Zechen Bai 白泽琛

Applied Scientist

AWS AI Labs, Shanghai

              


Biography

I'm currently a full-time Applied Scientist at AWS AI Labs, working with Tianjun Xiao, Tong He, Francesco Locatello, and Prof. Zheng Zhang. I also work closely with Prof. Thomas Brox, Prof. Yanwei Fu, and Prof. Mike Shou. Before joining Amazon, I received my M.S degree in Computer Science from Chinese Academy of Sciences, advised by Prof. Hui Chen, and B.S degree in Computer Science from University of Science and Technology Beijing, under the supervision of Prof. Xu-Cheng Yin and Prof. Weiming Dong. I was a research intern at Bytedance AI-Lab and Baidu VIS, respectively. Also, I was fortunate to work with Prof. Nadia Magnenat Thalmann (Nanyang Technological University), Prof. Noa Garcia (Osaka University) and Prof. Yuta Nakashima (Osaka University).

My research interests include computer vision, deep learning, and virtual reality.

News

Publications

                        
A Simple Approach to Animating Virtual Characters by Facial Expressions Reenactment.
Zechen Bai, Naiming Yao, Lu Liu, Hui Chen, Hongan Wang.
IEEE Virtual Reality Conference (VR), 2023.

[paper]

Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation.
Zechen Bai, Yuta Nakashima, and Noa Garcia.
IEEE International Conference on Computer Vision (ICCV), 2021.

[paper][code][project]

Robust Vehicle Re-identification via Rigid Structure Prior.
Minyue Jiang, Xuanmeng Zhang, Yue Yu, Zechen Bai, Zhedong Zheng, Zhigang Wang, Jian Wang, Xiao Tan, Hao Sun, Errui Ding, Yi Yang.
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2021.
(Ranked 2nd place in CVPR 2021 AI City Challenge Vehicle Re-id Track)

[paper]

Enhancing Emotional Experience by Building Emotional Virtual Characters in VR Volleyball Games.
Zechen Bai, Naiming Yao, Nidhi Mishra, Hui Chen, Hongan Wang, Nadia Magnenat Thalmann.
International Conference on Computer Animation and Social Agents (CASA), 2021.

[paper]

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification.
Zechen Bai, Zhigang Wang, Jian Wang, Di Hu, Errui Ding.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. (Oral)

[paper][code]

Play with Emotional Characters: Improving User Emotional Experience by A Data-driven Approach in VR Volleyball Games.
Zechen Bai, Naiming Yao, Nidhi Mishra, Hui Chen, Hongan Wang, Nadia Magnenat Thalmann.
IEEE Virtual Reality Conference (VR), 2021.
(Best Poster Award!)

[paper]

Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification.
Zhedong Zheng, Minyue Jiang, Zhigang Wang, Jian Wang, Zechen Bai, Xuanmeng Zhang, Xin Yu, Yi Yang, Shilei Wen, Errui Ding.
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2020.
(Ranked 1st place in CVPR 2020 AI City Challenge Vehicle Re-id Track)

[paper][code]

Show, Recall, and Tell: Image Captioning with Recall Mechanism.
Li Wang, Zechen Bai, Yonghua Zhang, Hongtao Lu.
AAAI Conference on Artificial Intelligence (AAAI), 2020.

[paper]

Research Experience

  • Research Intern
    April 2021 - September 2021
    Intelligent Creation Team (AI-Lab CV), Bytedance, Beijing, China
    Advisor: Panpan Xu and Qian He

  • Visiting Student (remote)
    September 2020 - March 2021
    ISLab, Osaka University, Osaka, Japan
    Advisor: Prof. Noa Garcia and Prof. Yuta Nakashima

  • Research Intern
    February 2020 - September 2020
    Department of Computer Vision Technology (VIS), Baidu, Beijing, China
    Advisor: Zhigang Wang and Jian Wang

  • Visiting Student
    November 2019 - February 2020
    Institute for Media Innovation, Nanyang Technological University, Singapore
    Advisor: Prof. Nadia Magnenat Thalmann

  • Research Intern
    February 2019 - August 2019
    Visual Search Team (AI-Lab VS), Bytedance, Beijing, China
    Advisor: Yonghua Zhang

  • Selected Awards

    China National Scholarship, 2021
    Best Poster Award at IEEE-VR 2021
    Champion of AI City Challenge Vehicle Re-id Track at CVPR 2020
    Beijing Distinguished Graduate Award, 2019


    © Zechen Bai | Last updated: Mar. 2023