Shape classification through structured learning of matching measures
Date
2009
Authors
Chen, Longbin
McAuley, Julian
Feris, Rogerio S.
Caetano, Tiberio
Turk, Matthew
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers (IEEE Inc)
Abstract
Many traditional methods for shape classification involve establishing point correspondences between shapes to produce matching scores, which are in turn used as similarity measures for classification. Learning techniques have been applied only in the second stage of this process, after the matching scores have been obtained. In this paper, instead of simply taking for granted the scores obtained by matching and then learning a classifier, we learn the matching scores themselves so as to produce shape similarity scores that minimize the classification loss. The solution is based on a max-margin formulation in the structured prediction setting. Experiments in shape databases reveal that such an integrated learning algorithm substantially improves on existing methods.
Description
Keywords
Keywords: Existing method; Integrated learning; Learning techniques; Matching score; Point correspondence; Santa Barbara; Shape classification; Shape database; Shape similarity; Similarity measure; Structured learning; Structured prediction; University of Californi
Citation
Collections
Source
Proceeings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009)
Type
Conference paper
Book Title
Entity type
Access Statement
License Rights
Restricted until
2037-12-31