Shape classification through structured learning of matching measures
作者： Longbin Chen , Julian J. McAuley , Rogerio S. Feris , Tiberio S. Caetano , Matthew Turk
DOI: 10.1109/CVPR.2009.5206792
关键词:
摘要: Many traditional methods for shape classification involve establishing point correspondences between shapes to produce matching scores, which are in turn used as similarity measures classification. Learning techniques have been applied only the second stage of this process, after scores obtained. In paper, instead simply taking granted obtained by and then learning a classifier, we learn themselves so that minimize loss. The solution is based on max-margin formulation structured prediction setting. Experiments databases reveal such an integrated algorithm substantially improves existing methods.
ucsb.edu
tiberiocaetano.com 
stanford.edu 参考文章(17)
Matthew B. Blaschko, Christoph H. Lampert, Learning to Localize Objects with Structured Output Regression european conference on computer vision. pp. 2- 15 ,(2008) , 10.1007/978-3-540-88682-2_2
Choon Hui Teo, Alex Smola, S. V.N. Vishwanathan, Quoc Viet Le, A scalable modular convex solver for regularized risk minimization Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '07. pp. 727- 736 ,(2007) , 10.1145/1281192.1281270
S. Belongie, J. Malik, J. Puzicha, Shape matching and object recognition using shape contexts IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 24, pp. 509- 522 ,(2002) , 10.1109/34.993558
T.F. Smith, M.S. Waterman, Identification of common molecular subsequences. Journal of Molecular Biology. ,vol. 147, pp. 195- 197 ,(1981) , 10.1016/0022-2836(81)90087-5
Ioannis Tsochantaridis, Thorsten Joachims, Thomas Hofmann, Yasemin Altun, Yoram Singer, Large Margin Methods for Structured and Interdependent Output Variables Journal of Machine Learning Research. ,vol. 6, pp. 1453- 1484 ,(2005)
L.J. Latecki, R. Lakamper, T. Eckhardt, Shape descriptors for non-rigid shapes with a single closed contour computer vision and pattern recognition. ,vol. 1, pp. 1424- 1429 ,(2000) , 10.1109/CVPR.2000.855850
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Hao Zhang, J. Malik, Learning a discriminative classifier using shape context distances computer vision and pattern recognition. ,vol. 1, pp. 242- 247 ,(2003) , 10.1109/CVPR.2003.1211360
Pedro F. Felzenszwalb, Joshua D. Schwartz, Hierarchical Matching of Deformable Shapes computer vision and pattern recognition. pp. 1- 8 ,(2007) , 10.1109/CVPR.2007.383018
Andrea Frome, Yoram Singer, Fei Sha, Jitendra Malik, Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification international conference on computer vision. pp. 1- 8 ,(2007) , 10.1109/ICCV.2007.4408839