Workshop in conjunction with ICCV2009
Sep. 27, 2009
GOAL OF THE WORKSHOP
The goal of the workshop is to share the potential of subspace methods with researchers working on various problems in computer vision, and to encourage interactions which could lead to further developments of subspace methods. The fundamental theories of subspace methods and their applications in computer vision will be discussed at the workshop.
Subspace methods are important for solving many theoretical problems in pattern recognition and computer vision. Also they have been widely used as a practical methodology in a large variety of real applications. Subspace methods have been studied intensively, in particular, in the field of character recognition, contributing to a number of commercial optical character recognition systems. During the last three decades, the area has become one of the most successful underpinnings of diverse applications such as classification, recognition, pose estimation, motion estimation. At the same time, there are many new and evolving research topics: nonlinear methods including kernel methods, manifold learning, subspace update and tracking.
PREVIOUSLY ORGANIZED WORKSHOPS
Prior to this workshop, we have successfully organized three related workshops: an international workshop on subspace methods, Subspace 2007 in conjunction with ACCV2007, and two Japanese workshops, Subspace 2006 and 2008. The number of attendees and submissions for these workshops demonstrate their success. Especially, the Proceedings of the Subspace2007 workshop have been downloaded more than 800 times from the workshopfs website from 38 different countries for the first six months. We believe that Subspace 2009 in conjunction with ICCV will stimulate fruitful discussions among the participants and provide novel ideas for future research in computer vision.
The program is opened on 23, August. Click Here.
Final Camera Ready:
Camera Ready Submission Guidelines and Online Submission Site
Call for papers [PDF]
The topics of interest include, but are not limited to, the following:
- Theoretical foundations of subspace methods
Iijima equation, Watanabe's formulation of CLAFIC theory,
subspace method as degenerated Gaussian, geometry for subspace methods, etc.
- Theoretical extensions of subspace methods
methodology of subspace (PCA, CCA, FA,
nonlinear subspace methods, mutual Subspace Method and their theoretical extensions,
manifold learning, similarity measure with subspace, illumination cone, etc.
- Related technology
Mathematical feature extraction (n-mode SVD), eigenspace method,@
discriminant analysis, subspaces in factorization method
Object recognition, face recognition, Gesture recognition, character recognition,
motion analysis, scene analysis, robot vision, biometrics, anomaly (unusual) detection,
data visualization, other novel applications
Toru Tamaki (Hiroshima University, Japan)
David Suter (The University of Adelaide, Australia)
Björn Stenger (Toshiba Cambridge Research Lab., UK)
Toshiyuki Amano (NAIST, Japan)
Horst Bischof (TU Graz, Austria)
Jun Fujiki (AIST, Japan)
Kazuhiro Fukui (University of Tsukuba, Japan)
Seiji Hotta (Tokyo University of Agriculture and Technology, Japan)
Masakazu Iwamura (Osaka Prefecture University, Japan)
Tae-Kyun Kim (University of Cambridge, UK)
Xi Li (Xifan Jiaotong University, China)
Yi Ma (University of Illinois at Urbana Champaign, USA)
Atsuto Maki (Toshiba Cambridge Research Lab., UK)
Hiroshi Murase (Nagoya University, Japan)
Shree K. Nayar (Columbia University, USA)
Shinichiro Omachi (Tohoku University, Japan)
Bisser Raytchev (Hiroshima University, Japan)
Peter Roth (TU Graz, Austria)
Hitoshi Sakano (NTT CS Laboratories, Japan)
Atsushi Sato (NEC, Japan)
Satoh (National Institute of Informatics, Japan)
Fernando De la Torre (Carnegie Mellon University, USA)
Seiichi Uchida (Kyushu University, Japan)
M. Alex O. Vasilescu (Stony Brook University, USA)
Jakob Verbeek (Inria Rhone-Alpes, Grenoble, France)
Liwei Wang (Peking University, China)
The workshop proceedings will be published as the ICCV main conference DVD.
The submitted papers will be included in the IEEE Digital Library.
By submitting a manuscript to Subspace 2009, the authors assert that it has not been previously published in substantially similar form. Furthermore, no paper which contains significant overlap with the contributions of this paper either has been or will be submitted during the Subspace 2009 review period to either a journal or a conference. For ICCV 2009 we allow dual submissions to ICCV 2009 workshops and the main conference. In case of acceptance, the author will have to decide where the paper should appear (main conference or workshop.
Paper format should be the same as ICCV2009, and page limit is 8 pages. Please refer the ICCV author guidelines and author kit available at ICCV website. Reviewing is double-blind: remove names and affiliations of authors as indicated by the ICCV author guidelines.