Experimental Investigation of Spatial-temporal Graph Convolutional Networks and Attentional Mechanism in Skeleton-Based Action Recognition

Basit Öğe Kaydı
dc.contributor.authorKiliç, Uğur
dc.contributor.authorÖztimur Karada?, Özge
dc.contributor.authorTumuklu Ozyer, Gülşah
dc.date.accessioned2026-01-24T12:20:41Z
dc.date.available2026-01-24T12:20:41Z
dc.date.issued2023
dc.departmentAlanya Alaaddin Keykubat Üniversitesi
dc.description2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023 -- 2023-10-11 through 2023-10-13 -- Sivas -- 194153
dc.description.abstractSkeleton-based action recognition has attracted much attention in recent years as skeleton data is robust to body scales, dynamic camera images, illumination changes and complex background situations. The natural structure of the human skeleton is well suited to structuring it as a graph. Therefore, many researchers have been working on graph convolution networks for skeleton-based action recognition task. In particular, spatial-temporal graph convolutional networks (STGCN) have proven effective in learning both spatial and temporal dependencies on skeleton graph data. Although it has proven to perform well on skeleton data, the topology of the graph representing the human body in ST-GCN models is manually adjusted and fixed on all layers. This limits the ability to obtain more complex and richer representations. In contrast, spatial-temporal attention graph convolutional networks (STA-GCN) operates by taking into account the critical connections between joints and the importance of joints in each frame, according to actions. In this way, it can identify important joint relations specific to actions. In this study, four network models with different layer depths were designed, based on the ST-GCN and STA-GCN architectures. Subsequently, these models were trained with various numbers of epochs, and the effects of layer depth and the number of epochs on the performance of skeleton-based action recognition were experimentally investigated. According to the experimental results, the proposed 3xSTA-GCN block structured model achieved an accuracy rate of 86.71% on the CS test set and 92.76% on the CV test set. © 2023 IEEE.
dc.identifier.doi10.1109/ASYU58738.2023.10296711
dc.identifier.isbn9798350306590
dc.identifier.scopus2-s2.0-85178294964
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/ASYU58738.2023.10296711
dc.identifier.urihttps://hdl.handle.net/20.500.12868/4496
dc.indekslendigikaynakScopus
dc.language.isotr
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20260121
dc.subject3D skeleton
dc.subjectAction recognition
dc.subjectAttention edge
dc.subjectAttention mechanism
dc.subjectAttention node
dc.subjectGraph Convolutional Networks
dc.titleExperimental Investigation of Spatial-temporal Graph Convolutional Networks and Attentional Mechanism in Skeleton-Based Action Recognition
dc.title.alternativeIskelet Tabanli Eylem Tanimada Uzaysal-Zamansal izge Evrişimsel Aglar ve Dikkat Mekanizmasinin Deneysel İncelenmesi
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu