Search papers, labs, and topics across Lattice.
The paper introduces M3GCLR, a novel contrastive learning framework for skeleton-based action recognition that addresses limitations in view discrepancy modeling, adversarial mechanisms, and augmentation control. It establishes an Infinite Skeleton-data Game (ISG) model with a proven equilibrium theorem to enable mini-max optimization based on multi-view mutual information. The framework uses multi-view rotation augmentation to generate normal-extreme data pairs and a dual-loss equilibrium optimizer to maximize action-relevant information while minimizing redundancy, achieving state-of-the-art results on multiple datasets.
State-of-the-art skeleton-based action recognition is now possible through a game-theoretic contrastive learning framework that maximizes action-relevant information while minimizing encoding redundancy.
In recent years, contrastive learning has drawn significant attention as an effective approach to reducing reliance on labeled data. However, existing methods for self-supervised skeleton-based action recognition still face three major limitations: insufficient modeling of view discrepancies, lack of effective adversarial mechanisms, and uncontrollable augmentation perturbations. To tackle these issues, we propose the Multi-view Mini-Max infinite skeleton-data Game Contrastive Learning for skeleton-based action Recognition (M3GCLR), a game-theoretic contrastive framework. First, we establish the Infinite Skeleton-data Game (ISG) model and the ISG equilibrium theorem, and further provide a rigorous proof, enabling mini-max optimization based on multi-view mutual information. Then, we generate normal-extreme data pairs through multi-view rotation augmentation and adopt temporally averaged input as a neutral anchor to achieve structural alignment, thereby explicitly characterizing perturbation strength. Next, leveraging the proposed equilibrium theorem, we construct a strongly adversarial mini-max skeleton-data game to encourage the model to mine richer action-discriminative information. Finally, we introduce the dual-loss equilibrium optimizer to optimize the game equilibrium, allowing the learning process to maximize action-relevant information while minimizing encoding redundancy, and we prove the equivalence between the proposed optimizer and the ISG model. Extensive Experiments show that M3GCLR achieves three-stream 82.1%, 85.8% accuracy on NTU RGB+D 60 (X-Sub, X-View) and 72.3%, 75.0% accuracy on NTU RGB+D 120 (X-Sub, X-Set). On PKU-MMD Part I and II, it attains 89.1%, 45.2% in three-stream respectively, all results matching or outperforming state-of-the-art performance. Ablation studies confirm the effectiveness of each component.
