Electronic Proceedings of the
British Machine Vision Conference 2013

Editors: Tilo Burghardt, Dima Damen, Walterio Mayol-Cuevas, Majid Mirmehdi

An electronic version of the Book of Abstracts distributed at BMVC 2013 is available.

Tutorial 1
1. Deep Learning for Machine Vision
Adam Coates (Stanford)
DOI: http://dx.doi.org/10.5244/C.27.1
Tutorial 2
2. Submodularity in Machine Learning and Vision
Andreas Krause (ETH Zurich)
DOI: http://dx.doi.org/10.5244/C.27.2
Keynote 1
3. Towards on-the-fly Large Scale Video Search
Andrew Zisserman (University of Oxford)
DOI: http://dx.doi.org/10.5244/C.27.3
Session 1: Statistics and Machine Learning for Computer Vision I
4. Metric Regression Forests for Human Pose Estimation
Gerard Pons-Moll (Leibniz University Hannover), Jonathan Taylor (University of Toronto), Jamie Shotton , Aaron Hertzmann , Andrew Fitzgibbon (Microsoft Research Cambridge)
DOI: http://dx.doi.org/10.5244/C.27.4
5. Label embedding for text recognition
Jose Rodriguez , Florent Perronnin (Xerox (XRCE) Grenoble)
DOI: http://dx.doi.org/10.5244/C.27.5
Session 2: Statistics and Machine Learning for Computer Vision II
6. Change Detection in Dynamic Scenes using Local Adaptive Transform
Hakan Haberdar (University of Houston), Shishir Shah (University of Houston)
DOI: http://dx.doi.org/10.5244/C.27.6
7. Learning beautiful (and ugly) attributes
Luca Marchesotti (Xerox), Florent Perronnin (Xerox (XRCE) Grenoble)
DOI: http://dx.doi.org/10.5244/C.27.7
8. Fisher Vector Faces in the Wild
Karen Simonyan (University of Oxford), Omkar Parkhi (University of Oxford), Andrea Vedaldi (University of Oxford), Andrew Zisserman (University of Oxford)
DOI: http://dx.doi.org/10.5244/C.27.8
9. Perception Preserving Projections
Saining Xie (Shanghai Jiao Tong University), Jiashi Feng (National University of Singapore), Shuicheng Yan (National University of Singapore), Hongtao Lu (Shanghai Jiao Tong University)
DOI: http://dx.doi.org/10.5244/C.27.9
10. A Novel Approach for Efficient SVM Classification with Histogram Intersection Kernel
Gaurav Sharma (University of Caen), Frederic Jurie (University of Caen)
DOI: http://dx.doi.org/10.5244/C.27.10
Session 3: Posters I
11. Inferring Ongoing Human Activities Based on Recurrent Self-Organizing Map Trajectory
Qianru Sun (Peking University), Hong Liu (Peking University)
DOI: http://dx.doi.org/10.5244/C.27.11
12. Match-time covariance for descriptors
Eric Christiansen (UC San Diego), Vincent Rabaud , Andrew Ziegler , David Kriegman (UCSD), Serge Belongie (UCSD)
DOI: http://dx.doi.org/10.5244/C.27.12
13. Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces
Pablo Alcantarilla (Georgia Institute of Technolog), Jesus Nuevo (TrueVision Solutions AU), Adrien Bartoli
DOI: http://dx.doi.org/10.5244/C.27.13
14. From Bikers to Surfers: Visual Recognition of Urban Tribes
Iljung Kwak (UCSD), Ana Murillo (University of Zaragoza), Peter Belhumeur (Columbia University), David Kriegman (UCSD), Serge Belongie (UCSD)
DOI: http://dx.doi.org/10.5244/C.27.14
15. Ultra-wide Baseline Aerial Imagery Matching in Urban Environments
Hani Altwaijry (UC San Diego), Serge Belongie (UCSD)
DOI: http://dx.doi.org/10.5244/C.27.15
16. FRIF: Fast Robust Invariant Feature
Zhenhua Wang (NLPR, CASIA), Bin Fan (NLPR, CASIA, CHINA), Fuchao Wu
