Short-term path signature for skeleton-based action recognition

Skeleton-based action recognition (SBAR) is an important task in the field of computer vision. Learning effective action representations from skeleton sequences and improving the performance of action recognition models remain challenging problems. To capture effective features from skeleton sequences, a novel feature called a short-term path signature (STPS) is proposed in this work. Based on the STPS, a plug-and-play module is proposed to achieve improved SBAR. In this module, the STPS is applied as input, and a spatial-temporal graph convolutional network (ST-GCN) is used to learn action features. Finally, a multistream ST-GCN is built to achieve SBAR. The proposed method is verified on the NTU-RGB+D dataset. Several ablation experiments are conducted to verify the effectiveness of the proposed module. The experimental results show that the proposed STPS is beneficial for improving the accuracy of action recognition networks.