The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2012)
Providence, RI USA
June 16, 2012 to June 21, 2012
ISSN: 1063-6919
ISBN: 978-1-4673-1226-4
TABLE OF CONTENTS
Papers

Table of contents (Abstract)

pp. 1-41

The inverted multi-index (Abstract)

V. Lempitsky , Yandex, Moscow, Russia
A. Babenko , Yandex, Moscow, Russia
pp. 3069-3076

Aligning images in the wild (Abstract)

Kok-Lim Low , Nat. Univ. of Singapore, Singapore, Singapore
pp. 1-8

A physically-based approach to reflection separation (Abstract)

Yu-Wing Tai , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
Naejin Kong , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
Sung Yong Shin , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
pp. 9-16

Motion-aware noise filtering for deblurring of noisy and blurry images (Abstract)

Yu-Wing Tai , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
pp. 17-24

Nonlinear camera response functions and image deblurring (Abstract)

M. S. Brown , Nat. Univ. of Singapore, Singapore, Singapore
Seon Joo Kim , SUNY Korea, South Korea
Yu-Wing Tai , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
Sunyeong Kim , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
pp. 25-32

Scene warping: Layer-based stereoscopic image resizing (Abstract)

Cheng-Da Chung , Nat. Taiwan Univ., Taipei, Taiwan
Ken-Yi Lee , Nat. Taiwan Univ., Taipei, Taiwan
Yung-Yu Chuang , Nat. Taiwan Univ., Taipei, Taiwan
pp. 49-56

A two-stage approach to blind spatially-varying motion deblurring (Abstract)

Kang Wang , Dept. of Math., Nat. Univ. of Singapore, Singapore, Singapore
Hui Ji , Dept. of Math., Nat. Univ. of Singapore, Singapore, Singapore
pp. 73-80

Enhancing underwater images and videos by fusion (Abstract)

P. Bekaert , IBBT, Hasselt Univ., Hasselt, Belgium
T. Haber , IBBT, Hasselt Univ., Hasselt, Belgium
C. O. Ancuti , IBBT, Hasselt Univ., Hasselt, Belgium
C. Ancuti , IBBT, Hasselt Univ., Hasselt, Belgium
pp. 81-88

Video stabilization with a depth camera (Abstract)

Ping Tan , Nat. Univ. of Singapore, Singapore, Singapore
Yinting Wang , Nat. Univ. of Singapore, Singapore, Singapore
Shuaicheng Liu , Nat. Univ. of Singapore, Singapore, Singapore
pp. 89-95

Compressive depth map acquisition using a single photon-counting detector: Parametric signal processing meets sparsity (Abstract)

A. Kirmani , Massachusetts Inst. of Technol., Cambridge, MA, USA
A. Colaco , Massachusetts Inst. of Technol., Cambridge, MA, USA
V. K. Goyal , Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. 96-102

A new convexity measurement for 3D meshes (Abstract)

Xianfang Sun , Cardiff Univ., Cardiff, UK
P. L. Rosin , Cardiff Univ., Cardiff, UK
A. Godil , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
Zhouhui Lian , Inst. of Comput. Sci. & Technol., Peking Univ., Beijing, China
pp. 119-126

Factorized graph matching (Abstract)

F. De la Torre , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Feng Zhou , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 127-134

Learning contour-fragment-based shape model with And-Or tree representation (Abstract)

Jianhuang Lai , Sun Yat-Sen Univ., Guangzhou, China
Wei Yang , Sun Yat-Sen Univ., Guangzhou, China
Xiaolong Wang , Sun Yat-Sen Univ., Guangzhou, China
Liang Lin , Sun Yat-Sen Univ., Guangzhou, China
pp. 135-142

Fan Shape Model for object detection (Abstract)

Wenyu Liu , Dept. of Electron. & Inf. Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
Xiang Bai , Dept. of Electron. & Inf. Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
Xinggang Wang , Dept. of Electron. & Inf. Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
pp. 151-158

Intrinsic shape context descriptors for deformable shapes (Abstract)

A. M. Bronstein , Sch. of Electr. Eng., Tel Aviv Univ., Tel Aviv, Israel
R. Litman , Sch. of Electr. Eng., Tel Aviv Univ., Tel Aviv, Israel
M. M. Bronstein , Fac. of Inf., Univ. della Svizzera Italiana, Lugano, Switzerland
I. Kokkinos , Center for Visual Comput., Ecole Centrale Paris, Chetenay-Malabry, France
pp. 159-166

Twisted window search for efficient shape localization (Abstract)

C. Tomasi , Duke Univ., Durham, NC, USA
Ying Zheng , Duke Univ., Durham, NC, USA
S. Gu , Duke Univ., Durham, NC, USA
pp. 167-173

Robust nonrigid ICP using outlier-sparsity regularization (Abstract)

Y. Sawada , Nagoya Inst. of Technol., Nagoya, Japan
T. Matsuno , Nagoya Inst. of Technol., Nagoya, Japan
H. Hontani , Nagoya Inst. of Technol., Nagoya, Japan
pp. 174-181

A game-theoretic approach to deformable shape matching (Abstract)

A. Torsello , Dip. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari, Venezia, Italy
F. Bergamasco , Dip. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari, Venezia, Italy
A. Albarelli , Dip. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari, Venezia, Italy
A. M. Bronstein , Sch. of Electr. Eng., Tel Aviv Univ., Tel Aviv, Israel
E. Rodola , Dip. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari, Venezia, Italy
pp. 182-189

Progressive shape models (Abstract)

A. Letouzey , INRIA Grenoble Rhone-Alpes, St. Ismier, France
E. Boyer , INRIA Grenoble Rhone-Alpes, St. Ismier, France
pp. 190-197

The Schrödinger distance transform (SDT) for point-sets and curves (Abstract)

K. Gurumoorthy , Dept. of Comput. & Inf. Sci. & Eng., Univ. of Florida, Gainesville, FL, USA
M. Sethi , Dept. of Comput. & Inf. Sci. & Eng., Univ. of Florida, Gainesville, FL, USA
A. Rangarajan , Dept. of Comput. & Inf. Sci. & Eng., Univ. of Florida, Gainesville, FL, USA
pp. 198-205

Geometric understanding of point clouds using Laplace-Beltrami operator (Abstract)

Tsz Wai Wong , UC Irvine, Irvine, CA, USA
Rongjie Lai , USC, Los Angeles, CA, USA
Jian Liang , UC Irvine, Irvine, CA, USA
Hongkai Zhao , UC Irvine, Irvine, CA, USA
pp. 214-221

On the dimensionality of video bricks under varying illumination (Abstract)

Youdong Zhao , Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
Xi Song , Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
Yunde Jia , Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
pp. 222-229

A biquadratic reflectance model for radiometric image analysis (Abstract)

Ping Tan , Nat. Univ. of Singapore, Singapore, Singapore
K. Ikeuchi , Univ. of Tokyo, Tokyo, Japan
Boxin Shi , Univ. of Tokyo, Tokyo, Japan
pp. 230-237

Single image multimaterial estimation (Abstract)

K. Nishino , Dept. of Comput. Sci., Drexel Univ., Philadelphia, PA, USA
S. Lombardi , Dept. of Comput. Sci., Drexel Univ., Philadelphia, PA, USA
pp. 238-245

Photometric stereo for outdoor webcams (Abstract)

F. Langguth , Tech. Univ. Darmstadt, Darmstadt, Germany
J. Ackermann , Tech. Univ. Darmstadt, Darmstadt, Germany
S. Fuhrmann , Tech. Univ. Darmstadt, Darmstadt, Germany
M. Goesele , Tech. Univ. Darmstadt, Darmstadt, Germany
pp. 262-269

Bispectral photometric stereo based on fluorescence (Abstract)

Y. Sato , Univ. of Tokyo, Tokyo, Japan
T. Okabe , Univ. of Tokyo, Tokyo, Japan
I. Sato , Nat. Inst. of Inf., Tokyo, Japan
pp. 270-277

Names and shades of color for intrinsic image estimation (Abstract)

M. Serra , Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
O. Penacchio , Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
R. Benavente , Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
M. Vanrell , Comput. Sci. Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
pp. 278-285

Refractive height fields from single and multiple images (Abstract)

Qi Shan , Univ. of Washington, Seattle, WA, USA
B. Curless , Univ. of Washington, Seattle, WA, USA
pp. 286-293

Example-based 3D object reconstruction from line drawings (Abstract)

Xiaoou Tang , 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
Tianfan Xue , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 302-309

Angular domain reconstruction of dynamic 3D fluid surfaces (Abstract)

Jingyi Yu , Univ. of Delaware, Newark, DE, USA
Feng Li , Univ. of Delaware, Newark, DE, USA
Yu Ji , Univ. of Delaware, Newark, DE, USA
Jinwei Ye , Univ. of Delaware, Newark, DE, USA
pp. 310-317

Robust photometric stereo using sparse regression (Abstract)

K. Aizawa , Univ. of Tokyo, Tokyo, Japan
S. Ikehata , Univ. of Tokyo, Tokyo, Japan
pp. 318-325

Shape, albedo, and illumination from a single image of an unknown object (Abstract)

J. T. Barron , UC Berkeley, Berkeley, CA, USA
J. Malik , UC Berkeley, Berkeley, CA, USA
pp. 334-341

Robust stereo with flash and no-flash image pairs (Abstract)

K. Pulli , NVIDIA Res., Santa Clara, CA, USA
A. Troccoli , NVIDIA Res., Santa Clara, CA, USA
Changyin Zhou , Columbia Univ., New York, NY, USA
pp. 342-349

Detection by detections: Non-parametric detector adaptation for a video (Abstract)

T. X. Han , Electr. & Comput. Eng. Dept., Univ. of Missouri, Columbia, MO, USA
Gang Hua , Comput. Sci. Dept., Stevens Inst. of Technol., Hoboken, NJ, USA
Xiaoyu Wang , Electr. & Comput. Eng. Dept., Univ. of Missouri, Columbia, MO, USA
pp. 350-357

Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture (Abstract)

W. T. Freeman , Comput. Sci. & Artificial Intell. Lab. (CSAIL), MIT, Cambridge, MA, USA
A. Torralba , Comput. Sci. & Artificial Intell. Lab. (CSAIL), MIT, Cambridge, MA, USA
pp. 374-381

Jigsaw puzzles with pieces of unknown orientation (Abstract)

A. C. Gallagher , Eastman Kodak Res. Labs., Rochester, NY, USA
pp. 382-389

Affine-invariant, elastic shape analysis of planar contours (Abstract)

E. Klassen , Dept. of Math., Florida State Univ., Tallahassee, FL, USA
A. Srivastava , Dept. of Stat., Florida State Univ., Tallahassee, FL, USA
D. Bryner , Dept. of Stat., Florida State Univ., Tallahassee, FL, USA
pp. 390-397

Progressive graph matching: Making a move of graphs via probabilistic voting (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Minsu Cho , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 398-405

The Shape Boltzmann Machine: A strong model of object shape (Abstract)

N. Heess , Gatsby Unit, Univ. Coll. London, London, UK
S. M. A. Eslami , Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK
J. Winn , Microsoft Res., Cambridge, UK
pp. 406-413

Discrete texture traces: Topological representation of geometric context (Abstract)

V. Ramesh , Dept. of Comput. Sci. & Math., Goethe Univ., Frankfurt am Main, Germany
M. K. Singh , Corp. Res. & Technol., Siemens Corp., Princeton, NJ, USA
J. Ernst , Corp. Res. & Technol., Siemens Corp., Princeton, NJ, USA
pp. 422-429

Cross-based local multipoint filtering (Abstract)

Liang Lin , Sun Yat-Sen Univ., Guangzhou, China
Keyang Shi , Sun Yat-Sen Univ., Guangzhou, China
M. N. Do , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 430-437

Boosting bottom-up and top-down visual features for saliency estimation (Abstract)

A. Borji , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
pp. 438-445

Identigram/watermark removal using cross-channel correlation (Abstract)

Yu-Wing Tai , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
Jaesik Park , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
In So Kweon , Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
pp. 446-453

Leveraging stereopsis for saliency analysis (Abstract)

Feng Liu , Dept. of Comput. Sci., Portland State Univ., Portland, OR, USA
Xueqing Li , Sch. of Comput. Sci. & Technol., Shandong Univ., Jinan, China
Yujie Geng , Dept. of Comput. Sci., Portland State Univ., Portland, OR, USA
Yuzhen Niu , Dept. of Comput. Sci., Portland State Univ., Portland, OR, USA
pp. 454-461

The scale of edges (Abstract)

Hongxun Yao , Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China
Changhu Wang , Microsoft Res. Asia, Beijing, China
Xian-Ming Liu , Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China
Lei Zhang , Microsoft Res. Asia, Beijing, China
pp. 462-469

Probabilistic learning of task-specific visual attention (Abstract)

L. Itti , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
D. N. Sihite , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
A. Borji , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
pp. 470-477

Example-based cross-modal denoising (Abstract)

M. Elad , Dept. Comput. Sci., Technion - Israel Inst. Technol., Haifa, Israel
Y. Y. Schechner , Dept. Electr. Eng., Technion - Israel Inst. Technol., Haifa, Israel
D. Segev , Dept. Electr. Eng., Technion - Israel Inst. Technol., Haifa, Israel
pp. 486-493

A unifying resolution-independent formulation for early vision (Abstract)

A. Fitzgibbon , Microsoft Res. Cambridge, Cambridge, UK
F. Viola , Univ. of Cambridge, Cambridge, UK
R. Cipolla , Univ. of Cambridge, Cambridge, UK
pp. 494-501

The image torque operator: A new tool for mid-level vision (Abstract)

D. DeMenthon , Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
C. Fermuller , UMIACS, Univ. of Maryland, College Park, MD, USA
M. Nishigaki , Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
pp. 502-509

FREAK: Fast Retina Keypoint (Abstract)

P. Vandergheynst , Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
R. Ortiz , Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
A. Alahi , Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
pp. 510-517

Per-pixel translational symmetry detection, optimization, and segmentation (Abstract)

Honghui Zhang , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Lei Yang , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Peng Zhao , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Long Quan , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
pp. 526-533

Fast and globally optimal single view reconstruction of curved objects (Abstract)

E. Toppe , Tech. Univ. Munich, Munich, Germany
M. R. Oswald , Tech. Univ. Munich, Munich, Germany
D. Cremers , Tech. Univ. Munich, Munich, Germany
pp. 534-541

Multi-class cosegmentation (Abstract)

