Spatialoral graph neural network based on node attention

Simple item page
dc.contributor.authorLi, Qiang
dc.contributor.authorWan, Jun
dc.contributor.authorZhang, Wucong
dc.contributor.authorKweh, Qian Long
dc.date.accessioned2022-05-22T10:41:34Z
dc.date.available2022-05-22T10:41:34Z
dc.date.copyright© 2021
dc.date.issued2022
dc.description.abstractRecently, the method of using graph neural network based on skeletons for action recognition has become more and more popular, due to the fact that a skeleton can carry very intuitive and rich action information, without being affected by background, light and other factors. The spatialoral graph convolutional neural network (ST-GCN) is a dynamic skeleton model that automatically learns spatialoral model from data, which not only has stronger expression ability, but also has stronger generalisation ability, showing remarkable results on public data sets. However, the ST-GCN network directly learns the information of adjacent nodes (local information), and is insufficient in learning the relations of non-adjacent nodes (global information), such as clapping action that requires learning the related information of non-adjacent nodes. Therefore, this paper proposes an ST-GCN based on node attention (NA-STGCN), so as to solve the problem of insufficient global information in ST-GCN by introducing node attention module to explicitly model the interdependence between global nodes. The experimental results on the NTU-RGB+D set show that the node attention module can effectively improve the accuracy and feature representation ability of the existing algorithms, and obviously improve the recognition effect of the actions that need global information. © 2021 Qiang Li et al., published by Sciendo 2021.
dc.identifier.citationLi, Q., Wan, J., Zhang, W., & Kweh, Q. L. (2022). Spatialoral graph neural network based on node attention. Applied Mathematics and Nonlinear Sciences. https://doi.org/10.2478/amns.2022.1.00005
dc.identifier.issn24448656
dc.identifier.urihttps://doi.org/10.2478/amns.2022.1.00005
dc.identifier.urihttp://hdl.handle.net/20.500.12519/654
dc.language.isoen_US
dc.publisherSciendo
dc.relationAuthors Affiliations : Li, Q., School Of Electronic And Information Engineering, South China University Of Technology, Guangzhou, China; Wan, J., School Of Electronic And Information Engineering, South China University Of Technology, Guangzhou, China; Zhang, W., School Of Electronic And Information Engineering, South China University Of Technology, Guangzhou, China; Kweh, Q.L., Canadian University Dubai, Canada
dc.relation.ispartofseriesApplied Mathematics and Nonlinear Sciences
dc.rightsCreative Commons Attribution 4.0 International License.
dc.rights.holderCopyright : © 2021 Qiang Li et al., published by Sciendo 2021.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectAction recognition
dc.subjectattention mechanism
dc.subjectskeletons
dc.subjectspatialoral graph convolution
dc.titleSpatialoral graph neural network based on node attention
dc.typeArticle
dspace.entity.type

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Access Instruction
Size:
1.45 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Accounting & Finance