Accepted Papers


This year BMVC received 414 valid paper submissions, of which 32 were accepted for oral presentation (8%) and 100 were accepted as posters (24%).

The BMVC 2012 conference programme is now available.


Oral Presentations


29Using Richer Models for Articulated Pose Estimation of Footballers
 Vahid Kazemi, Josephine Sullivan
51Let the Shape Speak - Discriminative Face Alignment using Conjugate Priors
 Pedro Martins, Rui Caseiro, Joao Henriques, Jorge Batista
53A Videography Analysis Framework for Video Retrieval and Summarization
 Kang Li, Sangmin Oh, A. G. Amitha Perera, Yun Fu
55Image Segmentation using Dual Distribution Matching
 Tatsunori Taniai, Viet Pham, Keita Takahashi, Takeshi Naemura
94Transfer Learning by Ranking for Weakly Supervised Object Annotation
 Zhiyuan Shi, Parthipan Siva, Tao Xiang
124PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation
 Frederic Besse, Carsten Rother, Andrew Fitzgibbon, Jan Kautz
143Stixmentation - Probabilistic Stixel based Traffic Scene Labeling
 Friedrich Erbs, Uwe Franke, Beate Schwarz
145Him-vs-Her Classifiers and Identity-Preserving Alignment for Face Verification
 Thomas Berg, Peter Belhumeur
156Data-Driven Scene Understanding from 3D Models
 Scott Satkin, Jason Lin, Martial Hebert
197Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts
 Tomas Pfister, James Charles, Mark Everingham, Andrew Zisserman
217Improved Geometric Verification for Large Scale Landmark Image Collections
 Rahul Raguram, Joseph Tighe, Jan-Michael Frahm
238Dense Active Appearance Models Using a Bounded Diameter Minimum Spanning Tree
 Robert Anderson, Bjorn Stenger, Roberto Cipolla
240MoT - Mixture of Trees Probabilistic Graphical Model for Video Segmentation
 Ignas Budvytis, Vijay Badrinarayanan, Roberto Cipolla
241Deformable 3D Reconstruction with an Object Database
 Pablo Alcantarilla, Adrien Bartoli
245Close-Range Human Detection and Tracking for Head-Mounted Cameras
 Dennis Mitzel, Bastian Leibe
251Learning discriminative space-time actions from weakly labelled videos
 Michael Sapienza, Fabio Cuzzolin, Philip Torr
256Incremental Light Bundle Adjustment
 Vadim Indelman, Richard Roberts, Chris Beall, Frank Dellaert
309Do We Need More Training Data or Better Models for Object Detection?
 Xiangxin Zhu, Carl Vondrick, Deva Ramanan, Charless Fowlkes
316Fast Non-uniform Deblurring using Constrained Camera Pose Subspace
 Zhe Hu, Ming-Hsuan Yang
327Enhancing Exemplar SVMs using Part Level Transfer Regularization
 Yusuf Aytar, Andrew Zisserman
335Deformable Tracking of Textured Curvilinear Objects
 Nicolas Padoy, Gregory Hager
344Scene Text Recognition using Higher Order Language Priors
 ANAND MISHRA, Karteek Alahari, CV Jawahar
422Latent SVMs for Human Detection with a Locally Affine Deformation Field
 Lubor Ladicky, Andrew Zisserman, Philip Torr
446Improved Initialization and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference
 Vibhav Vineet, Jonathan Warrell, Paul Sturgess, Philip Torr
492Image Retrieval for Image-Based Localization Revisited
 Torsten Sattler, Tobias Weyand, Bastian Leibe, Leif Kobbelt
499Efficient Kernels Couple Visual Words Through Categorical Opponency
 Ioannis Alexiou, Anil Bharath
515Dynamical Pose Filtering for Mixtures of Gaussian Processes
 Martin Fergie, Aphrodite Galata
572Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
 Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-Line Alberi Morel
583Cross-View Action Recognition via a Transferable Dictionary Pair
 Jingjing Zheng, Zhuolin Jiang, Jonathon Phillips, Rama Chellappa
588Detection and Tracking of Occluded People
 Siyu Tang, Mykhaylo Andriluka, Bernt Schiele
589An Object Co-occurrence Assisted Hierarchical Model for Scene Understanding
 Xin Li, Yuhong Guo
614Spatio-Temporal Convolutional Sparse Auto-Encoder for Sequence Classification
 Moez Baccouche, Franck Mamalet, Christian Wolf, Christophe Garcia, Atilla Baskurt
 
 

