Show simple item record

dc.contributor.authorAn, Senjian
dc.contributor.authorPeursum, Patrick
dc.contributor.authorLiu, Wanquan
dc.contributor.authorVenkatesh, Svetha
dc.contributor.editorNot known
dc.date.accessioned2017-01-30T11:22:10Z
dc.date.available2017-01-30T11:22:10Z
dc.date.created2012-03-07T20:01:06Z
dc.date.issued2011
dc.identifier.citationAn, S. and Peursum, P. and Liu, Wanquan and Venkatesh, S. 2011. Efficient subwindow search with submodular score functions, Computer Vision and Pattern Recognition (CVPR) 2011, Jun 20 2011, pp. 1409-1416. Colorado Springs, USA: IEEE
dc.identifier.urihttp://hdl.handle.net/20.500.11937/10983
dc.identifier.doi10.1109/CVPR.2011.5995355
dc.description.abstract

Subwindow search aims to find the optimal subimage which maximizes the score function of an object to be detected. After the development of the branch and bound (B&B) method called Efficient Subwindow Search (ESS), several algorithms (IESS, AESS, ARCS) have been proposed to improve the performance of ESS. For n×n images, IESS's time complexity is bounded by O(n3) which is better than ESS, but only applicable to linear score functions. Other work shows that Monge properties can hold in subwindow search and can be used to speed up the search to O(n3), but only applies to certain types of score functions. In this paper we explore the connection between submodular functions and the Monge property, and prove that sub-modular score functions can be used to achieve O(n3) time complexity for object detection. The time complexity can be further improved to be sub-cubic by applying B&B methods on row interval only, when the score function has a multivariate submodular bound function. Conditions for sub-modularity of common non-linear score functions and multivariate submodularity of their bound functions are also provided, and experiments are provided to compare the proposed approach against ESS and ARCS for object detection with some nonlinear score functions.

dc.publisherIEEE
dc.titleEfficient subwindow search with submodular score functions
dc.typeConference Paper
dcterms.source.startPage1409
dcterms.source.endPage1416
dcterms.source.titleCVPR 2011
dcterms.source.seriesCVPR 2011
dcterms.source.conferenceCVPR 2011
dcterms.source.conference-start-dateJun 20 2011
dcterms.source.conferencelocationColorado Springs, USA
dcterms.source.placeUSA
curtin.departmentDepartment of Computing
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record