Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition

Abstract In skeleton-based action recognition, abstracting the human body to skeletal representations often results in the loss of crucial information, which may result in misclassification of similar actions. To address this issue, we propose a Cross-scale Spatial Refinement Graph Convolutional Net...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengyuan Ke, Sheng Liu, Zhenghao Ke, Yuan Feng, Shengyong Chen
Format: Article
Language:English
Published: Springer 2025-04-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00802-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726431958925312
author Chengyuan Ke
Sheng Liu
Zhenghao Ke
Yuan Feng
Shengyong Chen
author_facet Chengyuan Ke
Sheng Liu
Zhenghao Ke
Yuan Feng
Shengyong Chen
author_sort Chengyuan Ke
collection DOAJ
description Abstract In skeleton-based action recognition, abstracting the human body to skeletal representations often results in the loss of crucial information, which may result in misclassification of similar actions. To address this issue, we propose a Cross-scale Spatial Refinement Graph Convolutional Network (CSR-GCN), which aims to improve action recognition accuracy by effectively capturing fine-grained features of skeleton sequences. In detail, we introduce an Attention-based Graph Pooling (AGP) module and a Cross-scale Feature Aggregation (CFA) module. The AGP module uses graph pooling to construct multi-scale skeletal sub-graphs, capturing implicit joint relationships and preserving crucial motion details. It retains global motion information while emphasizing local joint interactions, which enables a better understanding of dynamic changes in complex actions. Furthermore, the CFA module selectively integrates features from different spatial scales, enhancing feature distinctiveness while balancing global motion and local details. This multi-scale refinement of skeletal sequence representations, thereby capturing subtle dynamic changes in actions more precisely and enhancing the ability of the model to recognize and classify complex movement patterns. Finally, we validate the effectiveness of our method on three large-scale datasets, achieving superior accuracy compared to other state-of-the-art methods.
format Article
id doaj-art-eba52016d98745b785390319e87a4cf4
institution DOAJ
issn 1875-6883
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-eba52016d98745b785390319e87a4cf42025-08-20T03:10:10ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-04-0118111710.1007/s44196-025-00802-xCross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action RecognitionChengyuan Ke0Sheng Liu1Zhenghao Ke2Yuan Feng3Shengyong Chen4Zhejiang University of TechnologyZhejiang University of TechnologyZhejiang University of TechnologyZhejiang University of TechnologyTianjin University of TechnologyAbstract In skeleton-based action recognition, abstracting the human body to skeletal representations often results in the loss of crucial information, which may result in misclassification of similar actions. To address this issue, we propose a Cross-scale Spatial Refinement Graph Convolutional Network (CSR-GCN), which aims to improve action recognition accuracy by effectively capturing fine-grained features of skeleton sequences. In detail, we introduce an Attention-based Graph Pooling (AGP) module and a Cross-scale Feature Aggregation (CFA) module. The AGP module uses graph pooling to construct multi-scale skeletal sub-graphs, capturing implicit joint relationships and preserving crucial motion details. It retains global motion information while emphasizing local joint interactions, which enables a better understanding of dynamic changes in complex actions. Furthermore, the CFA module selectively integrates features from different spatial scales, enhancing feature distinctiveness while balancing global motion and local details. This multi-scale refinement of skeletal sequence representations, thereby capturing subtle dynamic changes in actions more precisely and enhancing the ability of the model to recognize and classify complex movement patterns. Finally, we validate the effectiveness of our method on three large-scale datasets, achieving superior accuracy compared to other state-of-the-art methods.https://doi.org/10.1007/s44196-025-00802-xGraph convolutional networkAction recognitionSkeleton-basedGraph pooling
spellingShingle Chengyuan Ke
Sheng Liu
Zhenghao Ke
Yuan Feng
Shengyong Chen
Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
International Journal of Computational Intelligence Systems
Graph convolutional network
Action recognition
Skeleton-based
Graph pooling
title Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
title_full Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
title_fullStr Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
title_full_unstemmed Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
title_short Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
title_sort cross scale spatial refinement graph convolutional network for skeleton based action recognition
topic Graph convolutional network
Action recognition
Skeleton-based
Graph pooling
url https://doi.org/10.1007/s44196-025-00802-x
work_keys_str_mv AT chengyuanke crossscalespatialrefinementgraphconvolutionalnetworkforskeletonbasedactionrecognition
AT shengliu crossscalespatialrefinementgraphconvolutionalnetworkforskeletonbasedactionrecognition
AT zhenghaoke crossscalespatialrefinementgraphconvolutionalnetworkforskeletonbasedactionrecognition
AT yuanfeng crossscalespatialrefinementgraphconvolutionalnetworkforskeletonbasedactionrecognition
AT shengyongchen crossscalespatialrefinementgraphconvolutionalnetworkforskeletonbasedactionrecognition