Bo Dai 戴勃

PostDoc

Department of Information Engineering

The Chinese University of Hong Kong

Email: bdai [at] ie [dot] cuhk [dot] edu [dot] hk



CV

Bio

Dr. Bo Dai is a PostDoc in Multimedia Laboratory (MMLab) at CUHK, working with Prof.Dahua Lin. His research interests include computer vision and machine learning. Recently, he focuses on generative models, video analysis, and cross-modality analysis.

He received his Ph.D. (2014-2018) from Multimedia Laboratory (MMLab) at CUHK, advised by Prof.Dahua Lin. He obtained his B.Eng. (2010-2014) from ACM class of SJTU. Previously, he is fortunate to intern at Microsoft Research Asia. He also visited University of Toronto in 2017, working with Prof.Sanja Fidler.

News

  • [03/2020] Four papers (2 orals and 2 posters) are accepted to CVPR 2020. One of them got three strong accepts! Stay tuned!
  • [02/2020] Code of "Real or not Real, that is the Question" is available at here.
  • [12/2019] One paper is accepted to ICLR 2020 as a spotlight paper.
  • [07/2019] One paper is accepted to ICCV 2019.
  • [12/2018] One paper is accepted to ICLR 2019.
  • [09/2018] One paper is accepted to NIPS 2018.

Recent Work

In our recent work, Real or not Real, that is the Question, we propose a generalization to the standard GAN framework, where we treat the concept of realness as a random variable rather than a single scale. Consequently, the proposed framework, RealnessGAN, can not only train the generator with a loss of maximizing KL divergence, but also train a nonprogressive DCGAN to produce realistic images at 1024x1024 resolution.