tokens": ["the", "zebra", "on", "the", "extreme", "right", "hand", "side", "looking", "other", "zebras"], "raw": "The zebra on the extreme right hand side looking other zebras", "sent_id": 73430, "sent": "the zebra on the extreme right hand side looking other zebras"}, {"tokens": ["the", "zebra", "on", "the", "right"], "raw": "the zebra on the right", "sent_id": 73431, "sent": "the zebra on the right"}], "file_name": "COCO_train2014_000000253942_593570.jpg", "ann_id": 593570, "sent_ids": [73430, 73431], "ref_id": 48472}, {"segmentation": [[399.24, 220.43, 415.32, 209.08, 415.32, 203.4, 409.65, 196.78, 408.7, 177.86, 430.46, 175.97, 438.03, 185.43, 431.41, 202.46, 433.3, 214.76, 446.54, 216.65, 452.22, 236.52, 450.33, 281.93, 457.9, 295.17, 447.49, 305.58, 454.11, 386.94, 438.03, 386.0, 428.57, 305.58, 421.95, 295.17, 420.05, 388.83, 398.29, 388.83, 403.97, 375.59, 400.19, 374.64, 406.81, 344.37, 400.19, 295.17, 391.67, 297.07, 398.29, 215.7, 406.81, 214.76]], "area": 8736.493550000003, "iscrowd": 0, "image_id": 405777, "bbox": [391.67, 175.97, 66.23, 212.86], "category_id": 1, "id": 224072, "split": "val", "sentences": [{"tokens": ["a", "woman", "standing", "next", "to", "a", "horse", "head", "sculpture"], "raw": "A woman standing next to a horse head sculpture.", "sent_id": 73567, "sent": "a woman standing next to a horse head sculpture"}, {"tokens": ["a", "women", "wearing", "a", "white", "top"], "raw": "A women wearing a white top", "sent_id": 73568, "sent": "a women wearing a white top"}], "file_name": "COCO_train2014_000000405777_224072.jpg", "ann_id": 224072, "sent_ids": [73567, 73568], "ref_id": 48480}, {"segmentation": [[3.24, 473.35, 0.0, 374.11, 151.01, 459.33, 156.4, 475.51]], "area": 8588.303, "iscrowd": 0, "image_id": 291493, "bbox": [0.0, 374.11, 156.4, 101.4], "category_id": 67, "id": 1090879, "split": "val", "sentences": [{"tokens": ["part", "of", "table", "completely", "in", "shadows"], "raw": "Part of table completely in shadows.", "sent_id": 73613, "sent": "part of table completely in shadows"}, {"tokens": ["the", "shaded", "area", "to", "the", "bottom", "left", "of", "the", "plate"], "raw": "The shaded area to the bottom left of the plate.", "sent_id": 73614, "sent": "the shaded area to the bottom left of the plate"}], "file_name": "COCO_train2014_000000291493_1090879.jpg", "ann_id": 1090879, "sent_ids": [73613, 73614], "ref_id": 48485}, {"segmentation": [[121.57, 332.56, 134.63, 287.35, 141.66, 267.25, 174.82, 259.21, 208.98, 263.23, 234.1, 267.25, 222.04, 273.28, 220.03, 293.37, 224.05, 311.46, 247.16, 318.49, 261.22, 323.52, 252.18, 368.73, 242.13, 383.8, 216.01, 383.8, 157.74, 368.73, 120.56, 352.65, 117.55, 339.59, 123.58, 329.54]], "area": 12469.035950000001, "iscrowd": 0, "image_id": 504744, "bbox": [117.55, 259.21, 143.67, 124.59], "category_id": 53, "id": 1048911, "split": "val", "sentences": [{"tokens": ["a", "ripe", "apple", "between", "two", "oranges"], "raw": "A ripe apple between two oranges", "sent_id": 74253, "sent": "a ripe apple between two oranges"}, {"tokens": ["red", "apple", "between", "two", "oranges", "on", "bottom", "left", "of", "bowl"], "raw": "red apple between two oranges on bottom left of bowl", "sent_id": 74254, "sent": "red apple between two oranges on bottom left of bowl"}], "file_name": "COCO_train2014_000000504744_1048911.jpg", "ann_id": 1048911, "sent_ids": [74253, 74254], "ref_id": 48512}, {"segmentation": [[2.89, 142.41, 28.92, 163.62, 55.91, 202.17, 71.33, 260.97, 78.07, 287.0, 78.07, 315.91, 73.26, 330.37, 20.24, 339.05, 4.82, 325.55, 3.86, 275.43, 3.86, 250.37, 3.86, 200.25, 4.82, 154.94]], "area": 10492.830750000001, "iscrowd": 0, "image_id": 533220, "bbox": [2.89, 142.41, 75.18, 196.64], "category_id": 1, "id": 557475, "split": "val", "sentences": [{"tokens": ["woman", "with", "long", "dark", "hair", "in", "denim", "shirt", ",", "far", "left", "of", "picture"], "raw": "Woman with long dark hair in denim shirt, far left of picture.", "sent_id": 74467, "sent": "woman with long dark hair in denim shirt , far left of picture"}, {"tokens": ["a", "woman", "off", "to", "the", "left", "with", "a", "demin", "jacket", "on"], "raw": "A woman off to the left with  a demin jacket on", "sent_id": 74468, "sent": "a woman off to the left with a demin jacket on"}], "file_name": "COCO_train2014_000000533220_557475.jpg", "ann_id": 557475, "sent_ids": [74467, 74468], "ref_id": 48517}, {"segmentation": [[220.04, 473.53, 217.89, 454.11, 227.6, 396.94, 201.71, 280.45, 182.29, 229.75, 146.7, 214.65, 165.03, 184.45, 177.98, 167.19, 170.43, 151.01, 168.27, 127.28, 145.62, 103.55, 99.24, 104.63, 81.98, 122.97, 78.74, 162.88, 79.82, 183.37, 58.25, 196.31, 48.54, 206.02, 1.08, 224.36, 4.31, 473.53]], "area": 63275.050449999995, "iscrowd": 0, "image_id": 408954, "bbox": [1.08, 103.55, 226.52, 369.98], "category_id": 1, "id": 488371, "split": "val", "sentences": [{"tokens": ["a", "gray", "haired", "man", "wearing", "glasses", "and", "a", "gray", "coat"], "raw": "A gray haired man wearing glasses and a gray coat.", "sent_id": 74959, "sent": "a gray haired man wearing glasses and a gray coat"}, {"tokens": ["a", "balding", "man", "with", "a", "brown", "coat", "and", "glasses"], "raw": "A balding man with a brown coat and glasses", "sent_id": 74960, "sent": "a balding man with a brown coat and glasses"}], "file_name": "COCO_train2014_000000408954_488371.jpg", "ann_id": 488371, "sent_ids": [74959, 74960], "ref_id": 48543}, {"segmentation": [[291.74, 192.06, 274.05, 186.37, 254.47, 175.64, 234.26, 162.37, 282.9, 178.79, 298.06, 184.48, 344.8, 226.17, 387.12, 264.7, 470.5, 346.81, 458.5, 354.39, 428.18, 324.07, 368.8, 264.7, 327.11, 223.01]], "area": 3258.7957000000006, "iscrowd": 0, "image_id": 79111, "bbox": [234.26, 162.37, 236.24, 192.02], "category_id": 50, "id": 708800, "split": "val", "sentences": [{"tokens": ["the", "bottom", "most", "wooden", "spoon", "closest", "to", "the", "apples"], "raw": "The bottom most wooden spoon closest to the apples", "sent_id": 74978, "sent": "the bottom most wooden spoon closest to the apples"}], "file_name": "COCO_train2014_000000079111_708800.jpg", "ann_id": 708800, "sent_ids": [74978], "ref_id": 48545}, {"segmentation": [[455.18, 110.3, 454.74, 109.0, 462.56, 99.44, 453.87, 79.45, 462.13, 89.44, 466.04, 99.44, 468.21, 99.44, 466.04, 86.84, 468.65, 82.49, 492.11, 72.06, 486.9, 61.95, 478.21, 28.05, 470.82, 0.0, 541.21, 0.0, 556.35, 36.06, 570.85, 29.37, 572.53, 32.16, 587.02, 26.58, 609.33, 16.55, 607.1, 4.28, 607.66, 0.29, 639.44, 0.0, 640.0, 20.92, 638.89, 51.03, 618.25, 34.3, 594.83, 53.26, 572.53, 72.22, 593.72, 126.87, 596.5, 133.14, 584.24, 149.87, 563.04, 153.22, 554.68, 138.16, 545.2, 142.62, 539.45, 142.05, 530.76, 136.84, 530.32, 133.36, 523.81, 132.93, 519.9, 129.88, 522.07, 125.54, 522.94, 123.37, 512.51, 105.99, 496.0, 110.77, 477.32, 112.5, 473.4, 107.29, 469.93, 109.46, 476.45, 128.15, 466.89, 111.2, 459.07, 112.5, 455.59, 110.33]], "area": 15056.022550000002, "iscrowd": 0, "image_id": 310006, "bbox": [453.87, 0.0, 186.13, 153.22], "category_id": 5, "id": 160684, "split": "val", "sentences": [{"tokens": ["the", "red", "airplane"], "raw": "The red airplane.", "sent_id": 75236, "sent": "the red airplane"}, {"tokens": ["a", "red", "plane", "flying", "behind", "2", "white", "planes"], "raw": "A red plane flying behind 2 white planes.", "sent_id": 75237, "sent": "a red plane flying behind 2 white planes"}], "file_name": "COCO_train2014_000000310006_160684.jpg", "ann_id": 160684, "sent_ids": [75236, 75237], "ref_id": 48553}, {"segmentation": [[426.32, 453.16, 414.97, 432.52, 406.71, 412.9, 386.06, 403.61, 402.58, 378.84, 384.0, 325.16, 384.0, 325.16, 384.0, 325.16, 369.55, 335.48, 369.55, 335.48, 345.81, 356.13, 334.45, 349.94, 342.71, 334.45, 352.0, 332.39, 352.0, 332.39, 336.52, 330.32, 329.29, 336.52, 329.29, 342.71, 314.84, 344.77, 296.26, 334.45, 296.26, 334.45, 276.65, 343.74, 277.68, 353.03, 277.68, 353.03, 299.35, 344.77, 295.23, 364.39, 283.87, 362.32, 285.94, 388.13, 217.81, 439.74, 239.48, 449.03, 242.58, 454.19, 226.06, 462.45, 199.23, 463.48, 175.48, 458.32, 178.58, 436.65, 190.97, 418.06, 177.55, 370.58, 177.55, 370.58, 173.42, 370.58, 174.45, 393.29, 160.0, 406.71, 105.29, 393.29, 104.26, 393.29, 81.55, 398.45, 45.42, 418.06, 33.03, 440.77, 28.9, 457.29, 27.87, 480.0, 27.87, 480.0, 242.58, 480.0, 242.58, 480.0, 235.35, 472.77, 301.42, 409.81, 304.52, 419.1, 282.84, 443.87, 282.84, 443.87, 279.74, 463.48, 279.74, 464.52, 285.94, 480.0, 285.94, 480.0, 426.32, 480.0, 426.32, 480.0, 427.35, 469.68, 427.35, 469.68, 427.35, 467.61, 427.35, 467.61]], "area": 31843.5602, "iscrowd": 0, "image_id": 532175, "bbox": [27.87, 325.16, 399.48, 154.84], "category_id": 2, "id": 128906, "split": "val", "sentences": [{"tokens": ["a", "blue", "bicycle", "with", "a", "wire", "basket"], "raw": "A blue bicycle with a wire basket.", "sent_id": 75526, "sent": "a blue bicycle with a wire basket"}, {"tokens": ["a", "blue", "bicycle", "is", "ridden", "by", "a", "woman", "wearing", "white", "in", "a", "city"], "raw": "A blue bicycle is ridden by a woman wearing white in a city.", "sent_id": 75527, "sent": "a blue bicycle is ridden by a woman wearing white in a city"}], "file_name": "COCO_train2014_000000532175_128906.jpg", "ann_id": 128906, "sent_ids": [75526, 75527], "ref_id": 48567}, {"segmentation": [[552.53, 401.68, 553.51, 390.88, 559.4, 375.17, 564.31, 363.88, 579.53, 365.84, 595.24, 371.24, 607.52, 368.79, 612.43, 360.93, 617.83, 354.06, 622.74, 348.66, 631.57, 344.24, 637.46, 337.37, 639.43, 418.37, 640.0, 425.25, 553.02, 425.25, 550.08, 412.97, 552.04, 411.99], [530.93, 318.71, 542.22, 312.82, 547.62, 311.35, 575.61, 319.2, 575.11, 304.97, 556.95, 294.66, 547.62, 297.11, 540.75, 295.64, 527.0, 296.62, 526.51, 323.62]], "area": 6241.928399999999, "iscrowd": 0, "image_id": 487284, "bbox": [526.51, 294.66, 113.49, 130.59], "category_id": 63, "id": 115897, "split": "val", "sentences": [{"tokens": ["the", "seat", "the", "main", "in", "the", "background", "is", "sitting", "on", "in", "the", "gray", "shirt"], "raw": "The seat the main in the background is sitting on in the gray shirt.", "sent_id": 75625, "sent": "the seat the main in the background is sitting on in the gray shirt"}, {"tokens": ["striped", "barely", "visible", "couch", "with", "man", "sitting", "on", "it"], "raw": "Striped barely visible couch with man sitting on it.", "sent_id": 75626, "sent": "striped barely visible couch with man sitting on it"}], "file_name": "COCO_train2014_000000487284_115897.jpg", "ann_id": 115897, "sent_ids": [75625, 75626], "ref_id": 48574}, {"segmentation": [[205.74, 367.33, 208.71, 359.9, 229.51, 339.84, 230.26, 328.7, 235.46, 322.01, 242.14, 319.78, 250.32, 324.24, 250.32, 330.19, 255.52, 337.62, 268.15, 345.05, 278.55, 370.31, 292.66, 382.94, 289.69, 388.88, 277.06, 382.19, 264.43, 366.59, 264.43, 371.05, 265.17, 377.74, 261.46, 389.62, 237.68, 437.92, 233.97, 446.09, 229.51, 448.32, 227.28, 429.74, 227.28, 427.51, 223.57, 434.2, 220.6, 440.89, 216.88, 446.09, 216.88, 447.57, 211.68, 446.83, 211.68, 430.49, 213.17, 420.83, 222.83, 406.71, 225.05, 391.11, 223.57, 373.28, 223.57, 366.59, 207.22, 379.96, 199.79, 385.17, 194.59, 382.19, 199.79, 373.28]], "area": 4879.570799999999, "iscrowd": 0, "image_id": 417761, "bbox": [194.59, 319.78, 98.07, 128.54], "category_id": 1, "id": 431254, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "black", "skiing", "down", "a", "hill"], "raw": "A man in black skiing down a hill", "sent_id": 75847, "sent": "a man in black skiing down a hill"}, {"tokens": ["skier", "in", "white", "and", "black", "going", "down", "a", "slope"], "raw": "Skier in white and black going down a slope.", "sent_id": 75848, "sent": "skier in white and black going down a slope"}], "file_name": "COCO_train2014_000000417761_431254.jpg", "ann_id": 431254, "sent_ids": [75847, 75848], "ref_id": 48581}, {"segmentation": [[635.51, 230.12, 560.28, 241.54, 555.57, 231.46, 521.99, 181.08, 508.55, 175.04, 507.21, 172.35, 505.19, 153.54, 509.89, 144.14, 520.64, 141.45, 530.05, 138.76, 535.42, 133.39, 542.14, 124.65, 549.53, 113.24, 553.56, 103.83, 550.2, 94.43, 521.31, 54.12, 508.55, 29.27, 530.72, 19.19, 569.01, 0.38, 639.54, 1.72, 638.2, 131.37]], "area": 24870.240900000008, "iscrowd": 0, "image_id": 310457, "bbox": [505.19, 0.38, 134.35, 241.16], "category_id": 62, "id": 2124582, "split": "val", "sentences": [{"tokens": ["a", "brown", "leather", "chair"], "raw": "a brown leather chair", "sent_id": 76014, "sent": "a brown leather chair"}, {"tokens": ["a", "black", "leather", "chair", "with", "a", "gold", "pillow"], "raw": "A black leather chair with