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
Computer scienceGeneralizationTree traversalAction recognitionGraphArtificial intelligenceGraph traversalConvolutional neural networkPattern recognition (psychology)Theoretical computer scienceAlgorithmMathematicsClass (philosophy)
Affiliated Institutions
Related Publications
Reentrant polygon clipping
A new family of clipping algorithms is described. These algorithms are able to clip polygons against irregular convex plane-faced volumes in three dimensions, removing the parts...
Fuel Cell Systems Explained
Preface. Foreword to the first edition. Acknowledgements. Abbreviations. Symbols. Introduction. Efficiency and Open Circuit Voltage. Operational Fuel Cell Voltages. Proton Excha...
Publication Info
- Year
- 2018
- Type
- article
- Volume
- 32
- Issue
- 1
- Citations
- 4453
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
4453
OpenAlex
Cite This
Sijie Yan,
Yuanjun Xiong,
Dahua Lin
(2018).
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition.
Proceedings of the AAAI Conference on Artificial Intelligence
, 32
(1)
.
https://doi.org/10.1609/aaai.v32i1.12328
Identifiers
- DOI
- 10.1609/aaai.v32i1.12328