Proceedings of the British Machine Vision Conference 2015
Editors: Xianghua Xie, Mark W. Jones, and Gary K. L. Tam BMVA Press, September 2015, ISBN 1-901725-53-7
Book of Abstracts(PDF, 236 pages, 399M)Tutorial
Keynote 1
Tracking
- Online Domain Adaptation for Multi-Object Tracking DOI: https://dx.doi.org/10.5244/C.29.3
- Learning Optimal Parameters For Multi-target Tracking DOI: https://dx.doi.org/10.5244/C.29.4
Deep Learning
- R-CNN minus R DOI: https://dx.doi.org/10.5244/C.29.5
- Convolutional Neural Networks for Direct Text Deblurring DOI: https://dx.doi.org/10.5244/C.29.6
- Sketch-a-Net that Beats Humans DOI: https://dx.doi.org/10.5244/C.29.7
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection DOI: https://dx.doi.org/10.5244/C.29.8
- Deep Perceptual Mapping for Thermal to Visible Face Recogntion DOI: https://dx.doi.org/10.5244/C.29.9
Poster 1
- An Efficient Algorithm for Learning Distances that Obey the Triangle Inequality DOI: https://dx.doi.org/10.5244/C.29.10
- Diagnosing state-of-the-art object proposal methods DOI: https://dx.doi.org/10.5244/C.29.11
- WxBS: Wide Baseline Stereo Generalizations DOI: https://dx.doi.org/10.5244/C.29.12
- Planar shape decomposition made simple DOI: https://dx.doi.org/10.5244/C.29.13
- Adaptation of Synthetic Data for Coarse-to-Fine Viewpoint Refinement DOI: https://dx.doi.org/10.5244/C.29.14
- Saliency Prediction with Active Semantic Segmentation DOI: https://dx.doi.org/10.5244/C.29.15
- Using Near-Field Light Sources to Separate Illumination from BRDF DOI: https://dx.doi.org/10.5244/C.29.16
- Multi-scale Graph-based Guided Filter for De-noising Cryo-Electron Tomographic Data DOI: https://dx.doi.org/10.5244/C.29.17
- Spotlight the Negatives: A Generalized Discriminative Latent Model DOI: https://dx.doi.org/10.5244/C.29.18
- Perceptual Dynamic Range for In-Camera Image Processing DOI: https://dx.doi.org/10.5244/C.29.19
- Robust Multiple Model Fitting with Preference Analysis and Low-rank Approximation DOI: https://dx.doi.org/10.5244/C.29.20
- Robust Global Motion Compensation in Presence of Predominant Foreground DOI: https://dx.doi.org/10.5244/C.29.21
- Using Segmentation to Predict the Absence of Occluded Parts DOI: https://dx.doi.org/10.5244/C.29.22
- Learning the Structure of Deep Architectures Using L1 Regularization DOI: https://dx.doi.org/10.5244/C.29.23
- Subspace Distribution Alignment for Unsupervised Domain Adaptation DOI: https://dx.doi.org/10.5244/C.29.24
- Robust Spatial Matching as Ensemble of Weak Geometric Relations DOI: https://dx.doi.org/10.5244/C.29.25
- Kernelized View Adaptive Subspace Learning for Person Re-identification DOI: https://dx.doi.org/10.5244/C.29.26
- Object localization in ImageNet by looking out of the window DOI: https://dx.doi.org/10.5244/C.29.27
- Unsupervised Behavior-Specific Dictionary Learning for Abnormal Event Detection DOI: https://dx.doi.org/10.5244/C.29.28
- Joint Calibration for Semantic Segmentation DOI: https://dx.doi.org/10.5244/C.29.29
- Camera Elevation Estimation from a Single Mountain Landscape Photograph DOI: https://dx.doi.org/10.5244/C.29.30
- Data-free Parameter Pruning for Deep Neural Networks DOI: https://dx.doi.org/10.5244/C.29.31
- Real-Time Pedestrian Detection with Deep Network Cascades DOI: https://dx.doi.org/10.5244/C.29.32
- Rule of thumb: Deep derotation for improved fingertip detection DOI: https://dx.doi.org/10.5244/C.29.33
