Aug 2026
Self-supervised skeleton action recognition based on graph prototype learning
This work presents a novel self-supervised architecture centered on graph prototype learning that sets a new state-of-the-art on the ARMM dataset with an accuracy of 95.70%, substantiating the efficacy and transferability of prototype-guided self-supervised learning for skeleton-based action representation.
Zhijie Xu, Hongwei Chen, Xia Li
· International Journal of Mac... · 0 citations