commit files to HF hub

papers.csv

@@ -1,6 +1,6 @@
 title,authors,type,arxiv_id,arxiv,github,hf_paper,hf_space,hf_model,hf_dataset,n_authors,n_linked_authors
 Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning,"Huang, Yangru; Peng, Peixi*; Zhao, Yifan; Zhai, Yunpeng; Xu, Haoran; Tian, Yonghong",poster,,,,,,,,,
-Among Us: Adversarially Robust Collaborative Perception by Consensus,"Li, Yiming; Fang, Qi; Bai, Jiamu; Chen, Siheng; Juefei-Xu, Felix; Feng, Chen*",poster,2303.09495,https://arxiv.org/abs/2303.09495,,https://huggingface.co/papers/2303.09495,,,,6,2
+Among Us: Adversarially Robust Collaborative Perception by Consensus,"Li, Yiming; Fang, Qi; Bai, Jiamu; Chen, Siheng; Juefei-Xu, Felix; Feng, Chen*",poster,2303.09495,https://arxiv.org/abs/2303.09495,,https://huggingface.co/papers/2303.09495,,,,6,3
 Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation,"Saltori, Cristiano*; Osep, Aljosa; Ricci, Elisa; Leal-Taixé, Laura",poster,2304.11705,https://arxiv.org/abs/2304.11705,,https://huggingface.co/papers/2304.11705,,,,4,1
 Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation,"Zhai, Yunpeng*; Peng, Peixi; Zhao, Yifan; Huang, Yangru; Tian, Yonghong",poster,,,,,,,,,
 MAAL: Multimodality-Aware Autoencoder-based Affordance Learning for 3D Articulated Objects,"liang, yuanzhi*; Wang, Xiaohan; Zhu, Linchao; Yang, Yi",poster,,,,,,,,,
@@ -593,7 +593,7 @@ FB-BEV: BEV Representation from Forward-Backward View Transformations,"Li, Zhiqi
 Learning from Noisy Data for Semi-Supervised 3D Object Detection,"Chen, Zehui; Li, Zhenyu; Wang, Shuo; Fu, Dengpan; Zhao, Feng*",poster,,,,,,,,,
 Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data,"Dong, Na*; Zhang, Yongqiang; Ding, Mingli; Lee, Gim Hee",poster,2305.12833,https://arxiv.org/abs/2305.12833,,https://huggingface.co/papers/2305.12833,,,,4,0
 Objects do not disappear: Video object detection by single-frame object location anticipation,"Liu, Xin*; Karimi Nejadasl, Fatemeh; van Gemert, Jan C; Booij, Olaf; Pintea, Silvia L",poster,2308.04770,https://arxiv.org/abs/2308.04770,https://github.com/L-KID/Videoobject-detection-by-location-anticipation,https://huggingface.co/papers/2308.04770,,,,5,0
-Unified Visual Relationship Detection with Vision and Language Models,"Zhao, Long*; Yuan, Liangzhe; Gong, Boqing; Cui, Yin; Schroff, Florian; Yang, Ming-Hsuan; Adam, Hartwig; Liu, Ting",poster,2303.08998,https://arxiv.org/abs/2303.08998,,https://huggingface.co/papers/2303.08998,,,,8,0
+Unified Visual Relationship Detection with Vision and Language Models,"Zhao, Long*; Yuan, Liangzhe; Gong, Boqing; Cui, Yin; Schroff, Florian; Yang, Ming-Hsuan; Adam, Hartwig; Liu, Ting",poster,2303.08998,https://arxiv.org/abs/2303.08998,,https://huggingface.co/papers/2303.08998,,,,8,1
 Universal Domain Adaptation via Compressive Attention Matching,"zhu, didi; Li, Yinchuan; Yuan, Junkun; Li, Zexi; Kuang, Kun; Wu, Chao*",poster,2304.11862,https://arxiv.org/abs/2304.11862,,https://huggingface.co/papers/2304.11862,,,,6,0
 Unsupervised Domain Adaptive Detection with Network Stability Analysis,"Zhou, Wenzhang; Fan, Heng; Luo, Tiejian; Zhang, Libo*",poster,2308.08182,https://arxiv.org/abs/2308.08182,https://github.com/tiankongzhang/NSA,https://huggingface.co/papers/2308.08182,,,,4,0
 ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection,"Tu, Tao*; Chuang, Shun-Po; Liu, Yu-Lun; Sun, Cheng; Zhang, Ke; Roy, Donna; Kuo, Cheng-Hao; Sun, Min",poster,2308.09098,https://arxiv.org/abs/2308.09098,,https://huggingface.co/papers/2308.09098,,,,8,0
@@ -654,7 +654,7 @@ An Empirical Study of Perceptual Artifacts Localization on Image Synthesis,"Zhan
 Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis,"Park, Minho; Yun, JooYeol*; Choi, Seunghwan; Choo, Jaegul",poster,2308.08157,https://arxiv.org/abs/2308.08157,,https://huggingface.co/papers/2308.08157,,,,4,2
 StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model,"Xu, Zipeng*; Sangineto, Enver; Sebe, Niculae",poster,2303.09268,https://arxiv.org/abs/2303.09268,https://github.com/zipengxuc/StylerDALLE,https://huggingface.co/papers/2303.09268,,,,3,0
 Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction,"Chung, Chaeyeon*; Park, Yeojeong; Choi, Seunghwan; Ganbat, Munkhsoyol; Choo, Jaegul",poster,,,,,,,,,
-Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation,"Wu, Jay Zhangjie*; Ge, Yixiao; Wang, Xintao; Lei, Stan Weixian; Gu, Yuchao; Shi, Yufei; Hsu, Wynne; Shan, Ying; Qie, Xiaohu; Shou, Mike Zheng",poster,2212.11565,https://arxiv.org/abs/2212.11565,https://github.com/showlab/Tune-A-Video,https://huggingface.co/papers/2212.11565,https://huggingface.co/spaces/Tune-A-Video-library/Tune-A-Video-Training-UI,,,10,1
+Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation,"Wu, Jay Zhangjie*; Ge, Yixiao; Wang, Xintao; Lei, Stan Weixian; Gu, Yuchao; Shi, Yufei; Hsu, Wynne; Shan, Ying; Qie, Xiaohu; Shou, Mike Zheng",poster,2212.11565,https://arxiv.org/abs/2212.11565,https://github.com/showlab/Tune-A-Video,https://huggingface.co/papers/2212.11565,https://huggingface.co/spaces/Tune-A-Video-library/Tune-A-Video-Training-UI,,,9,1
 BlendFace: Re-designing Identity Encoders for Face-Swapping,"Shiohara, Kaede*; Yang, Xingchao; Taketomi, Takafumi",poster,2307.10854,https://arxiv.org/abs/2307.10854,,https://huggingface.co/papers/2307.10854,,,,3,0
 Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors,"Yu, Zhentao*; Yin, Zixin; Zhou, Deyu; Wang, Duomin; Wong, Finn; Wang, Baoyuan",poster,2212.04248,https://arxiv.org/abs/2212.04248,,https://huggingface.co/papers/2212.04248,,,,6,0
 LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis,"Zhu, Jiapeng*; Yang, Ceyuan; Shen, Yujun; SHI, Zifan; Dai, Bo; Zhao, Deli; Chen, Qifeng",poster,2301.04604,https://arxiv.org/abs/2301.04604,,https://huggingface.co/papers/2301.04604,,,,6,0
@@ -677,7 +677,7 @@ On the Audio-visual Synchronization for Lip-to-Speech Synthesis,"NIU, Zhe*; Mak,
 Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples ,"Chen, Mingfei*; Su, Kun; Shlizerman, Eli",poster,,,,,,,,,
 Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation,"Yun, Heeseung*; Na, Joonil; Kim, Gunhee",poster,,,,,,,,,
 Hyperbolic Audio-visual Zero-shot Learning,"Hong, Jie*; Hayder, Zeeshan; Han, Junlin; Fang, Pengfei; Harandi, Mehrtash; Petersson, Lars",poster,2308.12558,https://arxiv.org/abs/2308.12558,,https://huggingface.co/papers/2308.12558,,,,6,2
-AdVerb: Visually Guided Audio Dereverberation,"Chowdhury, Sanjoy*; Ghosh, Sreyan; Dasgupta, Subhrajyoti; Ratnarajah, Anton J; Tyagi, Utkarsh; Manocha, Dinesh",poster,2308.12370,https://arxiv.org/abs/2308.12370,,https://huggingface.co/papers/2308.12370,,,,6,0
+AdVerb: Visually Guided Audio Dereverberation,"Chowdhury, Sanjoy*; Ghosh, Sreyan; Dasgupta, Subhrajyoti; Ratnarajah, Anton J; Tyagi, Utkarsh; Manocha, Dinesh",poster,2308.12370,https://arxiv.org/abs/2308.12370,,https://huggingface.co/papers/2308.12370,,,,6,1
 Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation,"Chen, Ziyang*; Qian, Shengyi; Owens, Andrew",poster,2303.11329,https://arxiv.org/abs/2303.11329,,https://huggingface.co/papers/2303.11329,,,,3,1
 Learning Conditional Control for Pretrained Text-to-Image Diffusion Models,"Zhang, Lvmin*; Rao, Anyi; Agrawala, Maneesh",oral,,,,,,,,,
 Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation,"Zhu, Rui*; Wu, Liwen; Ramamoorthi, Ravi; Zhu, Yinhao; Cai, Hong; Matai, Janarbek; Li, Tzu-Mao; Yaldiz, Mustafa B; Porikli, Fatih; Chandraker, Manmohan",oral,2304.05669,https://arxiv.org/abs/2304.05669,https://github.com/lwwu2/fipt,https://huggingface.co/papers/2304.05669,,,,10,0
