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 461470 of 1149 papers

TitleStatusHype
Screencast Tutorial Video UnderstandingCode0
ScaleLong: A Multi-Timescale Benchmark for Long Video UnderstandingCode0
SeriesBench: A Benchmark for Narrative-Driven Drama Series UnderstandingCode0
Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action SegmentationCode0
Gaussian Temporal Awareness Networks for Action LocalizationCode0
Relation-aware Hierarchical Attention Framework for Video Question AnsweringCode0
Re-ID-AR: Improved Person Re-identification in Video via Joint Weakly Supervised Action RecognitionCode0
Representation Flow for Action RecognitionCode0
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video ProcessingCode0
Contextual Explainable Video Representation: Human Perception-based UnderstandingCode0
Show:102550
← PrevPage 47 of 115Next →

No leaderboard results yet.