Spatial Temporal Transformer Network for Skeleton-Based Action Recognition

Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data been demonstrated to be robust illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an effective encoding of the latent information underlying 3D is still open problem. In this work, we propose novel Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using self-attention operator. our ST-TR model, Spatial Self-Attention module (SSA) used understand intra-frame interactions different parts, Temporal (TSA) model inter-frame correlations. The two are combined two-stream outperforms state-of-the-art same input on both NTU-RGB+D 60 120.