- Adversarial Attention Networks for Early Action Recognition.[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2025,9(2):1581-1594.
- Images, normal maps and point clouds fusion decoder for 6D pose estimation.[J].Information Fusion,2025,117
- Visual audio and textual triplet fusion network for multi-modal sentiment analysis.[J].Signal, Image and Video Processing,2024,18(12):9505-9513.
- Radical Constraint-Based Generative Adversarial Network for Handwritten Chinese Character Generation.Computing and Informatics,2024,43(2):482-504.
- A Transformer-based multi-modal fusion network for 6D pose estimation.Information Fusion,2024,105
- Spatial and temporal consistency learning for monocular 6D pose estimation.[J].Engineering Applications of Artificial Intelligence,2024,131
- Point-Based Learnable Query Generator for Human–Object Interaction Detection.[J].IEEE Transactions on Image Processing,2023,326469-6484.
- Short-term path signature for skeleton-based action recognition.Signal, Image and Video Processing,2023,17(5):1925–1934.
- Label-reconstruction-based pseudo-subscore learning for action quality assessment in sporting events.[J].Applied Intelligence,2023,53(9):10053–10067.
- Gaussian guided frame sequence encoder network for action quality assessment.[J].Complex & Intelligent Systems,2023,9(2):1963–1974.