BMVC 2011

Proceedings of the British Machine Vision Conference 2011
Jesse Hoey, Stephen McKenna and Emanuele Trucco, editors,
BMVA Press, September 2011. DOI:http://dx.doi.org/10.5244/C.25 ISBN: 1-901725-43-X

Tutorial

Matthew Blaschko (Univ. of Oxford),
Structured Learning and Inference in Computer Vision

Invited Speaker

David Fleet (Univ. of Toronto),
Tracking and Understanding Human Motion

Learning I

Sean Moran (Edinburgh Univ.), Victor Lavrenko (Edinburgh Univ.),
Optimal Tag Sets for Automatic Image Annotation
Ronak Shah (IIT, Bombay), Rishabh Iyer (IIT, Bombay), Subhasis Chaudhuri (IIT, Bombay),
Object Mining for Large Video data
David Rim (École Polytechnique de Montréal), Kamrul Hassan (École Polytechnique de Montréal), Christopher Pal (École Polytechnique de Montréal),
Semi Supervised Learning for Wild Faces and Video

Representation/Recognition I

Peter Kontschieder (Graz Univ. of Technology), Hayko Riemenschneider (Graz Univ. of Technology), Michael Donoser (Graz Univ. of Technology), Horst Bischof (Graz Univ. of Technology),
Discriminative Learning of Contour Fragments for Object Detection
Leonid Pishchulin (MPI Informatics), Arjun Jain (MPI Informatics), Christian Wojek (MPI Informatics), Thorsten Thormaehlen (MPI Informatics)), Bernt Schiele (MPI Informatics),
In Good Shape: Robust People Detection based on Appearance and Shape
Gaurav Sharma (Univ. of Caen/INRIA), Frederic Jurie (Univ. of Caen/INRIA),
Learning discriminative spatial representation for image classification
Juan Cerrolaza (Public Univ. of Navarra), Arantxa Villanueva (Public Univ. of Navarra), Rafael Cabeza (Public Univ. of Navarra),
Shape Constraint Strategies: Novel Approaches and Comparative Robustness

Learning II

Alain Lehmann (ETH Zurich), Peter Gehler (ETC Zurich), Luc Van Gool (ETH Zurich),
Branch&Rank: Non-Linear Object Detection
Tom Haines (Queen Mary- Uni. of London), Tao Xiang (Queen Mary - Uni. of London),
Active Learning using Dirichlet Processes for Rare Class Discovery and Classification
Edward Johns (Imperial College London), Guang-Zhong Yang (Imperial College London),
Place Recognition and Online Learning in Dynamic Scenes with Spatio-Temporal Landmarks