J. Ponce , Ecole Normale Super., Paris, France
F. Bach , INRIA, Paris, France
A. Joulin , INRIA, Paris, France
pp. 542-549

Improved subspace clustering via exploitation of spatial constraints (Abstract)

S. Venkatesh , PRaDA, Deakin Univ., Geelong, VIC, Australia
D. Phung , PRaDA, Deakin Univ., Geelong, VIC, Australia
S. Budhaditya , PRaDA, Deakin Univ., Geelong, VIC, Australia
Duc-Son Pham , Dept. of Comput., Curtin Univ., Perth, WA, Australia
pp. 550-557

Automated reconstruction of tree structures using path classifiers and Mixed Integer Programming (Abstract)

F. Benmansour , Comput. Vision Lab. (EPFL), Lausanne, Switzerland
P. Fua , Comput. Vision Lab. (EPFL), Lausanne, Switzerland
E. Turetken , Comput. Vision Lab. (EPFL), Lausanne, Switzerland
pp. 566-573

Efficient structure detection via random consensus graph (Abstract)

Shuicheng Yan , Nat. Univ. of Singapore, Singapore, Singapore
Hairong Liu , Nat. Univ. of Singapore, Singapore, Singapore
pp. 574-581

Learning image-specific parameters for interactive segmentation (Abstract)

K-Y K. Wong , Univ. of Hong Kong, Hong Kong, China
Hao Zhou , Univ. of Hong Kong, Hong Kong, China
D. Schnieders , Univ. of Hong Kong, Hong Kong, China
Zhanghui Kuang , Univ. of Hong Kong, Hong Kong, China
Yizhou Yu , Univ. of Hong Kong, Hong Kong, China
Bo Peng , Hong Kong Polytech. Univ., Hong Kong, China
pp. 590-597

Mode-seeking on graphs via random walks (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Minsu Cho , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 606-613

Higher order motion models and spectral clustering (Abstract)

T. Brox , Comput. Vision Group, Univ. of Freiburg, Freiburg, Germany
P. Ochs , Comput. Vision Group, Univ. of Freiburg, Freiburg, Germany
pp. 614-621

The role of image understanding in contour detection (Abstract)

D. Parikh , Toyota Technol. Inst., Chicago (TTIC), Chicago, IL, USA
pp. 622-629

Globally optimal line clustering and vanishing point estimation in Manhattan world (Abstract)

K. Ikeuchi , CV Lab., Univ. of Tokyo, Tokyo, Japan
P. Vasseur , LITIS, Univ. of Rouen, Rouen, France
C. Demonceaux , Le2i, Univ. of Burgundy, Dijon, France
Inso Kweon , RCV Lab., KAIST, Daejeon, South Korea
Yongduek Seo , Dept. of Media Technol., Sogang Univ., Seoul, South Korea
J.-C Bazin , CGL, ETHZ, Zürich, Switzerland
M. Pollefeys , CVG, ETHZ, Zürich, Switzerland
pp. 638-645

Actionable saliency detection: Independent motion detection without independent motion estimation (Abstract)

S. Soatto , Univ. of California, Los Angeles, CA, USA
A. Ayvaci , Univ. of California, Los Angeles, CA, USA
G. Georgiadis , Univ. of California, Los Angeles, CA, USA
pp. 646-653

Adaptive figure-ground classification (Abstract)

A. B. Chan , Dept. of Comput. Sci., City Univ. of Hong Kong, Hong Kong, China
pp. 654-661

What are good parts for hair shape modeling? (Abstract)

Feng Tang , Hewlett-Packard Labs., Palo Alto, CA, USA
Haizhou Ai , Comput. Sci. & Technol. Dept., Tsinghua Univ., Beijing, China
Nan Wang , Comput. Sci. & Technol. Dept., Tsinghua Univ., Beijing, China
pp. 662-669

Linear solution to scale invariant global figure ground separation (Abstract)

Hao Jiang , Comput. Sci. Dept., Boston Coll., Boston, MA, USA
pp. 678-685

A hierarchical image clustering cosegmentation framework (Abstract)

Xiaolei Huang , Dept. of Comput. Sci. & Eng., Lehigh Univ., Bethlehem, PA, USA
Hongsheng Li , Dept. of Comput. Sci. & Eng., Lehigh Univ., Bethlehem, PA, USA
E. Kim , Dept. of Comput. Sci. & Eng., Lehigh Univ., Bethlehem, PA, USA
pp. 686-693

Higher level segmentation: Detecting and grouping of invariant repetitive patterns (Abstract)

G. Baciu , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Yunliang Cai , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
pp. 694-701

Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation (Abstract)

S. Fidler , Univ. of Toronto, Toronto, ON, Canada
Jian Yao , TTI Chicago, Chicago, IL, USA
R. Urtasun , TTI Chicago, Chicago, IL, USA
pp. 702-709

The Random Cluster Model for robust geometric fitting (Abstract)

D. Suter , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
Jin Yu , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
Tat-Jun Chin , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
Trung Thanh Pham , Sch. of Comput. Sci., Univ. of Adelaide, Adelaide, SA, Australia
pp. 710-717

Weighted color and texture sample selection for image matting (Abstract)

D. Rajan , Nanyang Technol. Univ., Singapore, Singapore
E. Shahrian , Nanyang Technol. Univ., Singapore, Singapore
pp. 718-725

Graph cuts optimization for multi-limb human segmentation in depth maps (Abstract)

S. Escalera , Comput. Vision Center, Barcelona, Spain
P. Radeva , Comput. Vision Center, Barcelona, Spain
D. Dimov , Inst. of Inf. & Commun. Technol., Sofia, Bulgaria
M. Reyes , Comput. Vision Center, Barcelona, Spain
A. Marinov , Inst. of Inf. & Commun. Technol., Sofia, Bulgaria
A. Hernandez-Vela , Comput. Vision Center, Barcelona, Spain
N. Zlateva , Inst. of Inf. & Commun. Technol., Sofia, Bulgaria
pp. 726-732

Exploiting nonlocal spatiotemporal structure for video segmentation (Abstract)

N. Ahuja , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Hsien-Ting Cheng , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 741-748

Unsupervised co-segmentation through region matching (Abstract)

N. Paragios , Center for Visual Comput., Ecole Centrale de Paris, Paris, France
J. Serrat , Dept. Comp. Sci., Univ. Autonoma de Barcelona, Cerdanyola, Spain
A. Lopez , Dept. Comp. Sci., Univ. Autonoma de Barcelona, Cerdanyola, Spain
J. C. Rubio , Dept. Comp. Sci., Univ. Autonoma de Barcelona, Cerdanyola, Spain
pp. 749-756

Seeded watershed cut uncertainty estimators for guided interactive segmentation (Abstract)

F. A. Hamprecht , HCI Univ. of Heidelberg, Heidelberg, Germany
W. Denk , MPI for Med. Res., Heidelberg, Germany
K. Briggman , Nat. Inst. of Health, Bethesda, MD, USA
G. Knott , EPF, EPFL SV-GE, Lausanne, Switzerland
U. Koethe , HCI Univ. of Heidelberg, Heidelberg, Germany
C. Straehle , HCI Univ. of Heidelberg, Heidelberg, Germany
pp. 765-772

Affinity aggregation for spectral clustering (Abstract)

Chu-Song Chen , Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
Yung-Yu Chuang , Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Hsin-Chien Huang , Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 773-780

Bag of textons for image segmentation via soft clustering and convex shift (Abstract)

Chunjing Xu , Multimedia Lab., SIAT, Shenzhen, China
Ang Li , Robot. Inst, Pittsburgh, PA, USA
pp. 781-788

Segmentation using superpixels: A bipartite graph partitioning approach (Abstract)

Shih-Fu Chang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Xiao-Ming Wu , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Zhenguo Li , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
pp. 789-796

Discriminative illumination: Per-pixel classification of raw materials based on optimal projections of spectral BRDF (Abstract)

Chao Liu , Rochester Inst. of Technol., Rochester, NY, USA
Jinwei Gu , Rochester Inst. of Technol., Rochester, NY, USA
pp. 797-804

Camera spectral sensitivity estimation from a single image under unknown illumination by using fluorescence (Abstract)

T. Okabe , Univ. of Tokyo, Tokyo, Japan
I. Sato , Nat. Inst. of Inf., Tokyo, Japan
Y. Matsushita , Microsoft Res. Asia, Beijing, China
Y. Sato , Univ. of Tokyo, Tokyo, Japan
Shuai Han , Univ. of Tokyo, Tokyo, Japan
pp. 805-812

Micro Phase Shifting (Abstract)

S. K. Nayar , Columbia Univ., New York, NY, USA
M. Gupta , Columbia Univ., New York, NY, USA
pp. 813-820

A closed-form solution to uncalibrated photometric stereo via diffuse maxima (Abstract)

T. Papadhimitri , Heriot-Watt Univ., Edinburgh, UK
P. Favaro , Heriot-Watt Univ., Edinburgh, UK
pp. 821-828

Connected contours: A new contour completion model that respects the closure effect (Abstract)

Xuming He , NICTA, Sydney, NSW, Australia
Hongdong Li , Australian Nat. Univ., Canberra, ACT, Australia
Yansheng Ming , Australian Nat. Univ., Canberra, ACT, Australia
pp. 829-836

Weakly supervised structured output learning for semantic segmentation (Abstract)

J. M. Buhmann , ETH Zurich, Zurich, Switzerland
V. Ferrari , Univ. of Edinburgh, Edinburgh, UK
A. Vezhnevets , ETH Zurich, Zurich, Switzerland
pp. 845-852

A unified approach to salient object detection via low rank matrix recovery (Abstract)

Ying Wu , Northwestern Univ., Evanston, IL, USA
Xiaohui Shen , Northwestern Univ., Evanston, IL, USA
pp. 853-860

Facial expression editing in video using a temporally-smooth factorization (Abstract)

D. Metaxas , Rutgers Univ., Piscataway, NJ, USA
Jue Wang , Adobe Syst., Seattle, WA, USA
E. Shechtman , Adobe Syst., Seattle, WA, USA
L. Bourdev , Facebook, Menlo Park, CA, USA
Fei Yang , Rutgers Univ., Piscataway, NJ, USA
pp. 861-868

KNN matting (Abstract)

Chi-Keung Tang , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Dingzeyu Li , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Qifeng Chen , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
pp. 869-876

Automatic upright adjustment of photographs (Abstract)

Jue Wang , Adobe Syst., Seattle, WA, USA
E. Shechtman , Adobe Syst., Seattle, WA, USA
Hyunjoon Lee , POSTECH, Pohang, South Korea
Seungyong Lee , POSTECH, Pohang, South Korea
pp. 877-884

Synthesizing oil painting surface geometry from a single photograph (Abstract)

Xiaoou Tang , Chinese Univ. of Hong Kong, Hong Kong, China
Xiaogang Wang , Chinese Univ. of Hong Kong, Hong Kong, China
Zheng Lu , Nat. Univ. of Singapore, Singapore, Singapore
Wei Luo , Chinese Univ. of Hong Kong, Hong Kong, China
M. S. Brown , Nat. Univ. of Singapore, Singapore, Singapore
pp. 885-892

An analysis of color demosaicing in plenoptic cameras (Abstract)

T. Georgiev , Qualcomm, San Diego, CA, USA
A. Lumsdaine , Indiana Univ., Bloomington, IN, USA
Jingyi Yu , Univ. of Delaware, Newark, DE, USA
Zhan Yu , Univ. of Delaware, Newark, DE, USA
pp. 901-908

Spatial bias in multi-atlas based segmentation (Abstract)

P. A. Yushkevich , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
Hongzhi Wang , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 909-916

2D/3D rotation-invariant detection using equivariant filters and kernel weighted mapping (Abstract)

O. Ronneberger , Dept. of Comput. Sci., Univ. of Freiburg, Freiburg, Germany
W. Driever , Inst. of Biol. I, Univ. of Freiburg, Freiburg, Germany
Qing Wang , Dept. of Comput. Sci., Univ. of Freiburg, Freiburg, Germany
Kun Liu , Dept. of Comput. Sci., Univ. of Freiburg, Freiburg, Germany
pp. 917-924

Reconstruction of super-resolution lung 4D-CT using patch-based sparse representation (Abstract)

Dinggang Shen , Dept. of Radiol., Univ. of North Carolina, Chapel Hill, NC, USA
Wufan Chen , Sch. of Biomed. Eng., Southern Med. Univ., Guang Zhou, China
Jun Lian , Dept. of Radiat. Oncology, Univ. of North Carolina, Chapel Hill, NC, USA
Qianjin Feng , Sch. of Biomed. Eng., Southern Med. Univ., Guang Zhou, China
Pew-Thian Yap , Dept. of Radiol., Univ. of North Carolina, Chapel Hill, NC, USA
Guorong Wu , Dept. of Radiol., Univ. of North Carolina, Chapel Hill, NC, USA
Yu Zhang , Sch. of Biomed. Eng., Southern Med. Univ., Guang Zhou, China
pp. 925-931

Fast radial symmetry detection under affine transformations (Abstract)

C. Bahlmann , Siemens Corp. Res. & Technol., Siemens Co., Princeton, NJ, USA
M. K. Singh , Siemens Corp. Res. & Technol., Siemens Co., Princeton, NJ, USA
Jie Ni , Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
pp. 932-939

The use of on-line co-training to reduce the training set size in pattern recognition methods: Application to left ventricle segmentation in ultrasound (Abstract)

J. C. Nascimento , Inst. de Sist. e Robot., Inst. Super. Tecnico, Lisbon, Portugal
G. Carneiro , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
pp. 948-955

From label fusion to correspondence fusion: A new approach to unbiased groupwise registration (Abstract)

B. B. Avants , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
J. Pluta , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
Hongzhi Wang , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
P. A. Yushkevich , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 956-963

Multiple clustered instance learning for histopathology cancer image classification, segmentation and clustering (Abstract)

Jun-Yan Zhu , Microsoft Res. Asia, Beijing, China
Yan Xu , State Key Lab. of Software Dev. Environ., Beihang Univ., Beijing, China
E. Chang , Microsoft Res. Asia, Beijing, China
Zhuowen Tu , Microsoft Res. Asia, Beijing, China
pp. 964-971

Automatic mitral leaflet tracking in echocardiography by outlier detection in the low-rank representation (Abstract)

Weichuan Yu , Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Can Yang , Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Xiaowei Zhou , Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China
pp. 972-979

A learning based deformable template matching method for automatic rib centerline extraction and labeling in CT images (Abstract)