a gold pillow.", "sent_id": 76015, "sent": "a black leather chair with a gold pillow"}], "file_name": "COCO_train2014_000000310457_2124582.jpg", "ann_id": 2124582, "sent_ids": [76014, 76015], "ref_id": 48590}, {"segmentation": [[237.56, 64.26, 214.92, 62.64, 189.71, 63.44, 179.29, 64.26, 171.06, 60.97, 160.64, 59.33, 152.69, 59.05, 141.44, 60.15, 149.12, 52.47, 173.26, 30.8, 202.88, 14.35, 232.77, 6.12, 245.66, 2.83, 256.09, 1.73, 267.61, 3.38, 286.26, 5.85, 310.94, 11.88, 322.73, 25.32, 355.06, 70.03, 354.52, 72.02, 351.08, 68.76, 339.94, 61.12, 332.78, 62.32, 311.03, 62.32, 295.53, 62.02, 287.18, 55.16, 283.32, 53.12, 275.51, 54.96, 268.46, 57.87, 262.48, 64.15, 259.42, 64.61, 260.04, 84.61, 261.02, 103.85, 262.07, 132.8, 264.5, 133.0, 264.94, 148.82, 259.23, 148.27, 258.92, 132.99, 260.12, 132.99, 260.12, 132.05, 258.92, 131.99, 258.72, 128.92, 259.72, 128.65, 257.22, 65.13, 237.12, 64.36], [267.77, 151.03, 269.32, 157.84, 269.32, 163.69, 267.77, 168.22, 266.69, 169.78, 266.57, 166.43, 261.32, 166.67, 263.95, 172.76, 269.32, 174.55, 273.02, 169.9, 274.33, 166.91, 274.57, 160.11, 273.86, 154.85, 271.95, 149.6, 270.63, 149.36, 268.24, 151.03]], "area": 9037.10905, "iscrowd": 0, "image_id": 290354, "bbox": [141.44, 1.73, 213.62, 172.82], "category_id": 28, "id": 283552, "split": "val", "sentences": [{"tokens": ["plaid", "umbrella", "held", "by", "woman", "in", "black", "boots"], "raw": "Plaid umbrella held by woman in black boots.", "sent_id": 76262, "sent": "plaid umbrella held by woman in black boots"}, {"tokens": ["the", "umbrella", "is", "pink", "and", "orange"], "raw": "The umbrella is pink and orange.", "sent_id": 76263, "sent": "the umbrella is pink and orange"}], "file_name": "COCO_train2014_000000290354_283552.jpg", "ann_id": 283552, "sent_ids": [76262, 76263], "ref_id": 48597}, {"segmentation": [[161.72, 236.15, 201.52, 248.45, 210.2, 260.75, 231.91, 279.56, 253.61, 287.52, 260.85, 297.65, 266.64, 301.27, 274.6, 302.71, 289.07, 328.76, 289.07, 343.23, 285.45, 375.79, 283.28, 409.08, 274.6, 435.13, 278.94, 451.77, 279.66, 473.48, 273.15, 479.99, 263.74, 479.99, 265.19, 470.58, 272.43, 451.77, 269.53, 419.93, 262.3, 439.47, 255.78, 472.03, 253.61, 476.37, 236.25, 473.48, 249.27, 461.9, 262.3, 414.14, 253.61, 371.45, 241.31, 349.02, 223.95, 353.36, 213.09, 353.36, 210.2, 352.64, 219.6, 400.4, 236.97, 457.56, 234.8, 477.1, 222.5, 476.37, 221.78, 451.05, 210.2, 408.36, 208.03, 397.5, 189.94, 351.92, 187.77, 355.53, 194.28, 418.49, 192.83, 479.27, 176.91, 479.27, 184.87, 463.35, 183.43, 419.21, 173.3, 364.94, 152.31, 310.67, 161.72, 294.75, 155.93, 286.8, 84.3, 199.97, 77.06, 194.18, 75.61, 181.15, 71.27, 174.64, 66.93, 163.79, 67.65, 158.72, 75.61, 165.96, 77.06, 165.96, 77.06, 153.66, 82.85, 154.38, 82.85, 163.79, 85.74, 163.79, 87.91, 162.34, 86.47, 155.1, 91.53, 152.93, 94.43, 160.17, 98.04, 161.62, 105.28, 160.89, 106.73, 167.41, 96.6, 178.98, 98.77, 184.77]], "area": 20624.609200000006, "iscrowd": 0, "image_id": 566847, "bbox": [66.93, 152.93, 222.14, 327.06], "category_id": 25, "id": 2198722, "split": "val", "sentences": [{"tokens": ["a", "larger", "giraffe", "that", "has", "a", "smaller", "giraffe", "leaning", "on", "it"], "raw": "A larger giraffe that has a smaller giraffe leaning on it.", "sent_id": 76926, "sent": "a larger giraffe that has a smaller giraffe leaning on it"}, {"tokens": ["a", "large", "giraffe", "standing", "next", "to", "baby"], "raw": "A large giraffe standing next to baby.", "sent_id": 76927, "sent": "a large giraffe standing next to baby"}], "file_name": "COCO_train2014_000000566847_2198722.jpg", "ann_id": 2198722, "sent_ids": [76926, 76927], "ref_id": 48625}, {"segmentation": [[286.92, 38.83, 319.28, 26.97, 349.48, 26.97, 392.63, 65.8, 400.18, 90.61, 399.1, 143.46, 381.84, 194.16, 373.21, 165.03, 349.48, 143.46, 285.84, 129.44, 265.35, 148.85, 250.25, 176.9, 242.7, 215.73, 229.75, 222.2, 225.44, 200.63, 250.25, 165.03, 257.8, 119.73, 278.29, 63.64]], "area": 15070.478800000003, "iscrowd": 0, "image_id": 182642, "bbox": [225.44, 26.97, 174.74, 195.23], "category_id": 4, "id": 152650, "split": "val", "sentences": [{"tokens": ["the", "backside", "of", "the", "bike", "with", "a", "rider", "on", "it"], "raw": "The backside of the bike with a rider on it.", "sent_id": 77039, "sent": "the backside of the bike with a rider on it"}, {"tokens": ["back", "end", "of", "motorcycle"], "raw": "Back end of motorcycle", "sent_id": 77040, "sent": "back end of motorcycle"}], "file_name": "COCO_train2014_000000182642_152650.jpg", "ann_id": 152650, "sent_ids": [77039, 77040], "ref_id": 48630}, {"segmentation": [[336.71, 535.52, 341.48, 519.15, 342.16, 511.65, 344.55, 500.05, 343.52, 480.62, 341.48, 470.73, 350.34, 476.53, 365.69, 487.44, 358.87, 475.5, 345.57, 462.55, 336.02, 453.34, 327.5, 445.5, 317.61, 445.5, 312.84, 449.59, 308.06, 449.25, 306.02, 444.13, 301.93, 440.04, 300.56, 438.0, 304.99, 432.2, 306.36, 425.04, 306.36, 416.86, 302.61, 415.49, 299.88, 416.52, 298.52, 419.58, 291.7, 419.58, 284.88, 423.68, 277.04, 426.06, 270.22, 424.02, 263.4, 420.95, 259.3, 423.68, 254.87, 421.63, 253.17, 427.77, 255.21, 431.18, 258.28, 432.54, 263.06, 436.63, 265.1, 443.45, 264.42, 448.23, 264.08, 452.32, 269.19, 459.14, 271.24, 463.23, 272.6, 471.07, 271.58, 482.32, 266.81, 497.33, 266.81, 499.03, 261.35, 507.9, 257.94, 509.94, 252.48, 510.62, 247.03, 513.69, 246.35, 515.4, 248.05, 519.49, 257.6, 520.85, 262.03, 517.1, 267.15, 511.99, 278.4, 509.26, 284.88, 499.71, 288.29, 501.42, 293.06, 507.9, 297.83, 508.24, 291.36, 515.74, 289.99, 519.83, 297.15, 521.88, 303.63, 520.17, 305.34, 515.74, 306.36, 513.01, 309.77, 510.62, 314.88, 511.99, 314.54, 522.9, 315.22, 528.35, 322.73, 529.72, 323.41, 526.65, 322.04, 523.92, 321.36, 510.28, 320.68, 502.78, 328.52, 494.94, 329.89, 496.99, 331.59, 506.53, 333.98, 520.51, 331.25, 533.13, 332.61, 536.88, 338.07, 535.52]], "area": 6373.708899999997, "iscrowd": 0, "image_id": 360002, "bbox": [246.35, 415.49, 119.34, 121.39], "category_id": 18, "id": 13784, "split": "val", "sentences": [{"tokens": ["a", "dog", "coming", "towards", "camera"], "raw": "a dog coming towards camera", "sent_id": 77188, "sent": "a dog coming towards camera"}, {"tokens": ["a", "black", "dog", "jumping", "to", "catch", "frisbee"], "raw": "A black dog jumping to catch frisbee.", "sent_id": 77189, "sent": "a black dog jumping to catch frisbee"}], "file_name": "COCO_train2014_000000360002_13784.jpg", "ann_id": 13784, "sent_ids": [77188, 77189], "ref_id": 48635}, {"segmentation": [[143.18, 358.08, 323.58, 399.6, 372.26, 408.19, 373.69, 438.26, 373.69, 475.49, 373.69, 514.14, 372.26, 541.35, 312.13, 544.21, 277.76, 558.53, 229.08, 491.23, 188.99, 466.89, 146.04, 432.53, 107.38, 391.01, 93.06, 363.81, 87.34, 345.19]], "area": 31520.7666, "iscrowd": 0, "image_id": 30973, "bbox": [87.34, 345.19, 286.35, 213.34], "category_id": 1, "id": 456178, "split": "val", "sentences": [{"tokens": ["a", "girl", "wearing", "glasses", "and", "a", "gray", "shirt"], "raw": "A girl wearing glasses and a gray shirt.", "sent_id": 77643, "sent": "a girl wearing glasses and a gray shirt"}, {"tokens": ["a", "woman", "with", "eyeglasses"], "raw": "A woman with eyeglasses.", "sent_id": 77644, "sent": "a woman with eyeglasses"}], "file_name": "COCO_train2014_000000030973_456178.jpg", "ann_id": 456178, "sent_ids": [77643, 77644], "ref_id": 48651}, {"segmentation": [[25.82, 282.23, 227.94, 297.72, 255.23, 299.94, 317.93, 291.82, 332.69, 299.94, 346.7, 299.2, 355.56, 291.08, 361.46, 283.71, 482.43, 257.89, 537.02, 249.04, 549.56, 259.36, 556.94, 258.63, 564.32, 246.82, 594.56, 241.66, 626.28, 227.64, 618.9, 56.51, 615.95, 53.55, 478.75, 40.28, 246.38, 20.36, 151.22, 15.2, 67.13, 24.05, 36.88, 27.74, 16.23, 143.55, 19.18, 251.99, 19.92, 282.23, 21.39, 287.4]], "area": 148453.97559999998, "iscrowd": 0, "image_id": 105718, "bbox": [16.23, 15.2, 610.05, 284.74], "category_id": 6, "id": 163838, "split": "val", "sentences": [{"tokens": ["red", "bus", "in", "road"], "raw": "red bus in road", "sent_id": 78697, "sent": "red bus in road"}, {"tokens": ["red", "color", "bus", "on", "the", "road"], "raw": "red color bus on the road", "sent_id": 78698, "sent": "red color bus on the road"}], "file_name": "COCO_train2014_000000105718_163838.jpg", "ann_id": 163838, "sent_ids": [78697, 78698], "ref_id": 48693}, {"segmentation": [[420.67, 452.03, 587.87, 357.11, 608.36, 318.27, 618.07, 285.91, 618.07, 258.95, 615.91, 224.43, 536.09, 112.25, 559.82, 102.54, 549.03, 59.4, 574.92, 50.77, 594.34, 64.79, 640.0, 71.26, 638.56, 378.68, 637.48, 470.36]], "area": 29907.332749999998, "iscrowd": 0, "image_id": 291493, "bbox": [420.67, 50.77, 219.33, 419.59], "category_id": 67, "id": 420641, "split": "val", "sentences": [{"tokens": ["tan", "colored", "table", "food", "is", "on"], "raw": "tan colored table food is on", "sent_id": 79117, "sent": "tan colored table food is on"}, {"tokens": ["table", "on", "which", "a", "sandwich", "is", "kept"], "raw": "Table on which a sandwich is kept", "sent_id": 79118, "sent": "table on which a sandwich is kept"}], "file_name": "COCO_train2014_000000291493_420641.jpg", "ann_id": 420641, "sent_ids": [79117, 79118], "ref_id": 48716}, {"segmentation": [[366.84, 201.32, 403.54, 275.87, 414.44, 322.9, 408.7, 339.53, 405.26, 341.25, 397.81, 342.97, 393.22, 352.72, 410.42, 431.29, 415.58, 428.42, 432.21, 431.29, 447.12, 430.14, 451.0, 429.57, 451.0, 322.33, 451.0, 277.67, 451.0, 230.15, 443.68, 219.83, 433.36, 212.95, 418.45, 210.08, 390.35, 208.36, 373.72, 206.64, 369.13, 202.62]], "area": 11235.783499999998, "iscrowd": 0, "image_id": 20188, "bbox": [366.84, 201.32, 84.16, 229.97], "category_id": 27, "id": 1168551, "split": "val", "sentences": [{"tokens": ["a", "blue", "backpack", "on", "the", "skateboarder"], "raw": "A blue backpack on the skateboarder.", "sent_id": 79132, "sent": "a blue backpack on the skateboarder"}, {"tokens": ["a", "black", "backpack", "strapped", "to", "the", "back", "of", "a", "young", "man", "sitting", "on", "a", "skateboard"], "raw": "A black backpack strapped to the back of a young man sitting on a skateboard.", "sent_id": 79133, "sent": "a black backpack strapped to the back of a young man sitting on a skateboard"}], "file_name": "COCO_train2014_000000020188_1168551.jpg", "ann_id": 1168551, "sent_ids": [79132, 79133], "ref_id": 48717}, {"segmentation": [[17.26, 337.98, 17.26, 280.45, 53.21, 332.22, 71.91, 323.6, 47.46, 155.33, 38.83, 117.93, 31.64, 76.22, 43.15, 48.9, 43.15, 20.13, 7.19, 0.0, 7.19, 7.19, 8.63, 336.54]], "area": 12928.822450000001, "iscrowd": 0, "image_id": 68430, "bbox": [7.19, 0.0, 64.72, 337.98], "category_id": 1, "id": 1250518, "split": "val", "sentences": [{"tokens": ["a", "person", "in", "a", "black", "outfit", "to", "the", "left", "of", "a", "girl", "in", "a", "black", "dress"], "raw": "A person in a black outfit to the left of a girl in a black dress.", "sent_id": 79361, "sent": "a person in a black outfit to the left of a girl in a black dress"}, {"tokens": ["person", "in", "black", "next", "to", "the", "girl", "with", "flags"], "raw": "Person in black next to the girl with flags", "sent_id": 79362, "sent": "person in black next to the girl with flags"}], "file_name": "COCO_train2014_000000068430_1250518.jpg", "ann_id": 1250518, "sent_ids": [79361, 79362], "ref_id": 48728}, {"segmentation": [[123.96, 283.65, 135.52, 255.28, 143.93, 244.78, 156.53, 239.53, 179.64, 232.17, 192.25, 227.97, 192.25, 220.62, 178.59, 206.96, 176.49, 196.45, 177.54, 177.54, 183.85, 165.99, 193.3, 151.28, 211.16, 146.03, 241.63, 169.14, 242.68, 169.14, 243.73, 187.0, 239.53, 212.21, 234.27, 222.72, 237.42, 235.32, 260.54, 244.78, 273.14, 259.49, 275.24, 279.45, 274.19, 301.51, 275.24, 326.72, 275.24, 343.53, 267.89, 361.39, 261.59, 364.54, 278.4, 378.2, 280.5, 384.5, 246.88, 389.75, 239.53, 378.2, 229.02, 372.95, 217.46, 372.95, 201.71, 377.15, 192.25, 367.69, 188.05, 344.58, 187.0, 340.38, 173.34, 330.92, 160.73, 328.82, 137.62, 328.82, 125.02, 333.02, 120.81, 330.92, 118.71, 307.81, 117.66, 300.46, 122.91, 287.85, 123.96, 274.19]], "area": 22342.77235, "iscrowd": 0, "image_id": 571719, "bbox": [117.66, 146.03, 162.84, 243.72], "category_id": 1, "id": 492865, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "grey", "shrt"], "raw": "a woman wearing a grey shrt", "sent_id": 79629, "sent": "a woman wearing a grey shrt"}, {"tokens": ["woman", "wearing", "a", "gray", "shirt", "with", "a", "tank", "top", "underneath", "and", "hoop", "earrings"], "raw": "woman wearing a gray shirt with a tank top underneath and hoop earrings", "sent_id": 79630, "sent": "woman wearing a gray shirt with a tank top underneath and hoop earrings"}], "file_name": "COCO_train2014_000000571719_492865.jpg", "ann_id": 492865, "sent_ids": [79629, 79630], "ref_id": 48740}, {"segmentation": [[289.12, 83.15, 279.7, 88.95, 268.83, 94.74, 264.48, 97.64, 260.86, 103.44, 260.86, 116.48, 261.58, 123.0, 267.38, 128.07, 268.1, 131.7, 278.25, 136.04, 284.77, 138.94, 282.6, 143.29, 274.63, 151.99, 268.1, 160.68, 265.21, 186.04, 260.86, 199.09, 254.34, 212.13, 256.51, 213.58, 268.1, 226.62, 274.63, 230.24, 278.97, 233.14, 278.97, 233.14, 279.7, 215.03, 281.87, 201.26, 282.6, 199.81, 285.49, 199.81, 285.49, 204.16, 289.84, 208.51, 289.84, 243.29, 300.71, 244.74, 300.71, 258.5, 299.99, 267.92, 299.99, 268.65, 318.1, 283.14, 319.55, 273.72, 326.07, 262.85, 346.36, 262.85, 349.98, 261.4, 336.94, 257.05, 325.35, 249.81, 311.58, 253.43, 312.3, 248.36, 323.17, 246.91, 347.81, 241.11, 361.58, 239.66, 381.14, 217.2, 380.42, 206.33, 376.07, 202.71, 357.95, 195.46, 352.16, 175.17, 357.95, 166.48, 355.06, 159.23, 348.53, 146.91, 340.56, 135.32, 325.35, 126.62, 325.35, 116.48, 319.55, 99.81, 314.48, 94.74, 301.44, 86.77, 295.64, 83.87]], "area": 13246.9212, "iscrowd": 0, "image_id": 350280, "bbox": [254.34, 83.15, 126.8, 199.99], "category_id": 1, "id": 461539, "split": "val", "sentences": [{"tokens": ["woman", "with", "red", "hair"], "raw": "woman with red hair", "sent_id": 80059, "sent": "woman with red hair"}, {"tokens": ["woman", "wearing", "a", "black", "shawl", "looking", "downward"], "raw": "Woman wearing a black shawl looking downward.", "sent_id": 80060, "sent": "woman wearing a black shawl looking downward"}], "file_name": "COCO_train2014_000000350280_461539.jpg", "ann_id": 461539, "sent_ids": [80059, 80060], "ref_id": 48761}, {"segmentation": [[297.87, 196.28, 282.74, 249.86, 272.03, 276.34, 253.75, 294.62, 232.95, 300.92, 215.93, 299.66, 200.17, 285.79, 191.98, 278.86, 188.19, 274.45, 179.37, 254.27, 173.7, 250.49, 172.44, 240.41, 160.46, 232.84, 152.27, 230.32, 147.85, 208.89, 156.68, 185.57, 164.87, 178.63, 170.55, 167.29, 177.48, 155.31, 176.22, 134.51, 185.04, 124.43, 170.55, 108.04, 170.55, 96.06, 181.89, 67.06, 195.13, 46.89, 224.12, 27.98, 249.97, 27.35, 280.22, 45.0, 290.31, 54.46, 298.5, 58.87, 300.39, 64.54, 307.33, 74.0, 307.33, 79.67, 316.78, 84.71, 309.85, 96.06, 317.41, 102.99, 324.98, 106.78, 315.52, 123.16, 310.48, 124.43, 318.04, 142.71, 321.83, 154.05, 318.67, 161.62, 328.13, 171.07, 333.8, 190.61, 318.04, 178.0, 313.0, 179.89, 313.63, 186.2, 302.92, 191.87]], "area": 32756.982050000013, "iscrowd": 0, "image_id": 291897, "bbox": [147.85, 27.35, 185.95, 273.57], "category_id": 54, "id": 308263, "split": "val", "sentences": [{"tokens": ["the", "sandwich", "between", "the", "soup", "and", "one", "half", "of", "a", "sandwich", "top"], "raw": "The sandwich between the soup and one half of a sandwich top", "sent_id": 80138, "sent": "the sandwich between the soup and one half of a sandwich top"}, {"tokens": ["the", "sandwhich", "next", "to", "the", "soup"], "raw": "The sandwhich next to the soup", "sent_id": 80139, "sent": "the sandwhich next to the soup"}], "file_name": "COCO_train2014_000000291897_308263.jpg", "ann_id": 308263, "sent_ids": [80138, 80139], "ref_id": 48770}, {"segmentation": [[145.62, 388.31, 100.31, 371.06, 59.33, 336.54, 38.83, 297.71, 32.36, 262.11, 34.52, 215.73, 58.25, 175.82, 99.24, 134.83, 136.99, 118.65, 186.61, 115.42, 245.93, 121.89, 299.87, 154.25, 332.22, 193.08, 348.4, 239.46, 343.01, 283.69, 319.28, 333.3, 283.69, 365.66, 239.46, 387.24, 184.45, 393.71]], "area": 68772.41875, "iscrowd": 0, "image_id": 244836, "bbox": [32.36, 115.42, 316.04, 278.29], "category_id": 51, "id": 1039629, "split": "val", "sentences": [{"tokens": ["a", "vegetable", "dish", "on", "the", "left", "hand", "side"], "raw": "a vegetable dish on the left hand side", "sent_id": 80350, "sent": "a vegetable dish on the left hand side"}, {"tokens": ["left", "plate"], "raw": "left plate", "sent_id": 80351, "sent": "left plate"}], "file_name": "COCO_train2014_000000244836_1039629.jpg", "ann_id": 1039629, "sent_ids": [80350, 80351], "ref_id": 48780}, {"segmentation": [[416.88, 13.64, 496.75, 13.64, 499.68, 132.47, 497.73, 144.16, 412.99, 14.61, 416.88, 14.61]], "area": 5636.488299999997, "iscrowd": 0, "image_id": 554706, "bbox": [412.99, 13.64, 86.69, 130.52], "category_id": 67, "id": 2133230, "split": "val", "sentences": [{"tokens": ["the", "right", "half", "of", "the", "table", ",", "which", "is", "divided", "by", "a", "line"], "raw": "The right half of the table, which is divided by a line.", "sent_id": 81709, "sent": "the right half of the table , which is divided by a line"}, {"tokens": ["a", "wooden", "table", "with", "nothing", "in", "site", "on", "it"], "raw": "A wooden table with nothing in site on it.", "sent_id": 81710, "sent": "a wooden table with nothing in site on it"}], "file_name": "COCO_train2014_000000554706_2133230.jpg", "ann_id": 2133230, "sent_ids": [81709, 81710], "ref_id": 48846}, {"segmentation": [[178.64, 409.59, 191.55, 381.92, 145.45, 377.31, 152.82, 350.57, 158.22, 346.79, 191.99, 347.1, 192.62, 368.68, 205.44, 368.99, 212.32, 347.42, 213.57, 335.22, 222.33, 314.27, 232.96, 291.75, 240.15, 274.55, 242.97, 264.54, 251.1, 262.35, 264.23, 279.24, 262.04, 283.93, 261.11, 291.44, 252.66, 315.52, 233.9, 318.64, 232.96, 322.08, 236.09, 335.22, 238.9, 343.35, 240.47, 348.98, 243.91, 349.61, 250.47, 356.8, 249.53, 375.87, 249.85, 385.88, 257.98, 411.53, 261.73, 426.54, 263.92, 436.86, 262.67, 440.3, 257.04, 426.54, 247.97, 388.7, 244.84, 401.52, 246.09, 411.84, 258.29, 456.25, 263.29, 471.57, 266.42, 485.96, 260.79, 478.14, 255.16, 453.12, 247.97, 437.48, 241.72, 411.84, 238.9, 403.08, 233.9, 382.75, 207.63, 383.07, 189.8, 418.72, 166.04, 468.13, 160.72, 474.7, 159.47, 476.57, 156.97, 465.94, 162.6, 444.36, 174.17, 421.53, 178.86, 409.34]], "area": 7022.4415500000005, "iscrowd": 0, "image_id": 382469, "bbox": [145.45, 262.35, 120.97, 223.61], "category_id": 62, "id": 377555, "split": "val", "sentences": [{"tokens": ["a", "white", "chair", "facing", "to", "the", "left"], "raw": "A white chair facing to the left.", "sent_id": 81755, "sent": "a white chair facing to the left"}, {"tokens": ["chair", "in", "the", "left"], "raw": "Chair in the left.", "sent_id": 81756, "sent": "chair in the left"}], "file_name": "COCO_train2014_000000382469_377555.jpg", "ann_id": 377555, "sent_ids": [81755, 81756], "ref_id": 48849}, {"segmentation": [[376.98, 344.15, 355.47, 384.91, 340.75, 398.49, 318.11, 404.15, 330.57, 422.26, 326.04, 430.19, 343.02, 447.17, 378.11, 457.36, 430.19, 447.17, 472.08, 436.98, 483.4, 398.49, 484.53, 352.08, 461.89, 324.91, 435.85, 331.7, 420.0, 329.43, 401.89, 337.36, 381.51, 338.49, 375.85, 345.28]], "area": 15146.786049999997, "iscrowd": 0, "image_id": 491330, "bbox": [318.11, 324.91, 166.42, 132.45], "category_id": 56, "id": 1057536, "split": "val", "sentences": [{"tokens": ["a", "piece", "of", "broccoli", "next", "to", "two", "carrots"], "raw": "A piece of broccoli next to two carrots", "sent_id": 81886, "sent": "a piece of broccoli next to two carrots"}, {"tokens": ["the", "piece", "of", "broccoli", "that", "is", "near", "the", "carrots"], "raw": "the piece of broccoli that is near the carrots", "sent_id": 81887, "sent": "the piece of broccoli that is near the carrots"}], "file_name": "COCO_train2014_000000491330_1057536.jpg", "ann_id": 1057536, "sent_ids": [81886, 81887], "ref_id": 48860}, {"segmentation": [[3.32, 233.54, 23.23, 233.54, 22.12, 306.55, 23.23, 307.66, 36.51, 318.72, 60.84, 416.07, 63.05, 422.7, 1.11, 420.49], [181.42, 224.69, 230.09, 222.48, 245.58, 224.69, 242.26, 239.07, 205.76, 241.28, 202.44, 246.82, 184.74, 253.45, 181.42, 252.35]], "area": 7943.527749999999, "iscrowd": 0, "image_id": 24689, "bbox": [1.11, 222.48, 244.47, 200.22], "category_id": 15, "id": 2063054, "split": "val", "sentences": [{"tokens": ["the", "seat", "in", "which", "the", "blonde", "woman", "is", "sitting", "on"], "raw": "The seat in which the blonde woman is sitting on.", "sent_id": 82387, "sent": "the seat in which the blonde woman is sitting on"}], "file_name": "COCO_train2014_000000024689_2063054.jpg", "ann_id": 2063054, "sent_ids": [82387], "ref_id": 48883}, {"segmentation": [[457.32, 347.52, 465.0, 352.13, 474.21, 308.63, 485.98, 312.21, 504.41, 307.6, 519.25, 306.58, 526.42, 312.72, 529.49, 303.0, 518.23, 295.32, 497.24, 295.32, 470.63, 273.31, 474.72, 256.42, 467.56, 249.26, 466.02, 254.89, 467.05, 259.49, 458.86, 258.47, 458.86, 250.28, 453.23, 239.02, 440.43, 243.11, 432.24, 250.79, 436.34, 266.66, 444.53, 268.19, 430.2, 276.89, 422.01, 278.94, 411.26, 272.8, 407.17, 280.48, 408.7, 286.11, 425.08, 289.69, 440.94, 287.64, 443.5, 284.06, 459.37, 301.46, 459.37, 323.47, 457.32, 343.43]], "area": 3621.425600000001, "iscrowd": 0, "image_id": 240689, "bbox": [407.17, 239.02, 122.32, 113.11], "category_id": 1, "id": 424698, "split": "val", "sentences": [{"tokens": ["a", "boy", "in", "a", "white", "t", "-", "shirt", "and", "multi", "-", "colored", "shorts", "posing", "at", "the", "beach"], "raw": "A boy in a white t-shirt and multi-colored shorts posing at the beach.", "sent_id": 82552, "sent": "a boy in a white t - shirt and multi - colored shorts posing at the beach"}, {"tokens": ["young", "boy", "balancing", "on", "one", "leg"], "raw": "Young boy balancing on one leg", "sent_id": 82553, "sent": "young boy balancing on one leg"}], "file_name": "COCO_train2014_000000240689_424698.jpg", "ann_id": 424698, "sent_ids": [82552, 82553], "ref_id": 48889}, {"segmentation": [[20.98, 239.31, 44.96, 219.83, 82.44, 179.36, 125.9, 177.86, 131.9, 186.85, 128.9, 200.34, 128.9, 209.34, 122.9, 222.83, 113.91, 243.81, 110.91, 252.8, 101.92, 258.8, 89.93, 279.78, 71.94, 288.77, 44.96, 308.26, 80.94, 465.64, 56.96, 564.56, 32.97, 620.02, 1.5, 621.51, 3.0, 249.8]], "area": 28697.365299999998, "iscrowd": 0, "image_id": 87522, "bbox": [1.5, 177.86, 130.4, 443.65], "category_id": 1, "id": 1207535, "split": "val", "sentences": [{"tokens": ["a", "person", "'", "s", "hand", "positioning", "bananas", "on", "another", "person", "'", "s", "head"], "raw": "A person's hand positioning bananas on another person's head.", "sent_id": 82675, "sent": "a person ' s hand positioning bananas on another person ' s head"}, {"tokens": ["right", "hand", "of", "person", "with", "banana", "hat", "on"], "raw": "Right hand of person with banana hat on", "sent_id": 82676, "sent": "right hand of person with banana hat on"}], "file_name": "COCO_train2014_000000087522_1207535.jpg", "ann_id": 1207535, "sent_ids": [82675, 82676], "ref_id": 48895}, {"segmentation": [[24.72, 383.93, 26.97, 417.63, 7.87, 467.07, 23.6, 488.42, 57.3, 485.05, 85.39, 470.44, 84.27, 441.23, 70.79, 413.14, 71.91, 374.94]], "area": 6057.42355, "iscrowd": 0, "image_id": 388823, "bbox": [7.87, 374.94, 77.52, 113.48], "category_id": 86, "id": 1156969, "split": "val", "sentences": [{"tokens": ["two", "empty", "vases", "near", "a", "vase", "of", "flowers", ";", "one", "is", "clear", "glass", "and", "the", "other", "is", "opaque", "white"], "raw": "Two empty vases near a vase of flowers; one is clear glass and the other is opaque white.", "sent_id": 82688, "sent": "two empty vases near a vase of flowers ; one is clear glass and the other is opaque white"}, {"tokens": ["glass", "vase", "that", "is", "tinted", "a", "white", "color"], "raw": "Glass vase that is tinted a white color.", "sent_id": 82689, "sent": "glass vase that is tinted a white color"}], "file_name": "COCO_train2014_000000388823_1156969.jpg", "ann_id": 1156969, "sent_ids": [82688, 82689], "ref_id": 48896}, {"segmentation": [[166.79, 71.48, 156.43, 45.58, 174.04, 32.11, 190.62, 25.9, 207.19, 30.04, 223.77, 23.83, 264.17, 30.04, 371.91, 35.22, 440.28, 41.44, 466.18, 58.01, 488.97, 58.01, 498.29, 47.65, 521.09, 46.62, 527.3, 62.16, 552.16, 60.09, 538.7, 80.8, 542.84, 96.34, 539.73, 112.92, 552.16, 132.6, 549.06, 149.18, 539.73, 155.39, 527.3, 136.75, 502.44, 132.6, 492.08, 132.6, 476.54, 106.7, 423.71, 103.6, 383.3, 93.24, 341.87, 88.06, 289.03, 81.84, 276.6, 76.66, 244.49, 97.38, 245.52, 103.6, 212.37, 99.45, 196.83, 105.67, 186.47, 94.27, 186.47, 77.7, 175.08, 76.66], [229.98, 178.18, 221.69, 186.47, 216.51, 196.83, 213.41, 182.33, 219.62, 155.39, 226.87, 144.0, 237.23, 142.96, 231.02, 168.86, 229.98, 175.08]], "area": 24467.201650000006, "iscrowd": 0, "image_id": 179390, "bbox": [156.43, 23.83, 395.73, 173.0], "category_id": 21, "id": 75391, "split": "val", "sentences": [{"tokens": ["a", "cow", "walking", "behind", "two", "other", "cows"], "raw": "A cow walking behind two other cows.", "sent_id": 83379, "sent": "a cow walking behind two