DOI: http://dx.doi.org/10.5244/C.27.16
17. Distribution Fields with Adaptive Kernels for Large Displacement Image Alignment
Benjamin Mears (UMass Amherst), Laura Sevilla-Lara (UMass Amherst), Erik Learned-Miller (UMass Amherst)
DOI: http://dx.doi.org/10.5244/C.27.17
18. Fractal Approximate Nearest Neighbour Search in Log-Log Time
Martin Stommel (University of Bremen), Stefan Edelkamp (University of Bremen), Thiemo Wiedemeyer , Michael Beetz
DOI: http://dx.doi.org/10.5244/C.27.18
19. Flexible and User-Centric Camera Calibration using Planar Fiducial Markers
Shreyansh Daftry (Manipal Institute of Technology), Michael Maurer (Institute of Computer Graphics and Vision, Graz University of Technology), Andreas Wendel (Graz University of Technology), Horst Bischof (Graz University of Technology)
DOI: http://dx.doi.org/10.5244/C.27.19
20. Large-scale Learning of Sign Language by Watching TV (Using Co-occurrences)
Tomas Pfister (University of Oxford), James Charles (University of Leeds), Andrew Zisserman (University of Oxford)
DOI: http://dx.doi.org/10.5244/C.27.20
21. Detection of Abnormal Fish Trajectories Using a Clustering Based Hierarchical Classifier
Cigdem Beyan (University of Edinburgh), Robert Fisher
DOI: http://dx.doi.org/10.5244/C.27.21
22. Early Recurrence Improves Edge Detection
Xun Shi (York University), Bo Wang , John Tsotsos (York University)
DOI: http://dx.doi.org/10.5244/C.27.22
23. Modelling Visual Objects Invariant to Depictive Style
Qi Wu (University of Bath), Peter Hall (University of Bath)
DOI: http://dx.doi.org/10.5244/C.27.23
24. Free your Camera: 3D Indoor Scene Understanding from Arbitrary Camera Motion
Axel Furlan (University of Milano - Bicocca), Stephen D. Miller (Stanford University), Domenico G. Sorrenti (University of Milano - Bicocca), Li Fei-Fei (Stanford University), Silvio Savarese (University of Michigan at Ann Arbor)
DOI: http://dx.doi.org/10.5244/C.27.24
25. Exploring SVM for Image Annotation in Presence of Confusing Labels
Yashaswi Verma (IIIT, Hyderabad (India)), CV Jawahar
DOI: http://dx.doi.org/10.5244/C.27.25
26. Removing Mistracking of Multibody Motion Video Database Hopkins155
Yasuyuki Sugaya (Toyohashi University of Technology), Yuichi Matsushita (Toyohashi University of Tech.), Kenichi Kanatani (Okayama University)
DOI: http://dx.doi.org/10.5244/C.27.26
27. Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation
Yuliya Tarabalka (INRIA Sophia-Antipolis M\E9diterran\E9e), Guillaume Charpiat (INRIA Sophia-Antipolis M\E9diterran\E9e), Ludovic Brucker (NASA GSFC & Universities Space Research Association), Bjoern Menze (Computer Vision Laboratory, ETH Zurich)
DOI: http://dx.doi.org/10.5244/C.27.27
28. Deformable Part Models with Individual Part Scaling
Charles Dubout (Idiap Research Institute), Fran\E7ois Fleuret (Idiap Research Institute)
DOI: http://dx.doi.org/10.5244/C.27.28
29. Focusing Attention on Visual Features that Matter
Grace Tsai (University of Michigan), Benjamin Kuipers (University of Michigan)
DOI: http://dx.doi.org/10.5244/C.27.29
30. Object-Centric Spatio-Temporal Pyramids for Egocentric Activity Recognition
Tomas McCandless (University of Texas at Austin), Kristen Grauman (University of Texas at Austin)
