Show simple item record

dc.contributor.authorKhan, Naeemullah
dc.contributor.authorHong, Byung-Woo
dc.contributor.authorYezzi, Anthony
dc.contributor.authorSundaramoorthi, Ganesh
dc.date.accessioned2018-01-29T12:09:30Z
dc.date.available2018-01-29T12:09:30Z
dc.date.issued2017-11-09
dc.identifier.citationKhan N, Hong B-W, Yezzi A, Sundaramoorthi G (2017) Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.188.
dc.identifier.doi10.1109/CVPR.2017.188
dc.identifier.urihttp://hdl.handle.net/10754/626947
dc.description.abstractWe formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions. The energy is formulated by integrating a continuum of scales from a scale space computed from the heat equation within regions. We show that the energy can be optimized without computing a continuum of scales, but instead from a single scale. This makes the method computationally efficient in comparison to energies using a discrete set of scales. We apply our method to texture and motion segmentation. Experiments on benchmark datasets show that a continuum of scales leads to better segmentation accuracy over discrete scales and other competing methods.
dc.description.sponsorshipPartially funded by KAUST OCRF-2014-CRG3-62140401, NRF-2014R1A2A1A11051941, and NSF CCF-1526848.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttp://ieeexplore.ieee.org/document/8099671/
dc.relation.urlhttp://openaccess.thecvf.com/content_cvpr_2017/html/Khan_Coarse-To-Fine_Segmentation_With_CVPR_2017_paper.html
dc.rights(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.titleCoarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.dateJUL 21-26, 2017
dc.conference.name30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.locationHonolulu, HI
dc.eprint.versionPost-print
dc.contributor.institutionChung-Ang University, Korea
dc.contributor.institutionGeorgia Tech, USA
kaust.personKhan, Naeemullah
kaust.personSundaramoorthi, Ganesh
kaust.grant.numberOCRF-2014-CRG3-62140401
refterms.dateFOA2018-06-14T05:48:56Z
dc.date.published-online2017-11-09
dc.date.published-print2017-07


Files in this item

Thumbnail
Name:
Khan_Coarse-to-Fine SegmentationWith Shape-Tailored Continuum Scale Spaces.pdf
Size:
9.083Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record