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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–110 of 1149 papers

TitleStatusHype
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object TrajectoryCode2
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMsCode2
ST-LLM: Large Language Models Are Effective Temporal LearnersCode2
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language ModelsCode2
Neptune: The Long Orbit to Benchmarking Long Video UnderstandingCode2
Multi-granularity Correspondence Learning from Long-term Noisy VideosCode2
MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkCode2
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-ConquerCode2
Show:102550
← PrevPage 11 of 115Next →

No leaderboard results yet.