Poster Presentations


4Sparsity Potentials for Detecting Objects with the Hough Transform
 Nima Razavi, Nima Sedaghat Alvar, Juergen Gall, Luc Van Gool
14Gradient Edge Map Features for Frontal Face Recognition under Extreme Illumination Changes
 Ognjen Arandjelovic
25Fine Grained Character Recognition in the Wild
 Karthik Sheshadri
26Efficient Learning-based Image Enhancement: Application to Super-resolution and Compression Artifact Removal
 Younghee Kwon, Kwang In Kim, Jin Kim, Christian Theobalt
33Contour-HOG: A Stub Feature based Level Set Method for Learning Object Contour
 Zhi Yang, Yu Kong, Yun Fu
37Virtual Line Descriptor and Semi-Local Graph Matching Method for Reliable Feature Correspondence
 Zhe Liu, Renaud Marlet
44Learning Edge-Specific Kernel Functions For Pairwise Graph Matching
 Michael Donoser, Martin Urschler, Horst Bischof
52Genetic Programming-Evolved Spatio-Temporal Feature Descriptor for Human Action Recognition
 Li Liu, Ling Shao, Peter Rockett
68Racing Bib Numbers Recognition
 Idan Ben-Ami, Tali Basha, shai Avidan
70Learning Discriminative Chamfer Regularization
 Pradeep Yarlagadda, Angela Eigenstetter, Bjorn Ommer
81Feature Mining for Localised Crowd Counting
 Ke Chen, Chen Change Loy, Shaogang Gong, Tony Xiang
84Super-Resolution from Corneal Reflections
 Christian Nitschke, Atsushi Nakazawa
87Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach
 Dima Damen, Pished Bunnun, Andrew Calway, Walterio Mayol-Cuevas
91Person Re-identification by Attributes
 Ryan Layne, Tim Hospedales, Shaogang Gong
96A Closed Form Solution for the Self-Calibration of Heterogeneous Sensors
 Marco Crocco, Alessio Del Bue, Igor Barros Barbosa, Vittorio Murino
97Exemplar-Based Colour Constancy
 Hamid Reza Vaezi Joze, Mark Drew
104Exploiting relationship between attributes for improved face verification
 Fengyi Song, Xiaoyang Tan, Songcan Chen
109Single Image Segmentation with Estimated Depth
 Ryo Yonetani, Akisato Kimura, Hitoshi Sakano, Ken Fukuchi
113Teaching Stereo Perception to YOUR Robot
 Marcus Wallenberg, Per-Erik Forssén
120Recognizing activities with cluster-trees of tracklets
 Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid
121Detecting planes and estimating their orientation from a single image
 Osian Haines
123Efficient Point Feature Tracking based on Self-aware Distance Transform
 Min-Gyu Park, Kuk-Jin Yoon
127Doo-Sabin Surface Models with Biomechanical Constraints for Kalman Filter Based Endocardial Wall Tracking in 3D+T Echocardiography
 Engin Dikici, Gabriel Kiss, Anders Thorstensen, Fredrik Orderud, Hans Torp
130Incremental depthmap fusion for Large-scale scene
 Enliang Zheng, Rahul Raguram, Enrique Dunn, Jan-Michael Frahm
142Recovery of Slice Rotations with the Stack Alignment Transform in Cardiac MR Series
 Constantine Zakkaroff, Aleksandra Radjenovic, John Greenwood, Derek Magee
146Fine-Grained Categorization for 3D Scene Understanding
 Michael Stark, Jonathan Krause, Bojan Pepik, Bernt Schiele, Daphne Koller, David Meger, James Little
176Probabilistic Correspondence Matching using Random Walk with Restart
 Changjae Oh, Bumsub Ham, Kwanghoon Sohn
185Corner Matching Refinement for Monocular Pose Estimation
 Dinesh Gamage, Tom Drummond
194Unsupervised Feature Selection Via Hypergraph Embedding
 Zhihong Zhang, Edwin Hancock, Peng Ren
196Discriminative Hough Forests for Object Detection
 Paul Wohlhart, Samuel Schulter, Peter Roth
203Curvature Based Robust Descriptors
 Farlin Mohideen, Ranga Rodrigo
206GlandVision: A Novel Polar Space Random Field Model for Glandular Biological Structure Detection
 Hao Fu, Guoping Qiu, Mohammad Ilyas, Jie Shu
211Depth Correction for Depth Camera From Planarity
 Amira BELHEDI, Adrien Bartoli, vincent gay-bellile, Patrick Sayd, BOURGEOIS Steve, kamel hamrouni
215Gesture-based Object Recognition using Histograms of Guiding Strokes
 Amir Sadeghipour, Louis-Philippe Morency, Stefan Kopp
