Banner BMVC 2009 London

7th . 10th September





Tuesday September


Invited Speaker 9.00-10.00pm

Rama Chellappa, University of Maryland

Compressive Sensing for Computer Vision: Hype vs Hope


Object Recognition I . 10.00-11.00am


1.      On the completeness of coding with image features, Wolfgang Förstner, Timo Dickscheid and Falko Schindler[Abstract]

2.      Learning Models for Object Recognition from Natural Language Descriptions, Josiah Wang, Katja Markert and Mark Everingham.[Abstract]

3.      Better appearance models for pictorial structures, Marcin Eichner and Vittorio Ferrari


Segmentation I - 11.20am-12.20pm


1.      Bilateral Symmetry Detection via Symmetry-Growing, Minsu Cho and Kyoung Mu Lee[Abstract]

2.      Real-time texture boundary detection from ridges in the standard deviation space, Ray Hidayat and Richard Green[Abstract]

3.      Category-Specific Object Recognition and Segmentation Using a Skeletal Shape Model, Nhon Trinh and Benjamin Kimia


Posters I . 2.00-3.40pm


1.      SURF-Face: Face Recognition Under Viewpoint Consistency Constraints, Philippe Dreuw, Pascal Steingrube, Harald Hanselmann and Hermann Ney[Abstract]

2.      Unified Stereo-Based 3D Head Tracking Using Online Illumination Modeling, Kwang Ho An and Myung Jin Chung[Abstract]

3.      Neighborhood Preserving Nonnegative Matrix Factorization, Quanquan Gu and Jie Zhou[Abstract]

4.      Detecting local audio-visual synchrony in monologues utilizing vocal pitch and facial landmark trajectories, Steven Cadavid, Mohamed Abdel-Mottaleb, Daniel S. Messinger, Mohammad H. Mahoor and Lorraine E. Bahrick[Abstract]

5.      Backing Off: Hierarchical Decomposition of Activity for 3D Novel Pose Recovery, John Darby, Baihua Li, Nicholas Costen, David Fleet and Neil Lawrence[Abstract]

6.      3D Human Body-Part Tracking and Action Classification Using A Hierarchical Body Model, Leonid Raskin, Michael Rudzsky and Ehud Rivlin [Video][Abstract]

7.      Modelling Multi-object Activity by Gaussian Processes, Chen Change Loy, Tao Xiang and Shaogang Gong[Abstract]

8.      Guiding Visual Surveillance by Tracking Human Attention, Ben Benfold and Ian Reid [Video][Abstract]

9.      3D Extended Histogram of Oriented Gradients (3DHOG) for Classification of Road Users in Urban Scenes, Norbert Buch, James Orwell and Sergio Velastin [Supplementary Material][Video1][Video2][Abstract]

10.  A Comparative Analysis of Radial-Tchebichef Moments and Zernike Moments, Ramakrishnan Mukundan[Abstract]

11.  Real-time Stable Texture Regions Extraction for Motion-based Object Segmentation, Dubravko Culibrk, Borislav Antic and Vladimir Crnojevic [Video][Abstract]

12.  A Unified Bayesian Framework for Adaptive Visual Tracking, Emanuel Zelniker, Timothy Hospedales, Shaogang Gong and Tao Xiang [Supplementary Material][Abstract]

13.  Haar Local Binary Pattern Feature for Fast Illumination Invariant Face Detection, Anindya Roy and Sebastien Marcel[Abstract]

14.  Ranking user-annotated images for multiple query terms, Moray Allan and Jakob Verbeek[Abstract]

15.  On-line Learning of Shape Information for Object Segmentation and Tracking, John Chiverton, Majid Mirmehdi and Xianghua Xie[Abstract]

16.  Shape-from-shading driven 3D Morphable Models for Illumination Insensitive Face Recognition , Ankur Patel and William Smith[Abstract]

