본문 바로가기

Deep attention network for person re-identification with multi-loss

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
피인용
Web of Science 12Scopus 14
FWCI (Scopus)
0.78
JCR IF
JCR 2018 2.189
ISSN
0045-7906

저자

  1. Li, Rui제1저자School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
  2. Zhang, BaopengSchool of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
  3. 강동중Mechanical Engineering, Pusan National University, Busan, South Korea
  4. Teng, Zhu교신저자School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China

초록

Person re-identification (person re-ID) is one of the most challenging tasks in the computer vision area as it involves large variations in human appearances, human poses, background illuminations, camera views, etc. In particular, images for person re-ID are mostly low resolution due to the long-range deployment of the cameras and the cropping operation from the surveillance system. In this paper, we present a novel deep Siamese person re-ID network equipped with an attention mechanism, constrained by a multi-loss function. The attention mechanism enhances the discriminability of the network by emphasizing effective features and suppressing the less useful ones. The purpose of the multi-loss function is to diminish distances of identical persons and at the same time expand distances between dissimilar persons in the learned feature space. Extensive comparative evaluations demonstrate that the proposed method significantly outperforms a number of state-of-the-art approaches, including both conventional and deep network based ones, on the challenging Market1501 and CUHK03 data sets. (C) 2019 Elsevier Ltd. All rights reserved.

키워드

Person re-identificationSiamese networkAttention mechanismIdentificationVerificationNEURAL-NETWORK

식별자

Scopus EID
2-s2.0-85071870074
WoS UID
000492799200010