DOI: http://dx.doi.org/10.5244/C.27.30
31. Learning to approximate global shape priors for figure-ground segmentation
Daniel Kuettel (ETH Zurich), Vittorio Ferrari
DOI: http://dx.doi.org/10.5244/C.27.31
32. What is a good evaluation measure for semantic segmentation?
Gabriela Csurka (Xerox Research Centre Europe ), Diane Larlus , Florent Perronnin (Xerox (XRCE) Grenoble)
DOI: http://dx.doi.org/10.5244/C.27.32
33. Harmonic Variance: A Novel Measure for In-focus Segmentation
Feng Li (Mitsubishi Electric Res. Labs), Fatih Porikli
DOI: http://dx.doi.org/10.5244/C.27.33
34. Robust Image Matching with Line Context
Wei Guan (University of Southern Califor), Suya You (University of Southern California)
DOI: http://dx.doi.org/10.5244/C.27.34
35. Sketch Recognition by Ensemble Matching of Structured Features
Yi Li (QMUL), Yi-Zhe Song , Shaogang Gong
DOI: http://dx.doi.org/10.5244/C.27.35
36. Learnable Stroke Models for Example-based Portrait Painting
Tinghuai Wang , John Collomosse (University of Surrey), Andrew Hunter (Hewlett Packard Laboratories), Darryl Greig (Hewlett Packard Laboratories)
DOI: http://dx.doi.org/10.5244/C.27.36
37. Bayesian region selection for adaptive dictionary-based Super-Resolution
Eduardo P\E9rez-Pellitero (Technicolor), Jordi Salvador (Technicolor), Javier Ruiz-Hidalgo (UPC), Bodo Rosenhahn
DOI: http://dx.doi.org/10.5244/C.27.37
38. Replicator Graph Clustering
Michael Donoser
DOI: http://dx.doi.org/10.5244/C.27.38
39. Of Gods and Goats: Weakly Supervised Learning of Figurative Art
Elliot Crowley (University of Oxford), Andrew Zisserman (University of Oxford)
DOI: http://dx.doi.org/10.5244/C.27.39
40. Multi-scale Joint Encoding of Local Binary Patterns for Texture and Material Classification
Xianbiao Qi (BUPT), Yu Qiao (SIAT), Chun-Guang Li (BUPT), Jun Guo (BUPT)
DOI: http://dx.doi.org/10.5244/C.27.40
41. Spectral Imaging Using Basis Lights
Antony Lam (National Institute of Informatics), Art Subpa-Asa , Imari Sato (National Institute of Informatics), Takahiro Okabe (Kyushu Institute of Technology), Yoichi Sato (The University of Tokyo)
DOI: http://dx.doi.org/10.5244/C.27.41
42. Generalised Perspective Shape from Shading with Oren-Nayar Reflectance
Yong Chul Ju (BTU Cottbus), Silvia Tozza (University of Rome), Michael Breuss (BTU Cottbus), Andres Bruhn (Univ of Stuttgart), Andreas Kleefeld (BTU Cottbus)
DOI: http://dx.doi.org/10.5244/C.27.42
43. High Frequency 3D Reconstruction from Unsynchronized Multiple Cameras
Yumi Kakumu (Nagoya Institute of Technology), Fumihiko Sakaue (Nagoya Institute of Technology), Jun Sato (Nagoya Institute of Technology), Kazuhisa Ishimaru (Nippon Soken Inc), Masayuki Imanishi (DENSO Corporation)
DOI: http://dx.doi.org/10.5244/C.27.43
44. Properties of Datasets Predict the Performance of Classifiers
Omid Aghazadeh (KTH), Stefan Carlsson (KTH)
DOI: http://dx.doi.org/10.5244/C.27.44
Session 4: Human Body Pose and Tracking
45. Multi-view Pictorial Structures for 3D Human Pose Estimation
Sikandar Amin (TU M\FCnchen), Mykhaylo Andriluka (MPI Informatics), Marcus Rohrbach (Max Planck Institute for Infor), Bernt Schiele
DOI: http://dx.doi.org/10.5244/C.27.45
46. Transitive Re-identification
Yulia Brand (Technion), Tamar Avraham (Technion), Michael Lindenbaum (Technion)
DOI: http://dx.doi.org/10.5244/C.27.46
47. Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts
James Charles (University of Leeds), Tomas Pfister (University of Oxford), Derek Magee (University of Leeds), David Hogg (University of Leeds), Andrew Zisserman (University of Oxford)
DOI: http://dx.doi.org/10.5244/C.27.47
48. Multi-view Body Part Recognition with Random Forests
Vahid Kazemi (KTH), Magnus Burenius (KTH), Hossein Azizpour (KTH), Josephine Sullivan
DOI: http://dx.doi.org/10.5244/C.27.48
Keynote 2
49. Factor Graphs for Fast and Scalable 3D Reconstruction and Mapping
Frank Dellaert (Georgia Tech)
DOI: http://dx.doi.org/10.5244/C.27.49
Session 5: Motion and Flow
50. The Complete Rank Transform: A Tool for Accurate and Morphologically Invariant Matching of Structures
Oliver Demetz (Saarland University), David Hafner (Saarland University), Joachim Weickert (Saarland University)
DOI: http://dx.doi.org/10.5244/C.27.50
51. Efficient Dense 3D Rigid-Body Motion Segmentation in RGB-D Video
J\F6rg St\FCckler (University of Bonn), Sven Behnke (Computer Science Institute VI, University of Bonn)
DOI: http://dx.doi.org/10.5244/C.27.51
Session 6: Video Analysis
52. Enhancing Action Recognition by Cross-Domain Dictionary Learning
Fan Zhu , Ling Shao (The University of Sheffield)
DOI: http://dx.doi.org/10.5244/C.27.52
53. Unsupervised Object Discovery and Segmentation in Videos
Samuel Schulter (TUGraz), Christian Leistner (Microsoft), Peter Roth , Horst Bischof (Graz University of Technology)
DOI: http://dx.doi.org/10.5244/C.27.53
54. Evaluating Superpixels in Video: Metrics Beyond Figure-Ground Segmentation
Peer Neubert (TU Chemnitz), Peter Protzel (TU Chemnitz)
DOI: http://dx.doi.org/10.5244/C.27.54
55. Solving Person Re-identification in Non-overlapping Camera using Efficient Gibbs Sampling
Vijay John (University of Amsterdam), Gwenn Englebienne , Ben Krose
DOI: http://dx.doi.org/10.5244/C.27.55
56. Spacetime Forests with Complementary Features for Dynamic Scene Recognition
Christoph Feichtenhofer ( Graz University of Technology), Axel Pinz (Graz University of Technology), Richard Wildes (York University)
DOI: http://dx.doi.org/10.5244/C.27.56
Session 7: Posters II
57. Hyperspectral Face Recognition using 3D-DCT and Partial Least Squares
Muhammad Uzair (UWA), Arif Mahmood (UWA), Ajmal Mian (UWA)
DOI: http://dx.doi.org/10.5244/C.27.57
58. Merging Pose Estimates Across Space and Time
Xavier Burgos-Artizzu (CALTECH), David Hall (CALTECH), Pietro Perona (CALTECH), Piotr Dollar
DOI: http://dx.doi.org/10.5244/C.27.58
59. Exploring Motion Boundary based Sampling and Spatial-Temporal Context Descriptors for Action Recognition
Xiaojiang Peng (Southwest Jiaotong University), Yu Qiao (SIAT), Qiang Peng (SWJTU), Xianbiao Qi (BUPT)
DOI: http://dx.doi.org/10.5244/C.27.59
60. Can Your Eyes Tell Me How You Think? A Gaze Directed Estimation of the Mental Activity
Laura Florea (Univ. Politehnica of Bucharest), Corneliu Florea (Univ. Politehnica of Bucharest), Ruxandra Vranceanu (Univ. Politehnica of Bucharest), Constantin Vertan (Univ. Politehnica of Bucharest)
DOI: http://dx.doi.org/10.5244/C.27.60
61. Incremental Solid Modeling from Sparse and Omnidirectional Structure-from-Motion Data
Vadim Litvinov , Maxime Lhuillier (Institut Pascal)
DOI: http://dx.doi.org/10.5244/C.27.61
62. Egomotion Estimation Using Binocular Spatiotemporal Oriented Energy
Hao Zhong (York University), Richard Wildes (York University)
DOI: http://dx.doi.org/10.5244/C.27.62
63. Online Motion Agreement Tracking
ZHENG WU (Boston University), Jianming Zhang , Margrit Betke (Boston University)
DOI: http://dx.doi.org/10.5244/C.27.63
64. A Topic Model Approach to Representing and Classifying Football Plays
Jagannadan Varadarajan (ADSC), Indriyati Atmosukarto , Shaunak Ahuja (ADSC), Bernard Ghanem (KAUST), Narendra Ahuja (University of Illinois at Urbana Champaign)
DOI: http://dx.doi.org/10.5244/C.27.64
65. Sketch Retrieval via Dense Stroke Features
Chao Ma (Shanghai Jiao Tong University), Xiaokang Yang , Chongyang Zhang (Shanghai Jiao Tong University), Xiang Ruan (OMRON Corporation), Ming-Hsuan Yang (University of California, Merced)
DOI: http://dx.doi.org/10.5244/C.27.65
66. PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues
Fabian Flohr (Daimler), Dariu Gavrila (Daimler)
DOI: http://dx.doi.org/10.5244/C.27.66
67. Fast Approximation of Distance Between Elastic Curves using Kernels
Hedi Tabia (ETIS/ENSEA CNRS, UMR 8051, France), David Picard (ETIS/ENSEA CNRS, UMR 8051), Hamid Laga (Phenomics and Bioinformatics Research Centre, University of South Australia), Philippe-Henri Gosselin
DOI: http://dx.doi.org/10.5244/C.27.67