- Riesz-based Volume Local Binary Pattern and A Novel Group Expression Model for Group Happiness Intensity Analysis DOI: https://dx.doi.org/10.5244/C.29.34
- Weakly Supervised Metric Learning towards Signer Adaptation for Sign Language Recognition DOI: https://dx.doi.org/10.5244/C.29.35
- Hashmod: A Hashing Method for Scalable 3D Object Detection DOI: https://dx.doi.org/10.5244/C.29.36
- Multi-Task Transfer Methods to Improve One-Shot Learning for Multimedia Event Detection DOI: https://dx.doi.org/10.5244/C.29.37
- Appearance and Depth for Rapid Human Activity Recognition in Real Applications DOI: https://dx.doi.org/10.5244/C.29.38
- Robust Wearable Camera Localization as a Target Tracking Problem on SE(3) DOI: https://dx.doi.org/10.5244/C.29.39
- Joint Object-Material Category Segmentation from Audio-Visual Cues DOI: https://dx.doi.org/10.5244/C.29.40
- Deep Face Recognition DOI: https://dx.doi.org/10.5244/C.29.41
- Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation DOI: https://dx.doi.org/10.5244/C.29.42
- Discrete Light Source Estimation from Light Probes for Photorealistic Rendering DOI: https://dx.doi.org/10.5244/C.29.43
- Dictionary Learning with Iterative Laplacian Regularisation for Unsupervised Person Re-identification DOI: https://dx.doi.org/10.5244/C.29.44
- Camera Pose Estimation from Lines using Plücker Coordinates DOI: https://dx.doi.org/10.5244/C.29.45
- Linear Global Translation Estimation with Feature Tracks DOI: https://dx.doi.org/10.5244/C.29.46
- Learning Discriminative Visual N-grams from Mid-level Image Features DOI: https://dx.doi.org/10.5244/C.29.47
- Minimizing the Number of Keypoint Matching Queries for Object Retrieval DOI: https://dx.doi.org/10.5244/C.29.48
- JH2R: Joint Homography Estimation for Highlight Removal DOI: https://dx.doi.org/10.5244/C.29.49
- Action Recognition based on Subdivision-Fusion Model DOI: https://dx.doi.org/10.5244/C.29.50
- Mix and Match: Joint Model for Clothing and Attribute Recognition DOI: https://dx.doi.org/10.5244/C.29.51
- Describing Common Human Visual Actions in Images DOI: https://dx.doi.org/10.5244/C.29.52
- Searching for Objects using Structure in Indoor Scenes DOI: https://dx.doi.org/10.5244/C.29.53
- Fast Inverse Compositional Image Alignment with Missing Data and Re-weighting DOI: https://dx.doi.org/10.5244/C.29.54
- Automatic Age Estimation from Face Images via Deep Ranking DOI: https://dx.doi.org/10.5244/C.29.55
- Feature Encoding of Spectral Signatures for 3D Non-Rigid Shape Retrieval DOI: https://dx.doi.org/10.5244/C.29.56
- A BoW-equivalent Recurrent Neural Network for Action Recognition DOI: https://dx.doi.org/10.5244/C.29.57
- Depth Restoration via Joint Training of a Global Regression Model and CNNs DOI: https://dx.doi.org/10.5244/C.29.58
- Shape Detection with Nearest Neighbour Contour Fragments DOI: https://dx.doi.org/10.5244/C.29.59
- Exploiting Image-trained CNN Architectures for Unconstrained Video Classification DOI: https://dx.doi.org/10.5244/C.29.60
- Change Detection from a Street Image Pair using CNN Features and Superpixel Segmentation DOI: https://dx.doi.org/10.5244/C.29.61
- Robust Multiview Registration of 3D Surfaces via L_1-norm Minimization DOI: https://dx.doi.org/10.5244/C.29.62
- Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest DOI: https://dx.doi.org/10.5244/C.29.63
- Optimizing Partition Trees for Multi-Object Segmentation with Shape Prior DOI: https://dx.doi.org/10.5244/C.29.64