other cows"}, {"tokens": ["a", "cow", "standing", "in", "a", "field", "next", "to", "3", "other", "cows"], "raw": "A cow standing in a field next to 3 other cows", "sent_id": 83380, "sent": "a cow standing in a field next to 3 other cows"}], "file_name": "COCO_train2014_000000179390_75391.jpg", "ann_id": 75391, "sent_ids": [83379, 83380], "ref_id": 48927}, {"segmentation": [[18.25, 305.96, 64.71, 303.9, 100.9, 305.96, 108.71, 331.45, 111.18, 365.16, 98.02, 391.48, 68.83, 408.75, 66.36, 411.21, 61.84, 434.65, 64.3, 490.98, 74.58, 492.62, 88.56, 495.09, 99.66, 499.61, 99.66, 504.55, 74.99, 507.84, 57.72, 509.89, 49.5, 511.95, 44.16, 522.23, 37.17, 522.23, 21.13, 517.71, 16.2, 511.13, 20.31, 505.78, 25.24, 499.61, 35.93, 496.74, 51.14, 491.39, 52.38, 469.6, 52.38, 413.27, 31.41, 401.76, 18.25, 391.48, 7.15, 374.21, 3.04, 355.3, 5.09, 327.75, 15.37, 306.37]], "area": 11843.8243, "iscrowd": 0, "image_id": 316671, "bbox": [3.04, 303.9, 108.14, 218.33], "category_id": 46, "id": 664972, "split": "val", "sentences": [{"tokens": ["glass", "on", "left"], "raw": "GLASS ON LEFT", "sent_id": 84155, "sent": "glass on left"}, {"tokens": ["a", "glass", "of", "wine", "in", "front", "of", "a", "paper", "cup"], "raw": "A glass of wine in front of a paper cup.", "sent_id": 84156, "sent": "a glass of wine in front of a paper cup"}], "file_name": "COCO_train2014_000000316671_664972.jpg", "ann_id": 664972, "sent_ids": [84155, 84156], "ref_id": 48955}, {"segmentation": [[193.0, 52.48, 197.52, 61.51, 212.19, 71.67, 215.58, 73.93, 209.93, 78.44, 209.93, 91.99, 200.9, 103.27, 197.52, 116.82, 178.33, 124.72, 159.14, 136.0, 161.4, 150.68, 179.46, 145.03, 197.52, 137.13, 214.45, 150.68, 214.45, 156.32, 212.19, 170.99, 223.48, 192.44, 246.05, 187.92, 257.34, 182.28, 275.4, 175.51, 294.58, 157.45, 296.84, 137.13, 291.2, 120.2, 281.04, 108.92, 272.01, 69.41, 281.04, 54.74, 291.2, 40.07, 287.81, 23.14, 276.52, 15.24, 268.62, 24.27, 269.75, 37.81, 258.47, 54.74, 252.82, 60.38, 243.79, 61.51, 237.02, 52.48, 229.12, 40.07, 213.32, 35.55, 207.67, 35.55, 193.0, 44.58]], "area": 12144.838549999999, "iscrowd": 0, "image_id": 559331, "bbox": [159.14, 15.24, 137.7, 177.2], "category_id": 1, "id": 482068, "split": "val", "sentences": [{"tokens": ["a", "skateboarder", "doing", "a", "trick"], "raw": "A skateboarder doing a trick.", "sent_id": 84410, "sent": "a skateboarder doing a trick"}, {"tokens": ["the", "skateboarder", "in", "the", "air"], "raw": "The skateboarder in the air", "sent_id": 84411, "sent": "the skateboarder in the air"}], "file_name": "COCO_train2014_000000559331_482068.jpg", "ann_id": 482068, "sent_ids": [84410, 84411], "ref_id": 48973}, {"segmentation": [[339.46, 249.64, 363.5, 262.37, 386.14, 299.15, 413.01, 337.34, 434.23, 368.45, 445.54, 409.47, 445.54, 423.62, 417.25, 427.86, 398.86, 440.59, 408.77, 474.54, 418.67, 487.27, 421.5, 518.38, 434.23, 538.18, 431.4, 548.09, 417.25, 560.82, 405.94, 572.13, 393.21, 582.03, 396.04, 591.93, 391.79, 599.0, 373.41, 600.42, 349.36, 601.83, 329.56, 601.83, 321.07, 601.83, 329.56, 591.93, 343.7, 582.03, 352.19, 573.55, 353.6, 556.57, 343.7, 524.04, 333.8, 487.27, 332.39, 464.64, 346.53, 433.52, 357.85, 412.3, 360.68, 391.09, 357.85, 385.43, 345.12, 405.23, 338.05, 419.37, 330.97, 427.86, 318.24, 427.86, 302.68, 419.37, 306.93, 405.23, 323.9, 392.5, 349.36, 376.94, 338.05, 361.38, 328.14, 348.65, 321.07, 334.51, 318.24, 316.12, 314.0, 301.98, 315.41, 280.76, 315.41, 272.27, 302.68, 258.13, 297.03, 258.13, 285.71, 248.23, 275.81, 235.5, 265.91, 227.01, 260.25, 212.87, 263.08, 202.97, 271.57, 200.14, 280.05, 190.24, 287.13, 181.75, 299.86, 180.34, 321.07, 184.58, 329.56, 193.07, 330.97, 197.31, 336.63, 204.38, 346.53, 212.87, 347.95, 218.53, 346.53, 229.84, 340.87, 232.67, 340.87, 232.67]], "area": 32289.155400000003, "iscrowd": 0, "image_id": 100034, "bbox": [260.25, 180.34, 185.29, 421.49], "category_id": 1, "id": 483681, "split": "val", "sentences": [{"tokens": ["the", "closest", "girl"], "raw": "The closest girl.", "sent_id": 85680, "sent": "the closest girl"}, {"tokens": ["girl", "in", "green", "shirt"], "raw": "GIRL IN GREEN SHIRT", "sent_id": 85681, "sent": "girl in green shirt"}], "file_name": "COCO_train2014_000000100034_483681.jpg", "ann_id": 483681, "sent_ids": [85680, 85681], "ref_id": 49019}, {"segmentation": [[369.43, 212.95, 350.96, 213.83, 339.53, 219.99, 330.73, 209.43, 328.97, 205.91, 345.69, 205.03, 355.36, 206.79], [422.21, 253.41, 439.8, 213.83, 466.19, 201.51, 500.0, 196.24, 494.34, 316.74, 438.92, 298.27, 421.33, 288.6, 451.24, 285.08, 450.36, 254.29, 450.36, 254.29], [375.59, 313.23, 314.9, 300.03, 228.7, 266.61, 211.11, 276.28, 204.95, 283.32, 194.39, 278.04, 170.64, 292.99, 162.73, 322.9, 169.76, 326.42, 167.13, 358.0, 281.47, 356.33, 292.03, 341.37, 319.3, 337.85, 333.37, 344.01, 334.25, 346.65, 341.29, 342.25, 357.12, 342.25, 369.43, 344.89, 372.95, 344.89, 374.71, 336.97, 366.8, 328.18]], "area": 19071.51905, "iscrowd": 0, "image_id": 65407, "bbox": [162.73, 196.24, 337.27, 161.76], "category_id": 63, "id": 2224832, "split": "val", "sentences": [{"tokens": ["a", "red", "chair", "that", "rick", "walton", "is", "sitting", "on"], "raw": "A red chair that rick Walton is sitting on.", "sent_id": 85969, "sent": "a red chair that rick walton is sitting on"}, {"tokens": ["rick", "walton", "sitting", "in", "a", "red", "chair", "with", "legs", "crossed"], "raw": "Rick Walton sitting in a red chair with legs crossed", "sent_id": 85970, "sent": "rick walton sitting in a red chair with legs crossed"}], "file_name": "COCO_train2014_000000065407_2224832.jpg", "ann_id": 2224832, "sent_ids": [85969, 85970], "ref_id": 49029}, {"segmentation": [[140.69, 337.5, 181.87, 337.5, 369.45, 348.94, 495.27, 344.37, 494.13, 315.77, 487.27, 316.91, 482.69, 334.07, 478.12, 338.65, 468.97, 338.65, 467.82, 329.5, 468.97, 324.92, 471.25, 319.2, 476.97, 316.91, 462.1, 315.77, 330.56, 291.75, 327.13, 282.6, 248.21, 279.17, 243.63, 294.04, 132.68, 290.61, 123.53, 290.61, 138.4, 336.36]], "area": 16983.217099999994, "iscrowd": 0, "image_id": 7653, "bbox": [123.53, 279.17, 371.74, 69.77], "category_id": 9, "id": 175779, "split": "val", "sentences": [{"tokens": ["the", "speedboat", "in", "the", "water"], "raw": "the speedboat in the water", "sent_id": 86078, "sent": "the speedboat in the water"}, {"tokens": ["a", "boat"], "raw": "a boat", "sent_id": 86079, "sent": "a boat"}], "file_name": "COCO_train2014_000000007653_175779.jpg", "ann_id": 175779, "sent_ids": [86078, 86079], "ref_id": 49032}, {"segmentation": [[1.08, 36.72, 76.41, 35.64, 160.36, 42.1, 199.1, 47.48, 213.09, 53.94, 226.01, 72.23, 237.85, 103.44, 245.38, 166.94, 242.15, 222.91, 235.7, 235.82, 199.1, 241.2, 152.83, 245.51, 83.95, 247.66, 83.95, 232.59, 83.95, 232.59, 78.57, 228.29, 78.57, 228.29, 75.34, 246.58, 75.34, 250.89, 2.15, 250.89, 1.08, 39.95]], "area": 48302.0307, "iscrowd": 0, "image_id": 20769, "bbox": [1.08, 35.64, 244.3, 215.25], "category_id": 6, "id": 167077, "split": "val", "sentences": [{"tokens": ["the", "white", "bus", "with", "no", "markings"], "raw": "The white bus with no markings.", "sent_id": 87545, "sent": "the white bus with no markings"}, {"tokens": ["a", "white", "bus", "behind", "the", "white", "suv"], "raw": "a white bus behind the white suv", "sent_id": 87546, "sent": "a white bus behind the white suv"}], "file_name": "COCO_train2014_000000020769_167077.jpg", "ann_id": 167077, "sent_ids": [87545, 87546], "ref_id": 49090}, {"segmentation": [[202.86, 310.9, 167.6, 296.93, 171.59, 290.94, 186.23, 290.28, 190.89, 286.29, 197.54, 280.3, 216.83, 237.05, 217.5, 233.72, 258.09, 209.77, 256.09, 203.78, 251.43, 204.45, 250.1, 197.13, 249.44, 192.47, 240.79, 165.19, 220.83, 159.87, 212.84, 171.84, 200.2, 173.84, 219.5, 139.91, 229.48, 137.25, 240.79, 135.92, 240.79, 124.6, 252.76, 122.61, 260.08, 125.27, 265.41, 129.26, 270.73, 128.6, 276.05, 133.25, 301.33, 136.58, 318.63, 133.92, 311.98, 126.6, 312.65, 122.61, 319.3, 123.94, 329.28, 128.6, 333.27, 131.92, 325.95, 151.22, 315.97, 151.88, 312.65, 157.21, 298.67, 157.87, 298.67, 197.13, 302.67, 213.1, 295.35, 229.73, 295.35, 247.7, 337.26, 262.33, 352.57, 276.31, 337.93, 289.61, 321.96, 290.94, 322.63, 286.95, 327.95, 284.96, 327.28, 276.31, 271.39, 259.67, 268.73, 253.02, 267.4, 236.38, 250.1, 245.7, 236.13, 248.36, 233.47, 256.34, 217.5, 280.96, 211.51, 293.6, 206.85, 309.57, 205.52, 310.9]], "area": 11442.606500000002, "iscrowd": 0, "image_id": 123247, "bbox": [167.6, 122.61, 184.97, 188.29], "category_id": 1, "id": 434201, "split": "val", "sentences": [{"tokens": ["a", "baseball", "player", "in", "jersey", "number", "43"], "raw": "A baseball player in jersey number 43.", "sent_id": 87817, "sent": "a baseball player in jersey number 43"}, {"tokens": ["the", "ball", "player", "throwing", "the", "ball"], "raw": "The ball player throwing the ball.", "sent_id": 87818, "sent": "the ball player throwing the ball"}], "file_name": "COCO_train2014_000000123247_434201.jpg", "ann_id": 434201, "sent_ids": [87817, 87818], "ref_id": 49102}, {"segmentation": [[128.4, 65.14, 328.89, 46.37, 328.89, 52.3, 328.89, 160.94, 326.17, 159.65, 324.81, 194.97, 165.86, 243.2, 163.82, 221.46, 159.75, 216.71, 157.03, 214.67, 137.33, 212.63]], "area": 31723.838799999998, "iscrowd": 0, "image_id": 445127, "bbox": [128.4, 46.37, 200.49, 196.83], "category_id": 72, "id": 35285, "split": "val", "sentences": [{"tokens": ["a", "monitor", "to", "the", "left", "of", "another", "monitor"], "raw": "A monitor to the left of another monitor.", "sent_id": 88161, "sent": "a monitor to the left of another monitor"}, {"tokens": ["a", "monitor", "with", "two", "speakers"], "raw": "A MONITOR WITH TWO SPEAKERS", "sent_id": 88162, "sent": "a monitor with two speakers"}], "file_name": "COCO_train2014_000000445127_35285.jpg", "ann_id": 35285, "sent_ids": [88161, 88162], "ref_id": 49117}, {"segmentation": [[68.05, 326.8, 53.47, 351.1, 181.47, 351.1, 202.53, 530.95, 335.39, 508.26, 319.19, 334.9, 294.89, 317.07, 186.33, 312.21, 76.15, 325.18]], "area": 31658.931800000002, "iscrowd": 0, "image_id": 500662, "bbox": [53.47, 312.21, 281.92, 218.74], "category_id": 33, "id": 1187016, "split": "val", "sentences": [{"tokens": ["a", "suitcase", "with", "blue", "and", "red", "squares"], "raw": "A suitcase with blue and red squares.", "sent_id": 88461, "sent": "a suitcase with blue and red squares"}, {"tokens": ["the", "suitcase", "with", "twelve", "red", "rectangles", "on", "it"], "raw": "The suitcase with twelve red rectangles on it.", "sent_id": 88462, "sent": "the suitcase with twelve red rectangles on it"}], "file_name": "COCO_train2014_000000500662_1187016.jpg", "ann_id": 1187016, "sent_ids": [88461, 88462], "ref_id": 49131}, {"segmentation": [[242.7, 228.67, 226.52, 248.09, 218.97, 297.71, 207.1, 317.12, 209.26, 357.03, 230.83, 382.92, 282.61, 398.02, 361.35, 405.57, 395.87, 379.69, 418.52, 335.46, 406.65, 308.49, 395.87, 262.11, 379.69, 230.83, 353.8, 214.65, 304.18, 208.18, 264.27, 215.73, 242.7, 226.52]], "area": 32279.3765, "iscrowd": 0, "image_id": 149202, "bbox": [207.1, 208.18, 211.42, 197.39], "category_id": 61, "id": 1085065, "split": "val", "sentences": [{"tokens": ["a", "small", "black", "and", "white", "cake", "with", "a", "ribbon", "on", "top"], "raw": "A small black and white cake with a ribbon on top", "sent_id": 88881, "sent": "a small black and white cake with a ribbon on top"}, {"tokens": ["a", "pastry", "with", "a", "bow", "-", "tie", "and", "spiral", "dots"], "raw": "A pastry with a bow-tie and spiral dots", "sent_id": 88882, "sent": "a pastry with a bow - tie and spiral dots"}], "file_name": "COCO_train2014_000000149202_1085065.jpg", "ann_id": 1085065, "sent_ids": [88881, 88882], "ref_id": 49150}, {"segmentation": [[256.01, 619.15, 280.25, 621.84, 306.28, 618.25, 326.03, 611.52, 326.03, 605.68, 320.19, 585.93, 315.26, 575.16, 312.56, 565.73, 313.01, 545.99, 312.56, 527.58, 314.81, 506.94, 306.73, 480.01, 320.64, 479.11, 343.53, 478.21, 343.53, 439.16, 332.31, 366.9, 327.83, 338.62, 316.6, 321.12, 310.32, 311.24, 300.45, 299.13, 269.48, 266.81, 246.59, 242.57, 227.29, 228.66, 223.25, 223.72, 226.84, 217.89, 223.69, 212.95, 217.86, 209.36, 215.62, 196.34, 208.43, 181.08, 199.01, 177.04, 188.24, 174.8, 172.53, 179.73, 163.55, 190.06, 162.2, 197.24, 159.06, 205.77, 158.61, 211.15, 159.06, 217.89, 159.96, 225.07, 158.61, 229.56, 133.93, 226.86, 122.26, 224.62, 89.49, 220.13, 67.05, 214.29, 56.28, 207.11, 51.79, 203.52, 33.84, 199.48, 36.08, 204.42, 36.98, 206.22, 23.51, 207.56, 27.55, 209.81, 33.84, 211.15, 33.84, 214.74, 32.94, 216.99, 32.94, 219.68, 33.39, 221.92, 32.49, 223.72, 32.49, 227.31, 49.55, 230.9, 