Mathematical Sciences Research Institute - Emphasis Week on Learning and Inference in Low and Mid Level Vision

Note: All lectures are to be held in the MSRI lecture hall
2850 Telegraph Avenue, second floor.

Low level vision addresses the issues of labelling and organising image pixels according to scene related properties - known as intrinsic images - such as motion, contrast, relief, texture and reflectance. Such properties are hard to capture by hand-constructed models, and so there has been a considerable movement towards specifying them "generatively": models involving cascades of random variables are constructed as explanations of images. Details of the models are filled in by learning parameters from labelled training data. New inference algorithms such belief propagation, variational inference, particle filtering, min cut and others are used to apply these models to image analysis. Already some very promising results have been obtained, for example in segmentation, in stereo vision and in analysis of texture. This workshop will be a forum for some of the latest results and thinking in this area to be presented and explored.

Program Schedule

Monday 21st Feb
2.30-3.30: Prof Eero Simoncelli, New York University. Image statistics, efficient coding, and visual perception
4.15-5.15: Prof David Mumford, Brown University. Is there a simple statistical model of generic natural images?

Tuesday 22nd Feb
09.30-10.30: Prof Michael Black, Brown University. Image statistics and low level vision
11.00-12.00: Dr Andrew Fitzgibbon, U. Oxford. Applied natural image statistics
2.00-3.00: Prof Alyosha Efros, CMU. Data-driven vision: learning by lookup
3.30-4.30: Prof Brendan Frey, U. Toronto. Using data-based parameterizations to efficient learn hierarchical models.

Wednesday 23rd Feb
09.30-10.30: Prof Bill Freeman, MIT. Learning to separate shading from paint
11.00-12.00: Prof Song Chun Zhu, UCLA. From primal sketch to 2 1/2 Sketch -- shape from shading, stereo, and motion
2.00-3.00: Prof Andrew Blake, Microsoft Research. Fusion of colour, contrast and stereo for bi-layer segmentation
3.30-4.30: Dr Michael Isard, Microsoft Research. Estimating stereo and optic flow using loopy belief propagation

Thursday 24th Feb
09.30-10.30: Prof Daniel Huttenlocher, Cornell. Speeding up belief propagation for low and mid level vision
11.00-12.00: Prof Yair Weiss, Hebrew University. Linear programming belief propagation and low-level vision
1.30-2.30: Prof Alan Yuille, UCLA. Beyond BP? Approximate Inference and the DLR equations
3.00-4.00: MSRI mathematics seminar for those who wish to attend
4.30-5.30: Prof Ramin Zabih, Cornell. Graph cut energy minimization algorithms for computer vision

Friday 25th Feb
09.30-10.30: Prof Julian Besag and Raphael Gottardo, U. Washington. Microarray imaging with MRFs and MCMC
11.00-12.00: Prof David Donoho, Stanford. Scaling properties of higher-order image statistics: implications for edge/object detection

Follow this link to read about the new U.S. visa requirements

Currently Available Videos

Eero Simoncelli , Image Statistics, Efficent Coding and Visual Perception. February 21,2005, 02:30 PM to 03:30 PM
David Mumford , Is There Simple Statistical Model of Generic Natural Images? February 21,2005, 03:00 PM to 04:00 PM
Andrew Fitzgibbon , Applied Natural Image Statistics February 22,2005, 11:00 AM to 12:00 PM
Alexei Efros , Data-driven Vision: Learning by Lookup February 22,2005, 02:00 PM to 03:00 PM
Brendan Frey , Using Data-based Parameterizations to Efficient Learn Hierarchical Models. February 22,2005, 03:30 PM to 04:30 PM
Song Chun Zhu , From Primal Sketch to 2 1/2 Sketch -- Shape from Shading, Stereo, and Motion. February 23,2005, 12:00 AM to 12:00 AM
William Freeman , Learning to Separate Shading From Paint . February 23,2005, 09:30 AM to 10:30 AM
Michael Black , Image Satistics and Low Level Vision. February 23,2005, 09:30 AM to 10:30 AM
Andrew Blake , Fusion of Colour, Contrast and Stereo for Bi-layer Segmentation. February 23,2005, 02:00 PM to 03:00 PM
Michael Isard , Estimating Stereo and Optic Flow Using Loopy Belief Propagation. February 23,2005, 03:30 PM to 04:30 PM
Yair Weiss , Linear Programming, Belief Propagation and Low-level Vision. February 24,2005, 12:00 AM to 12:00 PM
Yair Weiss , Linear Programming, Belief Propagation and Low-level Vision. February 24,2005, 12:00 AM to 12:00 PM
Dan Huttenlocher , Speeding up Belief Propagation for Low and Mid Level Vision February 24,2005, 09:30 AM to 10:30 AM
Alan Yuille , Beyond BP? Approximate Inference and the DLR Equations. February 24,2005, 01:30 PM to 02:30 PM
Ramin Zabih , Graph Cut Energy Minimization Algorithms for Computer Vision. February 24,2005, 04:30 PM to 05:30 PM
Julian Besag, Raphael Gottardo , Microarray Imaging with MRFs and MCMC . February 25,2005, 09:30 AM to 10:30 AM
Julian Besag, Raphael Gottardo , Microarray Imaging with MRFs and MCMC . February 25,2005, 09:30 AM to 10:30 AM
David Donoho , Scaling Properties of Higher-order Image Statistics: Implications for Edge/Object Detection. February 25,2005, 11:00 AM to 12:00 PM

You can find videos of other workshops and events on our VMath - Streaming Video page.

For more information:
Questions about this workshop should be sent either by email to

298@msri.org

or by regular mail to:

Emphasis Week on Learning and Inference in Low and Mid Level Vision Mathematical Sciences Research Institute 17 Gauss Way, Berkeley, CA 94720-5070. USA

The Institute is committed to the principles of Equal Opportunity and Affirmative Action.

Back to Workshop Listing

Want to be kept updated on upcoming events? Then Click Here to Subscribe to Our Newsletters!