Department of Information and Computing Sciences

Departement Informatica Onderwijs
Bachelor Informatica Informatiekunde Kunstmatige intelligentie Master Computing Science Game&Media Technology Artifical Intelligence Business Informatics

Onderwijs Informatica en Informatiekunde

Vak-informatie Informatica en Informatiekunde

Multimedia retrieval

Website:website containing additional information
Course code:INFOMR
Credits:7.5 ECTS
Period:period 1 (week 36 through 45, i.e., 6-9-2006 through 10-11-2006; retake week 1)
Timeslot:C
Participants:up till now 34 subscriptions
Schedule:Dit is een oud rooster!
formgrouptimeweekroomteacher
college   Mon 13-1537-44 BBL-471
Thu 09-1136-44 BBL-471
lecture          Remco Veltkamp
 
Contents:Multimedia retrieval is about the search for and delivery of multimedia documents: images, sound, video, 3D scenes, and the combination of these. This course deals with the technical aspect of multimedia retrieval: techniques, algorithms, and data structures for search query formulation, media description, matching of descriptions, indexing, visualization of retrieval results, and relevance feedback.
Literature:M. Lew (ed.). Principles of Visual Information Retrieval. Springer 2001. The slides of the lectures are made available.
Course form:A number of lectures, an experimentation assignment.
Exam form:A written exam about the lectures (50%), experimentation assignment (50%).
Minimum effort to qualify for 2nd chance exam:To participate in the retake of the exam, the original grade must be at least 4.
Description:During a number of initial lectures, a critical amount of knowledge is provided about he technical aspect of multimedia retrieval: techniques, algorithms, and data structures for search query formulation, media description, matching of descriptions, indexing, visualization of retrieval results, relevance feedback, etc. In order to experimentally verify various techniques, we will experiment with SIDESTEP - Shape-based Image Delivery Statistics Evaluation Project, a web-based experimentation platform for content-based retrieval. It allows to experiment with different types of features, matching algorithms, and evaluation statistics.
wijzigen?