63.91, 230.0, 101.16, 244.82, 124.5, 253.79, 159.96, 254.69, 182.85, 257.83, 178.81, 285.21, 188.69, 312.14, 194.07, 324.26, 194.97, 332.34, 176.12, 347.6, 154.12, 358.37, 137.52, 356.13, 113.28, 362.86, 115.52, 367.8, 139.76, 365.1, 141.11, 366.45, 134.82, 370.49, 136.17, 374.98, 140.21, 374.53, 143.8, 372.29, 149.19, 370.49, 156.82, 371.84, 168.04, 366.45, 192.72, 359.72, 210.23, 350.74, 221.9, 355.68, 228.18, 358.82, 242.55, 357.47, 243.89, 356.13, 236.26, 383.51, 238.96, 418.07, 238.51, 447.24, 242.1, 472.83, 244.79, 486.74, 244.79, 517.26, 247.48, 537.46, 248.38, 559.9, 246.59, 563.04, 241.65, 576.51, 224.14, 588.63, 229.98, 594.91, 212.47, 599.4, 208.43, 605.68, 214.27, 611.07, 225.04, 612.86, 241.65, 610.62, 254.66, 612.86, 254.66, 619.6]], "area": 43678.644150000015, "iscrowd": 0, "image_id": 101503, "bbox": [23.51, 174.8, 320.02, 447.04], "category_id": 1, "id": 502341, "split": "val", "sentences": [{"tokens": ["a", "basketball", "player", "dribbling", "the", "ball", "in", "a", "black", "uniform"], "raw": "A basketball player dribbling the ball in a black uniform", "sent_id": 89342, "sent": "a basketball player dribbling the ball in a black uniform"}, {"tokens": ["a", "woman", "holding", "a", "basketball", ",", "wearing", "black", "shorts", "and", "a", "black", "shirt"], "raw": "A woman holding a basketball, wearing black shorts and a black shirt.", "sent_id": 89343, "sent": "a woman holding a basketball , wearing black shorts and a black shirt"}], "file_name": "COCO_train2014_000000101503_502341.jpg", "ann_id": 502341, "sent_ids": [89342, 89343], "ref_id": 49170}, {"segmentation": [[176.4, 111.05, 186.52, 87.45, 189.89, 72.85, 189.89, 58.24, 188.76, 43.63, 197.75, 43.63, 211.24, 43.63, 221.35, 44.76, 221.35, 53.75, 215.73, 66.1, 219.1, 71.72, 219.1, 81.84, 219.1, 95.32, 217.98, 109.93, 212.36, 120.04, 207.87, 133.52, 202.25, 142.51, 187.64, 166.1, 182.02, 179.59, 174.16, 217.79, 167.42, 227.9, 162.92, 230.15, 158.43, 227.9, 167.42, 214.42, 169.66, 173.97, 174.16, 141.39, 167.42, 129.03, 153.93, 129.03, 147.19, 129.03, 138.2, 126.78, 133.71, 114.42, 137.08, 109.93, 143.82, 104.31, 167.42, 104.31]], "area": 5465.885699999999, "iscrowd": 0, "image_id": 46885, "bbox": [133.71, 43.63, 87.64, 186.52], "category_id": 1, "id": 467677, "split": "val", "sentences": [{"tokens": ["a", "skate", "boarder", "doing", "a", "trick", "off", "the", "ramp"], "raw": "A skate boarder doing a trick off the ramp.", "sent_id": 89433, "sent": "a skate boarder doing a trick off the ramp"}, {"tokens": ["boy", "in", "red", "shirt", ",", "above", "ramp"], "raw": "boy in red shirt, above ramp", "sent_id": 89434, "sent": "boy in red shirt , above ramp"}], "file_name": "COCO_train2014_000000046885_467677.jpg", "ann_id": 467677, "sent_ids": [89433, 89434], "ref_id": 49177}, {"segmentation": [[296.13, 126.19, 310.46, 104.22, 313.32, 83.2, 328.61, 76.51, 330.52, 65.05, 352.49, 50.72, 362.04, 63.14, 405.98, 63.14, 448.02, 79.38, 456.61, 93.71, 504.38, 87.98, 533.03, 94.66, 554.05, 123.32, 552.14, 194.96, 538.77, 246.55, 534.94, 298.13, 534.94, 313.42, 525.39, 315.33, 520.62, 306.73, 519.66, 216.94, 497.69, 229.35, 491.0, 229.35, 509.15, 297.18, 498.64, 305.77, 480.49, 246.55, 451.84, 317.24, 434.64, 327.75, 408.85, 327.75, 429.87, 301.95, 426.04, 293.36, 423.18, 238.91, 413.63, 199.74, 398.34, 199.74, 409.81, 189.23, 405.98, 154.84, 394.52, 148.16, 361.09, 129.05, 320.97, 151.02, 304.73, 158.67, 293.26, 153.89, 287.53, 140.52, 292.31, 128.1]], "area": 34970.74874999999, "iscrowd": 0, "image_id": 210279, "bbox": [287.53, 50.72, 266.52, 277.03], "category_id": 24, "id": 589262, "split": "val", "sentences": [{"tokens": ["female", "zebra"], "raw": "female zebra", "sent_id": 89759, "sent": "female zebra"}, {"tokens": ["an", "adult", "zebra", "is", "licking", "a", "young", "zebra"], "raw": "An adult zebra is licking a young zebra", "sent_id": 89760, "sent": "an adult zebra is licking a young zebra"}], "file_name": "COCO_train2014_000000210279_589262.jpg", "ann_id": 589262, "sent_ids": [89759, 89760], "ref_id": 49193}, {"segmentation": [[297.08, 190.75, 303.9, 102.11, 310.71, 80.68, 362.34, 75.81, 412.01, 77.76, 413.96, 114.77, 415.91, 158.6, 415.91, 196.59, 412.99, 215.1, 393.51, 236.53, 361.36, 259.9, 350.65, 310.55, 357.47, 324.19, 382.79, 331.98, 392.53, 338.8, 394.48, 357.31, 389.61, 369.97, 304.87, 368.02, 292.21, 360.23, 286.36, 344.64, 293.18, 327.11, 307.79, 323.21, 331.17, 318.34, 342.86, 293.02, 343.83, 271.59, 333.12, 256.98, 306.82, 219.97, 293.18, 198.54]], "area": 24209.257050000004, "iscrowd": 0, "image_id": 80590, "bbox": [286.36, 75.81, 129.55, 294.16], "category_id": 46, "id": 2183062, "split": "val", "sentences": [{"tokens": ["the", "glass", "infront", "of", "the", "2007", "bottle"], "raw": "The glass infront of the 2007 bottle.", "sent_id": 89825, "sent": "the glass infront of the 2007 bottle"}, {"tokens": ["wine", "glass", "in", "front", "of", "chardonnay", "bottle"], "raw": "wine glass in front of chardonnay bottle", "sent_id": 89826, "sent": "wine glass in front of chardonnay bottle"}], "file_name": "COCO_train2014_000000080590_2183062.jpg", "ann_id": 2183062, "sent_ids": [89825, 89826], "ref_id": 49196}, {"segmentation": [[91.44, 485.8, 107.53, 446.98, 111.32, 412.9, 123.63, 399.65, 126.47, 374.08, 128.36, 340.95, 127.41, 314.44, 126.47, 301.19, 133.09, 285.09, 120.79, 276.57, 118.89, 218.82, 103.74, 197.04, 92.38, 190.42, 72.5, 191.36, 69.66, 178.11, 54.51, 177.16, 46.94, 164.86, 57.35, 152.55, 76.29, 147.81, 93.33, 150.65, 115.1, 143.08, 134.04, 140.24, 135.93, 149.71, 157.71, 150.65, 156.76, 135.51, 156.76, 125.09, 162.44, 107.11, 180.43, 96.69, 205.99, 99.53, 221.14, 114.68, 223.98, 127.93, 236.29, 131.72, 218.3, 143.08, 214.51, 158.23, 213.56, 167.7, 228.71, 175.27, 234.39, 197.04, 223.98, 222.61, 218.3, 238.7, 221.14, 256.69, 221.14, 276.57, 233.45, 292.66, 257.11, 327.69, 285.52, 366.51, 308.24, 393.02, 353.68, 456.45, 349.89, 466.86, 365.04, 495.27, 359.36, 510.41, 342.32, 512.31, 336.64, 480.12, 328.12, 480.12, 264.69, 398.7, 251.43, 391.12, 194.63, 351.36, 164.33, 381.66, 157.71, 410.06, 145.4, 427.1, 134.99, 461.18, 131.2, 488.64, 135.93, 501.89, 122.68, 503.79, 130.25, 510.41, 112.26, 518.93, 90.49, 509.47, 92.38, 492.43]], "area": 42023.30974999999, "iscrowd": 0, "image_id": 94392, "bbox": [46.94, 96.69, 318.1, 422.24], "category_id": 1, "id": 502701, "split": "val", "sentences": [{"tokens": ["player", "#", "24", "swinging", "a", "bat"], "raw": "Player #24 swinging a bat", "sent_id": 89838, "sent": "player # 24 swinging a bat"}, {"tokens": ["a", "baseball", "player", "batting"], "raw": "A baseball player batting", "sent_id": 89839, "sent": "a baseball player batting"}], "file_name": "COCO_train2014_000000094392_502701.jpg", "ann_id": 502701, "sent_ids": [89838, 89839], "ref_id": 49198}, {"segmentation": [[200.53, 287.08, 206.65, 280.28, 216.18, 274.16, 227.06, 268.04, 222.3, 250.35, 219.58, 217.69, 219.58, 195.92, 229.78, 186.4, 239.31, 183.68, 247.47, 183.68, 250.19, 196.6, 256.32, 219.05, 260.4, 240.82, 277.41, 251.71, 279.45, 270.08, 281.49, 274.84, 267.88, 333.35, 269.24, 370.76, 225.02, 431.31, 150.87, 459.2, 137.94, 436.75, 167.88, 400.7, 177.4, 390.49, 185.56, 372.8, 184.2, 363.96, 154.27, 338.79, 116.17, 319.06, 102.57, 312.26, 99.16, 310.9, 76.03, 295.93, 73.31, 288.45, 65.15, 275.52, 65.15, 272.12, 67.87, 266.68, 73.31, 261.23, 163.79, 320.42, 169.92, 311.58, 174.0, 311.58]], "area": 21495.90615, "iscrowd": 0, "image_id": 512561, "bbox": [65.15, 183.68, 216.34, 275.52], "category_id": 1, "id": 537187, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "white", "shirt", "with", "the", "wrist", "watch"], "raw": "The man in the white shirt with the wrist watch.", "sent_id": 90384, "sent": "the man in the white shirt with the wrist watch"}], "file_name": "COCO_train2014_000000512561_537187.jpg", "ann_id": 537187, "sent_ids": [90384], "ref_id": 49221}, {"segmentation": [[399.73, 163.12, 530.16, 170.75, 503.47, 308.06, 472.19, 294.33, 401.25, 261.53, 382.94, 245.51, 395.91, 223.39, 395.15, 191.35, 383.71, 185.25, 383.71, 166.94, 395.91, 161.6]], "area": 15042.6999, "iscrowd": 0, "image_id": 429059, "bbox": [382.94, 161.6, 147.22, 146.46], "category_id": 38, "id": 1855683, "split": "val", "sentences": [{"tokens": ["a", "purple", "folder", "on", "the", "bottom", "row"], "raw": "A purple folder on the bottom row.", "sent_id": 90964, "sent": "a purple folder on the bottom row"}, {"tokens": ["a", "purple", "tote", "bag"], "raw": "A purple tote bag", "sent_id": 90965, "sent": "a purple tote bag"}], "file_name": "COCO_train2014_000000429059_1855683.jpg", "ann_id": 1855683, "sent_ids": [90964, 90965], "ref_id": 49242}, {"segmentation": [[175.22, 261.35, 193.01, 299.46, 194.7, 318.95, 191.32, 323.18, 191.32, 323.18, 208.26, 334.19, 220.96, 353.67, 220.11, 396.02, 207.41, 417.2, 207.41, 427.0, 134.34, 420.12, 134.34, 420.12, 44.14, 422.04, 57.57, 380.78, 90.2, 337.6, 90.2, 337.6, 121.86, 288.66, 125.7, 274.27, 118.98, 238.77, 128.58, 219.58, 142.01, 226.29, 150.65, 245.48, 155.45, 242.61, 165.04, 242.61]], "area": 20374.555099999994, "iscrowd": 0, "image_id": 436941, "bbox": [44.14, 219.58, 176.82, 207.42], "category_id": 24, "id": 588946, "split": "val", "sentences": [{"tokens": ["a", "small", "zebra", "being", "nibbled", "on", "by", "a", "larger", "zebra"], "raw": "A small zebra being nibbled on by a larger zebra.", "sent_id": 91869, "sent": "a small zebra being nibbled on by a larger zebra"}, {"tokens": ["a", "zebra", "that", "is", "standing", "to", "the", "left", "of", "another", "zebra"], "raw": "A zebra that is standing to the left of another zebra.", "sent_id": 91870, "sent": "a zebra that is standing to the left of another zebra"}], "file_name": "COCO_train2014_000000436941_588946.jpg", "ann_id": 588946, "sent_ids": [91869, 91870], "ref_id": 49284}, {"segmentation": [[64.05, 140.68, 90.0, 135.0, 132.97, 131.76, 149.19, 125.27, 158.92, 125.27, 168.65, 125.27, 179.19, 132.57, 185.68, 174.73, 190.54, 202.3, 184.86, 237.16, 179.19, 291.49, 175.14, 300.41, 175.14, 291.49, 170.27, 267.16, 171.89, 254.19, 172.7, 243.65, 175.14, 225.81, 175.95, 208.78, 167.03, 202.3, 162.16, 201.49, 161.35, 193.38, 162.16, 181.22, 159.73, 176.35, 152.43, 171.49, 146.76, 175.54, 146.76, 196.62, 140.27, 196.62, 138.65, 202.3, 130.54, 188.51, 122.43, 175.54, 113.51, 160.95, 85.95, 148.78, 76.22, 146.35, 65.68, 143.92], [101.35, 232.3, 106.22, 251.76, 108.65, 271.22, 108.65, 283.38, 104.59, 286.62, 103.78, 303.65, 107.84, 302.03, 132.16, 299.59, 138.65, 294.73, 145.14, 287.43, 139.46, 274.46, 130.54, 251.76, 130.54, 244.46]], "area": 7849.320749999997, "iscrowd": 0, "image_id": 522834, "bbox": [64.05, 125.27, 126.49, 178.38], "category_id": 22, "id": 584432, "split": "val", "sentences": [{"tokens": ["a", "big", "elephant", "whose", "trunk", "pointing", "to", "the", "floor", ",", "may", "be", "touching"], "raw": "A big elephant whose trunk pointing to the floor , may be touching", "sent_id": 91907, "sent": "a big elephant whose trunk pointing to the floor , may be touching"}, {"tokens": ["the", "two", "elephants", "and", "their", "trainer"], "raw": "The two elephants and their trainer.", "sent_id": 91908, "sent": "the two elephants and their trainer"}], "file_name": "COCO_train2014_000000522834_584432.jpg", "ann_id": 584432, "sent_ids": [91907, 91908], "ref_id": 49286}, {"segmentation": [[439.9, 240.94, 440.44, 256.98, 442.04, 281.58, 453.81, 296.02, 451.14, 304.04, 435.63, 312.6, 421.72, 317.41, 421.19, 309.92, 437.77, 295.48, 430.28, 273.02, 427.07, 251.1, 425.47, 233.98, 426.53, 219.01, 434.56, 181.57, 436.16, 173.02, 422.26, 165.53, 414.77, 151.09, 424.93, 119.0, 436.16, 113.66, 440.44, 110.45, 430.28, 97.08, 431.35, 79.43, 446.86, 74.62, 455.95, 81.57, 460.76, 96.54, 462.9, 105.1, 463.44, 108.31, 482.69, 112.59, 490.71, 122.21, 507.29, 158.58, 480.55, 153.77, 486.43, 174.09, 483.76, 175.69, 490.17, 234.73, 476.27, 239.55, 478.41, 265.75, 486.54, 302.97, 496.16, 311.53, 485.47, 313.67, 476.91, 322.23, 470.49, 325.97, 465.15, 317.95, 479.05, 306.18, 469.42, 271.42, 461.94, 258.59, 459.8, 244.15, 457.66, 237.73]], "area": 11157.694900000002, "iscrowd": 0, "image_id": 212757, "bbox": [414.77, 74.62, 92.52, 251.35], "category_id": 1, "id": 506792, "split": "val", "sentences": [{"tokens": ["the", "man", "in", "the", "white", "shirt"], "raw": "The man in the white shirt.", "sent_id": 92080, "sent": "the man in the white shirt"}, {"tokens": ["the", "man", "in", "the", "white", "shirt"], "raw": "The man in the white shirt.", "sent_id": 92081, "sent": "the man in the white shirt"}], "file_name": "COCO_train2014_000000212757_506792.jpg", "ann_id": 