University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Leader-based Multi-Scale Attention Deep Architecture for Person Re-identification

Qian, Xuelin, Fu, Yanwei, Xiang, Tao, Jiang, Yu-Gang and Xue, Xiangyang (2019) Leader-based Multi-Scale Attention Deep Architecture for Person Re-identification IEEE Transactions on Pattern Analysis and Machine Intelligence.

final_version.pdf - Accepted version Manuscript

Download (4MB) | Preview


Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers – a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Qian, Xuelin
Fu, Yanwei
Jiang, Yu-Gang
Xue, Xiangyang
Date : 15 July 2019
DOI : 10.1109/TPAMI.2019.2928294
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords : Person re-identification; Multi-scale deep learning; Self-attention; Domain generalization
Depositing User : Diane Maxfield
Date Deposited : 03 Oct 2019 15:41
Last Modified : 03 Oct 2019 15:41

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800