Yantao SHEN, 沈岩涛

PhD Candidate,
Electronic Engineering Department,
The Chinese University of Hong Kong (CUHK)
E-mail: ytshen [@] ee [DOT] cuhk [DOT] edu [DOT] hk

About Me

I am currently a Ph.D. candidate in the Department of Electronic Engineering and Multimedia Laboratory (MMLAB), The Chinese University of Hong Kong, supervised by Prof. Xiaogang Wang. I also work closly with Prof. Hongsheng Li and Dr. Tong Xiao. I received my B.E. degree from the Department of Automation, Northeastern University, China, in 2015.

My CV, Google Scholar, Github

Research Interest

My research interests include

  • Computer Vision

  • Machine Learning

News

  • Jun 24, 2019: I am now serving as an Applied Scientist Intern at Amazon Rekognition Team.

  • Jul 9, 2018: The first AI teaching material for high school students is published now. It is my great honor to be one of the editors of this book.

  • Jul 3, 2018: 2 papers accepted to ECCV 2018.

  • Feb 20, 2018: 2 papers accepted to CVPR 2018, code is available now.

  • Jul 19, 2017: 1 paper accepted to ICCV 2017.

Recent Publications

Y. Shen, H. Li, S. Yi, D. Chen, X. Wang, "Person Re-identification with Deep Similarity-Guided Graph Neural Network", 15th European Conference on Computer Vision (ECCV), 2018. [PDF link]

D. Chen, H. Li, X, Liu, Y. Shen, J. Shao, Z. Yuan, X. Wang, "Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association", 15th European Conference on Computer Vision (ECCV), 2018. [PDF link]

Y. Shen, H. Li, S. Yi, D. Chen, X. Wang, "Deep Group-shuffling Random Walk for Person Re-identification ", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF link] [Code]

Y. Shen^, T. Xiao^, H. Li, S. Yi, X. Wang, " End-to-End Deep Kronecker-Product Matching for Person Re-identification ", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF link] [Code] (^denotes co-first authors)

Y. Shen, T. Xiao, H. Li, S. Yi, X. Wang, " Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals ", IEEE International Conference on Computer Vision (ICCV), 2017. [PDF link]