17.  Associating Groups of People, Wei-Shi Zheng, Shaogang Gong and Tao Xiang[Abstract]

18.  Segmentation Based Interest Points and Evaluation of Unsupervised Image Segmentation Methods, Piotr Koniusz and Krystian Mikolajczyk[Abstract]

19.  Semantic Image Classification using Consistent Regions and Individual Context, Stefan Kluckner, Thomas Mauthner, Peter M. Roth and Horst Bischof[Abstract]

20.  Latent Semantics Local Distribution for CRF-based Image Semantic Segmentation, Giuseppe Passino, Ioannis Patras and Ebroul Izquierdo[Abstract]

21.  Contour Segment Matching by Integrating Intra and Inter Shape Cues of Objects, Ishani Chakraborty and Ahmed Elgammal[Abstract]

22.  Bag of Optical Flow Volumes for Image Sequence Recognition, Hayko Riemenschneider, Michael Donoser and Horst Bischof[Abstract]

23.  Object Recognition with 3D Models, Bernd Heisele, Gunhee Kim and Andrew Meyer[Abstract]

24.  Log-Linear Mixtures for Object Class Recognition, Tobias Weyand, Thomas Deselaers and Hermann Ney[Abstract]

25.  Learning-based Face Synthesis for Pose-Robust Recognition from Single Image , Akshay Asthana, Conrad Sanderson, Tom Gedeon and Roland Goecke [Supplementary Material][Abstract]

26.  Semi-Supervised Discriminant Analysis via Spectral Transduction, Deming Zhai, Hong Chang, Bo Li, Shiguang Shan, Xilin Chen and Wen Gao[Abstract]

27.  New Conditional Sampling Strategies for Speeded-Up RANSAC, Tom Botterill, Steven Mills and Richard Green[Abstract]

28.  HMM based Archive Film Defect Detection with Spatial and Temporal Constraints, Xiaosong Wang and Majid Mirmehdi[Abstract]

29.  Incremental Visual Hull Reconstruction, Ali Bigdelou, Alexander Ladikos and Nassir Navab [Video][Abstract]

30.  Bundle Adjustment using Conjugate Gradients with Multiscale Preconditioning, Martin Byröd and Karl Åström[Abstract]

31.  Particle Filter Approach Adapted to Catadioptric Images for Target Tracking Application, Jean-Charles Bazin, Kuk-Jin Yoon, Inso Kweon, Cedric Demonceaux and Pascal Vasseur[Abstract]

32.  Combining meshes and geometric primitives for accurate and semantic modeling, Florent Lafarge, Renaud Keriven and Mathieu Bredif[Abstract]

33.  Obtaining the Shape of a Moving Object with a Specular Surface, Atsuto Maki and Roberto Cipolla[Abstract]

34.  Shape From Motion of Nonrigid Objects: The Case of Isometrically Deformable Flat Surfaces, Ricardo Ferreira, João Xavier and João Costeira[Abstract]

35.  Minimal Solutions for Panoramic Stitching with Radial Distortion, Martin Byröd, Matthew Brown and Karl Åström[Abstract]

36.  Efficient Disparity Computation without Maximum Disparity for Real-Time Stereo Vision, Christian Unger, Selim Benhimane, Eric Wahl and Nassir Navab[Abstract]

37.  Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement, Jose Martinez-Carranza and Andrew Calway [Video][Abstract]

38.  Algebraic Line Search for Bundle Adjustment, Julien Michot, Adrien Bartoli and Francois Gaspard [Supplementary Material][Abstract]

39.  Robust Density Comparison for Visual Tracking, Omar Arif and Patricio Vela [Supplementary Material][Abstract]

40.  An implicit non-linear numerical scheme for illumination-robust variational optical flow, Sandor Fazekas, Dmitry Chetverikov and Jozsef Molnar[Abstract]

41.  PWP3D: Real-time segmentation and tracking of 3D objects, Victor Prisacariu and Ian Reid [Supplementary Material][Abstract]