S. K. Zhou , Siemens Corp. Res., Princeton, NJ, USA
G. Soza , Siemens Healthcare, Forchheim, Germany
C. Tietjen , Siemens Healthcare, Forchheim, Germany
A. Wimmer , Siemens Healthcare, Forchheim, Germany
Chao Lu , Siemens Corp. Res., Princeton, NJ, USA
Z. Puskas , Siemens Corp. Res., Princeton, NJ, USA
D. Liu , Siemens Corp. Res., Princeton, NJ, USA
Dijia Wu , Siemens Corp. Res., Princeton, NJ, USA
pp. 980-987

Graph-based detection, segmentation & characterization of brain tumors (Abstract)

N. Paragios , Center for Visual Comput., Ecole Centrale de Paris, Paris, France
S. Chemouny , Intrasense SAS, Montpellier, France
H. Duffau , Dept. de Neurochirurgie, Hopital Gui de Chauliac, Montpellier, France
S. Parisot , Center for Visual Comput., Ecole Centrale de Paris, Paris, France
pp. 988-995

Robust non-rigid registration of 2D and 3D graphs (Abstract)

Pascal Fua , Comput. Vision Lab., EPFL, Lausanne, Switzerland
Francese Moreno-Noguer , Inst. de Robot. i Inforrnatica Ind., UPC, Barcelona, Spain
Jan Kybic , Fac. of Electr. Eng., CTU, Prague, Czech Republic
Przemyslaw Glowacki , Comput. Vision Lab., EPFL, Lausanne, Switzerland
Eduard Serradell , Inst. de Robot. i Inforrnatica Ind., UPC, Barcelona, Spain
pp. 996-1003

Learning to segment dense cell nuclei with shape prior (Abstract)

F. A. Hamprecht , HCI, Univ. of Heidelberg, Heidelberg, Germany
J. Wittbrodt , Dept. of Dev. Biol., Univ. of Heidelberg, Heidelberg, Germany
U. Koethe , HCI, Univ. of Heidelberg, Heidelberg, Germany
Xinghua Lou , HCI, Univ. of Heidelberg, Heidelberg, Germany
pp. 1012-1018

A Riemannian approach for estimating orientation distribution function (ODF) images from high-angular resolution diffusion imaging (HARDI) (Abstract)

H. Scharr , IBG-2: Plant Sci., Forschungszentrum Julich, Julich, Germany
K. Krajsek , IBG-2: Plant Sci., Forschungszentrum Julich, Julich, Germany
pp. 1019-1026

Sasaki metrics for analysis of longitudinal data on manifolds (Abstract)

P. T. Fletcher , Sch. of Comput., Univ. of Utah, Salt Lake City, UT, USA
P. Muralidharan , Sch. of Comput., Univ. of Utah, Salt Lake City, UT, USA
pp. 1027-1034

Globally optimal hand-eye calibration (Abstract)

L. Kruger , Daimler AG, Ulm, Germany
T. Pajdla , Czech Tech. Univ., Prague, Czech Republic
T. Ruland , Ulm Univ., Ulm, Germany
pp. 1035-1042

Real-time image-based 6-DOF localization in large-scale environments (Abstract)

M. Uyttendaele , Microsoft Res., Redmond, WA, USA
M. F. Cohen , Microsoft Res., Redmond, WA, USA
S. N. Sinha , Microsoft Res., Redmond, WA, USA
Hyon Lim , Seoul Nat. Univ., Seoul, South Korea
pp. 1043-1050

A new mirror-based extrinsic camera calibration using an orthogonality constraint (Abstract)

T. Matsuyama , Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan
S. Nobuhara , Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan
K. Takahashi , Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan
pp. 1051-1058

Online continuous stereo extrinsic parameter estimation (Abstract)

P. Rander , Nat. Robot. Eng. Center, Carnegie Mellon Univ., Pittsburgh, PA, USA
B. Browning , Nat. Robot. Eng. Center, Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Hansen , Comput. Sci. Dept., Carnegie Mellon Univ. in Qatar, Doha, Qatar
H. Alismail , Nat. Robot. Eng. Center, Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 1059-1066

Learning attention map from images (Abstract)

Xiangyang Xue , Sch. of Comput. Sci., Fudan Univ., Shanghai, China
Cheng Jin , Sch. of Comput. Sci., Fudan Univ., Shanghai, China
Wei Zhang , Sch. of Comput. Sci., Fudan Univ., Shanghai, China
Yao Lu , Sch. of Comput. Sci., Fudan Univ., Shanghai, China
pp. 1067-1074

A line-structure-preserving approach to image resizing (Abstract)

Yung-Yu Chuang , Nat. Taiwan Univ., Taipei, Taiwan
Che-Han Chang , Nat. Taiwan Univ., Taipei, Taiwan
pp. 1075-1082

Detecting texts of arbitrary orientations in natural images (Abstract)

Zhuowen Tu , Microsoft Res. Asia, Beijing, China
Yi Ma , Microsoft Res. Asia, Beijing, China
Wenyu Liu , Huazhong Univ. of Sci. & Technol., Wuhan, China
Xiang Bai , Huazhong Univ. of Sci. & Technol., Wuhan, China
Cong Yao , Huazhong Univ. of Sci. & Technol., Wuhan, China
pp. 1083-1090

Markov Weight Fields for face sketch synthesis (Abstract)

K. K. Wong , Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China
Zhanghui Kuang , Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China
Hao Zhou , Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China
pp. 1091-1097

Unsupervised feature learning framework for no-reference image quality assessment (Abstract)

D. Doermann , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Le Kang , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
J. Kumar , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Peng Ye , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
pp. 1098-1105

Multi-scale dictionary for single image super-resolution (Abstract)

Xuelong Li , Xi'an Inst. of Opt. & Precision Mech., Xi'an, China
Dacheng Tao , QCIS, Univ. of Technol., Sydney, NSW, Australia
Xinbo Gao , Sch. of E.E., Xidian Univ., Xi'an, China
Kaibing Zhang , Sch. of E.E., Xidian Univ., Xi'an, China
pp. 1114-1121

Image collection summarization via dictionary learning for sparse representation (Abstract)

Jianping Fan , Sch. of Inf. Sci. & Technol., Northwest Univ., Xi'an, China
Jinye Peng , Sch. of Inf. Sci. & Technol., Northwest Univ., Xi'an, China
Chunlei Yang , Dept. of Comput. Sci., Univ. of North Carolina, Charlotte, NC, USA
pp. 1122-1129

Icon scanning: Towards next generation QR codes (Abstract)

L. Zelnik-Manor , Technion - Israel Inst. of Technol., Haifa, Israel
I. Friedman , Technion - Israel Inst. of Technol., Haifa, Israel
pp. 1130-1137

Automated quantitative description of spiral galaxy arm-segment structure (Abstract)

W. B. Hayes , Univ. of California, Irvine, CA, USA
D. R. Davis , Univ. of California, Irvine, CA, USA
pp. 1138-1145

Sparse representation for blind image quality assessment (Abstract)

Dacheng Tao , Centre for Quantum Comput. & Intell. Syst., Univ. of Technol., Sydney, NSW, Australia
Lihuo He , Sch. of Electron. Eng., Xidian Univ., Xi'an, China
Xuelong Li , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xi'an, China
Xinbo Gao , Sch. of Electron. Eng., Xidian Univ., Xi'an, China
pp. 1146-1153

