no code implementations • 2 Jun 2018 • Gaoyun An, Wen Zhou, Yuxuan Wu, Zhenxing Zheng, Yongwen Liu
Spatial and temporal features are two key and complementary information for human action recognition.
no code implementations • 22 Nov 2017 • Zhenxing Zheng, Gaoyun An, Qiuqi Ruan
Each stream consists of a Residual Networks(ResNets) and a recurrent model.