AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
Paper
•
2410.03051
•
Published
•
4
Aurora Series: AuroraCap
Efficient, Performant Video Detailed Captioning and a New Benchmark
-
-
wchai/AuroraCap-7B-VID-xtuner
Video-Text-to-Text • Updated • 121 • 2 -
wchai/AuroraCap-7B-IMG-xtuner
Image-Text-to-Text • Updated • 32 • 1
wchai/Video-Detailed-Caption
Viewer • Updated • 1.03k • 4.2k • 2Note The VDC benchmark contains 1,027 videos with captions averaging over 500 words.
wchai/lmms_VDC_test
Viewer • Updated • 5.14k • 1.44k • 1Note VDC benchmark in lmms-eval format.
wchai/AuroraCap-trainset
Preview • Updated • 3.09k • 5Note over 20M image and video data collection for AuroraCap training with vicuna and llama-3 pre-tokenize.
wchai/AuroraCap-recaption
Viewer • Updated • 22.4k • 72 • 4Note video data recaptioned by AuroraCap.