Improving person re-identification by attribute and identity learning

Lin, Y; Zheng, L; Zheng, Z; Wu, Y; Hu, Z; Yan, C; Yang, Y

Improving person re-identification by attribute and identity learning

Lin, Y Zheng, L Zheng, Z

Wu, Y

Hu, Z Yan, C Yang, Y

Permalink

Publication Type:: Journal Article
Citation:: Pattern Recognition, 2019, 95 pp. 151 - 161
Issue Date:: 2019-11-01

Closed Access

	Filename	Description	Size
	paper.pdf	Published Version	1.7 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, Y	en_US
dc.contributor.author	Zheng, L	en_US
dc.contributor.author	Zheng, Z https://orcid.org/0000-0002-2434-9050	en_US
dc.contributor.author	Wu, Y https://orcid.org/0000-0002-1680-8253	en_US
dc.contributor.author	Hu, Z	en_US
dc.contributor.author	Yan, C	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.date.issued	2019-11-01	en_US
dc.identifier.citation	Pattern Recognition, 2019, 95 pp. 151 - 161	en_US
dc.identifier.issn	0031-3203	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134471
dc.description.abstract	© 2019 Elsevier Ltd Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines.	en_US
dc.relation.ispartof	Pattern Recognition	en_US
dc.relation.isbasedon	10.1016/j.patcog.2019.06.006	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Improving person re-identification by attribute and identity learning	en_US
dc.type	Journal Article
utslib.citation.volume	95	en_US
utslib.for	0899 Other Information and Computing Sciences	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0806 Information Systems	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	95	en_US

Abstract:

© 2019 Elsevier Ltd Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/134471