Posters I-A

Yong Jae Lee (Univ. of Texas at Austin), Kristen Grauman (Univ. of Texas at Austin),
Face Discovery with Social Context
Oksana Samko (Cardiff Univ.), Yu-Kun Lai (Cardiff Univ.), David Marshall (Cardiff Univ.), Paul Rosin (Cardiff Univ.),
Segmentation of Parchment Scrolls for Virtual Unrolling
Xinqi Chu (UIUC), Tian-Tsong Ng (A*STAR), Ramanpreet Pahwa (UIUC), Tony Q. Quek (A*STAR), Thomas Huang (UIUC),
Compressive Inverse Light Transport
Huanzhang Fu (ECL - LIRIS), Emmanuel Dellandrea (ECL - LIRIS), Liming Chen (ECL - LIRIS),
Reconstructive and Discriminative Sparse Representation for Visual Object Categorization
Mohamed Aly (Caltech), Mario Munich (Evolution Robotics), Pietro Perona (Evolution Robotics),
Distributed Kd-Trees for Ultra Large Scale Object Recognition
Aly S. Abdelrahim (Univ. of Louisville), Mostafa A. Abdelrahman (Univ. of Louisville), Hossam Abdelmunim (Ain Shams Univ.), Aly Farag (Univ. of Louisville), Mike Miller (Univ. of Louisville),
Novel Image-Based 3D Reconstruction of the Human Jaw using Shape from Shading and Feature Descriptors
Junyu Han (Xidian Univ.), Fei Qi (Xidian Univ.), Guangming Shi (Xidian Univ.),
Enhancing Gradient Sparsity for Parametrized Motion Estimation
Nikolaos Kyriazis (FORTH), Iason Oikonomidis (FORTH), Antonis Argyros (FORTH),
Binding Computer Vision to Physics Based Simulation: The Case Study of a Bouncing Ball
Julien Mille (Université Lyon 1 / LIRIS), Jean-Loïc Rose (Université Lyon 2 / LIRIS),
Multitarget region tracking based on short-sight modelling of background and color distribution temporal variation
Maxime Meilland (INRIA), Andrew Comport (CNRS), Patrick Rives (INRIA),
Real-time Dense Visual Tracking under Large Lighting Variations
Antoine Letouzey (INRIA), Benjamin Petit (INRIA), Edmond Boyer (INRIA),
Scene Flow from Depth and Color Images
Iason Oikonomidis (FORTH), Nikolaos Kyriazis (FORTH), Antonis Argyros (FORTH),
Efficient model-based 3D tracking of hand articulations using Kinect
Xu Yan (Univ. of Houston), Ioannis Kakadiaris (Univ. of Houston), Shishir Shah (Univ. of Houston),
Predicting Social Interactions for Visual Tracking
Chang-kyu Song (POSTECH), Jeany Son (POSTECH), Suha Kwak (POSTECH), Bohyung Han (POSTECH),
Dynamic Resource Allocation by Ranking SVM for Particle Filter Tracking
Dennis Mitzel (RWTH Aachen Univ.), Patrick Sudowe (RWTH-Aachen Univ.), Bastian Leibe (RWTH-Aachen Univ.),
Real-Time Multi-Person Tracking with Time-Constrained Detection
Jesús Martínez del Rincón (Kingston Univ.), Jean-Christophe Nebel (Kingston Univ.), Dimitrios Makris (Kingston Univ.),
Graph-based Particle Filter for Human Tracking with Stylistic Variations

Posters I-B

Ali Borji (USC), Dicky Sihite (USC), Laurent Itti (USC),
Computational Modeling of Top-down Visual Attention in Interactive Environments
Jian Li (NUDT), Martin Levine (McGill), Xiangjing An (NUDT), Hangen He (NUDT),
Saliency Detection Based on Frequency and Spatial Domain Analyses
Xiaoyue Jiang (Univ. of Birmingham), Andrew Schofield (Univ. of Birmingham), Jeremy Wyatt
Shadow Detection based on Colour Segmentation and Estimated Illumination
Oswald Aldrian (Univ. of York), William Smith (Univ. of York),
Inverse Rendering with a Morphable Model: A Multilinear Approach
Shireen Elhabian (Univ. of Louisville), Ham Rara (Univ. of Louisville), Aly Farag (Univ. of Louisville),
Towards Efficient and Compact Phenomenological Representation of Arbitrary Bidirectional Surface Reflectance
Yue Wu (Tufts Univ.), Pradeep Natarajan (Raytheon BBN Techonlogies), Joseph Noonan (Tufts Univ.), Rohit Prasad (Raytheon BBN Technologies), Premkumar Natarajan (Raytheon BBN Technologies),
Wavelet Band-pass Filters for Matching Multiple Templates in Real-time
Mads Fogtmann Hansen (DTU Informatics), Jens Fagertun (DTU Informatics), Rasmus Larsen (DTU Informatics),
Elastic appearance models
Mohsen Aabbas Pour Seyyedi (Queen's Univ. Belfast), Paul Miller (Queen's Univ. Belfast), Hugh Gribben (Andor Technology),
Improved Elastic Registration of Low-Contrast Fluorescent Microscopy Images Using the Behaviour of Local Similarity
Steffen Gauglitz (UC Santa Barbara), Matthew Turk (UC Santa Barbara), Tobias Höllerer (UC Santa Barbara),
Improving Keypoint Orientation Assignment
Meijuan Yang (Chinese Academy of Sciences), Yuan Yuan (Chinese Academy of Sciences), Xuelong Li (Chinese Academy of Sciences), Pingkun Yan (Chinese Academy of Sciences),
Medical Image Segmentation Using Descriptive Image Features
Yi-Hung Jen (UNC), Enrique Dunn (UNC), Pierre Fite-Georgel (UNC), Jan-Michael Frahm (UNC),
Adaptive Scale Selection for Hierarchical Stereo
Shuntaro Yamazaki (AIST), Akira Nukada (Tokyo Institute of Technology), Masaaki Mochimaru (AIST),
Hamming Color Code for Dense and Robust One-shot 3D Scanning
Michel Antunes (ISR), João Barreto (ISR), Xenophon Zabulis (Foundation for Research and Technology - Hellas),
Plane Surface Detection and Reconstruction using Induced Stereo Symmetry
Domenico Tegolo (Univ. of Palermo), Fabio Bellavia (Univ. of Palermo),
noRANSAC for fundamental matrix estimation
Paul McIlroy (Univ. of Cambridge), Roberto Cipolla (Univ. of Cambridge), Ed Rosten (Univ. of Cambridge),
High-level scene structure using visibility and occlusion
Amir-Hossein Shabani (Univ. of Waterloo), David Clausi (Univ. of Waterloo), John S. Zelek (Univ. of Waterloo),
Improved Spatio-temporal Salient Feature Detection for Action Recognition

