Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/84361
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorVasconcelos, M.en
dc.contributor.authorCarneiro, G.en
dc.contributor.authorVasconcelos, N.en
dc.date.issued2006en
dc.identifier.citation2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: volume 2, 2006 / A. Fitzgibbon, C. J. Taylor, Y. LeCun (eds.), pp.1001-1006en
dc.identifier.isbn0769525970en
dc.identifier.isbn9780769525976en
dc.identifier.issn1063-6919en
dc.identifier.urihttp://hdl.handle.net/2440/84361-
dc.description.abstractThere has recently been significant interest in top-down image segmentation methods, which incorporate the recognition of visual concepts as an intermediate step of segmentation. This work addresses the problem of top-down segmentation with weak supervision. Under this framework, learning does not require a set of manually segmented examples for each concept of interest, but simply a weakly labeled training set. This is a training set where images are annotated with a set of keywords describing their contents, but visual concepts are not explicitly segmented and no correspondence is specified between keywords and image regions. We demonstrate, both analytically and empirically, that weakly supervised segmentation is feasible when certain conditions hold. We also propose a simple weakly supervised segmentation algorithm that extends state-of-theart bottom-up segmentation methods in the direction of perceptually meaningful segmentation1.en
dc.description.statementofresponsibilityManuela Vasconcelos, Gustavo Carneiro, Nuno Vasconcelosen
dc.language.isoenen
dc.publisherIEEE Computer Societyen
dc.rightsCopyright © 2006 by The Institute of Electrical and Electronics Engineers, Inc.en
dc.titleWeakly supervised top-down image segmentationen
dc.typeConference paperen
dc.identifier.rmid0020114269en
dc.contributor.conferenceIEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006) (2006 : New York, USA)en
dc.identifier.doi10.1109/CVPR.2006.333en
dc.publisher.placeUSAen
dc.identifier.pubid27062-
pubs.library.collectionComputer Science publicationsen
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]en
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.