Shuai Yuan @ Duke CS

Shuai Yuan Ph.D. student in Computer Science Duke University Office: North N209/LSRC D122 Address: 308 Research Drive, Durham, NC 27708

Biography

I am currently a fifth-year Ph.D. candidate in the Department of Computer Science at Duke University. My advisor is Professor Carlo Tomasi. Before coming to Duke, I received my B.Sc. degree in Computer Science and Technology in June 2018 from Nanjing University, where I did undergraduate research supervised by Professor Zhi-Hua Zhou at NJU LAMDA Group. For more information, please refer to my latest CV (2023-08-08 version).

Research Interests

I am interested in Computer Vision and Deep Learning. Currently, I mainly focus on the following topics:

• Video motion and tracking: optical flow, occlusion, and motion boundary estimation
• Video 3D scene geometry/SLAM: stereo matching, 3D rigid motion/pose
• Computer vision applications in autonomous driving and virtual/augmented reality

Work Experiences

• Research Intern, Facebook Reality Labs, Agios team. Redmond WA, USA. May 2020 - Aug 2020.
• Research Intern, Meta Reality Labs, Surreal team. Redmond WA, USA. May 2022 - Aug 2022.
• Research Intern, Meta Reality Labs, Core AI team. Seattle WA, USA. May 2023 - present.

Publications

• Xiang Wang, Shuai Yuan, Chenwei Wu, and Rong Ge. Guarantees for Tuning the Step Size using a Learning-to-Learn Approach. International Conference on Machine Learning (ICML), 2021.
  [code] | [appendix] | [poster] | [cite]
• Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, and Carlo Tomasi. Optical Flow Training under Limited Label Budget via Active Learning. European Conference on Computer Vision (ECCV), 2022.
  [code] | [appendix] | [poster] | [video] | [cite]
• Shuzhi Yu, Hannah Kim, Shuai Yuan, and Carlo Tomasi. Unsupervised Flow Refinement near Motion Boundaries. British Machine Vision Conference (BMVC), 2022.
  [code] | [appendix] | [poster] | [video] | [cite]
• Hannah Kim, Shuzhi Yu, Shuai Yuan, and Carlo Tomasi. Cross-Attention Transformer for Video Interpolation. Asian Conference on Computer Vision (ACCV) - Workshop on Vision Transformers: Theory and Application, 2022. Best Paper Award.
  [code] | [video] | [cite]
• Shuai Yuan, Shuzhi Yu, Hannah Kim, and Carlo Tomasi. SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving. Accepted by International Conference on Computer Vision (ICCV), 2023.
  [code] | [appendix] | [poster] | [video]
• Fanjie Kong, Shuai Yuan, Weituo Hao, and Ricardo Henao. Mitigating Test-Time Bias for Fair Image Retrieval. Accepted by Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.

Teaching Assistant

• CompSci 371D - Elements of Machine Learning, for undergraduate students, Fall 2019.
• CompSci 527 - Computer Vision, for graduate students, Spring 2019.