Please use this identifier to cite or link to this item: http://hdl.handle.net/2381/43276
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, S-
dc.contributor.authorZhang, X-
dc.contributor.authorChen, L-
dc.contributor.authorZhou, H-
dc.contributor.authorDong, J-
dc.date.accessioned2019-02-08T11:15:55Z-
dc.date.issued2018-11-12-
dc.identifier.citationJournal of Visual Communication and Image Representation, 2018, 57, pp. 262-271en
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S1047320318302864#!en
dc.identifier.urihttp://hdl.handle.net/2381/43276-
dc.descriptionThe file associated with this record is under embargo until 12 months after publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.en
dc.description.abstractPerson re-identification aims at matching individuals across multiple camera views under surveillance systems. The major challenges lie in the lack of spatial and temporal cues, which makes it difficult to cope with large variations of lighting conditions, viewing angles, body poses and occlusions. How to extract multimodal features including facial features, physical features, behavioral features, color features, etc is still a fundamental problem in person re-identification. In this paper, we propose a novel Convolutional Neural Network, called Asymmetric Filtering-based Dense Convolutional Neural Network (AF D-CNN) to learn powerful features, which can extract different levels’ features and take advantage of identity information. Moreover, instead of using typical metric learning methods, we obtain the ranking lists by merging Joint Bayesian and re-ranking techniques which do not need dimensionality reduction. Finally, extensive experiments show that our proposed architecture performs well on four popular benchmark datasets (CUHK01, CUHK03, Market-1501, DukeMTMC-reID).en
dc.description.sponsorshipThis work is supported by the National Natural Science Foundation of China (NSFC) Grants U1706218, 61602229, 41606198, 61501417 and 41706010, Natural Science Foundation of Shandong Provincial ZR2016FM13, ZR2016FB02. H. Zhou was supported in part by the European Union’s Horizon 2020 research and innovation program under the Marie-Sklodowska-Curie grant agreement No 720325 FoodSmartphone, the UK EPSRC under Grant EP/N011074/1 and the Royal Society-Newton Advanced Fellowship under Grant NA160342.en
dc.language.isoenen
dc.publisherElsevier for Academic Pressen
dc.rightsCopyright © Elsevier, 2018. After an embargo period this version of the paper will be an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.en
dc.titleAsymmetric filtering-based dense convolutional neural network for person re-identification combined with Joint Bayesian and re-rankingen
dc.typeJournal Articleen
dc.identifier.doi10.1016/j.jvcir.2018.11.013-
dc.identifier.eissn1095-9076)-
dc.description.statusPeer-revieweden
dc.description.versionPost-printen
dc.type.subtypeArticle-
pubs.organisational-group/Organisationen
pubs.organisational-group/Organisation/COLLEGE OF SCIENCE AND ENGINEERINGen
pubs.organisational-group/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Informaticsen
dc.rights.embargodate2019-11-12-
dc.dateaccepted2018-11-10-
Appears in Collections:Published Articles, College of Science and Engineering

Files in This Item:
File Description SizeFormat 
final version.pdfPost-review (final submitted author manuscript)2.07 MBAdobe PDFView/Open


Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.