Hehe Fan

Research Fellow
School of Computing, National University of Singapore

Email: hehe.fannus.edu.sg

Address: i4 (Innovation 4.0) Building #04-03, 3 Research Link,
National University of Singapore, Singapore 117602

Google Scholar / GitHub

About Me

I’m currently a research fellow with Prof. Mohan S. Kankanhalli at National University of Singapore. I received my Ph.D. degree at University of Technology Sydney in 2020, advised by Prof. Yi Yang. I was a visiting scholar at Carnegie Mellon University in 2016, working with Prof. Alexander G. Hauptmann. My research focuses on deep learning, computer vision and multimedia, with an emphasis on video (including point cloud video) analysis, unsupervised learning and vision-language applications.

Selected Publications

  1. Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition
    Hehe Fan, Xin Yu, Yi Yang and Mohan Kankanhalli
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2021 [PDF] [BibTex]
  2. PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
    Hehe Fan, Xin Yu, Yuhang Ding, Yi Yang and Mohan Kankanhalli
    The Ninth International Conference on Learning Representations (ICLR) 2021 [PDF] [BibTex]
  3. Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
    Hehe Fan, Yi Yang and Mohan Kankanhalli
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 (Oral) [PDF] [BibTex]
  4. Recurrent Attention Network with Reinforced Generator for Visual Dialog
    Hehe Fan, Linchao Zhu, Yi Yang and Fei Wu
    ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMM) 2020 [PDF] [BibTex]
  5. Unsupervised Person Re-identification: Clustering and Fine-tuning
    Hehe Fan, Liang Zheng, Chenggang Yan and Yi Yang
    ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMM) 2018 [PDF] [BibTex]
  6. Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification
    Hehe Fan, Zhongwen Xu, Linchao Zhu, Chenggang Yan, Jianjun Ge and Yi Yang
    International Joint Conference on Artificial Intelligence (IJCAI) 2018 [PDF] [BibTex]
  7. Complex Event Detection by Identifying Reliable Shots from Untrimmed Videos
    Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu and Alexander G. Hauptmann
    IEEE/CVF International Conference on Computer Vision (ICCV) 2017 [PDF] [BibTex]

Professional Service