 ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression RecognitionIEEE Transactions on Affective Computing (IEEE Trans. Affective Comput.), 2025 |
 Probabilistic Temporal Masked Attention for Cross-view Online Action DetectionIEEE transactions on multimedia (TMM), 2025 |
 Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature AlignmentIEEE Transactions on Image Processing (IEEE TIP), 2025 |
An Effective End-to-End Solution for Multimodal Action RecognitionInternational Conference on Pattern Recognition (ICPR), 2025 |
 DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection TransformerComputer Vision and Pattern Recognition (CVPR), 2025 |
