Multimodal Adaptive Graph Convolution: Toward Robust Skeleton-based Action Recognition.
Saved in:
| Title: | Multimodal Adaptive Graph Convolution: Toward Robust Skeleton-based Action Recognition. |
|---|---|
| Authors: | Guo, Lijuan1 guolj.sy@gx.csg.cn, Xie, Guoshan2 xiegs.sy@gx.csg.cn, Mo, Jing3 moj@gx.csg.cn, Shi, Fengwei4 shifw.lbg@gx.csg.cn, Wang, Le2 wangl.sy@gx.csg.cn |
| Source: | IAENG International Journal of Computer Science. Jun2026, Vol. 53 Issue 6, p2400-2409. 10p. |
| Subjects: | Human activity recognition, Graph neural networks, Learning, Multisensor data fusion, Spatiotemporal processes |
| Abstract: | Significant progress has been made in human action recognition through the use of various modalities, such as RGB videos, depth maps, skeleton data, and infrared imaging. Skeleton-based methods that use graph convolutional networks (GCNs) are particularly impressive. Recent methods employ deformable graph convolution operations to automatically identify semantically important body joints, increasing computational efficiency while maintaining high recognition accuracy. However, current methods still have three basic limitations: (1) rigid feature extraction that cannot adaptively learn discriminative joint-level representations, (2) overreliance on fixed hyperparameters, and (3) inadequate ability to model the complex spatiotemporal variations in skeleton sequences. These deficiencies significantly limit their generalizability across diverse datasets. To overcome these challenges, we propose an innovative multimodal adaptive graph convolution network (MMA-GCN), which can effectively improve skeleton-based action recognition. First, we develop an adaptive parameterization mechanism that dynamically adjusts network parameters to increase generalization robustness. Second, our model automatically learns deformable temporal sampling patterns while adaptively optimizing spatial correlation weights, enabling context-sensitive perception of discriminative features. Third, we propose a principled multimodal fusion strategy that effectively integrates four complementary representations: joint positions, bone vectors, motion velocities, and joint-bone correlations. This comprehensive representation captures richer action semantics than conventional single-modal approaches do. Through extensive experiments on two large-scale benchmarks (NTURGBD60 and NTURGBD120), we demonstrate that our method achieves new state-of-the-art performance. More importantly, compared with existing approaches, the proposed techniques substantially improve cross-dataset generalization, validating the effectiveness of our architectural innovations. The excellent results stem from the unique ability of our method to adaptively learn both spatial and temporal features while exploiting multimodal skeletal information. [ABSTRACT FROM AUTHOR] |
| Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194196022 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Multimodal Adaptive Graph Convolution: Toward Robust Skeleton-based Action Recognition. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Guo%2C+Lijuan%22">Guo, Lijuan</searchLink><relatesTo>1</relatesTo><i> guolj.sy@gx.csg.cn</i><br /><searchLink fieldCode="AR" term="%22Xie%2C+Guoshan%22">Xie, Guoshan</searchLink><relatesTo>2</relatesTo><i> xiegs.sy@gx.csg.cn</i><br /><searchLink fieldCode="AR" term="%22Mo%2C+Jing%22">Mo, Jing</searchLink><relatesTo>3</relatesTo><i> moj@gx.csg.cn</i><br /><searchLink fieldCode="AR" term="%22Shi%2C+Fengwei%22">Shi, Fengwei</searchLink><relatesTo>4</relatesTo><i> shifw.lbg@gx.csg.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Le%22">Wang, Le</searchLink><relatesTo>2</relatesTo><i> wangl.sy@gx.csg.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IAENG+International+Journal+of+Computer+Science%22">IAENG International Journal of Computer Science</searchLink>. Jun2026, Vol. 53 Issue 6, p2400-2409. 10p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Human+activity+recognition%22">Human activity recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+neural+networks%22">Graph neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Learning%22">Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Multisensor+data+fusion%22">Multisensor data fusion</searchLink><br /><searchLink fieldCode="DE" term="%22Spatiotemporal+processes%22">Spatiotemporal processes</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Significant progress has been made in human action recognition through the use of various modalities, such as RGB videos, depth maps, skeleton data, and infrared imaging. Skeleton-based methods that use graph convolutional networks (GCNs) are particularly impressive. Recent methods employ deformable graph convolution operations to automatically identify semantically important body joints, increasing computational efficiency while maintaining high recognition accuracy. However, current methods still have three basic limitations: (1) rigid feature extraction that cannot adaptively learn discriminative joint-level representations, (2) overreliance on fixed hyperparameters, and (3) inadequate ability to model the complex spatiotemporal variations in skeleton sequences. These deficiencies significantly limit their generalizability across diverse datasets. To overcome these challenges, we propose an innovative multimodal adaptive graph convolution network (MMA-GCN), which can effectively improve skeleton-based action recognition. First, we develop an adaptive parameterization mechanism that dynamically adjusts network parameters to increase generalization robustness. Second, our model automatically learns deformable temporal sampling patterns while adaptively optimizing spatial correlation weights, enabling context-sensitive perception of discriminative features. Third, we propose a principled multimodal fusion strategy that effectively integrates four complementary representations: joint positions, bone vectors, motion velocities, and joint-bone correlations. This comprehensive representation captures richer action semantics than conventional single-modal approaches do. Through extensive experiments on two large-scale benchmarks (NTURGBD60 and NTURGBD120), we demonstrate that our method achieves new state-of-the-art performance. More importantly, compared with existing approaches, the proposed techniques substantially improve cross-dataset generalization, validating the effectiveness of our architectural innovations. The excellent results stem from the unique ability of our method to adaptively learn both spatial and temporal features while exploiting multimodal skeletal information. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194196022 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 10 StartPage: 2400 Subjects: – SubjectFull: Human activity recognition Type: general – SubjectFull: Graph neural networks Type: general – SubjectFull: Learning Type: general – SubjectFull: Multisensor data fusion Type: general – SubjectFull: Spatiotemporal processes Type: general Titles: – TitleFull: Multimodal Adaptive Graph Convolution: Toward Robust Skeleton-based Action Recognition. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Guo, Lijuan – PersonEntity: Name: NameFull: Xie, Guoshan – PersonEntity: Name: NameFull: Mo, Jing – PersonEntity: Name: NameFull: Shi, Fengwei – PersonEntity: Name: NameFull: Wang, Le IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 1819656X Numbering: – Type: volume Value: 53 – Type: issue Value: 6 Titles: – TitleFull: IAENG International Journal of Computer Science Type: main |
| ResultId | 1 |
