SG-CLR: Semantic representation-guided contrastive learning for self-supervised skeleton-based action recognition

R Liu, Y Liu, M Wu, W **n, Q Miao, X Liu, L Li - Pattern Recognition, 2025 - Elsevier
Contrastive learning and multimodal representation learning have been widely applied to
skeleton-based action recognition. However, the majority of the research focuses on the …

Unsupervised Feature Enrichment and Fidelity Preservation Learning Framework for Skeleton-based Action Recognition

C Li, S Li, Y Gao, X Gao, P Chen, J Li… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Unsupervised skeleton-based action recognition has achieved remarkable progress
recently. Existing unsupervised learning methods suffer from severe overfitting problem, and …