Multi-scale local-global architecture for person re-identification

Jing Liu, Prayag Tiwari*, Tri Gia Nguyen, Deepak Gupta, Shahab S. Band

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)
13 Downloads (Pure)


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.

Original languageEnglish
Pages (from-to)7967-7977
JournalSoft Computing
Issue number16
Early online date2022
Publication statusPublished - Aug 2022
MoE publication typeA1 Journal article-refereed


  • Attention mechanism
  • Deep learning
  • Multi-scale local-global architecture
  • Person re-identification


Dive into the research topics of 'Multi-scale local-global architecture for person re-identification'. Together they form a unique fingerprint.

Cite this