General Information

Course Title: Structured Prediction in Computer Vision
Instructors: Tibério Caetano and Richard Hartley (Australian National University and NICTA)
Date/Time: 28 September, morning

Course Description

This tutorial will review basic methods of structured prediction, i.e., supervised learning of discriminative models when the output domain is extremely high dimensional and the output variables are interdependent. This is the case for many fundamental vision problems such as image labeling and image matching. As learning engines, we cover max-margin and maximum-likelihood estimators, including structured SVMs and CRFs. As inference engines, we cover graph-cuts, variable elimination and junction trees. The effectiveness of learning structured prediction models will be illustrated in real vision problems from several domains, including graph and point-pattern matching, image segmentation, joint object categorization and stereo matching.

Course Materials

AVAILABLE BELOW!!

Parts I and III (Caetano)
Part II (Hartley)

Some Related References (list to be expanded)

[1] I. Tsochantaridis, T. Joachims, T. Hofmann, Y. Altun.
Large Margin Methods for Structured and Interdependent Output Variables, JMLR 2005.

[2] B. Taskar, C. Guestrin, D. Koller.
Max-Margin Markov Networks, NIPS 2004.

[3] L. Chen, J. J. McAuley, R. S. Feris, T. S. Caetano and M. Turk.
Shape Classification Through Structured Learning of Matching Measures, CVPR 2009.

[4] T. S. Caetano, J. J. McAuley, L. Cheng, Q. V. Le and A. J. Smola.
Learning Graph Matching, PAMI 2009, ICCV 2007.

[5] J. J. McAuley, T. S. Caetano and A. J. Smola.
Robust Near-Isometric Matching via Structured Learning of Graphical Models, NIPS 2008.

[6] D. Anguelov, B. Taskar, V. Chatalbashev, D. Koller, D. Gupta, G. Heitz, A. Ng.
Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data, CVPR 2005.

[7] X. He, R. Zemel, M. A. Carreira-Perpinan.
Multiscale Conditional Random Fields for Image Labeling, CVPR 2004.

[8] D. Scharstein, C. Pal.
Learning Conditional Random Fields for Stereo, CVPR 2007.

Instructors

Tibério Caetano Tibério Caetano is an Adjunct Research Fellow at the Australian National University and a Senior Researcher at the Statistical Machine Learning Group in NICTA. He has authored about 30 papers in Graph Matching, Structured Prediction, Computer Vision, Machine Learning, Pattern Recognition, Bioinformatics, Complex Networks and Theory of Particle Accelerators. He has been recently interested in both theory and practice of Structured Prediction in the domain of Computer Vision.

Richard Hartley Richard Hartley is a Professor at the Australian National University and a member of the Vision Science, Technology and Applications Group in NICTA; from 2003 until 2006 he was the leader of this research group. In 2000, he co-authored a book ``Multiple View Geometry in Computer Vision'' for Cambridge University Press, summarizing the previous decade's research in this area. This has become one of the most popular research reference texts in Computer Vision. He has authored over 100 papers in Photogrammetry, Computer Vision, Geometric Topology, Geometric Voting Theory, Computational Geometry and Computer-Aided Design, and holds 34 US patents. He has been recently interested in Discrete Optimization methods in Computer Vision.