Aug 2026
HPCLR: hierarchical part-aware contrastive learning for skeleton-based action recognition
Hongwei Chen, Min Wei, Yuanyuan Zhu et al.
· Journal of Supercomputing · 0 citations
We have 2 of 17 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
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.