Fast axis estimation from a segment of rotationally symmetric object (Abstract)

D. B. Cooper , Lems, Brown Univ., Providence, RI, USA
Dongjin Han , ITRC, Soongsil Univ., Seoul, South Korea
Hern-soo Hahn , E.E., Soongsil Univ., Seoul, South Korea
pp. 1154-1161

Computer vision aided target linked radiation imaging (Abstract)

Tai-Peng Tian , GE Global Res., Niskayuna, NY, USA
B. Yanoff , GE Global Res., Niskayuna, NY, USA
W. Dixon , GE Global Res., Niskayuna, NY, USA
Li Guan , GE Global Res., Niskayuna, NY, USA
Bing Yu , GE Global Res., Niskayuna, NY, USA
Ting Yu , GE Global Res., Niskayuna, NY, USA
Feng Pan , GE Global Res., Niskayuna, NY, USA
Yi Yao , GE Global Res., Niskayuna, NY, USA
N. Krahnstoever , Google Inc., Cambridge, MA, USA
Dashan Gao , GE Global Res., Niskayuna, NY, USA
pp. 1162-1169

Classifying covert photographs (Abstract)

Haibin Ling , Dept. of Comput. & Inf. Sci., Temple Univ., Philadelphia, PA, USA
Haitao Lang , Dept. of Phys. & Electron., Beijing Univ. of Chem. Technol., Beijing, China
pp. 1178-1185

A database for fine grained activity detection of cooking activities (Abstract)

B. Schiele , Max Planck Inst. for Inf., Saarbrücken, Germany
M. Andriluka , Max Planck Inst. for Inf., Saarbrücken, Germany
S. Amin , Max Planck Inst. for Inf., Saarbrücken, Germany
M. Rohrbach , Max Planck Inst. for Inf., Saarbrücken, Germany
pp. 1194-1201

Evaluation of super-voxel methods for early video processing (Abstract)

J. J. Corso , Comput. Sci. & Eng., SUNY at Buffalo, Buffalo, NY, USA
Chenliang Xu , Comput. Sci. & Eng., SUNY at Buffalo, Buffalo, NY, USA
pp. 1202-1209

Scalable action recognition with a subspace forest (Abstract)

B. A. Draper , Colorado State Univ., Fort Collins, CO, USA
S. O'Hara , Colorado State Univ., Fort Collins, CO, USA
pp. 1210-1217

A flow model for joint action recognition and identity maintenance (Abstract)

L. S. Davis , Univ. of Maryland, College Park, MD, USA
V. I. Morariu , Univ. of Maryland, College Park, MD, USA
S. Khamis , Univ. of Maryland, College Park, MD, USA
pp. 1218-1225

Action bank: A high-level representation of activity in video (Abstract)

J. J. Corso , Comput. Sci. & Eng., SUNY at Buffalo, Buffalo, NY, USA
S. Sadanand , Comput. Sci. & Eng., SUNY at Buffalo, Buffalo, NY, USA
pp. 1234-1241

Detecting regions of interest in dynamic scenes with camera motions (Abstract)

I. Essa , Georgia Inst. of Technol., Atlanta, GA, USA
Dongryeol Lee , Georgia Inst. of Technol., Atlanta, GA, USA
Kihwan Kim , Georgia Inst. of Technol., Atlanta, GA, USA
pp. 1258-1265

A unified framework for event summarization and rare event detection (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Junseok Kwon , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 1266-1273

Efficient activity detection with max-subgraph search (Abstract)

K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
Chao-Yeh Chen , Univ. of Texas at Austin, Austin, TX, USA
pp. 1274-1281

Multimodal feature fusion for robust event detection in web videos (Abstract)

P. Natarajan , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
R. Prasad , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
Unsang Park , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
S. Tsakalidis , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
Xiaodan Zhuang , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
S. Vitaladevuni , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
Shuang Wu , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
P. Natarajan , Speech, Language & Multimedia Bus. Unit, Raytheon BBN Technol., Cambridge, MA, USA
pp. 1298-1305

Dynamic scene understanding: The role of orientation features in space and time in scene classification (Abstract)

R. P. Wildes , Dept. of Comput. Sci. & Eng., York Univ., Toronto, ON, Canada
K. Daniilidis , GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
M. Lecce , GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
K. G. Derpanis , GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 1306-1313

Sum-product networks for modeling activities with stochastic structure (Abstract)

S. Todorovic , Oregon State Univ., Corvallis, OR, USA
M. R. Amer , Oregon State Univ., Corvallis, OR, USA
pp. 1314-1321

Social behavior recognition in continuous video (Abstract)

D. J. Anderson , California Inst. of Technol., Pasadena, CA, USA
Dayu Lin , Med. Center, NYU, New York, NY, USA
P. Dollar , Microsoft Res., Redmond, WA, USA
X. P. Burgos-Artizzu , California Inst. of Technol., Pasadena, CA, USA
P. Perona , California Inst. of Technol., Pasadena, CA, USA
pp. 1322-1329

Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach (Abstract)

Shih-Fu Chang , Columbia Univ., New York, NY, USA
Dong Xu , Nanyang Technol. Univ., Singapore, Singapore
Lixin Duan , Nanyang Technol. Univ., Singapore, Singapore
pp. 1338-1345

Discovering important people and objects for egocentric video summarization (Abstract)

J. Ghosh , Univ. of Texas at Austin, Austin, TX, USA
Yong Jae Lee , Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
pp. 1346-1353

Social roles in hierarchical models for human activity recognition (Abstract)

G. Mori , Simon Fraser Univ., Burnaby, BC, Canada
L. Sigal , Disney Res., Pittsburgh, PA, USA
Tian Lan , Simon Fraser Univ., Burnaby, BC, Canada
pp. 1354-1361

Cross-view activity recognition using Hankelets (Abstract)

M. Sznaier , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
O. I. Camps , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
Binlong Li , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
pp. 1362-1369

Action recognition by exploring data distribution and feature correlation (Abstract)

A. G. Hauptmann , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Chaoyi Pang , Australian e-Health Res. Centre, CSIRO, Brisbane, QLD, Australia
Xue Li , Sch. of ITEE, Univ. of Queensland, Brisbane, QLD, Australia
Zhigang Ma , Dept. of Inf. Eng. & Comput. Sci., Univ. of Trento, Trento, Italy
Yi Yang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Sen Wang , Sch. of ITEE, Univ. of Queensland, Brisbane, QLD, Australia
pp. 1370-1377

General trajectory prior for Non-Rigid reconstruction (Abstract)

S. Lucey , Commonwealth Sci. & Ind. Res. Organ., Brisbane, QLD, Australia
J. Valmadre , Queensland Univ. of Technol., Brisbane, QLD, Australia
pp. 1394-1401

A non-local cost aggregation method for stereo matching (Abstract)

Qingxiong Yang , City Univ. of Hong Kong, Hong Kong, China
pp. 1402-1409

Practical low-rank matrix approximation under robust L1-norm (Abstract)

M. Okutomi , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
Shuicheng Yan , Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
S. Sugimoto , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
Guangcan Liu , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Yinqiang Zheng , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
pp. 1410-1417

Finite Element based sequential Bayesian Non-Rigid Structure from Motion (Abstract)