228Prime Shapes in Natural Images
 Qi Wu, Peter Hall
229An Evaluation of 3-d Local Descriptors for Object Categorization in Probabilistic Volumetric Scenes
 Maria Restrepo, Joseph Mundy
232Learning geometrical transforms between multi camera views using Canonical Correlation Analysis
 Christian Conrad, Rudolf Mester
233Structured Learning for Multiple Object Tracking
 Wang Yan, Xiaoye Han, Vladimir Pavlovic
236Metric Learning from Poses for Temporal Clustering of Human Motion
 Adolfo López-Méndez, Juergen Gall, Josep Casas, Luc Van Gool
248Divergence-Based One-Class Classification Using Gaussian Processes
 Paul Bodesheim, Erik Rodner, Alexander Lütz, Joachim Denzler
259Hierarchical Sparse Spectral Clustering For Image Set Classification
 Arif Mahmood Mahmood, Ajmal Mian
262Manifold-enhanced Segmentation through Random Walks on Linear Subspace Priors
 Pierre-Yves Baudin, Noura Azzabou, Pierre Carlier, Nikos Paragios
263Towards Longer Long-Range Motion Trajectories
 Michael Rubinstein, Ce Liu
265Non-parametric synthesis of laminar volumetric textures from a 2D sample
 Radu URS, Jean-Pierre Da Costa, Jean-Marc Leyssale, Geerard Vignoles, Christian Germain
266Motion Models that Only Work Sometimes
 Cristina Garcia Cifuentes, Marc Sturzel, Frederic Jurie, Gabriel Brostow
268Depiction Inviariant Object Matching
 Anupriya Balikai, Peter Hall
274BiCov: a novel image representation for person re-identification and face verification
 Bingpeng MA, Yu Su, Frederic Jurie
285Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates
 Danhang Tang, Yang Liu, Tae-Kyun Kim
288A method for improving consistency in photometric databases
 Felipe Hernández-Rodríguez, Mario Castelán
301Liberating Objects from Bounding Boxes
 Santosh Kumar Divvala, Alexei Efros, Martial Hebert
303MaxFlow Revisited: An Empirical Comparison of Maxflow Algorithms for Dense Vision Problems
 Tanmay Verma, Dhruv Batra
311Scalable Cascade Inference for Semantic Image Segmentation
 Paul Sturgess, Lubor Ladicky, Nigel Crook, Philip Torr
325Image Text Detection Using a Bandlet-Based Edge Detector and Stroke Width Transform
 Ali Mosleh, Nizar Bouguila, A. Ben Hamza
341Higher-order Co-occurrence Features based on Discriminative Co-clusters for Image Classification
 Takumi Kobayashi
359An Assessment of Visual Discomfort Caused by Motion-in-Depth in Stereoscopic 3D Video
 Sang-Hyun Cho, Hang-Bong Kang
369MCMC Supervision for People Re-identification in Nonoverlapping Cameras
 Boris Meden, Frédéric Lerasle, Patrick Sayd
374Object Matching Using Boundary Descriptors
 Ognjen Arandjelovic
387Transductive Kernel Map Learning and Its Application Image Annotation
 Phong Vo, Hichem Sahbi
389Multi-camera Pedestrian Detection with Multi-view Bayesian Network Model
 peixi Peng, Yonghong Tian, Yaowei Wang, Tiejun Huang
398Online Feedback for Structure-from-Motion Image Acquisition
 Christof Hoppe, Manfred Kopschitz, Markus Rumpler, Andreas Wendel, Horst Bischof, Stefan Kluckner
403Efficient Exemplar Word Spotting
 Jon Almazán, Albert Gordo, Alicia Fornés, Ernest Valveny
405Novel Line Descriptor for Line-based SLAM
 Keisuke Hirose, Hideo Saito
407A local Rayleigh model with spatial scale selection for Ultrasound image segmentation
 Boukerroui Djamal
411Hash-Based Support Vector Machines Approximation for Large Scale Prediction
 Saloua Litayem Ouertani, Alexis Joly, Nozha Boujemaa
412Leveraging over prior knowledge for online learning of visual categories
 Tatiana Tommasi, Francesco Orabona, mohsen Kaboli, Barbara Caputo
414Unsupervised Texture Segmentation using Active Contours and Local Distributions of Gaussian Markov Random Field Parameters
 Chathurika Dharmagunawardhana, Sasan Mahmoodi, Michael Bennet, Mahesan Niranjan
416Spatial orientations of visual word pairs to improve Bag-of-Visual-Words model
 Rahat Khan, Cecile BARAT, Damien Muselet, Christophe DUCOTTET
