ML Anthology

Shape Classification Through Structured Learning of Matching Measures

Longbin Chen, Julian J. McAuley, Rogério Schmidt Feris, Tibério S. Caetano, Matthew Turk
CVPR 2009 pp. 365-372
doi:10.1109/CVPR.2009.5206792 /cvpr/2009/chen2009cvpr-shape/

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.

CVPR Semantic Scholar

Cite

Text

Chen et al. "Shape Classification Through Structured Learning of Matching Measures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206792

Markdown

[Chen et al. "Shape Classification Through Structured Learning of Matching Measures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/chen2009cvpr-shape/) doi:10.1109/CVPR.2009.5206792

BibTeX

@inproceedings{chen2009cvpr-shape,
  title     = {{Shape Classification Through Structured Learning of Matching Measures}},
  author    = {Chen, Longbin and McAuley, Julian J. and Feris, Rogério Schmidt and Caetano, Tibério S. and Turk, Matthew},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {365-372},
  doi       = {10.1109/CVPR.2009.5206792},
  url       = {https://mlanthology.org/cvpr/2009/chen2009cvpr-shape/}
}