Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition

Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition

Abstract For the purpose of achieving accurate skeleton-based action recognition, the majority of prior approaches have adopted a serial strategy that combines Graph Convolutional Networks (GCNs) with attention-based methods. However, this approach frequently treats the human skeleton as an isolated...

Cijeli opis

Bibliografski detalji
Glavni autori: Dong Chen, Mingdong Chen, Peisong Wu, Mengtao Wu, Tao Zhang, Chuanqi Li
Format: Članak
Jezik:English
Izdano: Nature Portfolio 2025-02-01
Serija:Scientific Reports
Teme:
Action recognition
Graph convolutional networks
Transformer
Online pristup:https://doi.org/10.1038/s41598-025-87752-8

Internet

https://doi.org/10.1038/s41598-025-87752-8

Slični predmeti