Back to welcome page





Misc







Brochure


VIPS Advanced School on
Computer Vision, Pattern Recognition
and Image Processing


NEWS: 24 May 2004

The school is now over and it's been a great success! We wish to thank you prof. Frey for being a great host, and all the people who came to attend to our first school. Thank you all for the wonderful experience, you made all our efforts worthwhile!

Click >>here<< to access all the materials of this course as well as photographs of the attendants.


Click here for a tourist tour!
May 17-20, 2004
Organized by Vision, Image Processing and Sound Laboratory
University of Verona - Computer Science Department

This school would like to be the first of a series of seminars, aiming at offering advanced lectures on significant topics related to Computer Vision, Pattern Recognition, and Image Processing.
These schools are particularly addressed to PhD students, but all types of researchers are welcome.
They will typically hold one week on one specific topic, so that audience can install a more productive interaction with the lecturer.

The maximum number of participants is limited to 50 persons. In case of a larger number of applicants, priority will be given to PhD students.

This first school focuses on the statistical approach in computer vision, analyzing the graphical models for learning and inference with related applications.

Note for PhD students: we anticipated the possibility of an exam on friday 21 for those requiring a credit, but we decided against. The credit will be appointed upon completion of a given homework in the following weeks.

Directors

Vittorio Murino
Andrea Fusiello

Local Organizers

Andrea Colombari
Marco Cristani
Michela Farenzena

Lecturer

Prof. Brendan J. Frey

University of Toronto, Canada

Course Title:

Bayesian Networks and Algorithms for Inference and Learning: Applications in Computer Vision, Audio Processing, and Molecular Biology

Description:

Algorithms for automatically analyzing images, video, audio, communication signals, biological sequences, text, and other types of data should take into account the uncertain relationships between inputs, intermediate representations, and outputs. Probability theory can account for these uncertainties, and provides a way to pose information processing problems as the computational task of finding an appropriate probability model and computing conditional probabilities using the model. Complex probability models for real-world applications often involve millions of random variables and intractable density functions, so probabilities cannot be computed using straightforward approaches.

This course examines the fundamental concepts of graph-based formulations of complex probability models and introduces computationally efficient techniques for computing probabilities and estimating parameters in these models. Although the course is a "fundamentals" course, we will study several impressive real-world applications.

Day 1
Bayesian networks, Markov random fields and factor graphs. Computing probabilities in graphical models, the elimination algorithm and the sum-product algorithm. Generative models. Case study: Computer Vision.

Day 2
Learning observed graphical models, the exponential family. Parameterized models, parameters as variables, models for classification, regression and clustering. Learning partially unobserved graphical models, free energy, iterative conditional modes, the EM algorithm. Case study: Molecular Biology.

Day 3
Mixtures of Gaussians, HMMs, the multivariate Gaussian, factor analysis, linear dynamic systems, Kalman filtering and smoothing, learning linear dynamic systems. Variational techniques, the sum-product algorithm in graphs with cycles, Bethe free energy. Case study: Audio Processing.

Day 4
Monte Carlo methods, rejection sampling, adaptive rejection sampling, importance sampling, particle filters, Markov chain Monte Carlo methods, Gibbs sampling, Metropolis algorithm. Wrap-up.

Lecture Schedule:

Monday 10.00-13.00 14.30-17.30
Tuesday 10.00-13.00 14.30-17.30
Wednesday 10.00-13.00 14.30-17.30
Thursday 10.00-13.00 14.30-17.30

Course fee:

150 euro for students, researchers, and other people working directly for a university
300 euro for anybody else

Registration

We have received a great number of registrations hence, from now on, you are requested to:

  • send us an email in which you ask for partecipation

  • wait our confirmation

  • after confirmation do the following steps:
    download the registration form, print it, fill each field (in capital letters), and send it with the money order by fax before April 30, 2004, to the following no. +39 045 8027068, to the attention of Prof. V. Murino, VIPS School on Computer Vision, Pattern Recognition, and Image Processing.

The proposed payment method is bank wire transfer (all necessary data are in the form). The payment must be made by April 30, 2004.

NOTE (for NOT italian people only): in the previous registration form the IBAN was wrong, please download the updated version.

Important dates:

Registration deadline:

April 30, 2004

Course Fee payment deadline:

April 30, 2004

School:

May 17-20, 2004

Accomodations

NOTE: the accomodation costs are not included in the Course Fee.
A list of possible accomodation can be found here

How to reach us

If you need to reach our department please consult this page.

Other Information

For any other information, please send an email to school_info@zeus.sci.univr.it

Top of the page

Credits
Last revision: 19 April 2004