42.  Clustering Videos by Location, Florian Schroff, Larry Zitnick and Simon Baker[Abstract]

43.  Hierarchical Image-Region Labeling via Structured Learning, Julian McAuley, Teofilo De Campos, Gabriela Csurka and Florent Perronnin[Abstract]

44.  Edge-Directed Interpolation in a Bayesian Framework, Karen Simonyan and Dmitriy Vatolin[Abstract]

45.  An Empirical Camera Model for Internet Color Vision, Ayan Chakrabarti, Daniel Scharstein and Todd Zickler[Abstract]

46.  Automatic Camera Calibration Applied to Medical Endoscopy , Joao Barreto, Jose Roquette, Peter Sturm and Fernando Fonseca[Abstract]

47.  Next best view planning for active model improvement, Enrique Dunn and Jan-Michael Frahm


Registration, Geometry and Stereo . 4.00-5.40pm


1.      A Constant-Time Efficient Stereo SLAM System, Christopher Mei, Gabe Sibley, Marc Cummins, Paul Newman and Ian Reid[Abstract]

2.      Disparity estimation in stereo sequences using scene flow, Fang Liu and Vasanth Philomin[Abstract]

3.      Multi-View Geometry of the Refractive Plane, Visesh Chari and Peter Sturm[Abstract]

4.      Estimation of Location Uncertainty for Scale Invariant Features Points, Bernhard Zeisl, Pierre Georgel, Florian Schweiger, Eckehard Steinbach and Nassir Navab [Video][Abstract]

5.      Multiple Target Localisation at over 100 FPS, Simon Taylor and Tom Drummond



Wednesday September


Invited Speaker 9.00-10.00pm

Alexei Efros, Carnegie Mellon University

What can the world tell us about an image?


Segmentation II - 10.00-11.00pm


1.      Semantic Scene Segmentation using Random Multinomial Logit, Ananth Ranganathan[Abstract]

2.      Fast Segmentation via Randomized Hashing, Camillo J. Taylor and Anthony Cowley[Abstract]

3.      Multiframe Motion Segmentation via Penalized MAP Estimation and Linear Programming, Han Hu, Quanquan Gu, Lei Deng and Jie Zhou


Object Recognition II . 11.20-12.20pm


1.      Combining Appearance and Structure from Motion Features for Road Scene Understanding, Paul Sturgess, Karteek Alahari, Lubor Ladicky and Philip H.S. Torr [Video][Abstract]

2.      Object Localization with Global and Local Context Kernels, Matthew Blaschko and Christoph Lampert[Abstract]

3.      PRISM: PRincipled Implicit Shape Model, Alain Lehmann, Bastian Leibe and Luc Van Gool


Posters . 2.00-3.40pm


1.      Palmprint based Verification System Robust to Occlusion using Low-order Zernike Moments of Sub-image, Badrinath Srinivas, Naresh Kachi and Phalguni Gupta[Abstract]

2.      Interactive Texture Segmentation using Random Forests and Total Variation, Jakob Santner, Markus Unger, Thomas Pock, Christian Leistner, Amirreza Saffari and Horst Bischof [Video][Abstract]

3.      A Latent Model for Visual Disambiguation of Keyword-based Image Search , Kongwah Wan, Ahhwee Tan, Joohwee Lim, Liang-Tien Chia and Sujoy Roy[Abstract]

4.      Cancer cell detection and invasion depth estimation in brightfield images, Pedro Quelhas, Monica Marcuzzo, Ana Maria Mendonça, Maria José Oliveira and Aurelio Campilho[Abstract]

5.      A Framework For Evaluating Visual SLAM, Tobias Pietzsch and Jan Funke[Abstract]

6.      Time based Activity Inference using Latent Dirichlet Allocation, Tanveer Faruquie, Prem Kalra and Subhashis Banerjee[Abstract]

7.      Dynamic Partitioned Sampling For Tracking With Discriminative Features, Stefan Duffner, Jean-Marc Odobez and Elisa Ricci [Video][Abstract]