- Face Painting: querying art with photos DOI: https://dx.doi.org/10.5244/C.29.65
- Cross-Domain Object Recognition Using Object Alignment DOI: https://dx.doi.org/10.5244/C.29.66
- Dynamical Regularity for Action Analysis DOI: https://dx.doi.org/10.5244/C.29.67
- Efficient Spatio-Temporal Data Association Using Multidimensional Assignment in Multi-Camera Multi-Target Tracking DOI: https://dx.doi.org/10.5244/C.29.68
- A New Face Recognition Algorithm based on Dictionary Learning for a Single Training Sample per Person DOI: https://dx.doi.org/10.5244/C.29.69
- Robust Direct Visual Localisation using Normalised Information Distance DOI: https://dx.doi.org/10.5244/C.29.70
- Joint Clustering and Classification for Multiple Instance Learning DOI: https://dx.doi.org/10.5244/C.29.71
- Multi-Modality Feature Transform: An Interactive Image Segmentation Approach DOI: https://dx.doi.org/10.5244/C.29.72
- Multi-Shot Human Re-Identification Using Adaptive Fisher Discriminant Analysis DOI: https://dx.doi.org/10.5244/C.29.73
- Hierarchical Hybrid Shape Representation for Medical Shapes DOI: https://dx.doi.org/10.5244/C.29.74
- Data Separation of L1-minimization for Real-time Motion Detection DOI: https://dx.doi.org/10.5244/C.29.75
- Color Constancy by Deep Learning DOI: https://dx.doi.org/10.5244/C.29.76
- Model-based 3D Hand Tracking with on-line Shape Adaptation DOI: https://dx.doi.org/10.5244/C.29.77
- Globally Optimal DLS Method for PnP Problem with Cayley parameterization DOI: https://dx.doi.org/10.5244/C.29.78
- Joint Tracking and Event Analysis for Carried Object Detection DOI: https://dx.doi.org/10.5244/C.29.79
- Occlusion-Aware Object Localization, Segmentation and Pose Estimation DOI: https://dx.doi.org/10.5244/C.29.80
- VESICLE: Volumetric Evaluation of Synaptic Inferfaces using Computer Vision at Large Scale DOI: https://dx.doi.org/10.5244/C.29.81
Medical Applications
- Epipolar Consistency in Fluoroscopy for Image-Based Tracking DOI: https://dx.doi.org/10.5244/C.29.82
- Automatic Aortic Root Segmentation with Shape Constraints and Mesh Regularisation DOI: https://dx.doi.org/10.5244/C.29.83
- Anatomical triangulation: from sparse landmarks to dense annotation of the skeleton in CT images DOI: https://dx.doi.org/10.5244/C.29.84
- Primal-Dual convex optimization in large deformation diffeomorphic registration with robust regularizers DOI: https://dx.doi.org/10.5244/C.29.85
- Global Minimum for Curvature Penalized Minimal Path Method DOI: https://dx.doi.org/10.5244/C.29.86
3D Vision
- Adaptive Contour Fitting for Pose-Invariant 3D Face Shape Reconstruction DOI: https://dx.doi.org/10.5244/C.29.87
- Freehand Laser Scanning Using Mobile Phone DOI: https://dx.doi.org/10.5244/C.29.88
- Stochastic visibility in point-sampled scenes DOI: https://dx.doi.org/10.5244/C.29.89
- MGM: A Significantly More Global Matching for Stereovision DOI: https://dx.doi.org/10.5244/C.29.90
Keynote 2
Identification and Scene Annotation
- Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery DOI: https://dx.doi.org/10.5244/C.29.92
- Generating Multi-sentence Natural Language Descriptions of Indoor Scenes DOI: https://dx.doi.org/10.5244/C.29.93
Learning and Recognition
- Overlapping Domain Cover for Scalable and Accurate Regression Kernel Machines DOI: https://dx.doi.org/10.5244/C.29.94
