Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107291
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Joint probabilistic matching using m-best solutions
Author: Rezatofighi, S.
Milan, A.
Zhang, Z.
Shi, Q.
Dick, A.
Reid, I.
Citation: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2016), 2016 / vol.2016-December, pp.136-145
Publisher: IEEE
Issue Date: 2016
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467388511
ISSN: 1063-6919
Conference Name: 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2016) (26 Jun 2016 - 01 Jul 2016 : Las Vegas, NV)
Statement of
Responsibility: 
Seyed Hamid Rezatofighi, Anton Milani, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid
Abstract: Matching 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.
Rights: © 2016 IEEE
RMID: 0030055702
DOI: 10.1109/CVPR.2016.22
Grant ID: http://purl.org/au-research/grants/arc/LP130100154
http://purl.org/au-research/grants/arc/DP140102270
http://purl.org/au-research/grants/arc/DP160100703
http://purl.org/au-research/grants/arc/FL130100102
Appears in Collections:Computer Science publications

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


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