I have moved. The following is a snapshot of this site in August 2010.


 Karteek Alahari


Hello! I recently completed a Ph.D. at Oxford Brookes University, and was supervised by Prof. Philip Torr. I am a member of the Brookes Vision Group and an associate member of the Visual Geometry Group, University of Oxford. I graduated from the International Institute of Information Technology (IIIT) with Master's (MS by Research, 2005) and Bachelor's (B.Tech. Honours, 2004) degrees.

Email: <first_name>.<last_name> @ ens.fr


RECENT PUBLICATIONS (ALL PUBLICATIONS)

Karteek Alahari
Efficient Inference and Learning for Computer Vision Labelling Problems
Ph.D. Thesis, July 2010.
[abstract] [pdf] [bibtex]

Ľubor Ladický, Paul Sturgess, Karteek Alahari, Chris Russell, P. H. S. Torr
What, Where & How Many? Combining Object Detectors and CRFs
In Proceedings of the European Conference on Computer Vision (ECCV), 2010 (oral).
[abstract] [pdf] [bibtex]

Karteek Alahari, Chris Russell, P. H. S. Torr
Efficient Piecewise Learning for Conditional Random Fields
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
[abstract] [pdf] [bibtex]

Karteek Alahari, Pushmeet Kohli, P. H. S. Torr
Dynamic Hybrid Algorithms for MAP Inference in Discrete MRFs
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2010.
[abstract] [pdf] [bibtex][code][README]

Paul Sturgess, Karteek Alahari, Ľubor Ladický, P. H. S. Torr
Combining Appearance and Structure from Motion Features for Road Scene Understanding
In Proceedings of the British Machine Vision Conference (BMVC), 2009 (oral).
[abstract] [pdf] [bibtex]

Karteek Alahari, Pushmeet Kohli, P. H. S. Torr
Reduce, Reuse & Recycle: Efficiently Solving Multi-Label MRFs
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
[abstract] [pdf] [bibtex][code][README]

Srikumar Ramalingam, Pushmeet Kohli, Karteek Alahari, P. H. S. Torr
Exact Inference in Multi-label CRFs with Higher Order Cliques
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
[abstract] [pdf] [bibtex]

TALKS

Reduce, Reuse & Recycle: Efficiently Solving Multi-Label MRFs - Oxford/Willow Mini Vision Workshop [pdf].

MRF Optimization via Dual Decomposition: Message-Passing Revisited - Brookes Vision Reading Group.

Approximation Algorithms for Classification Problems with Pairwise Relationships - Brookes Vision Reading Group.


CV (html, pdf, txt)     DBLP Page

PERSONAL



Thanks to M. Pawan Kumar for the page style.