J. M. M. Montiel , Inst. de Investig. en Ing. de Aragon (I3A), Univ. de Zaragoza, Zaragoza, Spain
B. Calvo , Inst. de Investig. en Ing. de Aragon (I3A), Univ. de Zaragoza, Zaragoza, Spain
A. Agudo , Inst. de Investig. en Ing. de Aragon (I3A), Univ. de Zaragoza, Zaragoza, Spain
pp. 1418-1425

Rolling shutter bundle adjustment (Abstract)

E. Ringaby , Dept. of Electr. Eng., Linkoping Univ., Linkoping, Sweden
M. Felsberg , Dept. of Electr. Eng., Linkoping Univ., Linkoping, Sweden
J. Hedborg , Dept. of Electr. Eng., Linkoping Univ., Linkoping, Sweden
P-E Forssen , Dept. of Electr. Eng., Linkoping Univ., Linkoping, Sweden
pp. 1434-1441

Visibility Based Preconditioning for bundle adjustment (Abstract)

A. Kushal , Univ. of Washington, Seattle, WA, USA
pp. 1442-1449

Dense reconstruction on-the-fly (Abstract)

H. Bischof , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
T. Pock , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
G. Graber , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Maurer , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
A. Wendel , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
pp. 1450-1457

Seeing double without confusion: Structure-from-motion in highly ambiguous scenes (Abstract)

Loong-Fah Cheong , Nat. Univ. of Singapore, Singapore, Singapore
Ping Tan , Nat. Univ. of Singapore, Singapore, Singapore
Nianjuan Jiang , Nat. Univ. of Singapore, Singapore, Singapore
pp. 1458-1465

Saliency-guided integration of multiple scans (Abstract)

P. L. Rosin , Dept. of Comput. Sci. & Inf., Cardiff Univ., Cardiff, UK
R. R. Martin , Dept. of Comput. Sci. & Inf., Cardiff Univ., Cardiff, UK
Yonghuai Liu , Dept. of Comput. Sci., Aberystwyth Univ., Aberystwyth, UK
Ran Song , Dept. of Comput. Sci., Aberystwyth Univ., Aberystwyth, UK
pp. 1474-1481

Schematic surface reconstruction (Abstract)

S. M. Seitz , Univ. of Washington, Seattle, WA, USA
B. Curless , Univ. of Washington, Seattle, WA, USA
S. Agarwal , Univ. of Washington, Seattle, WA, USA
Changchang Wu , Univ. of Washington, Seattle, WA, USA
pp. 1498-1505

Making minimal solvers fast (Abstract)

T. Pajdla , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
Z. Kukelova , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
pp. 1506-1513

Discovering and exploiting 3D symmetries in structure from motion (Abstract)

M. Pollefeys , ETH Zurich, Zurich, Switzerland
S. N. Sinha , Microsoft Res., Redmond, WA, USA
C. Zach , Microsoft Res., Cambridge, UK
A. Cohen , ETH Zurich, Zurich, Switzerland
pp. 1514-1521

On SIFTs and their scales (Abstract)

V. Mayzels , Technion - Israel Inst. of Technol., Haifa, Israel
T. Hassner , Open Univ. of Israel, Ra'anana, Israel
L. Zelnik-Manor , Technion - Israel Inst. of Technol., Haifa, Israel
pp. 1522-1528

Real-time 6D stereo Visual Odometry with non-overlapping fields of view (Abstract)

M. Pollefeys , Comput. Vision & Geometry Group, ETH Zurich, Zurich, Switzerland
J. Nikolic , Autonomous Syst. Lab., ETH Zurich, Zurich, Switzerland
L. Kneip , Autonomous Syst. Lab., ETH Zurich, Zurich, Switzerland
T. Kazik , Autonomous Syst. Lab., ETH Zurich, Zurich, Switzerland
R. Siegwart , Autonomous Syst. Lab., ETH Zurich, Zurich, Switzerland
pp. 1529-1536

Video from nearly still: An application to low frame-rate gait recognition (Abstract)

Y. Yagi , Inst. of Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
Y. Makihara , Inst. of Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
N. Akae , Inst. of Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
A. Mansur , Inst. of Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
pp. 1537-1543

We are not contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video (Abstract)

J. Odobez , Idiap Res. Inst., Martigny, Switzerland
Cheng Chen , Idiap Res. Inst., Martigny, Switzerland
pp. 1544-1551

What are we looking for: Towards statistical modeling of saccadic eye movements and visual saliency (Abstract)

Rongrong Ji , Dept. of Comput. Sci., Harbin Inst. of Technol., Harbin, China
Hongxun Yao , Dept. of Comput. Sci., Harbin Inst. of Technol., Harbin, China
Xiaoshuai Sun , Dept. of Comput. Sci., Harbin Inst. of Technol., Harbin, China
pp. 1552-1559

Stream-based joint exploration-exploitation active learning (Abstract)

Shaogang Gong , Sch. of EECS, Queen Mary Univ. of London, London, UK
Tao Xiang , Sch. of EECS, Queen Mary Univ. of London, London, UK
T. M. Hospedales , Sch. of EECS, Queen Mary Univ. of London, London, UK
C. C. Loy , Vision Semantics Ltd., UK
pp. 1560-1567

Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video (Abstract)

L. Balzano , Univ. of Wisconsin, Madison, WI, USA
A. Szlam , City Univ. of New York, New York, NY, USA
Jun He , Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
pp. 1568-1575

Curvature-based regularization for surface approximation (Abstract)

Y. Boykov , Dept. of Comput. Sci., Univ. of Western Ontario, London, ON, Canada
C. Olsson , Centre for Math. Sci., Lund Univ., Lund, Sweden
pp. 1576-1583

General and nested Wiberg minimization (Abstract)

D. Strelow , Google, Mountain View, CA, USA
pp. 1584-1591

A-Optimal Non-negative Projection for image representation (Abstract)

Zhaohui Wu , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Zheng Yang , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Haifeng Liu , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Xuelong Li , State Key Lab. of Transient Opt. & Photonics, Center for Opt. IMagery Anal. & Learning (OPTIMAL), Xi'an, China
pp. 1592-1599

A branch-and-bound algorithm for globally optimal hand-eye calibration (Abstract)

T. Pajdla , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
J. Heller , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
M. Havlena , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
pp. 1608-1615

An efficient branch-and-bound algorithm for optimal human pose estimation (Abstract)

S. Savarese , Dept. of EECS, Univ. of Michigan, Ann Arbor, MI, USA
Honglak Lee , Dept. of EECS, Univ. of Michigan, Ann Arbor, MI, USA
M. Telaprolu , Dept. of EECS, Univ. of Michigan, Ann Arbor, MI, USA
Min Sun , Dept. of EECS, Univ. of Michigan, Ann Arbor, MI, USA
pp. 1616-1623

Isogeometric finite-elements methods and variational reconstruction tasks in vision — A perfect match (Abstract)

T. Morwald , Vienna Univ. of Technol., Vienna, Austria
J. Balzer , Univ. of California, Los Angeles, CA, USA
pp. 1624-1631

Irregular lattices for complex shape grammar facade parsing (Abstract)

H. Riemenschneider , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
U. Krispel , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
W. Thaller , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
M. Donoser , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
S. Havemann , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
D. Fellner , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
H. Bischof , Inst. for Comput. Graphics & Vision & Comput. Graphics & Knowledge Visualization, Graz Univ. of Technol., Graz, Austria
pp. 1640-1647

