Warwick Piazza

Home

Committees

Programme

Proceedings

Tutorial

Keynote Speakers

Awards

Contact


BMVC2007 Detailed Technical Programme (as of 03/09/2007)

Monday (Sep 10, 2007)

Arrivals & Registration 09:00AM - 05:00PM Whole day
Tutorial: "Visual SLAM" by Andrew Davison, Andrew Calway, and Walterio Mayol-Cuevas 02:00PM - 05:30PM 2.5 hours
Reception (wine & snacks) 07:00PM - 09:00PM 2 hours

Tuesday (Sep 11, 2007)

Breakfast 07:30AM - 08:45AM 75 mins

Opening Remarks (Welcome + logistics) 09:00AM - 09:05AM 05 mins
Invited Talk 1: "Manifolds and Images: Signal processing goes round the bend" by Prof Hans Knutsson 09:05AM - 10:00AM 55 mins

Coffee 10:00AM - 10:30AM 30 mins

Oral Session 1: Tracking
Session Chair: Tim Cootes
10:30AM - 12:30PM 120 mins
Paper 46: Combining Local Appearance and Motion Cues for Occlusion Boundary Detection; Stein, Hebert 10:30AM - 10:50AM 20 mins
Paper 197: Motion Segmentation Using Inference in Dynamic Bayesian Networks; Toussaint, Willert, Eggert, Korner 10:50AM - 11:10AM 20 mins
Paper 265: Layered Active Contours for Tracking; Pryor, Vela, Rehman, Tannenbaum 11:10AM - 11:30AM 20 mins
Paper 70: Automatic Player Detection, Labeling and Tracking in Broadcast Soccer Video; Liu, Tong, Li, Wang, Zhang, Wang, Yang, Sun, Yang 11:30AM - 11:50AM 20 mins
Paper 21: Feature-Driven Direct Non-Rigid Image Registration; Vincent, Bartoli, Sayd 11:50AM - 12:10PM 20 mins
Paper 301: Discovering Planes and Collapsing the State Space in Visual SLAM; Gee, Chekhlov, Mayol, Calway 12:10AM - 12:30PM 20 mins

Lunch 12:30PM - 01:30PM 60 mins

Oral Session 2: Surveillance/Registration
Session Chair: Tony Pridmore
01:30PM - 03:10PM 100 mins
Paper 161: A Probabilistic Framework for Recognizing Similar Actions using Spatio-Temporal Features; Patron, Reid 01:30PM - 01:50PM 20 mins
Paper 164: Associating People Dropping off and Picking up Objects; Damen, Hogg 01:50PM - 02:10PM 20 mins
Paper 132: Spatial modelling of multi-layered LiDAR images using reversible jump MCMC; Hernandez-Marin, Wallace, Gibson 02:10PM - 02:30PM 20 mins
Paper 207: A New Framework for Automatic Registration of 2D/3D Texture Images; El-Baz, Gimel'farb 02:30PM - 02:50PM 20 mins
Paper 302: Fast Multigrid Optimal Mass Transport for Image Registration and Morphing; Rehman, Pryor, Tannenbaum 02:50PM - 03:10PM 20 mins

