Attentional weighting strategy-based dynamic GCN for skeleton-based action recognition

Graph Convolutional Networks (GCNs) have become the standard skeleton-based human action recognition research paradigm. As a core component in graph convolutional networks, the construction of graph topology often significantly impacts the accuracy of classification. Considering that the fixed physi...

Full description

Saved in:
Bibliographic Details
Published inMultimedia systems Vol. 29; no. 4; pp. 1941 - 1954
Main Authors Hu, Kai, Jin, Junlan, Shen, Chaowen, Xia, Min, Weng, Liguo
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2023
Springer Nature B.V
Subjects
Artificial neural networks
Computer Communication Networks
Computer Graphics
Computer Science
Cryptology
Data Storage Representation
Human activity recognition
Multimedia Information Systems
Nodes
Operating Systems
Regular Paper
Topology
Weighting
Position feature
Skeleton-based action recognition
Graph topology
Online AccessGet full text

Cover

More Information
Summary:Graph Convolutional Networks (GCNs) have become the standard skeleton-based human action recognition research paradigm. As a core component in graph convolutional networks, the construction of graph topology often significantly impacts the accuracy of classification. Considering that the fixed physical graph topology cannot capture the non-physical connection relationship of the human body, existing methods capture more flexible node relationships by constructing dynamic graph structures. This paper proposes a novel attentional weighting strategy-based dynamic GCN (AWD-GCN). We construct a new dynamic adjacency matrix, which uses the attention weighting mechanism to simultaneously capture the dynamic relationships among the three partitions of the human skeleton under multiple actions to extract the discriminative action features fully. In addition, considering the importance of skeletal node position features for action differentiation, we propose new multi-scale position attention and multi-level attention. We use a multi-scale modelling method to capture the complex relationship between skeletal node position features, which is helpful in distinguishing human action in different spatial scales. Extensive experiments on two challenging datasets, NTU-RGB+D and Skeleton-Kinetics, demonstrate the effectiveness and superiority of our method.
ISSN:0942-4962
1432-1882
DOI:10.1007/s00530-023-01082-1