506792, "sent_ids": [92080, 92081], "ref_id": 49294}, {"segmentation": [[33.59, 39.63, 47.98, 21.39, 119.95, 13.72, 143.94, 27.15, 148.73, 47.3, 167.92, 174.92, 151.61, 188.36, 125.7, 197.95, 95.96, 202.75, 74.85, 196.99, 35.51, 59.78]], "area": 18787.7421, "iscrowd": 0, "image_id": 239596, "bbox": [33.59, 13.72, 134.33, 189.03], "category_id": 47, "id": 1501857, "split": "val", "sentences": [{"tokens": ["a", "glass", "of", "juice", "on", "the", "table"], "raw": "A GLASS OF JUICE ON THE TABLE", "sent_id": 92693, "sent": "a glass of juice on the table"}, {"tokens": ["a", "glass", "of", "orange", "juice"], "raw": "A glass of orange juice", "sent_id": 92694, "sent": "a glass of orange juice"}], "file_name": "COCO_train2014_000000239596_1501857.jpg", "ann_id": 1501857, "sent_ids": [92693, 92694], "ref_id": 49326}, {"segmentation": [[307.03, 158.92, 307.03, 134.05, 311.35, 118.92, 328.65, 112.43, 339.46, 116.76, 348.11, 125.41, 337.3, 150.27, 347.03, 160.0, 356.76, 168.65, 366.49, 175.14, 374.05, 207.57, 374.05, 229.19, 363.24, 241.08, 356.76, 247.57, 352.43, 259.46, 354.59, 284.32, 347.03, 285.41, 344.86, 270.27, 344.86, 257.3, 335.14, 248.65, 314.59, 248.65, 300.54, 256.22, 300.54, 270.27, 296.22, 278.92, 284.32, 277.84, 283.24, 275.68, 283.24, 256.22, 282.16, 236.76, 277.84, 231.35, 260.54, 230.27, 248.65, 222.7, 252.97, 200.0, 288.65, 161.08]], "area": 11401.744350000004, "iscrowd": 0, "image_id": 492040, "bbox": [248.65, 112.43, 125.4, 172.98], "category_id": 1, "id": 481690, "split": "val", "sentences": [{"tokens": ["man", "in", "grey", "sweater"], "raw": "man in grey sweater", "sent_id": 92783, "sent": "man in grey sweater"}, {"tokens": ["a", "man", "stirring", "a", "pot", "of", "food"], "raw": "A man stirring a pot of food.", "sent_id": 92784, "sent": "a man stirring a pot of food"}], "file_name": "COCO_train2014_000000492040_481690.jpg", "ann_id": 481690, "sent_ids": [92783, 92784], "ref_id": 49330}, {"segmentation": [[171.96, 358.68, 193.05, 370.29, 200.44, 406.15, 195.16, 427.25, 203.6, 429.36, 193.05, 442.02, 174.07, 442.02, 169.85, 425.14, 168.79, 407.21, 173.01, 389.27, 173.01, 387.16, 146.64, 382.95, 123.43, 377.67, 116.04, 374.51, 111.82, 387.16, 108.66, 397.71, 104.44, 408.26, 87.56, 400.88, 96.0, 376.62, 98.11, 362.9, 105.49, 342.86, 110.77, 338.64, 118.15, 308.04, 145.58, 291.16, 146.64, 276.4, 156.13, 270.07, 171.96, 266.9, 176.18, 284.84, 166.68, 294.33, 181.45, 310.15, 185.67, 330.2, 185.67, 341.8, 165.63, 343.91, 165.63, 344.97, 171.96, 357.63]], "area": 8948.742199999999, "iscrowd": 0, "image_id": 349686, "bbox": [87.56, 266.9, 116.04, 175.12], "category_id": 1, "id": 481843, "split": "val", "sentences": [{"tokens": ["the", "baseball", "umpire", "wearing", "black", "and", "gray"], "raw": "The baseball umpire wearing black and gray.", "sent_id": 93141, "sent": "the baseball umpire wearing black and gray"}, {"tokens": ["the", "umpire", "in", "a", "black", "shirt", "standing", "behind", "the", "baseball", "players"], "raw": "The umpire in a black shirt standing behind the baseball players.", "sent_id": 93142, "sent": "the umpire in a black shirt standing behind the baseball players"}], "file_name": "COCO_train2014_000000349686_481843.jpg", "ann_id": 481843, "sent_ids": [93141, 93142], "ref_id": 49351}, {"segmentation": [[211.59, 41.24, 229.27, 54.34, 212.24, 77.92, 225.34, 105.43, 224.03, 169.63, 210.28, 236.45, 188.0, 237.1, 174.25, 176.84, 177.52, 114.6, 195.86, 79.23, 192.59, 51.72, 194.55, 47.13]], "area": 7283.865349999999, "iscrowd": 0, "image_id": 205223, "bbox": [174.25, 41.24, 55.02, 195.86], "category_id": 32, "id": 294920, "split": "val", "sentences": [{"tokens": ["the", "tie", "at", "the", "second", "from", "the", "left"], "raw": "The tie at the second from the left.", "sent_id": 93958, "sent": "the tie at the second from the left"}, {"tokens": ["the", "second", "tie", "from", "the", "left", "in", "the", "collage"], "raw": "The second tie from the left in the collage.", "sent_id": 93959, "sent": "the second tie from the left in the collage"}], "file_name": "COCO_train2014_000000205223_294920.jpg", "ann_id": 294920, "sent_ids": [93958, 93959], "ref_id": 49381}, {"segmentation": [[151.65, 355.82, 151.65, 355.82, 154.19, 310.07, 160.12, 295.67, 159.27, 280.42, 155.88, 271.1, 155.88, 262.63, 145.72, 248.23, 152.49, 194.85, 149.95, 173.67, 166.9, 150.8, 172.83, 144.87, 180.45, 142.33, 181.3, 133.86, 178.76, 122.0, 210.1, 116.07, 210.1, 122.84, 210.1, 127.93, 215.19, 133.01, 209.26, 136.4, 204.17, 155.04, 199.94, 155.88, 207.56, 171.13, 205.02, 175.37, 205.87, 214.34, 205.87, 232.13, 205.87, 232.98, 210.95, 249.07, 209.26, 254.16, 209.26, 264.32, 201.63, 274.49, 201.63, 274.49, 197.4, 293.13, 188.08, 300.75, 188.08, 300.75, 182.99, 309.22, 177.91, 352.43, 177.91, 352.43, 188.08, 357.51, 169.44, 358.36, 151.65, 357.51, 149.95, 354.13]], "area": 10308.403400000003, "iscrowd": 0, "image_id": 376838, "bbox": [145.72, 116.07, 69.47, 242.29], "category_id": 1, "id": 193103, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "hat", "with", "a", "strap"], "raw": "A man in a hat with a strap.", "sent_id": 94116, "sent": "a man in a hat with a strap"}, {"tokens": ["a", "man", "standing", "with", "a", "hat", "on", "in", "a", "leather", "coat", "listening", "to", "other", "men", "talking"], "raw": "A man standing with a hat on in a leather coat listening to other men talking.", "sent_id": 94117, "sent": "a man standing with a hat on in a leather coat listening to other men talking"}], "file_name": "COCO_train2014_000000376838_193103.jpg", "ann_id": 193103, "sent_ids": [94116, 94117], "ref_id": 49392}, {"segmentation": [[191.38, 1.44, 203.88, 33.18, 203.88, 41.83, 146.18, 57.22, 166.38, 153.39, 177.92, 153.39, 186.57, 120.69, 226.0, 99.54, 276.97, 86.07, 359.68, 101.46, 401.03, 128.39, 406.8, 170.7, 449.12, 188.98, 437.58, 153.39, 468.35, 78.38, 474.12, 55.3, 469.32, 38.95, 504.9, 16.83, 535.67, 11.06, 535.67, 11.06]], "area": 33514.09545, "iscrowd": 0, "image_id": 239596, "bbox": [146.18, 1.44, 389.49, 187.54], "category_id": 67, "id": 1612803, "split": "val", "sentences": [{"tokens": ["a", "placemat", "is", "empty", "behind", "a", "placemat", "that", "is", "full"], "raw": "A placemat is empty behind a placemat that is full", "sent_id": 94469, "sent": "a placemat is empty behind a placemat that is full"}], "file_name": "COCO_train2014_000000239596_1612803.jpg", "ann_id": 1612803, "sent_ids": [94469], "ref_id": 49411}, {"segmentation": [[71.87, 2.57, 75.72, 15.4, 71.87, 15.4, 102.67, 116.79, 105.24, 123.21, 132.19, 134.76, 162.99, 130.91, 180.96, 115.51, 188.66, 112.94, 193.8, 14.12, 189.95, 14.12, 187.38, 0.0]], "area": 13086.11585, "iscrowd": 0, "image_id": 568840, "bbox": [71.87, 0.0, 121.93, 134.76], "category_id": 47, "id": 679786, "split": "val", "sentences": [{"tokens": ["coffee", "cup", "on", "left", "side", "in", "the", "back"], "raw": "coffee cup on left side in the back", "sent_id": 94934, "sent": "coffee cup on left side in the back"}, {"tokens": ["a", "cup", "of", "coffee", "at", "the", "back"], "raw": "A cup of coffee at the back", "sent_id": 94935, "sent": "a cup of coffee at the back"}], "file_name": "COCO_train2014_000000568840_679786.jpg", "ann_id": 679786, "sent_ids": [94934, 94935], "ref_id": 49429}, {"segmentation": [[391.79, 356.89, 382.38, 409.43, 374.54, 443.94, 382.38, 485.51, 379.24, 531.0, 361.99, 581.2, 359.63, 596.1, 360.42, 618.84, 384.73, 640.0, 426.0, 640.0, 426.0, 483.16, 426.0, 459.63, 423.95, 341.99, 404.34, 345.91]], "area": 14332.149799999997, "iscrowd": 0, "image_id": 384888, "bbox": [359.63, 341.99, 66.37, 298.01], "category_id": 47, "id": 1879710, "split": "val", "sentences": [{"tokens": ["a", "large", "glass", "with", "an", "amber", "liquid", "in", "it"], "raw": "a large glass with an amber liquid in it.", "sent_id": 95012, "sent": "a large glass with an amber liquid in it"}, {"tokens": ["glass", "of", "beer"], "raw": "glass of beer", "sent_id": 95013, "sent": "glass of beer"}], "file_name": "COCO_train2014_000000384888_1879710.jpg", "ann_id": 1879710, "sent_ids": [95012, 95013], "ref_id": 49432}, {"segmentation": [[267.01, 103.75, 247.58, 317.47, 241.11, 347.26, 225.56, 343.37, 256.65, 92.1, 259.24, 83.03, 267.01, 95.98], [221.06, 379.78, 218.67, 414.34, 225.83, 442.95, 236.55, 391.7, 230.59, 377.39], [296.15, 278.47, 283.04, 273.7, 280.65, 175.97, 288.99, 159.28, 294.95, 150.94, 297.34, 155.71, 290.19, 199.81]], "area": 5928.264050000004, "iscrowd": 0, "image_id": 286132, "bbox": [218.67, 83.03, 78.67, 359.92], "category_id": 35, "id": 2200478, "split": "val", "sentences": [{"tokens": ["a", "pair", "of", "adult", "skis"], "raw": "A pair of adult skis.", "sent_id": 95191, "sent": "a pair of adult skis"}], "file_name": "COCO_train2014_000000286132_2200478.jpg", "ann_id": 2200478, "sent_ids": [95191], "ref_id": 49438}, {"segmentation": [[172.03, 250.74, 162.75, 251.73, 150.49, 250.4, 117.71, 246.76, 108.43, 245.43, 97.83, 239.8, 95.51, 243.45, 85.57, 240.13, 77.95, 232.84, 74.3, 224.89, 71.32, 205.01, 72.65, 184.13, 79.94, 175.19, 94.85, 169.34, 101.81, 168.35, 110.42, 163.04, 122.35, 162.71, 139.58, 165.03, 160.13, 167.68, 181.0, 173.65, 200.22, 183.92, 220.76, 194.85, 240.98, 200.82, 248.6, 204.46, 255.22, 204.23, 269.14, 205.88, 264.83, 212.84, 258.21, 214.83, 255.56, 217.15, 256.55, 226.43, 255.22, 234.38, 248.93, 242.67, 244.62, 244.65, 239.32, 250.29, 235.01, 251.94, 230.37, 251.94, 223.41, 248.63, 212.15, 248.63, 198.56, 248.63, 181.33, 250.62, 172.05, 252.27]], "area": 12742.415199999998, "iscrowd": 0, "image_id": 473500, "bbox": [71.32, 162.71, 197.82, 89.56], "category_id": 17, "id": 51594, "split": "val", "sentences": [{"tokens": ["the", "cat", "on", "the", "back", "of", "the", "toilet"], "raw": "The cat on the back of the toilet", "sent_id": 95309, "sent": "the cat on the back of the toilet"}, {"tokens": ["cat", "sitting", "on", "toilet"], "raw": "cat sitting on toilet", "sent_id": 95310, "sent": "cat sitting on toilet"}], "file_name": "COCO_train2014_000000473500_51594.jpg", "ann_id": 51594, "sent_ids": [95309, 95310], "ref_id": 49445}, {"segmentation": [[371.84, 362.32, 369.08, 370.14, 350.23, 370.14, 339.65, 363.24, 336.44, 343.93, 335.98, 327.83, 335.06, 313.12, 349.31, 294.27, 351.15, 279.55, 352.53, 256.1, 353.91, 247.37, 350.69, 214.26, 360.81, 201.85, 359.89, 183.91, 351.15, 178.86, 341.03, 164.6, 340.11, 157.7, 343.33, 136.09, 352.53, 105.29, 370.92, 97.47, 373.22, 82.3, 378.28, 80.0, 377.36, 62.98, 388.39, 51.49, 398.97, 50.57, 407.71, 57.47, 412.76, 70.34, 414.14, 83.22, 415.52, 91.03, 414.14, 95.63, 438.97, 121.38, 438.97, 126.44, 445.87, 144.83, 446.79, 151.73, 449.09, 156.32, 455.99, 165.52, 463.8, 172.42, 467.94, 189.89, 461.5, 195.41, 454.15, 193.11, 451.39, 190.81, 445.87, 190.81, 435.29, 184.83, 429.78, 174.26, 426.1, 170.12, 426.1, 178.86, 421.04, 186.21, 423.34, 198.17, 413.22, 244.15, 408.17, 262.08, 404.95, 282.77, 405.87, 297.03, 392.07, 330.59, 396.21, 348.06, 406.79, 359.1, 402.65, 366.92, 386.55, 368.3, 377.82, 362.78]], "area": 21238.047349999997, "iscrowd": 0, "image_id": 141711, "bbox": [335.06, 50.57, 132.88, 319.57], "category_id": 1, "id": 459833, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "jacket", "skiing", "down", "a", "mountain"], "raw": "A man in a blue jacket skiing down a mountain.", "sent_id": 95707, "sent": "a man in a blue jacket skiing down a mountain"}, {"tokens": ["a", "man", "stands", "majestically", "on", "his", "skis", "on", "a", "snow", "covered", "area", "with", "2", "other", "people", "behind", "him", "in", "the", "distance"], "raw": "a man stands majestically on his skis on a snow covered area with 2 other people behind him in the distance", "sent_id": 95708, "sent": "a man stands majestically on his skis on a snow covered area with 2 other people behind him in the distance"}], "file_name": "COCO_train2014_000000141711_459833.jpg", "ann_id": 459833, "sent_ids": [95707, 95708], "ref_id": 49464}, {"segmentation": [[138.68, 451.02, 46.23, 456.01, 44.98, 473.5, 39.98, 472.25, 11.24, 384.8, 21.24, 371.06, 76.21, 337.32, 96.2, 339.82, 99.95, 349.82, 163.66, 348.57, 172.41, 411.04, 157.42, 447.27, 159.92, 468.51, 144.92, 472.25]], "area": 15532.47905, "iscrowd": 0, "image_id": 320611, "bbox": [11.24, 337.32, 161.17, 136.18], "category_id": 63, "id": 1951655, "split": "val", "sentences": [{"tokens": ["a", "single", "white", "cousioned", "chair", "farthest", "away", "from", "the", "french", "doors"], "raw": "a single white cousioned chair farthest away from the french doors.", "sent_id": 96247, "sent": "a single white cousioned chair farthest away from the french