The student should have taken a course in image processing and be fluent in C/C++ programming.
In this course we focus on a scientific view of the field of multimedia search and retrieval as represented by top major conferences and journals.
Generally speaking, this course covers the technologies that will be used by Google and Bing in the future.
This course provides an introduction to the state-of-the-art and leads to a final project that will be distributed (or placed online) to the public.
We introduce, discuss and develop the leading paradigms and techniques on how to browse, search, and summarize multimedia datasets (e.g. the WWW).
At the end of the Multimedia Information Retrieval course, the student should be able to
- understand the fundamental principles of information retrieval
- analyze an information retrieval system with regard to strengths and weaknesses and potential areas for improvements
- explain the differences between modern search engines and database systems.
- have insight into traditional and state-of-the-art multimedia features
- have insight into scientifically evaluating an information retrieval system
- have insight into the integration of intelligent algorithms into the retrieval process
- have insight into the limits and challenges of modern multimedia information retrieval systems
- build a modern multimedia information retrieval system which addresses contextual requirements.
The most recent timetable can be found at the students' website.
Mode of instruction
- student discussions
- homework and software assignments
The final grade is composed of
(1) 50% for Paper Presentation/Seminar (class participation & questions & homework).
(2) 50% for Software Assignments (25%) & Final Project (25%).
Assignments turned in late: grade penalty of -1 per 24 hours (1 day)
Source code for assignments must include instructions for compiling and execution in the machines in rooms 302, 303. This is necessary for grading/evaluating the work by the class organizers.
As this is a seminar, attendance is mandatory
University Leiden students do a presentation and workshop/project for 6 ECTS.
TU Delft students are not required to do the final project for 3 ECTS.
- Reading: Principles of Visual Information Retrieval, M. S. Lew, Springer, 2001, ISBN: 978-1-85233-381-2
- Research papers from recent ACM conferences and journals
- You have to sign up for courses and exams (including retakes) in uSis. Check this link for information about how to register for courses.