Posters I-C

Hao Fu (Univ. of Nottingham), Guoping Qiu (Univ. of Nottingham), Hangen He (NUDT),
Feature Combination beyond Basic Arithmetics
Oksana Yakhnenko (Google Inc.), Vasant Honavar (Iowa State Univ.),
Multi-Instance Multi-Label Learning for Image Classification with Large Vocabularies
Muhammad Awais (Univ. of Surrey), Fei Yan (Univ. of Surrey), Krystian Mikolajczyk (Univ. of Surrey), Josef Kittler (Univ. of Surrey),
Augmented Kernel Matrix vs Classifier Fusion for Object Recognition
Radu Timofte (KU Leuven), Luc Van Gool (KU Leuven),
Sparse Representation Based Projections
Jingchen Liu (Pennsylvania State Univ.), Robert Collins (Pennsylvania State Univ.), Yanxi Liu (Pennsylvania State Univ.),
Automatic Surveillance Camera Calibration without Pedestrian Tracking
Anne Sedlazeck (Christian-Albrechts-Univ. of Kiel), Reinhard Koch (Christian-Albrechts-Univ. of Kiel),
Calibration of Housing Parameters for Underwater Stereo-Camera Rigs
Yimo Guo (Univ. of Oulu), Guoying Zhao (Univ. of Oulu), Matti Pietikäinen (Univ. of Oulu),
Texture Classification using a Linear Configuration Model based Descriptor
Alasdair Clarke (Heriot-Watt Univ.), Fraser Halley (Heriot-Watt Univ.), Andrew Newell (Univ. College London), Lewis Griffin (Univ. College London), Mike Chantler (Heriot-Watt Univ.),
Perceptual Similarity: A Texture Challenge
Alexander Mansfield (ETH Zurich), Mukta Prasad (ETH Zurich), Carsten Rother (Microsoft Research), Toby Sharp (Microsoft Research), Pushmeet Kohli (Microsoft Research), Luc Van Gool (ETH Zurich),
Transforming Image Completion
Gui-Song Xia (CNRS), Fei Yuan (CNRS),
Texture Segmentation by Grouping Ellipse Ensembles via Active Contours
Liu Li (NUDT), Paul Fieguth (Univ. of Waterloo), Gangyao Kuang (NUDT),
Generalized Local Binary Patterns for Texture Classification
Samuel Schulter (Graz Univ. of Technology), Christian Leistner (ETH Zurich), Peter Roth (Graz Univ. of Technology), Horst Bischof (Graz Univ. of Technology), Luc Van Gool (ETH Zurich),
On-line Hough Forests
Vijay B.G. Kumar (Queen Mary - Univ. of London), Ioannis Patras (Queen Mary - Univ. of London), Irene Kotsia (Queen Mary - Univ. of London),
Max-Margin Semi-NMF
Songfeng Zheng (Missouri State Univ.),
Labeling Image Patches by Boosting based Median Classifier
Hossein Ragheb (Univ. of Manchester), Neil Thacker (The Univ. of Manchester),
Morphometric Shape Analysis with Measurement Covariance Estimates
Zhi Feng Huang (Simon Fraser Univ.), Weilong Yang (Simon Fraser Univ.), Yang Wang (UIUC), Greg Mori (Simon Fraser Univ.),
Latent Boosting for Action Recognition

