EUVIMEDDescoperă EUVIMED
Open access · CC BY 4.0

SGT‐Net: A Synergistic Graph‐Transformer Network for Skeleton‐Based Gesture Recognition

Jiahao Zhao, Haibo Hong, Qingkun Chen

IET Image Processing · 2026-01 · 20 (1)

DOI: 10.1049/ipr2.70426 ↗

At a glance

Journal article in IET Image Processing, published online on 2026-07-07. Written by Jiahao Zhao and 2 co-authors. 52 references. The full text is freely available (open access, CC BY 4.0). Funded by: Natural Science Foundation of Fujian Province.

RezumatDate bibliograficeCiteRelated studies

Abstract (original language)

Skeleton‐based hand gesture recognition is critical for human–computer interaction and virtual reality. However, two fundamental challenges persist in existing methods. Regarding spatial modelling, the inability to capture global dependencies among distant joints remains a bottleneck. Regarding temporal modelling, the prevalent coupled scheme tends to obscure fine‐grained spatial structures during temporal aggregation, thereby limiting the learning of accurate gesture dynamics. To address these issues, this paper proposes the synergistic graph‐transformer network (SGT‐Net). First, a dynamic dual‐stream attention (DDA) module integrates a graph convolutional network (GCN) stream and a Transformer stream for synergistic spatial modelling, where a dynamic fusion gate (DFG) dynamically orchestrates the two streams via context‐aware fusion weights coordinating local and global cues complementarily. Second, a hierarchical cascaded architecture based on spatiotemporal units (STUs) progressively refines spatial features through the DDA module prior to temporal aggregation by the MS‐TCN module. By stacking STUs and progressively expanding channels, the network achieves hierarchical abstraction to higher‐level semantic features for better spatiotemporal modelling. Experiments on SHREC'17 Track, NTU‐RGB+D, and NW‐UCLA datasets demonstrate competitive accuracy, particularly in multi‐view settings and small‐sample datasets.

Funding

  • Natural Science Foundation of Fujian Province

Cite

APA

Zhao, J., Hong, H., & Chen, Q. (2026). SGT‐Net: A Synergistic Graph‐Transformer Network for Skeleton‐Based Gesture Recognition. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70426

Vancouver

Zhao J, Hong H, Chen Q. SGT‐Net: A Synergistic Graph‐Transformer Network for Skeleton‐Based Gesture Recognition. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70426

BibTeX
@article{Zhao2026,
  author = {Zhao, Jiahao and Hong, Haibo and Chen, Qingkun},
  title = {SGT‐Net: A Synergistic Graph‐Transformer Network for Skeleton‐Based Gesture Recognition},
  journal = {IET Image Processing},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/ipr2.70426}
}
Start for free →