Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification

Lin, Shan, Li, Haoliang, Li, Chang-Tsun and Kot, Alex Chichung 2018, Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification, in BMVC 2018: Proceedings of the 29th British Machine Vision Conference, BMVC, [Newcastle upon Tyne, England].

Attached Files
Name Description MIMEType Size Downloads

Title Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification
Author(s) Lin, Shan
Li, Haoliang
Li, Chang-TsunORCID iD for Li, Chang-Tsun orcid.org/0000-0003-4735-6138
Kot, Alex Chichung
Conference name BMVC 2018 (29th : 2018 : Newcastle upon Tyne, England)
Conference location Newcastle upon Tyne, England
Conference dates 2018/09/03 - 2018/09/06
Title of proceedings BMVC 2018: Proceedings of the 29th British Machine Vision Conference
Publication date 2018
Total pages 13
Publisher BMVC
Place of publication [Newcastle upon Tyne, England]
Summary © 2018. The copyright of this document resides with its authors. Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world applications where no labelled samples are available during the training phase. To overcome this limitation, we develop a novel unsupervised Multi-task Mid-level Feature Alignment (MMFA) network for the unsupervised cross-dataset person re-identification task. Under the assumption that the source and target datasets share the same set of mid-level semantic attributes, our proposed model can be jointly optimised under the person's identity classification and the attribute learning task with a cross-dataset mid-level feature alignment regularisation term. In this way, the learned feature representation can be better generalised from one dataset to another which further improve the person re-identification accuracy. Experimental results on four benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art baselines.
Language eng
Indigenous content off
HERDC Research category E1.1 Full written paper - refereed
Copyright notice ©2018, The Authors
Persistent URL http://hdl.handle.net/10536/DRO/DU:30130402

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 49 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Thu, 10 Oct 2019, 11:19:36 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.