Motion and Tracking

Yuheng Ren (Univ. of Oxford), Victor Prisacariu (Univ. of Oxford), Ian Reid (Univ. of Oxford),
Regressing Local to Global Shape Properties for Online Segmentation and Tracking
Vasileios Zografos (Linkoping Univ.), Klas Nordberg (Linkoping Univ.),
Fast and accurate motion segmentation using Linear Combination of Views
Chris Russell (Queen Mary - Univ. of London), Lourdes Agapito (Queen Mary - Univ. of London), Francesco Setti (Univ. of Trento),
Efficient Second Order Multi-Target Tracking with Exclusion Constraints

Invited Speaker

Nikos Paragios (École Centrale de Paris),
Shape Grammars and Procedural Modeling towards Large Scale 3D Modeling and Reconstruction

Robotics and Stereo

Michael Bleyer (Vienna Univ. of Technology), Christoph Rhemann (Vienna Univ. of Technology), Carsten Rother (Microsoft Research),
PatchMatch Stereo - Stereo Matching with Slanted Support Windows
Sacha Bernet (MIPS), Peter Sturm (INRIA), Christophe Cudel (MIPS), Michel Basset (MIPS),
Study on the interest of hybrid fundamental matrix for head mounted eye tracker modeling
Laurent Kneip (ETH Zurich), Margarita Chli (ETH Zurich), Roland Siegwart (ETH Zurich),
Robust Real-Time Visual Odometry with a Single Camera and an IMU

Representation/Recognition II

Hakan Bilen (KU Leuven), Vinay Namboodiri (KU Leuven), Luc Van Gool (KU Leuven),
Object and Action Classification with Latent Variables
Seyed Mohammadali Eslami (Univ. of Edinburgh), Christopher Williams (Univ. of Edinburgh),
Factored Shapes and Appearances for Parts-based Object Understanding
Michael Villamizar (IRI CSIC-UPC), Helmut Grabner, Francesc Moreno-Noguer (IRI CSIC-UPC), Juan Andrade-Cetto (IRI CSIC-UPC), Luc Van Gool (ETH Zurich), Alberto Sanfeliu (IRI CSIC-UPC),
Efficient 3D Object Detection using Multiple Pose-Specific Classifiers
Huiyu Zhou (Queen's Univ. Belfast), Paul Miller (Queen's Univ. Belfast), Jianguo Zhang (Univ. of Dundee),
Age classification using Radon transform and entropy based scaling SVM

Activity in Video

Fabian Nater (ETH Zurich), Helmut Grabner (ETH Zurich), Luc Van Gool (ETH Zurich),
Temporal Relations in Videos for Unsupervised Activity Analysis
Manuel Marin-Jimenez (Univ. of Cordoba), Andrew Zisserman (Univ. of Oxford), Vittorio Ferrari (ETH Zurich),
"Here's looking at you, kid". Detecting people looking at each other in videos
Marco Cristani (Univ. of Verona), Loris Bazzani (Univ. of Verona), Giulia Paggetti (Univ. of Verona), Andrea Fossati (ETH Zurich), Diego Tosato (Univ. of Verona), Alessio Del Bue (Instituto Italiano di Tecnologia), Gloria Menegaz (Univ. of Verona), Vittorio Murino (Istituto Italiano di Tecnologia),
Social interaction discovery by statistical analysis of F-formations

