AGMS-GCN: Attention-guided multi-scale graph convolutional networks for skeleton-based action recognition

Basit Öğe Kaydı
dc.authorid0000-0003-4092-3785
dc.contributor.authorKilic, Ugur
dc.contributor.authorKaradag, Ozge Oztimur
dc.contributor.authorOzyer, Gulsah Tumuklu
dc.date.accessioned2026-01-24T12:31:16Z
dc.date.available2026-01-24T12:31:16Z
dc.date.issued2025
dc.departmentAlanya Alaaddin Keykubat Üniversitesi
dc.description.abstractGraph Convolutional Networks have the capability to model non-Euclidean data with high effectiveness. Due to this capability, they perform well on standard benchmarks for skeleton-based action recognition (SBAR). Specifically, spatial-temporal graph convolutional networks (ST-GCNs) function effectively in learning spatial- temporal relationships on skeletal graph patterns. In ST-GCN models, a fixed skeletal graph pattern is used across all layers. ST-GCN models obtain spatial-temporal features by performing standard convolution on this fixed graph topology within a local neighborhood limited by the size of the convolution kernel. This convolution kernel dimension can only model dependencies between joints at short distances and shortrange temporal dependencies. However, it fails to model long-range temporal information and long-distance joint dependencies. Effectively capturing these dependencies is key to improving the performance of ST-GCN models. In this study, we propose AGMS-GCN, an attention-guided multi-scale graph convolutional network structure that dynamically determines the weights of the dependencies between joints. In the proposed AGMSGCN architecture, new adjacency matrices that represent action-specific joint relationships are generated by obtaining spatial-temporal dependencies with the attention mechanism on the feature maps extracted using spatial-temporal graph convolutions. This enables the extraction of features that take into account both the shortand long-range spatial-temporal relationship between action-specific joints. This data-driven graph construction method provides amore robust graph representation for capturing subtle differences between different actions. In addition, actions occur through the coordinated movement of multiple body joints. However, most existing SBAR approaches overlook this coordination, considering the skeletal graph from a single-scale perspective. Consequently, these methods miss high-level contextual features necessary for distinguishing actions. The AGMS-GCN architecture addresses this shortcoming with its multi-scale structure. Comprehensive experiments demonstrate that our proposed method attains state-of-the-art (SOTA) performance on the NTU RGB+D 60 and Northwestern-UCLA datasets. It also achieves SOTA competitive performance on the NTU RGB+D 120 dataset. The source code of the proposed AGMS-GCN model is available at: https: //github.com/ugrkilc/AGMS-GCN.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [124E309, 123E635]; Atatrk University under the BAP project [FDK-2023-11957]; TUBITAK; Atatuerk University
dc.description.sponsorshipThis study was supported by Scientific and Technological Research Council of Turkey (TUBITAK) under the Grant Numbers 124E309 and 123E635, and by Atatuerk University under the BAP project with code FDK-2023-11957. The authors thank to TUBITAK and Atatuerk University for their support.
dc.identifier.doi10.1016/j.knosys.2025.113045
dc.identifier.issn0950-7051
dc.identifier.issn1872-7409
dc.identifier.scopus2-s2.0-85216491021
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.knosys.2025.113045
dc.identifier.urihttps://hdl.handle.net/20.500.12868/5757
dc.identifier.volume311
dc.identifier.wosWOS:001434257800001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofKnowledge-Based Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WoS_20260121
dc.subjectAction recognition
dc.subjectSkeletal data
dc.subjectGraph convolutional networks
dc.subjectAttention mechanism
dc.subjectMulti-scale
dc.titleAGMS-GCN: Attention-guided multi-scale graph convolutional networks for skeleton-based action recognition
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu