Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107728
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorEriksson, A.en
dc.contributor.authorPham, T.en
dc.contributor.authorChin, T.en
dc.contributor.authorReid, I.en
dc.date.issued2015en
dc.identifier.citationProceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015 / vol.07-12-June-2015, pp.3349-3357en
dc.identifier.isbn9781467369640en
dc.identifier.issn1063-6919en
dc.identifier.urihttp://hdl.handle.net/2440/107728-
dc.description.abstractSparsity, or cardinality, as a tool for feature selection is extremely common in a vast number of current computer vision applications. The k-support norm is a recently proposed norm with the proven property of providing the tightest convex bound on cardinality over the Euclidean norm unit ball. In this paper we present a re-derivation of this norm, with the hope of shedding further light on this particular surrogate function. In addition, we also present a connection between the rank operator, the nuclear norm and the k-support norm. Finally, based on the results established in this re-derivation, we propose a novel algorithm with significantly improved computational efficiency, empirically validated on a number of different problems, using both synthetic and real world data.en
dc.description.statementofresponsibilityAnders Eriksson, Trung Thanh Pham, Tat-Jun Chin, Ian Reiden
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognitionen
dc.rights© 2015 IEEEen
dc.subjectOptimization, computer science, computer vision, computational modeling, convex functions, convergence, electrical engineeringen
dc.titleThe k-support norm and convex envelopes of cardinality and ranken
dc.typeConference paperen
dc.identifier.rmid0030046341en
dc.contributor.conference2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) (07 Jun 2015 - 12 Jun 2015 : Boston, MA)en
dc.identifier.doi10.1109/CVPR.2015.7298956en
dc.relation.granthttp://purl.org/au-research/grants/arc/DE130101775en
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016en
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102en
dc.identifier.pubid239400-
pubs.library.collectionComputer Science publicationsen
pubs.library.teamDS06en
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidReid, I. [0000-0001-7790-6423]en
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107728.pdfRestricted Access784.42 kBAdobe PDFView/Open


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