Posters II-A

Emil Bilgazyev (Univ. of Houston), Boris Efraty (Univ. of Houston), Shishir Shah (Univ. of Houston), Ioannis Kakadiaris (Univ. of Houston),
Sparse Representation-Based Super Resolution for Face Recognition At a Distance
Carl Scheffler (IDIAP Research Institute), Jean-Marc Odobez (IDIAP Research Institute),
Joint Adaptive Colour Modelling and Skin, Hair and Clothes Segmentation using Coherent Probabilistic Index Maps
Hua Gao (KIT), Hazim Kemal Ekenel (KIT), Mika Fischer (KIT), Rainer Stiefelhagen (KIT),
Boosting Pseudo Census Transform Features for Face Alignment
Eng-Jon Ong (Univ. of Surrey), Richard Bowden (Univ. of Surrey),
Learning Sequential Patterns for Lipreading
Xiangyang Liu (Shanghai JiaoTong Univ.), Hongtao Lu (Shanghai JiaoTong Univ.), Hua Gu (Hohai Univ.),
Group Sparse Non-negative Matrix Factorization for Multi-Manifold Learning
Yuandong Xu (Peking Univ.), Jinshi Cui (Peking Univ.), Huijing Zhao (Peking Univ.), Hongbin Zha (Peking Univ.),
Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches
John Greenall (Univ. of Leeds), David Hogg, Anthony Cohn (Univ. of Leeds),
Temporal Structure Models for Event Recognition
Adrien Gaidon (INRIA), Zaid Harchoui (INRIA), Cordelia Schmid (INRIA),
A time series kernel for action recognition
Khai Tran (Univ. of Houston), Ioannis Kakadiaris (Univ. of Houston), Shishir Shah (Univ. of Houston),
Modeling Motion of Body Parts for Action Recognition
Parthipan Siva (Queen Mary Univ. of London), Tao Xiang (Queen Mary, Uni. of London),
Weakly Supervised Action Detection
Andrew Gilbert (Univ. of Surrey), Richard Bowden (Univ. of Surrey),
Push and Pull: Iterative grouping of media
Angela Yao (ETH Zurich), Juergen Gall (ETH Zurich), Gabriele Fanelli, Luc Van Gool (ETH Zurich),
Does Human Action Recognition Benefit from Pose Estimation?
Nicholas Michael (Rutgers Univ.), Peng Yang (Rutgers Univ.), Qingshan Liu (Rutgers Univ.), Dimitris Metaxas (Rutgers Univ.), Carol Neidle (Boston Univ.),
A Framework for the Recognition of Nonmanual Markers in Segmented Sequences of American Sign Language
Meina Kan (CAS), Shiguang Shan (CAS), Dong Xu (Nanyang Technological Univ.), Xilin Chen (CAS),
Side-Information based Linear Discriminant Analysis for Face Recognition
Feng Lu (The Univ. of Tokyo), Takahiro Okabe (The Univ. of Tokyo), Yusuke Sugano (The Univ. of Tokyo), Yoichi Sato (The Univ. of Tokyo),
A Head Pose-free Approach for Appearance-based Gaze Estimation
Akshay Asthana (Australian National Univ.), Michael Jones (MERL), Tim Marks (MERL), Kinh Tieu (Heartland Robotics), Roland Goecke (Univ. of Canberra),
Pose Normalization via Learned 2D Warping for Fully Automatic Face Recognition

