Hongwei Chen

TopoMoE: a topology-fidelity discrete mixture-of-experts framework for multi-modal knowledge graph completion

HPCLR: hierarchical part-aware contrastive learning for skeleton-based action recognition

HPCLR is a hierarchical part-aware contrastive learning framework for skeleton-based action recognition that leverages the consistency among joint, motion, and bone modalities to select more reliable positive samples, thereby contributing to more stable and informative multi-stream skeleton representations.

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.