SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–60 of 1149 papers

Title	Date	Tasks	Status	Hype	Score
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos	Apr 24, 2025	MMEVideo MME	CodeCode Available	3	5
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding	Jun 13, 2024	Dense Video CaptioningMVBench	CodeCode Available	3	5
Harnessing Temporal Causality for Advanced Temporal Action Detection	Jul 25, 2024	Action DetectionAction Recognition	CodeCode Available	3	5
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models	Jul 22, 2024	Language Modeling	CodeCode Available	3	5
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference	Oct 6, 2024	Language ModelingLanguage Modelling	CodeCode Available	3	5
Towards Universal Soccer Video Understanding	Dec 2, 2024	Action ClassificationSports Understanding	CodeCode Available	3	5
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams	Jun 30, 2025	cross-modal alignmentEgoSchema	CodeCode Available	3	5
MLVU: Benchmarking Multi-task Long Video Understanding	Jun 6, 2024	BenchmarkingVideo Understanding	CodeCode Available	3	5
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams	Jun 12, 2024	cross-modal alignmentLanguage Modelling	CodeCode Available	3	5
EgoLife: Towards Egocentric Life Assistant	Mar 5, 2025	Question AnsweringVideo Understanding	CodeCode Available	3	5

Show:10 25 50

← PrevPage 6 of 115Next →

No leaderboard results yet.