Posters II-B

Josip Krapac (INRIA Grenoble), Jakob Verbeek (INRIA Grenoble), Frederic Jurie (Univ. de Caen),
Learning Tree-structured Quantizers for Image Categorization
Diane Hu (UCSD), Liefeng Bo (Univ. of Washington), Xiaofeng Ren (Intel Labs),
Toward Robust Material Recognition for Everyday Objects
Neda Salamati (Xerox Research Center Europe), Diane Larlus (Xerox Research Center Europe), Gabriela Csurka (Xerox Research Center Europe),
Combining Visible and Near-Infrared Cues for image Categorisation
Joseph Schlecht (Univ. of Heidelberg), Björn Ommer (Univ. of Heidelberg),
Contour-based object detection
David Pfeiffer (Daimler AG), Uwe Franke (Daimler AG),
Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data
Byung Soo Kim (Univ. of Michigan), Jae Young Park (Univ. of Michigan), Anush Mohan (Univ. of Michigan), Anna Gilbert (Univ. of Michigan), Silvio Savarese (Univ. of Michigan),
Hierarchical Classification of Images by Sparse Approximation
Jukka Lankinen (Lappeenranta Univ. of Tech.), Joni Kamarainen (Lappeenranta Univ. of Tech.),
Local Feature Based Unsupervised Alignment of Object Class Images
Adam Rhodes (Univ. of Nottingham), Li Bai (Univ. of Nottingham),
Circle Detection Using a Gabor Annulus
Sirion Vittayakorn (Brown Univ.), James Hays (Brown Univ.),
Quality Assessment for Crowdsourced Object Annotations
Huaizu Jiang (Xi'an Jiaotong Univ.), Jingdong Wang (Microsoft Research Asia), Zejian Yuan (Xi'an Jiaotong Univ.), Tie Liu (IBM China Research Lab), Nanning Zheng (Xi'an Jiaotong Univ.),
Automatic salient object segmentation based on context and shape prior
Peter Kontschieder (Graz Univ. of Technology), Samuel Rota Bulò (Ca' Foscari Univ. of Venice), Michael Donoser (Graz Univ. of Technology), Marcello Pelillo (Ca' Foscari Univ. of Venice), Horst Bischof (Graz Univ. of Technology),
Semantic Image Labelling as a Label Puzzle Game
Yang Wang (UIUC), Greg Mori (Simon Fraser Univ.),
Max-margin Latent Dirichlet Allocation for Image Classification and Annotation
David Meger (Univ. of British Columbia), Christian Wojek (MPI Informatics), James Little (Univ. of British Columbia), Bernt Schiele (Max-Planck-Institute for Computer Science),
Explicit Occlusion Reasoning for 3D Object Detection
Andreas Jordt (Christian-Albrechts-Univ. Kiel), Reinhard Koch (Institute for Computer Science, Christian-Albrechts-Univ. of Kiel),
Fast Tracking of Deformable Objects in Depth and Colour Video
Katrin Pirker (Graz Univ. of Technology), Matthias Rüther (Graz Univ. of Technology), Gerald Schweighofer (Joanneum Research), Horst Bischof (Graz Univ. of Technology),
GPSlam: Marrying Sparse Geometric and Dense Probabilistic Visual Mapping
Wei-Chen Chiu (MPI Informatik), Ulf Blanke (MPI Informatik), Mario Fritz (MPI Informatik),
Improving the Kinect by Cross-Modal Stereo

Posters II-C

Dong Seon Cheng (Univ. of Verona), Marco Cristani (Universita' di Verona), Michele Stoppa (Instituto italiano di Tecnologia), Loris Bazzani (Univ. of Verona), Vittorio Murino (Univ of Verona),
Custom Pictorial Structures for Re-identification
Matthias Straka (Graz Univ. of Technology), Stefan Hauswiesner (Graz Univ. of Technology), Matthias Rüther (Graz Univ. of Technology), Horst Bischof (Graz Univ. of Technology),
Skeletal Graph Based Human Pose Estimation in Real-Time
Darren Caulfield (Trinity College Dublin), Kenneth Dawson-Howe (Trinity College Dublin),
Track validation using gradient-based normalised cross-correlation
Li Yang, Xianghua Ying, Lulu Hou, Jing Kong, Hongbin Zha (Peking Univ.),
Camera Resectioning from Image Edges with the $L_\infty$-Norm Using Linear Programming
Alexander Belyaev (Heriot-Watt Univ.),
On Implicit Image Derivatives and Their Applications
Zhen Qiu (Heriot-Watt Univ.), Lei Yang (Heriot-Watt Univ.), Weiping Lu (Heriot-Watt Univ.),
A New Feature-preserving Nonlinear Anisotropic Diffusion Method for Image Denoising
Xiaoqiang Lu (Chinese Academy of Sciences), Haoliang Yuan (Hubei Univ.), Pingkun Yan (Chinese Academy of Sciences), Luoqing Li (Hubei Univ.), Xuelong Li (Chinese Academy of Sciences),
Image Denoising via Improved Sparse Coding
Arpit Mittal (Univ. of Oxford), Andrew Zisserman (Univ. of Oxford), Philip Torr (Oxford Brookes),
Hand detection using multiple proposals
Ken Chatfield (Univ. of Oxford), Victor Lempitsky (Univ. of Oxford), Andrea Vedaldi (Univ. of Oxford), Andrew Zisserman (Univ. of Oxford),
The devil is in the details: an evaluation of recent feature encoding methods
Anders Dahl (DTU Informatics), Rasmus Larsen (DTU Informatics),
Learning Dictionaries of Discriminative Image Patches
Alireza Fathi (Georgia Institute of Tech.), Maria Florina Balcan (Georgia Institute of Tech.), Xiaofeng Ren (Intel Labs), James M. Rehg (Georgia Institute of Tech.),
Combining Self Training and Active Learning for Video Segmentation
Georgios Floros (RWTH-Aachen Univ.), Konstantinos Rematas (KU Leuven), Bastian Leibe (RWTH-Aachen Univ.),
Multi-Class Image Labeling with Top-Down Segmentation and Generalized Robust $P^N$ Potentials
Vibhav Vineet (Oxford Brookes Univ.), Jonathan Warrell (Oxford Brookes Univ.), Lubor Ladicky (Univ. of Oxford), Philip Torr (Oxford Brookes Univ.),
Human Instance Segmentation from Video using Detector-based Conditional Random Fields
Padraig Corcoran (Univ. College Dublin), Peter Mooney (National Univ. of Ireland Maynooth), Adam Winstanley (National Univ. of Ireland Maynooth),
A Convexity Measure for Open and Closed Contours
Yu Chen (Univ. of Cambridge), Duncan Robertson (Metail Inc.), Roberto Cipolla (Univ. of Cambridge),
A Practical System for Modelling Body Shapes from Single View Measurements
Florent Brunet (IMFT), Emmanuel Cid (IMFT), Adrien Bartoli (CNRS),
Simultaneous Image Registration and Monocular Volumetric Reconstruction of a Fluid Flow
Hao Du (Univ. of Washington), Dan Goldman (Adobe Systems), Steven Seitz (Univ. of Washington),
Binocular Photometric Stereo