Coffee and Tuesday's Poster Session 03:10PM - 04:10PM 60 mins

Paper 263: Super-resolution of faces using the epipolar constraint; Den Hollander,De Lange,Schutte
Paper 279: Incremental LDA Learning by Combining Reconstructive and Discriminative Approaches; Uray, Skocaj, Roth, Bischof, Leonardis
Paper 89: Generalised Linear Pose Estimation; Ess, Neubeck, van Gool
Paper 223: A multi-class SVM classifier for automatic hand washing quality assessment; Llorca, Vilarino, Zhou, Lacey
Paper 142: Learning object classes from structure; Bai, Song, Hall
Paper 305: Enforcing 3D Constraints To Improve Object and Scene Recognition; Hewitt, Goncalves, Munich
Paper 231: Simple Representation and Approximate Search of Feature Vectors for Large-Scale Object Recognition; Kise, Noguchi, Iwamura
Paper 220: Bayesian Surface Estimation from Multiple Cameras Using a Prior Based on the Visual Hull and its Application to Image Based Rendering; Mullins, Bowen, Wilson, Rajpoot
Paper 201: Class-Specific Binary Correlograms for Object Recognition; Amores, Sebe, Radeva
Paper 78: Towards Automated Visual Assessment of Progress in Construction Projects; Lukins, Trucco
Paper 236: A framework for learning to recognize and segment object classes using weakly supervised training data; Pantofaru, Hebert
Paper 198: Colour Constancy Based on Model Selection; Li, Hall
Paper 227: Unsupervised Learning of Shape Manifolds; Rajpoot, Arif, Bhalerao
Paper 60: The DIARETDB1 diabetic retinopathy database and evaluation protocol; Kauppi, Kalesnykiene, Kamarainen, Lensu, Sorri, Raninen, Voutilainen, Uusitalo, Kalviainen, Pietila
Paper 83: Automated Segmentation of Low-Light Level Imagery using Poisson MAP-MRF Labelling; Gribben, Miller, Wang, Browne
Paper 61: Hilbert-Huang Transform-based Local Regions Descriptors; Han, Li, Guo
Paper 158: Fibre Centred Tensor Faces; Tiddeman,Hunter,Meng
Paper 81: High Accuracy Computation of Rank-Constrained Fundamental Matrix; Sugaya, Kanatani
Paper 33: Binary Co-occurrences of Weak Descriptors; Winter, Bischof
Paper 151: Unsupervised extraction of coherent regions for image based rendering; Berent, Dragotti
Paper 123: Identifying Lens Distortions in Image Registration by Learning from Examples; Moeller, Posch
Paper 254: Image Enhancement Using Vector Quantisation Based Interpolation; Cockshott, Balasuriya, Gunawan, Siebert
Paper 209: Local Image Features for Shoeprint Image Retrieval; Su, Crookes, Bouridane, Gueham
Paper 203: Overcoming Parallax and Sampling Density Issues in Image Mosaicing of Non-Planar Scenes; Qi, Cooperstock
Paper 86: Real-Time Humans Detection in Urban Scenes; BEGARD,ALLEZARD,SAYD
Paper 297: A single-perspective novel panoramic view from radially distorted non-central images; Molana, Daniilidis
Paper 38: Rotation, Rescaling and Occlusion Invariant Object Retrieval; Lecca, Messelodi
Paper 298: Finsler Level Set Segmentation for Imagery in Oriented Domains; Mohan, Melonakos, Niethammer, Kubicki, Tannenbaum
Paper 232: An Automatic Framework for Figure-Ground Segmentation in Cluttered Backgrounds; Loss, Bebis, Nicolescu, Skurikhin
Paper 199: Interest-point Based Face Recognition from Range Images; Al-Osaimi, Bennamoun, Mian
Paper 171: Colour Transfer by Feature Based Histogram Registration; Senanayake, Alexander
Paper 65: Robust Active Appearance Models with Iteratively Rescaled Kernels; Roberts, Cootes, Adams
Paper 141: Epsilon Stereo Pairs; Yu, Ding
Paper 186: Camera calibration for miniature, low-cost, wide-angle imaging systems; Frank, Katz, Tisse, Durrant-Whyte
Paper 119: Towards Real-Time Traffic Sign Recognition by Class-Specific Discriminative Features; Ruta, Li, Liu
Paper 276: Beyond Facial Expressions: Learning Human Emotion from Body Gestures; Shan, Gong, McOwan

Oral Session 3: Biometrics
Session Chair: Peter Hall
04:10PM - 05:50PM 100 mins
Paper 169: Capturing Correlations Among Facial Parts for Facial Expression Analysis; Shan, Gong, McOwan 04:10PM - 04:30PM 20 mins
Paper 240: Facial Emotions and Emotion Intensity Levels Classification and Classification Evaluation; Beszedes, Culverhouse 04:30PM - 04:50PM 20 mins
Paper 106: Segmented AAMs Improve Person-Indepedent Face Fitting; Peyras 04:50PM - 05:10PM 20 mins
Paper 122: Gender Classification using Shape from Shading; Wu, Smith, Hancock 05:10PM - 05:30PM 20 mins
Paper 16: Who are you? - real-time person identification; Apostoloff, Zisserman 05:30PM - 05:50PM 20 mins

Members AGM (Majid Mirmehdi) 05:50PM - 06:30PM 40 mins
Free Evening 06:30PM - midnight

Wednesday (Sep 12, 2007)

Breakfast 07:30AM - 08:45AM 75 mins

Announcements 09:00AM - 09:05AM 05 mins
Invited Talk 2: "Recognizing Actions, Objects, and Actions as Objects" by Prof Mubarak Shah 09:05AM - 10:00AM 55 mins

