SOTAVerified

Online Action Detection

Online action detection is the task of predicting the action as soon as it happens in a streaming video without access to video frames in the future.

Papers

Showing 110 of 39 papers

TitleStatusHype
Colar: Effective and Efficient Online Action Detection by Consulting ExemplarsCode2
Context-Enhanced Memory-Refined Transformer for Online Action DetectionCode1
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming VideosCode1
Memory-and-Anticipation Transformer for Online Action UnderstandingCode1
E2E-LOAD: End-to-End Long-form Online Action DetectionCode1
MiniROAD: Minimal RNN Framework for Online Action DetectionCode1
Real-time Online Video Detection with Temporal Smoothing TransformersCode1
Continual Transformers: Redundancy-Free Attention for Online InferenceCode1
Long Short-Term Transformer for Online Action DetectionCode1
OadTR: Online Action Detection with TransformersCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.