Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/107291
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRezatofighi, S.-
dc.contributor.authorMilan, A.-
dc.contributor.authorZhang, Z.-
dc.contributor.authorShi, Q.-
dc.contributor.authorDick, A.-
dc.contributor.authorReid, I.-
dc.date.issued2016-
dc.identifier.citationProceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol.2016-December, pp.136-145-
dc.identifier.isbn9781467388511-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/2440/107291-
dc.description.abstractMatching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score. In this paper, we argue that this single solution does not necessarily lead to the optimal matching accuracy and that general one-to-one assignment problems can be improved by considering multiple hypotheses before computing the final similarity measure. To that end, we propose to utilize the marginal distributions for each entity. Previously, this idea has been neglected mainly because exact marginalization is intractable due to a combinatorial number of all possible matching permutations. Here, we propose a generic approach to efficiently approximate the marginal distributions by exploiting the m-best solutions of the original problem. This approach not only improves the matching solution, but also provides more accurate ranking of the results, because of the extra information included in the marginal distribution. We validate our claim on two distinct objectives: (i) person re-identification and temporal matching modeled as an integer linear program, and (ii) feature point matching using a quadratic cost function. Our experiments confirm that marginalization indeed leads to superior performance compared to the single (nearly) optimal solution, yielding state-of-the-art results in both applications on standard benchmarks.-
dc.description.statementofresponsibilitySeyed Hamid Rezatofighi, Anton Milani, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid-
dc.language.isoen-
dc.publisherIEEE-
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition-
dc.rights© 2016 IEEE-
dc.source.urihttp://dx.doi.org/10.1109/cvpr.2016.22-
dc.titleJoint probabilistic matching using m-best solutions-
dc.typeConference paper-
dc.contributor.conference29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2016) (26 Jun 2016 - 1 Jul 2016 : Las Vegas, NV)-
dc.identifier.doi10.1109/CVPR.2016.22-
dc.relation.granthttp://purl.org/au-research/grants/arc/LP130100154-
dc.relation.granthttp://purl.org/au-research/grants/arc/DP140102270-
dc.relation.granthttp://purl.org/au-research/grants/arc/DP160100703-
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102-
pubs.publication-statusPublished-
dc.identifier.orcidZhang, Z. [0000-0003-2805-4396]-
dc.identifier.orcidShi, Q. [0000-0002-9126-2107]-
dc.identifier.orcidDick, A. [0000-0001-9049-7345]-
dc.identifier.orcidReid, I. [0000-0001-7790-6423]-
Appears in Collections:Aurora harvest 3
Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107291.pdf
  Restricted Access
Restricted Access4.46 MBAdobe PDFView/Open


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