Biography

I am currently a PhD student in the School of Engineering at the HKUST, advised by Prof. DAN XU. My research interest is about talking head generation and image generation. I received my master's Degree in 2021 at Sun Yat-sen University, where I was advised by Prof. Wei-Shi Zheng and researched in video understanding. Before SYSU, I have completed my B.E. supervised by Prof. Sheng Bi at the South China University of Technology where I was working on the SLAM of mobile robot.

I am currently seeking a postdoctoral position starting in the second half of 2025. If you have any opportunities that align with my expertise, please feel free to reach out to me via email. :)

Education

  • 08/2021 ~ Present: PhD Student, Department of Computer Science & Engineering, Hong Kong University of Science and Technology
  • 09/2018 ~ 07/2021: Computer Science and Technology, Sun Yat-sen University
  • 09/2014 ~ 07/2018: Computer Science and Technology, South China University of Technology

News

  • (Sept 2023): Our DaGAN project is accept at TPAMI.
  • (July 2023): One paper was accepted by ICCV 2023.
  • (Sept. 2022): One paper was accepted by TMM 2022.
  • (Apr. 2022): The project page and code of our CVPR2022 paper, DaGAN, can be found in PROJECT and CODE
  • (Mar. 2022): One paper accepted to CVPR 2022. Stay tuned for more details.
  • (Jul. 2021): One paper on weakly-supervised video action localization has been accepted by ACM MM 2021.
  • (Apr. 2021): The project page of our paper "MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection" has been presented at HERE. And the paper has been released in ARXIV.
  • (Mar. 2021): One of our paper "MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection" has been accepted by CVPR 2021. Paper and Code will come soon!
  • (Nov. 2020): I won the Chinese National Scholarship in my third year of master program!!
  • (Aug. 2020): Code for MINI-NET has been released in GITHUB
  • (Aug. 2020): The paper accpted by ACM MM2020 has been released in ARXIV, while the code also has been released in github.
  • (Jul. 2020): One of our paper "Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos" has been accepted by ACM MM 2020. Paper and Code will come soon!
    • ▶ Click for More News
  • (Jul. 2020): One paper to appear at ECCV 2020 named "MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection". We will release our paper and code online as soon as possible.
  • (Jun. 2020): The both EMS dataset and ENCAA dataset evaluated in our work at CVPR2020 have been released. The EMS dataset and ENCAA dataset are now online
  • (Jun. 2020): Attending the AIDU activity hold by BAIDU.
  • (May 2020): Attending the CSIG-Guangdong Province CVPR2020 Online Academic Report.
  • (Feb. 2020): One paper to appear at CVPR 2020. The paper and poster are now online.
  • (May 2019): Attending the CVPR2019 Academic Report held by Tencent PCG.
  • (Apr. 2019): One paper to appear at CVPR 2019. The paper is now online.

Preprints * Equal Contribution, # corresponding author.

Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning.
Jia-Run Du, Jia-Chang Feng, Kun-Yu Lin, Fa-Ting Hong,Xiao-Ming Wu, Zhongang Qi, Ying Shan, Wei-Shi Zheng
 arXiv, 2022.
[arXiv]
Learning Online Scale Transformation for Talking Head Video Generation.
Fa-Ting Hong,Dan Xu
 Under Review.
DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis.
Fa-Ting Hong, ..., Dan Xu
 Under Review.

Selected Publications * Equal Contribution, # corresponding author.

DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation.
Fa-Ting Hong, Li Shen, Dan Xu
 TPAMI
[arXiv]
Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation.
Fa-Ting Hong, Dan Xu
 ICCV 2023.
[Project] [arXiv] [Code]
GitHub stars GitHub forks GitHub issues
Learning Relation Models to Detect Important People in Still Images.
Yu-Kun Qiu, Fa-Ting Hong, Wei-Hong Li, and Wei-Shi Zheng
 TMM 2022.
[IEEE Xplore]
Depth-Aware Generative Adversarial Network for Talking Head Video Generation.
Fa-Ting Hong, Longhao Zhang, Li Shen, Dan Xu#.
 International Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[Project] [arXiv] [Code]
GitHub stars GitHub forks GitHub issues
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization.
Fa-Ting Hong*, Jia-Chang Feng*, Dan Xu, Ying Shan and Wei-Shi Zheng#.
 ACM International Conference on Multimedia (ACM MM), 2021.
[Project] [arXiv] [Code]
GitHub stars GitHub forks GitHub issues
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection.
Jia-Chang Feng, Fa-Ting Hong and Wei-Shi Zheng#.
International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[arXiv] [Code] [Project]
GitHub stars GitHub forks GitHub issues
Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos.
Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng#, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, and Jian-Huang Lai.
ACM International Conference on Multimedia (ACM MM), 2020.
[arXiv] [Code]
GitHub stars GitHub forks GitHub issues
MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection.
Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, Wei-Shi Zheng#.
European Conference on Computer Vision (ECCV), 2020.
[arXiv] [ECVA] [Code] [Supplementary Material] [Project]
GitHub stars GitHub forks GitHub issues
Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection.
Fa-Ting Hong*, Wei-Hong Li*, Wei-Shi Zheng#.
International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[arXiv] [CVF] [Code]
GitHub stars GitHub forks GitHub issues
Learning to Learn Relation for Important People Detection in Still Images.
Wei-Hong Li*, Fa-Ting Hong*, Wei-Shi Zheng#.
International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[arXiv] [CVF] [Supplementary Material] [Code]
GitHub stars GitHub forks GitHub issues
▶ Click for More Papers

Optimization of Robot Path Planning Parameters Based on Genetic Algorithm.
Liang, Y., Hong, F., Lin, Q., Bi, S.#, & Feng, L..
IEEE International Conference on Real-time Computing and Robotics, 2017.
[paper][Project]

A Global Localization System for Mobile Robot Using LIDAR Sensor.
Liqian Feng; Sheng Bi#; Min Dong; Fating Hong; Yuhong Liang; Qinjie Lin; Yunda Liu.
IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2017.
[paper]

Indoor mapping using gmapping on embedded system.
Qinjie Lin; Zhaowu Ke; Sheng Bi#; Sirui Xu; Yuhong Liang; Fating Hong; Liqian Feng.
IEEE International Conference on Robotics and Biomimetics (ROBIO), 2017.
[paper]

Experiences

  • Applied Research Center (ARC), PCG, Tencent

    Research Intern, supervised by Dr. YING SHAN
    Research Topic: Weakly supervised temporal action localization
    Jun. 2020 - May 2021

Activities

Journal Reviews

  • TIP
  • Neurocomputing
  • Transactions on Multimedia, TMM
  • Transactions on Pattern Analysis and Machine Intelligence, TPAMI

Conference Reviews

  • CVPR, ECCV, ICCV, AAAI, ACM MM

Teaching

Teaching Assistant at HKUST

  • Computer Vision (COMP5421) 2022 Spring

Projects

  • National Innovation and Entrepreneurship Project

    Title: Autonomous Navigation of Mobile Robot Based on Laser

    Role: Leader

    Project Evaluation: Excellent

    Supervisor: Prof. Sheng Bi

Honors & Awards

  • Chinese National Scholarship, by Minister of Education of China, 2020
  • Chinese National Scholarship, by Minister of Education of China, 2017

Misc