A Separable Spatial-Temporal Graph Learning Approach for Skeleton-Based Action Recognition

• Published in: IEEE sensors letters 2024-11, Vol.8 (11), p.1-4
• Main Authors: Zheng, Hui, Zhao, Ye-Sheng, Zhang, Bo, Shang, Guo-Qiang
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial neural networks; Bones; Convolution; Costs; Data mining; Feature extraction; Graph convolutional networks; Graphical representations; human action recognition (HAR); Human activity recognition; Joints; Laplace equations; Machine learning; Pipelines; Pose estimation; Sensor signal processing; separable; spatial–temporal graph network; Spatiotemporal data
• ISSN: 2475-1472; 2475-1472
• DOI: 10.1109/LSENS.2024.3475515

With the popularization of sensors and the development of pose estimation algorithms, a skeleton-based action recognition task has gradually become mainstream in human action recognition tasks. The key to solving skeleton-based action recognition task is to extract feature representations that can accurately outline the characteristics of human actions from sensor data. In this letter, we propose a separable spatial-temporal graph learning approach, which is composed of independent spatial and temporal graph networks. In the spatial graph network, spectral-based graph convolutional network is selected to mine spatial features of each moment. In the temporal graph network, a global-local attention mechanism is embedded to excavate interdependence at different times. Extensive experiments are carried out on the NTU-RGB+D and NTU-RGB+D 120 datasets, and the results show that our proposed method outperforms several other baselines.