ICCV 2007

Eleventh IEEE International Conference on Computer Vision

Rio de Janeiro, Brazil, October 14-20, 2007

Information for Presenters

For Orals: Talks will be about 20 minutes including questions, so please plan on a 17-18 minute talk maximum.

For Posters: The poster boards are approximately 102cm (h) x 196cm (w) (3.35 ft. x 6.5 ft. or 40 inches x 77 inches), standard industry size, in landscape format.

Sunday, October 14


Optical Motion Capture

Human-Centered Vision Systems

Gradient Domain Manipulation Techniques in Vision and Graphics

Tensor Methods for Computer Vision, Graphics and Machine Learning



PETS Performance Evaluation of Tracking and Surveillance

Mathematical Methods in Biomedical Image Analysis

Non-rigid registration and tracking through learning

Photometric Analysis for Computer Vision

VRML Visual Representations and Modeling of Large-scale environments

Monday, October 15


Content-based image and video retrieval

Principles of Appearance Acquisition and Representation

Visual Recognition

Discrete Optimization methods in Computer Vision



ICV07: Interactive Computer Vision

Mathematical Methods in Biomedical Image Analysis

4th International Workshop on Object Categorization

Computer Vision Applications for Developing Countries

Visual Recognition Challenge (Caltech 256 and PASCAL VOC2007)

Tuesday, October 16

8:45am - 9:00am: Opening Remarks

9am - 10:30am: Oral session 1: Learning-1

  • Tiberio Caetano, Li Cheng, Quoc Le, Alex Smola: Learning Graph Matching
  • Andrea Frome, Yoram Singer, Fei Sha, Jitendra Malik: Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification
  • Andrea Vedaldi, Paolo Favaro, Enrico Grisan: Boosting Invariance and Efficiency in Supervised Learning
  • Andrew Stein, Derek Hoiem, Martial Hebert: Learning to Extract Object Boundaries using Motion Cues

10:30am - 12:30pm: Poster Session 1

Learning and Recognition-1

  • Abhinav Gupta, Anurag Mittal, Larry Davis: COST: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes
  • Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Trevor Darrell: Active Learning with Gaussian Processes for Object Categorization
  • Atul Kanaujia, Cristian Sminchisescu, Dimitris Metaxas: Spectral Latent Variable Models for Perceptual Inference
  • Bing Jian, Baba Vemuri: Metric Learning Using Iwasawa Decomposition
  • Vidal Rene, Paolo Favaro: DynamicBoost: Boosting Time Series Generated by Dynamical Systems
  • Boris Babenko, Piotr Dollar, Serge Belongie: Task Specific Local Region Matching
  • Daniel Weinland, Edmond Boyer, Remi Ronfard: Action Recognition from Arbitrary Views using 3D Exemplars
  • Chang Huang, Haizhou Ai, Takayoshi Yamashita, Shihong Lao, Masato Kawade: Incremental Learning of Boosted Face Detector
  • Yuchi Huang, Qingshan Liu, Dimitris Metaxas: A Component Based Deformable Model for Generalized Face Alignment
  • Dashan Gao, Nuno Vasconcelos: Bottom-up saliency is a discriminant process
  • David Liu, Tsuhan Chen: Unsupervised Image Categorization and Object Localization using Topic Models and Correspondences between Images
  • Delbert Dueck, Brendan Frey: Non-metric affinity propagation for unsupervised image categorization
  • Deli Zhao, Zhouchen Lin, Xiaoou Tang: Contextual Distance for Data Perception
  • Deng Cai, Xiaofei He, Jiawei Han: Spectral Regression for Efficient Regularized Subspace Learning
  • Deng Cai, Xiaofei He, Jiawei Han: Semi-supervised Discriminant Analysis
  • Gang Hua, Matthew Brown, Simon Winder: Discriminant Embedding for Local Image Descriptors
  • Gary Huang, Vidit Jain, Erik Learned-Miller: Unsupervised Joint Alignment of Complex Images
  • Haibin Ling, Stefano Soatto: Proximity Distribution Kernels for Geometric Context in Category Recognition
  • Hamed Masnadi-Shirazi, Nuno Vasconcelos: High Detection-rate Cascades for Real-Time Object Detection
  • Hichem Sahbi, Jean-Yves Audibert, Renaud Keriven: Graph-Cut Transducers for Relevance Feedback in Content Based Image Retrieval
  • Hong Chang, Dit-Yan Yeung: Locally Smooth Metric Learning with Application to Image Retrieval
  • Ian Simon, Noah Snavely, Steven M. Seitz: Scene Summarization for Online Image Collections
  • Iasonas Kokkinos, Alan Yuille: Unsupervised Learning of Object Deformation Models
  • Jianxin Wu, Adebola Osuntogun, Tanzeem Choudhury, Matthai Philipose, James Rehg: A Scalable Approach to Activity Recognition based on Object Use
  • Jingen Liu, Mubarak Shah: Scene Modeling Using Co-clustering
  • JinHyeong Park, S. Kevin Zhou, Otsuki Otsuki, Costas Simopoulos, Dorin Comaniciu: Automatic Cardiac View Classification of Echocardiogram
  • Johannes Stallkamp, Hazim Kemal Ekenel, Rainer Stiefelhagen: Video-based Face Recognition on Real-World Data
  • Junsong Yuan, Ying Wu: Spatial Random Partition for Common Visual Pattern Discovery
  • Jyri Kivinen, Erik Sudderth, Michael Jordan: Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes
  • Krystian Mikolajczyk, Jiri Matas: Improving SIFT for Fast Tree Matching by Optimal Linear Projection
  • Li-Jia Li, Li Fei-Fei: What, where and who? Classifying events by scene and object recognition
  • Liang Lin, Shaowu Peng, Jake Porway, Song-Chun Zhu, Yongtian Wang: An Empirical Study of Object Category Recognition: Sequential Testing with Generalized Samples
  • Mahesh Ramachandran, Ashok Veeraraghavan, Rama Chellappa: Fast Bilinear SFM with side information
  • Manik Varma, Debajyoti Ray: Learning The Discriminative Power-Invariance Trade-Off
  • Manik Varma, Rahul Garg: Locally Invariant Fractal Features for Statistical Texture Classification
  • Michael Jamieson, Sven Dickinson, Suzanne Stevenson, Afsaneh Fazly, Sven Wachsmuth: Learning Structured Appearance Models from Captioned Images of Cluttered Scenes
  • Michael Stark, Bernt Schiele: How Good are Local Features for Classes of Geometric Objects
  • Nagesh Adluru, Longin Jan Latecki, Rolf Lakaemper, Thomas Young, Xiang Bai, Gross Ari: Contour Grouping Based on Local Symmetry
  • Dusan Omercevic, Ondrej Drbohlav, Ales Leonardis: High-dimensional feature matching: Employing the concept of meaningful nearest neighbors

12:30pm - 2:00pm: Lunch

2:00pm - 3:00pm: Oral session 2: Stereo and Reconstruction

  • Neil Alldrin, David Kriegman: Toward Reconstructing Surfaces With Arbitrary Isotropic Reflectance : A Stratified Photometric Stereo Approach
  • Nigel Morris, Kiriakos Kutulakos: Reconstructing the Surface of Inhomogeneous Transparent Scenes by Scatter-Trace Photography
  • Yair Adato, Yuriy Vasilyev, Ohad Ben-Shahar, Todd Zickler: Toward a theory of shape from specular flow

3pm - 5pm: Poster Session 2

Low Level Vision & Applications

  • Martin Bujnak, Radim Sara: A Robust Graph-Based Method for The General Correspondence Problem Demonstrated on Image Stitching
  • Martin Byröd, Klas Josephson, Kalle Åström: Improving Numerical Accuracy of Gröbner Basis Polynomial Equation Solvers
  • Maxime Boucher, Oliver Lyttelton, Sue Whitesides, Alan Evans: A Discrete Differential Operator for Direction-Based Surface Morphometry
  • Michal Perdoch, Jiri Matas, Stepan Obdrzalek: Stable Affine Frames on Isophotes
  • Moshe Ben-Ezra, Zhouchen Lin, Bennett Wilburn: Penrose Pixels; Super-Resolution in the Detector Layout Domain
  • Nicolas Papadakis, Thomas Corpetti, Etienne Memin: Dynamically consistent optical flow estimation
  • Nikos Komodakis, Nikos Paragios, Georgios Tziritas: MRF Optimization via Dual Decomposition: Message-Passing Revisited
  • Ondrej Chum, James Philbin, Josef Sivic, Michael Isard, Andrew Zisserman: Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval
  • Patrick Labatut, Jean-Philippe Pons, Renaud Keriven: Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts
  • Peter Hansen, Peter Corke, Wageeh Boles, Kostas Daniilidis: Scale-Invariant Features on the Sphere
  • Raffay Hamid, Siddhartha Maddi, Aaron Bobick, Irfan Essa: Structure from Statistics - Unsupervised Activity Analysis using Suffix Trees
  • Ramunas Girdziusas, Jorma Laaksonen: When is Discrete Diffusion a Scale-Space?
  • Richard Hartley, Fredrik Kahl: Global Optimization through Searching Rotation Space and Optimal Estimation of the Essential Matrix
  • Saad M. Khan, Pingkun Yan, Mubarak Shah: A Homographic Framework for the Fusion of Multi-view Silhouettes
  • Samuel W. Hasinoff, Kiriakos N. Kutulakos: A Layer-Based Restoration Framework for Variable-Aperture Photography
  • Samy Metari, François Deschênes: A New Convolution Kernel for Atmospheric Point Spread Function Applied to Computer Vision
  • Sanjeev Koppal, Srinivasa Narasimhan: Novel Depth Cues from Uncalibrated Near-field Lighting
  • Shanmuganathan Raman, Subhasis Chaudhuri: A Matte-less, Variational Approach to Automatic Scene Compositing
  • Shuntaro Yamazaki, Srinivasa Narasimhan, Simon Baker, Takeo Kanade: Coplanar Shadowgrams for Acquiring Visual Hulls of Intricate Objects
  • Simon Baker, Michael J. Black, J.P. Lewis, Stefan Roth, Daniel Scharstein, Richard Szeliski: A Database and Evaluation Methodology for Optical Flow
  • Sunghyun Cho, Yasuyuki Matsushita, Seungyong Lee: Removing Non-Uniform Motion Blur from Images
  • Tianli Yu, Ruei-Sung Lin, Boaz Super, Bei Tang: Efficient Message Representations for Belief Propagation
  • Till Quack, Vittorio Ferrari, Bastian Leibe, Luc Van Gool: Efficient Mining of Frequent and Distinctive Feature Configurations
  • Victor Lempitsky, Carsten Rother, Andrew Blake: LogCut - Efficient Graph Cut Optimization for Markov Random Fields
  • Huai-Yu Wu, Chunhong Pan, Qing Yang, Songde Ma: Consistent Correspondence between Arbitrary Manifold Surfaces
  • Viren Jain, Joseph Murray, Fabian Roth, Srinivas Turaga, Kevin Briggman, Moritz Helmstaedter, Winfried Denk, Sebastian Seung: Supervised Image Restoration with Convolutional Networks
  • Vladimir Kolmogorov, Yuri Boykov, Carsten Rother: Applications of parametric maxflow in computer vision
  • Wei-Shi Zheng, Stan Z. Li, J. H. Lai, Shengcai Liao: On Constrained Sparse Matrix Factorization
  • Xiaoming Liu, Ting Yu: Gradient Feature Selection for Online Boosting
  • Yongduek SEO, Richard Hartley: A Fast Method to Minimize L-infinity Error Norm for Geometric Vision Problems
  • Kalle Åström, Olof Enquist, Carl Olsson, Fredrik Kahl, Richard Hartley: An L_infinity Approach to Structure and Motion Problems for 1D-vision.
  • Yuan Lu, Jian Sun, Quan Long, Shum Heung-Yeung: Blurred/Non-Blurred Image Alignment using Sparseness Prior
  • Yueting Zhuang, Cheng Chen: Efficient Silhouette Extraction with Dynamic Viewpoint
  • Yunqiang Chen, Lin Cheng, Tong Fang, Rainer Raupach: A Multi-Image Restoration Method for Image Reconstruction from Projections
  • Ozlem Subakan, Bing Jian, Baba C. Vemuri, C. Eduardo Vallejos: Feature Preserving Image Smoothing Using a Continuous Mixture of Tensors
  • Amir Tamrakar, Benjamin Kimia: No Grouping Left Behind: From Edges to Curve Fragments
  • Meirav Galun, Ronen Basri, Achi Brandt: Multiscale Edge Detection and Fiber Enhancement Using Differences of Oriented Means
  • Anderson Rocha, Siome Goldenstein: PR: More than Meets the Eye
  • Qi Shan, Wei Xiong, Jiaya Jia: Rotational Motion Deblurring of a Rigid Object from a Single Image

5:00pm - 6:30pm: Oral session 3: Features

  • Shu-Fai Wong, Roberto Cipolla: Extracting Spatiotemporal Interest Points using Global Information
  • Yefeng Zheng, Adrian Barbu, Bogdan Georgescu, Michael Scheuering, Dorin Comaniciu: Fast Automatic Heart Chamber Segmentation from 3D CT Data Using Marginal Space Learning and Steerable Features
  • Minh-Tri Pham, Tat-Jen Cham: Fast training and selection of Haar features using statistics in boosting-based face detection
  • Narendra Ahuja, Sinisa Todorovic: Extracting Texels in 2.1D Natural Textures

Wednesday, October 17

8:30am - 10:00am: Oral session 4: Segmentation & Grouping

  • Ali Kemal Sinop, Leo Grady: A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New Algorithm
  • Jianxiong Xiao, Jingdong Wang, Ping Tan, Long Quan: Joint Affinity Propagation for Multiple View Segmentation
  • Qihui Zhu, Gang Song, Jianbo Shi: Untangling Cycles for Contour Grouping
  • Yaser Yacoob, Larry Davis: Segmentation using Meta-texture Saliency

10:30am - 12:15pm: Oral session 5: Vision and Graphics

  • Xue Bai, Guillermo Sapiro: A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting
  • Tao Ding, Mario Sznaier, Octavia Camps: A Rank Minimization Approach to Video Inpainting
  • Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe, Steven M. Seitz: Multi-View Stereo for Community Photo Collections
  • Yael Pritch, Alex Rav-Acha, Tali Gutman, Shmuel Peleg: Webcam Synopsis: Peeking Around the World
  • Abhijeet Ghosh, Shruthi Achutha, Wolfgang Heidrich, Matthew O'Toole: BRDF Acquisition with Basis Illumination

12:15pm - 2:00pm: Lunch

2pm - 4:15pm: Poster Session 3

Tracking & Segmentation


  • Bastian Leibe, Konrad Schindler, Luc Van Gool: Coupled Detection and Trajectory Estimation for Multi-Object Tracking
  • Bi Song, Amit K. Roy-Chowdhury: Stochastic Adaptive Tracking In A Camera Network
  • Bohyung Han, Seong-Wook Joo, Larry Davis: Probabilistic Fusion Tracking Using Mixture Kernel-Based Bayesian Filtering
  • Carlos Hernandez, George Vogiatzis, Gabriel J. Brostow, Bjorn Stenger, Roberto Cipolla: Non-Rigid Photometric Stereo with Colored Lights
  • Li Zhang, Ramakant Nevatia, Bo Wu: Detection and Tracking of Multiple Humans with Extensive Pose Articulation
  • GuoJun Liu, XiangLong Tang, JianHua Huang, JiaFeng Liu, Da Sun: Hierarchical Model-Based Human Motion Tracking Via Unscented Kalman Filter
  • Ming Yang, Ting Yu, Ying Wu: Game-Theoretic Multiple Target Tracking
  • Minyoung Kim, Vladimir Pavlovic: Conditional State Space Models for Discriminative Motion Estimation
  • Nicolas Papadakis, Eienne Memin: Variational optimal control technique for the tracking of deformable objects
  • Seon Joo Kim, Jan-Michael Frahm, Marc Pollefeys: Joint Feature Tracking and Radiometric Calibration from Auto-Exposure Video
  • Shaobo Hou, Aphrodite Galata, Fabrice Caillette, Neil Thacker, Paul Bromiley: Real-time Body Tracking Using a Gaussian Process Latent Variable Model
  • Slobodan Ilic, Pascal Fua: Non-Linear Beam Model for Tracking Large Deformations
  • Son Tran, Davis Larry: Robust Object Tracking with Regional Affine Invariant Features
  • Yichen Wei, Jian Sun, Xiaoou Tang and Heung-Yeung Shum: Interactive Offline Tracking for Color Objects
  • Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, Guan Luo: Robust Visual Tracking Based on Incremental Tensor Subspace Learning
  • Xinyu Xu, Baoxin Li: Learning Motion Correlation for Tracking Articulated Human Body with a Rao-Blackwellised Particle Filter
  • Yonggang Jin, Farzin Mokhtarian: Variational Particle Filter for Multi-Object Tracking
  • Gang Li, Yanghai Tsin, Yakup Genc: Exploiting Occluding Contours for Real-Time 3D Tracking: A Unified Approach
  • Shane Brennan, Feng Tang, Qi Zhao, Hai Tao: Co-Tracking Using Semi-Supervised Support Vector Machines
  • Vijay Badrinarayanan, Patrick P¨¦rez, Francois Le Clerc, Lionel Oisel: Probabilistic color and adaptive multi-feature tracking with dynamically switched priority between cues
  • Hao Wu, Rama Chellappa, Aswin S. Sankaranarayanan, S. Kevin Zhou: Robust Visual Tracking Using the Time-Reversibility Constraint


  • Ali Sinop, Leo Grady: Uninitialized, Globally Optimal, Graph-Based Rectilinear Shape Segmentation --- The Opposing Metrics Method
  • Anders Eriksson, Carl Olsson, Fredrik Kahl: Normalized Cuts Revisited: A Reformulation for Segmentation with Linear Grouping Constraints
  • Benoit Mory, Roberto Ardon, Jean-Philippe Thiran: Variational Segmentation using Fuzzy Region Competition and Local Non-Parametric Probability Density Functions
  • Devi Parikh, Tsuhan Chen: Hierarchical Semantics of Objects (hSOs)
  • Fernando De la Torre, Joan Campoy, Zara Ambadar, Jeff Cohn: Temporal Segmentation of Facial Behavior
  • Guangcan Liu, Zhouchen Lin, Xiaoou Tang, Yong Yu: A Hybrid Graph Model for Unsupervised Object Segmentation
  • Guofeng Zhang, Jiaya Jia, Wei Xiong, Tien-Tsin Wong, Pheng-Ann Heng, Hujun Bao: Moving Object Extraction with a Hand-held Camera
  • Kemal Egemen Ozden, Konrad Schindler, Luc Van Gool: Simultaneous Segmentation and 3D Reconstruction of Monocular Image Sequences
  • Liangliang Cao, Li Fei-Fei: Spatially coherent latent topic model for concurrent object segmentation and classification
  • Lopamudra Mukherjee, Vikas Singh, Jiming Peng, Jinhui Xu, Ronald Berezney, Michael Zeitz: Generalized Median Graphs: Theory and Applications
  • Luca Bertelli, Marco Zuliani, B. S. Manjunath: Pairwise Similarities across Images for Multiple View Rigid/Non-Rigid Segmentation and Registration
  • Marco Andreetto, Lihi Zelnik-Manor, Pietro Perona: Non-Parametric Probabilistic Image Segmentation
  • Nicholas A. Lord, Jeffrey Ho, Baba C. Vemuri: USSR: A Unified Framework for Simultaneous Smoothing, Segmentation, and Registration of Multiple Images
  • Olivier Juan, Yuri Boykov: Capacity Scaling for Graph Cuts in Vision
  • Reza Hoseinnezhad, Alireza Bab-Hadiashar: A Novel High Breakdown M-estimator for Visual Data Segmentation
  • Thomas Schoenemann, Daniel Cremers: Globally Optimal Image Segmentation with an Elastic Shape Prior
  • Thomas Schoenemann, Daniel Cremers: Introducing Curvature into Globally Optimal Image Segmentation: Minimum Ratio Cycles on Product Graphs
  • Yong-Dian Jian, Chu-Song Chen: Two-View Motion Segmentation by Mixtures of Dirichlet Process with Model Selection and Outlier Removal
  • Zhe Lin, Larry Davis, David Doermann, Daniel DeMenthon: Hierarchical Part-Template Matching for Human Detection and Segmentation

4:15pm - 6:30pm: Oral session 6: Statistical Methods

  • Ramanan Navaratnam, Andrew Fitzgibbon, Roberto Cipolla: Semi-supervised Joint Manifold Learning for Multi-valued Regression
  • Bradley Davis, P. Thomas Fletcher, Elizabeth Bullitt, Sarang Joshi: Population Shape Regression From Random Design Data
  • Yaser Sheikh, Erum Khan, Takeo Kanade: Mode-seeking by Medoidshifts
  • Xiaotong Yuan, Stan Z. Li: Half Quadratic Analysis for Mean Shift: with Extension to A Sequential Data Mode-Seeking Method
  • Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song-Chun Zhu: Deformable Template As Active Basis
  • Stefan Roth, Michael J. Black: Steerable Random Fields

Thursday, October 18

8:30am - 10:00am: Oral session 7: 3D Reconstruction

  • Chadi Albitar, Pierre Graebling, Christophe Doignon: Robust Structured Light Coding for 3D Reconstruction
  • Christopher Zach, Thomas Pock, Horst Bischof: A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration
  • Paul Merrell, Amir Akbarzadeh, Liang Wang, Philippos Mordohai, Jan-Michael Frahm , Ruigang Yang, David Nister, Marc Pollefeys: Real-Time Visibility-Based Fusion of Depth Maps
  • Derek Hoiem, Andrew Stein, Alexei A. Efros, Martial Hebert: Recovering Occlusion Boundaries from a Single Image

10:30am - 12:00pm: Oral session 8: Recognition and Registration

  • Andrew Rabinovich, Andrea Vedaldi, Carolina Galleguillos, Eric Wiewiora, Serge Belongie: Objects in Context
  • Silvio Savarese, Li Fei-Fei: 3D generic object categorization, localization and pose estimation
  • Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Poggio: A Biologically Inspired System for Action Recognition
  • Vincent Gay-Bellile, Adrien Bartoli, Patrick Sayd: Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

12:00pm - 12:30pm: ICCV Awards

12:30pm - 2:00pm: Lunch

2pm - 4:15pm: Poster Session 4

Cameras, Stereo, Pose Estimation, Video & Shape


  • Aubrey K. Dunne, John Mallon, Paul F. Whelan: Efficient Generic Calibration Method for General Cameras with Single Centre of Projection
  • Brice Michoud, Erwan Guillou, Hector Briceno, Saida Bouakaz: Real-Time Marker-free Motion Capture from multiple cameras
  • Hidetoshi Mannami, Sagawa Ryusuke, Mukaigawa Yasuhiro, Echigo Tomio, Yagi Yasushi: High Dynamic Range Camera using Reflective Liquid Crystal
  • Li Zhang, Andy M. Yip, Chew Lim Tan: A Restoration Framework for Correcting Photometric and Geometric Distortions in Camera-based Document Images
  • Liang Wang, Fuchao Wu, Zhanyi Hu: Multi-Camera Calibration with One-Dimensional Object under General Motions
  • Andrew Fitzgibbon, Duncan Robertson, Srikumar Ramalingam, Andrew Blake, Antonio Criminisi: Learning Priors for Calibrating Families of Stereo Cameras
  • Nathan Jacobs, Scott Satkin, Nathaniel Roman, Richard Speyer, Robert Pless: Geolocating Static Cameras


  • Rami Ben-Ari, Nir Sochen: Variational Stereo Vision with Sharp Discontinuities and Occlusion Handling
  • Sudipta Sinha, Philippos Mordohai, Marc Pollefeys: Multi-View Stereo via Graph Cuts on the Dual of an Adaptive Tetrahedral Mesh
  • Brian Amberg, Andrew Blake, Andrew Fitzgibbon, Sami Romdhani, Thomas Vetter: Reconstructing High Quality Face Surfaces using Model Based Stereo
  • Dengfeng Chai, Qunsheng Peng: Bilayer Stereo Matching
  • Frederic Huguet, Frederic Devernay: A Variational Method for Scene Flow Estimation from Stereo Sequences
  • Hao Du, Danping Zou, Yan Qiu Chen: Relative Epipolar Motion of Tracked Features for Correspondence in Binocular Stereo
  • Kuk-Jin Yoon, In So Kweon: Stereo Matching with the Distinctive Similarity Measure
  • Pau Gargallo, Emmanuel Prados, Peter Sturm: Minimizing the Reprojection Error in Surface Reconstruction from Images


  • Stefan Hinterstoisser, Selim Benhimane, Nassir Navab: N3M: Natural 3D Markers for Real-time Object Detection and Pose Estimation
  • Alexandru Balan, Leonid Sigal, Michael Black, Horst Haussecker: Shining a Light on Human Pose: On Shadows, Shading and the Estimation of Pose and Shape
  • Bo Wu, Nevatia Ram: Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Object Detection


  • Henrik Malm, Magnus Oskarsson, Petrik Clarberg, Jon Hasselgren, Calle Lejdfors, Eric Warrant: Adaptive enhancement and noise reduction in very low light-level video
  • imran junejo, foroosh hassan: Trajectory Rectification and Path Modeling for Video Surveillance
  • Leah Bar, Benjamin Berkels, Guillermo Sapiro, Martin Rumpf: A Variational Framework for Simultaneous Motion Estimation and Restoration of Motion-Blurred Video
  • Lior Wolf, Moshe Guttmann, Daniel Cohen-Or: Non-homogeneous Content-driven Video-retargeting
  • Yan Ke, Rahul Sukthankar, Martial Hebert: Event Detection in Crowded Videos
  • Deva Ramanan, Simon Baker, Sham Kakade: Leveraging archival video for building face datasets
  • E. Scott Larsen, Philippos Mordohai, Marc Pollefeys, Henry Fuchs: Temporally Consistent Reconstruction from Multiple Video Streams using Enhanced Belief Propagation


  • Xiaofeng Mi, Doug DeCarlo: Separating Parts from 2D Shapes using Relatability
  • Christian Vogler, Zhiguo Li, Atul Kanaujia, Siome Goldenstein, Dimitris Metaxas: The Best of Both Worlds: Combining 3D Deformable Models with Active Shape Models
  • Ehsan Aganj, Jean-Philippe Pons, Florent Segonne, Renaud Keriven: Spatio-Temporal Shape from Silhouette using Four-Dimensional Delaunay Meshing
  • Frank R. Schmidt, Dirk Farin, Daniel Cremers: Fast Matching of Planar Shapes in Sub-cubic Runtime
  • Xiaogang Wang, Gianfranco Doretto, Thomas Sebastian, Jens Rittscher, Peter Tu: Shape and appearance context modeling
  • Imari Sato, Takahiro Okabe, Qiong Yu, Yoichi Sato: Shape Reconstruction Based on Similarity of Radiance Changes under Varying Illumination
  • Neel Joshi, David Kriegman: Shape from Varying Illumination and Viewpoint
  • Nhon Trinh, Benjamin Kimia: A Symmetry-Based Generative Model for Shape
  • Onur Hamsici, Aleix Martinez: Spherical-Homoscedastic Shapes
  • Paolo Favaro: Shape from Focus and Defocus: Convexity, Quasiconvexity, and Defocus-Invariant Textures
  • Per-Erik Forssen, David Lowe: Shape Descriptors for Maximally Stable Extremal Regions
  • Rui Huang, Vladimir Pavlovic, Dimitris Metaxas: Embedded Profile Hidden Markov Models for Shape Analysis
  • Soma Biswas, Gaurav Aggarwal, Rama Chellappa: Robust Estimation of Albedo for Illumination-invariant Matching and Shape Recovery
  • Xianfeng Gu, Sen Wang, Junho Kim, Yun Zeng, Yang Wang, Hong Qin, Dimitris Samaras: Ricci Flow for 3D Shape Analysis
  • Volker Blanz, Kristina Scherbaum, Hans-Peter Seidel: Fitting a Morphable Model to 3D Scans of Faces

4:15pm - 6:30pm: Oral session 9: Tracking

  • Chan-Su Lee, Ahmed Elgammal: Modeling View and Posture Manifolds for Tracking
  • Mathieu Salzmann, Richard Hartley, Pascal Fua: Convex Optimization for Deformable Surface 3-D Tracking
  • Neel Joshi, Shai Avidan, Wojciech Matusik, David Kriegman: Synthetic Aperture Tracking:Tracking through Occlusions
  • Qi Zhao, Shane Brennan, Hai Tao: Differential EMD Tracking
  • Xiaoqin Zhang, Weiming Hu, Steve Maybank, Xi Li: Graph Based Discriminative Learning for Robust and Efficient Object Tracking
  • Vinay Sharma, James W. Davis: Integrating Appearance and Motion Cues for Simultaneous Detection and Segmentation of Pedestrians

End of Third Day: Banquet

Friday, October 19

9:00am - 10:00am: Oral session 10: Learning-2

  • Junzhou Huang, Xiaolei Huang, Dimitris Metaxas: Optimizing and Learning for Registration of Moving Dynamic Textures
  • Yanghai Tsin, Yakup Genc, Ying Zhu, Visvanathan Ramesh: Learn To Track Edges
  • Tinne Tuytelaars, Cordelia Schmid: Vector Quantizing Feature Space with a Regular Lattice

10am - 12pm: Poster Session 5

Learning and Recognition- 2

  • Narendra Ahuja, Sinisa Todorovic: Discovering Hierarchical Taxonomy of Categories and Shared Subcategories in Images
  • Ognjen Arandjelovic, Roberto Cipolla: A Manifold Approach to Face Recognition from Low Quality Video Across Illumination and Pose using Implicit Super-Resolution
  • Patrick Etyngier, Florent Segonne, Renaud Keriven: Shape Priors using Manifold Learning Techniques
  • Pawan Mudigonda, Philip Torr, Andrew Zisserman: Invariant Large Margin Nearest Neighbour Classifier
  • Pingkun Yan, Saad M. Khan, Mubarak Shah: 3D Model based Object Class Detection in An Arbitrary View
  • Rong Xiao, Huaiyi Zhu, He Sun, Xiaoou Tang: Dynamic Cascades for Face Detection
  • Rui Li, Tian Tai-Peng, Sclaroff Stan: Simultaneous Learning of Non-linear Manifold and Dynamical Models for High-dimensional Time Series
  • S. Kevin Zhou, Guo Feng, JinHyeong Park, Gustavo Carneiro, Comaniciu Dorin: A probabilistic, hierarchical, and discriminant framework for rapid and accurate detection of deformable anatomic structure
  • Saad Ali, Arslan Basharat, Mubarak Shah: Chaotic Invariants for Human Action Recognition
  • Sanjiv Kumar, Henry Rowley: Classification of Weakly-Labeled Data with Partial Equivalence Relations
  • Tamir Hazan, Roee Hardoon, Amnon Shashua: pLSA for Sparse Arrays with Tsallis Pseudo-Additive Divergence: Noise Robustness and Algorithm
  • Sebastian Nowozin, Gökhan BakIr, Koji Tsuda: Discriminative Subsequence Mining for Action Classification
  • Shuicheng Yan, Huan Wang, Thomas Huang, Xiaoou Tang: Learning Auto-Structured Regressor from Uncertain Labels
  • Simon Polak, Amnon Shashua: Latent Model Clustering and Applications to Visual Recognition
  • Simon Prince, James Elder: Probabilistic Linear Discriminant Analysis for Face Recognition
  • Tom Yeh, John J. Lee, Trevor Darrell: Adaptive Vocabulary Forests for Dynamic Indexing and Category Learning
  • Vassilis Athitsos, Alexandra Stefan, Quan Yuan, Stan Sclaroff: ClassMap: Efficient Multiclass Recognition via Embeddings
  • Vidit Jain, Erik Learned-Miller, Andrew McCallum: People-LDA: Anchoring Topics to People using Face Recognition
  • Vladimir Nedovic, Arnold Smeulders, Andre Redert, Jan-Mark Geusebroek: Depth Information by Stage Classification
  • Wei Zhang, Gregory J. Zelinsky, Dimitris Samaras: Real-time accurate object detection using multiple resolutions
  • Wei Zhang, Xiangyang Xue, Zichen Sun, Yue-Fei Guo, Mingmin Chi, Hong Lu: Efficient Feature Extraction for Image Classification
  • Yu Chen, Jianzhuang Liu, Xiaoou Tang: A Divide-and-Conquer Approach to 3D Object Reconstruction from Line Drawings
  • Yu Su, Shiguang Shan, Xilin Chen, Wen Gao: Hierarchical Ensemble of Global and Local Classifiers for Face Recognition
  • Zhenguo Li, Jianzhuang Liu, Shifeng Chen, Xiaoou Tang: Noise Robust Spectral Clustering
  • Zhiwei Zhu, Taragay Oskiper, Supun Samarasekera, Harpreet Sawhney, Rakesh Kumar: Ten-fold Improvement in Visual Odometry Using Landmark Matching
  • Zhouchen Lin, Junfeng He, Xiaoou Tang, Chi-Keung Tang: Limits of Learning-Based Superresolution Algorithms
  • Alon Zweig, Daphna Weinshall: Exploiting Object Hierarchy: Combining Models from Different Category Levels
  • Ankita Kumar, Cristian Sminchisescu: Support Kernel Machines for Object Recognition
  • Anna Bosch, Andrew Zisserman, Xavier Muñoz: Image Classification using Random Forests
  • M. Alex O. Vasilescu, D. Terzopoulos: Multilinear Projection for Recognition: Extending the Tensor Framework
  • Gang Pan, Lin Sun, Zhaohui Wu, Shihong Lao: Eyeblink-based Anti-Spoofing in Face Recognition from a Generic WebCamera
  • Haibin Ling, Stefano Soatto, Narayanan Ramanathan, David Jacobs: A Study of Face Recognition as People Age
  • Jian Yang, Chengjun Liu: A General Discriminant Model for Color face Recognition
  • Robin Hess, Alan Fern, Eric Mortensen: Mixture-of-Parts Pictorial Structures for Objects with Variable Part Sets
  • Marin Ferecatu, Donald Geman: Interactive Search for Image Categories by Mental Matching
  • Alireza Fathi, Greg Mori: Human Pose Estimation using Motion Exemplars

12:00pm - 1:30pm: Lunch

1:30pm - 3:45pm: Poster Session 6

Registration, Shape, Illumination, Texture, Segmentation and Motion Analysis


  • Zhao Yi, Stefano Soatto: Correspondence Transfer For Functional-to-Anatomical Image Registration
  • Lan Dong, Vasu Parameswaran, Visvanathan Ramesh, Imad Zoghlami: Fast Crowd Segmentation Using Shape Indexing
  • Alexander Bronstein, Michael Bronstein, Ron Kimmel: Rock, Paper, and Scissors: extrinsic vs. instrinsic similarity of non-rigid shapes
  • Hongdong Li, Richard Hartley: The 3D-3D registration problem revisited
  • Sherif Makram-Ebeid, Oudom Somphone: Non-Rigid Image Registration using a Hierarchical Partition of Unity Finite Element Method
  • Terrence Chen, Thomas Huang: Optimizing Image Registration by Mutually Exclusive Scale Components
  • Ramtin Shams, Rodney Kennedy, Parastoo Sadeghi, Richard Hartley: Gradient Intensity-Based Registration of Multi-Modal Images of the Brain
  • Tae Eun Choe, Gerard Medioni: 3-D Metric Reconstruction and Registration of Images of Near-planar Surfaces

3D Shape & Applications

  • Diego Rother, Kedar Patwardhan, Guillermo Sapiro: What can casual walkers tell us about a 3D scene?
  • George Kamberov, Gerda Kamberova: Geometric Integrability and Consistency of 3D Point Clouds
  • John Novatnack, Ko Nishino: Scale-Dependent 3D Geometric Features
  • Kai Ni, Drew Steedly, Frank Dellaert: Out-of-Core Bundle Adjustment for Large-Scale 3D Reconstruction
  • Peter Savadjiev, Steven W. Zucker, Kaleem Siddiqi: On the Differential Geometry of 3D Flow Patterns: Generalized Helicoids and Diffusion MRI Analysis
  • Carl Olsson, Anders P. Eriksson, Fredrik Kahl: Efficient Optimization for L_infinity problems using Pseudoconvexity


  • Raj Gupta, Anurag Mittal: Illumination and Affine- Invariant Point Matching using an Ordinal Approach
  • Graham Finlayson, Clement Fredembach, Mark Drew: Detecting Illumination in Images
  • Jong-Il Park, Moon-Hyun Lee, Michael Grossberg, Shree Nayar: Multispectral Imaging Using Multiplexed Illumination

Data Driven and Bottom up Methods

  • Alexander C. Berg, Floraine Grabler, Jitendra Malik: Parsing Images of Architectural Scenes
  • Andreas Ess, Bastian Leibe, Luc Van Gool: Depth and Appearance for Mobile Scene Analysis
  • Baback Moghaddam, Yair Weiss, Shai Avidan: Fast Pixel/Part Selection with Sparse Eigenvectors
  • Bernard Ghanem, Narendra Ahuja: Phase Based Modelling of Dynamic Textures
  • David Nister, Fredrik Kahl, Henrik Stewenius: Structure from Motion with Missing Data is NP-Hard
  • Deli Zhao, Zhouchen Lin, Xiaoou Tang: Laplacian PCA and Its Applications
  • Elli Angelopoulou: Specular Highlight Detection Based on the Fresnel Reflection Coefficient
  • Ethan Eade, Tom Drummond: Monocular SLAM as a Graph of Coalesced Observations
  • Florian Schroff, Antonio Criminisi, Andrew Zisserman: Harvesting Image Databases from the Web
  • Marina Bertolini, GianMario Besana, Cristina Turrini: Instability of Projective Reconstruction of Dynamic Scenes near Critical Configurations
  • Hajime Nagahara, Koji Yoshida, Masahiko Yachida: An Omnidirectional Vision Sensor with Single View and Constant Resolution
  • Hamilton Chong, Steven Gortler, Todd Zickler: The von Kries Hypothesis and a Basis for Color Constancy
  • Heung-Sun Ng, Tai-Pang Wu, Chi-Keung Tang: Surface-from-Gradients with Incomplete Data for Single View Modeling
  • Ido Leichter, Michael Lindenbaum, Ehud Rivlin: Visual Tracking by Affine Kernel Fitting Using Color and Object Boundary
  • Ivan Laptev, Patrick P¨¦rez: Retrieving actions in movies
  • Jason Saragih, Roland Goecke: A Nonlinear Discriminative Approach to AAM Fitting
  • Jean-Francois Lalonde, Alexei A. Efros: Using Color Compatibility for Assessing Image Realism
  • Jonathan Starck, Adrian Hilton: Correspondence labelling for wide-timeframe freeform surface matching
  • Joost van de Weijer, Cordelia Schmid, Jakob Verbeek: Using High-Level Visual Information for Color Constancy
  • Justin Domke, Yiannis Aloimonos: Signals on Pencils of Lines
  • Kevin Loewke, Sebastian Thrun, David Camarillo, Kenneth Salisbury: Deformable Image Mosaicing for Optical Biopsy
  • M. Sabry Hassouna, Aly A. Farag: On the Extraction of Curve Skeletons using Gradient Vector Flow

3:45pm - 5:05pm: Oral session 11: Calibration and Localization

  • Jean-Philippe Tardif, Peter Sturm, Sebastien Roy: Plane-based self-calibration of radial distortion
  • Manmohan Chandraker, Sameer Agarwal, David Kriegman, Serge Belongie: Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration
  • Brian Williams, Georg Klein, Ian Reid: Real-time SLAM Relocalisation
  • Francesc Moreno-Noguer, Vincent Lepetit, Pascal Fua: Accurate Non-Iterative O(n) Solution to the PnP Problem

Saturday, October 20


3D Representation for Recognition 3dRR-07

OmniVis 2007, the Seventh Workshop on Omnidirectional Vision

3rd. International Workshop on Dynamical Vision

Human Computer Interaction Workshop

AMFG07 Analysis and Modeling of Faces and Gestures

Human Motion