Xiaowei Hu


Postdoctoral Fellow

Rm 1024, Ho Sin-Hang Engineering Building,
Department of Computer Science and Engineering,
The Chinese University of Hong Kong,
Shatin, Hong Kong.

Email: xwhu@cse.cuhk.edu.hk
[Curriculum Vitae]


Xiaowei Hu received his Ph.D. degree in Computer Science and Engineering from The Chinese University of Hong Kong (CUHK) in 2020, supervised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu. Before that, he received the B. Eng. degree in Computer Science and Technology from South China University of Technology (SCUT) in 2016, under the supervision of Prof. Xuemiao Xu. He is currently working as a postdoctoral fellow in the Chinese University of Hong Kong.

His research interests cover computer vision and deep learning, with special emphasis on low-level vision. Specifically, he is dedicated to designing learning frameworks by exploring the physical properties of various vision applications, including shadow image analysis, rain removal, and saliency detection. He is also interested in exploring robust learning algorithms with less human supervision for image recognition and restoration, which helps to improve scene understanding and enhance camera capability.


Publications [Google Scholar]

Summary: TPAMI, CVPR, ICCV & ECCV (7), IEEE Transactions (10).






Honors & Awards

Teaching and Supervision

  • Teaching Assistant at CUHK

    Advanced Topics in Computer Graphics and Visualization (Excellent Teaching Assistant), Spring 2018.
    Digital Logic and Systems, Fall 2016-2018.
    Linear Algebra and Vector Calculus for Engineers, Spring 2017.

  • Supervision

    Supervise junior Ph.D. (Tianyu Wang and Xiao Tang), M.Phil. (Zijun Deng, Lihao Liu, and Tianfei Yu), and undergraduate (Yitong Jiang) students to publish research papers on top-tier conferences and journals.

Professional Activities

  • Invited Talks

    • Peng Cheng Laboratory Overseas Young Scientist Forum, "Shadow Detection and Removal with Deep Learning", July 2020.

    • Talk at Shantou University, "Deep Learning for Shadow Detection and Removal", December 2019.

    • Hong Kong Computer Vision Workshop, "Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data" (Best Oral Presentation Award), October 2019.

    • AI Massive Open Online Course, "Direction-Aware Spatial Context Features for Shadow Detection", July 2018.
      [video link1] [video link2] [report]

  • Conference Reviews

    AAAI'21, ECCV'20, CVPR'20, AAAI'20, PG'20, MICCAI'20, ICCV'19 (Outstanding Reviewer), CVPR'19, MICCAI'19.

  • Journal Reviews

    IJCV, IEEE TIP, IEEE TMM, IEEE TITS, IEEE TMI, IEEE TCSVT, IEEE TVT, Neurocomputing, JMLC, CUIV, The Visual Computer, Computers & Graphics, IEEE CG&A, IEEE Access.

  • Reading List on Deep Learning [link]

  • My Undergraduate Experiences (Chinese)

    Report 1, Report 2, Report 3, Report 4, Report 5