- Visual Comparison of Images Using Multiple Kernel Learning for Ranking DOI: https://dx.doi.org/10.5244/C.29.95
- Bridging the Domain Shift by Domain Adaptive Dictionary Learning DOI: https://dx.doi.org/10.5244/C.29.96
- Joint Feature Selection with Low-rank Dictionary Learning DOI: https://dx.doi.org/10.5244/C.29.97
- Scalable Visual Instance Mining with Instance Graph DOI: https://dx.doi.org/10.5244/C.29.98
Poster 2
- Perceptually Motivated Benchmark for Video Matting DOI: https://dx.doi.org/10.5244/C.29.99
- SDICP: Semi-Dense Tracking based on Iterative Closest Points DOI: https://dx.doi.org/10.5244/C.29.100
- Human Pose as Context for Object Detection DOI: https://dx.doi.org/10.5244/C.29.101
- Learning Depth Calibration of Time-of-Flight Cameras DOI: https://dx.doi.org/10.5244/C.29.102
- Low-Rank Spatio-Temporal Video Segmentation DOI: https://dx.doi.org/10.5244/C.29.103
- Fast Online Upper Body Pose Estimation from Video DOI: https://dx.doi.org/10.5244/C.29.104
- Simultaneous Inpainting and Super-resolution Using Self-learning DOI: https://dx.doi.org/10.5244/C.29.105
- Manitest: Are classifiers really invariant? DOI: https://dx.doi.org/10.5244/C.29.106
- MCSLAM : a Multiple Constrained SLAM DOI: https://dx.doi.org/10.5244/C.29.107
- Incremental Dictionary Learning for Unsupervised Domain Adaptation DOI: https://dx.doi.org/10.5244/C.29.108
- StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation DOI: https://dx.doi.org/10.5244/C.29.109
- Segmenting natural images with the least effort as humans DOI: https://dx.doi.org/10.5244/C.29.110
- Deep Fishing: Gradient Features from Deep Nets DOI: https://dx.doi.org/10.5244/C.29.111
- Multimodal Stereo Vision For Reconstruction In The Presence Of Reflection DOI: https://dx.doi.org/10.5244/C.29.112
- Real-time Human Detection based on Personness Estimation DOI: https://dx.doi.org/10.5244/C.29.113
- Semantic Classification of Boundaries of an RGBD Image DOI: https://dx.doi.org/10.5244/C.29.114
- Elliptical ASIFT Agglomeration in Class Prototype for Logo Detection DOI: https://dx.doi.org/10.5244/C.29.115
- Entire Reflective Object Surface Structure Understanding DOI: https://dx.doi.org/10.5244/C.29.116
- TennisVid2Text: Fine-grained Descriptions for Domain Specific Videos DOI: https://dx.doi.org/10.5244/C.29.117
- Human activity recognition in the semantic simplex of elementary actions DOI: https://dx.doi.org/10.5244/C.29.118
- Character Identification in TV-series via Non-local Cost Aggregation DOI: https://dx.doi.org/10.5244/C.29.119
- Prototypical Priors: From Improving Classification to Zero-Shot Learning DOI: https://dx.doi.org/10.5244/C.29.120
- Fast Affine Template Matching over Galois Field DOI: https://dx.doi.org/10.5244/C.29.121
- Universal Hough dictionaries for object tracking DOI: https://dx.doi.org/10.5244/C.29.122
- 3D Tracking of Human Hands in Interaction with Unknown Objects DOI: https://dx.doi.org/10.5244/C.29.123
- Handling Data Imbalance in Automatic Facial Action Intensity Estimation DOI: https://dx.doi.org/10.5244/C.29.124
- Hierarchical rank-based veiling light estimation for underwater dehazing DOI: https://dx.doi.org/10.5244/C.29.125
- The intrinsic error of exposure fusion for HDR imaging, and a way to reduce it DOI: https://dx.doi.org/10.5244/C.29.126
- Detecting Change for Multi-View, Long-Term Surface Inspection DOI: https://dx.doi.org/10.5244/C.29.127
- Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization DOI: https://dx.doi.org/10.5244/C.29.128
