Details
Poster
Presenter(s)
![Yunzhou Cheng Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/12611_0.jpg?h=b3b1b9cd&itok=00uCKITW)
Display Name
Yunzhou Cheng
- Affiliation
-
AffiliationSouthwest University
- Country
Abstract
This paper proposes a dual-path deep supervision network (DDSN) for visible-infrared person re-identification (VI-ReID), aiming to effectively utilize multi-level information through deep supervision and feature fusion methods. Besides, this paper introduces a self-attention mechanism to capture contextual information as a supplement. The above techniques have greatly enhanced discriminative feature learning. While these methods may seem simple, they provide great insight for VI-ReID.