---

NEWS: 20 September 2005

The final Lectures Schedule is now available, click >>here<<.

NEWS: 8 September 2005

If you are late but you would like to partecipating to the 5th VIPS Advanced School, you don't have to worry because you can pay directly here when you will arrive. So, what are you waiting for? Send your registration email as soon as possible. See you soon!

---

5th VIPS Advanced School on Computer Vision, Pattern Recognition and Image Processing

Julietta's Home (click >>here<< for more infos about Verona)

September 26-29, 2005 Organized by the Vision, Image Processing and Sound Laboratory Department of Computer Science, University of Verona, Italy

This is the 5th Advanced School organized by the VIPS laboratory, the fifth of a series of advanced lectures on significant topics in Computer Vision, Pattern Recognition, and Image Processing.

These courses are particularly addressed to PhD students, but open to all types of researchers. Each course will typically be held in at most one week and will be focused on one specific topic in order to provide a more productive interaction with the lecturer.

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

This school is titled "Visual Learning and Recognition". Details about the course, contents and the registration procedure are given in the following.

Lecturers

Prof. Horst Bischof

Institut for Computer Graphics and Vision

Technical University, Graz, Austria

Prof. Ales Leonardis

Faculty of Computer and Information Science

University of Ljubljana, Slovenia

Course title

Visual Learning and Recognition

Contents

• Introduction
  

• Generic Issues
  

  • Cognitive visual systems
  • Complexity of visual recognition
  • Generative vs. discriminative methods

• Visual Representations
  

  • Evolution of object models (recognition methods)
  • Generic (category-based) versus exemplar-based (geons, SQ, generalized cylinders)
  • Object-centered versus viewer-centered (perceptual grouping, features -ease of indexing)
  • Shape-based, appearance-based

• Global Representations
  

  • Subspace Methods
  • PCA, LDA, ICA, CCA, NMF, SVM, Kernel Methods
  • Robust Recognition (occlusions, varying illumination, scale, cluttered background, etc.)
  • Mixture Representations (Multiple Eigenspaces, Split ASM)

• Local Representations
  

  • Distinctive Regions (Harris, Hessian, Harris Affine, MSER, DOG,IBR,Kadir & Brady)
  • Local Feature (SIFT, Shape Context, Steerable Filters, Diff. Invariants)
  • Performance Evaluation
  • Extensions (Tracking, Constellations)

• Issues in Visual Learning
  

  • Robust Learning
  • Incremental Learning
  • Learning with Minimal (No) Supervision --> Conservative Learning

• Specific Approaches/Applications with possible exercises
  

  • Subspace Methods & Mobile Robotica
  • Trainable models for object class detection
  • Distinctive image features from scale-invariant keypoints (SIFT, Lowe)
  • Recognition Demos

If you are interested, you must send an email to vips_school@sci.univr.it in which you ask for participation. Please, state your identity and your status (undergraduate, PhD student, other) and wait for the confirmation email. The ultimate deadline is September 14, 2005.

Attached to our confirmation email you will find a registration form to print, compile and send together with a proof of the payment by fax before September 14, 2005, to the following no. +39 045 8027068, to the attention of Prof. V. Murino, 5th 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).

Important Dates

Accomodations

The accomodation costs are not covered by the Course Fee. However, we have made agreements with some convenient hotels and you can find a list of available places here.
If you wish to take advantage of these opportunities please remember to notify to the hotel that you are attending our school.

Information on how to reach our department are presented in this page.

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

Credits
Last revision: August 8, 2005