wchai/AuroraCap-7B-VID
Updated
•
23
•
2
AuroraCap
Efficient, Performant Video Detailed Captioning and a New Benchmark
-
-
wchai/AuroraCap-7B-VID-xtuner
Updated -
wchai/AuroraCap-7B-IMG
Updated • 4 • 2 -
wchai/AuroraCap-7B-IMG-xtuner
Updated
wchai/Video-Detailed-Caption
Viewer • Updated • 5Note The VDC benchmark contains 1,027 videos with captions averaging over 500 words.
wchai/AuroraCap-trainset
Viewer • Updated • 2Note over 20M image and video data collection for AuroraCap training with vicuna and llama-3 pre-tokenize.
wchai/AuroraCap-recaption
Viewer • Updated • 1Note video data recaptioned by AuroraCap.