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 291–300 of 1149 papers

TitleStatusHype
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot VideosCode1
ETAD: Training Action Detection End to End on a LaptopCode1
Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task PerspectivesCode1
REVECA -- Rich Encoder-decoder framework for Video Event CAptionerCode1
EPIC Fields: Marrying 3D Geometry and Video UnderstandingCode1
Revisiting spatio-temporal layouts for compositional action recognitionCode1
Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event AnalysisCode1
How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?Code1
Helping Hands: An Object-Aware Ego-Centric Video Recognition ModelCode1
Enhancing Self-supervised Video Representation Learning via Multi-level Feature OptimizationCode1
Show:102550
← PrevPage 30 of 115Next →

No leaderboard results yet.