CVPR 2009 Program

Monday, June 22

Time: 3:10—5:10
Location: Splash 9-16

• Learning Partially-Observed Hidden Conditional Random Fields for Facial Expression Recognition (Kai-Yueh Chang (National Tsing Hua University), Tyng-Luh Liu (IIS, Academia Sinica), Shang-Hong Lai (National Tsing Hua University))
• Real-time Vehicle Detection for Highway Driving (Ben Southall (Sarnoff Corporation), Mayank Bansal (Sarnoff Corporation), Jayan Eledath (Sarnoff Corporation))
• Dictionary-Free Categorization of Very Similar Objects via Stacked Evidence Trees (Gonzalo Martinez Munoz (Oregon State University), Wei Zhang (Oregon State University), Nadia Payet (Oregon State University), Sinisa Todorovic (Oregon State University), Natalia Larios Delgado (University of Washington), Asako Yamamuro (Oregon State University), David Lytle (Oregon State University), Andrew Moldenke (Oregon State University), Eric Mortensen (Oregon State University), Robert Paasch (Oregon State University), Linda Shapiro (University of Washington), Thomas Dietterich (Oregon State University))
• Real-Time $O(1)$ Bilateral Filtering (Qingxiong Yang (University of Illinois at Urbana-Champaign), Kar Han Tan (HP Labs), Narendra Ahuja (University of Illinois at Urbana Champaign))

• Learning Photometric Invariance from Diversified Color Model Ensembles (Jose Manuel Alvarez (Computer Vision Center), Theo Gevers (University of Amsterdam), Antonio Lopez (Computer Vision Center))

• Combining powerful local and global statistics for texture description (Yong Xu (South China University of Technology), Sibin Huang (South China University of Technology), Hui Ji (National University of Singapore), Cornelia Fermuller (University of Maryland))
• Physics-based Edge Evaluation for Improved Color Constancy (Arjan Gijsenij (University of Amsterdam), Theo Gevers (University of Amsterdam), Joost Van de Weijer (Computer Vision Center, Barcelona))
• Reducing JointBoost-Based Multiclass Classification to Proximity Search (Alexandra Stefan (University of Texas at Arlington), Vassilis Athitsos (University of Texas At Arlington), Quan Yuan (Boston University), Stan Sclaroff (Boston University))
• Towards a Practical Face Recognition System: Robust Registration and Illumination by Sparse Representation (Andrew Wagner (University of Illinois at Urbana-Champaign), John Wright (University of Illinois at Urbana-Champaign), Arvind Ganesh (University of Illinois at Urbana-Champaign), Zihan Zhou (University of Illinois at Urbana-Champaign), Yi Ma (University of Illinois at Urbana-Champaign))
• Maximizing Intra-individual Correlations for Face Recognition Across Pose Differences (Annan Li (Chinese Academy of Sciences), Shiguang Shan (Chinese Academy of Sciences), Xilin Chen (Chinese Academy of Sciences), Wen Gao (Chinese Academy of Sciences))

• Robustifying Eye Center Localization by Head Pose Cues (Roberto Valenti (University of Amsterdam), Zeynep Yucel (University Of Amsterdam), Theo Gevers (University of Amsterdam))

• Illumination and Spatially Varying Specular Reflectance from a Single View (Kenji Hara (Kyushu University), Ko Nishino (Drexel University))
• Relighting Objects from Image Collections (Tom Haber (Hasselt University), Christian Fuchs (Max Planck Institut Informatik), Philippe Bekaert (Hasselt University), Hans-Peter Seidel (Max Planck Institut Informatik), Michael Goesele (TU Darmstadt), Hendrik P. A. Lensch (Ulm University))
• Color Estimation from a Single Surface Color (Rei Kawakami (The University of Tokyo), Katsushi Ikeuchi (The University of Tokyo))
• A Unified Model of Specular and Diffuse Reflectance for Rough, Glossy Surfaces (William Smith (University of York), Edwin Hancock (University of York))
• Robust Shadow and Illumination Estimation Using a Mixture Model (Alexandros Panagopoulos (Stony Brook University), Dimitris Samaras (Stony Brook University), Nikos Paragios (Ecole Centrale de Paris/INRIA Saclay, Ile-de-France))
• New Appearance Models for Natural Image Matting (Dheeraj Singaraju (Johns Hopkins University), Carsten Rother (Microsoft Research Cambridge), Christoph Rhemann (Vienna University of Technology))

• Similarity Metrics and Efficient Optimization for Simultaneous Registration (Christian Wachinger (TU Munich), Nassir Navab (TU Munich))

• StaRSaC: Stable Random Sample Consensus for Parameter Estimation (Jongmoo Choi (University of Southern California), Gerard Medioni (University of Southern California))
• Shape Comparison Using Perturbing Shape Registration (Yifeng Jiang (Yale University), Erin Edmiston (Yale School of Medicine), Fei Wang (Yale University), Hilary Blumberg (Yale University), Lawrence Staib (Yale University), Xenophon Papademetris (Yale University))
• Robust Guidewire Tracking in Fluoroscopy (Peng Wang (Siemens Corporate Research), Terrence Chen (Siemens Corporate Research), Ying Zhu (Siemens), Wei Zhang (Siemens Corporate Research), S. Kevin Zhou (Siemens Corporate Research), Comaniciu Dorin (Siemens Corporate Research))
• Optimization of Landmark Selection for Cortical Surface Registration (Anand Joshi (UCLA), David Shattuck (UCLA), Dimitrios Pantazis (University of Southern California), Quanzheng Li (University of Southern California), Hanna Damasio (University of Southern California), Richard Leahy (University of Southern California))
• Active Volume Models for 3D Medical Image Segmentation (Tian Shen (Lehigh University), Hongsheng Li (Lehigh University), Zhen Qian (Piedmont Heart Institute), Xiaolei Huang (Lehigh University))
• Fuzzy-Cuts: A Knowledge-Driven Graph-Based Method for Medical Image Segmentation (Deepak Roy Chittajallu (University of Houston), Gerd Brunner (University of Houston), Uday Kurkure (University of Houston), Raja Yalamanchili (University of Houston), Ioannis Kakadiaris (University of Houston))
• Echocardiogram View Classification using Edge Filtered Scale-invariant Motion Features (Ritwik Kumar (University of Florida), Fei Wang (IBM Almaden Research Center), David Beymer (IBM Almaden Research Center), Tanveer Syeda-Mahmood (IBM Almaden Research Center))
• Shape Constrained Figure-Ground Segmentation and Tracking (Zhaozheng Yin (Pennsylvania State University), Robert Collins (Pennsylvania State University))
• Trajectory Parsing by Cluster Sampling in Spatio-temporal Graph (Xiaobai Liu (Huazhong University of Science and Technology & Lotus Hill Institute), Liang Lin (UCLA), Song-Chun Zhu (UCLA & Lotus Hill Institute), Hai Jin (Huazhong University of Science and Technology))
• Learning Visual Flows: A Lie Algebraic Approach (Dahua Lin (MIT), Eric Grimson (MIT), John Fisher III (MIT))
• Vanishing Point Estimation by Self Similarity (Hadas Kogan (HP Labs), Ron Maurer (HP Labs), Renato Keshet (HP Labs))
• Active Learning for Large Multi-class Problems (Prateek Jain (University of Texas at Austin), Ashish Kapoor (Microsoft Research))
• What is the Spatial Extent of an Object? (Jasper Uijlings (University of Amsterdam), Arnold Smeulders (University of Amsterdam), Remko Scha (University of Amsterdam))
• Pose Estimation for Category Specific Multiview Object Localization (Mustafa Ozuysal (EPFL), Vincent Lepetit (EPFL), Pascal Fua (EPFL))
• Non-Rigid 2D-3D Pose Estimation and 2D Image Segmentation (Romeil Sandhu (Georgia Institute of Technology), Samuel Dambreville (Georgia Institute of Technology), Anthony Yezzi (Georgia Institute of Technology), Allen Tannenbaum (Georgia Institute of Technology))
• Multi-Cue Onboard Pedestrian Detection (Christian Wojek (TU Darmstadt), Stefan Walk (TU Darmstadt), Bernt Schiele (TU Darmstadt))

• HOP: Hierarchical Object Parsing (Iasonas Kokkinos (Ecole Centrale Paris & INRIA Saclay), Alan Yuille (UCLA))
• A Convex Relaxation Approach for Computing Minimal Partitions (Thomas Pock (Graz University of Technology), Antonin Chambolle (Ecole Polytechnique & CNRS), Daniel Cremers (University of Bonn), Horst Bischof (Graz University of Technology))
• Global Connectivity Potentials for Random Field Models (Sebastian Nowozin (Max Planck Institute for Biological Cybernetics), Christoph Lampert (Max Planck Institute for Biological Cybernetics))

• Symmetry Integrated Region-based Image Segmentation (Yu Sun (University of California, Riverside), Bir Bhanu (University of California, Riverside))
• On the Set of Images Modulo Viewpoint and Contrast Changes (Ganesh Sundaramoorthi (UCLA), Peter Petersen (UCLA), V. S. Varadarajan (UCLA), Stefano Soatto (UCLA))
• Fast Multiple Shape Correspondence by Pre-Organizing Shape Instances (Brent Munsell (University of South Carolina), Andrew Temlyakov (University of South Carolina), Song Wang (University Of South Carolina))
• Learning Shape Prior Models for Object Matching (Tingting Jiang (INRIA), Frederic Jurie (University of Caen), Cordelia Schmid (INRIA))
• Global Optimization for Alignment of Generalized Shapes (Hongsheng Li (Lehigh University), Tian Shen (Lehigh University), Xiaolei Huang (Lehigh University))
• Unsupervised Learning for Graph Matching (Marius Leordeanu (Carnegie Mellon University), Martial Hebert (Carnegie Mellon University))
• Max-Margin Hidden Conditional Random Fields for Human Action Recognition (Yang Wang (Simon Fraser University), Greg Mori (Simon Fraser University))
• Rank Priors for Continuous Non-Linear Dimensionality Reduction (Andreas Geiger (Karlsruhe Institute of Technology), Raquel Urtasun (University of California, Berkeley), Trevor Darrell (University of California, Berkeley))
• Unsupervised Maximum Margin Feature Selection with Manifold Regularization (Bin Zhao (Tsinghua University), James Kwok (Hong Kong University of Science and Technology), Fei Wang (Florida International University), Changshui Zhang (Tsinghua University))
• Learning a Distance Metric from Multi-instance Multi-label Data (Rong Jin (Michigan State University), Shijun Wang (National Institutes of Health), Zhi-Hua Zhou (Nanjing University))
• Alphabet SOUP: A Framework for Approximate Energy Minimization (Stephen Gould (Stanford University), Fernando Amat (Stanford University), Daphne Koller (Stanford University))
• An Instance Selection Approach to Multiple Instance Learning (Zhouyu Fu (Australian National University), Antonio Robles-Kelly (NICTA & Australian National University))
• Learning from Ambiguously Labeled Images (Timothee Cour (University of Pennsylvania), Benjamin Sapp (University of Pennsylvania), Chris Jordan (University of Pennsylvania), Ben Taskar (University of Pennsylvania))
• Recognizing Linked Events: Searching the Space of Feasible Explanations (Dima Damen (University of Leeds), David Hogg (University of Leeds))
• Abnormal Crowd Behavior Detection using Social Force Model (Ramin Mehran (University of Central Florida), Alexis Oayama (University of Nevada Reno), Mubarak Shah (University of Central Florida))
• Recognition of Repetitive Sequential Human Activity (Quanfu Fan (IBM), Russell Bobbitt (IBM), Zhai Yun (IBM), Akira Yanagwa (IBM), Sharath Pankanti (IBM), Arun Hampapur (IBM))

Monday, June 22

Time: 2:00—3:00
Location: Sparkle West
Session Chair: M. Brown (NU Singapore)

• High Dynamic Range Image Reconstruction from Hand-held Cameras (Pei-Ying Lu (National Taiwan University), Tz-Huan Huang (National Taiwan University), Meng-Sung Wu (National Taiwan University), Yi-Ting Cheng (National Taiwan University), Yung-Yu Chuang (National Taiwan University))
• Contextual Restoration of Severely Degraded Document Images (Jyotirmoy Banerjee (IIIT-Hyderabad), Anoop Namboodiri (IIIT-Hyderabad), C. V. Jawahar (IIIT-Hyderabad))
• Polarization: Beneficial for Visibility Enhancement? (Tali Treibitz (Technion - Israel Institute of Technology), Yoav Schechner (Technion - Israel Institute of Technology))

Monday, June 22

Time: 2:00—3:00
Location: Sparkle East
Session Chair: K. Kutulakos (U Toronto)

• Stereo Matching with Nonparametric Smoothness Priors in Feature Space (Brandon Smith (University of Wisconsin-Madison), Li Zhang (University of Wisconsin-Madison), Hailin Jin (Adobe Systems Inc.))
• Spatiotemporal Stereo via Spatiotemporal Quadric Element (Stequel) Matching (Mikhail Sizintsev (York University), Richard Wildes (York University))
• A Stereo Approach that Handles the Matting Problem via Image Warping (Michael Bleyer (Vienna University of Technology), Margrit Gelautz (Vienna University of Technology), Carsten Rother (Microsoft Research Cambridge), Christoph Rhemann (Vienna University of Technology))

Monday, June 22

Time: 10:30—12:30
Location: Splash 9-16

• A Unified Active and Semi-Supervised Learning Framework for Image Compression (Xiaofei He (Zhejiang University), Ming Ji (Zhejiang University), Hujun Bao (Zhejiang University))
• Digital Face Makeup by Example (Dong Guo (National University of Singapore), Terence Sim (National University of Singapore))
• Hardware-Efficient Belief Propagation (Chia-Kai Liang (National Taiwan University), Chao-Chung Cheng (National Taiwan University), Yen-Chieh Lai (National Taiwan University), Liang-Gee Chen (National Taiwan University), Homer Chen (National Taiwan University))

• Directed Assistance for Ink-Bleed Reduction in Old Documents (Zheng Lu (National University of Singapore), Zheng Wu (National University Of Singapore), Michael Brown (National University of Singapore))
• Vanishing Point Detection for Road Detection (Hui Kong (Ecole Normale Superieure), Jean-Yves Audibert (Ecole des Ponts & Ecole Normale SupŽrieure), Jean Ponce (Ecole Normale Superieure))
• Blind motion deblurring from a single image using sparse approximation (Jian-Feng Cai (National University of Singapore), Hui Ji (National University of Singapore), Chaoqiang Liu (National University of Singapore), Zuowei Shen (National University of Singapore))
• Human Age Estimation Using Bio-inspired Features (Guodong Guo (North Carolina Central University), Guowang Mu (North Carolina Central University), Yun Fu (BBN Technologies), Thomas Huang (University of Illinois at Urbana-Champaign))
• Cancelable Iris Biometrics and Using Error Correcting Codes to Reduce Variability in Biometric Data (Sanjay Kanade (Institut TELECOM; TELECOM & Management SudParis), Dijana Petrovska-DelacrŽtaz (Institut TELECOM; TELECOM & Management SudParis), Bernadette Dorizzi (Institut TELECOM; TELECOM & Management SudParis))
• Physiological Face Recognition Is Coming of Age (Pradeep Buddharaju (University of Houston), Ioannis Pavlidis (University of Houston))
• Support Vector Machines in Face Recognition with Occlusions (Hongjun Jia (The Ohio State University), Aleix Martinez (The Ohio State University))
• Boosted Multi-Task Learning for Face Verification With Applications to Web Image and Video Search (Xiaogang Wang (MIT), Cha Zhang (Microsoft Research), Zhengyou Zhang (Microsoft Research))
• Volterrafaces: Discriminant Analysis using Volterra Kernels (Ritwik Kumar (University of Florida), Arunava Banerjee (University of Florida), Baba Vemuri (University of Florida))
• Learning Mappings for Face Synthesis from Near Infrared to Visual Light Images (Jie Chen (University of Oulu), Dong Yi (Chinese Academy of Sciences), Jimei Yang (University of Science and Technology of China), Guoying Zhao (University of Oulu), Stan Li (Chinese Academy of Sciences), Matti PietikŠinen (University of Oulu))
• Shape Evolution for Rigid and Nonrigid Shape Registration and Recovery (Junyan Wang (Nanyang Technological University), Kap Luk Chan (Nanyang Technological University))
• SIFT-Rank: Ordinal Description for Invariant Feature Correspondence (Matthew Toews (Brigham and Women’s Hospital & Harvard Medical School), William Wells (Harvard Medical School & Brigham and Women’s Hospital))
• Picking the best DAISY (Simon Winder (Microsoft Research), Gang Hua (Microsoft Live Labs Research), Matthew Brown (University of British Columbia))
• Learning Similarity Measure for Multi-Modal 3D Image Registration (Daewon Lee (Max Planck Institute for Biological Cybernetics), Matthias Hofmann (Max Planck Institute for Biological Cybernetics), Florian Steinke (Siemens Corporate Technology), Yasemin Altun (Max Planck Institute for Biological Cybernetics), Nathan Cahill (University of Oxford), Bernhard Schšlkopf (Max Planck Institute for Biological Cybernetics))
• Constrained Marginal Space Learning for Efficient 3D Anatomical Structure Detection in Medical Images (Yefeng Zheng (Siemens Corporate Research), Bogdan Georgescu (Siemens Corporate Research), Haibin Ling (Temple University), S. Kevin Zhou (Siemens Corporate Research), Michael Scheuering (Siemens Corporate Research), Comaniciu Dorin (Siemens Corporate Research))
• Shape Analysis with Conformal Invariants for Multiply Connected Domains and its Application to Analyzing Brain Morphology (Yalin Wang (UCLA), Xianfeng Gu (State University of New York at Stony Brook), Tony Chan (Mathematics Department, UCLA), Paul Thompson (UCLA))
• Automated Feature Extraction for Early Detection of Diabetic Retinopathy in Fundus Images (Saiprasad Ravishankar (University of Illinois Urbana Champaign), Arpit Jain (University of Maryland), Anurag Mittal (IIT Madras))
• A Robust Parametric Method for Bias Field Estimation and Segmentation of MR Images (Chunming Li (Vanderbilt University), Chris Gatenby (Vanderbilt University), Li Wang (Nanjing University of Science and Technology), John Gore (Vanderbilt University))
• Markerless Motion Capture with Unsynchronized Moving Cameras (Nils Hasler (MPI Informatik), Bodo Rosenhahn (University of Hannover), Thorsten ThormŠhlen (Max Planck Institut Informatik), Michael Wand (Saarland University & Max Planck Institut Informatik), Juergen Gall (BIWI, ETH Zurich), Hans-Peter Seidel (Max Planck Institut Informatik))

• Early Spatiotemporal Grouping with a Distributed Oriented Energy Representation (Konstantinos Derpanis (York University), Richard Wildes (York University))

• Discriminatively Trained Particle Filters for Complex Multi-Object Tracking (Rob Hess (Oregon State University), Alan Fern (Oregon State University))
• ImageNet: A Large-Scale Hierarchical Image Database (Jia Deng (Princeton University), Wei Dong (Princeton University), Richard Socher (Princeton University), Li-Jia Li (Princeton University), Kai Li (Princeton University), Li Fei-Fei (Princeton University))
• Understanding Images of Groups of People (Andrew Gallagher (Eastman Kodak Company & Carnegie Mellon University), Tsuhan Chen (Cornell University))
• Efficient Algorithms for Subwindow Search in Object Detection and Localization (Senjian An (Curtin University of Technology), Patrick Peursum (Curtin University of Technology), Wanquan Liu (Curtin University of Technology), Svetha Venkatesh (Curtin University of Technology))
• Learning Mixed Templates for Object Recognition (Zhangzhang Si (UCLA), Haifeng Gong (UCLA), Ying Nian Wu (UCLA), Song-Chun Zhu (UCLA & Lotus Hill Institute))
• Fast concurrent object localization and recognition (Tom Yeh (MIT), John Lee (MIT), Trevor Darrell (University of California, Berkeley))
• Shape-based Detection of Moving Objects in Videos Using Synthetic 3D Models (Alexander Toshev (University of Pennsylvania), Ameesh Makadia (Google Research), Kostas Daniilidis (University of Pennsylvania))
• A Collaborative Benchmark for Region of Interest Detection Algorithms (Tz-Huan Huang (National Taiwan University), Kai-Yin Cheng (National Taiwan University), Yung-Yu Chuang (National Taiwan University))
• Pedestrian Detection: A Benchmark (Piotr Dollar (Caltech), Christian Wojek (TU Darmstadt), Bernt Schiele (TU Darmstadt), Pietro Perona (Caltech))
• Learning Trajectory Patterns by Clustering: Experimental Studies and Comparative Evaluation (Brendan Morris (University of California, San Diego), Mohan Trivedi (University of California, San Diego))
• Learning color and locality cues for moving object detection and segmentation (Feng Liu (University of Wisconsin-Madison), Michael Gleicher (University of Wisconsin-Madison))
• Increased Discrimination in Level Set Methods with Embedded Conditional Random Fields (Dana Cobzas (University of Alberta), Mark Schmidt (University of British Columbia))
• Extraction of Tubular Structures over an Orientation Domain (Micka‘l PŽchaud (CERTIS / LIENS), Gabriel PeyrŽ (CEREMADE), Renaud Keriven (Ecole des Ponts ParisTech))
• LidarBoost: Depth Superresolution for ToF 3D Shape Scanning (Sebastian Schuon (Stanford University), Christian Theobalt (Stanford University), James Davis (University of California, Santa Cruz), Sebastian Thrun (Stanford University))

• Efficient Planar Graph Cuts with Applications in Computer Vision (Frank Schmidt (University Of Bonn), Eno Toeppe (University of Bonn), Daniel Cremers (University of Bonn))
• Locally Constrained Diffusion Process on Locally Densified Distance Spaces with Applications to Shape Retrieval (Xingwei Yang (Temple University), Suzan Koknar-Tezel (Temple University), Longin Jan Latecki (Temple University))
• Shape Classification Through Structured Learning of Matching Measures (Longbin Chen (University of California, Santa Barbara), Julian McAuley (NICTA & Australian National University), Rogerio Feris (IBM T. J. Watson Research Center), Tiberio Caetano (NICTA), Matthew Turk (University of California, Santa Barbara))
• Surface Feature Detection and Description with Applications to Mesh Matching (Andrei Zaharescu (INRIA Grenoble), Edmond Boyer (LJK - INRIA Grenoble), Kiran Varanasi (INRIA Grenoble), Radu Horaud (INRIA Grenoble))
• Robust Multi-Class Transductive Learning with Graphs (Wei Liu (Columbia University), Shih-fu Chang (Columbia University))
• Multiplicative Nonnegative Graph Embedding (Changhu Wang (University of Science and Technology of China), Zheng Song (National University of Singapore), Shuicheng Yan (National University of Singapore), Lei Zhang (Microsoft Research Asia), Hong-Jiang Zhang (Microsoft Corporation))
• Image Categorization with Spatial Mismatch Kernels (Zhiwu Lu (City University of Hong Kong), Horace Ip (City University of Hong Kong))
• Multiple Instance Feature for Robust Part-based Object Detection (Zhe Lin (University of Maryland at College Park), Gang Hua (Microsoft Live Labs Research), Larry Davis (University of Maryland))
• Recognizing Indoor Scenes (Ariadna Quattoni (MIT & ICSI, Berkeley CA), Antonio Torralba (MIT))
• Constrained Clustering via Spectral Regularization (Zhenguo Li (The Chinese University of Hong Kong), Jianzhuang Liu (The Chinese University of Hong Kong), Xiaoou Tang (The Chinese University of Hong Kong))
• Manifold Discriminant Analysis (Ruiping Wang (Chinese Academy of Sciences), Xilin Chen (Chinese Academy of Sciences))
• Stereo Matching in the Presence of Sub-Pixel Calibration Errors (Heiko Hirschmueller (German Aerospace Center / DLR), Stefan Gehrig (Daimler AG))

• Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space (Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University))
• Joint Depth and Alpha Matte Optimization via Fusion of Stereo and Time-of-Flight Sensor (Jiejie Zhu (University of Kentucky), Miao Liao (University of Kentucky), Ruigang Yang (University of Kentucky), Zhigeng Pan (Zhejiang University))

• Learning Semantic Visual Vocabularies Using Diffusion Distance (Jingen Liu (University of Central Florida), Yang Yang (University of Central Florida), Mubarak Shah (University of Central Florida))
• Topology Dictionary with Markov Model for 3D Video Content-Based Skimming and Description (Tony Tung (Kyoto University), Takashi Matsuyama (Kyoto University))
• Learning Optimized MAP Estimates in Continuously-Valued MRF Models (Kegan Samuel (University of Central Florida), Marshall Tappen (University of Central Florida))

Monday, June 22

Time: 9:00—10:20
Location: Sparkle West
Session Chair: R. Wildes (York U)

• Contextual Flow (Ying Wu (Northwestern University), Jialue Fan (Northwestern University))
• Large Displacement Optical Flow (Thomas Brox (University of California, Berkeley), Christoph Bregler (New York University), Jitendra Malik (University of California, Berkeley))
• Image Registration by Minimization of Residual Complexity (Andriy Myronenko (Oregon Health and Science University), Xubo Song (Oregon Health and Science University))
• Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies (Richard Roberts (Georgia Institute of Technology), Christian Potthast (Georgia Institute of Technology), Frank Dellaert (Georgia Institute of Technology))

Monday, June 22

Time: 9:00—10:20
Location: Sparkle East
Session Chair: K. Graumann (UT Austin)

• Pose Search: retrieving people using their pose (Vittorio Ferrari (ETH Zurich), Manuel Marin-Jimenez (University of Granada), Andrew Zisserman (University of Oxford))
• Efficient Representation of Local Geometry for Large Scale Object Retrieval (Michal Perdoch (Czech Technical University), Ondrej Chum (Czech Technical University), Jiri Matas (Czech Technical University))
• Geometric min-Hashing: Finding a (Thick) Needle in a Haystack (Ondrej Chum (Czech Technical University), Michal Perdoch (Czech Technical University), Jiri Matas (Czech Technical University))
• Bundling Features for Large Scale Partial-Duplicate Web Image Search (Zhong Wu (Tsinghua University), Qifa Ke (Microsoft Research-ISRC), Michael Isard (Microsoft Research), Jian Sun (Microsoft Research Asia))

Ramesh Raskar, MIT
Se Baek Oh, MIT
Anthony Accardi, MIT
Zhengyun Zhang, Stanford

The ray–based 4D lightfield representation, based on simple 3D geometric principles, has led to a range of new algorithms and applications in Computer Vision and Graphics. They include digital refocusing,
depth estimation, synthetic aperture, and glare reduction within a camera or using an array of cameras.

The lightfield representation is, however, inadequate to describe interactions with diffractive or phase–sensitive optical elements. Fourier optics principles are used to represent wavefronts with additional phase information. This course reviews the current and future directions in exploiting higher dimensional representation of light transport. We hope the course will inspire researchers in computer vision comfortable with ray–based analysis to develop new tools and algorithms based on joint exploration of geometric and wave optics concepts.

This page is available for job postings.

Job posters: Please use the comments submission mechanism below to make your post.  Comments are moderated.

Job seekers: Please do NOT submit a comment below as this page is for job listings only.  If you submit a resume or request for a job, your comment will be rejected by the moderation process.

Jianxin Wu Sat/Sun
Philip Rogers Sat/Sun
Carlos Nieto Sat/Sun
Grant Schindler Sat
Andy Bardagjy Sat
Alireza Fathi Sun
Sangmin Oh Sun

We would like to thank you for agreeing to review for CVPR2009. Please read the following instructions about how to review papers using the CVPR2009 submission and reviewer system. In addition, please see the Reviewer Guidelines and FAQs.

• REMEMBER: Reviews are DUE 5pm Pacific Standard Time (PST) Jan 29, 2009.
• The submission site is https://cmt.research.microsoft.com/CVPR2009/ (bookmark or save this URL!).
• Please make sure that your browser has cookies and Javascript enabled.
• Please add “cmt@microsoft.com” to your list of safe senders to prevent important email announcements from being blocked by spam filters.
• Do not create a new account! You will have the opportunity to change your contact email/account name after you log in using the email address we used to contact you.

Important things to remember:

1. If you have forgotten your password, go to the main page, click “Reset Your Password” and follow instructions to get a password sent to the email address we used to contact you on 10/17/2008.
2. Log in and go to “Edit Contact Information” (item near the top right in the submission site). Don’t forget to click the “Update” button to save the edited information. If you wish to change the contact email address (and hence account name), you can modify it via the “Change your Email” box.
3. Click on “Reviewer” link. When in doubt, click on this “Reviewer” link, as it always brings you to the reviewer console.
4. Please enter the following information in order (see pink bar): conflict domain, reviewer type, subject areas. Note that when specifying subject areas, you indicate only one “primary” subject area and any number of “secondary” subject areas. Please pay extra attention in selecting your subject areas, as this information is critical in allowing us to properly assign papers to you. Caution: you cannot pick the “primary” subject area as a “secondary” subject area; if you do this, the system will not allow you to save. For example, if you had picked “Face and Gesture” as the “primary” area, you cannot pick “Face and Gesture” as a “secondary” area.
5. Since this site is new for CVPR, please read all instructions carefully. Note that edited information is not saved until you click the “Save Changes” or “Update” button.
6. If you do not enter your conflict domain, reviewer type, and subject areas by 5 PM Nov. 24 (Pacific Standard Time)/1 AM Nov. 25 (GMT), you will be removed as a reviewer.
7. For your reference, the paper submission guidelines can be found here.

Discussions with Area Chairs via a NEW bulletin board:

In our invitation, we mentioned that we expect reviewers to work with area chairs to clear up confusions and reach consensus on papers. This new site has an electronic bulletin board feature that allows area chairs to contact reviewers anonymously. Once the area chair posts a note, reviewers will be notified and asked to log in to see the post and respond. The identities of the reviewers will be hidden from each other.

Once you’ve been notified that the papers have been assigned to you, please log in to the site and follow these steps:

1. Download papers and check for possible conflict or submission rule violation:

• Click on “Paper Reviews and Discussions”.
• In the “Paper Reviews and Discussions” page, click on “Download Assigned Papers”. This allows you to download a zip file containing all the papers plus supplementary files (if available).
• Contact the program chairs immediately (cvpr09-pc-chairs@googlegroups.com) if:
  1. You think you are in any way conflicted with the paper.
  2. There is a violation of the stated paper submission rules.
  • Such a violation include:
    • Not anonymous (names listed on front page),
    • Over 8 pages,
    • Is double submission,
    • Supplementary material includes newer version of the paper.
  • Please specify the exact nature of the violation.
  • For your reference, the paper submission guidelines can be found here.

2. Familiarize yourself with the “Paper Reviews and Discussions” page (part of which shown below):

• Please ignore all references to “bids” (these references will be removed).
• “Paper Summary” label: next to it, you’ll see the icons ”+” and ”-”. Clicking on ”+” shows you all the abstracts; clicking on “-” collapses all them back.
• At the end of each paper title, you’ll see “+” as well. This has the same function of showing the abstract for that paper, toggling to “-” at the same time, which collapses it when selected.
• Please take the time to familiarize yourself with the table entries; clicking on any of the column heading (e.g., “Paper ID” or “Rank”) sorts according to its description.

3. Review papers:

• For a paper, under the review column, click “Add” (to the right of the “Review” line) to review. Please read instructions carefully. Please see the Reviewer Guidelines AND take each review seriously.  Authors are counting on you for a fair and thorough review.
• Currently, CMT does not allow users to type in certain characters into a text box that could be interpreted as html tags (for example, “y<x”) or a malicious script. As a workaround, introducing spaces between these characters (for example, “y < x”) will allow you to submit the text since this can no longer be interpreted as an html tag.
• If you save your review as a draft, it is visible only to you. You can access your draft review form by clicking on the same “Add” link. To make the review visible to the area chair, click on the “Submit” button in the review form. “Submit” won’t work if any of the required items is not filled.

4. (Optional) Review papers offline:

• You have two options to access the “Offline Reviewing” page: (1) In the “Paper Reviews and Discussions” page, click on “Review papers offline” link near the top of the page, or (2) In the “View/Edit Review” page, click on “offline reviewing” link.
• In the “Offline Reviewing” page, you can download one review template file for a single paper, several papers, or all the papers. We suggest that you download a review template file for each paper to avoid confusion.
• Please read instructions on how to modify the file to incorporate your responses. Note that you must not add certain characters in your responses that could be interpreted as html tags or a malicious script. See item 3 above.
• You can upload the completed file using the “Upload” interface at the bottom of the page. The new uploaded version will (destructively) overwrite the current review.
• We suggest that you try downloading a review template file for one paper, enter test responses, and upload to get a sense of how it works.
• You should always verify the review after uploading (by inspecting it online).
• We suggest that you use an XML editor to edit the file, for example: EditiX (Windows, Unix/Linux, Mac OS X) or XML Notepad 2007 (Windows only). (Remember to edit only fields currently filled with the phrase ”REPLACE THIS WITH YOUR ANSWER”.)

5. (Optional, for originally assigned reviewer ONLY) Assign external reviewer:

• This feature is to be used sparingly. Use it only when you know someone else who is substantially more qualified than you in reviewing the paper and that he/she is willing to review the paper. You are ultimately responsible for the timeliness and quality of the review. You will hear from us if you use this feature for many of the papers assigned to you.
  
• In the “Papers Reviews and Discussion” page, you are given the option to assign an external reviewer for any paper. Under the “Review” column, click “Assign” to the right of “External Reviewer”.
• Follow the instructions. You will be asked to supply the email address of the external reviewer. This email address will be the account of this external reviewer. IMPORTANT: Check with this external reviewer if he/she already has a CMT account; if so, make sure you use the exact email address associated with this account. Otherwise, you will be unnecessarily creating a new account for this person and resulting in delays.
• Ask the external reviewer to log in to the CMT site (https://cmt.research.microsoft.com/CVPR2009) using the instructions in this page (http://www.cvpr2009.org/reviewer-instructions).
• The review will be shared between the original and external reviewers; both can see and update the same review.
• Later, if the area chair requests for a discussion, only the area chair, you, and the other originally assigned reviewers will be able to access the discussion page. External reviewers will not be able to participate.

6. Rank papers:

• Once you’ve reviewed the papers, you can rank them (the first being the best in your batch). In the “Paper Reviews and Discussions” page, click on “Edit Ranks” near the top of the page.
• In the “Edit Paper Ranks” page, click on the “Start Ranking” link for the papers.
• Use the “Move Up” and “Move Down” to adjust the ranks.
• Remember to click on the “Save Changes” button.

7. (For originally assigned reviewer ONLY) Discuss reviews between review deadline (5PM PST Jan 29, 2009) and 5PM PST Feb 5, 2009:

• You can view the other reviews for your papers through the “View Paper Statuses and Reviewing Data for Papers Assigned to Me” link in the “Reviewer” console.
• If the area chair decides to initiate a discussion associated with a paper, he/she will make a post for that paper, and all the reviewers will receive an email from CMT. Please do not respond to this email as such an email is not monitored. The email will have a heading like “CVPR2009: New reviewer discussion posted for Paper ID XXX”. There is a link in the email you can use to join the discussion (after logging in, you will be routed directly to the discussion page).
• Alternatively, you can log in to CMT, and in the “Reviewer” console, select “Paper Reviews and Discussions”. Then click on “View/Post Message” (in “Discussion | Author Feedback” column) for the paper being discussed.
• To see all three (anonymized) reviews, click on “View All” in the “Review” column in the “Paper Reviews and Discussions” page. Please note which reviewer you are. (Alternatively, you can select “View Paper Statuses and Reviewing Data for Papers Assigned to Me” link in the “Reviewer” console.)
• In your post (created via “Reply” in the “Paper Discussion” page), please identify yourself as “Reviewer X”, where “X” is the review with which you’re associated. Do not identify yourself by name. Once you’ve posted, the area chair and all reviewers for that paper will receive a similar notification email from CMT.
• Please conduct the discussion in a professional manner. Be aware that while the other reviewers do not know who you are, the AC (for the paper being discussed) does.
• If you gave a “Borderline” rating and at least one other reviewer also gave a “Borderline” rating: It would help the AC if you say you’re closer to accepting or rejecting the paper (based on the discussion), and then make the change to your review accordingly.
• After you’ve posted, DO NOT REFRESH PAGE (e.g., by hitting F5)! This will generate another post with the exact same message!
• You will be given the opportunity to revise your reviews as a result of the discussions, up til the 5PM PST Feb 5 deadline. To be fair to authors, after this deadline, all reviews will be frozen.
• Because of the frank nature of the discussions, the authors will not see them at any time.
• Guidelines for ACs are given here.

8. (For originally assigned reviewer ONLY) Discuss author rebuttals between author rebuttal deadline (5PM PST Feb 13, 2009) and 5PM PST Feb 20, 2009:

• The author rebuttal period is Feb 6, 2009 5pm PST - Feb 13, 2009 5pm PST. You need not do anything during this time.
• Once the author rebuttal period is over, you will be able to see the author rebuttal (but not before). We will be enabling discussions for a week past the rebuttal deadline. The ACs, at their discretion, may initiate another round of discussions to get your reactions to the author rebuttals.
• Again, because of the frank nature of the discussions, the authors will not see these discussions at any time.
• Note that at this point, your reviews are frozen and you will not be able to make any more changes to your review—we will not respond to emails regarding this matter.

Finally:

If you encounter any problems, please email cvpr09-pc-chairs@googlegroups.com.

Thanks again,

Irfan Essa, Marc Pollefeys, Sing Bing Kang
CVPR 2009 Program Chairs