Multi-scale local-global architecture for person re-identification
No Thumbnail Available
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2022-08
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
Series
Soft Computing, Volume 26, issue 16, pp. 7967-7977
Abstract
With the emergence of deep learning method, which has been driven a great success for the field of person re-identification (re-ID). However, the existing works mainly focus on first-order attention (i.e., spatial and channels attention) statistics to model the valuable information for person re-ID. On the other hand, most existing methods operate data points respectively, which ignores discriminative patterns to some extent. In this paper, we present an automated framework named multi-scale local-global for person re-ID. The framework consists of two components. The first component is that a high-order attention module is adopted to learn high-order attention patterns to model the subtle differences among pedestrians and to generate the informative attention features. On the other hand, a novel architecture named spectral feature transformation is designed to make for the optimization of group wise similarities. Furthermore, we fuse the components together to form an ensemble model for person re-ID. Extensive experiments were conducted on the three benchmark datasets, i.e., Market-1501, DukeMTMC-reID, CUHK03, showing the superiority of the proposed method.Description
| openaire: EC/H2020/101016775/EU//INTERVENE Funding Information: Open Access funding provided by Aalto University. This work was supported by the Academy of Finland (Grants 336033, 315896), Business Finland (Grant 884/31/2018), and EU H2020 (Grant 101016775). Publisher Copyright: © 2022, The Author(s).
Keywords
Attention mechanism, Deep learning, Multi-scale local-global architecture, Person re-identification
Other note
Citation
Liu, J, Tiwari, P, Nguyen, T G, Gupta, D & Band, S S 2022, ' Multi-scale local-global architecture for person re-identification ', Soft Computing, vol. 26, no. 16, pp. 7967-7977 . https://doi.org/10.1007/s00500-022-06859-6