Utrecht Summer School in Computing Science: Multimedia Retrieval
20-24 August, 2007

General:
This course is about the search and retrieval of images, music, and 3D scenes.
Not only the perceptual and cognitive aspects, but also many of the algorithmic
and performance aspects are still badly understood. Relevant issues are the
design of dissimilarity measures that have desired properties, and the
development of efficient algorithms. Apart from provable properties of
individual algorithms, the experimental verification of the performance of a
complete retrieval system is important to analyse merits and drawbacks of
certain approaches, and to compare various techniques. The course consists
of lectures as well as exercises and hands-on experience.

Course leader: Dr. Remco Veltkamp, Remco.Veltkamp@cs.uu.nl

Lecturers: Prof. H. Alt, dr. Jorg Garbers, R. van Leuken, dr. S. Marini,
Ludmila Scharf, Sven Schulz, dr. M. Spagnuolo, dr. R. Veltkamp, dr. Anja Volk,
dr. F. Wiering.

Organized by:
Department of Computer Science.

Target group:
Graduate students (advanced master students and PhD students in
the early stage of their study) with a background in computer science.

Maximum number of participants: 30

Aim of the course:  This course provides fundamental knowledge and hands-on
experience on the basics as well as on research issues in Multimedia Retrieval.

Fee: €425 (includes course materials and housing).

Scholarships: A limited number of scholarships is available.

Information:
Graduate School of Natural Sciences
Ms Leonie Silkens
T: +31 30 253 2284
E: International.Office@phys.uu.nl

Online application:
http://www.science.uu.nl/summerschools

Deadline for application:
1 May 2007

Program:

Monday August 20
Topic: Issues in Multimedia Retrieval
Lecturer: Remco Veltkamp, Utrecht University
We will address perceptual issues, as well as formal properties of features,
similarity measures, and algorithms.

Tuesday August 21
Topic: Retrieval of Trademark Images
Lecturers: Helmut Alt, Ludmila Scharf, Sven Schulz, Free University Berlin
In trademark images, shape is a dominant feature. We will address shape
similiarity measures and algorithms to compute them.

Wednesday August 22
Topic: Retrieval of Music
Lecturers: Frans Wiering, Anja Volk, Jorg Garbers, Utrecht University
Two main groups of Music Information Retrieval (MIR) systems for content-based
searching can be distinguished, systems for searching audio data and systems
for searching notated music. This lecture will primarily focus on searching
notated music

Thursday August 23
Topic: Retrieval of 3D Objects
Lecturers: Michela Spagnuolo, Simone Marini, CNR-IMATI
Three-dimensional shape retrieval is fundamentally different from 2D shape
retrieval. Most 2D methods do not generalize directly to 3D. This is due to
the different nature of the content: descriptors used for 2D images are
concerned with color, textures, and properties that capture geometric details
of the shapes segmented in the image.

Friday August 24
Topic: Indexing
Lecturer: Reinier van Leuken, Utrecht University
Indexing data structures and search algorithms are necessary to make the
search more efficient than sequential browsing through large collections.