Multimedia Computing and Computer Vision Lab

Login  

Home

     

Courses

     

People

     

Research

     

Publications

     

Student Theses

     

Source Code / Datasets

     

Contact

     

WS 08/09: Media Mining I

From Multimedia Computing Lab - University of Augsburg


Instructors: Prof. Dr. Rainer Lienhart, Eva Hörster
Time Lecture: Tue, 8:15-9:45 and Thu, 12:15-13:45, room 207 (Eichleitnerstr.); starts Oct., 14 2008 at 8:15am sharp
Time Exercise: Wed, 12:15-13:45, room 202 (Eichleitnerstr.); first exercise will be on Oct, 29th 2008
Please register with LectureReg
Credits: 6 SWS, Schein: yes, LP: 9
Exam: Thursday, 12 Feb 2009, 10:00am – 12:00pm, Room306 (MMC Lab); The following tools are allowed: Non-programmable calculator, two A4 pages of handwritten notes, something to drink and to eat, ballpen(s). Everything else is forbidden (especially no cellular phones).

In order to be admitted to the final exam, students are required:

  • to score at least 50% of the points archievable on the weekly assignments
  • to attend the weekly exercise session (Wednesday, 12:15-1:45pm). Students are allowed to miss the exercise session at most three times.
Multimedia Teilbereiche: Multimedia-Methoden, Multimedia-Anwendungen
Synopsis: The course addresses all aspects of computer algorithms that let a computer see, hear, learn, and understand audio-visual and multimedia data in the small and large scale. Small scale refers to individual media files or streams, while large scale refers to mining the web.

Mining media data is inherently a multidisciplinary field. Thus, the course will lay down the foundations of

  • Machine learning,
  • Image/video processing, and
  • Media content analysis.

The learned concepts will be illustrated by successful examples in practice. The accompanying exercises will contain some hands-on experiences. Towards the end of the course more advanced topics in object detection and object recognition will be addressed.



Announcements

  • The exam will be written on Thursday, 12 Feb 2009, 10:00am – 12:00pm.

Important Comments

  • All specified reading notes are relevant for the exams independent on how thoroughly they have been discussed during the lecture. Thus read them carefully.

Literature

  1. Mandatory reading: M. Mitchell. Machine Learning. McGraw-Hill Science/Engineering/Math; Chapters 1-8; (http://www-2.cs.cmu.edu/~tom/mlbook.html)
  2. Mandatory reading: Jeff Hawkins, Sandra Blakeslee. On Intelligence. B&T; Auflage: Reprint (August 2005), ISBN-13: 978-0805078534
  3. Bernd Jähne. Digital Image Processing. Springer Verlag.
  4. David A. Forsyth and Jean Ponce. Computer Vision: A Modern Approach. Prentice Hall, Upper Saddle River, New Jersey 07458.( http://www.cs.berkeley.edu/~daf/book.html )
  5. Martin Schader and Stefan Kuhlins. Programmieren in C++. Springer-Verlag. ISBN 3540637761
    This is a perfect resource for all your questions relating C/C++; recommended if you are not skilled in C/C++

Online Material

Date Content Slides Exercise
14.10. 1-01 Introduction PDF
16.10. 2-01 Introduction to Machine Learning PDF PDF ZIP
21.10. 2-02 Concept Learning PDF
28.10. 2-03 Decision Tree Learning PDF PDF
30.10 2-04 Artificial Neural Networks PDF
04.11 2-05 Evaluating Hypotheses PDF PDF
11.11. 2-06 Bayesian Learning PDF PDF ZIP
13.11 2-07 Computational Learning Theory PDF
18.11 2-08 Instance Based Learning PDF PDF
20.11 2-09 Reinforcement Learning PDF
25.11 / 27.11 / 02.12 3-01 Dimensionality_Reduction_Techniques PDF PDF Data
04.12 / 9.12 3-02 ShotDetection PDF PDF
11.12 3-03 Scene_and_Locale_Detection PDF PDF
16.12/18.12 3-04 Commercial Detection PDF PDF
8.1./13.1./15.1. 3-05 ObjectDetection PDF PDF
20.1./22.1. 3-06 Local Features PDF PDF
22.1./26.1 3-07 Salient-Features PDF
26.1./29.1. 3-08 Image Search PDF PDF Video
29.1./3.2. 3-09 Text Localization & Segmentation in Images, Web PDF