8.      Unsupervised Learning of Stereo Vision with Monocular Depth Cues, Hoang Trinh and David McAllester[Abstract]

9.      Variance Ranklets: orientation-selective rank features for contrast modulations, George Azzopardi and Fabrizio Smeraldi[Abstract]

10.  From Rank-N to Rank-1 Face Recognition Based on Motion Similarity, Hui Fang and Nicholas Costen[Abstract]

11.  Incremental learning of dynamical models of faces, Cyril Charron, Yulia Hicks, Peter Hall and Darren Cosker [Video][Abstract]

12.  Face Pose Estimation in Uncontrolled Environments, Jania Aghajanian and Simon J.D. Prince[Abstract]

13.  Multiple One-Shots for Utilizing Class Label Information, Yaniv Taigman, Lior Wolf and Tal Hassner[Abstract]

14.  Hough transform-based mouth localization for audio-visual speech recognition, Gabriele Fanelli, Jürgen Gall and Luc Van Gool[Abstract]

15.  The effect of pose on Facial Expression Recognition, Stephen Moore and Richard Bowden[Abstract]

16.  The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories, Tatiana Tommasi and Barbara Caputo[Abstract]

17.  Performance Evaluation of RANSAC Family, Sunglok Choi, Taemin Kim and Wonpil Yu[Abstract]

18.  Face recognition using tensors of census transform histograms from Gaussian features maps, John Ruiz-Hernandez, James Crowley, Antoine Meler and Augustin Lux[Abstract]

19.  VillageFinder: Segmentation of Nucleated Villages in Satellite Imagery, Kashif Murtaza, Sohaib Khan and Nasir Rajpoot[Abstract]

20.  Segmentation-Based Urban Traffic Scene Understanding, Andreas Ess, Tobias Mueller, Helmut Grabner and Luc Van Gool [Video][Abstract]

21.  Hierarchical Image Matching for Pose-invariant Face Recognition, Shervin Rahimzadeh Arashloo and Josef Kittler[Abstract]

22.  Learning Local Patch Orientation with a Cascade of Sparse Regressors, Alain Pagani and Didier Stricker [Video][Abstract]

23.  Multi-person tracking with overlapping cameras in complex, dynamic environments, Martijn Liem and Dariu Gavrila [Video][Abstract]

24.  Vistas: Hierarchial boundary priors using multiscale conditional random fields, Jonathan Warrell, Alastair Moore and Simon J.D. Prince[Abstract]

25.  Unsupervised Object Pose Classification from Short Video Sequences, Liang Mei, Min Sun, Kevin M. Carder, Alfred O. Hero III and Silvio Savarese[Abstract]

26.  Exemplar-based action recognition in video, Geert Willems, Jan Hendrik Becker, Tinne Tuytelaars and Luc Van Gool [Video][Abstract]

27.  Integral Channel Features, Piotr Dollar, Zhuowen Tu, Pietro Perona and Serge Belongie[Abstract]

28.  Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction, Damian Eads, Edward Rosten and David Helmbold[Abstract]

29.  Optimization framework for learning a hierarchical shape vocabulary for object class detection, Sanja Fidler, Marko Boben and Ales Leonardis[Abstract]

30.  Stereo-based Pedestrian Detection using Multiple Patterns, Hiroshi Hattori, Akihito Seki, Manabu Nishiyama and Tomoki Watanabe[Abstract]

31.  Combining Local and Global Shape Models for Deformable Object Matching, Philip Tresadern, Harish Bhaskar, Steve Adeshina, Chris Taylor and Tim Cootes[Abstract]

32.  Disparity from stereo-segment silhouettes of weakly-textured images, Babette Dellen and Florentin Woergoetter[Abstract]

33.  Incorporating Higher-Order Cues in Image Colorization, Tae Hoon Kim, Kyoung Mu Lee and Sang Uk Lee[Abstract]

34.  Non-parametric patch based video matting, Muhammad Sarim, Adrian Hilton and Jean-Yves Guillemaut[Abstract]

35.  Geometric Potential Force for the Deformable Model, Si Yong Yeo, Xianghua Xie, Igor Sazonov and Perumal Nithiarasu [Video][Abstract]

