Multimedia Information Retrieval 2010

IMPORTANT! - Students must register on the class forum -
- (1) Register yourself on the forum;
- (2) Join the Multimedia Information Retrieval 2010 Course
- Contact Bart Thomee, about any problems

Joint Leiden University & TU Delft BioInformatics Course (IN4174)

Period: 2 Feb - 27 April, 2010
Time: 15:45 - 17:30
Place: Rm. 174


Dr. Michael S. Lew, (Lecturer) email: (Email to make an appointment)

Bart Thomee, (Teaching Assistant),

For questions, contact Bart Thomee


Extending beyond the borders of culture, art, and science, the search for digital information is one of the major challenges of our time. Digital libraries, bio-computing & medical science, the Internet, streaming video, databases, cultural heritage collections and peer-2-peer networks have created a worldwide need for new paradigms and techiques on how to browse, search, and summarize multimedia collections.

This course focusses on the area of searching and retrieving multimedia information from digital databases and collections. Examples of multimedia would be X-Ray and MRI scans, general photos, and video.

Requirements: Willingness to learn or already know C, C++ programming languages

(Class participation is part of the grading. As this is a seminar, attendance is mandatory)

- 6 EC for Leiden University Students (presentation and software project)
- 3 EC for TU Delft Students (presentation only); It is possible for Delft students to do the project also.

Class Project

The class project information has been posted on the MIR forum

Recommended Reading: Principles of Visual Information Retrieval, M. S. Lew, Springer, 2001, ISBN: 978-1-85233-381-2

Suggestions for class presentations

- Introduce the problem and main idea - Explain the motivation for the paper
- Cover the main points of the algorithm
- Make sure you have a slide which clearly states the main contribution of the paper at the end
- There should be a little humor in the presentation to make it interesting for the audience


Class 1: 2 Feb - Introduction to Multimedia Information Retrieval

Class 2: 9 Feb - Content Based Retrieval: Color, Texture, and Shape Analysis - Notes

Class 3: 16 Feb - Content Based Retrieval: Similarity and Classification - Notes

Class 4: 23 Feb - Advanced Methods Lecture - Notes

Presentation Assignments

If you are taking this course and your name is not listed below, contact Bart, immediately.

-> Paper/Presentation Assignments are listed below
-> Papers in PDF can be downloaded from
-> For each paper, the presenter's name is first and the Questioners are listed at the end.
-> Presenter's should prepare a 20 minute Powerpoint presentation, which must be posted on the MIR 2010 forum
-> Questioners must ask at least 3 questions each.
-> All students are encouraged to also ask questions.

Class 5: 2 March - Student Presentations - Session 1 (presentations in PowerPoint)
Ji - Locating Key Views for Image Indexing of Spaces - Q:  Nobakht, Gritsenko
Dippel - A Novel Approach to Enable Semantic and Visual Image Summarization for Exploratory Image Search - Q: Smit, Zwet

Class 6: 9 March - Student Presentations - Session 2 (presentations in PowerPoint)
Nobakht - A Framework for Classifier Adaptation and its Applications in Concept Detection - Q: Luiten, Ji
Gritsenko - Unsupervised Modeling and Recognition of Object Categories - Q: Dippel, Smit

Class 7: 16 March - Student Presentations - Session 3 (presentations in PowerPoint)
Smit - Collaborative Learning for Image and Video Annotation - Q: Luiten, Ji
- Large Scale Content Based Audio Retrieval from Text Queries - Q: Dippel, Nobakht

Class 8: 23 March - Student Presentations - Session 4 (presentations in PowerPoint)
Luiten - Outdoors Augmented Reality on Mobile Phone using Loxel Based Visual Feature Organization - Q: Gritsenko, Zwet