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 10511060 of 1149 papers

TitleStatusHype
Temporally smooth online action detection using cycle-consistent future anticipationCode0
HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge UnderstandingCode0
Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTubeCode0
Temporal Action Proposal Generation With Action Frequency Adaptive NetworkCode0
A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero ShotCode0
Telling Stories for Common Sense Zero-Shot Action RecognitionCode0
Technical Report for CVPR 2022 LOVEU AQTC ChallengeCode0
Tiny Video NetworksCode0
Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental LearningCode0
Task-Aware KV Compression For Cost-Effective Long Video UnderstandingCode0
Show:102550
← PrevPage 106 of 115Next →

No leaderboard results yet.