Projects per year
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.
|Early online date||2022|
|Publication status||Published - Aug 2022|
|MoE publication type||A1 Journal article-refereed|
- Attention mechanism
- Deep learning
- Multi-scale local-global architecture
- Person re-identification
FingerprintDive into the research topics of 'Multi-scale local-global architecture for person re-identification'. Together they form a unique fingerprint.
INTERVENE: International consortium for integrative genomics prediction
01/01/2021 → 31/12/2025
Project: EU: Framework programmes funding
Data Literacy for Responsible Decision-Making
Marttinen, P., Gröhn, T., Honkamaa, J., Kumar, Y., Ji, S., Raj, V., Ojala, F., Pöllänen, A. & Tiwari, P.
01/10/2020 → 30/09/2023
Project: Academy of Finland: Strategic research funding
eMOM: CleverHealth Network: eMOM GDM -Project
Marttinen, P., Alizadeh Ashrafi, R., Hizli, C. & Zhang, G.
05/02/2018 → 31/01/2023
Project: Business Finland: Other research funding