Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLi, X.en
dc.contributor.authorShen, C.en
dc.contributor.authorShi, Q.en
dc.contributor.authorDick, A.en
dc.contributor.authorVan Den Hengel, A.en
dc.identifier.citationProceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition, held in Providence, Rhode Island, 16-21 June, 2012: pp. 1760-1767en
dc.description.abstractMost sparse linear representation-based trackers need to solve a computationally expensive ℓ₁-regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient closed-form solution without sacrificing accuracy. Moreover, in order to capture the correlation information between different feature dimensions, we learn a Mahalanobis distance metric in an online fashion and incorporate the learned metric into the optimization problem for obtaining the linear representation. We show that online metric learning using proximity comparison significantly improves the robustness of the tracking, especially on those sequences exhibiting drastic appearance changes. Furthermore, in order to prevent the unbounded growth in the number of training samples for the metric learning, we design a time-weighted reservoir sampling method to maintain and update limited-sized foreground and background sample buffers for balancing sample diversity and adaptability. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.en
dc.description.statementofresponsibilityXi Li, Chunhua Shen, Qinfeng Shi, Anthony Dick, Anton van den Hengelen
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognitionen
dc.rights© 2012 IEEEen
dc.subjectVisual tracking; linear representation; reservoir sampling; metric learningen
dc.titleNon-sparse linear representations for visual tracking with online reservoir metric learningen
dc.typeConference paperen
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (25th : 2012 : Providence, Rhode Island)en
pubs.library.collectionComputer Science publicationsen
dc.identifier.orcidShen, C. [0000-0002-8648-8718]en
dc.identifier.orcidDick, A. [0000-0001-9049-7345]en
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]en
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_70244.pdfAccepted version712.41 kBAdobe PDFView/Open

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