SPAR: An efficient self-attention network using Switching Partition Strategy for skeleton-based action recognition

Zijie Zhu, Rendong Ying, Fei Wen, Peilin Liu

Abstract: Highlights•We propose an efficient method for skeleton-based action recognition.•We adopt self-attention to model the long-range features of joints.•We design two partition strategies for low computational cost of self-attention.•Our method achieves state-of-the-art in accuracy along with efficiency.