Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Ming-hsuan | - |
dc.date.accessioned | 2017-02-22T05:59:00Z | - |
dc.date.available | 2017-02-22T05:59:00Z | - |
dc.date.issued | 2015-06 | - |
dc.identifier.citation | Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 1770-1778 | en_US |
dc.identifier.isbn | 978-1-4673-6964-0 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://ieeexplore.ieee.org/document/7298786/?isnumber=7298593&arnumber=7298786 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11754/25641 | - |
dc.description.abstract | Object segmentation is highly desirable for image understanding and editing. Current interactive tools require a great deal of user effort while automatic methods are usually limited to images of special object categories or with high color contrast. In this paper, we propose a data-driven algorithm that uses examples to break through these limits. As similar objects tend to share similar local shapes, we match query image patches with example images in multiscale to enable local shape transfer. The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation. In each stage of the cascade, local shape mask candidates are selected to refine the estimated segmentation of the previous stage iteratively with color models. Experimental results on various datasets (Weizmann Horse, Fashionista, Object Discovery and PASCAL) demonstrate the effectiveness and robustness of our algorithm. | en_US |
dc.description.sponsorship | This work is done partially when the first author was an intern at Adobe. The work is supported in part by NSF CAREER Grant #1149783 and NSF IIS Grant #1152576, and a gift from Adobe. | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE | en_US |
dc.subject | Shape | en_US |
dc.subject | Image segmentation | en_US |
dc.subject | Object segmentation | en_US |
dc.subject | Yttrium | en_US |
dc.subject | Image color analysis | en_US |
dc.subject | Proposals | en_US |
dc.subject | Databases | en_US |
dc.title | PatchCut: Data-Driven Object Segmentation via Local Shape Transfer | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1109/CVPR.2015.7298786 | - |
dc.relation.page | 1770-1778 | - |
dc.contributor.googleauthor | Yang, Jimei | - |
dc.contributor.googleauthor | Price, Brian | - |
dc.contributor.googleauthor | Cohen, Scott | - |
dc.contributor.googleauthor | Lin, Zhe | - |
dc.contributor.googleauthor | Yang, Ming-Hsuan | - |
dc.relation.code | 20150012 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF COMPUTER SCIENCE | - |
dc.identifier.pid | mhyang | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.