Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

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

Chinese University of Hong Kong HK

Related Publications

Psychological Safety and Learning Behavior in Work Teams

Amy C. Edmondson

This paper presents a model of team learning and tests it in a multimethod field study. It introduces the construct of team psychological safety—a shared belief held by members ...

1999 Administrative Science Quarterly 9366 citations

Bridging the Boundary: External Activity and Performance in Organizational Teams

Deborah Ancona , David F. Caldwell

1992 Administrative Science Quarterly 2170 citations

Narration as a human communication paradigm: The case of public moral argument

Walter R. Fisher

This essay proposes a theory of human communication based on a conception of persons as homo narrans. It compares and contrasts this view with the traditional rational perspecti...

1984 Communication Monographs 1704 citations

SELF-REGULATION FOR MANAGERIAL EFFECTIVENESS: THE ROLE OF ACTIVE FEEDBACK SEEKING.

Susan J. Ashford , Anne S. Tsui

This field study examined the feedback-seeking behavior of 387 managers as observed by their superiors, subordinates, and peers. Results suggest that managers' tendency to seek ...

1991 Academy of Management Journal 721 citations

Institutional Constraints on Social Movement "Frame Extension": Shifts in the Legislative Agenda of the American Federation of Labor, 1881-1955

Daniel B. Cornfield , Bill Fletcher

Journal Article Institutional Constraints on Social Movement “Frame Extension”: Shifts in the Legislative Agenda of the American Federation of Labor, 1881–1955 Get access Daniel...

1998 Social Forces 37 citations

Publication Info

Year: 2018
Type: article
Volume: 32
Issue: 1
Citations: 4453
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

4453

OpenAlex

Cite This

APA Style

                            
                                    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