68. Line extraction in uncalibrated central images with revolution symmetry
Jesus Bermudez-Cameo (Universidad de Zaragoza), Gonzalo Lopez-Nicolas (Universidad de Zaragoza), J.J. Guerrero (Universidad de Zaragoza)
DOI: http://dx.doi.org/10.5244/C.27.68
69. Tree-like Shapes Distance Using the Elastic Shape Analysis Framework
Alejandro Mottini (INRIA/I3S/IBV), Xavier Descombes (INRIA), Florence Besse (IBV)
DOI: http://dx.doi.org/10.5244/C.27.69
70. Image Blur Classification and Parameter Identification Using Two-stage Deep Belief Networks
Ruomei Yan , Ling Shao (The University of Sheffield)
DOI: http://dx.doi.org/10.5244/C.27.70
71. Discriminative tree-based feature mapping
Miroslav Kobetski (CVAP, KTH), Josephine Sullivan
DOI: http://dx.doi.org/10.5244/C.27.71
72. Unsupervised (parameter) learning for MRFs on bipartite graphs
Boris Flach (Czech Technical University in Prague), Tomas Sixta (Czech Technical University)
DOI: http://dx.doi.org/10.5244/C.27.72
73. Generic Object Crowd Tracking by Multi-Task Learning
Wenhan Luo (Imperial College London), Tae-Kyun Kim
DOI: http://dx.doi.org/10.5244/C.27.73
74. Discriminative Generative Contour Detection
Chao Zhang (IBM China Research Lab), Xiong Li , Xiang Ruan , Yuming Zhao , Ming-Hsuan Yang (University of California, Merced)
DOI: http://dx.doi.org/10.5244/C.27.74
75. Accurate and Computationally-inexpensive Recovery of Ego-Motion using Optical Flow and Range Flow with Extended Temporal Support
Graeme Jones (Kingston University)
DOI: http://dx.doi.org/10.5244/C.27.75
76. Emotion recognition from facial images with arbitrary views
Xiaohua Huang (University of Oulu), Guoying Zhao , Matti Pietikainen (University of Oulu)
DOI: http://dx.doi.org/10.5244/C.27.76
77. RPM: Random Points Matching for Pair wise Face-Similarity
M. Saquib Sarfraz (KIT), Muhammad Adnan Siddique (Swiss Federal Institute of Technology (ETH) Zurich), Rainer Stiefelhagen (KIT)
DOI: http://dx.doi.org/10.5244/C.27.77
78. Segmentation Driven Low-rank Matrix Recovery for Saliency Detection
Wenbin Zou (INSA Rennes), Kidiyo Kpalma (INSA Rennes), Zhi Liu , joseph Ronsin (INSA Rennes)
DOI: http://dx.doi.org/10.5244/C.27.78
79. Action Attribute Detection from Sports Videos with Contextual Constraints
Xiaodong Yu (Comcast Corp), Ching Lik Teo (Department of Computer Science, University of Maryland), Yezhou Yang (Department of Computer Science, University of Maryland), Cornelia Fermuller (UMIACS, University of Maryland), Yiannis Aloimonos (Department of Computer Science, University of Maryland)
DOI: http://dx.doi.org/10.5244/C.27.79
80. Decomposed Learning for Joint Segmentation and Categorization
Yi-Hsuan Tsai (UC Merced), Jimei Yang (UC Merced), Ming-Hsuan Yang (University of California, Merced)
DOI: http://dx.doi.org/10.5244/C.27.80
81. Action Chart: A Representation for Efficient Recognition of Complex Activity
Hyung Jin Chang (Imperial College London), Jiyun Kim (Seoul National University), Jungchan Cho , Songhwai Oh (Seoul National University), Kwang Yi (Seoul National University), Jin Young Choi (Seoul National University)
DOI: http://dx.doi.org/10.5244/C.27.81
82. Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations
Adrian Penate-Sanchez (Iri.upc.edu), Eduard Serradell (Institut de Rob\F2tica i Inform\E0tica Industrial (CSIC-UPC)), Francesc Moreno-Noguer , Juan Andrade-Cetto (iri.upc.edu)
DOI: http://dx.doi.org/10.5244/C.27.82
83. Discriminative Tensor Sparse Coding for Image Classification
Yangmuzi Zhang (University of Maryland), Zhuolin Jiang (Umiacs), Larry Davis (University of Maryland at College Park)
DOI: http://dx.doi.org/10.5244/C.27.83
84. Hierarchical Scene Annotation
Michael Maire (Caltech), Stella Yu (International Computer Science Institute, Berkeley), Pietro Perona (CALTECH)
DOI: http://dx.doi.org/10.5244/C.27.84
85. Blockwise Linear Regression for Face Alignment
Enrique S\E1nchez-Lozano (University of Vigo), Enrique Argones-R\FAa (Gradiant), Jose Luis Alba-Castro (University of Vigo)
