Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Lena Gorelick"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:1985-1999
Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Unlike standard LP relaxation methods that linearize the whole energy gl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf953cb045d65232c78360470eb561ae
https://doi.org/10.1109/tpami.2016.2630686
https://doi.org/10.1109/tpami.2016.2630686
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:258-271
Convexity is a known important cue in human vision. We propose shape convexity as a new high-order regularization constraint for binary image segmentation. In the context of discrete optimization, object convexity is represented as a sum of three-cli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43866305ca4004b3a82f70acdb621aef
https://doi.org/10.1109/tpami.2016.2547399
https://doi.org/10.1109/tpami.2016.2547399
Autor:
Olga Veksler, Lena Gorelick
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319781983
EMMCVPR
EMMCVPR
Convexity is known as an important cue in human vision and has been recently proposed as a shape prior for segmenting a single foreground object. We propose a mutli-object convexity shape prior for multilabel image segmentation. We formulate a novel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7a866f45e4e75c70a495dd5ffaf8724
https://doi.org/10.1007/978-3-319-78199-0_30
https://doi.org/10.1007/978-3-319-78199-0_30
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012519
ECCV (11)
ECCV (11)
This work extends popular star-convexity and other more general forms of convexity priors. We represent an object as a union of “convex” overlappable subsets. Since an arbitrary shape can always be divided into convex parts, our regularization mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e8fc4ad7ff1db36222a9590b8ce9934
https://doi.org/10.1007/978-3-030-01252-6_3
https://doi.org/10.1007/978-3-030-01252-6_3
Publikováno v:
CVPR
Many computer vision problems require optimization of binary non-submodular energies. In this context, iterative submodularization techniques based on trust region (LSA-TR) and auxiliary functions (LSA-AUX) have been recently proposed [9]. They achie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4107b50caf565a19171fe95bf8c19777
https://doi.org/10.1109/cvpr.2017.642
https://doi.org/10.1109/cvpr.2017.642
Publikováno v:
BMVC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::642b662c3356b605a961e00c0711cd1b
https://doi.org/10.5244/c.31.19
https://doi.org/10.5244/c.31.19
Autor:
Mena Gaed, Glenn Bauman, Aaron D. Ward, Lena Gorelick, Olga Veksler, Jose A. Gomez, Madeleine Moussa, Aaron Fenster
Publikováno v:
IEEE Transactions on Medical Imaging. 32:1804-1818
Radical prostatectomy is performed on approximately 40% of men with organ-confined prostate cancer. Pathologic information obtained from the prostatectomy specimen provides important prognostic information and guides recommendations for adjuvant trea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcf9f1eddf7efe4585147a2906b2360a
https://doi.org/10.1109/tmi.2013.2265334
https://doi.org/10.1109/tmi.2013.2265334
Publikováno v:
Mathematics and Visualization ISBN: 9783319247243
Perspectives in Shape Analysis
Perspectives in Shape Analysis
Shape distances are an important measure to guide the task of shape classification. In this chapter we show that the right choice of shape similarity is also important for the task of image segmentation, even at the absence of any shape prior. To thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::43f00f5d3904246aafbad04bbf15e88d
https://doi.org/10.1007/978-3-319-24726-7_6
https://doi.org/10.1007/978-3-319-24726-7_6
Publikováno v:
International Journal of Computer Vision. 100:38-58
Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hierarchical fusion algorithm. Hierarchical costs are natural for modeling an arr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d0c00f6de6c913fd35b996f6b03daff
https://doi.org/10.1007/s11263-012-0531-x
https://doi.org/10.1007/s11263-012-0531-x
Autor:
Ronen Basri, Lena Gorelick
Publikováno v:
International Journal of Computer Vision. 83:211-232
We introduce a segmentation-based detection and top-down figure-ground delineation algorithm. Unlike common methods which use appearance for detection, our method relies primarily on the shape of objects as is reflected by their bottom-up segmentatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3f65447adc2e46e65e092836235e830
https://doi.org/10.1007/s11263-009-0216-2
https://doi.org/10.1007/s11263-009-0216-2