A GCN and Transformer complementary network for skeleton-based action recognition

Xuezhi Xiang, Xiaoheng Li, Xuzhao Liu, Yulong Qiao, Abdulmotaleb El-Saddik

Abstract: Highlights•We propose a combined GCN and self-attention module for parallel communication and effective correlation modeling.•We design a position-aware module to handle long-term sequence ordering and position detection.•Experiments on NTU RGBD+60 and NTU RGBD+120 demonstrates competitive results.