.png){kind=icon}
.png){kind=icon}
Return
Self-supervised skeleton action recognition based on graph prototype learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s13042-026-03263-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A critical bottleneck in self-supervised skeleton-based action recognition is the limited semantic distinctiveness of learned features. While conventional approaches predominantly utilize global data augmentation to facilitate contrastive learning across different views, they often fail to establish sharp semantic boundaries in the latent space. To mitigate this issue, we present a novel self-supervised architecture centered on graph prototype learning. Our framework integrates two pivotal modules: a Graph Prototype Learning Network, which employs learnable prototype vectors to reconstruct masked inputs thereby coercing the encoder to distill shared action semantics rather than fitting redundant noise and a Discriminative Class Contrastive Learning mechanism. The latter utilizes a memory bank to maintain dynamic class centroids, optimizing the alignment between samples and their respective prototypes via contrastive loss. Extensive evaluations on the NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD benchmarks reveal superior performance, particularly in terms of class discrimination and robustness to occlusion. Notably, our method 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.
Keywords:
Graph prototype learning
Discriminative class contrastive learning
Action recognition
Self-supervised learning
Journal
IF:
2.7
Papers:
3.1K
Citations:
5.6K