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 3140 of 1149 papers

TitleStatusHype
VideoEval-Pro: Robust and Realistic Long Video Understanding EvaluationCode4
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsCode4
VideoChat: Chat-Centric Video UnderstandingCode4
Video Understanding with Large Language Models: A SurveyCode4
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming VideosCode3
Towards Universal Soccer Video UnderstandingCode3
Harnessing Temporal Causality for Advanced Temporal Action DetectionCode3
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceCode3
Hawk: Learning to Understand Open-World Video AnomaliesCode3
Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsCode3
Show:102550
← PrevPage 4 of 115Next →

No leaderboard results yet.