Multimedia Information Systems


The course multimedia information aims to give an overview on multimedia information retrieval, multimedia databases and multimedia metadata. The course also took place in summer semesters in 2015 and years previous to that. You can find a page and all the slides of the former courses, like here. A large part of the course is based on the book "Visual Information Retrieval with Java and LIRE" by M. Lux and O. Marques (see here)

Grading and Modalities

Grading is based on 3 main factors with a 1/3 weighting each.

  • Exercises: Do the exercises handed out through the course and finish the exercises with running a linear search on the Ferrari data set for your descriptor (see slides)
  • Project: Choose a project in the context of (visual) information retrieval, multimedia analysis or multimedia information system and implement a solution.
  • Project Presentation: Present your project including motivation, approach and results.

Schedule and Materials

Day Time Place Topic Readings / Exercises Downloads
07.03. 8:30-10:00 E.2.42 Introduction   slides
22.03. 8:30-12:00 E.2.42 Information Retrieval, mmis-ex01.xls, mmis-ex03.txt (R) slides A, slides B
28.03. 10:00-12:00 E.2.69 Retrieval Evaluation I precision-recall plot slides
04.04. 10:00-12:00 E.2.69 Image Features I   slides
25.04. 10:00-12:00 E.2.69 Image Features II   see above
02.05. 10:00-12:00 E.2.69 Image Features III    
23.05. 10:00-12:00 E.2.69 Image Features IV    
30.05. 10:00-12:00 E.2.69 Indexing    
13.06. 10:00-12:00 E.2.69 Deep Learning    
27.06. 10:00-12:00 E.2.69 Student Presentations    


Note that the numbers of the exercises are somewhat messed up, so exercise 3 is named "2" in some slides, exercise 4 is named "3" in nearly all slides.