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 251260 of 1149 papers

TitleStatusHype
Large Scale Holistic Video UnderstandingCode1
EEV: A Large-Scale Dataset for Studying Evoked Expressions from VideoCode1
Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task PerspectivesCode1
Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional PropertiesCode1
PhysGame: Uncovering Physical Commonsense Violations in Gameplay VideosCode1
Is Appearance Free Action Recognition Possible?Code1
Procedure-Aware Pretraining for Instructional Video UnderstandingCode1
HAT: History-Augmented Anchor Transformer for Online Temporal Action LocalizationCode1
Panoramic Vision Transformer for Saliency Detection in 360° VideosCode1
Compositional Video Understanding with Spatiotemporal Structure-based TransformersCode1
Show:102550
← PrevPage 26 of 115Next →

No leaderboard results yet.