https://openreview.net/forum?id=BJN04bf_WS&referrer=%5Bthe%20profile%20of%20Lin%20Sun%5D(%2Fprofile%3Fid%3D~Lin_Sun1)
Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks | OpenReview
Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the...
human action recognitionusingfactorizedspatiotemporal