Login
Register
Reset Password
Publish & Distribute
Publishing Solutions
Distribution Solutions
Subjects
Architecture and Design
Arts
Business and Economics
Chemistry
Classical and Ancient Near Eastern Studies
Computer Sciences
Cultural Studies
Engineering
General Interest
Geosciences
History
Industrial Chemistry
Jewish Studies
Law
Library and Information Science, Book Studies
Life Sciences
Linguistics and Semiotics
Literary Studies
Materials Sciences
Mathematics
Medicine
Music
Pharmacy
Philosophy
Physics
Social Sciences
Sports and Recreation
Theology and Religion
Publications
Journals
Books
Proceedings
Publishers
Blog
Contact
Search
EUR
USD
GBP
English
English
Deutsch
Polski
Español
Français
Italiano
Cart
Home
Journals
Applied Mathematics and Nonlinear Sciences
Volume 7 (2022): Issue 2 (July 2022)
Open Access
Spatial–temporal graph neural network based on node attention
Qiang Li
Qiang Li
,
Jun Wan
Jun Wan
,
Wucong Zhang
Wucong Zhang
and
Qian Long Kweh
Qian Long Kweh
| Apr 08, 2022
Applied Mathematics and Nonlinear Sciences
Volume 7 (2022): Issue 2 (July 2022)
About this article
Previous Article
Next Article
Abstract
Article
Figures & Tables
References
Authors
Articles in this Issue
Preview
PDF
Cite
Share
Published Online:
Apr 08, 2022
Page range:
703 - 712
Received:
May 23, 2021
Accepted:
Sep 27, 2021
DOI:
https://doi.org/10.2478/amns.2022.1.00005
Keywords
Action recognition
,
skeletons
,
spatial–temporal graph convolution
,
attention mechanism
© 2021 Qiang Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.
Fig. 1
(a) Spatial–temporal skeletal graph. (b) Partitioning strategy graph.
Fig. 2
Structure diagram of NA-STGCN. GCN, graph convolutional neural network; NA-STGCN, node attention spatial–temporal graph convolutional neural network.
Fig. 3
Change curve of loss values. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.
Fig. 4
Node activation response maps: (a) top left: ST-GCN clapping action; (b) top right: NA-STGCN clapping action; (c) bottom left: ST-GCN brushing action; (d) bottom right: NA-STGCN brushing action. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.
Comparison with representative methods (%).
Model
CS
CV
Two-Stream 3DCNN [
8
]
66.8
72.6
TCN [
22
]
74.3
83.1
Clip + CNN + MTLN [
23
]
79.6
84.8
VA-LSTM [
10
]
79.4
87.6
ST-GCN [
13
]
81.5
88.3
NA-STGCN (ours)
85.8
89.3