DAGM Workshop on
Unsolved Problems in Pattern Recognition and Computer Vision
Saarbrücken, September 3, 2013
In Conjuction With
35th German Conference on Pattern Recognition (GCPR 2013)
Location
Building E1.4, Ground Floor, Seminar Room 024. Venue info here.
Call for Contributions
The technical committee of the German Association for Pattern Recognition (DAGM) invites to this workshop that provides a platform for discussing the major challenges of pattern recognition and computer vision in the next years. The event is an opportunity to take a step back from the daily business and debate about the currently most relevant problems in the field and emphasize the most promising future research directions. Participants are kindly requested to submit an extended abstract of not more than two pages, which sketches an open problem in the respective field or in related application areas. The proposal should contain:
- a specification of the problem and a characterization of its relevance for research in the field of interest and its application areas, and – if applicable – its societal or economic implications
- cause of the problem; what deficits in our field are causing this problem
- relations to the state-of-the-art in our field; which research initiatives would be necessary to devise a solution
The technical committee will select a small number of proposals to be presented in talks. Plenty of time is planned to allow for controversial panel discussions on the presented problems.
Jitendra Malik (UC Berkeley) and Jean-Michel Morel (ENS Cachan) have agreed to actively participate in the workshop.
Important Dates
May 31, 2013: Submission of extended abstracts (≤ 2 page) via email to
Bernt Schiele
June 14, 2013: Notification of participants
Sept 3, 2013: Workshop in Saarbrücken
Confirmed list of speakers
| Name | Institution | Title | Time |
|---|---|---|---|
| Jitendra Malik | U Berkeley | Computational Architectures for Visual Recognition. Slides | 09:00 - 09:30 |
| Bastian Leibe | RWTH Aachen | Next Challenges in Dynamic Scene Understanding: Beyond Tracking. Slides | 09:30 - 10:00 |
| Joachim Denzler, Erik Rodner, Paul Bodesheim, Alexander Freytag | U Jena | Beyond the closed-world assumption: The importance of novelty detection and open set recognition. Abstract Slides | 10:00 - 10:30 |
| Thomas Brox | U Freiburg | The mirage of a general purpose robot and the combinatorial explosion Abstract Slides | 11:00 - 11:30 |
| Uwe Franke | Daimler | The Quest for Robustness and Accuracy - Mission Impossible? Abstract Slides | 11:30 - 12:00 |
| Daniel Kondermann | U Heidelberg | Ground Truth Generation Abstract Slides | 12:00 - 12:30 |
| Jan-Michel Morel | ENS Cachan | What matters more for image matching and the comparison of descriptors: invariance and causality requirements or repeatability criteria? Abstract Slides | 14:00 - 14:30 |
| Joachim Buhmann | ETH Zurich | Decision making under uncertainty: how Informative is your algorithm with noisy inputs and internal computation errors. Abstract Slides | 14:30 - 15:00 |
| Carsten Rother | TU Dresden | An Open Challenge in Computer Vision: From Inverse Rendering to Scene Understanding. Slides | 15:00 - 15:30 |
| - | - | Podium Discussions | 16:00 - 17:30 |
Program Committee
H. Bischof, TU Graz
J.M. Buhmann, ETH Zurich
A. Dengel, DFKI
U. Franke, Daimler AG
M. Hein, Universität des Saarlandes
R. Koch, Universität Kiel
H. Mayer, Universität der BW München
B. Rosenhahn, Universität Hannover
B. Schiele, MPI for Informatics (workshop chair and local organization)
J. Weickert, Universität des Saarlandes
