SOTAVerified

Video Understanding

A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.

Source: Action Detection from a Robot-Car Perspective

Papers

Showing 7180 of 1149 papers

TitleStatusHype
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video ComprehensionCode2
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
Omni-Video: Democratizing Unified Video Understanding and GenerationCode2
AIN: The Arabic INclusive Large Multimodal ModelCode2
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-ConquerCode2
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object TrajectoryCode2
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and PruningCode2
AIM: Adapting Image Models for Efficient Video Action RecognitionCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
Multi-granularity Correspondence Learning from Long-term Noisy VideosCode2
Show:102550
← PrevPage 8 of 115Next →

No leaderboard results yet.