BMVC 2009 Papers
8 3D Extended Histogram of Oriented Gradients (3DHOG) for Classification of Road Users in Urban Scenes
9 Category-Specific Object Recognition and Segmentation Using a Skeletal Shape Model
31 Efficient Disparity Computation without Maximum Disparity for Real-Time Stereo Vision
35 Head Pose Classification in Crowded Scenes
36 Multi-View Geometry of the Refractive Plane
38 Backing Off: Hierarchical Decomposition of Activity for 3D Novel Pose Recovery
41 Clustering Videos by Location
43 An implicit non-linear numerical scheme for illumination-robust variational optical flow
55 Better appearance models for pictorial structures. Better appearance/motion models for pictorial structures
56 A Constant-Time Efficient Stereo SLAM System
57 Minimal Solutions for Panoramic Stitching with Radial Distortion
59 Multi-view synchronization of human actions and dynamic scenes
60 On-line Learning of Shape Information for Object Segmentation and Tracking
65 Semi-Supervised Discriminant Analysis via Spectral Transduction
66 Semantic Image Classification using Consistent Regions and Individual Context
77 Multi-object Activity Modelling Using Gaussian Processes
80 Stochastic Image Denoising
81 Object Recognition with 3D Models
83 HMM based Archive Film Defect Detection with Spatial and Temporal Constraints
85 3D Human Body-Part Tracking and Action Classification Using A Hierarchical Body Model
87 Real-time Stable Texture Regions Extraction for Motion-based Object Segmentation
93 Hierarchical Image-Region Labeling via Structured Learning
94 Algebraic Line Search for Bundle Adjustment
96 Bundle Adjustment using Conjugate Gradients with Multiscale Preconditioning
97 Shape-from-shading driven 3D Morphable Models for Illumination Insensitive Face Recognition
101 Particle Filter Approach Adapted to Catadioptric Images for Target Tracking Application
106 Learning Recognition of Fine-Grain Object Categories from Natural Language Descriptions
109 Bag of Optical Flow Volumes for Image Sequence Recognition
111 Attribute Multiset Grammars for Global Explanations of Activities
118 PRISM: PRincipled Implicit Shape Model
121 Haar Local Binary Pattern Feature for Fast Illumination Invariant Face Detection
126 Latent Semantics Local Distribution for CRF-based Image Semantic Segmentation
130 Combining meshes and geometric primitives for accurate and semantic modeling
137 Ranking user-annotated images for multiple query terms
138 Get Out of my Picture! Internet-based Inpainting
140 Segmentation Based Interest Points and Evaluation of Unsupervised Image Segmentation Methods.
142 Specularity and Shadow Interpolation via Robust Polynomial Texture Maps
143 Evaluation of local spatio-temporal features for action recognition
144 PWP3D: Real-time segmentation and tracking of 3D objects
145 Guiding Visual Surveillance by Tracking Human Attention
146 Obtaining the Shape of a Moving Object with a Specular Surface
149 Unified Stereo-Based 3D Head Tracking Using Online Illumination Modeling
153 Semantic Scene Segmentation using Random Multinomial Logit
155 A Comparative Analysis of Radial-Tchebichef Moments and Zernike Moments
164 Mining visual actions from movies
167 Associating Groups of People
171 Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurements
172 3D head pose estimation from multiple distant views
174 Multiframe Motion Segmentation via Penalized MAP Estimation and Linear Programming
175 Shape From Motion of Nonrigid Objects: The Case of Isometrically Deformable Flat Surfaces
179 Fast Segmentation via Randomized Hashing
180 3D-assisted Facial Texture Super-Resolution
182 Real-time texture boundary detection from ridges in the standard deviation space
189 Robust Density Comparison for Visual Tracking
195 A Unified Approach for Adaptive Multiple Feature Tracking for Surveillance Applications
196 Log-Linear Mixtures for Object Recognition
198 Incremental Visual Hull Reconstruction
199 Neighborhood Preserving Nonnegative Matrix Factorization
208 Learning generative texture models with extended Fields-of-Experts
209 SURF-Face: Face Recognition Under Viewpoint Consistency Constraints
216 Combining Appearance and Structure from Motion Features for Object Category Segmentation
222 Edge-Directed Interpolation in a Bayesian Framework
223 New Conditional Sampling Strategies for Speeded-Up RANSAC
224 Contour Segment Matching by Integrating Intra and Inter Shape Cues of Objects
228 Object Localization with Global and Local Context Kernels#
230 Detecting local audio-visual synchrony in monologues utilizing vocal pitch and facial landmark trajectories
233 Depth estimation with a practical camera
243 Stereo-based Pedestrian Detection using Multiple Patterns 244 Channel Features for Pedestrian Detection
247 Hierarchical Image Matching for Pose-invariant Face Recognition
248 Inpainting in Shape from Focus: Taking a Cue from Motion Parallax
253 Learning Local Patch Orientation with a Cascade of Sparse Regressors
256 Face Pose Estimation in Uncontrolled Environments
260 Anisotropic Huber-L1 Optical Flow
261 Multi-person tracking with overlapping cameras in complex, dynamic environments
268 NURBS Warps
273 Subtitle-free Movie to Script Alignment
275 Semantic Shape Context for the Registration of Multiple Partial 3{D} Views
276 Estimation of Location Uncertainty for Scale Invariant Features Points
277 Disparity estimation in stereo sequences using scene flow
283 Hough transform-based mouth localization for audio-visual speech recognition
286 Bilateral Symmetry Detection and Segmentation via Symmetry-Growing
289 Incorporating Higher-Order Cues in Image Colorization
297 ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition
300 Interactive Texture Segmentation
302 The effect of pose on Facial Expression Recognition
305 Non-parametric patch based video matting
306 Reconstruction from Uncalibrated Affine Silhouettes
307 Vistas: Hierarchial boundary priors using multiscale conditional random fields.
312 Non-rigid structure from motion using quadratic deformation models
314 Disparity from stereo-segment silhouettes of weakly-textured images
315 On the completeness of coding with image features
322 Multiple Target Localisation at over 100 FPS
323 Selecting surface features for accurate multi-camera surface reconstruction
324 Learning-based Face Synthesis for Pose-Robust Recognition from Single Image
336 A shape-from-shading framework for satisfying data-closeness and structure-preserving smoothness constraints
339 FACE RECOGNITION USING TENSORS OF CENSUS TRANSFORM HISTOGRAMS FROM GAUSSIAN FEATURES MAPS
350 Segmentation-Based Urban Traffic Scene Understanding
353 The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories
355 Performance Evaluation of RANSAC Family
357 Gait Representation Using Flow Fields
359 Dynamic Partitioned Sampling For Tracking With Discriminative Features
360 Exemplar-based action recognition in video
364 An Empirical Camera Model for Internet Color Vision
379 Palmprint based verification System Robust to Occlusion using Low-order Zernike Moments of Sub-images
380 Time based Activity Inference using Latent Dirichlet Allocation
391 Multiple One-Shots for Utilizing Class Label Information
396 A Framework For Evaluating Visual SLAM
397 Clustering using a Decision Forest and Application to Video Segmentation
406 Object Pose Classification from Short Video Sequences
411 Combining Pixel and Location Information for Grammar-Guided Object Detection
424 Parametric Trajectory Representations for Behaviour Classification
428 VillageFinder: Segmentation of Nucleated Villages in Satellite Imagery
429 Cancer cell detection and invasion depth estimation in brightfield images
431 Two View Geometry from Uncertain Correspondences
432 Unsupervised Learning of Stereo Vision with Monocular Depth Cues
436 Next best view planning for active model improvement
443 Optimization framework for learning a hierarchical shape vocabulary for object class detection
444 Combining Local and Global Shape Models for Deformable Object Matching
450 Geometric Potential Force for the Deformable Model#
451 Incremental learning of dynamical models of faces
454 From Rank-N to Rank-1 Face Recognition Based on Motion Similarity
456 Variance Ranklets: orientation-selective rank features for contrast modulations
461 Automatic Calibration of Medical Endoscopes using a Single Image of a Planar Grid
466 A Latent Model for Visual Disambiguation of Keyword-based Image Search