DOI: http://dx.doi.org/10.5244/C.27.85
86. Fast and Robust $ell_1$-averaging-based Pose Estimation for Driving Scenarios
German Ros (Computer Vision Center), Angel Sappa (Computer Vision Center), Daniel Ponsa (Universitat Aut\F2noma de Barcelona, Computer Vision Center), Antonio L\F3pez (Universitat Aut\F2noma de Barcelona, Computer Vision Center), Julio Guerrero (Universidad de Murcia, FIUM, Dept. de Matem\E1tica Aplicada)
DOI: http://dx.doi.org/10.5244/C.27.86
87. Learning Speed Invariant Gait Template via Thin Plate Spline Kernel Manifold Fitting
Sheng Huang (Chongqing University), Ahmed Elgammal (Rutgers University), Dan Yang (Chongqing University)
DOI: http://dx.doi.org/10.5244/C.27.87
88. Parsing Clothes in Unrestricted Images
Nataraj Jammalamadaka (IIIT Hyderabad), Ayush Minocha (IIIT Hyderabad), Digvijay Singh (IIIT Hyderabad), CV Jawahar
DOI: http://dx.doi.org/10.5244/C.27.88
89. Image Fusion using Gaussian Mixture Models
Stacey Levine (Duquesne University), Katie Heaps (University of Minnesota), Joshua Koslosky (University of Minnesota), Glenn Sidle (Duquesne University)
DOI: http://dx.doi.org/10.5244/C.27.89
Session 8: Stereo and Geometry I
90. Real Projective Plane Mapping for Detection of Orthogonal Vanishing Points
Mark\E9ta Dubsk\E1 (Brno University of Technology), Adam Herout (Brno University of Technology)
DOI: http://dx.doi.org/10.5244/C.27.90
91. Efficient Shape Matching using Vector Extrapolation
Emanuele Rodola (The University of Tokyo), Tatsuya Harada (The University of Tokyo), Yasuo Kuniyoshi (The University of Tokyo), Daniel Cremers (TU M\FCnchen)
DOI: http://dx.doi.org/10.5244/C.27.91
92. Incremental Line-based 3D Reconstruction using Geometric Constraints
Manuel Hofer (Graz University of Technology), Andreas Wendel (Graz University of Technology), Horst Bischof (Graz University of Technology)
DOI: http://dx.doi.org/10.5244/C.27.92
93. Spline Fusion: A continuous-time representation for visual-inertial fusion with application to rolling shutter cameras
Steven Lovegrove (George Washington University), Alonso Patron-Perez (George Washington University), Gabe Sibley (George Washington University)
DOI: http://dx.doi.org/10.5244/C.27.93
Session 9: Stereo and Geometry II
94. Incremental Surface Extraction from Sparse Structure-from-Motion Point Clouds
Christof Hoppe (Graz University of Technology), Manfred Klopschitz (Siemens), Michael Donoser , Horst Bischof (Graz University of Technology)
DOI: http://dx.doi.org/10.5244/C.27.94
95. Dense, Auto-Calibrating Visual Odometry from a Downward-Looking Camera
Jacek Zienkiewicz (Imperial College London), Robert Lukierski , Andrew Davison
DOI: http://dx.doi.org/10.5244/C.27.95
96. A Novel Trilateral Filter based Adaptive Support Weight Method for Stereo Matching
Dongming Chen (Ecole Centrale de Lyon), Mohsen Ardabilian (Ecole Centrale de Lyon), Liming Chen (Ecole Centrale de Lyon)
DOI: http://dx.doi.org/10.5244/C.27.96
Session 10: Posters III
97. Exploring Cross-Channel Texture Correlation for Color Texture Classification
Xianbiao Qi (BUPT), Yu Qiao (SIAT), Chun-Guang Li (BUPT), Jun Guo (BUPT)
DOI: http://dx.doi.org/10.5244/C.27.97
98. Depth really Matters: Improving Visual Salient Region Detection with Depth
Karthik Desingh (IIIT - Hyderabad), Madhava Krishna K (IIIT-Hyderabad), Deepu Rajan (NTU Singapore), CV Jawahar
DOI: http://dx.doi.org/10.5244/C.27.98
99. Oriented pooling for dense and non-dense rotation-invariant features
Wan-Lei Zhao (INRIA), Guillaume Gravier (CNRS/IRISA, Rennes, France), Herve Jegou (INRIA Rennes)
DOI: http://dx.doi.org/10.5244/C.27.99
100. Efficient Discriminative Convolution Using Fisher Weight Map
Hideki Nakayama (The University of Tokyo)
DOI: http://dx.doi.org/10.5244/C.27.100
101. Single-Image Super-Resolution via Adaptive Joint Kernel Regression