doors"}], "file_name": "COCO_train2014_000000320611_1951655.jpg", "ann_id": 1951655, "sent_ids": [96247], "ref_id": 49487}, {"segmentation": [[87.48, 303.66, 91.26, 333.89, 95.98, 360.34, 95.98, 389.62, 92.2, 409.46, 95.98, 440.63, 98.82, 448.3, 102.59, 469.08, 105.43, 480.42, 130.93, 482.3, 137.55, 475.69, 125.27, 448.3, 114.87, 423.74, 116.76, 389.73, 123.38, 373.67, 126.21, 349.11, 131.88, 378.4, 127.15, 400.12, 128.1, 425.63, 129.04, 438.85, 127.15, 452.08, 140.38, 452.08, 160.22, 452.08, 168.72, 452.08, 171.55, 445.46, 157.38, 439.8, 145.1, 422.79, 149.83, 392.57, 151.71, 357.62, 155.49, 329.28, 155.49, 301.88, 155.49, 274.84, 155.49, 249.34, 163.99, 256.89, 171.55, 261.62, 186.67, 258.78, 199.89, 249.34, 214.06, 246.5, 221.62, 229.5, 196.11, 232.33, 174.39, 226.66, 161.16, 189.82, 141.32, 183.21, 149.83, 170.93, 151.71, 136.93, 139.43, 120.87, 120.54, 135.04, 114.87, 161.49, 108.26, 175.66, 87.48, 180.38, 69.53, 199.27, 57.25, 234.22, 51.59, 255.95, 53.47, 282.4, 50.64, 304.12, 53.47, 318.29, 62.92, 326.79, 69.53, 324.9, 74.26, 306.01, 69.53, 292.79, 68.59, 273.9, 76.15, 250.28, 77.09, 245.56, 83.7, 271.06, 86.54, 306.96]], "area": 24109.639899999995, "iscrowd": 0, "image_id": 286132, "bbox": [50.64, 120.87, 170.98, 361.43], "category_id": 1, "id": 428626, "split": "val", "sentences": [{"tokens": ["a", "man", "in", "a", "blue", "coat", "standing", "in", "the", "snow"], "raw": "A man in a blue coat standing in the snow", "sent_id": 96718, "sent": "a man in a blue coat standing in the snow"}, {"tokens": ["a", "man", "with", "blue", "shirt", "and", "black", "pants", "holding", "skis"], "raw": "A man with Blue shirt and black pants holding skis", "sent_id": 96719, "sent": "a man with blue shirt and black pants holding skis"}], "file_name": "COCO_train2014_000000286132_428626.jpg", "ann_id": 428626, "sent_ids": [96718, 96719], "ref_id": 49507}, {"segmentation": [[640.0, 445.48, 640.0, 480.0, 506.11, 480.0, 508.34, 442.75, 508.09, 418.22, 512.8, 417.23, 515.77, 415.49, 516.52, 406.08, 518.0, 402.85, 519.24, 402.11, 539.81, 398.89, 536.09, 394.92, 532.62, 389.72, 527.67, 391.95, 521.22, 390.46, 520.73, 386.25, 521.72, 357.51, 528.16, 323.06, 536.09, 281.93, 538.82, 277.22, 543.28, 237.57, 543.28, 214.53, 555.83, 210.86, 581.37, 211.24, 640.0, 217.25, 640.0, 319.78, 640.0, 411.43]], "area": 30493.533349999998, "iscrowd": 0, "image_id": 564271, "bbox": [506.11, 210.86, 133.89, 269.14], "category_id": 82, "id": 1983348, "split": "val", "sentences": [{"tokens": ["the", "white", "refrigerator", "in", "the", "front"], "raw": "the white refrigerator in the front", "sent_id": 96820, "sent": "the white refrigerator in the front"}, {"tokens": ["the", "white", "fridge", "on", "the", "left"], "raw": "The white fridge on the left", "sent_id": 96821, "sent": "the white fridge on the left"}], "file_name": "COCO_train2014_000000564271_1983348.jpg", "ann_id": 1983348, "sent_ids": [96820, 96821], "ref_id": 49510}, {"segmentation": [[189.85, 342.13, 187.72, 327.91, 182.74, 317.24, 177.05, 291.64, 170.65, 269.6, 170.65, 256.8, 172.07, 246.85, 182.74, 241.87, 184.87, 244.72, 184.87, 244.0, 184.87, 235.47, 187.01, 232.63, 196.25, 225.52, 207.63, 204.18, 207.63, 198.5, 211.18, 180.72, 211.18, 173.61, 199.09, 160.81, 170.65, 135.92, 165.67, 130.95, 162.12, 130.95, 159.27, 118.15, 146.48, 98.95, 134.39, 88.99, 128.7, 92.55, 113.06, 110.32, 109.5, 123.84, 113.06, 136.63, 121.59, 145.88, 125.14, 150.86, 128.7, 160.81, 129.41, 170.76, 127.28, 182.14, 113.77, 194.23, 104.52, 199.92, 107.37, 207.74, 118.03, 207.03, 125.14, 202.76, 128.7, 198.5, 129.41, 209.16, 131.54, 224.81, 128.7, 241.87, 127.28, 247.56, 121.59, 256.8, 119.46, 268.18, 129.41, 285.25, 142.92, 315.11, 145.76, 336.44, 141.5, 347.11, 150.74, 351.37, 158.56, 344.97, 159.27, 344.97, 164.25, 344.97, 180.61, 349.95, 189.14, 349.24, 191.98, 346.4]], "area": 14404.429900000001, "iscrowd": 0, "image_id": 90573, "bbox": [104.52, 88.99, 106.66, 262.38], "category_id": 1, "id": 565634, "split": "val", "sentences": [{"tokens": ["a", "young", "boy", "in", "a", "blue", "uniform", "is", "kicking", "a", "soccer", "ball"], "raw": "A young boy in a blue uniform is kicking a soccer ball.", "sent_id": 97703, "sent": "a young boy in a blue uniform is kicking a soccer ball"}, {"tokens": ["a", "boy", "in", "blue", "kicking", "a", "soccer", "ball"], "raw": "A boy in blue kicking a soccer ball", "sent_id": 97704, "sent": "a boy in blue kicking a soccer ball"}], "file_name": "COCO_train2014_000000090573_565634.jpg", "ann_id": 565634, "sent_ids": [97703, 97704], "ref_id": 49546}, {"segmentation": [[487.24, 248.79, 429.31, 232.24, 414.83, 225.0, 403.45, 237.41, 401.38, 244.66, 399.31, 253.97, 388.97, 277.76, 394.14, 309.83, 401.38, 312.93, 412.76, 299.48, 422.07, 275.69, 446.9, 305.69, 461.38, 366.72, 464.48, 401.9, 486.21, 416.38, 493.45, 400.86, 491.38, 393.62, 488.28, 381.21, 495.52, 341.9, 505.86, 354.31, 501.72, 373.97, 518.28, 366.72, 512.07, 336.72, 516.21, 323.28, 533.79, 337.76, 536.9, 354.31, 537.93, 361.55, 538.97, 383.28, 548.28, 386.38, 552.41, 369.83, 548.28, 333.62, 548.28, 309.83, 545.17, 267.41, 545.17, 267.41, 534.83, 255.0]], "area": 15172.609349999995, "iscrowd": 0, "image_id": 154257, "bbox": [388.97, 225.0, 163.44, 191.38], "category_id": 19, "id": 56473, "split": "val", "sentences": [{"tokens": ["the", "horse", "on", "the", "right", "in", "the", "right", "hand", "picture"], "raw": "the horse on the right in the right hand picture", "sent_id": 97981, "sent": "the horse on the right in the right hand picture"}, {"tokens": ["horse", "with", "white", "strip", "on", "face"], "raw": "Horse with white strip on face.", "sent_id": 97982, "sent": "horse with white strip on face"}], "file_name": "COCO_train2014_000000154257_56473.jpg", "ann_id": 56473, "sent_ids": [97981, 97982], "ref_id": 49558}, {"segmentation": [[161.62, 105.66, 164.4, 132.7, 173.95, 132.3, 177.93, 132.3, 186.68, 132.3, 195.83, 132.7, 204.18, 137.87, 207.76, 141.05, 209.75, 143.04, 209.75, 139.46, 208.95, 130.71, 208.55, 123.16, 208.15, 113.61, 215.71, 138.27, 214.92, 151.0, 215.31, 155.37, 216.9, 159.35, 220.48, 162.93, 222.87, 162.93, 225.26, 162.93, 226.05, 161.74, 224.06, 142.25, 220.48, 117.19, 220.48, 115.2, 218.1, 94.92, 207.36, 81.79, 197.02, 77.82, 193.04, 75.43, 191.85, 70.26, 191.85, 64.69, 188.67, 53.16, 174.75, 48.38, 166.79, 53.95, 159.28, 59.78, 157.29, 64.95, 162.46, 67.34, 165.24, 71.32, 164.84, 80.46, 145.36, 83.25, 131.04, 86.43, 119.11, 91.6, 108.77, 92.0, 102.0, 92.4, 95.24, 98.36, 95.64, 103.13, 98.03, 107.91, 102.8, 105.52, 117.91, 102.74, 122.69, 101.54, 132.23, 99.16, 140.19, 97.57, 142.57, 98.36, 146.95, 100.35, 153.71, 101.94, 154.9, 101.94]], "area": 4984.3031, "iscrowd": 0, "image_id": 32801, "bbox": [95.24, 48.38, 130.81, 114.55], "category_id": 1, "id": 452691, "split": "val", "sentences": [{"tokens": ["a", "worker", "in", "a", "black", "ballcap", "reaches", "over", "the", "machinery"], "raw": "A worker in a black ballcap reaches over the machinery.", "sent_id": 99065, "sent": "a worker in a black ballcap reaches over the machinery"}, {"tokens": ["a", "man", "in", "a", "black", "hat"], "raw": "A man in a black hat", "sent_id": 99066, "sent": "a man in a black hat"}], "file_name": "COCO_train2014_000000032801_452691.jpg", "ann_id": 452691, "sent_ids": [99065, 99066], "ref_id": 49605}, {"segmentation": [[51.7, 272.54, 31.59, 194.03, 27.76, 160.52, 4.79, 124.14, 2.87, 117.44, 9.57, 88.72, 51.7, 79.15, 65.1, 83.93, 75.63, 96.38, 80.42, 124.14, 79.46, 144.25, 73.72, 157.65, 99.57, 170.1, 98.61, 143.29, 108.19, 127.01, 112.97, 127.97, 112.97, 159.57, 112.02, 174.88, 117.76, 176.8, 127.33, 200.73, 126.38, 227.54, 120.63, 239.99, 108.19, 235.2, 111.06, 255.31, 132.12, 308.92, 139.78, 373.07, 141.7, 391.26, 141.7, 404.66, 141.7, 421.89, 39.25, 419.02, 38.3, 335.73]], "area": 28294.059500000003, "iscrowd": 0, "image_id": 137377, "bbox": [2.87, 79.15, 138.83, 342.74], "category_id": 1, "id": 463283, "split": "val", "sentences": [{"tokens": ["woman", "on", "left", "with", "phone"], "raw": "woman on left with phone", "sent_id": 99328, "sent": "woman on left with phone"}, {"tokens": ["a", "girl", "with", "a", "cellphone"], "raw": "A girl with a cellphone.", "sent_id": 99329, "sent": "a girl with a cellphone"}], "file_name": "COCO_train2014_000000137377_463283.jpg", "ann_id": 463283, "sent_ids": [99328, 99329], "ref_id": 49614}, {"segmentation": [[222.32, 2.6, 214.77, 19.38, 205.54, 36.15, 195.47, 57.97, 192.95, 69.71, 213.09, 70.55, 252.52, 73.91, 276.85, 74.75, 277.68, 74.75, 281.04, 94.04, 286.07, 120.89, 287.75, 94.88, 284.4, 74.75, 278.52, 55.45, 270.97, 36.99, 266.78, 25.25, 260.07, 11.83, 256.71, 0.92, 224.83, 0.08], [193.79, 77.26, 190.44, 120.89, 192.95, 161.99, 194.63, 185.48, 194.63, 203.94, 191.28, 224.07, 210.57, 224.07, 234.9, 226.59, 260.07, 224.91, 267.62, 204.78, 273.49, 178.77, 273.49, 156.96, 270.97, 131.79, 272.65, 130.11, 273.49, 116.69, 270.97, 100.75, 266.78, 77.26, 248.32, 76.42, 202.18, 72.23, 194.63, 73.07]], "area": 16536.9267, "iscrowd": 0, "image_id": 80590, "bbox": [190.44, 0.08, 97.31, 226.51], "category_id": 44, "id": 288570, "split": "val", "sentences": [{"tokens": ["an", "empty", "wine", "glass", "between", "two", "other", "empty", "wine", "glasses"], "raw": "An empty wine glass between two other empty wine glasses", "sent_id": 100576, "sent": "an empty wine glass between two other empty wine glasses"}, {"tokens": ["a", "bottle", "with", "the", "number", "2008", "and", "green", "label"], "raw": "A bottle with the number 2008 and green label.", "sent_id": 100577, "sent": "a bottle with the number 2008 and green label"}], "file_name": "COCO_train2014_000000080590_288570.jpg", "ann_id": 288570, "sent_ids": [100576, 100577], "ref_id": 49661}, {"segmentation": [[193.65, 345.26, 201.84, 210.57, 210.02, 188.25, 221.19, 180.8, 229.37, 177.08, 521.08, 140.62, 549.36, 154.01, 560.52, 167.41, 576.14, 255.96, 568.7, 270.1, 562.75, 272.33, 562.75, 302.84, 580.61, 314.01, 582.84, 364.61, 563.49, 370.56, 555.31, 372.79, 535.22, 378.0, 525.54, 386.93, 490.57, 392.89, 479.41, 389.91, 459.31, 375.03, 289.65, 355.68, 276.25, 366.1, 262.86, 366.84, 252.44, 361.63, 245.0, 354.19, 232.35, 348.24, 194.4, 346.75]], "area": 77434.04270000003, "iscrowd": 0, "image_id": 293860, "bbox": [193.65, 140.62, 389.19, 252.27], "category_id": 6, "id": 165011, "split": "val", "sentences": [{"tokens": ["black", "bus"], "raw": "black bus", "sent_id": 100852, "sent": "black bus"}, {"tokens": ["a", "double", "decker", "bus", "with", "the", "wording", "the", "ghost", "bus", "tours", ".", "com", "on", "the", "side"], "raw": "A double decker bus with the wording The Ghost Bus Tours.com on the side.", "sent_id": 100853, "sent": "a double decker bus with the wording the ghost bus tours . com on the side"}], "file_name": "COCO_train2014_000000293860_165011.jpg", "ann_id": 165011, "sent_ids": [100852, 100853], "ref_id": 49672}, {"segmentation": [[372.49, 256.0, 362.43, 227.24, 362.43, 204.22, 362.43, 185.53, 355.24, 161.08, 340.85, 115.06, 352.36, 94.92, 373.93, 99.24, 392.63, 119.37, 405.57, 119.37, 428.58, 94.92, 454.47, 90.61, 477.48, 93.48, 500.49, 100.67, 511.0, 100.67, 511.0, 522.07, 491.87, 549.39, 463.1, 628.49, 333.66, 627.06, 232.99, 602.61, 227.24, 585.35, 332.22, 579.6, 355.24, 533.57, 381.12, 454.47, 382.56, 378.25, 379.69, 348.04, 379.69, 335.1, 395.51, 322.16, 396.94, 299.15, 386.88, 268.94, 372.49, 247.37]], "area": 76883.83744999998, "iscrowd": 0, "image_id": 33991, "bbox": [227.24, 90.61, 283.76, 537.88], "category_id": 1, "id": 481425, "split": "val", "sentences": [{"tokens": ["a", "woman", "in", "a", "green", "hat", "holding", "a", "child", "in", "her", "arms"], "raw": "A woman in a green hat holding a child in her arms.", "sent_id": 100854, "sent": "a woman in a green hat holding a child in her arms"}, {"tokens": ["a", "lady", "holding", "his", "son", "in", "front", "of", "elephant", "at", "zoo"], "raw": "A LADY HOLDING HIS SON IN FRONT OF ELEPHANT AT ZOO", "sent_id": 100855, "sent": "a lady holding his son in front of elephant at zoo"}], "file_name": "COCO_train2014_000000033991_481425.jpg", "ann_id": 481425, "sent_ids": [100854, 100855], "ref_id": 49673}, {"segmentation": [[146.7, 283.69, 135.91, 257.8, 130.52, 235.15, 117.57, 199.55, 112.18, 168.27, 112.18, 161.8, 124.04, 168.27, 127.28, 166.11, 130.52, 147.78, 130.52, 128.36, 125.12, 100.31, 115.42, 65.8, 102.47, 51.78, 80.9, 43.15, 57.17, 34.52, 50.7, 29.12, 67.96, 29.12, 73.35, 9.71, 67.96, 4.31, 2.16, 2.16, 2.16, 375.37, 12.94, 340.85, 26.97, 332.22, 38.83, 331.15, 46.38, 336.54, 52.85, 341.93, 59.33, 345.17, 71.19, 339.78, 72.27, 319.28, 74.43, 305.26, 