Next Article in Journal
Extremal Trees with Respect to the Difference between Atom-Bond Connectivity Index and Randić Index
Previous Article in Journal
Supersymmetry of Relativistic Hamiltonians for Arbitrary Spin
Open AccessArticle

Dual Attention-Guided Multiscale Dynamic Aggregate Graph Convolutional Networks for Skeleton-Based Human Action Recognition

by and *,†
Department of Information Communication Engineering, Tongmyong University, Busan 48520, Korea
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Symmetry 2020, 12(10), 1589; https://doi.org/10.3390/sym12101589
Received: 13 August 2020 / Revised: 11 September 2020 / Accepted: 21 September 2020 / Published: 24 September 2020
(This article belongs to the Section Computer and Engineer Science and Symmetry)
Traditional convolution neural networks have achieved great success in human action recognition. However, it is challenging to establish effective associations between different human bone nodes to capture detailed information. In this paper, we propose a dual attention-guided multiscale dynamic aggregate graph convolution neural network (DAG-GCN) for skeleton-based human action recognition. Our goal is to explore the best correlation and determine high-level semantic features. First, a multiscale dynamic aggregate GCN module is used to capture important semantic information and to establish dependence relationships for different bone nodes. Second, the higher level semantic feature is further refined, and the semantic relevance is emphasized through a dual attention guidance module. In addition, we exploit the relationship of joints hierarchically and the spatial temporal correlations through two modules. Experiments with the DAG-GCN method result in good performance on the NTU-60-RGB+D and NTU-120-RGB+D datasets. The accuracy is 95.76% and 90.01%, respectively, for the cross (X)-View and X-Subon the NTU60dataset. View Full-Text
Keywords: human action recognition; multiscale graph convolutional networks; dynamic aggregation; hierarchical level semantic information; spatial and temporal correlation human action recognition; multiscale graph convolutional networks; dynamic aggregation; hierarchical level semantic information; spatial and temporal correlation
Show Figures

Graphical abstract

MDPI and ACS Style

Hu, Z.; Lee, E.-J. Dual Attention-Guided Multiscale Dynamic Aggregate Graph Convolutional Networks for Skeleton-Based Human Action Recognition. Symmetry 2020, 12, 1589.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop