IMPORTANT INFORMATION

THIS IS THE WEB SITE OF THE 1ST WORKSHOP HELD IN 2011.

THE WEB SITE OF THE 2ND WORKSHOP TO BE HELD IN CONJUNCTION WITH ICCV 2013 CAN BE FOUND HERE:

http://campar.in.tum.de/view/FourDMod13/WebHome

WORKSHOP DESCRIPTION

Modeling shapes that evolve over time, analyzing and interpreting their motion has been a subject of increasing interest of many research communities including the computer vision, the computer graphics and the medical imaging community. Recent evolutions in acquisition technologies including 3D depth cameras (Time-of-Light and Kinect), multi-camera systems, marker based motion capture systems, ultrasound and CT scans have made those communities consider capturing the real scene and their dynamics, create 4D spatio-temporal models, analyze and interpret them. A number of applications including motion capture, dynamic shape modeling and animation, temporally consistent 3D reconstruction, motion analyzes and interpretation have emerged. The purpose of this workshop is to provide a venue for researchers, from various communities, working in the field of modeling dynamic scenes from various modalities to present their work, exchange ideas and identify challenging issues in this domain.

SPONSORS

This workshop is sponsored by PASCAL2 NETWORK , 4DViews , Technicolor .

Program

Time	Papers
08:40	Introduction
08:45	Invited talk: On Modeling and Estimating Human Body Shape, Michael Black
Session	Shape Analysis
09:30	The Wave Kernel Signature: A Quantum Mechanical Approach to Shape Analysis, Mathieu Aubry, Ulrich Schlickewei, Daniel Cremers, Department of Computer Science, TU Munich.
09:55	3D Dynamics Analysis in Teichmuller Space, Wei Zeng, Xianfeng,David Gu, Department of Computer Science, Stony Brook University, Stony Brook, NY 11794, USA Mathematics Science Center, Tsinghua University, Beijing 100084, China.
10:20	Coffee break
Session	Shape and motion
10:50	A Pixel-Based Approach to Template-Based Monocular 3D Reconstruction of Deformable Surfaces, Abed Malti, Adrien Bartoli, Toby Collins, ALCoV-ISIT, Universite d’Auvergne Clermont-Ferrand, France.
11:15	FEM Models to Code Non-Rigid EKF Monocular SLAM, Antonio Agudo, Begona Calvo, J. M. M. Montiel Universidad de Zaragoza, Spain.
11:40	Joint Reconstruction of 3D Shape and Non-rigid Motion in a Region-Growing Framework, Ye Liu, Yan Qiu Chen, School of Computer Science, Fudan University, Shanghai, China.
12:05-13:35	Lunch break
13:35	Invited talk: Performance Capture - Reconstructing and Synthesizing Models of The World in Motion , Christian Theobalt
Session	Motion capture
14:20	Motion Capture from Dynamic Orthographic Cameras, Magnus Burenius, Josephine Sullivan, Stefan Carlsson, CVAP, Royal Institute of Technology (KTH), S-100 44 Stockholm, Sweden.
14:45	3D Reconstruction of Bat Flight Kinematics from Sparse Multiple Views, Attila J. Bergou, Sharon Swartz, Kenneth Breuer, Gabriel Taubin, Brown University, Providence RI, USA.
15:10	Break
Session	Reconstruction
15:25	Fast Volumetric Visual Hull Computation, Oliver Grau, BBC Research & Development.
15:50	Multiview Projectors/Cameras System for 3D Reconstruction of Dynamic Scenes, Ryo Furukawa, Hiroshima City University, Hiroshima, Japan, Ryusuke Sagawa, National Institute of Advanced, Industrial Science and Technology, Tsukuba, Japan, Amael Delaunoy, Hiroshi Kawasaki, Kagoshima University, Kagoshima, Japan.
16:15	Cofee break
Session	Face defomation
16:45	Facial Expression Recognition with Temporal Modeling of Shapes, Suyog Jain, Changbo Hu, J. K. Aggarwal, Computer & Vision Research Center / Department of ECE, The University of Texas at Austin.
17:10	4D Facial Expression Recognition, Tianhong Fang, Xi Zhao, Shishir K. Shah and Ioannis A. Kakadiaris, Computational Biomedicine Lab, University of Houston 4800 Calhoun Rd, Houston, TX 77004, USA.
17:35	Closing word
17:40	End of the workshop

NEWS

Decisions and camera ready:

* pdfeXpress conference ID is ICCV2011x

* Camera ready(hard deadline): September 13, 2011, 22:00h (GMT+2)

Submission site is open:

https://cmt.research.microsoft.com/FOURDMOD2011/

Submission deadline is extended:

• Submission deadline: July 12, 2011, 23:59h (GMT)

• Submission of the supplementary material: July 12, 2011, 23:59h (GMT)

Call for Papers

Call for papers is now ONLINE.

