SOTAVerified

Weakly-Supervised Action Recognition

Action recognition with single-point annotations in time (there are no action start/stop time annotations)

Papers

Showing 14 of 4 papers

TitleStatusHype
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Re-ID-AR: Improved Person Re-identification in Video via Joint Weakly Supervised Action RecognitionCode0
UntrimmedNets for Weakly Supervised Action Recognition and DetectionCode0
Show:102550

No leaderboard results yet.