Note that posters were distributed randomly across days and not grouped thematically, in order to allow poster presenters to see as many other posters possible in their respective area. Hence, poster spotlights are not perfectly fitting the main theme of the oral session they are part of.
Tuesday 8th November 2011
08:30 - 09:20
Opening remarks
09:20 - 10:20
Awards ceremony
10:20 - 10:50
Coffee Break
10:50 - 12:30
Session 1: Recognition
A Graph-matching Kernel for Object Categorization Olivier Duchenne, Armand Joulin, Jean Ponce
Domain Adaptation for Object Recognition: An Unsupervised Approach Raghuraman Gopalan, Ruonan Li, Rama Chellappa
Structured Class-Labels in Random Forests for Semantic Image Labelling Peter Kontschieder, Samuel Rota Bulò, Horst Bischof, Marcello Pelillo
12:30 - 14:00
Lunch
14:00 - 15:25
Session 2: Statistical Methods and Learning
Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models George Papandreou, Alan Yuille
Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition Tianshi Gao, Daphne Koller
Decision Tree Fields Sebastian Nowozin, Carsten Rother, Shai Bagon, Bangpeng Yao, Toby Sharp, Pushmeet Kohli
15:25 - 15:55
Coffee break
15:55 - 17:20
Session 3: Detection and Categorization
Strong Supervision From Weak Annotation: Interactive Training of Deformable Part Models Steven Branson, Serge Belongie, Pietro Perona
Birdlets: Subordinate Categorization Using Volumetric Primitives and Pose-Normalized Appearance Ryan Farrell, Om Oza, Ning Zhang, Vlad Morariu, Trevor Darrell, Larry Davis
From Contours to 3D Object Detection and Pose Estimation Nadia Payet, Sinisa Todorovic
17:20 - 20:00
Poster session
Food served starting at 19:00 and rooms open until 21:00 for people to mingle.
The following posters are presented in this session. The associated spotlight presentations are distributed across oral sessions of this day, as indicated below.
Tuesday 8th November 2011
Session 1: Recognition (30 spotlights)
Poster Number
Title / Authors
1-01
Pushing the limits of digital imaging using Structured Illumination Prasanna Rangarajan, Southern Methodist University; Indranil Sinharoy, Southern Methodist University; Panos Papamichalis; Marc Christensen, Southern Methodist University
1-02
Active Clustering of Document Fragments using Information Derived from both Images and Catalogs Lior Wolf; lior Litwak, Tel-Aviv University; Nachum Dershowitz, Tel-Aviv University; Roni Shweka, FGP; Yaacov Choueka, FGP
1-03
Non-stationary Correction of Optical Aberrations Christian Schuler, MPI for Intelligent Systems; Michael Hirsch, MPI for Metals Research; Stefan Harmeling, MPI for Metals Research; Bernhard Schölkopf, MPI
1-04
Contour Code: Robust and Efficient Multispectral Palmprint Encoding for Human Recognition
Zohaib Khan, University of WesternAustralia; Ajmal Mian, University of Western Australia; Yiqun Hu, University of Western Australia
1-05
Linear stereo matching
Leonardo De-Maeztu, Universidad Pública de Navarra; Stefano Mattoccia, University of Bologna; Arantxa Villanueva, Public University of Navarre; Rafael Cabeza, Public University of Navarre
1-06
Variational Stereo in Dynamic Illumination
Yohay Swirski, Technion; Yoav Schechner, Tehnion; Tal Nir, Technion
1-07
Learning Nonlinear Distance Functions using Neural Network for Regression with Application to Robust Human Age Estimation
Fan Na, Nanjing University
1-08
Revisiting Radiometric Calibration for Color Computer Vision
Lin Haiting, NUS; Seon Joo Kim; Sabine Susstrunk, EPFL; Michael Brown
1-09
The Medial Feature Detector: Stable Regions from Image Boundaries
Yannis Avrithis, National Technical Univ Athens; Konstantinos Rapantzikos, National Technical University of Athens
1-10
A Theory of Coprime Blurred Pairs
Feng Li, University of Delaware; Zijia Li; David Saunders; Jingyi Yu
1-11
Learning to Predict the Perceived Visual Quality of Photos
Ou Wu, NLPR, Institute of Automation; Weiming Hu, Institute of Automation; Jun Gao
Sparse Dictionary-based Representation and Recognition of Action Attributes
Qiang Qiu, U. of Maryland College Park; Zhuolin Jiang, University of Maryland; Rama Chellappa, UMD
1-14
HMDB: A Large Video Database for Human Motion Recognition
Hildegard Kuehne, KIT; Hueihan Jhuang, Massachusetts Institute of Technology; Estibaliz Garrote; Tomaso Poggio; Thomas Serre, Brown University
1-15
Inferring Social Relations from Visual Concepts
Lei Ding, Columbia University; Alper Yilmaz
1-16
A FACS Valid 3D Dynamic Action Unit Database with Applications to 3D Dynamic Morphable Facial Modeling
Darren Cosker, University of Bath; Eva Krumhuber; Adrian Hilton
1-17
Maximizing All Margins: Pushing Face Recognition with Kernel Plurality
Ritwik Kumar, IBM Research; Arunava Banerjee, CISE, Univ, of Florida; Baba Vemuri; Hanspeter Pfister, Harvard University
1-18
Exemplar Extraction using Spatio-Temporal Hierarchical Agglomerative Clustering for Face Recognition in Video
John See, Multimedia University, Malaysia; Chikkannan Eswaran, Multimedia University, Malaysia
1-19
Exploring Regularized Feature Selection for Person Specific Face Verification
Yixiong Liang, Central South Univ.; Shenghui Liao; Lei Wang; Beiji Zou
1-20
A Linear Subspace Learning Approach via Sparse Coding
Lei Zhang, The Hong Kong Polytechnic University; Pengfei Zhu, The Hong Kong Polytechnic University; Qinghua Hu, Harbin Institute of Technology; David Zhang
1-21
Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints
Branislav Micusik
1-22
DTAM: Dense Tracking and Mapping in Real-Time
Richard Newcombe; Steven Lovegrove; Andrew Davison
1-23
Scale Space for Central Catadioptric Systems. Towards a Generic Camera Feature Extractor.
Luis Puig, Universidad de Zaragoza; Jose Guerrero, Universidad de Zaragoza
1-24
Kernel Non-Rigid Structure from Motion
Paulo Gotardo, The Ohio State University; Aleix Martinez
1-25
A Dimensionality Result for Multiple Homography Matrices
Wojciech Chojnacki, University of Adelaide; Anton vandenHengel
1-26
Text-Based Image Retrieval using Progressive Multi-Instance Learning
Wen Li, NTU; Lixin Duan, NTU; Dong Xu; Ivor W. Tsang
1-27
Sparse Multi-Task Regression and Feature Selection to Identify Brain Imaging Predictors for Memory Performance
Hua Wang, Univ. of Texas at Arlington; Feiping Nie, University of Texas at Arlington, Department of Computer Science and Engineering; Heng Huang, University of Texas Arlington; Shannon Risacher; Chris Ding; Andrew Saykin
1-28
Content-Based Photo Quality Assessment
Wei Luo, CUHK; Xiaogang Wang, The Chinese University of Hong Kong; Xiaoou Tang, CUHK
1-29
HEAT: Iterative Relevance Feedback with One Million Images
Nicolae Suditu, Idiap Research Institute; Francois Fleuret, Idiap Research Institute
1-30
Unsupervised Learning of a Scene-Specific Coarse Gaze Estimator
Ben Benfold, University of Oxford; Ian Reid
Tuesday 8th November 2011
Session 2: Statistical Methods and Learning (20 spotlights)
Poster Number
Title / Authors
1-31
Learning to Cluster Using High Order Graphical Models with Latent Variables
Nikos Komodakis
1-32
Diagonal preconditioning for first order primal-dual algorithms in convex optimization
Thomas Pock; Antonin Chambolle, CMAP, Ecole Polytechnique-CNRS
1-33
Tracking Multiple People under Global Appearance Constraints
Horesh Ben Shitrit, EPFL; Jerome Berclaz, EPFL; Francois Fleuret, Idiap Research Institute; Pascal Fua
1-34
Treat samples differently: Object tracking with semi-supervised online CovBoost
Guorong Li, CAS; Lei Qin; Qingming Huang, Graduate Univ of Chinese Academy of Sciences; Junbiao Pang; Shuqiang Jiang
1-35
Kinecting the dots: Particle Based Scene Flow From Depth Sensors
Simon Hadfield, University of Surrey; Richard Bowden
1-36
Graph mode-based contextual kernels for robust SVM tracking
Xi Li, University of Adelaide; Anthony Dick, The University of Adelaide; Hanzi Wang; Chunhua Shen, University of Adelaide; Anton vandenHengel
1-37
Outdoor Human Motion Capture using Inverse Kinematics and von Mises-Fisher Sampling
Gerard Pons-Moll, Leibniz University Hannover; Andreas Baak, Saarland University; Juergen Gall, ETH Zurich; Laura Leal-Taixé, Leibniz Universitaet Hannover; Meinard Mueller, Saarland University and MPI Informatik; Hans-Peter Seidel; Bodo Rosenhahn
1-38
Blurred Target Tracking by Blur-driven Tracker
Yi Wu, Temple University; Haibin Ling; Jingyi Yu; Feng Li, University of Delaware; Xue Mei; erkang Cheng
1-39
Informative Feature Selection for Object Recognition via Sparse PCA
Nikhil Naikal, UC Berkeley; Allen Yang; Shankar Sastry, UC Berkeley
1-40
Action Recognition using Rank-1 Approximation of Joint Self-Similarity Volume
Chuan Sun, UCF; Hassan Foroosh, UCF; Imran Junejo
1-41
The Truth about Cats and Dogs
Omkar Parkhi, IIIT Hyderabad; Andrea Vedaldi, Oxford; C. V. Jawahar, IIIT Hyderabad; Andrew Zisserman
1-42
The NBNN kernel
Tinne Tuytelaars, K.U.Leuven; Mario Fritz, MPI; Kate Saenko; Trevor Darrell, UC Berkeley
1-43
A New Distance for Scale-Invariant 3D Shape Recognition and Registration
Minh-Tri Pham, Toshiba Research Europe Ltd; Oliver Woodford, Toshiba Research Europe Ltd; Frank Perbet, Toshiba Research Europe Ltd; Atsuto Maki; Bjorn Stenger, Toshiba Research Europe Ltd; Roberto Cipolla, University of Cambridge
1-44
Salient Object Detection using Concavity Context
Yao Lu, Fudan University; Wei Zhang, Fudan University; Hong Lu, Fudan University; Xiangyang Xue, Fudan University
1-45
Spatial Pyramid Co-occurrence for Image Classification
Yi Yang, University of California at Merced; Shawn Newsam
1-46
Actively Selecting Annotations Among Objects and Attributes
Adriana Kovashka, University of Texas at Austin; Sudheendra Vijayanarasimhan; Kristen Grauman
1-47
Scene Recognition and Weakly Supervised Object Localization with Deformable Part-Based Models
Megha Pandey, University of North Carolina at Chapel Hill; Svetlana Lazebnik, University of North Carolina at Chapel Hill
1-48
Multi-label Visual Classification with Label Exclusive Context
Xiangyu Chen, NUS; Xiao-Tong Yuan, National University of Singapo; Qiang Chen, National University of Singapore; Shuicheng Yan; Chua Tat-Seng, National University of Singapore
1-49
CARD: Compact And Real-time Descriptors
Mitsuru Ambai, Denso IT Laboratory, Inc.; Yuichi Yoshida, Denso IT Laboratory, Inc.
1-50
BiCoS: A Bi-level Co-Segmentation Method for Image Classification
Yuning Chai, ETHZ; Victor Lempitsky; Andrew Zisserman
Tuesday 8th November 2011
Session 3: Detection and Categorization (21 spotlights)
Poster Number
Title / Authors
1-51
Convex Multi-Region Probabilistic Segmentation with Shape Prior in the Isometric Log-Ratio Transformation Space
Shawn Andrews, Simon Fraser University; Chris McIntosh, Simon Fraser University; Ghassan Hamarneh, Simon Fraser University
1-52
A General Preconditioning Scheme for Difference Measures in Deformable Registration
Darko Zikic; Maximilian Baust, "CAMP, TU Munich"; Ali Kamen; Nassir Navab, TU Munich
1-53
A 3D Laplacian-Driven Parametric Deformable Model
Tian Shen, Lehigh University; Xiaolei Huang; Hongsheng Li; Edward Kim; Shaoting Zhang, Rutgers University; Junzhou Huang, Rutgers University
1-54
Object Segmentation in Video: A Hierarchical Variational Approach for Turning Point Trajectories into Dense Regions
Peter Ochs, University Freiburg; Thomas Brox, Albert-Ludwigs-University Freiburg
1-55
Spatio-Temporal Clustering of Probabilistic Region Trajectories
Fabio Galasso, University of Cambridge; Masahiro Iwasaki, Panasonic corp.; Kunio Nobori, Panasonic; Roberto Cipolla, University of Cambridge
1-56
Generalized Background Subtraction Based on Hybrid Inference by Belief Propagation and Bayesian Filtering
Suha Kwak, POSTECH; Taegyu Lim, POSTECH; Woonhyun Nam, POSTECH; Bohyung Han, POSTECH; Joon Hee Han, POSTECH
1-57
Video from a Single Coded Exposure Photograph using a Learned Over-Complete Dictionary
Yasunobu Hitomi, Sony Corporation; Jinwei Gu, Rochester Institute of Technology; Mohit Gupta, Columbia University; Tomoo Mitsunaga, Sony Corporation; Shree Nayar, Columbia University
1-58
Unwrapping Low-rank Textures on Generalized Cylindrical Surfaces
Zhengdong Zhang, Microsoft Research Asia; Xiao Liang, Tsinghua University; Yi Ma, Microsoft Research Asia
1-59
Unstructured Light Scanning to Overcome Interreflections
Vincent Couture, Université de Montréal; Nicolas Martin, Université de Montréal; Sebastien Roy
1-60
On the repeatability of the local reference frame for partial shape matching
Alioscia Petrelli, CVLab - University of Bologna; Luigi Di Stefano, DEIS , University of Bologna
1-61
Geometrically Consistent Elastic Matching of 3D Shapes: A Linear Programming Solution
Thomas Windheuser, TU Muenchen; Ulrich Schlickewei; Frank Schmidt, University of Western Ontario; Daniel Cremers, TU Munich
1-62
Correspondence Free Registration through a Point-to-Model Distance Minimization
Mohammad Rouhani, Computer Vision Center; Angel Sappa, Computer Vision Center
1-63
Multi-class Semi-supervised SVMs with Positiveness Exclusive Regularization
Xiaobai Liu, Hust.edu.cn; nus.edu.sg; Xiao-Tong Yuan, National University of Singapo; Shuicheng Yan; Hai Jin, hust.edu.cn
1-64
Centralized Sparse Representation for Image Restoration
Weisheng Dong, Xidian University; Lei Zhang, The Hong Kong Polytechnic University; Guangming Shi
1-65
Positive Definite Dictionary Learning for Region Covariances
Ravishankar Sivalingam, University of Minnesota; Daniel Boley, University of Minnesota; Vassilios Morellas, University of Minnesota; Nikolaos Papanikolopoulos
1-66
Learning Cross-modality Similarity for Multinomial Data
Yangqing Jia, UC Berkeley; Mathieu Salzmann, TTI Chicago; Trevor Darrell, UC Berkeley
1-67
Random Ensemble Metrics for Object Recognition
Tatsuo Kozakaya, Toshiba Corporation; Satoshi Ito, Toshiba Corporation; Susumu Kubota, Toshiba Corporation
1-68
Diffusion Runs Low on Persistence Fast
Chao Chen, IST Austria; Herbert Edelsbrunner, IST Austria
1-69
Illumination Demultiplexing from a Single Image
Christine Chen, ETH Zürich; Daniel Vaquero, UC Santa Barbara; Matthew Turk, University of California, Santa Barbara
1-70
ORB: an efficient alternative to SIFT or SURF
Ethan Rublee, Willow Garage; Vincent Rabaud, willowgarage; Kurt Konolige; Gary Bradski
1-71
Temporally Coded Flash Illumination for Motion Deblurring
Scott McCloskey, Honeywell ACS Labs
Wednesday 9th November 2011
08:30 - 09:30
Invited speaker
Hiroshi Ishiguro, Osaka University
09:30 - 10:30
Session 1: Illumination and Reflectance
What An Image Reveals About Material Reflectance Manmohan Chandraker, Ravi Ramamoorthi
Multiplexed Illumination for Scene Recovery in the Presence of Global Illumination Jinwei Gu, Toshihiro Kobayashi, Mohit Gupta, Shree Nayar
10:30 - 11:00
Coffee Break
11:00 - 12:45
Session 2: Activity Recognition
Data-driven Crowd Analysis in Videos Mikel Rodriguez, Josef Sivic, Ivan Laptev, Jean-Yves Audibert
A "String of Feature Graphs" Model for Recognition of Complex Activities in Natural Videos Utkarsh Gaur, Yingying Zhu, Bi Song, Amit Roy-Chowdhury
Learning Spatiotemporal Graphs of Human Activities William Brendel, Sinisa Todorovic
Human Action Recognition by Learning Bases of Action Attributes and Parts Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas J. Guibas, Li Fei-Fei
12:45 - 14:10
Lunch
14:10 - 15:35
Session 3: Attributes and Classification
Relative Attributes Devi Parikh, Kristen Grauman
Describing People: A Poselet-Based Approach to Attribute Classification Lubomir Bourdev, Subhransu Maji, Jitendra Malik
A Joint Learning Framework for Attribute Models and Object Descriptions Dhruv Mahajan, Sundararajan Sellamanickam, Vinod Nair
15:35 - 15:55
Coffee break
15:55 - 17:20
Session 4: Segmentation and Grouping
Object Detection and Segmentation from Joint Embedding of Parts and Pixels Michael Maire, Stella Yu, Pietro Perona
Distributed Cosegmentation via Submodular Optimization on Anisotropic Diffusion Gunhee Kim, Eric Xing, Li Fei-Fei, Takeo Kanade
Discovering Favorite Views of Popular Places with Iconoid Shift Tobias Weyand, Bastian Leibe
17:20 - 20:00
Poster session
Food served starting at 19:00 and rooms open until 21:00 for people to mingle.
The following posters are presented in this session. The associated spotlight presentations are distributed across oral sessions of this day, as indicated below.
Wednesday 9th November 2011
Session 1: Illumination and Reflectance (15 spotlights)
Poster Number
Title / Authors
2-01
Active Scene Recognition with Vision and Language
Xiaodong Yu, University of Maryland; Cornelia Fermuller, University of Maryland; ChingLik Teo, University of Maryland; Yezhou Yang, University of Maryland; Yiannis Aloimonos
2-02
Handling Label Noise in Video Classification via Multiple Instance Learning
Thomas Leung; Yang Song, Google; John Zhang
2-03
Unsupervised Learning of Event AND-OR Grammar and Semantics from Video
Zhangzhang Si, UCLA; Mingtao Pei, UCLA; Benjamin Yao, UCLA; Song-Chun Zhu, UCLA
2-04
Detailed Reconstruction of 3D Plant Root Shape
Ying Zheng, Duke University; Steve Gu, Duke University; Herbert Edelsbrunner, IST Austria; Carlo Tomasi, Duke University; Philip Benfey, Duke University
2-05
Dynamic Fluid Surface Acquisition Using a Camera Array
Yuanyuan Ding; Feng Li, University of Delaware; Yu Ji, University of Delaware; Jingyi Yu
2-06
Spatiotemporal Oriented Energies for Spacetime Stereo
Mikhail Sizintsev, York University; Richard Wildes, YorkUniversity
2-07
Image Representation by Active Curves
Wenze Hu, UCLA; Ying Nian Wu, UCLA; Song-Chun Zhu, UCLA
2-08
Diffuse Reflectance Imaging with Astronomical Applications
Samuel Hasinoff; Anat Levin, Weizmann Institute of Science; Philip Goode, Big Bear Solar Observatory; Bill Freeman
2-09
Video Primal Sketch: A Generic Middle-Level Representation of Video
Zhi Han, UCLA; Zongben Xu; Song-Chun Zhu, UCLA
2-10
Gradient-based learning of higher-order image features
Roland Memisevic
2-11
Action Recognition in Videos Acquired by a Moving Camera Using Motion Decomposition of Lagrangian Particle Trajectories
Shandong Wu, University of Central Florida; Omar Oreifej; Mubarak Shah
2-12
A Chains Model for Localizing Participants of Group Activities in Videos
Mohamed Amer, Oregon State University; Sinisa Todorovic
2-13
Parsing Video Events with Goal inference and Intent Prediction
Mingtao Pei, School of Computer Science, Beijing Institute of Technology; Yunde Jia; Song-Chun Zhu, UCLA
2-14
iGroup : Weakly supervised image and video grouping
Andrew Gilbert, University of Surrey; Richard Bowden
2-15
A Selective Spatio-Temporal Interest Point Detector for Human Action Recognition in Complex Scenes
Bhaskar Chakraborty, Computer Vision Center; Michael Holte, Aalborg University; Thomas Moeslund, Aalborg University; Jordi Gonzàlez, CVC-UAB; Xavier Roca, Computer Vision Center
Wednesday 9th November 2011
Session 2: Activity Recognition (20 spotlights)
Poster Number
Title / Authors
2-16
Optimal Landmark Detection using Shape Models and Branch and Bound
Brian Amberg; Thomas Vetter, University of Basel
2-17
Face Recognition Based on Non-Corresponding Region Matching
Annan Li, Chinese Academy of Sciences; Shiguang Shan; Xilin Chen, Institute of Computing Technology, CAS; Wen Gao
2-18
Pose, Illumination and Expression Invariant Pairwise Face-Similarity Measure via Doppelgänger List Comparison
Florian Schroff; Tali Treibitz; David Kriegman; Serge Belongie, UCSD
2-19
Face Recognition via Local Sparse Coding
Ilias Theodorakopoulos, University of Patras; Ioannis Rigas, University of Patras; George Economou, University of Patras; Spiros Fotopoulos, University of Patras
2-20
Double Window Optimisation for Constant Time Visual SLAM
Hauke Strasdat, Imperial College London; Andrew Davison; JOSE MARIA MARTINEZ MONTIEL, I3A; Kurt Konolige
2-21
Optimal Estimation of Vanishing Points in a Manhattan World
Faraz Mirzaei, University of Minnesota; Stergios Roumeliotis, University of Minnesota
2-22
A robust pipeline for rapid feature-based pre-alignment of dense range scans
Francesco Bonarrigo; Alberto Signoroni, University of Brescia; Riccardo Leonardi, University of Brescia
2-23
Simultaneous Localization, Mapping and Deblurring
Hee Seok Lee, Seoul National Univ.; Junghyun Kwon; Kyoung Mu Lee
2-24
The Generalized Trace-Norm and its Application to Structure-from-Motion Problems
Roland Angst, ETH Zurich; Christopher Zach, ETH Zurich; Marc Pollefeys, ETH Zurich
2-25
Multi-View 3D Reconstruction for Scenes under the Refractive Plane with Known Vertical Direction
Yao-Jen Chang, Cornell University; Tsuhan Chen
2-26
Learning Component-Level Sparse Representation Using Histogram Information for Image Classification
Chen-Kuo Chiang, National Tsing Hua University; Chih-Hsueh Duan, National Tsing Hua University; Shang-Hong Lai, NTHU; Shih-Fu Chang, Columbia University
2-27
From Images to Scenes: Compressing an Image Cluster into a Single Scene Model for Place Recognition
Edward Johns, Imperial College London; Guang-Zhong Yang
2-28
Dyadic Transfer Learning for Cross-Domain Image Classification
Hua Wang, Univ. of Texas at Arlington; Feiping Nie, University of Texas at Arlington, Department of Computer Science and Engineering; Heng Huang, University of Texas Arlington; Chris Ding
2-29
Contextual Weighting for Vocabulary Tree based Image Retrieval
Xiaoyu Wang, University of Missouri; Ming Yang, NEC Laboratories America; Timothee Cour, NEC Laboratories America; Shenghuo Zhu, NEC Laboratories America; Kai Yu; TonyX. Han
2-30
Efficient Regression of General-Activity Human Poses from Depth Images
Ross Girshick; Jamie Shotton, Microsoft Research Cambridge; Pushmeet Kohli; Antonio Criminisi; Andrew Fitzgibbon
2-31
3D Scene Flow Estimation with a Rigid Motion Prior
Christoph Vogel, ETH Zurich; Stefan Roth; Konrad Schindler
2-32
Superpixel Tracking
Shu Wang; Huchuan Lu; Fan Yang, Dalian University of Technolog; Ming-Hsuan Yang
2-33
Basis constrained 3D scene flow on a dynamic proxy
Neil Birkbeck, University of Alberta; Martin Jagersand, University of Alberta; Dana Cobzas, University of Alberta
2-34
Similarity Invariant Classification of Events by KL Divergence Minimization
Salman Khokhar, UCF; Mubarak Shah; Imran Saleemi, University of Central Florida
2-35
Learning Occlusion with Likelihoods for Visual Tracking
Suha Kwak, POSTECH; Woonhyun Nam, POSTECH; Bohyung Han, POSTECH; Joon Hee Han, POSTECH
Wednesday 9th November 2011
Session 3: Attributes and Classification (20 spotlights)
Poster Number
Title / Authors
2-36
Blurring-Invariant Riemannian Metrics for Comparing Signals and Images
Zhengwu Zhang, Florida State University; Eric Klassen; Pavan Turaga; Rama Chellappa, UMD; Anuj Srivastava
2-37
Simultaneous Correspondence and Non-Rigid 3D Reconstruction of the Coronary Tree from Single X-ray Images
Eduard Serradell, Institut de Robotica i Informatica Industrial (CSIC-UPC); Adriana Romero, Computer Vision Center, Bellaterra, Spain; Rubem Leta, Hospital de la Santa Creu i Sant Pau, Spain; Carlo Gatta, University of Barcelona; Francesc Moreno
2-38
Incremental On-line Semi-supervised Learning for Segmenting the Left Ventricle of the Heart from Ultrasound Data
Gustavo Carneiro, The University of Adelaide; Jacinto Nascimento, Instituto Superior Tecnico
2-39
Multi-observation Visual Recognition via Joint Dynamic Sparse Representation
Haichao Zhang, UIUC, NWPU; Nasser Nasrabadi, U.S. Army Research Laboratory; Yanning Zhang, Northwestern Polytechnical University; Thomas Huang, UIUC
2-40
Articulated Part-based Model for Joint Object Detection and Pose Estimation
Min Sun; Silvio Savarese
2-41
Weakly Supervised Semantic Segmentation with Multi-Image Model
Alexander Vezhnevets, ETHZ; Vittorio Ferrari; Joachim Buhmann, ETHZ
2-42
Segmentation as Selective Search for Object Recognition
Koen Van de Sande, University of Amsterdam; Jasper Uijlings, University of Trento; Theo Gevers, University of Amsterdam; Arnold Smeulders
2-43
Extracting Foreground Masks towards Object Recognition
Amir Rosenfeld, Hebrew University of Jerusalem; Daphna Weinshall, Hebrew University
2-44
Ensemble of Exemplar-SVMs for Object Detection and Beyond
Tomasz Malisiewicz, CMU; Abhinav Gupta; Alexei Efros, CMU
2-45
Viewpoint-Aware Object Detection and Pose Estimation
Daniel Glasner, Weizmann Institute of Science; Meirav Galun, Weizmann Inst. of Science; Sharon Alpert; Ronen Basri; Gregory Shakhnarovich
2-46
Extracting Adaptive Contextual Cues from Unlabeled Regions
Congcong Li, Cornell University; Devi Parikh; Tsuhan Chen
2-47
Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition
Kihyuk Sohn, University of Michigan; Dae Jung, University of Michigan; Honglak Lee; Alfred Hero
2-48
Silhouette-based Object Phenotype Recognition using 3D Shape Priors
Yu Chen, University of Cambridge; Tae-Kyun Kim, Imperial College London; Roberto Cipolla, University of Cambridge
2-49
Video Parsing for Abnormality Detection
Borislav Antic, University of Heidelberg; Bjorn Ommer
Recursive MDL via Graph Cuts: Application to Segmentation
Lena Gorelick; Andrew Delong; Olga Veksler, UWO; Yuri Boykov, University of Western Ontario
2-52
Efficient Orthogonal Matching Pursuit using sparse random projections for scene and video classification
Shiv Vitaladevuni, Raytheon BBN Technologies; Pradeep Natarajan; Rohit Prasad; Prem Natarajan
2-53
Building large urban environments from unstructured point data
Florent Lafarge; Clément Mallet, IGN
2-54
Local Intensity Order Pattern for Feature Description
Zhenhua Wang, National Laboratory of Pattern Recognition, CASIA; Bin Fan; Fuchao Wu
2-55
Minimum Near-Convex Decomposition for Robust Shape Representation
Zhou Ren, Nanyang Technological Univ.; Junsong Yuan, Nanyang Technological University; Li Chunyuan, Huazhong Univ. of Sci. and Tech.; Liu Wenyu, Huazhong Univ. of Sci. and Tech.
Wednesday 9th November 2011
Session 4: Segmentation and Grouping (20 spotlights)
Poster Number
Title / Authors
2-56
StereoCut: Consistent Interactive Object Selection in Stereo Image Pairs
Brian Price; Scott Cohen, Adobe Systems
2-57
Are Spatial and Global Constraints Really Necessary for Segmentation?
Aurelien Lucchi, EPFL; Yunpeng Li; Xavier Boix, CVC; Kevin Smith; Pascal Fua
2-58
Segmentation from a Box
Leo Grady; Marie-Pierre Jolly, Siemens Corporate Research; Aaron Seitz, University of California - Riverside
2-59
Multi-task Low-rank Affinity Pursuit for Image Segmentation
Bin Cheng, NUS; Guangcan Liu, NUS; Jingdong Wang; Zhongyang Huang, Panasonic; Shuicheng Yan
2-60
Structure-sensitive Superpixels via Geodesic Distance
Gang Zeng; Peng Wang, Peking Univ; Jingdong Wang; Rui Gan; Hongbin Zha
2-61
Point-based Calibration Using a Parametric Representation of the General Imaging Model
Pedro Miraldo, ISR - Universidade de Coimbra; Helder Araujo; Joao Queiro, University of Coimbra
2-62
Refractive Shape from Light Field Distortion
Gordon Wetzstein; David Roodnick, University of British Columbia; Wolfgang Heidrich; Ramesh Raskar, MIT Media Lab
2-63
Self-Calibrating Depth from Refraction
Zhihu Chen, The University of HongKong; Kwan-Yee Wong , The University of HongKong; Yasuyuki Matsushita; Xiaolong Zhu, The University of Hong Kong; Miaomiao Liu, The University of HongKong
2-64
Latent Low-Rank Representation for Subspace Segmentation and Feature Extraction
Guangcan Liu, NUS; Shuicheng Yan
2-65
Correlative Multi-Label Multi-Instance Image Annotation
Xiangyang Xue, Fudan University; Wei Zhang, Fudan.edu.cn; Jie Zhang, Fudan University, China; Bin Wu, Fudan University, China; Jianping Fan, UNC-Charlotte; Yao Lu, Fudan University
2-66
Learning Equivariant Structured Output SVM regressors
Andrea Vedaldi, Oxford; Matthew Blaschko; Andrew Zisserman
2-67
Learning A Mixture of Sparse Distance Metrics for Classification and Dimensionality Reduction
Yi Hong, UCLA; Quannan Li, UCLA; jiayan Jiang, ucla; Zhuowen Tu
2-68
Learning Specific-Class Segmentation from Diverse Data
M. Pawan Kumar, Stanford University; Haithem Turki, Stanford University; Dan Preston, Stanford University; Daphne Koller, Stanford University
2-69
Tasting Families of Features for Image Classification
Charles Dubout, IDIAP; Francois Fleuret, Idiap Research Institute
2-70
Low Order Dynamics Embedding for High Dimensional Time Series
Xiong Fei, Northeastern University; Octavia Camps; Mario Sznaier, Northeastern University
2-71
A Nonparametric Riemannian Framework on Tensor Field with Application to Foreground Segmentation
Rui Caseiro, Institute Systems Robotics - University Coimbra - Portugal; João Henriques, ISR - University of Coimbra; Pedro Martins, Institute of Systems and Robotics; Jorge Batista, ISR,DEEC,FCTUC
2-72
Gaussian Process Regression Flow for Analysis of Motion Trajectories
Kihwan Kim, Georgia Institute of Technolog; Dongryeol Lee, Georgia Institute of Technology; Irfan Essa
2-73
Panoramic Stereo Video Textures
Vincent Couture, Université de Montréal; Michael Langer; Sebastien Roy
2-74
Scale and Object Aware Image Retargeting for Thumbnail Browsing
Jin Sun, Temple University; Haibin Ling
2-75
Probabilistic 3D Object Recognition with Both Positive and Negative Evidences
Sukhan Lee, SungKyunKwan University; Zhaojin Lu, SungKyunKwan University; Hyunwoo Kim, Multimedia Research Team, Daum Communication Corp.
20:00 - 22:00
PAMI-TC meeting (schedule to be confirmed)
Thursday 10th November 2011
08:30 - 09:30
Invited speaker
James DiCarlo, MIT
09:30 - 10:30
Session 1: Optimization Methods
An Adversarial Optimization Approach to Efficient Outlier Removal Jin Yu, Anders Eriksson, Tat-Jun Chin, David Suter
Generalized Ordering Constraints for Multilabel Optimization Evgeny Strekalovskiy, Daniel Cremers
10:30 - 11:00
Coffee Break
11:00 - 12:45
Session 2: Geometric Computer Vision
Generalized Subgraph Preconditioners for Large-Scale Bundle Adjustment Yong-Dian Jian, Doru Balcan, Frank Dellaert
Realtime Multibody Visual SLAM with a Smoothly Moving Monocular Camera Abhijit Kundu, Madhava Krishna, C. V. Jawahar
A Revisit to Cost Aggregation in Stereo Matching: How Far Can We Reduce Its Computational Redundancy? Dongbo Min, Jiangbo Lu, Minh Do
12:45 - 14:10
Lunch
14:10 - 15:35
Session 3: Scene Understanding
Multimodal Templates for Real-Time Detection of Texture-less Objects in Heavily Cluttered Scenes Stefan Hinterstoisser, Stefan Holzer, Cedric Cagniart, Slobodan Ilic, Kurt Konolige, Nassir Navab, Vincent Lepetit
Image Based Detection of Geometric Changes in Urban Environments Aparna Taneja, Luca Ballan, Marc Pollefeys
Manhattan Scene Understanding Using Monocular, Stereo, and 3D Features Alex Flint, David Murray, Ian Reid
15:35 - 15:55
Coffee break
15:55 - 17:20
Session 4: Image Restoration and Retargeting
From Learning Models of Natural Image Patches to Whole Image Restoration Daniel Zoran, Yair Weiss
Close the Loop: Joint Blind Image Restoration and Recognition with Sparse Representation Prior Haichao Zhang, Jianchao Yang, Yanning Zhang, Nasser Nasrabadi, Thomas Huang
Food served starting at 19:00 and rooms open until 21:00 for people to mingle.
The following posters are presented in this session. The associated spotlight presentations are distributed across oral sessions of this day, as indicated below.
Thursday 10th November 2011
Session 1: Optimization Methods (15 spotlights)
Poster Number
Title / Authors
3-01
Automatic Salient Object Extraction with Contextual Cue
Le Wang, IAIR, XJTU, China; Jianru Xue; Nanning Zheng; Gang Hua
3-02
Predicting Occupation via Human Clothing and Contexts
Zheng Song, National University of Singapo; Meng Wang, National University of Singapo; Xian-Sheng Hua; Shuicheng Yan
3-03
An Automatic Assembly and Completion Framework for Fragmented Skulls
Zhao Yin, Xiamen University; Li Wei; Mary Manhein, Department of Geography and Anthropology; Xin Li, Louisiana State University
3-04
Stereo Reconstruction using High Order Likelihood
Hoyub Jung, Seoul National University; Kyoung Mu Lee; Sang Uk Lee, Seoul National University
3-05
2D-3D Fusion for Layer Decomposition of Urban Facades
Yangyan Li, SIAT, China; Qian Zheng , SIAT, China; Andrei Sharf, Ben-Gurion University; Daniel Cohen-Or, Tel-Aviv University; Baoquan Chen, SIAT, China; Niloy Mitra, IIT Delhi
3-06
Simultaneous Multi-Body Stereo and Segmentation
Guofeng Zhang, Zhejiang University; Jiaya Jia; Hujun Bao, Zhejiang University
3-07
Center-surround Divergence of Feature Statistics for Salient Object Detection
Dominik Klein, University of Bonn; Simone Frintrop, University of Bonn
3-08
What Characterizes a Shadow Boundary under the Sun and Sky?
Xiang Huang, Northwestern University; Gang Hua; Jack Tumblin; Lance Williams
Spectral Learning of Latent Semantics for Action Recognition
Zhiwu Lu, Peking University; Yuxin Peng, Peking University; Horace Ip
3-14
Learning parameterized histogram kernels on the simplex manifold for image and action classification
Vitaly Ablavsky, Boston University; Stan Sclaroff, Boston University
3-15
Probabilistic Group-Level Motion Analysis and Scenario Recognition
Ming-Ching Chang, General Electric; Nils Krahnstoever, GE Global Research Center; Weina Ge, GE Global Research Center
Recognising Spontaneous Facial Micro-expressions
Tomas Pfister, University of Oulu; Xiaobai Li, University of Oulu; Guoying Zhao, "University of Oulu, Finland"; Matti Pietikäinen
3-18
Inferring Human Gaze from Appearance via Adaptive Linear Regression
Feng Lu, The university of tokyo; Yusuke Sugano; Takahiro Okabe; Yoichi Sato
3-19
Sparse Representation or Collaborative Representation: Which Helps Face Recognition?
Lei Zhang, The Hong Kong Polytechnic University; Meng Yang, The Hong Kong Polytechnic University; Xiangchu Feng, Xidian University
3-20
Real-time Indoor Scene Understanding using Bayesian Filtering with Motion Cues
Grace Tsai, University of Michigan; Changhai Xu, University of Texas at Austin; Jingen Liu; Benjamin Kuipers
3-21
Pose Estimation from Reflections for Specular Surface Recovery
Miaomiao Liu, The University of HongKong; Kwan-Yee Wong , The University of HongKong; Zhenwen Dai, FIAS; Zhihu Chen, The University of HongKong
3-22
Scan Rectification for Structured Light Range Sensors with Rolling Shutters
Erik Ringaby, Linkoping University; Per-Erik Forssen
3-23
Decoupling Photometry and Geometry in Dense Variational Camera Calibration
Mathieu Aubry, TU Munchen; Kalin Kolev; Bastian Goldluecke; Daniel Cremers, TU Munich
3-24
Variational Recursive Joint Estimation of Dense Scene Structure and Camera Motion from Monocular High Speed Traffic Sequences
Florian Becker, Heidelberg University; Frank Lenzen, Heidelberg University; Joerg Kappes, Heidelberg University; Christoph Schnoerr, Heidelberg University
3-25
Automated Articulated Structure and 3D Shape Recovery from Point Correspondences
Joao Fayad, Queen Mary University of London; Chris Russell; Lourdes Agapito, Queen Mary University of London
3-26
Parallelizable Inpainting and Refinement of Diffeomorphisms using Beltrami Holomorphic Flow
Tsz Wai Wong, UCLA; David Gu; Tony F. Chan, HKUST; Lok Ming Lui, The Chinese University of Hong Kong
3-27
Markov Random Field-based Fitting of a Subdivision-based Geometric Atlas
Uday Kurkure; Yen Le; Nikos Paragios; Tao Ju; James Carson; Ioannis Kakadiaris
3-28
Physically-based Motion Models for 3D Tracking: A Convex Formulation
Mathieu Salzmann, TTI Chicago; Raquel Urtasun
3-29
Modeling Temporal Coherence for Optical Flow
Sebastian Volz, Saarland University; Andres Bruhn, Saarland University; Levi Valgaerts, Saarland University; Henning Zimmer
3-30
Accurate 3D Body Pose Estimation From a Single Depth Image
Mao Ye, University of Kentucky; Xianwang Wang, Hewlett-Packard Labs; Ruigang Yang, University of Kentucky; Liu Ren; Marc Pollefeys, ETH Zurich
A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera
Andreas Baak, Saarland University; Meinard Mueller, Saarland University and MPI Informatik; Gaurav Bharaj, MPI Informatik; Hans-Peter Seidel; Christian Theobalt
3-33
Optical Flow Estimation Using Learned Sparse Model
Kui Jia, Chinese Univ. of Hong Kong; Xiaogang Wang, The Chinese University of Hong Kong; Xiaoou Tang, CUHK
3-34
Struck: Structured Output Tracking with Kernels
Sam Hare, Oxford Brookes University; Amir Saffari, Oxford Brookes University; Phil Torr
3-35
Delta-Dual Hierarchical Dirichlet Processes: A pragmatic abnormal behaviour detector
Tom Haines, Queen Mary, Uni. of London; Tao Xiang, Queen Mary University of London
Thursday 10th November 2011
Session 3: Scene Understanding (20 spotlights)
Poster Number
Title / Authors
3-36
Modeling Image Similarity by Gaussian Mixture Models and the Signature Quadratic Form Distance
Christian Beecks, RWTH Aachen University; Anca Ivanescu; Steffen Kirchhoff; Thomas Seidl, RWTH Aachen University
3-37
Efficient Similarity Search for Covariance Matrices via the Jensen-Bregman LogDet Divergence
Anoop Cherain, University of Minnesota; Suvrit Sra, Max Planck Institute for Biological Cybernetics; Arindam Banerjee, University of Minnesota, Twin Cities; Nikolaos Papanikolopoulos
3-38
Scalable Object-Class Retrieval with Approximate and Top-k Ranking
Mohammad Rastegari; Chen Fang; Lorenzo Torresani
3-39
Complementary Hashing for Approximate Nearest Neighbor Search
Hao Xu, USTC; Jingdong Wang; Zhu Li; Gang Zeng; Shipeng Li, Microsoft Research Asia; Nenghai Yu
3-40
Visual Word Disambiguation by Semantic Contexts
Yu Su, University of Caen, France; Frederic Jurie
3-41
Understanding Scenes on Many Levels
Joseph Tighe, UNC at Chapel Hill; Svetlana Lazebnik, University of North Carolina at Chapel Hill
3-42
Multiclass Transfer Learning from Unconstrained Priors
Luo Jie, Idiap Research Institute & EPFL; Tatiana Tommasi, Idiap Research Institute; Barbara Caputo
3-43
Learning a Category Independent Object Detection Cascade
Esa Rahtu, University of Oulu; Juho Kannala, University of Oulu, Finland; Matthew Blaschko
3-44
In Defense of Soft-assignment Coding
Lingqiao Liu, ANU; Lei Wang, The Australian National University; Xinwang Liu, National University of Defense Technology
3-45
Assessing the aesthetic quality of photographs using generic image descriptors
Luca Marchesotti; Florent Perronnin; Diane Larlus; Gabriela Csurka, XRCE
3-46
Evaluation of Image Features Using a Photorealistic Virtual World
Biliana Kaneva, MIT; Antonio Torralba; Bill Freeman
3-47
Modeling Spatial Layout with Fisher Vectors for Image Categorization
Josip Krapac, INRIA Grenoble; Jakob Verbeek; Frederic Jurie
3-48
Annotator Rationales for Visual Recognition
Jeff Donahue, University of Texas at Austin; Kristen Grauman
3-49
Fusing visual and range imaging for object class recognition
Aharon Bar-Hillel, GM; Dmitri Hanukaev; Dan Levi, GM
3-50
Conditional Random Fields for Multi-Camera Object Detection
Gemma Roig, EPFL; Xavier Boix, EPFL; Horesh Ben Shitrit, EPFL; Pascal Fua
3-51
Tight Convex Relaxations for Vector-Valued Labeling Problems
Evgeny Strekalovskiy, TU Munich; Bastian Goldluecke; Daniel Cremers, TU Munich
3-52
Generalized Roof Duality for Pseudo-Boolean Optimization
Fredrik Kahl; Petter Strandmark, Lund University
3-53
A Graph Cut Algorithm for Higher-order Markov Random Fields
Alexander Fix, Cornell; Aritanan Gruber, Rutgers; Endre Boros; Ramin Zabih, Cornell
3-54
Stereo Time-of-Flight
Victor Castaneda, CAMP-TUM; Diana Mateus; Nassir Navab
3-55
Dense One-shot 3D Reconstruction by Detecting Continuous Regions with Parallel Line Projection
Ryusuke Sagawa, AIST; Hiroshi Kawasaki; Ryo Furukawa, Hiroshima City University; Shota Kiyota, Kagoshima University
Thursday 10th November 2011
Session 4: Image Restoration and Retargeting (20 spotlights)
Poster Number
Title / Authors
3-56
Shared Shape Spaces
Victor Prisacariu, University of Oxford; Ian Reid
3-57
Image Segmentation by Figure-Ground Composition into Maximal Cliques
Adrian Ion, PRIP, VUT and IST Austria; João Carreira, INS, Univ. of Bonn; Cristian Sminchisescu
3-58
A Convex Framework for Image Segmentation with Moment Constraints
Maria Klodt, TU München; Daniel Cremers, TU Munich
3-59
Active Geodesics: Region-based Active Contour Segmentation with a Global Edge-based Constraint
Vikram Appia, Georgia Tech; Anthony Yezzi, Georgia Institute of Technology
3-60
Probabilistic Image Segmentation with Closedness Constraints
Bjoern Andres, University of Heidelberg; Joerg Kappes, Heidelberg University; Thorsten Beier, University of Heidelberg; Ullrich Koethe, Univ. Heidelberg; Fred Hamprecht, Univ. of Heidelberg
3-61
Face Reconstruction in the Wild
Ira Kemelmacher; Steven Seitz, University of Washington
3-62
Multiview 3D Warps
Alessio Del Bue, Istituto Italiano di Tecnologia (IIT); Adrien Bartoli, Universite d'Auvergne
3-63
Optimal Object Matching via Convexification and Composition
Hongsheng Li; Junzhou Huang, Rutgers University; Shaoting Zhang, Rutgers University; Xiaolei Huang
3-64
Viewpoint Invariant 3D Landmark Model Inference from Monocular 2D Images Using Higher-Order Priors
Chaohui Wang, Ecole Centrale Paris/INRIA; Yun Zeng; Loic Simon, ECP; Ioannis Kakadiaris, University of Houston; Dimitris Samaras; Nikos Paragios
3-65
Isotonic CCA for Sequence Alignment and Activity Recognition
Shahriar Shariat, Rutgers; Vladimir Pavlovic
3-66
The Power of Comparative Reasoning
Jay Yagnik, Google Inc; Dennis Strelow, Google Inc; David Ross, Google Inc; Ruei-sung Lin, Google Inc
3-67
Adaptive Deconvolutional Networks for Mid and High Level Feature Learning
Matthew Zeiler, New York University; Graham Taylor; Rob Fergus
3-68
Multiclass Recognition and Part Localization with Humans in the Loop
Catherine Wah, UCSD; Steven Branson; Pietro Perona; Serge Belongie, UCSD
3-69
Unsupervised and Semi-supervised Learning via L1-norm Graph
Feiping Nie, University of Texas at Arlington, Department of Computer Science and Engineering; Hua Wang, Univ. of Texas at Arlington; Heng Huang, University of Texas Arlington; Chris Ding
3-70
Building a better probabilistic model of images by factorization
Jack Culpepper, UC Berkeley; Jascha Sohl-Dickstein, UC Berkeley; Bruno Olahausen, UC Berkeley
3-71
Dynamic Manifold Warping for View Invariant Action Recognition
Dian Gong, Univ. of Southern California; Gerard Medioni
3-72
Dynamic Texture Classification Using Dynamic Fractal Analysis
Yong Xu; Yuhui Quan, South China University of Technology; Haibin Ling; Hui Ji, National University of Singapore
3-73
Simplification of 3D Morphable Models
Ankur Patel, The University of York; William Smith
Multi-hypothesis Motion Planning for Visual Object Tracking
Haifeng Gong, University of Pennsylvania; Jack Sim, University of Pennsylvania; Maxim Likhachev, Carnegie Mellon University; Jianbo Shi, University of Pennsylvania"
21:00 - 23:00
Light banquet at Llotja de Mar
Friday 11th November 2011
08:30 - 09:30
Invited speaker
Larry Matthies, JPL
09:30 - 10:30
Session 1: Matching
Fast Template Matching in Non-Linear Tone-Mapped Images Yacov Hel-Or, Hagit Hel-Or, Eyal David
Coherency Sensitive Hashing Simon Korman, Shai Avidan
10:30 - 11:00
Coffee Break
11:00 - 12:45
Session 2: Motion and Tracking
Tracking by Sampling Trackers Junseok Kwon, Kyoung Mu Lee
Full DOF Tracking of a Hand Interacting with an Object by Modeling Occlusions and Physical Constraints Iasonas Oikonomidis, Nikolaos Kyriazis, Antonis Argyros
Latent Structured Models for Human Pose Estimation Catalin Ionescu, Fuxin Li, Cristian Sminchisescu
Globally Optimal Solution to Multi-Object Tracking with Merged Measurements João Henriques, Rui Caseiro, Jorge Batista
12:45 - 14:10
Lunch
14:10 - 15:35
Session 3: Image Processing
Handling Outliers in Non-Blind Image Deconvolution Sunghyun Cho, Jue Wang, Seungyong Lee
Fast Removal of Non-uniform Camera Shake Michael Hirsch, Christian Schuler, Stefan Harmeling, Bernhard Schölkopf
Introducing Total Curvature for Image Processing Bastian Goldluecke, Daniel Cremers
15:35 - 15:55
Coffee break
15:55 - 17:20
Session 4: Faces
Fourier Active Appearance Models Rajitha Navarathna, Simon Lucey, Sridha Sridharan
Learning Universal Multi-view Age Estimator using Video Context Zheng Song, Bingbing Ni, Dong Guo, Terence Sim, Shuicheng Yan
Robust and Efficient Parametric Face Alignment Georgios Tzimiropoulos, Stefanos Zafeiriou, Maja Pantic
17:20 - 20:00
Poster session
Food served starting at 19:00 and rooms open until 21:00 for people to mingle.
The following posters are presented in this session. The associated spotlight presentations are distributed across oral sessions of this day, as indicated below.
Friday 11th November 2011
Session 1: Matching (15 spotlights)
Poster Number
Title / Authors
4-01
Home 3D Body Scans from Noisy Image and Range Data
Alex Weiss, Brown University; David Hirshberg, Brown University; Michael Black, Max-Planck Inst. Tuebingen
4-02
High Quality Depth Map Upsampling for 3D-TOF Cameras
Jaesik Park, KAIST; Hyeongwoo Kim, Korea Advanced Institute of Science and Technology; Yu-Wing Tai, KAIST; Michael Brown; In-So Kweon
4-03
Material-Specific User Colour Profiles from Imaging Spectroscopy Data
Lin Gu, Australian National University; Cong Phuoc Huynh, Australian National University; Antonio Robles-Kelly; Jun Zhou, NICTA
4-04
Dense Disparity Maps from Sparse Disparity Measurements
Simon Hawe, Lehrstuhl für Datenverarbeitun; Martin Kleinsteuber; Klaus Diepold
4-05
Aerial 3D Reconstruction with Line-Constrained Dynamic Programming
Huei-Hung Liao, USC; Yuping Lin; Gerard Medioni
4-06
Fusing Generic Objectness and Visual Saliency for Salient Object Detection
Kai-Yueh Chang, NTHU and Academia Sinica; Tyng-Luh Liu; Hwann-Tzong Chen; Shang-Hong Lai, NTHU
4-07
Cluster-Based Color Space Optimizations
Cheryl Lau, University of British Columbia; Wolfgang Heidrich; Rafal Mantiuk, Bangor University
4-08
Towards Accurate and Efficient Representation of Image Irradiance of Convex-Lambertian Objects Under Unknown Near Lighting
Shireen Elhabian, University of Louisville; Ham Rara, University of Louisville; Aly Farag, University of Louisville
4-09
Color Photometric Stereo for Multicolored Surfaces
Robert Anderson, Cambridge University; Bjorn Stenger, Toshiba Research Europe Ltd; Roberto Cipolla, University of Cambridge
4-10
BRISK: Binary Robust Invariant Scalable Keypoints
Stefan Leutenegger, ASL-ETH; Margarita Chli, ASL-ETH; Roland Siegwart, ETH-ASL
4-11
Salient Object Detection by Composition
Jie Feng, Peking University; Yichen Wei; Litian Tao, Beihang University; Chao Zhang, Peking University; Jian Sun
4-12
Action Recognition in Cluttered Dynamic Scenes using Pose-Specific Part Models
Vivek Singh, USC; Ram Nevatia
4-13
Human Activity Prediction: Early Recognition of Ongoing Activities from Streaming Videos
Michael Ryoo, ETRI
4-14
Discriminative Figure-Centric Models for Joint Action Localization and Recognition
Tian Lan, Simon Fraser University; Yang Wang, University of Illinois at Urbana-Champaign; Greg Mori
4-15
Understanding Egocentric Activities
Alireza Fathi, Georgia Institute of Tech; Ali Farhadi, UIUC; James Rehg
Friday 11th November 2011
Session 2: Motion and Tracking (19 spotlights)
Poster Number
Title / Authors
4-16
Unsupervised Metric Learning for Face Identification in TV Video
Ramazan Gokberk Cinbis, INRIA Rhone-Alpes; Jakob Verbeek; Cordelia Schmid, INRIA
4-17
Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization
Akshay Asthana, Australian National University; Tim Marks; Michael Jones; Kinh Tieu; Rohith MV, University of Delaware
4-18
Shape-constrained Gaussian Process Regression for Facial-point-based Head-pose Normalization
Ognjen Rudovic, Imperial College London; Maja Pantic
4-19
Discriminative Multi-Manifold Analysis for Face Recognition from a Single Training Sample per Person
Jiwen Lu; Yap-Peng Tan; Gang Wang
4-20
Fisher Discrimination Dictionary Learning for Sparse Representation
Meng Yang, The Hong Kong Polytechnic University; Lei Zhang, The Hong Kong Polytechnic University; Xiangchu Feng, Xidian University; David Zhang
4-21
Robust Topological Features for Deformation Invariant Image Matching
Edgar Lobaton; Ramanarayan Vasudevan, University of California; Ron Alterovitz; Ruzena Bajcsy, UC Berkeley
4-22
Optimizing Polynomial Solvers for Minimal Geometry Problems
Oleg Naroditsky, University of Pennsylvania; Kostas Daniilidis, University of Pennsylvania
4-23
3D Reconstruction of a Smooth Articulated Trajectory from a Monocular Image Sequence
Hyun Soo Park, CMU; Yaser Sheikh
4-24
Multiview Structure from Motion in Trajectory Space
Aamer Zaheer, Lahore Univ of Management Sciences; Ijaz Akhter, Lahore Univ of Management Sciences; Mohammad Haris Baig, LUMS; Shabbir Marzban, LUMS; Sohaib Khan, Lahore Univ of Mngmnt Sciences
4-25
Exploiting the Manhattan-world Assumption for Extrinsic Self-calibration of Multi-modal Sensor Networks
Marcel Brückner, University Jena; Joachim Denzler, Uni Jena
4-26
A geometric solver for calibrated stereo egomotion
Enrique Dunn, UNC; Brian Clipp, ARA; Jan-Michael Frahm
4-27
Semi-supervised Learning and Optimization for Hypergraph Matching
Marius Leordeanu; Andrei Zanfir; Cristian Sminchisescu
4-28
Efficient Algorithm for Low-rank Matrix Factorization with Missing Components and Performance Comparison of Latest Algorithms
Takayuki Okatani; Takahiro Yoshida; Koichiro Deguchi, Tohoku University
4-29
An adaptive coupled-layer visual model for robust visual tracking
Luka ?ehovin, University of Ljubljana; Matej Kristan, University of Ljubljana; Aleš Leonardis, University of Ljubljana
4-30
Hough-based Tracking of Non-Rigid Objects
Martin Godec, Graz University of Technology; Peter Roth; Horst Bischof, Graz, University of Technology
4-31
Linear Time Offline Tracking and Lower Envelope Algorithms
Steve Gu, Duke University; Ying Zheng, Duke University; Carlo Tomasi, Duke University
4-33
N-best maximal decoders for part models
Dennis Park, UC Irvine; Deva Ramanan
4-34
Fast Articulated Motion Tracking using a Sums of Gaussians Body Model
Carsten Stoll, MPI Informatik; Nils Hasler; Juergen Gall, ETH Zurich; Hans-Peter Seidel; Christian Theobalt
4-35
Robust Unsupervised Motion Pattern Inference from Video and Applications
Xuemei Zhao, USC; Gerard Medioni
Friday 11th November 2011
Session 3: Image Processing (20 spotlights)
Poster Number
Title / Authors
4-36
Smooth Object Retrieval using a Bag of Boundaries
Relja Arandjelovic, University of Oxford; Andrew Zisserman
4-37
Fast Image-Based Localization using Direct 2D-to-3D Matching
Torsten Sattler, RWTH Aachen University; Bastian Leibe; Leif Kobbelt
4-38
Large-Scale Image Annotation using Visual Synset
David Tsai, Georgia Tech; Yushi Jing, Google; Yi Liu, Google; Henry Rowley; Sergey Ioffe; James Rehg
4-39
Edge Foci Interest Points
C. Lawrence Zitnick; Krishnan Ramnath
4-40
Weakly Supervised Object Detector Learning with Model Drift Detection
Parthipan Siva, Queen Mary University of Londo; Tao Xiang, Queen Mary University of London
4-41
End-to-End Scene Text Recognition
Kai Wang; Boris Babenko; Serge Belongie, UCSD
4-42
Regression from Local Features for Viewpoint and Pose Estimation
Marwan Torki, Rutgers University; Ahmed Elgammal
4-43
Recognizing Jumbled Images: The Role of Local and Global Information in Image Classification
Devi Parikh
4-44
Robust Object Pose Estimation via Statistical Manifold Modeling
Liang Mei; Jingen Liu; Alfred Hero; Silvio Savarese
4-45
Compact Correlation Coding for Visual Object Categorization
Nobuyuki Morioka, University of New South Wales; Shin'ichi Satoh, National Institute of Informatics
4-46
Discovering Object Instances from Scenes of Daily Living
Hongwen Kang, CMU; Martial Hebert; Takeo Kanade
4-47
Density-aware person detection and tracking in crowds
Mikel Rodriguez, "INRIA, Willow Group"; Ivan Laptev; Josef Sivic, INRIA / Ecole Normale Superieure; Jean-Yves Audibert, INRIA ENS
4-48
Source Camera Identification Using Auto-White Balance Approximation
Zhonghai Deng, Univ. of Alabama,Tuscaloosa; Arjan Gijsenij, Univ. of Amsterdam; Jingyuan Zhang, Univ. of Alabama, Tuscaloosa
4-49
Tabula Rasa: Model Transfer for Object Category Detection
Yusuf Aytar, Oxford university; Andrew Zisserman
4-50
Ask the locals: multi-way local pooling for image recognition
Y-Lan Boureau; Nicolas Le Roux; francis bach; Jean Ponce, ENS Paris; Yann LeCun
4-51
Superpixels via Pseudo-Boolean Optimization
Yuhang Zhang, The Australian National Uni; Richard Hartley, The Australian National University; John Mashford, CSIRO; Stewart Burn, CSIRO
4-52
Who Blocks Who: Simultaneous Clothing Segmentation for Grouping Images
Wang Nan, Tsinghua University; Haizhou Ai, Tsinghua University
4-53
Level-Set Person Segmentation and Tracking with Multi-Region Appearance Models and Top-Down Shape Information
Esther Horbert, RWTH Aachen; Konstantinos Rematas, RWTH Aachen; Bastian Leibe
4-54
Key-Segments for Video Object Segmentation
Yong Jae Lee, University of Texas at Austin; Jaechul Kim; Kristen Grauman
4-55
Localized Principal Component Analysis based Curve Evolution: A Divide and Conquer Approach
Vikram Appia, Georgia Tech; Balaji Ganapathy, Georgia Institute of Technology; Tracy Faber, Emory University; Anthony Yezzi, Georgia Institute of Technology
Friday 11th November 2011
Session 4: Faces (19 spotlights)
Poster Number
Title / Authors
4-57
Automated Corpus Callosum Extraction via Laplace-Beltrami Nodal Parcellation and Intrinsic Geodesic Curvature Flows on Surfaces
Rongjie Lai; Yonggang Shi; Nancy Sicotte; Arthur Toga
4-58
Segmentation Fusion for Connectomics
Amelio Vazquez-Reina, Harvard University; Michael Gelbart, Harvard University; Daniel Huang, Harvard University; Jeff Lichtman, Harvard University; Eric Miller, Tufts University; Hanspeter Pfister, Harvard University
4-59
Single-Shot High Dynamic Range Imaging with Conventional Camera Hardware
Keigo Hirakawa, University of Dayton; Paul Simon, University of Dayton
4-60
Imaging via Three-dimensional Compressive Sampling (3DCS)
Xianbiao Shu, University of Illinois ; Narendra Ahuja, University of Illinois
4-61
Locally Rigid Globally Non-rigid Surface Registration
Kent Fujiwara, The University of Tokyo; Ko Nishino, Drexel University; Jun Takamatsu; Bo Zheng, The University of Tokyo; Katsushi Ikeuchi, The University of Tokyo
4-62
Multiscale, Curvature-Based Shape Representation for Surfaces
Ruirui Jiang, Stony Brook University; David Gu
4-63
Robust Consistent Correspondence Between 3D Non-Rigid Shapes Based On "Dual Shape-DNA"
Huai-Yu Wu, Peking University & NLPR, CASIA; Hongbin Zha
4-64
Discriminative High Order SVD: Adaptive Tensor Subspace Selection for Image Classification, Clustering, and Retrieval
Dijun Luo, UTA; Heng Huang, University of Texas Arlington; Chris Ding
4-65
Dynamic and Hierarchical Multi-Structure Geometric Model Fitting
Hoi Sim Wong, The University of Adelaide; Tat-Jun Chin, The University of Adelaide; Jin Yu, The University of Adelaide; David Suter
4-66
Linear Dependency Modeling for Feature Fusion
Andy J H Ma, Hong Kong Baptist University; Pong C Yuen, Hong Kong Baptist University
4-67
Unsupervised Metric Learning by Self-Smoothing Operator
Jiayan Jiang, UCLA; Bo Wang, University of Toronto; Zhuowen Tu
4-68
Slow feature analysis and decorrelation filtering for separating correlated sources
Minh Ha Quang, Italian Institute of Technolog; Laurenz Wiskott, ruhr university bochum
4-69
Integrating Local Classifiers through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation
Yutian Chen, UC Irvine; Andrew Gelfand, University of California, Irvine; Charless Fowlkes, UC Irvine; Max Welling, UC Irvine
4-70
Means in spaces of tree-like shapes
Aasa Feragen, University of Copenhagen; Søren Hauberg, University of Copenhagen; Mads Nielsen; Francois Lauze, University of Copenhagen
4-71
Sorted Random Projections for Robust Texture Classification
Li Liu, NUDT; Paul Fieguth; Gangyao Kuang; Hongbin Zha
4-72
Object Recoloring based on Intrinsic Image Estimation
Shida Beigpour, Computer Vision Center, UAB; Joost van de Weijer, Computer Vision Center Barcelona
4-73
Shading-based Dynamic Shape Refinement from Multi-view Video under General Illumination
Chenglei Wu, Max Planck Institut Informatik; Kiran Varanasi, Max Planck Institut for Informatik; Yebin Liu, Max Planck Institut for Informatik; Hans-Peter Seidel; Christian Theobalt
4-74
A Direct Least-Squares (DLS) Method for PnP
Joel Hesch, University of Minnesota; Stergios Roumeliotis, University of Minnesota
4-75
Speeded-up, relaxed spatial matching
Giorgos Tolias, National Technical University of Athens; Yannis Avrithis, National Technical Univ Athens
