Seminar on Current Works in Computer Vision

Prof. Thomas Brox

Computer Vision is a very active research field with many practical applications, for instance in quality control, robotics, or driving assistance systems. The ultimate goal of Computer Vision is to imitate the great capabilies of the human visual system, allowing the computer not only to record images but also to interpret them. Research is still far from this goal, but significant progress has been made in recent years.
In this seminar we will take a detailed look at the most interesting recent works that have been published at the latest Computer Vision conference (CVPR 2011). You will read a number of research papers published at this conference. For each paper there will be one person, who performs a more detailed investigation of the research work and its background and gives a presentation. The presentation is followed by a discussion with all participants about the merits and limitations of the respective paper. You will learn to read and understand contemporary research papers, to give a good oral presentation, to ask questions, and to openly discuss a research problem.

(2 SWS)
Wednesday, 10-12am,
Room: HS 02-017, Building 052
Contact person: Robert Bensch

Beginning: Wednesday, Oct 26, 2011
Introduction and allocation of seminar topics.

ECTS Credits: 4

Recommended semester:

Requirements: any proseminar

Remarks: This course is offered to both Bachelor and Master students. Master students should give their presentation in English (to practise their English presentation skills), Bachelor students may present in German. The discussion can be in English and German.

Topics will be assigned in the first meeting. Please register for the seminar online before the first meeting. Just in case there are more interested students than places, places will be assigned by motivation in the first meeting, NOT by date of registration to avoid that people grab a topic and then jump off during the semester. So please have a coarse look at all available papers to make an informed decision in the first meeting.

Slides of first session with instructions for a good presentation


Date   Topic Paper Questions  Presenting student   Slides   Advisor
23.11. Diffeomorphic Image Registration Song et al., Murphy et al., Questions Sven Wehner pdf Benjamin Drayer
30.11. Human pose from depth images Shotton et al. Questions Jan Mattner pdf,vid Phillip Chlap
07.12. Datasets and benchmarking Torralba-Efros Questions Nikolaus Mayer pdf Kun Liu
14.12. Structure from motion Crandall et al. Questions Nikolas Engelhard pdf Benjamin Ummenhofer
21.12. Video segmentation Lezama et al. Questions Thomas Rinklin pdf Robert Bensch
11.01. Pose and action recognition with poselets Maji et al. Questions Alexander Fix pdf Dominic Mai
18.01. Shape from shading Barron-Malik Questions Andreas Peer pdf Qing Wang
25.01. Segmentation Jegelka-Bilmes Questions Claire Legendre pdf Thorsten Schmidt
01.02. Object learning Fathi et al. Questions Karina Fitriani Fatimah pdf Margret Keuper
08.02. Face recognition Belhumeur et al. Questions Mauricio Munoz pdf Maja Temerinac-Ott
15.02. Articulated part detection Yang-Ramanan Questions Andreas Behr pdf Naveen Shankar Nagaraja