Images and Shape I

Yair Adato (Ben Gurion Univ. of the Negev), Ohad Ben-Shahar (Ben Gurion Univ. of the Negev),
Specular Flow and Shape in One Shot:
Charles-Alban Deledalle (Telecom ParisTech), Joseph Salmon (Université Paris Diderot), Arnak Dalalyan (École des Ponts ParisTech),
Image denoising with patch based PCA: local versus global
Anna Hilsmann (Fraunhofer HHI), David Schneider (Fraunhofer HHI), Peter Eisert (Fraunhofer HHI),
Template-free Shape From Texture with Perspective Cameras

Images and Shape II

Jimei Yang (UC Merced), Ming-Hsuan Yang (UC Merced),
Learning Hierarchical Image Representation with Sparsity, Saliency and Locality
Oliver Woodford (Toshiba Research Europe Ltd.), Minh-Tri Pham (Toshiba Research Europe Ltd.), Atsuto Maki (Toshiba Research Europe Ltd.), Frank Perbet (Toshiba Research Europe Ltd.), Bjorn Stenger (Toshiba Research Europe Ltd.),
Demisting the Hough Transform for 3D Shape Recognition and Registration
Kun Liu (Univ. of Freiburg), Henrik Skibbe (Univ. of Freiburg), Thorsten Schmidt (Univ. of Freiburg), Thomas Blein (Univ. of Freiburg), Klaus Palme (Univ. of Freiburg), Olaf Ronneberger (Univ. of Freiburg),
3D Rotation-Invariant Description from Tensor Operation on Spherical HOG Field
Mukta Prasad (ETH Zurich), Jan Knopp (KUL), Luc Van Gool (ETH Zurich),
Class-specific 3D localization using constellations of object parts
Haithem Boussaid (École Centrale de Paris), Samuel Kadoury (Philips Research North America), Iasonas Kokkinos (École Centrale de Paris), Jean-Yves Lazennec (CHU Pitié Salpétrière - Paris), Guoyan Zheng (ISTB), Nikos Paragios (École Centrale de Paris),
3D Model-based Reconstruction of the Proximal Femur from Low-dose Biplanar X-Ray Images

Face and Gesture

Vahid Kazemi (KTH), Josephine Sullivan (KTH),
Face Alignment with Part-Based Modeling
Mert Özcan (ETH Zurich), Luo Jie (EPFL), Vittorio Ferrari (ETH Zurich), Barbara Caputo (IDIAP),
A Large-Scale Database of Images and Captions for Automatic Face Naming
Patrick Sauer (Univ. of Manchester), Tim Cootes (Univ. of Manchester), Chris Taylor (Univ. of Manchester),
Accurate Regression Procedures for Active Appearance Models
Ben Daubney (Swansea Univ.), Xianghua Xie (Swansea Univ.),
Entropy Driven Hierarchical Search for 3D Human Pose Estimation

3rd UK Computer Vision Students' Workshop

Proceedings