Zhaoyi Wan 万昭祎

Ph.D. Student and deep learning researcher

Shanghai, China

i[-at-]wanzy[-dot-]me

GitHub

I am a first-year Ph.D. student at the University of Rochester, advised by Prof. Jiebo Luo, and a quantitative trader at JQ Investigation. Previously I worked as an algorithm researcher at Megvii since late 2017 to December 2020, leading the R&D of scene text comprehension algorithms in Face++/FaceID. My research interest lies in computer vision and deep learning. I received my B.S. degree in Software Engineering of Beihang University, 2016. My detailed CV is available here.

I am serving as a reviewer of TPAMI, Pattern Recognition, CVPR, ICCV, and ACCV.

Research

Facial Attribute Transformers for Precise and Robust Makeup Transfer

Zhaoyi Wan, Haoran Chen, Jielei Zhang, Li Zhao, Jie An, Cong Yao, and Jiebo Luo. Under review.

Slender Object Detection: Diagnoses and Improvements

Zhaoyi Wan, Yimin Chen, Sutao Deng, Cong Yao, and Jiebo Luo. Under review.

On Vocabulary Reliance in Scene Text Recognition

Zhaoyi Wan, Jielei Zhang, Liang Zhang, Cong Yao, and Jiebo Luo. IEEE/CVF Conferences on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, June 2020.

Paper

Real-time Scene Text Detection with Differentiable Binarization

Minghui Liao, Zhaoyi Wan, Cong Yao, and Xiang Bai.

The 34th AAAI Conference on Artificial Intelligence (AAAI), New York, NY, February 2020.(oral presentation)

Paper Code

TextScanner: Reading Characters in Order for Robust Scene Text Recognition

Zhaoyi Wan, Minghang He, Haoran Chen, Xiang Bai, and Cong Yao.

The 34th AAAI Conference on Artificial Intelligence (AAAI), New York, NY, February 2020.

Paper

Scene text recognition from two-dimensional perspective

Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Cong Yao, and Xiang Bai

The 33rd AAAI Conference on Artificial Intelligence (AAAI), Honolulu, HI, February 2019.(oral presentation)

Paper

2D CTC for Scene Text Recognition

Zhaoyi Wan, Fengming Xie, Yibo Liu, Xiang Bai, and Cong Yao.

Paper Code