AAAI Publications, Thirty-Second AAAI Conference on Artificial Intelligence

Font Size: 
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Sijie Yan, Yuanjun Xiong, Dahua Lin

Last modified: 2018-04-27

Abstract


Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

Keywords


graph convolutional network; skeleton; action recognition

Full Text: PDF