- Gesture and Action Recognition by Evolved Dynamic Subgestures DOI: https://dx.doi.org/10.5244/C.29.129
- Face Alignment Assisted by Head Pose Estimation DOI: https://dx.doi.org/10.5244/C.29.130
- Score Normalization in Multimodal Systems using Generalized Extreme Value Distribution DOI: https://dx.doi.org/10.5244/C.29.131
- Manifold-Regularized Selectable Factor Extraction for Semi-supervised Image Classification DOI: https://dx.doi.org/10.5244/C.29.132
- Leaf Segmentation under Loosely Controlled Conditions DOI: https://dx.doi.org/10.5244/C.29.133
- Shape from Focus with Adaptive Focus Measure and High Order Derivatives DOI: https://dx.doi.org/10.5244/C.29.134
- A Segmentation Technique for Flexible Pipes in Deep Underwater Environments DOI: https://dx.doi.org/10.5244/C.29.135
- Structural Symmetries from Motion for Scene Reconstruction and Understanding DOI: https://dx.doi.org/10.5244/C.29.136
- Stereo Tracking and 3D Reconstruction of Underwater Pipes DOI: https://dx.doi.org/10.5244/C.29.137
- Nonlinear Metric Learning for Alzheimer’s Disease Diagnosis with Integration of Longitudinal Neuroimaging Features DOI: https://dx.doi.org/10.5244/C.29.138
- Boosted Metric Learning for Efficient Identity-Based Face Retrieval DOI: https://dx.doi.org/10.5244/C.29.139
- Enforcing Point-wise Priors on Binary Segmentation DOI: https://dx.doi.org/10.5244/C.29.140
- Sparse Discrimination based Multiset Canonical Correlation Analysis for Multi-Feature Fusion and Recognition DOI: https://dx.doi.org/10.5244/C.29.141
- Towards 4D Coupled Models of Conversational Facial Expression Interactions DOI: https://dx.doi.org/10.5244/C.29.142
- A Unified Bayesian Approach to Multi-Frame Super-Resolution and Single-Image Upsampling in Multi-Sensor Imaging DOI: https://dx.doi.org/10.5244/C.29.143
- Boosting the Performance of Model-based 3D Tracking by Employing Low Level Motion Cues DOI: https://dx.doi.org/10.5244/C.29.144
- Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling DOI: https://dx.doi.org/10.5244/C.29.145
- Experimental Evaluation of the Bag-of-Features Model for Unsupervised Learning of Images DOI: https://dx.doi.org/10.5244/C.29.146
- Indoor Localisation with Regression Networks and Place Cell Models DOI: https://dx.doi.org/10.5244/C.29.147
- Kinship Verification with Deep Convolutional Neural Networks DOI: https://dx.doi.org/10.5244/C.29.148
- Exploiting Low-rank Structure for Discriminative Sub-categorization DOI: https://dx.doi.org/10.5244/C.29.149
- Sparse 3D convolutional neural networks DOI: https://dx.doi.org/10.5244/C.29.150
- Multi-task Gaussian Process Regression-based Image Super Resolution DOI: https://dx.doi.org/10.5244/C.29.151
- Spatiotemporal Stereo Matching with 3D Disparity Profiles DOI: https://dx.doi.org/10.5244/C.29.152
- Randomized Global Transformation Approach for Dense Correspondence DOI: https://dx.doi.org/10.5244/C.29.153
- Achieving Turbidity Robustness on Underwater Images Local Feature Detection DOI: https://dx.doi.org/10.5244/C.29.154
- The Self-Equalizing De Bruijn Sequence for 3D Profilometry DOI: https://dx.doi.org/10.5244/C.29.155
- A fast and robust ellipse detector based on top-down least-square fitting DOI: https://dx.doi.org/10.5244/C.29.156
- Multiview Reconstruction of Complex Organic Shapes DOI: https://dx.doi.org/10.5244/C.29.157
