Xuanyi Dong
The ReLER(Recognition, LEarning, Reasoning) Lab
School of Computer Science, University of Technology Sydney (UTS)
Address: 15 Broadway, Ultimo NSW 2007, Australia
Email: xuanyi.dong [at] student.uts.edu.au

About Me ([CV] [GitHub] [Google Scholar] [Full Publications])

I am a third-year PhD candidate at the ReLER Lab, University of Technology Sydney (UTS). My academic advisor is Prof. Yi Yang. I received the B.Eng. degree from School of Computer Science and Technology, Beihang University in 2016.

My research is supported by Google PhD Fellowship (2019).


  • 2019.07: I was elected one of the 2019 Google PhD Fellows.
  • 2019: I have 1 NeurIPS, 1 CVPR, 3 ICCV, 1 AAAI, 1 TPAMI, 2 TIP, and 1 TCYB publications.
  • 2018: I have 3 CVPR, 1 IJCAI, and 1 ACM-MM publications.
  • 2017: I have 1 CVPR, 1 ICML, and 1 ACM-MM publications.
  • 2017.05: I interned at Facebook Reality Labs with Shoou-I and Yaser.

Selected Publications

Network Pruning via Transformable Architecture Search
Xuanyi Dong and Yi Yang
in NeurIPS, 2019.
[ Paper ] [ Code(coming soon) ] [ BibTex ]
Search for the network shape in a differentiable way.
One-Shot Neural Architecture Search via Self-Evaluated Template Network
Xuanyi Dong and Yi Yang
in ICCV, 2019.
[ Paper(coming soon) ] [ Code(coming soon) ] [ BibTex ]
Equip one-shot NAS with a sampler and train network weights using uniformly sampling.
Searching for A Robust Neural Architecture in Four GPU Hours
Xuanyi Dong and Yi Yang
in CVPR, 2019.
[ Paper ] [ Code ] [ BibTex ]
Propose a gradient-based searching algorithm using differentiable architecture sampling.
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
Xuanyi Dong, Shoou-I Yu, Xinshuo Weng, Shih-En Wei, Yi Yang, Yaser Sheikh
in CVPR, 2018.
[ Paper ] [ Code ] [ Video ] [ Blog ] [ BibTex ]
Utilize the fact that objects move smoothly in a video sequence (i.e. optical flow registration) to improve an existing facial landmark detector.


2019.03 - 2019.09: Baidu IDL, Neural architecture search, supervised by Prof. Yi Yang.
2017.05 - 2017.09: Facebook Reality Labs, Facial landmark detection, supervised by Dr. Shoou-I Yu and Prof. Yaser Sheikh.
2016.02 - 2016.10: Qihoo 360, CNN model acceleration, supervised by Prof. Shuicheng Yan.
2015.09 - 2016.01: SenseTime Group Limited, Object detection, supervised by Dr. Junjie Yan.

Academic Competitions

  • AutoCV2 2019: IMAGE + VIDEO Automated Computer Vision challenge, Rank 4st / 34 teams.
  • TRECVID 2016: Video Localization Task, Rank 1st.
  • ILSVRC 2015: Rank 3rd on Object Detection and 2nd on Object Localization.
  • ACM International Collegiate Programming Contest (ICPC) (2014~2015): 2 Gold and 1 Silver Medals.

Review Services

Journal Reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPMAI)
International Journal of Computer Vision (IJCV)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Pattern Recognition (PR) [Outstanding Reviewer]
Transactions on Computational Biology and Bioinformatics (TCBB)

Conference Reviewer
Computer Vision and Pattern Recognition (CVPR) 2019
International Conference on Computer Vision (ICCV) 2019
AAAI Conference on Artificial Intelligence (AAAI) 2020
ACM Multimedia (ACM MM), 2017, 2018