Current studentsExisting staffContact us
 

Formulating semantic image annotation as a supervised learning problem

Simple item page
dc.contributor.authorCarneiro, G.
dc.contributor.authorVasconcelos, N.
dc.contributor.conferenceIEEE Computer Society Conference on Computer Vision and Pattern Recognition (18th : 2005 : San Diego, CA, U.S.A.)
dc.contributor.editorSchmid, C.
dc.contributor.editorSoatto, S.
dc.contributor.editorTomasi, C.
dc.date.issued2005
dc.description.abstractWe introduce a new method to automatically annotate and retrieve images using a vocabulary of image semantics. The novel contributions include a discriminant formulation of the problem, a multiple instance learning solution that enables the estimation of concept probability distributions without prior image segmentation, and a hierarchical description of the density of each image class that enables very efficient training. Compared to current methods of image annotation and retrieval, the one now proposed has significantly smaller time complexity and better recognition performance. Specifically, its recognition complexity is O(C×R), where C is the number of classes (or image annotations) and R is the number of image regions, while the best results in the literature have complexity O(T×R), where T is the number of training images. Since the number of classes grows substantially slower than that of training images, the proposed method scales better during training, and processes test images faster This is illustrated through comparisons in terms of complexity, time, and recognition performance with current state-of-the-art methods.
dc.description.statementofresponsibilityGustavo Carneiro, Nuno Vasconcelos
dc.identifier.citationProceedings, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2 / C. Schmid, S. Soatto, and C. Tomasi (eds.): pp.163-168
dc.identifier.doi10.1109/CVPR.2005.164
dc.identifier.isbn0769523722
dc.identifier.issn1063-6919
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttp://hdl.handle.net/2440/84200
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeUSA
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rightsCopyright © 2005 by The Institute of Electrical and Electronics Engineers, Inc.
dc.source.urihttps://doi.org/10.1109/cvpr.2005.164
dc.titleFormulating semantic image annotation as a supervised learning problem
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications