My research interests lie in computer vision and in medical imaging. I have worked on a variety of problems in early vision, including motion and stereo; many of these problems can be solved very accurately using algorithms based on graph cuts (see the graph cuts home page for details, and the MRF comparison project for experimental results). Recently I have spent much of my time developing a new freshman course (CS100R) that uses robot vision to teach basic CS; the course was profiled in a Cornell Chronicle article.I served as a Program Chair for CVPR 2007 (the primary North American vision conference), and for the International Workshop on Computer Vision 2008 and 2010 (a small workshop for senior vision researchers). Since January 2009 I have served as Editor-in-Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence, generally viewed as the top journal in computer vision (see this recent press release by IEEE). In 2013 I will be a General Chair for CVPR.

My work with the Radiology department has focused on the problem of MR image reconstruction. More technical information is available from the CS Medical Imaging group page.

I have also investigated a number of applications of computer vision, including new methods for content-based access to databases of images, and have developed some simple computer vision techniques to automate program debugging at Microsoft.