36.  Random Forest Clustering and Application to Video Segmentation, Frank Perbet, Bjorn Stenger and Atsuto Maki[Abstract]

37.  Parametric Trajectory Representations for Behaviour Classification, Rowland Sillito and Robert Fisher[Abstract]

38.  Semantic Shape Context for the Registration of Multiple Partial 3D Views, Samir Khoualed, Umberto Castellani and Adrien Bartoli[Abstract]

39.  Reconstruction from Uncalibrated Affine Silhouettes, Paul McIlroy and Tom Drummond[Abstract]

40.  Depth estimation with a practical camera, Arnav Bhavsar and Rajagopalan Ambasamudram[Abstract]

41.  Inpainting in Shape from Focus: Taking a Cue from Motion Parallax, Rajiv Sahay and Rajagopalan Ambasamudram [Video][Abstract]

42.  A shape-from-shading framework for satisfying data-closeness and structure-preserving smoothness constraints, Rui Huang and William Smith[Abstract]

43.  Selecting surface features for accurate multi-camera surface reconstruction, Thomas Popham and Roland Wilson[Abstract]

44.  Anisotropic Huber-L1 Optical Flow, Manuel Werlberger, Werner Trobin, Thomas Pock, Andreas Wedel, Daniel Cremers and Horst Bischof[Abstract]

45.  Two View Geometry from Uncertain Correspondences, Olof Enqvist and Fredrik Kahl[Abstract]

46.  Non-rigid structure from motion using quadratic deformation models, Joao Fayad, Alessio Del Bue, Lourdes Agapito and Pedro Aguiar [Video][Abstract]

47.  NURBS Warps, Florent Brunet, Adrien Bartoli, Nassir Navab and Rémy Malgouyres[Abstract]

48.  ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition, Qi Pan, Gerhard Reitmayr and Tom Drummond [Video][Abstract]


Applications . 4.00-5.40 pm


1.      Gait Representation Using Flow Fields, Khalid Bashir, Tao Xiang and Shaogang Gong[Abstract]

2.      Specularity and Shadow Interpolation via Robust Polynomial Texture Maps , Mark Drew, Nasim Hajari, Yacov Hel-Or and Tom Malzbender[Abstract]

3.      Learning generative texture models with extended Fields-of-Experts , Nicolas Heess, Christopher K.I. Williams and Geoffrey Hinton [Supplementary Material][Abstract]

4.      Get Out of my Picture! Internet-based Inpainting , Oliver Whyte, Josef Sivic and Andrew Zisserman[Abstract]

5.      Stochastic Image Denoising, Francisco Estrada, David Fleet and Allan Jepson



Thursday September


Faces and Heads . 9.30-10.50am


1.      3D head pose estimation from multiple distant views , Xenophon Zabulis, Thomas Sarmis and Antonis Argyros [Video][Abstract]

2.      3D-assisted Facial Texture Super-Resolution , Pouria Mortazavian, Josef Kittler and William Christmas[Abstract]

3.      Head Pose Classification in Crowded Scenes , Javier Orozco, Shaogang Gong and Tao Xiang[Abstract]

4.      Subtitle-free Movie to Script Alignment, Pramod Sankar K., C.V. Jawahar and Andrew Zisserman


Human Activity Recognition . 11.10am-12.30pm


1.      Multi-view synchronization of human actions and dynamic scenes , Emilie Dexter, Patrick Pérez and Ivan Laptev[Abstract]

2.      Attribute Multiset Grammars for Global Explanations of Activities , Dima Damen and David Hogg[Abstract]

3.      Evaluation of local spatio-temporal features for action recognition , Heng Wang, Muhammad Muneeb Ullah, Alexander Klaser, Ivan Laptev and Cordelia Schmid[Abstract]

4.      Mining visual actions from movies, Adrien Gaidon, Marcin Marszalek and Cordelia Schmid[Abstract]