Monday 8th September |
Tutorial session |
Statistical Pattern Recognition |
Andrew R Webb (Qinetiq) |
14:00—17:00 |
| | Dinner (Refectory) |
Tuesday 9th September |
Plenary session |
Words,Pictures and Video |
David Forsyth (University California Berkeley) |
09:00—10:00 |
|
|
Coffee |
Oral session: Faces |
Using Local Context To Improve Face Detection |
Hannes Kruppa, Bernt Schiele (ETH Zurich) |
10:30—10:50 |
Exploratory Sparse Models for Face Recognition |
Nicholas Paul Costen, Martin Brown (Manchester Metropolitan University) |
10:50—11:10 |
An Analytical Mapping for LLE and Its Application in Multi-Pose Face Synthesis |
Jun Wang, Changshui Zhang, Zhongbao Kou (Tsinghua University) |
11:10—11:30 |
Modelling ‘Talking Head’ Behaviour |
Craig A Hack, Chris J Taylor (University of Manchester) |
11:30—11:50 |
2.5D Visual Speech Synthesis Using Appearance Models |
Barry-John Theobald, Andrew Bangham (University of East Anglia), Iain Matthews (Carnegie Mellon University), John R W Glauert, Gavin C Cawley (University of East Anglia) |
11:50—12:10 |
| | Lunch (LCR) |
Oral session: Geometry |
The Analysis of Ambiguous Solutions in Linear Systems and its Application to Computer Vision |
Marta Wilczkowiak, Peter Sturm, Edmond - Boyer (INRIA) |
13:10—13:30 |
Batch Recovery of Multiple Views with Missing Data Using Direct Sparse Solvers |
Nicolas Guilbert (Lund University) |
13:30—13:50 |
Joint Orientation of Epipoles |
Ondrej Chum, Tomas Werner, Tomas Pajdla (Czech Technical University in Prague) |
13:50—14:10 |
Invariant Fitting of Two View Geometry |
Andrew W Fitzgibbon (University of Oxford), Philip Torr (Microsoft Research Ltd) |
14:10—14:30 |
Poster session 1 |
(14:30—15:50) |
Discriminant Analysis by Locally Linear Transformations |
Tae-Kyun Kim (Samsung Advanced Institute of Technology (SAIT)), Josef Kittler (University of Surrey (UniS)), Hyun-Chul Kim (Pohang University of Science and Technology), Seok Cheol Kee (Samsung Advanced Institute of Technology (SAIT)) |
Class-based Multiple Light Detection: An Application to Faces |
Christos-Savvas Bouganis, Mike Brookes (Imperial College) |
A Linear Trinocular Rectification Method for Accurate Stereoscopic Matching |
Huaifeng Zhang (Chinese Academy of Science, Institute of Automation), Jan Cech, Radim Sara (Center for Machine Perception), Fuchao Wu, Zhanyi Hu (Chinese Academy of Science, Institute of Automation) |
Application of Characteristic Function Method in Target Detection |
Mohammad H Marhaban, Josef Kittler (University of Surrey (UniS)) |
Thresholding based on linear diffusion for feature segmentation |
Andreas Hoppe, Marco-Olivier Baradez (Kingston University) |
Tracking in a Hough Space with the Extended Kalman Filter |
Steven Mills (University of Nottingham), Tony P Pridmore (The University of Nottingham), Mark Hills (University of Nottingham) |
Dense matching using correlation: new measures that are robust near occlusions |
Sylvie Chambon, Alain Crouzil (Institut de Recherche en Informatique de Toulouse (IRIT)) |
Sparse IBR Using Range Space Rendering |
Dan Kong, Hao Tao (University of California, Santa Cruz), Hector H Gonzalez-Banos (Honda R&D Americans, Inc.) |
Ranklets on hexagonal pixel lattices |
Fabrizio Smeraldi, Mohammed Abdul Rob (Queen Mary, University of London) |
Dense 3-D Structure from Image Sequences Using Probabilistic Depth Carving |
Annie Yao, Andrew D Calway (University of Bristol) |
A Shape Descriptor for Shapes with Boundary Noise and Texture |
Wooi-Boon Goh, Kai-Yun Chan (Nanyang Technological University) |
Rough Surface Analysis using Kirchhoff Theory |
Hossein Ragheb, Edwin R Hancock (University of York) |
Learning Based Resolution Enhancement of Iris Images |
Junzhou Huang, Li Ma, Tieniu Tan, Yunhong Wang (Institute of Automation, Chinese Academy of Sciences) |
Facial feature detection using AdaBoost with shape constraints |
David Cristinacce, Timothy F Cootes (University of Manchester) |
Rendering Almost Perspective Views from a Sparse Set of Omnidirectional Images |
Hynek Bakstein, Tomas Pajdla, Daniel Vecerka (Center for Machine Perception) |
Synthesis of Photographic Quality Facial Composites using Evolutionary Algorithms |
Stuart J Gibson, Christopher J Solomon, Alvaro Pallares Bejarano (University of Kent) |
Multi-Modal Matching Applied to Stereo |
Nicolas Pugeault (University
of Stirling), Norbert Krueger (Aalborg University Esbjerg) |
3D Shape and Pose Estimation of Deformable Tapes from Multiple Views |
Hitoshi Kubota, Masakazu Ono, Masami Takeshi (Suzuki Motor Co.), Hideo Saito (Keio University) |
Minimizing the description length using steepest descent |
Anders Ericsson, Kalle Åström (Lund University) |
Determining pose of a human face from a single monocular image |
Jian-Gang Wang (Institute for Infocomm Research), Eric Sung (Nanyang Technological University), Ronda Venkateswarlu (Institute for Infocomm Research) |
A continuous Formulation of intrinsic Dimension |
Norbert Krueger (Aalborg
University Esbjerg), Michael Felsberg (Linköping University) |
Adding Curvature to Minimum Description Length Shape Models |
Hans Henrik Thodberg, Hildur Olafsdottir (Technical University of Denmark, DTU) |
Oral session: Techniques and Methods |
Graph Clustering using Symmetric Polynomials and Local Linear Embedding |
Edwin R Hancock, Richard C Wilson, Bai Xiao (University of York) |
15:50—16:10 |
Robust subspace mixture models using t-distributions |
Dick de Ridder (Delft University of Technology), Vojtech Franc (Center for Machine Perception) |
16:10—16:30 |
Exact polyhedral visual hulls |
Jean-Sebastien Franco, Edmond Boyer (INRIA) |
16:50—17:10 |
Stratified Dense Matching for Stereopsis in Complex Scenes |
Jana Kostkova, Radim Sara (Center for Machine Perception) |
17:10—17:30 |
| | Lord Mayor's Reception (City Hall) |
Wednesday 10th September |
Plenary session |
Pattern theory: the formative
years |
Ulf Grenander (Brown University) |
09:00—10:00 |
Oral session: Biomedical vision (10:00—11:00) |
Linking Sequences of Active Appearance Sub-Models via Constraints: An Application in Automated Vertebral Morphometry |
Martin G Roberts, Timothy F Cootes, Judith E Adams (University of Manchester) |
10:00—10:20 |
Strain Quantification In Ultrasound Sequences |
James Revell, Majid Mirmehdi (University of Bristol), Donal McNally (Nottingham University) |
10:20—10:40 |
Automatic Construction of Statistical Shape Models for Protein Spot Analysis in Electrophoresis Gels |
Mike Rogers, James Graham (University of Manchester), Robert P Tonge (AstraZeneca) |
10:40—11:00 |
|
|
Coffee |
Poster session 2 (11:00—12:20) |
Pose Evaluation Based on Bayesian classification Error |
Tieniu Tan (Chinese academy of science) |
Factorization Method Using Interpolated Feature Tracking via Projective Geometry |
Hideo Saito, Shigeharu Kamijima (Keio University) |
Classification of Moving Targets Based on Motion and Appearance |
Yuri Bogomolov (Technion - Israel Institute of Technology), Gideon Dror (Academic Colloege of Tel Aviv Yaffo), Stas Lapchev, Ehud Rivlin, Michael Rudzsky (Technion - Israel Institute of Technology) |
Error Equalisation for Sparse Image Mosaic Construction |
Bogdan J Matuszewski, Lik-Kwan Shark, John Smith, Martin Roy Varley (University of Central Lancashire) |
Spotting Scene Change for Indexing Surveillance Video |
Andrew Graves, Shaogang Gong (Queen Mary, University of London) |
Learning a Kinematic Prior for Tree-Based Filtering |
Arasanathan Thayananthan, Bjorn Stenger (University of Cambridge), Philip Torr (Microsoft Research Ltd), Roberto Cipolla (University of Cambridge) |
Visual Golf Club Tracking for Enhanced Swing Analysis |
Nicolas Gehrig, Vincent Lepetit, Pascal Fua (EPFL) |
Active Wavelet Networks for Face Alignment |
Changbo Hu, Rogerio S Feris (University of California), Matthew Turk (University of California, Santa Barbara) |
Automated Registration of 3D Faces using Dense Surface Models |
Tim J Hutton, Bernard F. Buxton, Peter Hammond (University College London) |
Face Model Adaptation for Tracking and Active Appearance Model Training |
Fadi Dornaika (Linköping University), Jörgen Ahlberg (Swedish Defence Research Agency) |
An Image-Based Three-Dimensional Digitizer for Pre-Decorating Thermoformed Parts |
JP Mellor (Rose-Hulman Institute of Technology) |
Fusing Complementary Operators to Enhance Foreground/Background Segmentation |
Ahmad H. Al-Mazeed, Mark S Nixon, Steve R Gunn (University of Southampton) |
Adaptive Probabilistic Models of Wavelet Packets for the Analysis and Segmentation of Textured Remote Sensing Images |
Karen Brady, Ian H. Jermyn, Josiane Zerubia (INRIA) |
A method to add Hidden Markov Models with application to learning articulated motion |
Yulia A Hicks (Cardiff University), Peter M Hall (University of Bath), David Marshall (Cardiff University) |
A Robust Iterative Shape-From-Shading Algorithm with Modified Transforming Matrix |
Osamu Ikeda (Takushoku University) |
Texture Edge Detection Using the Compass Operator |
Bruce A Maxwell (Swarthmore
College), Stephanie J. Brubaker(Georgia Institute of Technology) |
A Fully Unsupervised Texture Segmentation Algorithm |
Mohammad F. A. Fauzi, Paul H. Lewis (University of Southampton) |
Deterministic Surface Registration at 10Hz Based on Landmark Graphs With Prediction |
Fred W DePiero (CalPoly State University) |
The Art of Scale-Space |
J. Andrew Bangham, Stuart E Gibson, Richard Harvey (University of East Anglia) |
On-line Face Tracking Using a Feature Driven Level Set |
Derek R Magee (University of Leeds), Bastian Leibe (ETH Zurich) |
Face Detection Based on Multiple Regression and Recognition Support Vector Machines |
Jianzhong Fang (Nottingham University), Guoping Qiu (The University of Nottingham) |
Spatio-Temporal Semantic Object Segmentation using Probabilistic Sub-Object Regions |
David James Thirde, Graeme A. Jones (Kingston University), Julien Flack (DDD Group Plc) |
Geodesic Colour Active Contour Resistent to Weak Edges and Noise |
Xianghua Xie, Majid Mirmehdi
(University of Bristol) |
| | Lunch (LCR) |
Oral session: Shape and Motion |
3D head tracking using non-linear optimization |
James A Paterson, Andrew W Fitzgibbon (University of Oxford) |
13:20—13:40 |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
Tao Xiang, Shaogang Gong (Queen Mary, University of London) |
13:40—14:00 |
Synchronizing Image Sequences of Non-Rigid Objects |
Philip A Tresadern, Ian Reid (University of Oxford) |
14:00—14:20 |
Robust Motion Segmentation by Spectral Clustering |
Hongbin Wang, Phil F. Culverhouse (University of Plymouth (UK)) |
14:20—14:40 |
The Template Update Problem |
Iain Matthews, Takahiro Ishikawa, Simon Baker (Carnegie Mellon University) |
14:40—15:00 |
|
|
Coffee |
Oral session: Video and Motion |
Video Indexing using Motion Estimation |
Sarah V Porter, Majid Mirmehdi, Barry T. Thomas (University of Bristol) |
15:30—15:50 |
Robust multi-body segmentation |
Andreas Dante, Mike Brookes, Anthony G Constantinides (Imperial College) |
15:50—16:10 |
Guiding Optical Flow Estimation |
Peter J Myerscough (University of Southampton) |
16:10—16:30 |
An implicit motion likelihood for tracking with particle filters |
Jean-Marc Odobez, Sileye O Ba, Daniel Gatica-Perez (IDIAP) |
16:30—16:50 |
Simultaneous Pose Estimation of Multiple People using Multiple-View Cues with Hierarchical Sampling |
Joel R Mitchelson, Adrian Hilton (University of Surrey) |
16:50—17:10 |
| | Conference Dinner (Sainsbury Centre for Visual Arts) |
Thursday 11th September |
Oral session: The Interface with Graphics |
Bayesian Stochastic Mesh Optimization for 3D reconstruction |
George Vogiatzis (University of Cambridge), Philip Torr (Microsoft Research Ltd), Roberto Cipolla (University of Cambridge) |
09:00—09:20 |
Rapid rendering of apparent contours of implicit surfaces for real-time tracking |
Edward Rosten, Tom W Drummond (University of Cambridge) |
09:20—09:40 |
A Multiple View Layered Representation for Dynamic Novel View Synthesis |
Keith Richard Connor, Ian Reid (University of Oxford) |
09:40—10:00 |
Architectural Reconstruction with Multiple Views and Geometric Constraints |
Sébastien S.C. Cornou(CEA), Michel Dhome (CNRS/Université Blaise Pascal), Patrick Sayd (CEA) |
10:00—10:20 |
Video Analysis for Cartoon-like Special Effects |
John P Collomosse (University of Bath), David Rowntree (Nanomation Ltd.), Peter M Hall (University of Bath) |
10:20—10:40 |
| | Coffee |
Oral session: segmentation and low-level vision |
Interleaved Object Categorization and Segmentation |
Bastian Leibe, Bernt Schiele (ETH Zurich) |
11:10—11:30 |
Discriminant Feature Selection for Texture Classification |
Abhir H Bhalerao, Nasir M Rajpoot (University of Warwick) |
11:30—11:50 |
Shape recognition with edge-based features |
Krystian Mikolajczyk, Andrew Zisserman (University of Oxford), Cordelia Schmid (INRIA) |
11:50—12:10 |
Simultaneous surface texture classification and illumination tilt angle prediction |
Xavier Lladó, Arnau Oliver (University of Girona), Maria Petrou (University of Surrey), Jordi Freixenet, Joan Martí (University of Girona) |
12:10—12:30 |
Evaluating colour morphological scale-spaces |
Stuart E Gibson, J. Andrew Bangham, Richard Harvey (University of East Anglia) |
12:30—12:50 |
| | Lunch (LCR) |