Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/105524
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPham, T.en
dc.contributor.authorRezatofighi, S.en
dc.contributor.authorReid, I.en
dc.contributor.authorChin, T.en
dc.date.issued2016en
dc.identifier.citationProceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016 / vol.2016-December, pp.2837-2845en
dc.identifier.isbn9781467388511en
dc.identifier.issn1063-6919en
dc.identifier.urihttp://hdl.handle.net/2440/105524-
dc.description.abstractWe tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly encode object qualities and spatial interactions. But the corresponding optimisation problem is typically difficult or intractable, and many of the best current methods rely on Monte Carlo Markov Chain (MCMC) simulation, which converges slowly in a large solution space. We propose an efficient point process inference for largescale object detection using discrete energy minimization. In particular, we approximate the solution space by a finite set of object proposals and cast the point process density function to a corresponding energy function of binary variables whose values indicate which object proposals are accepted. We resort to the local submodular approximation (LSA) based trust-region optimisation to find the optimal solution. Furthermore we analyse the error of LSA approximation, and show how to adjust the point process energy to dramatically speed up the convergence without harming the optimality. We demonstrate the superior efficiency and accuracy of our method using a variety of large-scale object detection applications such as crowd human detection, birds, cells counting/localization.en
dc.description.statementofresponsibilityTrung T. Pham, Seyed Hamid Rezatofighi, Ian Reid and Tat-Jun Chinen
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognitionen
dc.rights© 2016 IEEEen
dc.titleEfficient point process inference for large-scale object detectionen
dc.typeConference paperen
dc.identifier.rmid0030056387en
dc.contributor.conference29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (26 Jun 2016 - 01 Jul 2016 : Las Vegas, NV)en
dc.identifier.doi10.1109/CVPR.2016.310en
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016en
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102en
dc.relation.granthttp://purl.org/au-research/grants/arc/DP160103490en
dc.identifier.pubid264884-
pubs.library.collectionComputer Science publicationsen
pubs.library.teamDS03en
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_105524.pdfRestricted Access1.54 MBAdobe PDFView/Open


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