M. Pawan Kumar

Postdoctoral Research Associate
Department of Computer Science
Stanford University
email address



SELECTED PUBLICATIONS (ALL PUBLICATIONS)

M. Pawan Kumar and D. Koller. Learning a Small Mixture of Trees.
In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2009.
[pdf][abstract][bibtex][poster]

M. Pawan Kumar, A. Zisserman and P.H.S. Torr. Efficient Discriminative Learning of Parts-based Models.
In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2009.
[pdf][abstract][bibtex][poster]

M. Pawan Kumar and D. Koller. MAP Estimation of Semi-Metric MRFs via Hierarchical Graph Cuts.
In Proceedings of the Conference on Uncertainity in Artificial Intelligence (UAI), 2009.
[pdf][abstract][bibtex][tech-report] [poster]

M. Pawan Kumar, V. Kolmogorov and P.H.S. Torr. An Analysis of Convex Relaxations for MAP Estimation of Discrete MRFs.
In the Journal of Machine Learning Research (JMLR), 2009.
[pdf][abstract][bibtex]
Earlier version appeared in NIPS, 2007.

M. Pawan Kumar, P.H.S. Torr and A. Zisserman. OBJCUT: Efficient Segmentation using Top-Down and Bottom-Up Cues.
To appear in the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2009.
[pdf][abstract][bibtex]
Earlier version appeared in CVPR, 2005.

M. Pawan Kumar, P.H.S. Torr and A. Zisserman. Learning Layered Motion Segmentations of Video.
In the International Journal of Computer Vision (IJCV), March, 2008.
[pdf][abstract][bibtex]
Earlier version appeared in ICCV, 2005.

TALKS

Improved Moves for Truncated Convex Models. [download]

An Invariant Large Margin Nearest Neighbour Classifier. [download]

Layered Pictorial Structures for Object Category Segmentation. [download]

Junction Tree Algorithm - Brookes Vision Reading Group. [download]

Introduction to Convex Programming - Brookes Vision Reading Group. [download]

MAP Estimation Algorithms in Computer Vision - ECCV 2008 Tutorial. [webpage]

MAP Inference in Discrete Models - ICCV 2009 Tutorial. [webpage]

Resume      DBLP Page      DAGS