dc.contributor.author | Yin, Q | |
dc.contributor.author | Wang, G | |
dc.contributor.author | Ding, G | |
dc.contributor.author | Gong, S | |
dc.contributor.author | Tang, Z | |
dc.date.accessioned | 2021-08-27T10:12:50Z | |
dc.date.available | 2021-08-27T10:12:50Z | |
dc.date.issued | 2021 | |
dc.identifier.issn | 1070-9908 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/73784 | |
dc.description.abstract | Person re-identification (ReID) aims to match pedestrian images across disjoint cameras. Existing supervised ReID methods utilize deep networks and train them with identity-labeled images, which suffer from limited annotations. Recently, clustering-based unsupervised ReID attracts more and more attention. It first clusters unlabeled images and assigns cluster index to the pseudo-identity-labels, then trains a ReID model with the pseudo-identity-labels. However, considering the slight inter-class variations and significant intra-class variations, pseudo-identity-labels learned from clustering algorithms are usually noisy and coarse. To alleviate the problems above, besides clustering pseudo-identity-labels, we propose to learn pseudo-patch-labels, which brings two advantages: (1) Patch naturally alleviates the effect of backgrounds, occlusions, and carryings since they usually occupy small parts in images, thus overcome noisy labels. (2) It is plausible that patches from different pedestrians belong to the same pseudo-identity-label. For example, pedestrians have a high probability of wearing either the same shoes or pants but a low possibility of wearing both. The experiments demonstrate our proposed method achieves the best performance by a large margin on both image- and video-based datasets. | en_US |
dc.format.extent | 1390 - 1394 | |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | IEEE SIGNAL PROCESSING LETTERS | |
dc.subject | Training | en_US |
dc.subject | Trajectory | en_US |
dc.subject | Noise measurement | en_US |
dc.subject | Clustering algorithms | en_US |
dc.subject | Annotations | en_US |
dc.subject | Merging | en_US |
dc.subject | Cameras | en_US |
dc.subject | Unsupervised learning | en_US |
dc.subject | multi-view learning | en_US |
dc.subject | person re-identification | en_US |
dc.subject | clustering | en_US |
dc.title | Multi-View Label Prediction for Unsupervised Learning Person Re-Identification | en_US |
dc.type | Article | en_US |
dc.rights.holder | © 2021 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. | |
dc.identifier.doi | 10.1109/LSP.2021.3090258 | |
pubs.author-url | http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000675200300003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=612ae0d773dcbdba3046f6df545e9f6a | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 28 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | Intelligent Video Analytics Solutions for Public Safety::Innovate UK | en_US |
qmul.funder | Intelligent Video Analytics Solutions for Public Safety::Innovate UK | en_US |