76.58, 295.55, 79.82, 278.29, 79.82, 257.8, 77.66, 225.44, 85.21, 222.2, 94.92, 235.15, 94.92, 254.56, 99.24, 268.58, 105.71, 284.76, 115.42, 303.1, 118.65, 308.49, 132.67, 324.67, 134.83, 325.75, 138.07, 325.75, 141.3, 308.49, 144.54, 289.08]], "area": 36055.204549999995, "iscrowd": 0, "image_id": 229825, "bbox": [2.16, 2.16, 144.54, 373.21], "category_id": 1, "id": 439003, "split": "val", "sentences": [{"tokens": ["a", "woman", "wearing", "a", "blue", "and", "white", "shirt"], "raw": "A woman wearing a blue and white shirt.", "sent_id": 101009, "sent": "a woman wearing a blue and white shirt"}, {"tokens": ["a", "girl", "blue", "color", "t", "shirt", "and", "blue", "color", "jeans"], "raw": "a girl blue color t shirt and blue color jeans", "sent_id": 101010, "sent": "a girl blue color t shirt and blue color jeans"}], "file_name": "COCO_train2014_000000229825_439003.jpg", "ann_id": 439003, "sent_ids": [101009, 101010], "ref_id": 49683}, {"segmentation": [[638.75, 288.63, 634.72, 296.11, 623.78, 308.2, 601.33, 323.74, 590.97, 339.28, 565.65, 355.98, 527.65, 368.06, 501.17, 368.64, 490.24, 359.43, 474.12, 354.82, 462.61, 348.49, 446.49, 339.28, 426.34, 323.74, 411.38, 321.44, 393.53, 305.32, 371.08, 304.17, 365.9, 303.02, 372.23, 292.08, 372.23, 275.96, 377.42, 258.7, 374.54, 239.7, 374.54, 236.82, 380.87, 236.82, 387.78, 232.22, 396.41, 228.76, 396.41, 222.43, 394.11, 210.34, 375.69, 204.59, 367.05, 199.98, 374.54, 187.89, 382.6, 173.5, 388.35, 160.26, 395.84, 150.48, 398.71, 142.42, 398.14, 129.75, 398.14, 125.15, 401.02, 125.73, 387.2, 106.15, 369.36, 103.28, 362.45, 90.04, 354.97, 87.73, 342.88, 83.13, 338.27, 73.92, 335.39, 62.98, 343.04, 51.76, 348.87, 46.83, 354.7, 35.16, 365.02, 14.98, 369.95, 4.67, 371.29, 2.42, 375.78, 1.08, 381.16, 0.18, 398.2, 1.53, 420.18, 0.63, 443.95, 1.98, 466.83, 0.63, 494.63, 1.08, 517.96, 1.08, 546.21, 1.98, 575.37, 0.63, 602.72, 0.63, 606.31, 1.08, 615.28, 12.29, 622.01, 23.06, 625.6, 33.37, 631.43, 43.24, 639.05, 52.21, 639.95, 84.5, 639.05, 122.18, 639.5, 163.44, 639.95, 181.83, 639.95, 272.43, 639.95, 288.57]], "area": 89059.41940000001, "iscrowd": 0, "image_id": 174700, "bbox": [335.39, 0.18, 304.56, 368.46], "category_id": 17, "id": 1402170, "split": "val", "sentences": [{"tokens": ["black", "cat", "sleeping", "on", "a", "red", "and", "black", "luggage", "beside", "a", "gray", "and", "white", "kitten"], "raw": "Black cat sleeping on a red and black luggage beside a gray and white kitten.", "sent_id": 101189, "sent": "black cat sleeping on a red and black luggage beside a gray and white kitten"}, {"tokens": ["a", "black", "cat", "in", "a", "suitcase"], "raw": "A black cat in a suitcase.", "sent_id": 101190, "sent": "a black cat in a suitcase"}], "file_name": "COCO_train2014_000000174700_1402170.jpg", "ann_id": 1402170, "sent_ids": [101189, 101190], "ref_id": 49694}, {"segmentation": [[250.57, 191.44, 256.1, 191.09, 243.65, 156.14, 255.76, 157.53, 269.95, 174.14, 269.6, 168.25, 277.56, 168.25, 278.25, 182.79, 289.67, 193.51, 315.96, 199.74, 337.42, 203.2, 337.42, 196.28, 350.91, 204.59, 366.83, 203.89, 412.5, 210.47, 427.38, 217.04, 437.07, 228.11, 432.22, 233.3, 414.58, 236.76, 371.33, 232.27, 347.11, 233.65, 348.84, 236.42, 352.3, 237.46, 350.22, 244.03, 331.19, 243.34, 328.77, 233.65, 302.12, 234.0, 306.97, 236.07, 309.74, 241.95, 309.04, 245.41, 290.36, 244.03, 286.9, 236.76, 261.64, 234.0, 258.18, 229.84, 245.38, 228.81, 329.8, 227.08, 319.77, 223.27, 291.05, 214.62, 261.29, 201.47, 234.31, 203.55, 234.31, 211.85, 225.31, 211.51, 223.58, 189.36, 234.31, 190.74, 237.42, 199.4, 252.3, 197.32, 249.88, 191.78]], "area": 6231.6801, "iscrowd": 0, "image_id": 569750, "bbox": [223.58, 156.14, 213.49, 89.27], "category_id": 5, "id": 156915, "split": "val", "sentences": [{"tokens": ["an", "airplane", "flying", "in", "the", "sky"], "raw": "An airplane flying in the sky.", "sent_id": 101528, "sent": "an airplane flying in the sky"}, {"tokens": ["the", "lower", "airplane"], "raw": "the lower airplane", "sent_id": 101529, "sent": "the lower airplane"}], "file_name": "COCO_train2014_000000569750_156915.jpg", "ann_id": 156915, "sent_ids": [101528, 101529], "ref_id": 49707}, {"segmentation": [[360.0, 283.27, 379.59, 279.18, 390.2, 279.18, 404.9, 275.92, 409.8, 273.47, 418.78, 272.65, 426.12, 280.82, 431.02, 287.35, 437.55, 288.98, 451.43, 288.98, 465.31, 288.98, 467.76, 284.08, 471.84, 279.18, 475.1, 276.73, 486.53, 267.76, 497.14, 263.67, 509.39, 260.41, 516.73, 257.96, 522.45, 261.22, 540.41, 267.76, 553.47, 266.12, 556.73, 264.49, 568.98, 254.69, 569.8, 234.29, 568.16, 104.49, 564.9, 97.14, 550.2, 96.33, 524.08, 99.59, 493.06, 111.02, 489.8, 100.41, 488.16, 97.14, 457.14, 88.16, 455.51, 57.96, 455.51, 60.41, 448.16, 62.04, 435.1, 62.04, 429.39, 62.04, 411.43, 62.04, 389.39, 61.22, 366.53, 61.22, 351.02, 58.78, 334.69, 60.41, 329.8, 64.49, 327.35, 75.1, 328.16, 81.63, 320.82, 81.63, 307.76, 83.27, 298.78, 81.63, 284.08, 81.63, 271.02, 84.08, 252.24, 86.53, 235.1, 87.35, 217.14, 145.31, 215.51, 150.2, 199.18, 161.63, 200.82, 174.69, 197.55, 213.88, 194.29, 234.29, 193.47, 249.8, 220.41, 271.02, 240.0, 275.92, 271.84, 276.73, 305.31, 279.18, 316.73, 279.18, 329.8, 279.18, 359.18, 283.27]], "area": 70137.52870000001, "iscrowd": 0, "image_id": 572405, "bbox": [193.47, 57.96, 376.33, 231.02], "category_id": 8, "id": 398800, "split": "val", "sentences": [{"tokens": ["red", "fire", "truck", "in", "a", "city"], "raw": "Red fire truck in a city.", "sent_id": 101678, "sent": "red fire truck in a city"}, {"tokens": ["the", "fire", "truck", "has", "the", "number", "33", "on", "the", "grill"], "raw": "The fire truck has the number 33 on the grill.", "sent_id": 101679, "sent": "the fire truck has the number 33 on the grill"}], "file_name": "COCO_train2014_000000572405_398800.jpg", "ann_id": 398800, "sent_ids": [101678, 101679], "ref_id": 49716}, {"segmentation": [[390.0, 141.19, 390.0, 165.19, 370.0, 219.19, 370.0, 258.19, 396.0, 260.19, 426.0, 262.19, 469.0, 261.19, 477.0, 256.19, 492.0, 256.19, 500.0, 247.19, 481.0, 242.19, 463.0, 247.19, 453.0, 243.19, 447.0, 229.19, 441.68, 232.56, 401.95, 236.35, 396.75, 225.47, 396.27, 138.43, 366.47, 142.69, 368.84, 143.16, 389.18, 147.89]], "area": 4384.155399999998, "iscrowd": 0, "image_id": 230436, "bbox": [366.47, 138.43, 133.53, 123.76], "category_id": 73, "id": 1100127, "split": "val", "sentences": [{"tokens": ["the", "laptop", "on", "which", "the", "woman", "is", "working"], "raw": "The laptop on which the woman is working", "sent_id": 101895, "sent": "the laptop on which the woman is working"}, {"tokens": ["the", "laptop", "being", "used", "by", "the", "woman"], "raw": "The laptop being used by the woman", "sent_id": 101896, "sent": "the laptop being used by the woman"}], "file_name": "COCO_train2014_000000230436_1100127.jpg", "ann_id": 1100127, "sent_ids": [101895, 101896], "ref_id": 49732}, {"segmentation": [[535.59, 242.64, 533.62, 230.86, 533.62, 227.91, 535.59, 224.47, 568.98, 218.58, 575.85, 223.98, 583.22, 225.95, 598.93, 244.12, 614.15, 273.09, 608.75, 276.03, 640.0, 332.51, 639.2, 343.8, 604.33, 281.44, 597.95, 280.94, 595.49, 293.71, 623.98, 353.13, 620.05, 353.13, 591.07, 302.06, 598.44, 275.05, 594.51, 255.9, 537.06, 241.66], [620.05, 370.32, 612.19, 355.59, 622.5, 353.62, 640.0, 353.62, 639.2, 378.67, 633.31, 379.16, 621.52, 375.72, 619.06, 370.81]], "area": 3231.0317999999984, "iscrowd": 0, "image_id": 408266, "bbox": [533.62, 218.58, 106.38, 160.58], "category_id": 62, "id": 378803, "split": "val", "sentences": [{"tokens": ["the", "empty", "chair", "to", "the", "right", "of", "man", "facing", "away", "from", "the", "camera"], "raw": "The empty chair to the right of man facing away from the camera.", "sent_id": 103110, "sent": "the empty chair to the right of man facing away from the camera"}, {"tokens": ["the", "chair", "not", "being", "used", "on", "the", "far", "right", ",", "perpendicular", "to", "the", "viewer"], "raw": "the chair not being used on the far right, perpendicular to the viewer", "sent_id": 103111, "sent": "the chair not being used on the far right , perpendicular to the viewer"}], "file_name": "COCO_train2014_000000408266_378803.jpg", "ann_id": 378803, "sent_ids": [103110, 103111], "ref_id": 49775}, {"segmentation": [[161.79, 307.97, 199.02, 302.24, 213.33, 323.72, 204.74, 380.99, 206.17, 418.21, 201.88, 455.44, 200.45, 482.64, 203.31, 542.78, 171.81, 549.94, 131.72, 537.05, 134.59, 504.12, 127.43, 471.19, 136.02, 436.83, 136.02, 411.06, 136.02, 380.99, 143.18, 353.78, 143.18, 325.15, 153.2, 312.26, 166.09, 302.24, 174.68, 302.24]], "area": 16344.702499999998, "iscrowd": 0, "image_id": 106660, "bbox": [127.43, 302.24, 85.9, 247.7], "category_id": 86, "id": 1156050, "split": "val", "sentences": [{"tokens": ["a", "blue", "colour", "flower", "pot", "holding", "up", "a", "yellow", "rose"], "raw": "A blue colour flower pot holding up a yellow rose", "sent_id": 103114, "sent": "a blue colour flower pot holding up a yellow rose"}, {"tokens": ["the", "blue", ",", "wavy", "vase"], "raw": "The blue, wavy vase", "sent_id": 103115, "sent": "the blue , wavy vase"}], "file_name": "COCO_train2014_000000106660_1156050.jpg", "ann_id": 1156050, "sent_ids": [103114, 103115], "ref_id": 49776}, {"segmentation": [[244.85, 255.71, 254.56, 225.51, 247.01, 214.72, 239.46, 162.95, 238.38, 101.47, 280.45, 78.81, 270.74, 60.48, 266.43, 41.06, 277.21, 6.54, 353.8, 6.54, 358.11, 5.47, 377.53, 50.77, 388.31, 60.48, 352.72, 62.63, 352.72, 62.63, 335.46, 90.68, 377.53, 101.47, 380.76, 115.49, 380.76, 184.52, 376.45, 207.17, 378.61, 216.88, 351.64, 196.39, 337.62, 225.51, 326.83, 241.69, 306.34, 248.16, 268.58, 252.48, 244.85, 257.87]], "area": 27152.414199999992, "iscrowd": 0, "image_id": 500057, "bbox": [238.38, 5.47, 149.93, 252.4], "category_id": 1, "id": 517726, "split": "val", "sentences": [{"tokens": ["the", "girl", "in", "black", "dress"], "raw": "the girl in black dress", "sent_id": 103299, "sent": "the girl in black dress"}, {"tokens": ["a", "young", "girl", "eating", "a", "yellow", "vegetable", "and", "wearing", "a", "black", "sleeveless", "top"], "raw": "A young girl eating a yellow vegetable and wearing a black sleeveless top.", "sent_id": 103300, "sent": "a young girl eating a yellow vegetable and wearing a black sleeveless top"}], "file_name": "COCO_train2014_000000500057_517726.jpg", "ann_id": 517726, "sent_ids": [103299, 103300], "ref_id": 49783}, {"segmentation": [[249.12, 141.35, 248.24, 189.05, 243.82, 218.2, 244.7, 220.85, 640.0, 242.05, 639.59, 78.62]], "area": 47628.3882, "iscrowd": 0, "image_id": 252277, "bbox": [243.82, 78.62, 396.18, 163.43], "category_id": 84, "id": 1140422, "split": "val", "sentences": [{"tokens": ["a", "book", "that", "says", "europe", "on", "the", "spine"], "raw": "A book that says EUROPE on the spine.", "sent_id": 103453, "sent": "a book that says europe on the spine"}, {"tokens": ["a", "book", "entitled", "let", "'", "s", "go", "europe", "on", "a", "budget"], "raw": "A book entitled Let's Go Europe On a Budget.", "sent_id": 103454, "sent": "a book entitled let ' s go europe on a budget"}], "file_name": "COCO_train2014_000000252277_1140422.jpg", "ann_id": 1140422, "sent_ids": [103453, 103454], "ref_id": 49789}, {"segmentation": [[211.01, 415.2, 219.74, 381.18, 215.37, 334.94, 220.61, 289.58, 207.52, 300.92, 185.72, 327.09, 177.86, 319.24, 190.95, 286.96, 236.31, 239.86, 272.94, 218.06, 288.65, 187.52, 348.84, 122.1, 371.52, 90.7, 368.04, 75.86, 386.35, 78.48, 387.23, 67.14, 416.01, 83.72, 430.84, 112.51, 420.37, 113.37, 381.11, 107.27, 330.52, 222.41, 342.73, 251.2, 334.01, 279.99, 359.3, 306.15, 368.04, 396.88, 347.97, 389.03, 351.45, 357.62, 349.71, 321.86, 313.07, 288.71, 304.35, 287.84, 288.65, 298.31, 306.1, 307.9, 277.31, 308.77, 266.84, 320.99, 271.21, 350.65, 294.75, 400.37, 287.78, 404.73, 244.16, 342.8, 245.9, 313.14, 234.56, 334.94, 231.08, 402.11, 223.23, 419.56, 208.4, 419.56]], "area": 22373.56980000001, "iscrowd": 0, "image_id": 395432, "bbox": [177.86, 67.14, 252.98, 352.42], "category_id": 25, "id": 595307, "split": "val", "sentences": [{"tokens": ["male", "giraffe", "alongside", "another", "giraffe"], "raw": "Male giraffe alongside another giraffe", "sent_id": 103912, "sent": "male giraffe alongside another giraffe"}, {"tokens": ["a", "larger", "giraffe", "climbing", "up", "behind", "a", "smaller", "giraffe"], "raw": "A larger giraffe climbing up behind a smaller giraffe", "sent_id": 103913, "sent": "a larger giraffe climbing up behind a smaller giraffe"}], "file_name": "COCO_train2014_000000395432_595307.jpg", "ann_id": 595307, "sent_ids": [103912, 103913], "ref_id": 49804}]}