Bottom-up & top-down object detection using primal sketch features and graphical models

Kokkinos, I; Maragos, P; Yuille, A

dc.contributor.author	Kokkinos, I	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Yuille, A	en
dc.date.accessioned	2014-03-01T02:43:58Z
dc.date.available	2014-03-01T02:43:58Z
dc.date.issued	2006	en
dc.identifier.issn	10636919	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31578
dc.subject	Feature Detection	en
dc.subject	Graphical Model	en
dc.subject	Interest Points	en
dc.subject	Object Detection	en
dc.subject	Object Representation	en
dc.subject	Bottom Up	en
dc.subject	Front End	en
dc.subject	Top Down	en
dc.subject.other	Graphical models	en
dc.subject.other	Object representation	en
dc.subject.other	Edge detection	en
dc.subject.other	Feature extraction	en
dc.subject.other	Graphic methods	en
dc.subject.other	Mathematical models	en
dc.subject.other	Set theory	en
dc.subject.other	Object recognition	en
dc.title	Bottom-up & top-down object detection using primal sketch features and graphical models	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/CVPR.2006.74	en
heal.identifier.secondary	http://dx.doi.org/10.1109/CVPR.2006.74	en
heal.identifier.secondary	1640984	en
heal.publicationDate	2006	en
heal.abstract	A combination of techniques that is becoming increasingly popular is the construction of part-based object representations using the outputs of interest-point detectors. Our contributions in this paper are twofold: first, we propose a primal-sketch-based set of image tokens that are used for object representation and detection. Second, top-down information is introduced based on an efficient method for the evaluation of the likelihood of hypothesized part locations. This allows us to use graphical model techniques to complement bottom-up detection, by proposing and finding the parts of the object that were missed by the front-end feature detection stage. Detection results for four object categories validate the merits of this joint top-down and bottom-up approach. © 2006 IEEE.	en
heal.journalName	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition	en
dc.identifier.doi	10.1109/CVPR.2006.74	en
dc.identifier.volume	2	en
dc.identifier.spage	1893	en
dc.identifier.epage	1900	en