报告题目：Deep Learning for Person Re-identification

报告人：Yantao Shen

Department of Electronic Engineering at the Chinese University of Hong Kong

时间: 2018年4 月4 日，9：30

地点:  信息学馆 228

邀请人: Associate Prof. Dali Chen

ABSTRACT:

In this talk, I would like to share our recent research about person re-identification  (person Re-ID), which includes a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network and a novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes. Both papers are accepted by CVPR 2018.

BIOGRAPHY:

 Yantao Shen is 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. He also works closly with Prof. Hongsheng Li and Dr. Tong Xiao. He received B.E. degree from the Department of Automation, Northeastern University, China, in 2015.  He is a Hong Kong PhD Fellowship Scheme (HKPFS)  awardee.  His research interests include machine learning and computer vision.