Chen Huang (Department of Electronic Engineering, Tsinghua University, Beijing, China), Xiaoqing Ding (Department of Electronic Engineering, Tsinghua University, Beijing, China), Chi Fang (Department of Electronic Engineering, Tsinghua University, Beijing, China)
DOI: http://dx.doi.org/10.5244/C.27.101
102. Anatomical Structure Sketcher for Cephalograms by Bimodal Deep Learning
Yuru Pei (Peking University), Bin Liu (Peking University), Hongbin Zha (Peking University), Bing Han , Tianmin Xu (Stomatology Hospital of Peking University)
DOI: http://dx.doi.org/10.5244/C.27.102
103. Reconstructing faces from their signatures using RBF regression
Alexis Mignon (GREYC -- CNRS UMR 6072), Frederic Jurie (University of Caen)
DOI: http://dx.doi.org/10.5244/C.27.103
104. Isowarp and Conwarp: Warps that Exactly Comply with Weak-Perspective Projection of Deforming Objects
Daniel Pizarro (Universit\E9 d'Auvergne), Adrien Bartoli , Toby Collins (Universit\E9 d'Auvergne)
DOI: http://dx.doi.org/10.5244/C.27.104
105. Point Light Source Estimation based on Scenes Recorded by a RGB-D camera
Bas Boom , Sergio Orts-Escolano (University of Alicante), Xi Ning (University of Edinburgh), Steven McDonagh (University of Edinburgh), Peter Sandilands (University of Edinburgh), Robert Fisher
DOI: http://dx.doi.org/10.5244/C.27.105
106. Closed form solution for radial distortion estimation from a single vanishing point
Horst Wildenauer (Vienna University of Technolog), Branislav Micusik (Austrian Institute of Technology)
DOI: http://dx.doi.org/10.5244/C.27.106
107. Robust Scene Stitching in Large Scale Mobile Mapping
Filip Schouwenaars (KULeuven), Radu Timofte (KU Leuven), Luc Van Gool (KU Leuven)
DOI: http://dx.doi.org/10.5244/C.27.107
108. Local Zernike Moment Representation for Facial Affect Recognition
Evangelos Sariyanidi (Queen Mary Univ. of London), Hatice Gunes (Queen Mary University of London), Muhittin G\F6kmen (Istanbul Technical University), Andrea Cavallaro (Queen Mary University of London)
DOI: http://dx.doi.org/10.5244/C.27.108
109. An Adaptive Subdivision Scheme for Quadratic Programming in Multi-Label Image Segmentation
Marko Rak (Department of Simulation and Graphics, University of Magdeburg), Tim K\F6nig (Department of Simulation and Graphics, University of Magdeburg), Klaus-Dietz T\F6nnies
DOI: http://dx.doi.org/10.5244/C.27.109
110. Visual Tracking via Subspace Motion Model
Jun Wang (Shandong University), Fan Zhong (School of Computer Science and Technology, Shandong University, Jinan, China), Guofeng Wang (School of Computer Science and Technology, Shandong University, Jinan, China), qunsheng Peng (The State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China), Xueying Qin (School of Computer Science and Technology, Shandong University, Jinan, China)
DOI: http://dx.doi.org/10.5244/C.27.110
111. Place recognition from disparate views
Rob Frampton (University of Bristol), Andrew Calway (University of Bristol)
DOI: http://dx.doi.org/10.5244/C.27.111
112. An In Depth View of Saliency
Arridhana Ciptadi (Georgia Institute of Technolog), Tucker Hermans (Georgia Institute of Technology), James Rehg
DOI: http://dx.doi.org/10.5244/C.27.112
113. Insulin Granule Segmentation in 3-D TEM Beta Cell Tomograms
David Nam (University of Bristol), Judith Mantell (University of Bristol), David Bull , Paul Verkade (University of Bristol), Alin Achim (University of Bristol)
DOI: http://dx.doi.org/10.5244/C.27.113
114. Plane-based Odometry using an RGB-D Camera
Carolina Raposo (ISR University of Coimbra), Miguel Lourenco , Michel Antunes , Joao Barreto
DOI: http://dx.doi.org/10.5244/C.27.114
115. Reflective Symmetry Detection by Rectifying Randomized Correspondences
Zhongwei Tang (ECE, Duke University), Mariano Tepper (ECE, Duke University), Guillermo Sapiro (ECE, Duke University)
DOI: http://dx.doi.org/10.5244/C.27.115
116. An Iterative 5-pt Algorithm for Fast and Robust Essential Matrix Estimation
Vincent Lui (Monash University), Tom Drummond (Monash University)
DOI: http://dx.doi.org/10.5244/C.27.116
