Multi-scale Deep Learning Architectures for Person Re-identification

Fu, Y; Qian, X; Jiang, Y-G; Xiang, T; Xue, X

Multi-scale Deep Learning Architectures for Person Re-identification

Fu, Y Qian, X Jiang, Y-G Xiang, T Xue, X

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings 2017 IEEE International Conference on Computer Vision, 2017
Issue Date:: 2017-12-25

Closed Access

	Filename	Description	Size
	08237839.pdf	Published version	1.36 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	Fu, Y	en_US
dc.contributor.author	Qian, X	en_US
dc.contributor.author	Jiang, Y-G	en_US
dc.contributor.author	Xiang, T	en_US
dc.contributor.author	Xue, X	en_US
dc.date	2017-10-22	en_US
dc.date.issued	2017-12-25	en_US
dc.identifier.citation	Proceedings 2017 IEEE International Conference on Computer Vision, 2017	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127550
dc.description.abstract	Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks.	en_US
dc.publisher	IEEE	en_US
dc.relation	http://purl.org/au-research/grants/arc/DE170101415
dc.relation.ispartof	Proceedings 2017 IEEE International Conference on Computer Vision	en_US
dc.relation.ispartof	IEEE International Conference on Computer Vision	en_US
dc.relation.isbasedon	10.1109/ICCV.2017.577	en_US
dc.rights	© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.title	Multi-scale Deep Learning Architectures for Person Re-identification	en_US
dc.type	Conference Proceeding
utslib.location	USA	en_US
utslib.location.activity	Venice, Italy	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	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/Faculty of Engineering and Information Technology/School of Software
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.consider-herdc	true	en_US
pubs.finish-date	2017-10-29	en_US
pubs.place-of-publication	USA	en_US
pubs.publication-status	Published	en_US
pubs.start-date	2017-10-22	en_US

Abstract:

Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks.

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

http://hdl.handle.net/10453/127550