Collaborative Attention Network for Person Re-identification. Issue 1 (April 2021)
- Record Type:
- Journal Article
- Title:
- Collaborative Attention Network for Person Re-identification. Issue 1 (April 2021)
- Main Title:
- Collaborative Attention Network for Person Re-identification
- Authors:
- Li, Wenpeng
Sun, Yongli
Wang, Jinjun
Cao, Junliang
Xu, Han
Yang, Xiangru
Sun, Guangze
Ma, Yangyang
Long, Yilin - Abstract:
- Abstract: The quality of visual feature representation has always been a key factor in many computer vision tasks. In the person re-identification (Re-ID) problem, combining global and local features to improve model performance is becoming a popular method, because previous works only used global features alone, which is very limited at extracting discriminative local patterns from the obtained representation. Some existing works try to collect local patterns explicitly slice the global feature into several local pieces in a handcrafted way. By adopting the slicing and duplication operation, models can achieve relatively higher accuracy but we argue that it still does not take full advantage of partial patterns because the rule and strategy local slices are defined. In this paper, we show that by firstly over-segmenting the global region by the proposed multi-branch structure, and then by learning to combine local features from neighbourhood regions using the proposed Collaborative Attention Network (CAN), the final feature representation for Re-ID can be further improved. The experiment results on several widely-used public datasets prove that our method outperforms many existing state-of-the-art methods.
- Is Part Of:
- Journal of physics. Volume 1848:Issue 1(2021)
- Journal:
- Journal of physics
- Issue:
- Volume 1848:Issue 1(2021)
- Issue Display:
- Volume 1848, Issue 1 (2021)
- Year:
- 2021
- Volume:
- 1848
- Issue:
- 1
- Issue Sort Value:
- 2021-1848-0001-0000
- Page Start:
- Page End:
- Publication Date:
- 2021-04
- Subjects:
- Physics -- Congresses
530.5 - Journal URLs:
- http://www.iop.org/EJ/journal/1742-6596 ↗
http://ioppublishing.org/ ↗ - DOI:
- 10.1088/1742-6596/1848/1/012074 ↗
- Languages:
- English
- ISSNs:
- 1742-6588
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 5036.223000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 25591.xml