My main research interests are in computer vision, artificial intelligence, machine learning and discrete algorithms. I have worked on a range of different problems within computer vision, including the “low-level” problem of image restoration, the "mid-level" problem of image segmentation, and the “high-level” problem of object recognition. This has led me to consider connections between computer vision and artificial intelligence to a variety of areas including combinatorial optimization, stochastic models, machine learning, and natural language processing.