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 891900 of 1149 papers

TitleStatusHype
Multi-modal Representation Learning for Video Advertisement Content Structuring0
Spatio-Temporal Perturbations for Video AttributionCode0
LIGAR: Lightweight General-purpose Action Recognition0
Identity-aware Graph Memory Network for Action Detection0
Foreground-Action Consistency Network for Weakly Supervised Temporal Action LocalizationCode1
AutoVideo: An Automated Video Action Recognition SystemCode1
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection0
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning0
Elaborative Rehearsal for Zero-shot Action RecognitionCode1
Token Shift Transformer for Video ClassificationCode1
Show:102550
← PrevPage 90 of 115Next →

No leaderboard results yet.