Hand-aware graph convolution network for skeleton-based sign language recognition

Skeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer fr...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Song, Huixuechun Wang, Jianan Li, Jian Zheng, Zhifu Zhao, Qingshan Li
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-01-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S294971592400074X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849253334647570432
author Juan Song
Huixuechun Wang
Jianan Li
Jian Zheng
Zhifu Zhao
Qingshan Li
author_facet Juan Song
Huixuechun Wang
Jianan Li
Jian Zheng
Zhifu Zhao
Qingshan Li
author_sort Juan Song
collection DOAJ
description Skeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer from a lack of explicit attention to hand topology which plays an important role in the sign language representation. To address this issue, we propose a novel hand-aware graph convolution network (HA-GCN) to focus on hand topological relationships of skeleton graph. Specifically, a hand-aware graph convolution layer is designed to capture both global body and local hand information, in which two sub-graphs are defined and incorporated to represent hand topology information. In addition, in order to eliminate the over-fitting problem, an adaptive DropGraph is designed in construction of hand-aware graph convolution block to remove the spatial and temporal redundancy in the sign language representation. With the aim to further improve the performance, the joints information, bones, together with their motion information are simultaneously modeled in a multi-stream framework. Extensive experiments on the two open-source datasets, AUTSL and INCLUDE, demonstrate that our proposed algorithm outperforms the state-of-the-art with a significant margin. Our code is available at https://github.com/snorlaxse/HA-SLR-GCN.
format Article
id doaj-art-6b2fab6acb77458e816efeaa5314071a
institution Kabale University
issn 2949-7159
language English
publishDate 2025-01-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-6b2fab6acb77458e816efeaa5314071a2025-08-20T03:56:23ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592025-01-0131365010.1016/j.jiixd.2024.08.001Hand-aware graph convolution network for skeleton-based sign language recognitionJuan Song0Huixuechun Wang1Jianan Li2Jian Zheng3Zhifu Zhao4Qingshan Li5School of Computer Science and Technology, Xidian University, Xi'an 710126, ChinaSchool of Computer Science and Technology, Xidian University, Xi'an 710126, ChinaSchool of Computer Science and Technology, Xidian University, Xi'an 710126, China; Corresponding author.School of Computer Science and Technology, Xidian University, Xi'an 710126, ChinaSchool of Artificial Intelligence Engineering, Xidian University, Xi'an 710126, ChinaSchool of Computer Science and Technology, Xidian University, Xi'an 710126, ChinaSkeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer from a lack of explicit attention to hand topology which plays an important role in the sign language representation. To address this issue, we propose a novel hand-aware graph convolution network (HA-GCN) to focus on hand topological relationships of skeleton graph. Specifically, a hand-aware graph convolution layer is designed to capture both global body and local hand information, in which two sub-graphs are defined and incorporated to represent hand topology information. In addition, in order to eliminate the over-fitting problem, an adaptive DropGraph is designed in construction of hand-aware graph convolution block to remove the spatial and temporal redundancy in the sign language representation. With the aim to further improve the performance, the joints information, bones, together with their motion information are simultaneously modeled in a multi-stream framework. Extensive experiments on the two open-source datasets, AUTSL and INCLUDE, demonstrate that our proposed algorithm outperforms the state-of-the-art with a significant margin. Our code is available at https://github.com/snorlaxse/HA-SLR-GCN.http://www.sciencedirect.com/science/article/pii/S294971592400074XSign language recognitionGraph convolutional networkHand-aware graphsSkeleton dataMulti-stream fusion
spellingShingle Juan Song
Huixuechun Wang
Jianan Li
Jian Zheng
Zhifu Zhao
Qingshan Li
Hand-aware graph convolution network for skeleton-based sign language recognition
Journal of Information and Intelligence
Sign language recognition
Graph convolutional network
Hand-aware graphs
Skeleton data
Multi-stream fusion
title Hand-aware graph convolution network for skeleton-based sign language recognition
title_full Hand-aware graph convolution network for skeleton-based sign language recognition
title_fullStr Hand-aware graph convolution network for skeleton-based sign language recognition
title_full_unstemmed Hand-aware graph convolution network for skeleton-based sign language recognition
title_short Hand-aware graph convolution network for skeleton-based sign language recognition
title_sort hand aware graph convolution network for skeleton based sign language recognition
topic Sign language recognition
Graph convolutional network
Hand-aware graphs
Skeleton data
Multi-stream fusion
url http://www.sciencedirect.com/science/article/pii/S294971592400074X
work_keys_str_mv AT juansong handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition
AT huixuechunwang handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition
AT jiananli handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition
AT jianzheng handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition
AT zhifuzhao handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition
AT qingshanli handawaregraphconvolutionnetworkforskeletonbasedsignlanguagerecognition