Organizers

• Slobodan Ilic (principal contact) Computer Science Department, Technical University Munich, Germany

• Edmond Boyer, Perception Team, Morpheo, INRIA Rhone-Alpes, France

• Adrian Hilton, Visual Media Research Group, CVSSP, University of Surrey, UK

Contact

All questions to be addressed to:

• 4dmod@mailnavab.in.tum.de

PASCAL2 Invited Speakers

• Christian Theobalt, MPI Saarbrucken, Germany

• Michael Black, MPI Tuebingen, Germany

Program Committee

• Adrian Bartoli, LASMEA Clermont-Ferrand, France
• Luca Ballan, ETHZ, Switzerland
• Peter Eisert, Heinrich-Hertz-Institute, Berlin, Germany
• Jean-Sebastien Franco, INRIA Rhone Alpes, France
• Ben Glocker, Microsoft Research, Cambridge, UK
• Juergen Gall, ETH Zurich, Switzerland
• Oliver Grau, BBC Research, UK
• Radu Horaud, INRIA Rhone-Alpes, France
• Ron Kimmel, Technion - Israel Institute of Technology, Israel
• Yebin Liu, Tsinghua University, China
• Marcus Magnor, TU Braunschweig, Germany
• Francesc Moreno-Noguer, Institut de Robotica i Informtica Industrial, Barcelona, Spain
• Christian Plaggerman, Stanford University, USA
• Bodo Rosenhahn, University of Hannover, Germany
• Mathieu Salzmann, TTI Chicago, USA
• Leonid Sigal, Disney Research Pittsburg, USA
• Christian Theobalt, MPI Informatik Saarbrucken, Germany
• Tony Tung, Kyoto University, Japan
• Raquel Urtasun, TTI Chichago, USA
• Michael Wand, Saarland University / MPI Informatik, Germany
• Andrei Zaharescu, AIMETIS Corporation, Waterloo, Canada
• Darko Zikic, TUM, Germany

Topics

• 4D acquisition of real-world dynamic scenes
• Shape recovery of dynamic 3D scenes
• Temporally consistent tracking of deformable surfaces
• 4D Representation
• 4D Reconstruction from Medical Images
• Deformation surface models
• Free-viewpoint and 3D video
• Marker-less human motion capture (articulated and surface based)
• Monocular and multi-view deformable surface capture
• Animation and texture transfer
• Deformable surface tracking for medical applications
• Deformable Shape Matching
• Motion analysis
• Scene Flow
• Non-rigid and Deformable shape analysis
• Shape segmentation
• Learning of model deformations
• Space-time geometry processing
• Applications of 3D video and 4D modeling

Important Dates

• Submission deadline: July 12, 2011, 23:59h (GMT)

• Submission of the supplementary material: July 12, 2011, 23:59h (GMT)

• Notification of acceptance: September 2, 2011

• Camera ready copy due: September 13, 2011

• Workshop date: November 13, 2011

Submission Instructions

Papers must describe high-quality, original research in areas related to modeling and analysis of dynamic scenes and their applications. By submitting a manuscript to 4DMOD, the authors assert that the submitted papers are not substantially similar to any paper published or submitted elsewhere. All submissions will be handled electronically through Microsoft Conference Management System CMT:

https://cmt.research.microsoft.com/FOURDMOD2011/

that is now open for submissions. The deadline for submissions is July 1, 2011 at 23:59h GMT. Submission of the supplementary material is allowed until one week after the paper submission deadline and is fixed until July 8, 2011 at 23:59h GMT.

No double submission to other conferences is allowed. Instructions on paper submission can be found at this web site. Please refer to the following files for detailed formatting instructions:

• Example submission paper with detailed instructions: egpaper_for_review.pdf
• LaTeX^?/Word Templates (tar): 4DMOD-iccv2011AuthorKit.tgz
• LaTeX^?/Word Templates (zip): 4DMOD-iccv2011AuthorKit.zip

Workshop papers should be submitted using the above templates. Submissions can be up to 8 pages in length prepared in this ICCV format with no additional charges.

All papers will be subject to peer review and published by the IEEE and will be part of the ICCV proceedings distributed on the conference DVD. Submitted papers must comply with the ICCV style and length requirements (up to 8 pages). 4DMOD reviewing is double blind, all papers should follow the usual guidelines for preservation of anonymity.