Coffee 10:00AM - 10:30AM 30 mins

Oral Session 4: Segmentation
Session Chair: Robert Fisher
10:30AM - 12:30PM 120 mins
Paper 1: A variational framework combining level-sets and thresholding; Dambreville, Tannenbaum, Yezzi, Niethammer 10:30AM - 10:50AM 20 mins
Paper 296: Automatic 3D Object Segmentation in Multiple Views using Volumetric Graph-Cuts; Campbell, Vogiatzis, Hernandez, Cipolla 10:50AM - 11:10AM 20 mins
Paper 288: Zipf's Law in Image Coding Schemes; Crosier, Griffin 11:10AM - 11:30AM 20 mins
Paper 225: Segmenting Highly Textured Nonstationary Background; Russell, Gong 11:30AM - 11:50AM 20 mins
Paper 304: Improving Spatial Support for Objects via Multiple Segmentations; Malisiewicz, Efros 11:50AM - 12:10PM 20 mins
Paper 129: Delving into the whorl of flower segmentation; Nilsback, Zisserman 12:10PM - 12:30PM 20 mins

Lunch 12:30PM - 01:30PM 60 mins

Oral Session 5: Image/Video Retrieval
Session Chair: Andrew Wallace
01:30PM - 03:10PM 100 mins
Paper 241: Topology-Preserved Diffusion Distance for Histogram Comparison; Yan, Wang, Liu, Lu, Ma 01:30PM - 01:50PM 20 mins
Paper 291: Distance-Free Image Retrieval Based on Stochastic Diffusion over Bipartite Graphs; Bauckhage 01:50PM - 02:10PM 20 mins
Paper 98: Word Co-occurrence and Markov Random Fields for Improving Automatic Image Annotation; Escalante, Montes y Gomez, Sucar 02:10PM - 02:30PM 20 mins
Paper 287: Image Retrieval through Qualitative Representations over Semantic Features; Qayyum, Cohn 02:30PM - 02:50PM 20 mins
Paper 42: Conditional Random Field for Natural Scene Categorization; Wang, Gong 02:50PM - 03:10PM 20 mins

Coffee and Wednesday's Poster Session 03:10PM - 04:10PM 60 mins

Paper 259: Improved Face Model Fitting on Video Sequences; Liu, Wheeler, Tu
Paper 268: Batch Algorithm with Additional Shape Constraints for Non-Rigid Factorization; Loke, Ranganath
Paper 286: Navier-Stokes formulation for modelling turbulent optical flow; Doshi, Bors
Paper 146: Time Varying Volumetric Scene Reconstruction Using Scene Flow; Smith, Redmill, Canagarajah, Bull
Paper 258: Layered image model using binary PCA transparency masks; Zivkovic
Paper 73: Shape from Texture: Fast Estimation of Planar Surface Orientation via Fourier Analysis; Galasso,Lasenby
Paper 37: Evolutionary feature selection for probabilistic object recognition, novel object detection and object saliency estimation using GMMs; Trujillo,Olague,Fernandez,Lutton
Paper 195: A phase field model incorporating generic and specific prior knowledge applied to road network extraction from VHR satellite images; Peng, Jermyn, Prinet, Zerubia, Hu
Paper 101: Higher-order Autoregressive Models for Dynamic Textures; Hyndman, Jepson, Fleet
Paper 24: An Evaluation of Shape Descriptors for Image Retrieval in Human Pose Estimation; Tresadern, Reid
Paper 75: Robust Multi-View Change Detection; Lanza, Di Stefano, Berclaz, Fleuret, Fua
Paper 29: Fully Automated Laser Range Calibration; Antone, Friedman
Paper 96: Structure from Motion via Two-State Pipeline of Extended Kalman Filters; Clipp, Welch, Frahm, Pollefeys
Paper 154: Integrating Stereo with Shape-from-Shading derived Orientation Information; Haines, Wilson
Paper 275: Isolating Motion and Color in a Motion Blurred Image; Giusti, Caglioti
Paper 95: Refining implicit function representations of 3-D scenes; Grum, Bors
Paper 137: Shape Recovery Using Stochastic Heat Flow; Namboodiri, Chaudhuri
Paper 159: Active Segmentation and Adaptive Tracking Using Level Sets; Chen, Wallace
Paper 183: Geometrical constraint based 3D reconstruction using implicit coplanarities; Furukawa, Kawasaki
Paper 293: Fitting Surface of Free Form Objects using Optimized NURBS Patches Network with Evolutionary Strategies (mu + lambda) - ES; Branch, Prieto, Boulanger
Paper 280: Denoising Manifold and Non-Manifold Point Clouds; Unnikrishnan, Hebert
Paper 168: Tracking Using Online Feature Selection and a Local Generative Model; Woodley, Stenger, Cipolla
Paper 39: All Pairs Shortest Path Formulation for Multiple Object Tracking with Application to Tennis Video Analysis; Yan, Christmas, Kittler
Paper 239: Multi-scale Adaptive Mask 3D Rigid Registration of Ultrasound and CT Images; Zhijun, Jerome, Soo, Yan, Yeung
Paper 260: A Combined RANSAC-Hough Transform Algorithm for Fundamental Matrix Estimation; Den Hollander, Hanjalic
Paper 19: Generic and Real-Time Structure from Motion; Mouragnon, Lhuillier, Dhome, Dekeyser, Sayd
Paper 112: Automatic Identification of Morphometric Landmarks in Digital Images; Palaniswamy, Thacker, Klingenberg
Paper 289: MOTEXATION: Multiple Object Tracking with Expectation-Maximization Algorithm; Jin, Mokhtarian
Paper 116: Tracking Through Clutter Using Graph Cuts; Malcolm,Rathi,Tannenbaum
Paper 147: Fast Motion Estimation on Range Image Sequences acquired with a 3-D Camera; Matzka,Petillot,Wallace
Paper 52: Managing Particle Spread via Hybrid Particle Filter/Kernel Mean Shift Tracking; Pridmore, Naeem, Mills
Paper 191: Non-Gibbsian Markov random field models for contextual labelling of structured scenes; Heesch,Petrou
Paper 251: Human Pose Extraction from Monocular Videos using Constrained Non-Rigid Factorization; Shaji, Chandran, Siddiquie, Suter
Paper 149: A Practical Approach for Super-Resolution using Photometric cue and Graph Cuts; Sharma, Joshi
Paper 131: Boosted Regression Active Shape Models; Cristinacce, Cootes
Paper 91: Multicues 3D Monocular Upper Body Tracking Using Constrained Belief Propagation; Noriega, Bernier

Oral Session 6: Object Recognition
Session Chair: Roy Davies
04:10PM - 05:50PM 100 mins
Paper 49: Retina Sampling Feature Detection and Saccades; A Statistical Perspective; Thacker, Leek 04:10PM - 04:30PM 20 mins
Paper 144: Unsupervised Category Discovery in Images Using Sparse Neural Coding; Waydo, Koch 04:30PM - 04:50PM 20 mins
Paper 230: Improvement of Retrieval Speed and Required Amount of Memory for Geometric Hashing by Combining Local Invariants; Iwamura, Nakai, Kise 04:50PM - 05:10PM 20 mins
Paper 13: Object Detection Using Shape Codebook; Yu, Li 05:10PM - 05:30PM 20 mins
Paper 281: Generic Object Recognition via Shock Patch Fragments; Ozcanli, Kimia 05:30PM - 05:50PM 20 mins

Coaches leave for Banquet 06:45PM
Banquet (Thanks & prizes) 07:15PM

Thursday (Sep 13, 2007)

Breakfast 07:30AM - 08:45AM 75 mins

Announcements 09:00AM - 09:10AM 10 mins
Oral Session 7: Shape Modelling and Analysis
Session Chair: David Hogg
09:10AM - 10:50AM 100 mins
Paper 109: Implicit Active Model using Radial Basis Function Interpolated Level Sets; Xie, Mirmehdi 09:10PM - 09:30PM 20 mins
Paper 23: Using Priors for Improving Generalization in Non-Rigid Structure-from-Motion; Olsen, Bartoli 09:30PM - 09:50PM 20 mins
Paper 107: Automated Analysis of Deformable Structure in Groups of Images; Petrovic, Cootes, Mills, Twining, Taylor 09:50PM - 10:10PM 20 mins
Paper 222: Distribution-based Level Set Segmentation for Brain MR Images; Liu, Chelberg, Smith, Chebrolu 10:10PM - 10:30PM 20 mins
Paper 274: Sparse MRF Appearance Models for Fast Anatomical Structure Localisation; Donner, Micusik, Langs, Bischof 10:30PM - 10:50PM 20 mins

Coffee 10:50AM - 11:20AM 30 mins

Oral Session 8: Video Analysis
Session Chair: Neil Thacker
11:20AM - 12:40PM 80 mins
Paper 80: Indoor Place Recognition using Online Independent Support Vector Machines; Orabona, Castellini, Caputo, Luo, Sandini 11:20AM - 11:40AM 20 mins
Paper 97: Video-rate recognition and localization for wearable cameras; Castle, Gawley, Klein, Murray 11:40AM - 12:00PM 20 mins
Paper 133: Probabilistic egomotion from a statistical framework; Shah, Lakshmikumar 12:00PM - 12:20PM 20 mins
Paper 15: On New View Synthesis Using Multiview Stereo; Woodford, Reid, Torr, Fitzgibbon 12:20PM - 12:40PM 20 mins

Lunch 12:40PM - 13:40PM 60 mins

Conference Finishes


Banner image from Warwick panoramas