|search externally:||Google Scholar, Springer, CiteSeer, Microsoft Academic Search, Scirus , DBlife|
My research interests are in developing robust and efficient algorithms which automatically interpret visual information. In particular I am interested in visual correspondence (stereo, motion), and image segmentation. Optimization techniques are of fundamental importance to computer vision problems. In my research I find graph algorithms and dynamic programming particularly useful for efficiently solving optimization problems arising in vision.
Tiered Scene Labeling with Dynamic Programming
as author at 23rd IEEE Conference on Computer Vision and Pattern Recognition 2010 - San Francisco,