publications

2025

  1. srapf.jpg
    Robust Few-Shot Vision-Language Model Adaptation
    Hanxin Wang, Tian Liu, and Shu Kong*
    arXiv preprint arXiv:2506.04713, 2025
    PDF Code Website
  2. artf.jpg
    Adversarially Regularized Tri-Transformer Fusion for continual multimodal egocentric activity recognition
    Shuchang Zhou†, Hanxin Wang†, Qingbo Wu*, Fanman Meng, Linfeng Xu, Wei Zhang, and Hongliang Li
    Displays, 2025
    PDF Code

2023

  1. cut_fruits.gif
    Towards Continual Egocentric Activity Recognition: A Multi-Modal Egocentric Activity Dataset for Continual Learning
    Linfeng Xu*, Qingbo Wu, Lili Pan, Fanman Meng, Hongliang Li, Chiyuan He, Hanxin Wang, Shaoxu Cheng, and Yu Dai
    IEEE Transactions on Multimedia, 2023
    PDF Code Website