Multimedia Computing and Computer Vision Lab












Student Theses


Source Code / Datasets




SS 10: Seminar Videoverarbeitung

From Multimedia Computing Lab - University of Augsburg

Registration is closed!


Title: Seminar: Videoverarbeitung
Instructors: Prof. Dr. Rainer Lienhart, Christian Ries
Time and Place: Wendesday, 14:00 - 15:30, Room: 1020N
First Meeting: Wendesday, 21. April 2010
Credits: 2 SWS, 4 LP
Multimedia Teilbereiche: Multimediale Informationsverarbeitung, Multimedia Methoden,
Multimedia Anwendungen, Systemnahe Grundlagen von Multimedia
Language: German
Possible follow-ups: Diploma thesis, Master thesis, Bachelor thesis


The results are now registered in LectureReg


This seminar covers a variety of topics in video processing. We will focus on human pose estimation, tracking, content analysis, and action recognition in videos. The goal is to learn both about these interesting topics as well as about how to give a scientific talk and to write a report.

Grading Policy

  • Presentation in class: 25 min talk, additional 5-10 min questions and discussion
  • Written report (LaTeX) on the topic presented
  • Preparation: every student must read the papers discussed in class in advance
  • Participation in class


Veranstaltung wird auf Deutsch gehalten (trotz der englischsprachigen Folien und Literatur)
Abgabe der Seminararbeit in Deutsch oder Englisch möglich.


Description File
Example LaTeX template ZIP


Date Lecturer Topic MUST read *before* lecture
21.04. Christian Ries Einführung PDF
19.05. Georg Döhring Video Completion by Motion Field Transfer Link
19.05. Michael Mair Video Copy Detection by Fast Sequence Matching Link
26.05. vacant
26.05. El Mostapha Kanoune Pose primitive based human action recognition in videos or still images Link
09.06. Elnaz Alyari Pose Search: retrieving people using their pose Link
09.06. Michael Lugmair Face Tracking and Recognition with Visual Constraints in Real-World Videos Link
16.06. vacant A Probabilistic Ranking Framework using Unobservable Binary Events for Video Search Link
16.06. Ulrich Berkmüller Pose and Illumination Invariant Registration and Tracking for Video-based Face Recognition Link
23.06. vacant Identifying Relevant Frames in Weakly Labeled Videos for Training ConceptDetectors Link
23.06. Claudius Hauser Recognizing Realistic Actions from Videos “in the Wild” Link
30.06. Jürgen Weichenmeier Automatic retrieval of visual continuity errors in movies Link
30.06. Christoph Lassner Bilattice-based Logical Reasoning for Human Detection Link
07.07. vacant Web-based Information Content and its Application to Concept-Based Video Retrieval Link
07.07. Petar Hristov Trajectory Based Event Tactics Analysis in Broadcast Sports Video Link

 ??.??. vacant Organizing Rushes Video by Visually Similar Setting Link
 ??.??. vacant Using Cross-Media Correlation for Scene Detection in Travel Videos Link
 ??.??. vacant Exploring Inter-concept Relationship with Context Space for Semantic Video Indexing Link
 ??.??. vacant SURFTrac: Efficient Tracking and Continuous Object Recognition using Local Feature Descriptors Link