@@ -1529,7 +1529,7 @@ Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation,"Ding, Shua
 Differentiable Transportation Pruning,"Li, Yunqiang*; van Gemert, Jan C; Hoefler, Torsten; Moons, Bert; Eleftheriou, Evangelos; Verhoef, Bram-Ernst",poster,2307.08483,https://arxiv.org/abs/2307.08483,,https://huggingface.co/papers/2307.08483,,,,6,0
 XiNet: Efficient Neural Networks for tinyML,"Ancilotto, Alberto*; Paissan, Francesco; Farella, Elisabetta",poster,,,,,,,,,
 Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers,"Frumkin, Natalia*; Gope, Dibakar; Marculescu, Diana",poster,2308.10814,https://arxiv.org/abs/2308.10814,https://github.com/enyac-group/evol-q,https://huggingface.co/papers/2308.10814,,,,3,1
-A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance,"Colbert, Ian*; Pappalardo, Alessandro; Petri-Koenig, Jakoba",poster,2308.13504,https://arxiv.org/abs/2308.13504,,https://huggingface.co/papers/2308.13504,,,,3,0
+A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance,"Colbert, Ian*; Pappalardo, Alessandro; Petri-Koenig, Jakoba",poster,2308.13504,https://arxiv.org/abs/2308.13504,,https://huggingface.co/papers/2308.13504,,,,3,1
 Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization,"Chen, Rui*; Wan, Qiyu ; Prakash, Pavana; Zhang, Lan; Yuan, Xu; Gong, Yanmin; Fu, Xin; Pan, Miao",poster,,,,,,,,,
 DenseShift: Towards Accurate and Transferable Low-Bit Shift Network,"Li, Xinlin*; Liu, Bang; Yang, Rui Heng; Courville, Vanessa; Xing, Chao; Partovi Nia, Vahid",poster,2208.09708,https://arxiv.org/abs/2208.09708,,https://huggingface.co/papers/2208.09708,,,,6,0
 PRANC: Pseudo RAndom Networks for Compacting deep models,"Nooralinejad, Parsa*; Abbasi, Ali; Abbasi Koohpayegani, Soroush; Khan, Rana Muhammad Shahroz; Pourahmadi Meibodi, Kossar; Kolouri, Soheil; Pirsiavash, Hamed",poster,2206.08464,https://arxiv.org/abs/2206.08464,https://github.com/UCDvision/PRANC,https://huggingface.co/papers/2206.08464,,,,7,1
@@ -2016,7 +2016,7 @@ Interactive Class-Agnostic Object Counting,"Huang, Yifeng; Ranjan, Viresh; Hoai,
 Agile Modeling: From Concept to Classifier in Minutes,"Stretcu, Otilia*; Vendrow, Edward; Hata, Kenji; Viswanathan, Krishnamurthy; Ferrari, Vittorio; Tavakkol, Sasan; Zhou, Wenlei; Avinash, Aditya; Luo, Emming; Alldrin, Neil; Bateni, MohammadHossein; Berger, Gabriel; Bunner, Andrew; Lu, Chun-Ta; Rey, Javier A; DeSalvo, Giulia; Krishna, Ranjay; Fuxman?, Ariel",poster,2302.12948,https://arxiv.org/abs/2302.12948,,https://huggingface.co/papers/2302.12948,,,,18,0
 TiDAL: Learning Training Dynamics for Active Learning,"Kye, Seong Min; Choi, Kwanghee; Byun, Hyeongmin; Chang, Buru*",poster,2210.06788,https://arxiv.org/abs/2210.06788,,https://huggingface.co/papers/2210.06788,,,,3,0
 Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning,"Zhou, Jizhe*; Ma, Xiaochen; Du, Xia; Alhammadi, Ahmed Y; Feng, Wentao",poster,,,,,,,,,
-VADER: Video Alignment Differencing and Retrieval,"Black, Alexander*; Jenni, Simon; Bui, Tu; Tanjim, Md. Mehrab; Petrangeli, Stefano; Sinha, Ritwik; Swaminathan, Viswanathan (Vishy); Collomosse, John",poster,2303.13193,https://arxiv.org/abs/2303.13193,,https://huggingface.co/papers/2303.13193,,,,8,0
+VADER: Video Alignment Differencing and Retrieval,"Black, Alexander*; Jenni, Simon; Bui, Tu; Tanjim, Md. Mehrab; Petrangeli, Stefano; Sinha, Ritwik; Swaminathan, Viswanathan (Vishy); Collomosse, John",poster,2303.13193,https://arxiv.org/abs/2303.13193,,https://huggingface.co/papers/2303.13193,,,,8,1
 PIRNet: Privacy-Preserving Image Restoration Network via Wavelet Lifting,"Deng, Xin; Gao, Chao*; Xu, Mai",poster,,,,,,,,,
 Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning,"Le, Binh M.*; Woo, Simon S",poster,,,,,,,,,
 Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning,"Zhai, Yuanhao*; Luan, Tianyu; Doermann, David; Yuan, Junsong",poster,,,,,,,,,