Unverified50% confidenceFactExact time
OmniCapBench contains 786 densely annotated videos.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedOmniCapBench (Omni-Video Caption Benchmark) is a deeply structured diagnostic framework for audio-visual caption evaluation, whose prediction targets are three groups of atomic, verifiable evaluation units: entity reference, visual shot, and audio event.61% similarUnverifiedThe GraftSet-Video dataset constructed by the research team contains 2,397 prompts corresponding to 9,588 format-matched video examples, with an average of approximately 4 examples per prompt.60% similarUnverifiedThe Dancing Stick Figures dataset contains 1,430 six-second short video clips, totaling 514,800 annotated frames.57% similarUnverifiedHiDream's open-sourced image-to-video model HiDream O Video 1.0 received a score of 1456 on the LMSIS Video Arena, ranking 7th.55% similarUnverifiedThe CapMem benchmark dataset contains 75 videos with a total duration of 33.7 hours, 1,000 manually annotated multiple-choice questions, covering 16 different scenarios.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1012771API
curl https://kongchang.com/api/v1/knowledge/claims/1012771MCP
get_claim(id=1012771)