CVPR 2009 Program

Time: Wednesday, 7/24/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Bernt Schiele

Time: Tuesday, 7/23/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Stan Sclaroff

Time: Monday, 7/22/09, 3:10 pm-3:40 pm
Location: Sparkle East
Session Chair: Pedro Felzenszwalb

Time: Monday, 7/22/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Kristen Grauman

Christoph Lampert
Margrit Gelautz
Trevor Darrell
Horst Bischof
Michael S. Brown
Larry Davis
Fei-Fei Li
Jean Ponce
Marshall Tappen
Frank Dellaert
Ramesh Raskar
Rob Fergus
Pedro Felzenszwalb
Bill Freeman
Rene Vidal
Baba Vemuri
Amit Roy-Chowdhury
Stefano Soatto
Yann LeCun
Jianbo Shi
David Hogg
Mark Everingham
Pascal Fua
Edmond Boyer
Daniel Cremers
Alyosha Efros
Cristian Sminchisescu
Matthew Turk
Ben Taskar
Serge Belongie
Mubarak Shah
Dorin Comaniciu
Shih-Fu Chang
Todd Zickler
Greg Mori
Jitendra Malik
Tsuhan Chen
Anthony Hoogs
Robert Collins

The Doctoral Spotlight will consist of short talks by the student authors, to be given during the main program. The goal is to give more exposure to student authors who are near graduation, and to specifically highlight their work to the rest of the community, including potential employers.

Update: The winners of the Doctoral Spotlight Awards are:

Efficient Planar Graph Cuts with Applications in Computer
Vision, by Frank R. Schmidt, Eno Toppe and Daniel Cremers

Shape Constrained Figure-Ground Segmentation and Tracking,
by Zhaozheng Yin and Robert Collins

Towards High-Resolution Large-Scale Multi-View Stereo, by
Vu Hoang Hiep, Renaud Keriven, Patrick Labatut, and Jean-Philippe Pons

Discriminative Subvolume Search for Efficient Action Detection, by
Junsong Yuan, Zicheng Liu, and Ying Wu

Each talk is 2 minutes long with 5 seconds between each talk. The slides will be on auto-play. Presentations are split among the following 4 sessions:

Session 1

Time: Monday, 7/22/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Kristen Grauman

Session 2

Time: Monday, 7/22/09, 3:10 pm-3:40 pm
Location: Sparkle East
Session Chair: Pedro Felzenszwalb

Session 3

Time: Tuesday, 7/23/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Stan Sclaroff

Session 4

Time: Wednesday, 7/24/09, 10:30-11:00 am
Location: Sparkle East
Session Chair: Bernt Schiele

Wednesday, June 24

Time: 3:10—5:10
Location: Splash 9-16

• Resolution-Invariant Image Representation and Its Applications (Jinjun Wang (NEC Laboratories America, Inc.), Shenghuo Zhu (NEC Laboratories America, Inc.), Yihong Gong (NEC Laboratories America, Inc.))
• Interval HSV: Extracting Ink Annotations (John Femiani (Arizona State University), Anshuman Razdan (Arizona State University))
• Catadioptric Projectors (Yuanyuan Ding (University of Delaware), Jing Xiao (Epson R&D, Inc.), Kar-Han Tan (HP Labs), Jingyi Yu (University of Delaware))
• Capturing Multiple Illumination Conditions using Time and Color Multiplexing (Bert De Decker (Hasselt University), Jan Kautz (University College London), Tom Mertens (University of Hasselt), Philippe Bekaert (Hasselt University))

• Removing Partial Blur in a Single Image (Shengyang Dai (Northwestern University), Ying Wu (Northwestern University))
• Uncalibrated Synthetic Aperture for Defocus Control (Natsumi Kusumoto (Osaka University), Shinsaku Hiura (Osaka University), Kosuke Sato (Osaka University))

• Optimal Single Image Capture for Motion Deblurring (Amit Agrawal (MERL), Ramesh Raskar (MIT))
• Learning Signs from Subtitles: A Weakly Supervised Approach to Sign Language Recognition (Helen Cooper (University Of Surrey), Richard Bowden (University of Surrey))
• Expression-Insensitive 3D Face Recognition using Sparse Representation (Xiaoxing Li (Virginia Tech), Tao Jia (Virginia Tech), Richard (hao) Zhang (Simon Fraser University))
• Automated Extraction of Signs from Continuous Sign Language Sentences using Iterated Conditional Modes (Sunita Nayak (Photometria Inc.), Sudeep Sarkar (University of South Florida), Barbara Loeding (University of South Florida))
• How far can you get with a modern face recognition test set using only simple features? (Nicolas Pinto (MIT), James DiCarlo (MIT), David Cox (Harvard University))
• From Structure-from-Motion Point Clouds to Fast Location Recognition (Arnold Irschara (Graz University of Technology), Christopher Zach (UNC Chapel Hill), Jan-Michael Frahm (UNC Chapel Hill), Horst Bischof (Graz University of Technology))

• Imbalanced RankBoost for Efficiently Ranking Large-Scale Image/Video Collections (Michele Merler (Columbia University), Rong Yan (IBM TJ Watson Research Center), John Smith (IBM TJ Watson Research))
• Learning query-dependent prefilters for scalable image retrieval (Lorenzo Torresani (Dartmouth College), Martin Szummer (Microsoft Research Cambridge), Andrew Fitzgibbon (Microsoft Research Cambridge))
• A Robust Approach for Automatic Registration of Aerial Images with Untextured Aerial LiDAR Data (Lu Wang (University of Southern California), Ulrich Neumann (University of Southern California))

• A Novel Feature Descriptor Invariant to Complex Brightness Changes (Feng Tang (HP Labs), Suk Hwan Lim (HP Labs), Nelson Chang (HP Labs), Hai Tao (University of California, Santa Cruz))
• Mutual Information Based Registration of Optical and Ladar Images (Andrew Mastin (MIT), Jeremy Kepner (MIT Lincoln Laboratory), John Fisher III (MIT))
• Learning to Track with Multiple Observers (Bjorn Stenger (Toshiba Research Europe), Thomas Woodley (University of Cambridge), Roberto Cipolla (University of Cambridge))
• Switching Gaussian Process Dynamic Models for Simultaneous Composite Motion Tracking and Recognition (Jixu Chen (Rensselaer Polytechnic Institute), Minyoung Kim (Rensselaer Polytechnic Institute), Yu Wang (Rensselaer Polytechnic Institute), Qiang Ji (Rensselaer Polytechnic Institute))
• A Distribution-Based Approach to Tracking Points in Velocity Vector Fields (Liefei Xu (Stevens Institute of Technology), H. Quynh Dinh (Stevens Institute of Technology), Eugene Zhang (Oregon State University), Zhongzang Lin (Oregon State University), Robert Laramee (Swansea University))

• Motion Pattern Interpretation and Detection for Tracking Moving Vehicles in Airborne Videos (Qian Yu (Sarnoff Corporation), Gerard Medioni (University of Southern California))

• Dual Distributions of Multilinear Geometric Entities (Sami Brandt (University of Oulu))
• A 3D Reconstruction Pipeline for Digital Preservation (Alexandre Vrubel (Universidade Federal Do Parana), Olga Bellon (Universidade Federal Do Parana), Luciano Silva (Universidade Federal do Parana))

• Efficient Reduction of L-infinity Geometry Problems (Hongdong Li (Australian National University))
• Fast Car Detection Using Image Strip Features (Wei Zheng (Chinese Academy of Sciences), Luhong Liang (Chinese Academy of Sciences))
• Building a database of 3D scenes from user annotations (Bryan Russell (ƒcole Normale SupŽrieu), Antonio Torralba (MIT))
• Image Categorization by Learning with Context and Consistency (Zhiwu Lu (City University of Hong Kong), Horace Ip (City University of Hong Kong))
• Classifier Grids for Robust Adaptive Object Detection (Peter Roth (Graz University of Technology), Sabine Sternig (Graz University of Technology), Helmut Grabner (ETH-Zurich), Horst Bischof (Graz University of Technology))

• Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning (Mohammad Norouzi (Simon Fraser University), Mani Ranjbar (Simon Fraser University), Greg Mori (Simon Fraser University))
• Unsupervised Learning of Hierarchical Spatial Structures In Images (Devi Parikh (Carnegie Mellon University), C. Lawrence Zitnick (Microsoft Research), Tsuhan Chen (Carnegie Mellon University))
• Optimal Scanning for Faster Object Detection (Nicholas Butko (University of California, San Diego), Javier Movellan (University of California, San Diego))
• A Streaming Framework for Seamless Building Reconstruction from Large-Scale Aerial LiDAR Data (Qian-Yi Zhou (University of Southern California), Ulrich Neumann (University of Southern California))

• On Edge Detection on Surfaces (Michael Kolomenkin (Technion - Israel Institute of Technology), Ilan Shimshoni (University of Haifa), Ayellet Tal (Technion - Israel Institute of Technology))
• Automatic Reconstruction of Cities from Remote Sensor Data (Charalambos Poullis (CGIT/IMSC/USC), Suya You (University of Southern California))
• D - Clutter: Building object model library from unsupervised segmentation of cluttered scenes (Gowri Somanath (University of Delaware), Rohith MV (University of Delaware), Dimitris Metaxas (Rutgers University), Chandra Kambhamettu (University Of Delaware))
• Sparse Subspace Clustering (Ehsan Elhamifar (Johns Hopkins University), Rene Vidal (Johns Hopkins University))
• Global Active Contour-based Image Segmentation via Probability Alignment (Andriy Myronenko (Oregon Health and Science University), Xubo Song (Oregon Health and Science University))
• Material Classification using BRDF Slices (Oliver Wang (University of California, Santa Cruz), Prabath Gunawardane (University of California, Santa Cruz), Steven Scher (University of California, Santa Cruz), James Davis (University of California, Santa Cruz))
• Epitomized Priors for Multi-labeling Problems (Jonathan Warrell (University College London), Simon Prince (University College London), Alastair Moore (University College London))
• Symmetric Two Dimensional Linear Discriminant Analysis (2DLDA) (Dijun Luo (University of Texas at Arlington), Chris Ding (University of Texas at Arlington), Heng Huang (University of Texas at Arlington))
• A Multiscale Hybrid Model Exploiting Heterogeneous Contextual Relationships for Image Segmentation (Lei Zhang (Rensselaer Polytechnic Institute), Qiang Ji (Rensselaer Polytechnic Institute))
• Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers (Peter Gehler (Max Planck Institute for Biological Cybernetics), Sebastian Nowozin (Max Planck Institute for Biological Cybernetics))
• Co-training with Noisy Perceptual Observations (Mario Christhoudias (University of Califonia, Berkeley), Raquel Urtasun (University of California, Berkeley), Ashish Kapoor (Microsoft Research), Trevor Darrell (University of California, Berkeley))
• Shared Kernel Information Embedding for Discriminative Inference (Leonid Sigal (University of Toronto), Roland Memisevic (University of Toronto), David Fleet (University of Toronto))
• Nonlinear Nonnegative Component Analysis (Stefanos Zafeiriou (Imperial College London), Maria Petrou (Imperial College London))
• Fast Normalized Cut with Linear Constraints (Linli Xu (University of Alberta), Wenye Li (University of Alberta), Dale Schuurmans (University of Alberta))
• Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets (Michal Havlena (Czech Technical University), Akihiko Torii (Czech Technical University), Jan Knopp (Czech Technical University), Tomas Pajdla (Czech Technical University))

• Towards Geographical Referencing of Monocular SLAM Reconstruction Using 3D City Models: Application to Real-Time Accurate Vision-Based Localization (Pierre Lothe (CEA LIST), Steve Bourgeois (CEA, LIST), Fabien Dekeyser (CEA, LIST), Eric Royer (LASMEA), Michel Dhome (Blaise Pascal University & CNRS))
• Trajectory Reconstruction for Affine Structure-from-Motion by Global and Local Constraints (Hanno Ackermann (Leibniz University of Hannover), Bodo Rosenhahn (Leibniz University of Hannover))
• Factorization for Non-Rigid and Articulated Structure using Metric Projections (Marco Paladini (Queen Mary, University of London), Alessio Del Bue (Instituto Superior Tecnico), Marko Sto_i_ (Instituto Superior TŽcnico), Marija Dodig (Universidade de Lisboa), Joao Xavier (Instituto Superior Tecnico), Lourdes Agapito (Queen Mary, University of London))
• Piecewise Planar City 3D Modeling from Street View Panoramic Sequences (Branislav Micusik (Austrian Research Centers), Jana Kosecka (George Mason University))
• Marked Point Processes for Crowd Counting (Weina Ge (Pennsylvania State University), Robert Collins (Pennsylvania State University))

• Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates (Jaechul Kim (University of Texas at Austin), Kristen Grauman (University of Texas at Austin))
• Actions in context (Marcin Marszalek (INRIA), Ivan Laptev (INRIA), Cordelia Schmid (INRIA))

Wednesday, June 24

Time: 2:00—3:00
Location: Sparkle West
Session Chair: G. Hager (JHU)

• Automatic Fetal Face Detection From Ultrasound Volumes Via Learning 3D and 2D Information (Shaolei Feng (Siemens Corporate Research), S. Kevin Zhou (Siemens Corporate Research), Sara Good (Siemens Corporate Research), Comaniciu Dorin (Siemens Corporate Research))
• A Nonparametric Riemannian Framework for Processing High Angular Resolution Diffusion Images (HARDI) (Alvina Goh (Johns Hopkins University), Christophe Lenglet (University of Minnesota), Paul Thompson (UCLA), Rene Vidal (Johns Hopkins University))
• CHoG: Compressed Histogram of Gradients: A Low Bit-Rate Feature Descriptor (Vijay Chandrasekhar (Stanford University), Gabriel Takacs (Stanford University), David Chen (Stanford University), Sam Tsai (Stanford University), Radek Grzeszczuk (Nokia Research Center), Bernd Girod (Stanford University))

Wednesday, June 24

Time: 2:00—3:00
Location: Sparkle East
Session Chair: Fei-fei Li (Princeton)

• A Robust Shape Model for Multi-view Car Alignment (Yan Li (Carnegie Mellon University), Leon Gu (Carnegie Mellon University), Takeo Kanade (Carnegie Mellon University))
• Linear Solution to Scale and Rotation Invariant Object Matching (Hao Jiang (Boston College), Stella Yu (Boston College))

• Dimension-Free Affine Shape Matching Through Subspace Invariance (Zhaozhong Wang (Beihang University), Han Xiao (Beihang University))