I am currently a junior research assistant at the Multimedia Laboratory, CUHK, supervised by Prof. Xiangyu Yue. I was honored to be supervised and collaborated with Prof. Weicheng Xie, Prof. Siyang Song and Prof. Linlin Shen during my undergraduate studies. I also work with Prof. Muhammad Haris Khan on domain generalization-related topics. My research interests include computer vision, model robustness and synthetic data.

I’m actively looking for collaboration and PhD opportunity, please feel free to drop me an email if interested.

πŸ”₯ News

  • 2025.05: Β πŸŽ‰πŸŽ‰ One paper accepted by ICML 2025.
  • 2024.12: Β πŸŽ‰πŸŽ‰ Three papers accepted by AAAI 2025 (2 Oral).
  • 2024.10: Β πŸŽ‰πŸŽ‰ Two papers accepted by WACV 2025.
  • 2024.10: Β πŸŽ‰πŸŽ‰ We released SynFER on ArXiv.
  • 2024.09: Β πŸŽ‰πŸŽ‰ One paper accepted by NeurIPS 2024.
  • 2024.07: Β πŸŽ‰πŸŽ‰ One paper accepted by ECCV 2024.
  • 2023.07: Β πŸŽ‰πŸŽ‰ One paper accepted by ICCV 2023.

πŸ“ Publications

* indicates equal contribution.

ArXiv
arxiv_synfer

SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

Xilin He*, Cheng Luo*, Xiaole Xian, Bing Li, Siyang Song, Muhammad Haris Khan, Weicheng Xie, Linlin Shen, Zongyuan Ge

NeurIPS 2024
neurips_24

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

Xilin He, Jingyu Hu, Qinliang Lin, Cheng Luo, Weicheng Xie, Siyang Song, Muhammad Haris Khan, Linlin Shen

ECCV 2024
eccv_24

MTaDCS: Moving Trace and Feature Density-based Confidence Sample Selection under Label Noise

Qingzheng Huang*, Xilin He*, Xiaole Xian, Qinliang Lin, Weicheng Xie, Siyang Song, Linlin Shen, Zitong Yu

ICCV 2023
eccv_24

Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition

Xilin He, Qinliang Lin, Cheng Luo, Weicheng Xie, Siyang Song, Feng Liu, Linlin Shen

πŸ—ΊοΈ Visitor Map