117. Reduced Dimensionality Extended Kalman Filter for SLAM
Dinesh Gamage (Monash University, Australia), Tom Drummond (Monash University)
DOI: http://dx.doi.org/10.5244/C.27.117
118. Learning Smooth Pooling Regions for Visual Recognition
Mateusz Malinowski (MPI Informatics), Mario Fritz (MPI Informatics)
DOI: http://dx.doi.org/10.5244/C.27.118
119. Towards Pain Monitoring: Facial Expression, Head Pose, a new Database, an Automatic System and Remaining
Philipp Werner (University of Magdeburg), Ayoub Al-Hamadi (Otto von Guericke University Magdeburg), Robert Niese , Steffen Walter , Sascha Gruss , Harald Traue
DOI: http://dx.doi.org/10.5244/C.27.119
120. Overlapping camera clustering through dominant sets for scalable 3D reconstruction
Massimo Mauro (University of Brescia), Hayko Riemenschneider (CVL, ETH Zurich), Luc Van Gool (CVL, ETH Zurich), Riccardo Leonardi (Universit\E0 degli Studi di Brescia)
DOI: http://dx.doi.org/10.5244/C.27.120
121. Social Group Discovery from Surveillance Videos: A Data-Driven Approach with Attention-Based Cues
Isarun Chamveha (The University of Tokyo), Yusuke Sugano , Yoichi Sato (The University of Tokyo), Akihiro Sugimoto
DOI: http://dx.doi.org/10.5244/C.27.121
122. RLBP: Robust Local Binary Pattern
Jie Chen (University of Oulu), Vili Kellokumpu (University of Oulu), Guoying Zhao , Matti Pietikainen (University of Oulu)
DOI: http://dx.doi.org/10.5244/C.27.122
123. 3D Deformable Shape Reconstruction with Diffusion Maps
Lili Tao (Uni of Central Lancashire), Bogdan Matuszewski (University of Central Lancashire)
DOI: http://dx.doi.org/10.5244/C.27.123
124. Towards a minimal solution for the relative pose between axial cameras
Francisco Vasconcelos (ISR), Jo\E3o Barreto (University of Coimbra)
DOI: http://dx.doi.org/10.5244/C.27.124
125. Combining Features and Intensity for Wide-Baseline Non-Rigid Surface Registration
Jim Braux-Zin (CEA, LIST), Romain Dupont (CEA, LIST), Adrien Bartoli
DOI: http://dx.doi.org/10.5244/C.27.125
126. Single Image Shadow Detection Using Multiple Cues in a Supermodular MRF
Tomas F Yago Vicente (Stony Brook University), Chen-Ping Yu (Stony Brook University), Dimitris Samaras (Stony Brook University)
DOI: http://dx.doi.org/10.5244/C.27.126
127. Recognizing Humans in Motion: Trajectory-based Aerial Video Analysis
Yumi Iwashita (Kyushu University), Michael Ryoo (JPL), Thomas Fuchs (JPL), Curtis Padgett (JPL)
DOI: http://dx.doi.org/10.5244/C.27.127
128. Combining Local and Global Cues for Closed Contour Extraction
Vida Movahedi (York University), James Elder (York University)
DOI: http://dx.doi.org/10.5244/C.27.128
129. Lagrangian Strain Tensor Computation with Higher Order Variational Models
Alexander Hewer (Saarland University), Joachim Weickert (Saarland University), Henning Seibert (Saarland University), Tobias Scheffer (Saarland University), Stefan Diebels (Saarland University)
DOI: http://dx.doi.org/10.5244/C.27.129
130. Object Recognition in Multi-View Dual Energy X-ray Images
Muhammet Bastan (Tech. Univ. of Kaiserslautern), Wonmin Byeon (Tech. Univ. of Kaiserslautern), Thomas Breuel (Tech. Univ. of Kaiserslautern)
DOI: http://dx.doi.org/10.5244/C.27.130
Session 11: Segmentation and Features
131. Relatively-Paired Space Analysis
Zhanghui Kuang (The University of Hong Kong), Kenneth Wong (the university of hong kong)
DOI: http://dx.doi.org/10.5244/C.27.131
132. Sparse-Coded Features for Image Retrieval
Tiezheng Ge (USTC), Qifa Ke (Microsoft), Jian Sun
DOI: http://dx.doi.org/10.5244/C.27.132
133. Combination of paths for interactive segmentation
Julien Mille (Universit\E9 Lyon 1 / LIRIS), S\E9bastien Bougleux (Universit\E9 de Caen-Basse Normandie), Laurent Cohen (CEREMADE, Universit\E9 Paris Dauphine)
DOI: http://dx.doi.org/10.5244/C.27.133
134. Collaboratively Regularized Nearest Points for Set Based Recognition
Yang Wu (Kyoto University), Michihiko Minoh (Kyoto University), Masayuki Mukunoki (Kyoto University)
DOI: http://dx.doi.org/10.5244/C.27.134