Qianyi Wu ("吴潜溢" in Chinese)
Researcher at Sensetime
Email : wqy9619 [at] gmail.com     Github     Resume     Scholar    

About Me

Qianyi Wu is currently a researcher at SenseTime, working with Dr. Wayne Wu. Qianyi received B.S degree from Special Class for the Gifted Youth at University of Science and Technology of China (USTC) in 2016. And he received M.Sc degree from Graphics and Geometric Computing Laboratory of School of Mathematical Sciences at USTC in 2019, under the supervision of Prof. Juyong Zhang. He spent one year as research intern at Nanyang Technological University, mentored by Prof. Jianfei Cai and Prof. Jianmin Zheng.
He will join Monash University as a PhD student in the future.

News

  • 2020.10: One paper related to face swaping was accepted to NeurIPS 2020. Welcome to star our project page.
  • 2020.07: One paper about emotional talking face dataset was accepted to ECCV 2020 finally.
  • 2019.07: Join SenseTime (Beijing) as a full-time researcher.
  • 2019.02: One paper was accepted by CVPR 2019.
  • 2018.01: One paper was accepted by CVPR 2018 as spotlight .
  • 2017.08: Research Intern at Nanyang Techonology University, Singapore.

Publications

AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection.
Hao Zhu*, Chaoyou Fu*, Qianyi Wu, Wayne Wu, Chen Qian, Ran He
Conference on Neural Information Processing Systems (NeurIPS), 2020
[PDF] [Project Page]
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking Face Generation.
Kaisiyuan Wang, Qianyi Wu, Linsen Song, Zhuoqian Yang, Wayne Wu, Chen Qian, Ran He, Yu Qiao, Chen Change Loy
European Conference on Computer Vision(ECCV), 2020
[PDF] [Project Page]
Disentangled Representation Learning for 3D Face Shape
Zi-Hang Jiang, Qianyi Wu, Keyu Chen, Juyong Zhang
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2019
[PDF] [Code]
Alive Caricature from 2D to 3D.
Qianyi Wu, Juyong Zhang, Yu-Kun Lai, Jianmin Zheng, Jianfei Cai.
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018 (Spotlight)
[PDF] [Data]

Industrial experience

SenseAR DigitalHuman - Audio-Driven Virtual Human
SenseAR Digital Human is a human-like intelligent multi-modal interactive system. As a primary member, I and my colleagues research and develop several key algorithms for audio-driven virtual human.
[Product] [Press(China Daily)]

Awards

  • National Scholarship, USTC, 2018.