The problem of analysing images of objects, especially against dense background clutter, is challenging. Uncertainty in the positions of visible features and ambiguity arising from the clutter, call for a probabilistic treatment. There is a great deal of interest currently in "generative" approaches: first take a constructive model that could account for how the image was composed; then find an inference engines to do the analysis.

This talk will illustrate the generative modelling paradigm with several examples in vision. Applications include audiovisual fusion, video superresolution and interactive segmentation.

Bio: Andrew Blake graduated in 1977 from Trinity College, Cambridge with a B.A. in Mathematics and Electrical Sciences. After a year as a Kennedy Scholar at MIT and two years in the defence electronics industry, he studied for a doctorate at the University of Edinburgh which was awarded in 1983. Until 1987 he was on the faculty of the department of Computer Science at the University of Edinburgh and a Royal Society Research Fellow. From 1987 to 1999, he has been on the faculty of the Department of Engineering Science in the University of Oxford, where he ran the Visual Dynamics Research Group, became a Professor in 1996, and and was a Royal Society Senior Research Fellow for 1998-9. In 1999 he moved to Microsoft Research Cambridge as Senior Researcher working in Machine Learning and Perception, while continuing to be associated with the University of Oxford as Visiting Professor of Engineering.