SOTAVerified

Long-video Activity Recognition

Long-video Activity Recognition (LAR) focuses on modeling long-term relations among all actions in a long video. LAR aims to recognize all actions within each long video, under the weak supervision of the video-level action category set. The mean average precision metric (mAP) is used for evaluation.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–6 of 6 papers

TitleStatusHype
Timeception for Complex Action RecognitionCode1
ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room—0
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition—0
Graph-Based High-Order Relation Modeling for Long-Term Action Recognition—0
VideoGraph: Recognizing Minutes-Long Human Activities in Videos—0
ActionVLAD: Learning spatio-temporal aggregation for action classification—0
Show:102550

No leaderboard results yet.