- Manifold Regularized Transfer Distance Metric Learning DOI: https://dx.doi.org/10.5244/C.29.158
- Top-down saliency with Locality-constrained Contextual Sparse Coding DOI: https://dx.doi.org/10.5244/C.29.159
- Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add DOI: https://dx.doi.org/10.5244/C.29.160
- Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning DOI: https://dx.doi.org/10.5244/C.29.161
- Camera Pose and Focal Length Estimation Using Regularized Distance Constraints DOI: https://dx.doi.org/10.5244/C.29.162
- Classifying Global Scene Context for On-line Multiple Tracker Selection DOI: https://dx.doi.org/10.5244/C.29.163
- Sketch based Image Retrieval using Learned KeyShapes (LKS) DOI: https://dx.doi.org/10.5244/C.29.164
- Online Visual Tracking via Coupled Object-Context Dictionary DOI: https://dx.doi.org/10.5244/C.29.165
- Subspace Alignment Based Domain Adaptation for RCNN Detector DOI: https://dx.doi.org/10.5244/C.29.166
- Time-slice Prediction of Dyadic Human Activities DOI: https://dx.doi.org/10.5244/C.29.167
- Adapting RANSAC SVM to Detect Outliers for Robust Classification DOI: https://dx.doi.org/10.5244/C.29.168
- Beyond MSER: Maximally Stable Regions using Tree of Shapes DOI: https://dx.doi.org/10.5244/C.29.169
- Exploring Locally Rigid Discriminative Patches for Learning Relative Attributes DOI: https://dx.doi.org/10.5244/C.29.170
- Semantic description of medical image findings: structured learning approach DOI: https://dx.doi.org/10.5244/C.29.171
Search and Detection
- Latent Structure Preserving Hashing DOI: https://dx.doi.org/10.5244/C.29.172
- Local Feature Binary Coding for Approximate Nearest Neighbor Search DOI: https://dx.doi.org/10.5244/C.29.173
- Revealing Smooth Structure of Visual Data by Permutation on Manifolds DOI: https://dx.doi.org/10.5244/C.29.174
- Normalized Autobinomial Markov Channels For Pedestrian Detection DOI: https://dx.doi.org/10.5244/C.29.175
- Exploring Prior Knowledge for Pedestrian Detection DOI: https://dx.doi.org/10.5244/C.29.176
Action and Event
- APT: Action localization proposals from dense trajectories DOI: https://dx.doi.org/10.5244/C.29.177
- Event Fisher Vectors: Robust Encoding Visual Diversity of Visual Streams DOI: https://dx.doi.org/10.5244/C.29.178
- Deep Structured Models For Group Activity Recognition DOI: https://dx.doi.org/10.5244/C.29.179
- Fast Action Retrieval from Videos via Feature Disaggregation DOI: https://dx.doi.org/10.5244/C.29.180
Tracking and Pose Estimation
- Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression DOI: https://dx.doi.org/10.5244/C.29.181
- Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties DOI: https://dx.doi.org/10.5244/C.29.182
- Particle dynamics and multi-channel feature dictionaries for robust visual tracking DOI: https://dx.doi.org/10.5244/C.29.183
- Collaborative Correlation Tracking DOI: https://dx.doi.org/10.5244/C.29.184
- Enable Scale and Aspect Ratio Adaptability in Visual Tracking with Detection Proposals DOI: https://dx.doi.org/10.5244/C.29.185
Detection and Recognition
- Multiple Frames Matching for Object Discovery in Video DOI: https://dx.doi.org/10.5244/C.29.186
- Surface Based Object Detection in RGBD Images DOI: https://dx.doi.org/10.5244/C.29.187
- Context Forest for Object Class Detection DOI: https://dx.doi.org/10.5244/C.29.188
- Spatiotemporal Deformable Prototypes for Motion Anomaly Detection DOI: https://dx.doi.org/10.5244/C.29.189