418Binocular projection of a random scene
 Miles Hansard
421Visual words assignment on the graph via minimal information loss
 Yanjun Qian, Yue Deng, Qionghai Dai, Yipeng Li, Guihua Er
445Multiple queries for large scale particular object retrieval
 Relja Arandjelovic, Andrew Zisserman
452A Learning-free Classification Framework for Textures, Writers, and Materials
 Radu Timofte, Luc Van Gool
458Comparing Visual Feature Coding for Learning Disjoint Camera Dependencies
 Xiatian Zhu, Shaogang Gong, Chen Change Loy
471Fixing the Locally Optimized RANSAC
 Karel Lebeda, Jiri Matas, Ondrej Chum
474One-sided Radial-Fundamental Matrix Estimation
 José Henrique Brito, Christopher Zach, Kevin Koeser, Manuel Ferreira, Marc Pollefeys
477Through-the-Lens Synchronisation for Heterogeneous Camera Networks
 Evren Imre, Adrian Hilton
493Indoor Scene Recognition using Task and Saliency-driven Feature Pooling
 Marco Fornoni, Barbara Caputo
500Face Recognition using Local Quantized Patterns
 Sibt ul Hussain, Thibault Napoléon, Frederic Jurie
514Context Aware Keypoint Extraction for Robust Image Representation
 Pedro Martins, Paulo Carvalho, Carlo Gatta
516Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification
 Giovani Chiachia, Nicolas Pinto, William Schwartz, Anderson Rocha, Alexandre Falcăo, David Cox
524Image Classification by Hierarchical Spatial Pooling with Partial Least Squares Analysis
 Jun Zhu, Weijia Zou, Xiaokang Yang, Rui Zhang, Quan Zhou, Wenjun Zhang
526On Cross-Spectral Stereo Matching using Dense Gradient Features
 Peter Pinggera, Toby Breckon, Horst Bischof
529Shape from Shading for Rough Surfaces: Analysis of the Oren-Nayar Model
 Yong Chul Ju, Michael Breuss, Andres Bruhn, Silvano Galliani
533Finding Groups of Duplicate Images In Very Large Dataset
 Winn Voravuthikunchai, Bruno Cremilleux, Frederic Jurie
536Fast and Robust Surface Normal Integration by a Discrete Eikonal Equation
 Silvano Galliani, Michael Breuss, Yong Chul Ju
537Multi-step flow fusion: towards accurate and dense correspondences in long video shots
 Tomas Crivelli, Pierre-Henri Conze, Philippe Robert, Matthieu Fradet, Patrick Perez
542Fusing Structured Light Consistency and Helmholtz Normals for 3D Reconstruction
 Michael Weinmann, Roland Ruiters, Aljosa Osep, Christopher Schwartz, Reinhard Klein
546Resolution Aware 3D Morphable Model
 Guosheng Hu, Chi Ho Chan, Josef Kittler, Bill Christmas
548Learning to rank images using semantic and aesthetic labels
 Naila Murray, Luca Marchesotti, Florent Perronnin
553Online Bayesian Non-parametrics for Social Group Detection
 Matteo Zanotto, Loris Bazzani, Vittorio Murino, Marco Cristani
561Moving Volume KinectFusion
 Henry Roth, Marsette Vona
5636D Relocalisation for RGBD Cameras Using Synthetic View Regression
 Andrew Gee, Walterio Mayol-Cuevas
565Image Priors for Image Deblurring with Uncertain Blur
 Daniele Perrone, Avinash Ravichandran, René Vidal, Paolo Favaro
568Improvements in Joint Domain-Range Modeling for Background Subtraction
 Manjunath Narayana, Allen Hanson, Erik Learned-Miller
573A Multi-layer Composite Model for Human Pose Estimation
 Kun Duan, Dhruv Batra, David Crandall
574Prioritizing the Propagation of Identity Beliefs for Multi-object Tracking
 Amit K. C., Christophe De Vleeschouwer
593Face Alignment Using a Ranking Model based on Regression Trees
 Hua Gao, Hazim Ekenel, Rainer Stiefelhagen
605Binary Pattern Analysis for 3D Facial Action Unit Detection
 Georgia Sandbach, Stefanos Zafeiriou, Maja Pantic
606A Phase Field Method for Tomographic Reconstruction from Limited Data
 Russell Hewett, Ian Jermyn, Michael Heath, Farzad Kamalabadi
625Adaptive hierarchical contexts for object recognition
 Billy Peralta, Pablo Espinace, Alvaro Soto
653Local Shape Representation in 3D: from Weighted Spherical Harmonics to Spherical Wavelet
 Chengjin Du, John Ferguson, Philip Hawkins, Len Stephens, Till Bretschneider