Skeleton-Based Multi-Stream Adaptive Graph Convolutional Network for Indoor Scene Action Recognition

Basit Öğe Kaydı
dc.contributor.authorLi, J.
dc.contributor.authorChen, L.
dc.contributor.authorLi, M.
dc.contributor.authorWu, M.
dc.contributor.authorPedrycz, W.
dc.contributor.authorHirota, K.
dc.date.accessioned2024-05-19T14:33:15Z
dc.date.available2024-05-19T14:33:15Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description2023 China Automation Congress, CAC 2023 -- 17 November 2023 through 19 November 2023 -- -- 198194en_US
dc.description.abstractWith the rapid advances in computer vision, human action recognition has gradually received attention, but the current methods still exhibit some problems in indoor environments. The human skeleton, as the framework of human motion, contains high-quality actional feature information, and the skeleton-based action recognition method effectively avoid the interference of interior background noise and has advantages in indoor action recognition. The outstanding effect of graph convolutional networks on graph structure data processing has led to its rapid development and wide application in skeleton-based action recognition. Second-order skeletal information also contains a large number of actional features but is not effectively utilized. The artificial predefined topology of the human skeleton map has limitations, and cannot reflect the interaction between limbs. To solve the above problems, this article designs an adaptive weighted multi-stream graph convolutional network (AM-GCN) based on skeletal information, using an attention mechanism to enhance the network's ability to extract actional features, and an adaptive layer to make the construction graph more flexible, incorporating second-order skeletal features through a dual-stream architecture. In this article, the NTU-RGB+D dataset has been used for the experiments, the results show that the method in this article has good results. © 2023 IEEE.en_US
dc.identifier.doi10.1109/CAC59555.2023.10451388
dc.identifier.endpage6108en_US
dc.identifier.isbn9798350303759
dc.identifier.scopus2-s2.0-85189327444en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage6103en_US
dc.identifier.urihttps://doi.org/10.1109/CAC59555.2023.10451388
dc.identifier.urihttps://hdl.handle.net/20.500.12713/4161
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 2023 China Automation Congress, CAC 2023en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectAction Recognitionen_US
dc.subjectAdaptive Layeren_US
dc.subjectAttention Mechanismen_US
dc.subjectSecond-Order Skeleton İnformationen_US
dc.subjectSkeleton-Baseden_US
dc.titleSkeleton-Based Multi-Stream Adaptive Graph Convolutional Network for Indoor Scene Action Recognitionen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu