The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2009)
Miami, FL, USA
June 20, 2009 to June 25, 2009
ISBN: 978-1-4244-3992-8
TABLE OF CONTENTS
Papers

Table of contents (PDF)

pp. i-xxxvi

Organizing committee (PDF)

pp. xli-xlvii

Robust multi-class transductive learning with graphs (Abstract)

Wei Liu , Electr. Eng. Dept., Columbia Univ., New York, NY, USA
Shih-Fu Chang , Electr. Eng. Dept., Columbia Univ., New York, NY, USA
pp. 381-388

Manhattan-world stereo (Abstract)

B. Curless , Dept. of Comput. Sci.&Eng., Univ. of Washington, Seattle, WA, USA
Y. Furukawa , Dept. of Comput. Sci.&Eng., Univ. of Washington, Seattle, WA, USA
S.M. Seitz , Dept. of Comput. Sci.&Eng., Univ. of Washington, Seattle, WA, USA
pp. 1422-1429

Dense 3D motion capture for human faces (Abstract)

Y. Furukawa , Univ. of Washington, Seattle, WA, USA
pp. 1674-1681

Multiplicative nonnegative greph embedding (Abstract)

Changhu Wang , MOE-MS Key Lab. of MCC, Univ. of Sci.&Technol. of China, Hefei, China
pp. 389-396

Multi-label sparse coding for automatic image annotation (Abstract)

Changhu Wang , MOE-MS Key Lab. of MCC, Univ. of Sci.&Technol. of China, Hefei, China
pp. 1643-1650

Efficient planar graph cuts with applications in Computer Vision (Abstract)

F.R. Schmidt , Comput. Sci. Dept., Univ. of Bonn, Bonn, Germany
E. Toppe , Comput. Sci. Dept., Univ. of Bonn, Bonn, Germany
D. Cremers , Comput. Sci. Dept., Univ. of Bonn, Bonn, Germany
pp. 351-356

Projective least-squares: Global solutions with local optimization (Abstract)

F. Kahl , Centre for Math. Sci., Lund Univ., Lund, Sweden
C. Olsson , Centre for Math. Sci., Lund Univ., Lund, Sweden
pp. 1216-1223

Image categorization with spatial mismatch kernels (Abstract)

H.H.S. Ip , Dept. of Comput. Sci., City Univ. of Hong Kong, Kowloon, China
Zhiwu Lu , Dept. of Comput. Sci., City Univ. of Hong Kong, Kowloon, China
pp. 397-404

Support Vector Machines in face recognition with occlusions (Abstract)

A.M. Martinez , Dept. of Electr.&Comput. Eng., Ohio State Univ., Columbus, OH, USA
Hongjun Jia , Dept. of Electr.&Comput. Eng., Ohio State Univ., Columbus, OH, USA
pp. 136-141

Markerless Motion Capture with unsynchronized moving cameras (Abstract)

B. Rosenhahn , MPI Inf., Saarbrucken, Germany
J. Gall , MPI Inf., Saarbrucken, Germany
N. Hasler , MPI Inf., Saarbrucken, Germany
H.-P. Seidel , MPI Inf., Saarbrucken, Germany
M. Wand , MPI Inf., Saarbrucken, Germany
T. Thormahlen , MPI Inf., Saarbrucken, Germany
pp. 224-231

Coupled Spectral Regression for matching heterogeneous faces (Abstract)

S.Z. Li , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Zhen Lei , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
pp. 1123-1128

Learning color and locality cues for moving object detection and segmentation (Abstract)

M. Gleicher , Dept. of Comput. Sci., Univ. of Wisconsin-Madison, Madison, WI, USA
Feng Liu , Dept. of Comput. Sci., Univ. of Wisconsin-Madison, Madison, WI, USA
pp. 320-327

Multiple instance fFeature for robust part-based object detection (Abstract)

Zhe Lin , Univ. of Maryland, College Park, MD, USA
L.S. Davis , Univ. of Maryland, College Park, MD, USA
pp. 405-412

(De) focusing on global light transport for active scene recovery (Abstract)

Yuandong Tian , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Gupta , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
S.G. Narasimhan , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 2969-2976

Contextualizing histogram (Abstract)

Shuicheng Yan , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
A. Kassim , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Bingbing Ni , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1682-1689

Recognizing human group activities with localized causalities (Abstract)

Bingbing Ni , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
A. Kassim , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Shuicheng Yan , Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1470-1477

Shape evolution for rigid and nonrigid shape registration and recovery (Abstract)

Kap Luk Chan , Sch. of Electr.&Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
Junyan Wang , Sch. of Electr.&Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
pp. 164-171

Image categorization by learning with context and consistency (Abstract)

Zhiwu Lu , Dept. of Comput. Sci., City Univ. of Hong Kong, Kowloon, China
H.H.S. Ip , Dept. of Comput. Sci., City Univ. of Hong Kong, Kowloon, China
pp. 2719-2726

Constrained clustering via spectral regularization (Abstract)

Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Zhenguo Li , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Jianzhuang Liu , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 421-428

SIFT-Rank: Ordinal description for invariant feature correspondence (Abstract)

M. Toews , Harvard Med. Sch., Brigham&Women's Hosp., MA, USA
W. Wells , Harvard Med. Sch., Brigham&Women's Hosp., MA, USA
pp. 172-177

Manifold Discriminant Analysis (Abstract)

Ruiping Wang , Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci. (CAS), Beijing, China
Xilin Chen , Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci. (CAS), Beijing, China
pp. 429-436

View-invariant dynamic texture recognition using a bag of dynamical systems (Abstract)

R. Vidal , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
R. Chaudhry , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
A. Ravichandran , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
pp. 1651-1657

ImageNet: A large-scale hierarchical image database (Abstract)

Jia Deng , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
R. Socher , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Li Fei-Fei , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Wei Dong , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Kai Li , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Li-Jia Li , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
pp. 248-255

Learning semantic visual vocabularies using diffusion distance (Abstract)

Yang Yang , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
M. Shah , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
Jingen Liu , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
pp. 461-468

Beyond pairwise energies: Efficient optimization for higher-order MRFs (Abstract)

N. Komodakis , Comput. Sci. Dept., Univ. of Crete, Heraklion, Greece
pp. 2985-2992

A nonparametric Riemannian framework for processing high angular resolution diffusion images (HARDI) (Abstract)

A. Goh , Johns Hopkins Univ., Baltimore, MD, USA
R. Vidal , Johns Hopkins Univ., Baltimore, MD, USA
pp. 2496-2503

Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval (Abstract)

S. Koknar-Tezel , Dept. of Comput.&Inf. Sci., Temple Univ., Philadelphia, PA, USA
L.J. Latecki , Dept. of Comput.&Inf. Sci., Temple Univ., Philadelphia, PA, USA
Xingwei Yang , Dept. of Comput.&Inf. Sci., Temple Univ., Philadelphia, PA, USA
pp. 357-364

3D reconstruction of curved objects from single 2D line drawings (Abstract)

Yingze Wang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Jianzhuang Liu , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 1834-1841

Non-rigid 2D-3D pose estimation and 2D image segmentation (Abstract)

A. Yezzi , Sch. of Electr.&Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
R. Sandhu , Sch. of Electr.&Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
A. Tannenbaum , Sch. of Electr.&Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
S. Dambreville , Sch. of Electr.&Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 786-793

Picking the best DAISY (Abstract)

S. Winder , Microsoft Res., Redmond, WA, USA
pp. 178-185

Learning similarity measure for multi-modal 3D image registration (Abstract)

M. Hofmann , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
B. Scholkopf , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
Daewon Lee , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
F. Steinke , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
Y. Altun , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
pp. 186-193

Volterrafaces: Discriminant analysis using Volterra kernels (Abstract)

R. Kumar , Dept. of Comput.&Inf. Sci.&Eng., Univ. of Florida, Gainesville, FL, USA
A. Banerjee , Dept. of Comput.&Inf. Sci.&Eng., Univ. of Florida, Gainesville, FL, USA
B.C. Vemuri , Dept. of Comput.&Inf. Sci.&Eng., Univ. of Florida, Gainesville, FL, USA
pp. 150-155

Echocardiogram view classification using edge filtered scale-invariant motion features (Abstract)

R. Kumar , Dept. of Comput.&Inf. Sci.&Eng., Univ. of Florida, Gainesville, FL, USA
pp. 723-730

A unified active and semi-supervised learning framework for image compression (Abstract)

Hujun Bao , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Ming Ji , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Xiaofei He , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
pp. 65-72

Multiple view image denoising (Abstract)

Li Zhang , Univ. of Wisconsin, Madison, WI, USA
S. Vaddadi , Univ. of Wisconsin, Madison, WI, USA
pp. 1542-1549

Digital face makeup by example (Abstract)

Dong Guo , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
T. Sim , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
pp. 73-79

Nonnegative Matrix Factorization with Earth Mover's Distance metric (Abstract)

M. Lindenbaum , Comput. Sci. dept., Technion - Israel Inst. of Technol., Haifa, Israel
R. Sandler , Comput. Sci. dept., Technion - Israel Inst. of Technol., Haifa, Israel
pp. 1873-1880

Learning mappings for face synthesis from near infrared to visual light images (Abstract)

Guoying Zhao , Dept. of Electr.&Inf. Eng., Univ. of Oulu, Oulu, Finland
M. Pietikainen , Dept. of Electr.&Inf. Eng., Univ. of Oulu, Oulu, Finland
Jie Chen , Dept. of Electr.&Inf. Eng., Univ. of Oulu, Oulu, Finland
pp. 156-163

A minimal parameterization of the trifocal tensor (Abstract)

K. Nordberg , Comput. Vision Lab., Linkoping Univ., Linkoping, Sweden
pp. 1224-1230

Face verification and identification using Facial Trait Code (Abstract)

Ping-Han Lee , Grad. Inst. of Comput. Sci.&Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 1613-1620

Multi-camera activity correlation analysis (Abstract)

Shaogang Gong , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
Tao Xiang , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
Chen Change Loy , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
pp. 1988-1995

Understanding images of groups of people (Abstract)

A.C. Gallagher , Carnegie Mellon Univ., Pittsburgh, PA, USA
Tsuhan Chen , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 256-263

Blind separation of superimposed images with unknown motions (Abstract)

Kun Gai , Dept. of Autom., Tsinghua Univ., Beijing, China
Changshui Zhang , Dept. of Autom., Tsinghua Univ., Beijing, China
pp. 1881-1888

Holistic context modeling using semantic co-occurrences (Abstract)

N. Rasiwasia , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
N. Vasconcelos , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
pp. 1889-1895

Topology dictionary with Markov model for 3D video content-based skimming and description (Abstract)

T. Matsuyama , Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan
T. Tung , Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan
pp. 469-476

Error propagations for local bundle adjustment (Abstract)

M. Lhuillier , LASMEA, Univ. Blaise Pascal, Aubiere, France
A. Eudes , LASMEA, Univ. Blaise Pascal, Aubiere, France
pp. 2411-2418

Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions (Abstract)

R. Chaudhry , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
R. Vidal , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
G. Hager , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
A. Ravichandran , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
pp. 1932-1939

Efficient algorithms for subwindow search in object detection and localization (Abstract)

Senjian An , Dept. of Comput., Curtin Univ. of Technol., Perth, WA, Australia
P. Peursum , Dept. of Comput., Curtin Univ. of Technol., Perth, WA, Australia
S. Venkatesh , Dept. of Comput., Curtin Univ. of Technol., Perth, WA, Australia
Wanquan Liu , Dept. of Comput., Curtin Univ. of Technol., Perth, WA, Australia
pp. 264-271

Hardware-efficient belief propagation (Abstract)

Chia-Kai Liang , Nat. Taiwan Univ., Taipei, Taiwan
Yen-Chieh Lai , Nat. Taiwan Univ., Taipei, Taiwan
H.H. Chen , Nat. Taiwan Univ., Taipei, Taiwan
Liang-Gee Chen , Nat. Taiwan Univ., Taipei, Taiwan
Chao-Chung Cheng , Nat. Taiwan Univ., Taipei, Taiwan
pp. 80-87

3D pose estimation and segmentation using specular cues (Abstract)

A. Agrawal , Mitsubishi Electr. Res. Labs. (MERL), Cambridge, MA, USA
Ju Yong Chang , Mitsubishi Electr. Res. Labs. (MERL), Cambridge, MA, USA
pp. 1706-1713

Early spatiotemporal grouping with a distributed oriented energy representation (Abstract)

R.P. Wildes , Dept. of Comput. Sci.&Eng., York Univ., Toronto, ON, Canada
K.G. Derpanis , Dept. of Comput. Sci.&Eng., York Univ., Toronto, ON, Canada
pp. 232-239

Enhanced Pictorial Structures for precise eye localization under incontrolled conditions (Abstract)

Songcan Chen , Dept. of Comput. Sci.&Eng., Nanjing Univ. of Aeronaut.&Astronaut., Nanjing, China
Xiaoyang Tan , Dept. of Comput. Sci.&Eng., Nanjing Univ. of Aeronaut.&Astronaut., Nanjing, China
Fengyi Song , Dept. of Comput. Sci.&Eng., Nanjing Univ. of Aeronaut.&Astronaut., Nanjing, China
pp. 1621-1628

Understanding and evaluating blind deconvolution algorithms (Abstract)

A. Levin , CSAIL, MIT, Cambridge, MA, USA
W.T. Freeman , CSAIL, MIT, Cambridge, MA, USA
Y. Weiss , CSAIL, MIT, Cambridge, MA, USA
F. Durand , CSAIL, MIT, Cambridge, MA, USA
pp. 1964-1971

Building text features for object image classification (Abstract)

Gang Wang , Dept. of Electr.&Comput. Eng., Univ. of Illinois Urbana-Champaign (UIUC), Urbana, IL, USA
pp. 1367-1374

Efficient multi-label classification with hypergraph regularization (Abstract)

Jianwen Zhang , Dept. of Autom., Tsinghua Univ., Beijing, China
Gang Chen , Dept. of Autom., Tsinghua Univ., Beijing, China
Changshui Zhang , Dept. of Autom., Tsinghua Univ., Beijing, China
Fei Wang , Dept. of Autom., Tsinghua Univ., Beijing, China
pp. 1658-1665

Curved glide-reflection symmetry detection (Abstract)

Yanxi Liu , Dept. of Comput. Sci.&Eng., Pennsylvania State Univ., University Park, PA, USA
Seungkyu Lee , Dept. of Comput. Sci.&Eng., Pennsylvania State Univ., University Park, PA, USA
pp. 1046-1053

Learning real-time MRF inference for image denoising (Abstract)

A. Barbu , Dept. of Stat., Florida State Univ., Tallahassee, FL, USA
pp. 1574-1581

Increased discrimination in level set methods with embedded conditional random fields (Abstract)

D. Cobzas , Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
pp. 328-335

Learning semantic scene models by object classification and trajectory clustering (Abstract)

S.Z. Li , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Tianzhu Zhang , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Hanqing Lu , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
pp. 1940-1947

Geometric and probabilistic image dissimilarity measures for common field of view detection (Abstract)

F. Bajramovic , Dept. of Comput. Vision, Friedrich Schiller Univ. of Jena, Jena, Germany
J. Denzler , Dept. of Comput. Vision, Friedrich Schiller Univ. of Jena, Jena, Germany
M. Bruckner , Dept. of Comput. Vision, Friedrich Schiller Univ. of Jena, Jena, Germany
pp. 2052-2057

Constrained marginal space learning for efficient 3D anatomical structure detection in medical images (Abstract)

B. Georgescu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
D. Comaniciu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
S.K. Zhou , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
Yefeng Zheng , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
pp. 194-201

Robust object detection using marginal space learning and ranking-based multi-detector aggregation: Application to left ventricle detection in 2D MRI images (Abstract)

Yefeng Zheng , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
Xiaoguang Lu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
B. Georgescu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
D. Comaniciu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
pp. 1343-1350

Fast concurrent object localization and recognition (Abstract)

T. Yeh , EECS, MIT, Cambridge, MA, USA
pp. 280-287

Intrinsic mean shift for clustering on Stiefel and Grassmann manifolds (Abstract)

H.E. Cetingul , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
R. Vidal , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
pp. 1896-1902

Shape-based object recognition in videos using 3D synthetic object models (Abstract)

K. Daniilidis , GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
A. Toshev , GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 288-295

LidarBoost: Depth superresolution for ToF 3D shape scanning (Abstract)

S. Thrun , Stanford Univ., Stanford, CA, USA
C. Theobalt , Stanford Univ., Stanford, CA, USA
S. Schuon , Stanford Univ., Stanford, CA, USA
pp. 343-350

Discriminatively trained particle filters for complex multi-object tracking (Abstract)

A. Fern , Sch. of EECS, Oregon State Univ., Corvallis, OR, USA
R. Hess , Sch. of EECS, Oregon State Univ., Corvallis, OR, USA
pp. 240-247

Image deblurring and denoising using color priors (Abstract)

N. Joshi , Microsoft Res., Redmond, WA, USA
R. Szeliski , Microsoft Res., Redmond, WA, USA
C.L. Zitnick , Microsoft Res., Redmond, WA, USA
pp. 1550-1557

A robust shape model for multi-view car alignment (Abstract)

Yan Li , Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Gu , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 2466-2473

Simultaneous image classification and annotation (Abstract)

D. Blei , Comput. Sci. Dept., Princeton Univ., Princeton, NJ, USA
Fei-Fei Li , Comput. Sci. Dept., Princeton Univ., Princeton, NJ, USA
Chong Wang , Comput. Sci. Dept., Princeton Univ., Princeton, NJ, USA
pp. 1903-1910

Textural Hausdorff Distance for wider-range tolerance to pose variation and misalignment in 2D face recognition (Abstract)

Sanqiang Zhao , Sch. of Eng., Griffith Univ., Brisbane, QLD, Australia
Yongsheng Gao , Sch. of Eng., Griffith Univ., Brisbane, QLD, Australia
pp. 1629-1634

]Video object segmentation by hypergraph cut (Abstract)

Qingshan Liu , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
D. Metaxas , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
Yuchi Huang , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
pp. 1738-1745

Localized content-based image retrieval through evidence region identification (Abstract)

Wu-Jun Li , Dept. of Comput. Sci.&Eng., Hong Kong Univ. of Sci.&Technol., Hong Kong, China
Dit-Yan Yeung , Dept. of Comput. Sci.&Eng., Hong Kong Univ. of Sci.&Technol., Hong Kong, China
pp. 1666-1673

Stereo matching with nonparametric smoothness priors in feature space (Abstract)

B.M. Smith , Univ. of Wisconsin-Madison, Madison, WI, USA
Li Zhang , Univ. of Wisconsin-Madison, Madison, WI, USA
pp. 485-492

Real-time learning of accurate patch rectification (Abstract)

O. Kutter , Dept. of Comput. Sci., Tech. Univ. of Munich, Garching, Germany
S. Hinterstoisser , Dept. of Comput. Sci., Tech. Univ. of Munich, Garching, Germany
N. Navab , Dept. of Comput. Sci., Tech. Univ. of Munich, Garching, Germany
pp. 2945-2952

Efficient Kernels for identifying unbounded-order spatial features (Abstract)

Tsuhan Chen , Carnegie Mellon Univ., Pittsburgh, PA, USA
Yimeng Zhang , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 1762-1769

Shape classification through structured learning of matching measures (Abstract)

M. Turk , Univ. of California, Santa Barbara, CA, USA
Longbin Chen , Univ. of California, Santa Barbara, CA, USA
pp. 365-372

Directed assistance for ink-bleed reduction in old documents (Abstract)

M.S. Brown , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
Zheng Wu , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
Zheng Lu , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
pp. 88-95

Vanishing point detection for road detection (Abstract)

J. Ponce , Ecole Normale Super., Paris, France
Hui Kong , Ecole Normale Super., Paris, France
pp. 96-103

Learning photometric invariance from diversified color model ensembles (Abstract)

A. Lopez , Comput. Vision Center&Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
J.M. Alvarez , Comput. Vision Center&Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
pp. 565-572

Implicit elastic matching with random projections for pose-variant face recognition (Abstract)

J. Wright , Electr.&Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 1502-1509

The geometry of 2D image signals (Abstract)

G. Sommer , Dept. of Comput. Sci., Kiel Univ., Kiel, Germany
O. Fleischmann , Dept. of Comput. Sci., Kiel Univ., Kiel, Germany
L. Wietzke , Dept. of Comput. Sci., Kiel Univ., Kiel, Germany
pp. 1690-1697

Modeling images as mixtures of reference images (Abstract)

F. Perronnin , Textual&Visual Pattern Anal. (TVPA), Xerox Res. Centre Eur. (XRCE), Meylan, France
Yan Liu , Textual&Visual Pattern Anal. (TVPA), Xerox Res. Centre Eur. (XRCE), Meylan, France
pp. 1770-1777

Extraction of tubular structures over an orientation domain (Abstract)

M. Pechaud , LIENS, Ecole Normale Super., Paris, France
pp. 336-342

Recognising action as clouds of space-time interest points (Abstract)

M. Bregonzio , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
Shaogang Gong , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
Tao Xiang , Sch. of Electron. Eng.&Comput. Sci., Queen Mary Univ. of London, London, UK
pp. 1948-1955

Cooperative mapping of multiple PTZ cameras in automated surveillance systems (Abstract)

Chung-Chen Chen , Dept. of Electr. Eng.&Comput. Sci., Univ. of Tennessee, Knoxville, TN, USA
A. Koschan , Dept. of Electr. Eng.&Comput. Sci., Univ. of Tennessee, Knoxville, TN, USA
A. Drira , Dept. of Electr. Eng.&Comput. Sci., Univ. of Tennessee, Knoxville, TN, USA
Yi Yao , Dept. of Electr. Eng.&Comput. Sci., Univ. of Tennessee, Knoxville, TN, USA
M. Abidi , Dept. of Electr. Eng.&Comput. Sci., Univ. of Tennessee, Knoxville, TN, USA
pp. 1078-1084

Distance transform templates for object detection and pose estimation (Abstract)

N. Navab , Dept. of Comput. Sci., Tech. Univ. of Munich (TUM), Garching, Germany
S. Holzer , Dept. of Comput. Sci., Tech. Univ. of Munich (TUM), Garching, Germany
S. Hinterstoisser , Dept. of Comput. Sci., Tech. Univ. of Munich (TUM), Garching, Germany
pp. 1177-1184

A min-max framework of cascaded classifier with multiple instance learning for computer aided diagnosis (Abstract)

K. Boyer , Rensselaer Polytech. Inst., Troy, NY, USA
Dijia Wu , Rensselaer Polytech. Inst., Troy, NY, USA
pp. 1359-1366

Isometric registration of ambiguous and partial data (Abstract)

M. Wand , Max-Planck Inst. Inf., Germany
A. Tevs , Max-Planck Inst. Inf., Germany
H.-P. Seidel , Max-Planck Inst. Inf., Germany
pp. 1185-1192

Linear solution to scale and rotation invariant object matching (Abstract)

S.X. Yu , Comput. Sci. Dept., Boston Coll., Chestnut Hill, MA, USA
Hao Jiang , Comput. Sci. Dept., Boston Coll., Chestnut Hill, MA, USA
pp. 2474-2481

Distributed multi-target tracking in a self-configuring camera network (Abstract)

A.K. Roy-Chowdhury , Dept. of Electr. Eng., Univ. of California, Riverside, CA, USA
Bi Song , Dept. of Electr. Eng., Univ. of California, Riverside, CA, USA
C. Soto , Dept. of Electr. Eng., Univ. of California, Riverside, CA, USA
pp. 1486-1493

Learning optimized MAP estimates in continuously-valued MRF models (Abstract)

K.G.G. Samuel , Sch. of Electr. Eng.&Comput. Sci., Univ. of Central Florida, Orlando, FL, USA
M.F. Tappen , Sch. of Electr. Eng.&Comput. Sci., Univ. of Central Florida, Orlando, FL, USA
pp. 477-484

Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models (Abstract)

K. Nishino , Dept. of Comput. Sci., Drexel Univ., Philadelphia, PA, USA
L. Kratz , Dept. of Comput. Sci., Drexel Univ., Philadelphia, PA, USA
pp. 1446-1453

Describing objects by their attributes (Abstract)

A. Farhadi , Comput. Sci. Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
D. Hoiem , Comput. Sci. Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
D. Forsyth , Comput. Sci. Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
I. Endres , Comput. Sci. Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 1778-1785

Visual loop closing using multi-resolution SIFT grids in metric-topological SLAM (Abstract)

G. Medioni , Univ. of Southern California, Los Angeles, CA, USA
V. Pradeep , Univ. of Southern California, Los Angeles, CA, USA
J. Weiland , Univ. of Southern California, Los Angeles, CA, USA
pp. 1438-1445

Learning mixed templates for object recognition (Abstract)

Zhangzhang Si , Dept. of Stat., UCLA, Los Angeles, CA, USA
Song-Chun Zhu , Dept. of Stat., UCLA, Los Angeles, CA, USA
Ying Nian Wu , Dept. of Stat., UCLA, Los Angeles, CA, USA
Haifeng Gong , Dept. of Stat., UCLA, Los Angeles, CA, USA
pp. 272-279

Random walks on graphs to model saliency in images (Abstract)

D. Rajan , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Yiqun Hu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
V. Gopalakrishnan , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
pp. 1698-1705

High dynamic range image reconstruction from hand-held cameras (Abstract)

Yung-Yu Chuang , Nat. Taiwan Univ., Taipei, Taiwan
Meng-Sung Wu , Nat. Taiwan Univ., Taipei, Taiwan
Tz-Huan Huang , Nat. Taiwan Univ., Taipei, Taiwan
Yi-Ting Cheng , Nat. Taiwan Univ., Taipei, Taiwan
Pei-Ying Lu , Nat. Taiwan Univ., Taipei, Taiwan
pp. 509-516

A collaborative benchmark for region of interest detection algorithms (Abstract)

Kai-Yin Cheng , Nat. Taiwan Univ., Taipei, Taiwan
Tz-Huan Huang , Nat. Taiwan Univ., Taipei, Taiwan
Yung-Yu Chuang , Nat. Taiwan Univ., Taipei, Taiwan
pp. 296-303

Learning based automatic face annotation for arbitrary poses and expressions from frontal images only (Abstract)

A. Asthana , RSISE, Australian Nat. Univ., Canberra, ACT, Australia
N. Quadrianto , RSISE, Australian Nat. Univ., Canberra, ACT, Australia
R. Goecke , RSISE, Australian Nat. Univ., Canberra, ACT, Australia
pp. 1635-1642

Automated feature extraction for early detection of diabetic retinopathy in fundus images (Abstract)

S. Ravishankar , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 210-217

Illumination and spatially varying specular reflectance from a single view (Abstract)

K. Hara , Dept. of Visual Commun. Design, Kyushu Univ., Japan
pp. 619-626

Efficient scale space auto-context for image segmentation and labeling (Abstract)

Jiayan Jiang , Dept. of Neurology, UCLA, Los Angeles, CA, USA
Zhuowen Tu , Dept. of Neurology, UCLA, Los Angeles, CA, USA
pp. 1810-1817

Adaptive Contour Features in oriented granular space for human detection and segmentation (Abstract)

Haizhou Ai , Comput. Sci.&Technol. Dept., Tsinghua Univ., Beijing, China
Wei Gao , Comput. Sci.&Technol. Dept., Tsinghua Univ., Beijing, China
pp. 1786-1793

Reconstructing sharply folding surfaces: A convex formulation (Abstract)

M. Salzmann , EECS&ICSI, UC Berkeley, Berkeley, CA, USA
pp. 1054-1061

A streaming framework for seamless building reconstruction from large-scale aerial LiDAR data (Abstract)

U. Neumann , Univ. of Southern California, Los Angeles, CA, USA
Qian-Yi Zhou , Univ. of Southern California, Los Angeles, CA, USA
pp. 2759-2766

Linear spatial pyramid matching using sparse coding for image classification (Abstract)

T. Huang , Beckman Inst., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Jianchao Yang , Beckman Inst., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 1794-1801

Capturing 3D stretchable surfaces from single images in closed form (Abstract)

F. Moreno-Noguer , Inst. de Robot. i Inf. Ind., CSIC-UPC, Barcelona, Spain
pp. 1842-1849

Pose estimation with radial distortion and unknown focal length (Abstract)

M. Byrod , Centre for Math. Sci., Lund Univ., Lund, Sweden
K. Josephson , Centre for Math. Sci., Lund Univ., Lund, Sweden
pp. 2419-2426

Relighting objects from image collections (Abstract)

T. Haber , EDM, Hasselt Univ., Belgium
P. Bekaer , EDM, Hasselt Univ., Belgium
pp. 627-634

Pictorial structures revisited: People detection and articulated pose estimation (Abstract)

B. Schiele , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
S. Roth , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
M. Andriluka , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
pp. 1014-1021

Convexity and Bayesian constrained local models (Abstract)

U. Paquet , Imense Ltd., Cambridge, UK
pp. 1193-1199

Capturing multiple illumination conditions using time and color multiplexing (Abstract)

B. De Decker , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
T. Mertens , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
P. Bekaert , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
pp. 2536-2543

Tour the world: Building a web-scale landmark recognition engine (Abstract)

Tat-Seng Chua , NUS Grad. Sch. for Integrative Sci.&Eng., Nat. Univ. of Singapore, Singapore, Singapore
Yan-Tao Zheng , NUS Grad. Sch. for Integrative Sci.&Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1085-1092

Facial deblur inference to improve recognition of blurred fFaces (Abstract)

H. Takeshima , Corp. R&D, Toshiba Corp., Japan
M. Nishiyama , Corp. R&D, Toshiba Corp., Japan
T. Kozakaya , Corp. R&D, Toshiba Corp., Japan
O. Yamaguchi , Corp. R&D, Toshiba Corp., Japan
pp. 1115-1122

Domain Transfer SVM for video concept detection (Abstract)

Dong Xu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Lixin Duan , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
I.W. Tsang , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
pp. 1375-1381

Surface feature detection and description with applications to mesh matching (Abstract)

K. Varanasi , Perception Team, INRIA Grenoble Rhone-Alpes, St. Ismier, France
A. Zaharescu , Perception Team, INRIA Grenoble Rhone-Alpes, St. Ismier, France
E. Boyer , Perception Team, INRIA Grenoble Rhone-Alpes, St. Ismier, France
R. Horaud , Perception Team, INRIA Grenoble Rhone-Alpes, St. Ismier, France
pp. 373-380

Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses (Abstract)

Junliang Xing , Comput. Sci.&Technol. Dept., Tsinghua Univ., Beijing, China
Haizhou Ai , Comput. Sci.&Technol. Dept., Tsinghua Univ., Beijing, China
pp. 1200-1207

Single-image optical center estimation from vignetting and tangential gradient symmetry (Abstract)

C. Kambhamettu , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
Yuanjie Zheng , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
pp. 2058-2065

Blind motion deblurring from a single image using sparse approximation (Abstract)

Jian-Feng Cai , Center for Wavelets, Approx.&Info. Proc., Nat. Univ. of Singapore, Singapore, Singapore
Chaoqiang Liu , Center for Wavelets, Approx.&Info. Proc., Nat. Univ. of Singapore, Singapore, Singapore
pp. 104-111

Recognizing realistic actions from videos (Abstract)

M. Shah , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
Jingen Liu , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
pp. 1996-2003

Combining powerful local and global statistics for texture description (Abstract)

Si-Bin Huang , Sch. of Comput. Sci.&Eng., South China Univ. of Tech., Guangzhou, China
Yong Xu , Sch. of Comput. Sci.&Eng., South China Univ. of Tech., Guangzhou, China
pp. 573-580

Sigma Set: A small second order statistical region descriptor (Abstract)

Wen Gao , Sch. of Comput. Sci.&Technol., Harbin Inst. of Technol., Harbin, China
Xiaopeng Hong , Sch. of Comput. Sci.&Technol., Harbin Inst. of Technol., Harbin, China
pp. 1802-1809

Minimizing sparse higher order energy functions of discrete variables (Abstract)

C. Rother , Microsoft Res., Cambridge, UK
P. Kohli , Microsoft Res., Cambridge, UK
pp. 1382-1389

Class-specific Hough forests for object detection (Abstract)

J. Gall , BIWI, ETH Zurich&MPI Inf., Zurich, Switzerland
pp. 1022-1029

Visual tracking with online Multiple Instance Learning (Abstract)

S. Belongie , Univ. of California, San Diego, CA, USA
B. Babenko , Univ. of California, San Diego, CA, USA
pp. 983-990

Predicting high resolution image edges with a generic, adaptive, 3-D vehicle model (Abstract)

J.L. Mundy , Brown Univ., Provdence, RI, USA
M.J. Leotta , Brown Univ., Provdence, RI, USA
pp. 1311-1318

Learning to associate: HybridBoosted multi-target tracker for crowded scene (Abstract)

Chang Huang , Inst. for Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
R. Nevatia , Inst. for Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
Yuan Li , Inst. for Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
pp. 2953-2960

CHoG: Compressed histogram of gradients A low bit-rate feature descriptor (Abstract)

B. Girod , Inf. Syst. Lab., Stanford Univ., Stanford, CA, USA
D. Chen , Inf. Syst. Lab., Stanford Univ., Stanford, CA, USA
S. Tsai , Inf. Syst. Lab., Stanford Univ., Stanford, CA, USA
G. Takacs , Inf. Syst. Lab., Stanford Univ., Stanford, CA, USA
V. Chandrasekhar , Inf. Syst. Lab., Stanford Univ., Stanford, CA, USA
pp. 2504-2511

Keypoint induced distance profiles for visual recognition (Abstract)

D. Suter , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
Tat-Jun Chin , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
pp. 1239-1246

A projective framework for radiometric image analysis (Abstract)

Ping Tan , Dept. of Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 2977-2984

Photometric stereo and weather estimation using internet images (Abstract)

Li Shen , Dept. of Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Ping Tan , Dept. of Electr.&Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1850-1857

Label diagnosis through self tuning forweb image search (Abstract)

Yu-Gang Jiang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Shih-Fu Chang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Jun Wang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
pp. 1390-1397

Efficiently training a better visual detector with sparse eigenvectors (Abstract)

S. Paisitkriangkrai , NICTA, Sydney, NSW, Australia
Chunhua Shen , NICTA, Sydney, NSW, Australia
Jian Zhang , NICTA, Sydney, NSW, Australia
pp. 1129-1136

Recognition using regions (Abstract)

P. Arbelaez , Univ. of California at Berkeley, Berkeley, CA, USA
J. Malik , Univ. of California at Berkeley, Berkeley, CA, USA
J.J. Lim , Univ. of California at Berkeley, Berkeley, CA, USA
Chunhui Gu , Univ. of California at Berkeley, Berkeley, CA, USA
pp. 1030-1037

Spatiotemporal stereo via spatiotemporal quadric element (stequel) matching (Abstract)

R.P. Wildes , Dept. of Comput. Sci.&Eng., York Univ., Toronto, ON, Canada
M. Sizintsev , Dept. of Comput. Sci.&Eng., York Univ., Toronto, ON, Canada
pp. 493-500

A graph-based approach to skin mole matching incorporating template-normalized coordinates (Abstract)

T.K. Lee , Med. Image Anal. Lab., Simon Fraser Univ., Burnaby, BC, Canada
H. Mirzaalian , Med. Image Anal. Lab., Simon Fraser Univ., Burnaby, BC, Canada
G. Hamarneh , Med. Image Anal. Lab., Simon Fraser Univ., Burnaby, BC, Canada
pp. 2152-2159

A multi-view probabilistic model for 3D object classes (Abstract)

Li Fei-Fei , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Hao Su , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Min Sun , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
pp. 1247-1254

Granularity-tunable gradients partition (GGP) descriptors for human detection (Abstract)

Wenchao Zhang , Sch. of Comput. Sci.&Technol., Harbin Inst. of Technol., Harbin, China
Yazhou Liu , Sch. of Comput. Sci.&Technol., Harbin Inst. of Technol., Harbin, China
pp. 1255-1262

Hierarchical spatio-temporal context modeling for action recognition (Abstract)

Ju Sun , Interactive&Digital Media Inst., Nat. Univ. of Singapore, Singapore, Singapore
pp. 2004-2011

On bias correction for geometric parameter estimation in computer vision (Abstract)

T. Okatani , Tohoku Univ., Japan
K. Deguchi , Tohoku Univ., Japan
pp. 959-966

Contextual flow (Abstract)

Ying Wu , Northwestern Univ., Evanston, IL, USA
Jialue Fan , Northwestern Univ., Evanston, IL, USA
pp. 33-40

Learning IMED via shift-invariant transformation (Abstract)

Wang Liwei , Dept. of Machine Intell., Peking Univ., Beijing, China
Feng Jufu , Dept. of Machine Intell., Peking Univ., Beijing, China
Sun Bing , Dept. of Machine Intell., Peking Univ., Beijing, China
pp. 1398-1405

Noninvasive volumetric imaging of cardiac electrophysiology (Abstract)

Pengcheng Shi , Comput. Biomedicine Lab., Rochester, NY, USA
Linwei Wang , Comput. Biomedicine Lab., Rochester, NY, USA
K.C.L. Wong , Comput. Biomedicine Lab., Rochester, NY, USA
pp. 2176-2183

Towards total scene understanding: Classification, annotation and segmentation in an automatic framework (Abstract)

R. Socher , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Li-Jia Li , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Li Fei-Fei , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
pp. 2036-2043

Regularized multi-class semi-supervised boosting (Abstract)

C. Leistner , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
A. Saffari , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
H. Bischof , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
pp. 967-974

Fast Mean Shift by compact density representation (Abstract)

D. Freedman , Hewlett-Packard Labs., Haifa, Israel
P. Kisilev , Hewlett-Packard Labs., Haifa, Israel
pp. 1818-1825

Vanishing points estimation by self-similarity (Abstract)

R. Keshet , HP-Labs. Israel, Haifa, Israel
R. Maurer , HP-Labs. Israel, Haifa, Israel
H. Kogan , HP-Labs. Israel, Haifa, Israel
pp. 755-761

Discrete tracking of parametrized curves (Abstract)

T.H. Heibel , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
M. Groher , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
B. Glocker , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
N. Navab , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
pp. 1754-1761

High-quality curvelet-based motion deblurring from an image pair (Abstract)

Jian-Feng Cai , Center for Wavelets, Approx.&Info. Proc., Nat. Univ. of Singapore, Singapore, Singapore
Chaoqiang Liu , Center for Wavelets, Approx.&Info. Proc., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1566-1573

Continuous depth estimation for multi-view stereo (Abstract)

Wenli Xu , Autom. Dept., Tsinghua Univ., Beijing, China
Qionghai Dai , Autom. Dept., Tsinghua Univ., Beijing, China
Yebin Liu , Autom. Dept., Tsinghua Univ., Beijing, China
Xun Cao , Autom. Dept., Tsinghua Univ., Beijing, China
pp. 2121-2128

Observable subspaces for 3D human motion recovery (Abstract)

P. Fua , CVLab, EPFL, China
A. Fossati , CVLab, EPFL, China
pp. 1137-1144

Curvature and singularity driven diffusion for oriented pattern enhancement with singular points (Abstract)

D. Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Lei Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Jian Bai , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Qijun Zhao , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Wenyi Huang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
pp. 2129-2135

New appearance models for natural image matting (Abstract)

D. Singaraju , Johns Hopkins Univ., Baltimore, MD, USA
pp. 659-666

Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos (Abstract)

L.S. Davis , Univ. of Maryland, College Park, MD, USA
A. Gupta , Univ. of Maryland, College Park, MD, USA
pp. 2012-2019

Stereo matching in the presence of sub-pixel calibration errors (Abstract)

H. Hirschmuller , Inst. of Robot.&Mechatron., German Aerosp. Center, Oberpfaffenhofen, Germany
pp. 437-444

Dual distributions of multilinear geometric entities (Abstract)

S.S. Brandt , Machine Vision Group, Univ. of Oulu, Oulu, Finland
pp. 2679-2686

Physics-based edge evaluation for improved color constancy (Abstract)

T. Gevers , Intell. Syst. Lab. Amsterdam, Univ. of Amsterdam, Amsterdam, Netherlands
A. Gijsenij , Intell. Syst. Lab. Amsterdam, Univ. of Amsterdam, Amsterdam, Netherlands
pp. 581-588

A unified model of specular and diffuse reflectance for rough, glossy surfaces (Abstract)

W.A.P. Smith , Dept. of Comput. Sci., Univ. of York, York, UK
E.R. Hancock , Dept. of Comput. Sci., Univ. of York, York, UK
pp. 643-650

Unsupervised feature optimization (UFO): Simultaneous selection of multiple features with their detection parameters (Abstract)

S. Ullman , Weizmann Inst. of Sci., Rehovot, Israel
M. Dinerstein , Weizmann Inst. of Sci., Rehovot, Israel
L. Karlinsky , Weizmann Inst. of Sci., Rehovot, Israel
pp. 1263-1270

Classification of tensors and fiber tracts using Mercer-kernels encoding soft probabilistic spatial and diffusion information (Abstract)

N. Paragios , Ecole Centrale Paris, Lab. MAS, Chastenay-Malabry, France
R. Neji , Ecole Centrale Paris, Lab. MAS, Chastenay-Malabry, France
pp. 2168-2175

Visual tracking via geometric particle filtering on the affine group with optimal importance functions (Abstract)

Junghyun Kwon , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 991-998

Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling (Abstract)

Junseok Kwon , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 1208-1215

A perceptually motivated online benchmark for image matting (Abstract)

C. Rhemann , Vienna Univ. of Technol., Vienna, Austria
P. Rott , Vienna Univ. of Technol., Vienna, Austria
M. Gelautz , Vienna Univ. of Technol., Vienna, Austria
pp. 1826-1833

Markov Chain Monte Carlo combined with deterministic methods for Markov random field optimization (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Wonsik Kim , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 1406-1413

A family of contextual measures of similarity between distributions with application to image retrieval (Abstract)

J.-M. Renders , Textual&Visual Pattern Anal. (TVPA), Xerox Res. Centre Eur. (XRCE), Meylan, France
Yan Liu , Textual&Visual Pattern Anal. (TVPA), Xerox Res. Centre Eur. (XRCE), Meylan, France
F. Perronnin , Textual&Visual Pattern Anal. (TVPA), Xerox Res. Centre Eur. (XRCE), Meylan, France
pp. 2358-2365

Shape of Gaussians as feature descriptors (Abstract)

Liyu Gong , Intell.&Distrib. Comput. Lab., Huazhong Univ. of Sci.&Technol., Wuhan, China
Fang Liu , Intell.&Distrib. Comput. Lab., Huazhong Univ. of Sci.&Technol., Wuhan, China
Tianjiang Wang , Intell.&Distrib. Comput. Lab., Huazhong Univ. of Sci.&Technol., Wuhan, China
pp. 2366-2371

Mutual information-based stereo matching combined with SIFT descriptor in log-chromaticity color space (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Sang Uk Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Yong Seok Heo , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 445-452

Nonparametric discriminant HMM and application to facial expression recognition (Abstract)

Kwok-Ping Chan , Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China
Lifeng Shang , Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China
pp. 2090-2096

Dimension-free affine shape matching through subspace invariance (Abstract)

Zhaozhong Wang , Image Process. Center, Beihang Univ., Beijing, China
Han Xiao , Image Process. Center, Beihang Univ., Beijing, China
pp. 2482-2487

Learning rotational features for filament detection (Abstract)

P. Fua , CVLab, EPFL, Lausanne, Switzerland
G. Gonzalez , CVLab, EPFL, Lausanne, Switzerland
F. Fleurety , CVLab, EPFL, Lausanne, Switzerland
pp. 1582-1589

Nonrigid shape recovery by Gaussian process regression (Abstract)

Jianke Zhu , ETH Zurich, Zurich, Switzerland
pp. 1319-1326

(Abstract)

J. Sivic , Lab. d'Inf., Ecole Normale Super., Paris, France
pp. 1145-1152

Appearance-based keypoint clustering (Abstract)

F.J. Estrada , Univ. of Toronto at Scarborough, Toronto, ON, Canada
pp. 1279-1286

Single image haze removal using dark channel prior (Abstract)

Kaiming He , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 1956-1963

An efficient stochastic approach to groupwise non-rigid image registration (Abstract)

D. Marshall , Sch. of Comput. Sci., Cardiff Univ., Cardiff, UK
K.A. Sidorov , Sch. of Comput. Sci., Cardiff Univ., Cardiff, UK
pp. 2208-2213

On edge detection on surfaces (Abstract)

A. Tal , Technion - Israel Inst. of Technol., Haifa, Israel
M. Kolomenkin , Technion - Israel Inst. of Technol., Haifa, Israel
pp. 2767-2774

A revisit of Generative Model for Automatic Image Annotation using Markov Random Fields (Abstract)

Xiangdong Zhou , Fudan Unviersity, Shanghai, China
Yu Xiang , Fudan Unviersity, Shanghai, China
pp. 1153-1160

Joint depth and alpha matte optimization via fusion of stereo and time-of-flight sensor (Abstract)

Ruigang Yang , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Jiejie Zhu , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Miao Liao , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
pp. 453-460

Histogram-based interest point detectors (Abstract)

Hwann-Tzong Chen , Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Wei-Ting Lee , Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 1590-1596

3D morphable face models revisited (Abstract)

W.A.P. Smith , Dept. of Comput. Sci., Univ. of York, York, UK
A. Patel , Dept. of Comput. Sci., Univ. of York, York, UK
pp. 1327-1334

Learning sign language by watching TV (using weakly aligned subtitles) (Abstract)

M. Everingham , Eng. Sci., Univ. of Oxford, Oxford, UK
P. Buehler , Eng. Sci., Univ. of Oxford, Oxford, UK
pp. 2961-2968

Multiphase geometric couplings for the segmentation of neural processes (Abstract)

E. Miller , Dept. of Comput. Sci., Tufts Univ., MA, USA
A. Vazquez-Reina , Dept. of Comput. Sci., Tufts Univ., MA, USA
pp. 2020-2027

Dense saliency-based spatiotemporal feature points for action recognition (Abstract)

Y. Avrithis , Sch. of Electr.&Comput. Eng., Nat. Tech. Univ. of Athens, Athens, Greece
K. Rapantzikos , Sch. of Electr.&Comput. Eng., Nat. Tech. Univ. of Athens, Athens, Greece
S. Kollias , Sch. of Electr.&Comput. Eng., Nat. Tech. Univ. of Athens, Athens, Greece
pp. 1454-1461

Monitoring, recognizing and discovering social networks (Abstract)

S.-N. Lim , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
Ting Yu , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
K. Patwardhan , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
N. Krahnstoever , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
pp. 1462-1469

Automatic fetal face detection from ultrasound volumes via learning 3D and 2D information (Abstract)

S.K. Zhou , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
D. Comaniciu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
Shaolei Feng , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
pp. 2488-2495

Wavelet energy map: A robust support for multi-modal registration of medical images (Abstract)

N. Navab , Computed Aided Med. Procedures, Tech. Univ. Munchen, Munich, Germany
O. Pauly , Computed Aided Med. Procedures, Tech. Univ. Munchen, Munich, Germany
N. Padoy , Computed Aided Med. Procedures, Tech. Univ. Munchen, Munich, Germany
pp. 2184-2191

Efficient representation of local geometry for large scale object retrieval (Abstract)

M. Perd'och , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
O. Chum , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
J. Matas , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
pp. 9-16

Stereographic rectification of omnidirectional stereo pairs (Abstract)

T. Pajdla , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
J. Heller , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
pp. 1414-1421

Geometric min-Hashing: Finding a (thick) needle in a haystack (Abstract)

O. Chum , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
M. Perdoch , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
J. Matas , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
pp. 17-24

An empirical study of context in object detection (Abstract)

J.H. Hays , Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hebert , Carnegie Mellon Univ., Pittsburgh, PA, USA
S.K. Divvala , Carnegie Mellon Univ., Pittsburgh, PA, USA
A.A. Efros , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 1271-1278

Shape band: A deformable object detection approach (Abstract)

Xiang Bai , Dept. of Electron.&Info. Eng., Huazhong Univ. of Sci.&Technol., Wuhan, China
Wenyu Liu , Dept. of Electron.&Info. Eng., Huazhong Univ. of Sci.&Technol., Wuhan, China
Quannan Li , Dept. of Electron.&Info. Eng., Huazhong Univ. of Sci.&Technol., Wuhan, China
pp. 1335-1342

Discriminative structure learning of hierarchical representations for object detection (Abstract)

P. Schnitzspan , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
S. Roth , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
B. Schiele , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
pp. 2238-2245

Fast human detection in crowded scenes by contour integration and local shape estimation (Abstract)

C. Beleznai , ARC, Austrian Res. Centers GmbH, Vienna, Austria
pp. 2246-2253

Continuous maximal flows and Wulff shapes: Application to MRFs (Abstract)

C. Zach , Univ. of North Carolina, Chapel Hill, NC, USA
M. Niethammer , Univ. of North Carolina, Chapel Hill, NC, USA
J.-M. Frahm , Univ. of North Carolina, Chapel Hill, NC, USA
pp. 1911-1918

A 3D reconstruction pipeline for digital preservation (Abstract)

A. Vrubel , IMAGO Res. Group, Univ. Fed. do Parana, Curitiba, Brazil
L. Silva , IMAGO Res. Group, Univ. Fed. do Parana, Curitiba, Brazil
O.R.P. Bellon , IMAGO Res. Group, Univ. Fed. do Parana, Curitiba, Brazil
pp. 2687-2694

Robust unsupervised segmentation of degraded document images with topic models (Abstract)

J.J. Corso , Comput. Sci.&Eng., SUNY at Buffalo, Buffalo, NY, USA
T.J. Burns , Comput. Sci.&Eng., SUNY at Buffalo, Buffalo, NY, USA
pp. 1287-1294

Joint and implicit registration for face recognition (Abstract)

S.J.D. Prince , Dept. of Comput. Sci., Univ. Coll. London, London, UK
Peng Li , Dept. of Comput. Sci., Univ. Coll. London, London, UK
pp. 1510-1517

Multi-class active learning for image classification (Abstract)

A.J. Joshi , Univ. of Minnesota, Minneapolis, MN, USA
N. Papanikolopoulos , Univ. of Minnesota, Minneapolis, MN, USA
pp. 2372-2379

Linear embeddings in non-rigid structure from motion (Abstract)

V. Rabaud , Dept. of Comput. Sci.&Eng., Univ. of California, San Diego, CA, USA
S. Belongie , Dept. of Comput. Sci.&Eng., Univ. of California, San Diego, CA, USA
pp. 2427-2434

Flow mosaicking: Real-time pedestrian counting without scene-specific learning (Abstract)

Yandong Tang , State Key Lab. of Robot., CAS, Shenyang, China
Yang Cong , State Key Lab. of Robot., CAS, Shenyang, China
pp. 1093-1100

Shape priors and discrete MRFs for knowledge-based segmentation (Abstract)

N. Paragios , Lab. MAS, Ecole Centrale Paris, Chatenay-Malabry, France
A. Besbes , Lab. MAS, Ecole Centrale Paris, Chatenay-Malabry, France
pp. 1295-1302

P-brush: Continuous valued MRFs with normed pairwise distributions for image segmentation (Abstract)

D. Singaraju , Johns Hopkins Univ., Baltimore, MD, USA
R. Vidal , Johns Hopkins Univ., Baltimore, MD, USA
pp. 1303-1310

Automatic facial landmark labeling with minimal supervision (Abstract)

Xiaoming Liu , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
F.W. Wheeler , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
P. Tu , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
Yan Tong , Visualization&Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
pp. 2097-2104

An empirical Bayes approach to contextual region classification (Abstract)

S. Lazebnik , Univ. of North Carolina, Chapel Hill, NC, USA
pp. 2380-2387

Super-resolution via recapture and Bayesian effect modeling (Abstract)

N. Toronto , Brigham Young Univ., Provo, UT, USA
B.S. Morse , Brigham Young Univ., Provo, UT, USA
D. Ventura , Brigham Young Univ., Provo, UT, USA
K. Seppi , Brigham Young Univ., Provo, UT, USA
pp. 2388-2395

Geometric reasoning for single image structure recovery (Abstract)

D.C. Lee , Dept. of Electr.&Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 2136-2143

Robust guidewire tracking in fluoroscopy (Abstract)

Ying Zhu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
Wei Zhang , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
S.K. Zhou , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
Peng Wang , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
D. Comaniciu , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
T. Chen , Corp. Res., Integrated Data Syst. Dept., Siemens, Princeton, NJ, USA
pp. 691-698

Object detection using a max-margin Hough transform (Abstract)

S. Maji , Comput. Sci. Div., Univ. of California at Berkeley, Berkeley, CA, USA
J. Malik , Comput. Sci. Div., Univ. of California at Berkeley, Berkeley, CA, USA
pp. 1038-1045

Similarity metrics and efficient optimization for simultaneous registration (Abstract)

C. Wachinger , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
N. Navab , Comput. Aided Med. Procedures (CAMP), Tech. Univ. Munchen, Munich, Germany
pp. 667-674

Ensemble manifold regularization (Abstract)

Chao Xu , Key Lab. of Machine Perception, Peking Univ., Beijing, China
Bo Geng , Key Lab. of Machine Perception, Peking Univ., Beijing, China
pp. 2396-2402

VideoTrek: A vision system for a tag-along robot (Abstract)

Zhiwei Zhu , Sarnoff Corp., Princeton, NJ, USA
R. Kumar , Sarnoff Corp., Princeton, NJ, USA
O. Naroditsky , Sarnoff Corp., Princeton, NJ, USA
S. Samarasekera , Sarnoff Corp., Princeton, NJ, USA
A. Das , Sarnoff Corp., Princeton, NJ, USA
T. Oskiper , Sarnoff Corp., Princeton, NJ, USA
pp. 1101-1108

Large displacement optical flow (Abstract)

T. Brox , Univ. of California, Berkeley, Berkeley, CA, USA
J. Malik , Univ. of California, Berkeley, Berkeley, CA, USA
pp. 41-48

Shape discovery from unlabeled image collections (Abstract)

Yong Jae Lee , Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
pp. 2254-2261

Structured output-associative regression (Abstract)

Liefeng Bo , Toyota Technol. Inst. at Chicago, IL, USA
pp. 2403-2410

Image deblurring for less intrusive iris capture (Abstract)

Xinyu Huang , Res.&Technol. Center, Robert Bosch, Palo Alto, CA, USA
Liu Ren , Res.&Technol. Center, Robert Bosch, Palo Alto, CA, USA
pp. 1558-1565

Average of Synthetic Exact Filters (Abstract)

B.A. Draper , Colorado State Univ., Fort Collins, CO, USA
D.S. Bolme , Colorado State Univ., Fort Collins, CO, USA
J.R. Beveridge , Colorado State Univ., Fort Collins, CO, USA
pp. 2105-2112

Efficient image alignment using linear appearance models (Abstract)

E.L. Zapata , Dept. of Comput. Archit., Univ. of Malaga, Malaga, Spain
J. Gonzalez-Mora , Dept. of Comput. Archit., Univ. of Malaga, Malaga, Spain
N. Guil , Dept. of Comput. Archit., Univ. of Malaga, Malaga, Spain
pp. 2230-2237

Tubular anisotropy for 2D vessel segmentation (Abstract)

L.D. Cohen , CEREMADE, Univ. Paris Dauphine, Paris, France
F. Benmansour , CEREMADE, Univ. Paris Dauphine, Paris, France
pp. 2286-2293

On the set of images modulo viewpoint and contrast changes (Abstract)

G. Sundaramoorthi , Univ. of California, Los Angeles, CA, USA
V.S. Varadarajan , Univ. of California, Los Angeles, CA, USA
P. Petersen , Univ. of California, Los Angeles, CA, USA
S. Soatto , Univ. of California, Los Angeles, CA, USA
pp. 832-839

What's it going to cost you?: Predicting effort vs. informativeness for multi-label image annotations (Abstract)

K. Grauman , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
S. Vijayanarasimhan , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
pp. 2262-2269

Contextual decomposition of multi-label images (Abstract)

In-So Kweon , Dept. of Electr. Eng., KAIST, Daejeon, South Korea
Teng Li , Dept. of Electr. Eng., KAIST, Daejeon, South Korea
pp. 2270-2277

From contours to regions: An empirical evaluation (Abstract)

M. Maire , Univ. of California at Berkeley, Berkeley, CA, USA
P. Arbelaez , Univ. of California at Berkeley, Berkeley, CA, USA
J. Malik , Univ. of California at Berkeley, Berkeley, CA, USA
pp. 2294-2301

Active stereo tracking of multiple free-moving targets (Abstract)

L. Perdigoto , Dept. of Electr.&Comput. Eng., Univ. of Coimbra, Coimbra, Portugal
H. Araujo , Dept. of Electr.&Comput. Eng., Univ. of Coimbra, Coimbra, Portugal
J.P. Barreto , Dept. of Electr.&Comput. Eng., Univ. of Coimbra, Coimbra, Portugal
R. Caseiro , Dept. of Electr.&Comput. Eng., Univ. of Coimbra, Coimbra, Portugal
pp. 1494-1501

Max-margin hidden conditional random fields for human action recognition (Abstract)

G. Mori , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
Yang Wang , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
pp. 872-879

Locally time-invariant models of human activities using trajectories on the grassmannian (Abstract)

R. Chellappa , Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
P. Turaga , Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
pp. 2435-2441

Discriminative subvolume search for efficient action detection (Abstract)

Ying Wu , EECS Dept., Northwestern Univ., Evanston, IL, USA
Junsong Yuan , EECS Dept., Northwestern Univ., Evanston, IL, USA
pp. 2442-2449

Rank priors for continuous non-linear dimensionality reduction (Abstract)

A. Geiger , Dept. of Meas.&Control, Karlsruhe Inst. of Technol., Karlsruhe, Germany
pp. 880-887

Angular embedding: From jarring intensity differences to perceived luminance (Abstract)

S.X. Yu , Comput. Sci. Dept., Boston Coll., Chestnut Hill, MA, USA
pp. 2302-2309

Shape constrained figure-ground segmentation and tracking (Abstract)

R.T. Collins , Dept. of Comput. Sci.&Eng., Pennsylvania State Univ., University Park, PA, USA
Zhaozheng Yin , Dept. of Comput. Sci.&Eng., Pennsylvania State Univ., University Park, PA, USA
pp. 731-738

Beyond the graphs: Semi-parametric semi-supervised discriminant analysis (Abstract)

Fei Wang , Sch. of Comput.&Inf. Sci., Florida Int. Univ., Miami, FL, USA
Xin Wang , Sch. of Comput.&Inf. Sci., Florida Int. Univ., Miami, FL, USA
Tao Li , Sch. of Comput.&Inf. Sci., Florida Int. Univ., Miami, FL, USA
pp. 2113-2120

Learning multi-modal densities on Discriminative Temporal Interaction Manifold for group activity recognition (Abstract)

Ruonan Li , Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
R. Chellappa , Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
pp. 2450-2457

Randomized structure from motion based on atomic 3D models from camera triplets (Abstract)

J. Knopp , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
M. Havlena , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
A. Torii , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
T. Pajdla , Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
pp. 2874-2881

StaRSaC: Stable random sample consensus for parameter estimation (Abstract)

Jongmoo Choi , Inst. of Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
G. Medioni , Inst. of Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
pp. 675-682

Resolution-Invariant Image Representation and its applications (Abstract)

Shenghuo Zhu , NEC Labs. America, Inc., Cupertino, CA, USA
Jinjun Wang , NEC Labs. America, Inc., Cupertino, CA, USA
Yihong Gong , NEC Labs. America, Inc., Cupertino, CA, USA
pp. 2512-2519

Vocabulary hierarchy optimization for effective and transferable retrieval (Abstract)

Rongrong Ji , Harbin Inst. of Technol., Harbin, China
Hongxun Yao , Harbin Inst. of Technol., Harbin, China
pp. 1161-1168

Unsupervised Maximum Margin Feature Selection with manifold regularization (Abstract)

Bin Zhao , Dept. of Autom., Tsinghua Univ., Beijing, China
Changshui Zhang , Dept. of Autom., Tsinghua Univ., Beijing, China
Fei Wang , Dept. of Autom., Tsinghua Univ., Beijing, China
pp. 888-895

Disambiguating the recognition of 3D objects (Abstract)

G. Guerra-Filho , Dept. of Comput. Sci.&Eng., Univ. of Texas at Arlington, Arlington, TX, USA
pp. 2278-2285

Learning a distance metric from multi-instance multi-label data (Abstract)

Rong Jin , Dept. of Comput. Sci.&Eng., Michigan State Univ., East Lansing, MI, USA
pp. 896-902

Coded exposure deblurring: Optimized codes for PSF estimation and invertibility (Abstract)

A. Agrawal , Mitsubishi Electr. Res. Labs. (MERL), Cambridge, MA, USA
Yi Xu , Mitsubishi Electr. Res. Labs. (MERL), Cambridge, MA, USA
pp. 2066-2073

Reducing JointBoost-based multiclass classification to proximity search (Abstract)

A. Stefan , Comput. Sci.&Eng. Dept., Univ. of Texas at Arlington, Arlington, TX, USA
V. Athitsos , Comput. Sci.&Eng. Dept., Univ. of Texas at Arlington, Arlington, TX, USA
pp. 589-596

Trajectory parsing by cluster sampling in spatio-temporal graph (Abstract)

Hai Jin , SCTS&CGCL, HUST, Wuhan, China
Xiaobai Liu , SCTS&CGCL, HUST, Wuhan, China
pp. 739-746

Higher-order clique reduction in binary graph cut (Abstract)

H. Ishikawa , Dept. of Inf.&Biol. Sci., Nagoya City Univ., Nagoya, Japan
pp. 2993-3000

Alphabet SOUP: A framework for approximate energy minimization (Abstract)

D. Koller , Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
S. Gould , Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
F. Amat , Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
pp. 903-910

Active learning for large multi-class problems (Abstract)

P. Jain , Univ. of Texas at Austin, Austin, TX, USA
pp. 762-769

Half-integrality based algorithms for cosegmentation of images (Abstract)

L. Mukherjee , Math.&Comput. Sci., Univ. of Wisconsin-Whitewater, Whitewater, WI, USA
pp. 2028-2035

Efficient reduction of L-infinity geometry problems (Abstract)

Hongdong Li , Res. Sch. of Inf. Sci.&Eng., Australian Nat. Univ., Canberra, ACT, Australia
pp. 2695-2702

Towards a practical face recognition system: Robust registration and illumination by sparse representation (Abstract)

Zihan Zhou , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
A. Ganesh , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
J. Wright , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Yi Ma , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
A. Wagner , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 597-604

An instance selection approach to Multiple instance Learning (Abstract)

Zhouyu Fu , Gippsland Sch. of IT, Monash Univ., Churchill, VIC, Australia
pp. 911-918

A stereo approach that handles the matting problem via image warping (Abstract)

M. Bleyer , Inst. for Software Technol.&Interactive Syst., Vienna Univ. of Technol., Vienna, Austria
C. Rhemann , Inst. for Software Technol.&Interactive Syst., Vienna Univ. of Technol., Vienna, Austria
M. Gelautz , Inst. for Software Technol.&Interactive Syst., Vienna Univ. of Technol., Vienna, Austria
pp. 501-508

A compressive sensing approach for expression-invariant face recognition (Abstract)

Baoxin Li , Dept. of Comput. Sci.&Eng., Arizona State Univ., Tempe, AZ, USA
P. Nagesh , Dept. of Comput. Sci.&Eng., Arizona State Univ., Tempe, AZ, USA
pp. 1518-1525

A projector-based movable hand-held display system (Abstract)

Kin Hong Wong , Dept. of Comput. Sci.&Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Man Chuen Leung , Dept. of Comput. Sci.&Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 1109-1114

Maximizing intra-individual correlations for face recognition across pose differences (Abstract)

Shiguang Shan , Key Lab. of Intell. Inf. Process. of CAS, CAS, Beijing, China
Annan Li , Key Lab. of Intell. Inf. Process. of CAS, CAS, Beijing, China
Xilin Chen , Key Lab. of Intell. Inf. Process. of CAS, CAS, Beijing, China
pp. 605-611

Learning visual flows: A Lie algebraic approach (Abstract)

E. Grimson , CSAIL, MIT, Cambridge, MA, USA
J. Fisher , CSAIL, MIT, Cambridge, MA, USA
Dahua Lin , CSAIL, MIT, Cambridge, MA, USA
pp. 747-754

Memory-based Particle Filter for face pose tracking robust under complex dynamics (Abstract)

J. Yamato , NTT Commun. Sci. Labs., Atsugi, Japan
K. Otsuka , NTT Commun. Sci. Labs., Atsugi, Japan
D. Mikami , NTT Commun. Sci. Labs., Atsugi, Japan
pp. 999-1006

Towards geographical referencing of monocular SLAM reconstruction using 3D city models: Application to real-time accurate vision-based localization (Abstract)

F. Dekeyser , LIST, CEA, Gif-sur-Yvette, France
P. Lothe , LIST, CEA, Gif-sur-Yvette, France
S. Bourgeois , LIST, CEA, Gif-sur-Yvette, France
pp. 2882-2889

What is the spatial extent of an object? (Abstract)

A.W.M. Smeulders , Intell. Syst. Lab., Univ. of Amsterdam, Amsterdam, Netherlands
J.R.R. Uijlings , Intell. Syst. Lab., Univ. of Amsterdam, Amsterdam, Netherlands
pp. 770-777

Trajectory reconstruction for affine structure-from-motion by global and local constraints (Abstract)

H. Ackermann , Leibniz Univ. Hannover, Hannover, Germany
B. Rosenhahn , Leibniz Univ. Hannover, Hannover, Germany
pp. 2890-2897

Robust shadow and illumination estimation using a mixture model (Abstract)

A. Panagopoulos , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
D. Samaras , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
pp. 651-658

Adaptive image and video retargeting technique based on Fourier analysis (Abstract)

Jin-Hwan Kim , Sch. of Electr. Eng., Korea Univ., Seoul, South Korea
Jun-Seong Kim , Sch. of Electr. Eng., Korea Univ., Seoul, South Korea
Chang-Su Kim , Sch. of Electr. Eng., Korea Univ., Seoul, South Korea
pp. 1730-1737

Learning from ambiguously labeled images (Abstract)

C. Jordan , Univ. of Pennsylvania, Philadelphia, PA, USA
B. Taskar , Univ. of Pennsylvania, Philadelphia, PA, USA
B. Sapp , Univ. of Pennsylvania, Philadelphia, PA, USA
T. Cour , Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 919-926

What is a camera? (Abstract)

J. Ponce , Ecole Normale Super., Paris, France
pp. 1526-1533

Moving cast shadow detection using physics-based features (Abstract)

Chu-Song Chen , Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
Jia-Bin Huang , Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
pp. 2310-2317

Image hallucination with feature enhancement (Abstract)

Zhiwei Xiong , Univ. of Sci.&Technol. of China, Hefei, China
pp. 2074-2081

Pedestrian detection: A benchmark (Abstract)

P. Perona , Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
P. Dollar , Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
pp. 304-311

Epitomized priors for multi-labeling problems (Abstract)

A.P. Moore , Univ. Coll. London, London, UK
J. Warrell , Univ. Coll. London, London, UK
S.J.D. Prince , Univ. Coll. London, London, UK
pp. 2812-2819

Pose estimation for category specific multiview object localization (Abstract)

M. Ozuysal , Comput. Vision Lab., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
V. Lepetit , Comput. Vision Lab., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
P. Fua , Comput. Vision Lab., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
pp. 778-785

Learning to track with multiple observers (Abstract)

B. Stenger , Comput. Vision Group, Toshiba Res. Eur., UK
pp. 2647-2654

Symmetric two dimensional linear discriminant analysis (2DLDA) (Abstract)

Heng Huang , Univ. of Texas at Arlington, Arlington, TX, USA
Dijun Luo , Univ. of Texas at Arlington, Arlington, TX, USA
C. Ding , Univ. of Texas at Arlington, Arlington, TX, USA
pp. 2820-2827

Recognizing linked events: Searching the space of feasible explanations (Abstract)

D. Damen , Sch. of Comput., Univ. of Leeds, Leeds, UK
D. Hogg , Sch. of Comput., Univ. of Leeds, Leeds, UK
pp. 927-934

Nonrigid registration combining global and local statistics (Abstract)

Zhao Yi , Univ. of California, Los Angeles, CA, USA
S. Soatto , Univ. of California, Los Angeles, CA, USA
pp. 2200-2207

Multi-cue onboard pedestrian detection (Abstract)

C. Wojek , Comput. Sci. Dept., Tech. Univ. Darmstadt, Darmstadt, Germany
S. Walk , Comput. Sci. Dept., Tech. Univ. Darmstadt, Darmstadt, Germany
B. Schiele , Comput. Sci. Dept., Tech. Univ. Darmstadt, Darmstadt, Germany
pp. 794-801

HOP: Hierarchical object parsing (Abstract)

I. Kokkinos , Lab. MAS, INRIA Saclay, Orsay, France
pp. 802-809

Robustifying eye center localization by head pose cues (Abstract)

R. Valenti , Intell. Syst. Lab., Univ. of Amsterdam, Amsterdam, Netherlands
T. Gevers , Intell. Syst. Lab., Univ. of Amsterdam, Amsterdam, Netherlands
Z. Yucel , Intell. Syst. Lab., Univ. of Amsterdam, Amsterdam, Netherlands
pp. 612-618

Abnormal crowd behavior detection using social force model (Abstract)

R. Mehran , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
M. Shah , Comput. Vision Lab., Univ. of Central Florida, Orlando, FL, USA
pp. 935-942

Fast car detection using image strip features (Abstract)

Luhong Liang , Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci. (CAS), Beijing, China
Wei Zheng , Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci. (CAS), Beijing, China
pp. 2703-2710

Recognition of repetitive sequential human activity (Abstract)

S. Pankanti , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
R. Bobbitt , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
A. Yanagawa , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
Q. Fan , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
A. Hampapur , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
Yun Zhai , T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
pp. 943-950

Color estimation from a single surface color (Abstract)

K. Ikeuchi , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
R. Kawakami , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
pp. 635-642

Cancelable iris biometrics and using Error Correcting Codes to reduce variability in biometric data (Abstract)

B. Dorizzi , Dept. of Electron.&Phys., Inst. TELECOM: TELECOM&Manage. SudParis, Evry, France
S. Kanade , Dept. of Electron.&Phys., Inst. TELECOM: TELECOM&Manage. SudParis, Evry, France
D. Petrovska-Delacretaz , Dept. of Electron.&Phys., Inst. TELECOM: TELECOM&Manage. SudParis, Evry, France
pp. 120-127

Learning signs from subtitles: A weakly supervised approach to sign language recognition (Abstract)

H. Cooper , CVSSP, Univ. Of Surrey, Guildford, UK
R. Bowden , CVSSP, Univ. Of Surrey, Guildford, UK
pp. 2568-2574

Continuous ratio optimization via convex relaxation with applications to multiview 3D reconstruction (Abstract)

D. Cremers , Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany
K. Kolev , Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany
pp. 1858-1864

On the burstiness of visual elements (Abstract)

H. Jegou , LJK, INRIA Grenoble, Grenoble, France
C. Schmid , LJK, INRIA Grenoble, Grenoble, France
M. Douze , LJK, INRIA Grenoble, Grenoble, France
pp. 1169-1176

Depth from sliding projections (Abstract)

Y. Francken , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
C. Hermans , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
T. Cuypers , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
P. Bekaert , Expertise Centre for Digital Media, Hasselt Univ., Hasselt, Belgium
pp. 1865-1872

Fast multiple shape correspondence by pre-organizing shape instances (Abstract)

A. Temlyakov , Dept. of Comput. Sci.&Eng., Univ. of South Carolina, Columbia, SC, USA
B.C. Munsell , Dept. of Comput. Sci.&Eng., Univ. of South Carolina, Columbia, SC, USA
Song Wang , Dept. of Comput. Sci.&Eng., Univ. of South Carolina, Columbia, SC, USA
pp. 840-847

Learning partially-observed hidden conditional random fields for facial expression recognition (Abstract)

Tyng-Luh Liu , Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
Kai-Yueh Chang , Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
pp. 533-540

Expression-insensitive 3D face recognition using sparse representation (Abstract)

Xiaoxing Li , Electr.&Comput. Eng., Virginia Tech, Blacksburg, VA, USA
Tao Jia , Electr.&Comput. Eng., Virginia Tech, Blacksburg, VA, USA
pp. 2575-2582

A projector-camera setup for geometry-invariant frequency demultiplexing (Abstract)

D.A. Vaquero , UC, Santa Barbara, CA, USA
M. Turk , UC, Santa Barbara, CA, USA
pp. 2082-2089

Compensation of motion artifacts in MRI via graph-based optimization (Abstract)

Tung-Ying Lee , Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Hong-Ren Su , Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Shang-Hong Lai , Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 2192-2199

Classifier grids for robust adaptive object detection (Abstract)

H. Bischof , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
S. Sternig , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
P.M. Roth , Inst. for Comput. Graphics&Vision, Graz Univ. of Technol., Graz, Austria
pp. 2727-2734

Towards high-resolution large-scale multi-view stereo (Abstract)

P. Labatut , IMAGINE, Univ. Paris-Est, Paris, France
J.-P. Pons , IMAGINE, Univ. Paris-Est, Paris, France
R. Keriven , IMAGINE, Univ. Paris-Est, Paris, France
V.H. Hiep , IMAGINE, Univ. Paris-Est, Paris, France
pp. 1430-1437

Planar orientation from blur gradients in a single image (Abstract)

S. McCloskey , Honeywell Labs., Golden Valley, MN, USA
pp. 2318-2325

A tensor-based algorithm for high-order graph matching (Abstract)

F. Bach , Ecole Normale Super. de Paris, Paris, France
O. Duchenne , Ecole Normale Super. de Paris, Paris, France
J. Ponce , Ecole Normale Super. de Paris, Paris, France
pp. 1980-1987

In defense of orthonormality constraints for nonrigid structure from motion (Abstract)

S. Khan , Sch. of Sci.&Eng., LUMS, Lahore, Pakistan
I. Akhter , Sch. of Sci.&Eng., LUMS, Lahore, Pakistan
pp. 1534-1541

Marked point processes for crowd counting (Abstract)

R.T. Collins , Pennsylvania State Univ., University Park, PA, USA
W. Ge , Pennsylvania State Univ., University Park, PA, USA
pp. 2913-2920

Catadioptric projectors (Abstract)

Jingyi Yu , Univ. of Delaware, Newark, DE, USA
Yuanyuan Ding , Univ. of Delaware, Newark, DE, USA
pp. 2528-2535

Fuzzy-Cuts: A knowledge-driven graph-based method for medical image segmentation (Abstract)

D.R. Chittajallu , Dept. of Comput. Sci., Elec.&Comp. Eng., Univ. of Houston, Houston, TX, USA
G. Brunner , Dept. of Comput. Sci., Elec.&Comp. Eng., Univ. of Houston, Houston, TX, USA
R.P. Yalamanchili , Dept. of Comput. Sci., Elec.&Comp. Eng., Univ. of Houston, Houston, TX, USA
U. Kurkure , Dept. of Comput. Sci., Elec.&Comp. Eng., Univ. of Houston, Houston, TX, USA
I.A. Kakadiaris , Dept. of Comput. Sci., Elec.&Comp. Eng., Univ. of Houston, Houston, TX, USA
pp. 715-722

Recovering specular surfaces using curved line images (Abstract)

Jingyi Yu , Dept. of Comput.&Inf. Sci., Univ. of Delaware, Newark, DE, USA
Yuanyuan Ding , Dept. of Comput.&Inf. Sci., Univ. of Delaware, Newark, DE, USA
pp. 2326-2333

Removing partial blur in a single image (Abstract)

Shengyang Dai , EECS Dept., Northwestern Univ., Evanston, IL, USA
Ying Wu , EECS Dept., Northwestern Univ., Evanston, IL, USA
pp. 2544-2551

Human motion synthesis from 3D video (Abstract)

Peng Huang , Centre for Vision Speech&Signal Processsing, Univ. of Surrey, Guildford, UK
J. Starck , Centre for Vision Speech&Signal Processsing, Univ. of Surrey, Guildford, UK
A. Hilton , Centre for Vision Speech&Signal Processsing, Univ. of Surrey, Guildford, UK
pp. 1478-1485

From structure-from-motion point clouds to fast location recognition (Abstract)

A. Irschara , Graz Univ. of Technol., Graz, Austria
H. Bischof , Graz Univ. of Technol., Graz, Austria
pp. 2599-2606

A multiscale hybrid model exploiting heterogeneous contextual relationships for image segmentation (Abstract)

Qiang Ji , Rensselaer Polytech. Inst., Troy, NY, USA
Lei Zhang , Rensselaer Polytech. Inst., Troy, NY, USA
pp. 2828-2835

Distributed volumetric scene geometry reconstruction with a network of distributed smart cameras (Abstract)

D.B. Cooper , Div. of Eng., Brown Univ., Providence, RI, USA
Kongbin Kang , Div. of Eng., Brown Univ., Providence, RI, USA
Shubao Liu , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 2334-2341

Contextual classification with functional Max-Margin Markov Networks (Abstract)

D. Munoz , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.A. Bagnell , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hebert , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
N. Vandapel , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 975-982

Fourier analysis and Gabor filtering for texture analysis and local reconstruction of general shapes (Abstract)

J. Lasenby , Univ. of Cambridge, Cambridge, UK
F. Galasso , Univ. of Cambridge, Cambridge, UK
pp. 2342-2349

Let the kernel figure it out; Principled learning of pre-processing for kernel classifiers (Abstract)

P.V. Gehler , Dept. of Empirical Inference, Max Planck Inst. for Biol. Cybern., Tubingen, Germany
S. Nowozin , Dept. of Empirical Inference, Max Planck Inst. for Biol. Cybern., Tubingen, Germany
pp. 2836-2843

Linear stratified approach for 3D modelling and calibration using full geometric constraints (Abstract)

Jae-Hean Kim , Electron.&Telecommun. Res. Inst. (ETRI), Daejeon, South Korea
pp. 2144-2151

Learning to detect unseen object classes by between-class attribute transfer (Abstract)

S. Harmeling , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
H. Nickisch , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
C.H. Lampert , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
pp. 951-958

Physiological face recognition is coming of age (Abstract)

P. Buddharaju , Dept. of Comput. Sci., Univ. of Houston, Houston, TX, USA
I. Pavlidis , Dept. of Comput. Sci., Univ. of Houston, Houston, TX, USA
pp. 128-135

Frequency-tuned salient region detection (Abstract)

S. Susstrunk , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
R. Achanta , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
F. Estrada , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
pp. 1597-1604

Real-time vehicle detection for highway driving (Abstract)

B. Southall , Sarnoff Corp., Princeton, NJ, USA
J. Eledath , Sarnoff Corp., Princeton, NJ, USA
M. Bansal , Sarnoff Corp., Princeton, NJ, USA
pp. 541-548

Shape comparison using perturbing shape registration (Abstract)

Yifeng Jiang , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
X. Papademetris , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
L.H. Staib , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
H.P. Blumberg , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
pp. 683-690

A robust approach for automatic registration of aerial images with untextured aerial LiDAR data (Abstract)

U. Neumann , Comput. Graphics&Immersive Technol. Lab., Univ. of Southern California, Los Angeles, CA, USA
Lu Wang , Comput. Graphics&Immersive Technol. Lab., Univ. of Southern California, Los Angeles, CA, USA
pp. 2623-2630

Contextual restoration of severely degraded document images (Abstract)

J. Banerjee , Center for Visual Inf. Technol., IIIT Hyderabad, Hyderabad, India
C.V. Jawahar , Center for Visual Inf. Technol., IIIT Hyderabad, Hyderabad, India
A.M. Namboodiri , Center for Visual Inf. Technol., IIIT Hyderabad, Hyderabad, India
pp. 517-524

Factorization for non-rigid and articulated structure using metric projections (Abstract)

L. Agapito , Queen Mary, Univ. of London, London, UK
M. Paladini , Queen Mary, Univ. of London, London, UK
pp. 2898-2905

Enforcing integrability by error correction using l<inf>1</inf>-minimization (Abstract)

R. Chellappa , Univ. of Maryland, College Park, MD, USA
D. Reddy , Univ. of Maryland, College Park, MD, USA
pp. 2350-2357

A convex relaxation approach for computing minimal partitions (Abstract)

T. Pock , Graz Univ. of Technol., Graz, Austria
H. Bischof , Graz Univ. of Technol., Graz, Austria
pp. 810-817

How far can you get with a modern face recognition test set using only simple features? (Abstract)

N. Pinto , MIT, Cambridge, MA, USA
J.J. DiCarlo , MIT, Cambridge, MA, USA
pp. 2591-2598

Bundling features for large scale partial-duplicate web image search (Abstract)

M. Isard , Microsoft Res., Redmond, WA, USA
Jian Sun , Microsoft Res., Redmond, WA, USA
Zhong Wu , Microsoft Res., Redmond, WA, USA
Qifa Ke , Microsoft Res., Redmond, WA, USA
pp. 25-32

Global connectivity potentials for random field models (Abstract)

S. Nowozin , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
C.H. Lampert , Max Planck Inst. for Biol. Cybern., Tubingen, Germany
pp. 818-825

Learning shape prior models for object matching (Abstract)

Tingting Jiang , LEAR team, INRIA, Grenoble, France
C. Schmid , LEAR team, INRIA, Grenoble, France
F. Jurie , LEAR team, INRIA, Grenoble, France
pp. 848-855

Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates (Abstract)

Jaechul Kim , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
pp. 2921-2928

Symmetry integrated region-based image segmentation (Abstract)

Yu Sun , Center for Res. in Intell. Syst., Univ. of California at Riverside, Riverside, CA, USA
B. Bhanu , Center for Res. in Intell. Syst., Univ. of California at Riverside, Riverside, CA, USA
pp. 826-831

Image registration by minimization of residual complexity (Abstract)

Xubo Song , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Portland, OR, USA
A. Myronenko , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Portland, OR, USA
pp. 49-56

Co-training with noisy perceptual observations (Abstract)

C.M. Christoudias , EECS, UC Berkeley, Berkeley, CA, USA
R. Urtasun , EECS, UC Berkeley, Berkeley, CA, USA
T. Darrell , EECS, UC Berkeley, Berkeley, CA, USA
pp. 2844-2851

Saliency-based discriminant tracking (Abstract)

V. Mahadevan , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
N. Vasconcelos , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
pp. 1007-1013

Dictionary-free categorization of very similar objects via stacked evidence trees (Abstract)

G. Martinez-Munoz , Oregon State Univ., Corvallis, OR, USA
T.G. Dietterich , Oregon State Univ., Corvallis, OR, USA
S. Todorovic , Oregon State Univ., Corvallis, OR, USA
A. Yamamuro , Oregon State Univ., Corvallis, OR, USA
Wei Zhang , Oregon State Univ., Corvallis, OR, USA
R. Paasch , Oregon State Univ., Corvallis, OR, USA
A. Moldenke , Oregon State Univ., Corvallis, OR, USA
D. Lytle , Oregon State Univ., Corvallis, OR, USA
N. Payet , Oregon State Univ., Corvallis, OR, USA
pp. 549-556

Imbalanced RankBoost for efficiently ranking large-scale image/video collections (Abstract)

M. Merler , Comput. Sci. Dept., Columbia Univ., New York, NY, USA
pp. 2607-2614

Shared Kernel Information Embedding for discriminative inference (Abstract)

D.J. Fleet , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
R. Memisevic , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
L. Sigal , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
pp. 2852-2859

Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning (Abstract)

M. Ranjbar , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
M. Norouzi , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
G. Mori , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
pp. 2735-2742

D - Clutter: Building object model library from unsupervised segmentation of cluttered scenes (Abstract)

M.V. Rohith , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
C. Kambhamettu , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
G. Somanath , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
pp. 2783-2789

Switching Gaussian Process Dynamic Models for simultaneous composite motion tracking and recognition (Abstract)

Jixu Chen , Dept. of Electr., Comput.&Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Yu Wang , Dept. of Electr., Comput.&Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Minyoung Kim , Dept. of Electr., Comput.&Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Qiang Ji , Dept. of Electr., Comput.&Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
pp. 2655-2662

Uncalibrated synthetic aperture for defocus control (Abstract)

S. Hiura , Grad. Sch. of Eng. Sci., Osaka Univ., Toyonaka, Japan
N. Kusumoto , Grad. Sch. of Eng. Sci., Osaka Univ., Toyonaka, Japan
K. Sato , Grad. Sch. of Eng. Sci., Osaka Univ., Toyonaka, Japan
pp. 2552-2559

Nonlinear Nonnegative Component Analysis (Abstract)

M. Petrou , Dept. of Electr.&Electron. Eng., Imperial Coll. London, London, UK
S. Zafeiriou , Dept. of Electr.&Electron. Eng., Imperial Coll. London, London, UK
pp. 2860-2865

Learning invariant features through topographic filter maps (Abstract)

M.A. Ranzato , Courant Inst. of Math. Sci., New York Univ., New York, NY, USA
R. Fergus , Courant Inst. of Math. Sci., New York Univ., New York, NY, USA
K. Kavukcuoglu , Courant Inst. of Math. Sci., New York Univ., New York, NY, USA
Yann Le-Cun , Courant Inst. of Math. Sci., New York Univ., New York, NY, USA
pp. 1605-1612

Optimal single image capture for motion deblurring (Abstract)

A. Agrawal , Mitsubishi Electr. Res. Labs., Cambridge, MA, USA
pp. 2560-2567

Sparse subspace clustering (Abstract)

R. Vidal , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
E. Elhamifar , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
pp. 2790-2797

Global optimization for alignment of generalized shapes (Abstract)

Xiaolei Huang , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
Tian Shen , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
Hongsheng Li , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
pp. 856-863

Unsupervised learning of hierarchical spatial structures in images (Abstract)

D. Parikh , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 2743-2750

A novel feature descriptor invariant to complex brightness changes (Abstract)

N.L. Chang , Hewlett-Packard Labs., Palo Alto, CA, USA
Feng Tang , Hewlett-Packard Labs., Palo Alto, CA, USA
Suk Hwan Lim , Hewlett-Packard Labs., Palo Alto, CA, USA
pp. 2631-2638

Polarization: Beneficial for visibility enhancement? (Abstract)

T. Treibitz , Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel
Y.Y. Schechner , Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel
pp. 525-532

Global active contour-based image segmentation via probability alignment (Abstract)

Xubo Song , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Beaverton, OR, USA
A. Myronenko , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Beaverton, OR, USA
pp. 2798-2804

A robust parametric method for bias field estimation and segmentation of MR images (Abstract)

Chunming Li , Vanderbilt Univ. of Imaging Sci., Nashville, TN, USA
J.C. Gore , Vanderbilt Univ. of Imaging Sci., Nashville, TN, USA
C. Gatenby , Vanderbilt Univ. of Imaging Sci., Nashville, TN, USA
pp. 218-223

Interval HSV: Extracting ink annotations (Abstract)

A. Razdan , Arizona State Univ., Mesa, AZ, USA
J.C. Femiani , Arizona State Univ., Mesa, AZ, USA
pp. 2520-2527

A distribution-based approach to tracking points in velocity vector fields (Abstract)

Liefei Xu , Dept. of Comput. Sci., Stevens Inst. of Technol., Hoboken, NJ, USA
H.Q. Dinh , Dept. of Comput. Sci., Stevens Inst. of Technol., Hoboken, NJ, USA
pp. 2663-2670

Variational layered dynamic textures (Abstract)

N. Vasconcelos , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
A.B. Chan , Dept. of Electr.&Comput. Eng., Univ. of California, San Diego, CA, USA
pp. 1062-1069

Actions in context (Abstract)

C. Schmid , INRIA Grenoble, Grenoble, France
M. Marszalek , INRIA Grenoble, Grenoble, France
pp. 2929-2936

Material classification using BRDF slices (Abstract)

J. Davis , Univ. of California, Santa Cruz, CA, USA
O. Wang , Univ. of California, Santa Cruz, CA, USA
S. Scher , Univ. of California, Santa Cruz, CA, USA
P. Gunawardane , Univ. of California, Santa Cruz, CA, USA
pp. 2805-2811

Learning trajectory patterns by clustering: Experimental studies and comparative evaluation (Abstract)

B. Morris , Comput. Vision&Robot. Res. Lab., Univ. of California, San Diego, La Jolla, CA, USA
M. Trivedi , Comput. Vision&Robot. Res. Lab., Univ. of California, San Diego, La Jolla, CA, USA
pp. 312-319

Optimization of landmark selection for cortical surface registration (Abstract)

D. Pantazis , Signal&Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA
R. Leahy , Signal&Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA
Quanzheng Li , Signal&Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA
A. Joshi , Signal&Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA
pp. 699-706

Fast normalized cut with linear constraints (Abstract)

Wenye Li , Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
Linli Xu , Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
D. Schuurmans , Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
pp. 2866-2873

Automatic reconstruction of cities from remote sensor data (Abstract)

C. Poullis , CGIT/IMSC, Univ. of Southern California, Los Angeles, CA, USA
S. You , CGIT/IMSC, Univ. of Southern California, Los Angeles, CA, USA
pp. 2775-2782

Active volume models for 3D medical image segmentation (Abstract)

Hongsheng Li , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
Tian Shen , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
Xiaolei Huang , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
pp. 707-714

Unsupervised learning for graph matching (Abstract)

M. Hebert , Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Leordeanu , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 864-871

Retrographic sensing for the measurement of surface texture and shape (Abstract)

E.H. Adelson , MIT, Cambridge, MA, USA
M.K. Johnson , MIT, Cambridge, MA, USA
pp. 1070-1077

Piecewise planar city 3D modeling from street view panoramic sequences (Abstract)

J. Kosecka , Comput. Sci. Dept., George Mason Univ., Fairfax, VA, USA
B. Micusik , Comput. Sci. Dept., George Mason Univ., Fairfax, VA, USA
pp. 2906-2912

Nonparametric scene parsing: Label transfer via dense scene alignment (Abstract)

Ce Liu , Comput. Sci.&Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
J. Yuen , Comput. Sci.&Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
A. Torralba , Comput. Sci.&Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. 1972-1979

Recognizing indoor scenes (Abstract)

A. Quattoni , CSAIL, MIT, Cambridge, MA, USA
A. Torralba , CSAIL, MIT, Cambridge, MA, USA
pp. 413-420

Learning general optical flow subspaces for egomotion estimation and detection of motion anomalies (Abstract)

F. Dellaert , Sch. of Interactive Comput., Georgia Inst. of Technol., Atlanta, GA, USA
C. Potthast , Sch. of Interactive Comput., Georgia Inst. of Technol., Atlanta, GA, USA
R. Roberts , Sch. of Interactive Comput., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 57-64

Automatic registration of LIDAR and optical images of urban scenes (Abstract)

A. Mastin , Comput. Sci.&Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
J. Fisher , Comput. Sci.&Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. 2639-2646

Optimal scanning for faster object detection (Abstract)

N.J. Butko , Dept. of Cognitive Sci., UC San Diego, La Jolla, CA, USA
pp. 2751-2758

Motion pattern interpretation and detection for tracking moving vehicles in airborne video (Abstract)

Qian Yu , Inst. for Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
G. Medioni , Inst. for Robot.&Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
pp. 2671-2678

Real-time O(1) bilateral filtering (Abstract)

N. Ahuja , Univ. of Illinois at Urbana Champaign, Champaign, IL, USA
Qingxiong Yang , Univ. of Illinois at Urbana Champaign, Champaign, IL, USA
pp. 557-564
105 ms
(Ver )