Abstract
Cross-domain person re-identification (Re-ID) is a challenging and important task in monitoring safety and procedure compliance of industrial work places. In this article, a novel method is proposed to reduce background induced domain shift for adaptive person Re-ID. Specifically, a foreground-background joint clustering module is proposed to extract discriminative foreground and background features and an attention-based feature disentanglement module is designed to reduce the interference of background with the extraction of discriminative foreground features. Experimental results on three widely used person Re-ID benchmarking datasets (Market-1501, DukeMTMC-reID, and MSMT17) have demonstrated that the proposed method achieves promising performance compared with the state-of-the-art methods.
| Original language | English |
|---|---|
| Pages (from-to) | 7377-7388 |
| Number of pages | 12 |
| Journal | IEEE Transactions on Industrial Informatics |
| Volume | 19 |
| Issue number | 6 |
| Early online date | 29 Sept 2022 |
| DOIs | |
| Publication status | Published - Jun 2023 |
| Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2005-2012 IEEE.
Funding
The work of Jianjun Lei and Bo Peng was supported in part by the National Natural Science Foundation of China under Grant 62125110 and Grant 62101379, in part by the Natural Science Foundation of Tianjin under Grant 18JCJQJC45800, in part by the China Postdoctoral Science Foundation under Grant 2021TQ0244 and in part by the Didi GAIA Research Cooperation Initiative. Paper no. TII-21-5133.
Keywords
- domain adaptation
- feature disentanglement
- intelligent surveillance
- Person re-identification