Geometry constrained sparse coding for single image super-resolution (Abstract)

Xiaoqiang Lu , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xian, China
Haoliang Yuan , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xian, China
Pingkun Yan , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xian, China
Yuan Yuan , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xian, China
Xuelong Li , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xian, China
pp. 1648-1655

Random walks based multi-image segmentation: Quasiconvexity results and GPU-based solutions (Abstract)

L. Grady , Siemens Corp. Res., Princeton, NJ, USA
Jia Xu , Univ. of Wisconsin-Madison, Madison, WI, USA
V. Singh , Univ. of Wisconsin-Madison, Madison, WI, USA
M. D. Collins , Univ. of Wisconsin-Madison, Madison, WI, USA
pp. 1656-1663

What is optimized in tight convex relaxations for multi-label problems? (Abstract)

M. Pollefeys , ETH Zurich, Zurich, Switzerland
C. Hane , ETH Zurich, Zurich, Switzerland
C. Zach , Microsoft Res. Cambridge, Cambridge, UK
pp. 1664-1671

Robust Maximum Likelihood estimation by sparse bundle adjustment using the L1 norm (Abstract)

Hongan Wang , Intell. Eng. Lab., Inst. of Software, Beijing, China
Fengjun Zhang , Intell. Eng. Lab., Inst. of Software, Beijing, China
Zhijun Dai , Intell. Eng. Lab., Inst. of Software, Beijing, China
pp. 1672-1679

Application of the mean field methods to MRF optimization in computer vision (Abstract)

K. Deguchi , Tohoku Univ., Sendai, Japan
T. Okatani , Tohoku Univ., Sendai, Japan
M. Saito , Tohoku Univ., Sendai, Japan
pp. 1680-1687

A bundle approach to efficient MAP-inference by Lagrangian relaxation (Abstract)

C. Schnorr , IPA, Heidelberg Univ., Heidelberg, Germany
B. Savchynskyy , HCI, Heidelberg Univ., Heidelberg, Germany
J. H. Kappes , IPA, Heidelberg Univ., Heidelberg, Germany
pp. 1688-1695

MAP-MRF inference based on extended junction tree representation (Abstract)

Jiang-Zhong Cao , Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
Pei Chen , Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
Yun Zheng , Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
pp. 1696-1703

Fast algorithms for structured robust principal component analysis (Abstract)

O. I. Camps , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
M. Sznaier , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
M. Ayazoglu , Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
pp. 1704-1711

A convex representation for the vectorial Mumford-Shah functional (Abstract)

D. Cremers , Tech. Univ. Munich, Munich, Germany
A. Chambolle , Ecole Polytech., Paris, France
E. Strekalovskiy , Tech. Univ. Munich, Munich, Germany
pp. 1712-1719

Parsing façade with rank-one approximation (Abstract)

Chiew-Lan Tai , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Long Quan , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Tian Han , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
Chao Yang , Hong Kong Univ. of Sci. & Technol., Hong Kong, China
pp. 1720-1727

Fast dynamic programming for labeling problems with ordering constraints (Abstract)

Xiaodong Wu , Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
O. Veksler , Comput. Sci. Dept., Univ. of Western Ontario, London, ON, Canada
Qi Song , Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Junjie Bai , Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
pp. 1728-1735

Seeing through the blur (Abstract)

Yi Ma , ECE Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
C. L. Zitnick , Interactive Visual Media Group, Microsoft Res., Redmond, WA, USA
H. Mobahi , CS Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 1736-1743

Multitarget data association with higher-order motion models (Abstract)

R. T. Collins , Pennsylvania State Univ., University Park, PA, USA
pp. 1744-1751

Optical flow in the presence of spatially-varying motion blur (Abstract)

Li Zhang , Univ. of Wisconsin - Madison, Madison, WI, USA
T. Portz , Univ. of Wisconsin - Madison, Madison, WI, USA
Hongrui Jiang , Univ. of Wisconsin - Madison, Madison, WI, USA
pp. 1752-1759

Non-sparse linear representations for visual tracking with online reservoir metric learning (Abstract)

A. van den Hengel , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
A. Dick , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
Qinfeng Shi , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
Chunhua Shen , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
Xi Li , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
pp. 1760-1767

Layered segmentation and optical flow estimation over time (Abstract)

M. J. Black , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
E. B. Sudderth , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
Deqing Sun , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
pp. 1768-1775

Decomposing and regularizing sparse/non-sparse components for motion field estimation (Abstract)

Ying Wu , EECS Dept., Northwestern Univ., Evanston, IL, USA
Jiang Wang , EECS Dept., Northwestern Univ., Evanston, IL, USA
Zhuoyuan Chen , EECS Dept., Northwestern Univ., Evanston, IL, USA
pp. 1776-1783

Dense Lagrangian motion estimation with occlusions (Abstract)

C. Tomasi , Duke Univ., Durham, NC, USA
S. Ricco , Duke Univ., Durham, NC, USA
pp. 1800-1807

Online robust image alignment via iterative convex optimization (Abstract)

Yi Wu , Comput. & Inf. Sci. Dept., Temple Univ., Philadelphia, PA, USA
Bin Shen , Dept. of Comput. Sci., Purdue Univ., West Lafayette, IN, USA
Haibin Ling , Comput. & Inf. Sci. Dept., Temple Univ., Philadelphia, PA, USA
pp. 1808-1814

Visual tracking via adaptive structural local sparse appearance model (Abstract)

Huchuan Lu , Dalian Univ. of Technol., Dalian, China
Xu Jia , Dalian Univ. of Technol., Dalian, China
Ming-Hsuan Yang , Univ. of California at Merced, Merced, CA, USA
pp. 1822-1829

Real time robust L1 tracker using accelerated proximal gradient approach (Abstract)

Hui Ji , Dept. of Math., Nat. Univ. of Singapore, Singapore, Singapore
Haibin Ling , Dept. of Comput. & Inf. Sci., Temple Univ., Philadelphia, PA, USA
Yi Wu , Dept. of Comput. & Inf. Sci., Temple Univ., Philadelphia, PA, USA
Chenglong Bao , Dept. of Math., Nat. Univ. of Singapore, Singapore, Singapore
pp. 1830-1837

Robust object tracking via sparsity-based collaborative model (Abstract)

Ming-Hsuan Yang , Univ. of California at Merced, Merced, CA, USA
pp. 1838-1845

Video segmentation by tracing discontinuities in a trajectory embedding (Abstract)

Jianbo Shi , Univ. of Pennsylvania, Philadelphia, PA, USA
Geng Zhang , Xi'an Jiaotong Univ., Xi'an, China
K. Fragkiadaki , Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 1846-1853

Robust tracking via weakly supervised ranking SVM (Abstract)

Yancheng Bai , Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Ming Tang , Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
pp. 1854-1861

Tracking the articulated motion of two strongly interacting hands (Abstract)

A. A. Argyros , Inst. of Comput. Sci., FORTH, Heraklion, Greece
N. Kyriazis , Inst. of Comput. Sci., FORTH, Heraklion, Greece
I. Oikonomidis , Inst. of Comput. Sci., FORTH, Heraklion, Greece
pp. 1862-1869

Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling (Abstract)

H. Bischof , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
T. Pock , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Werlberger , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Unger , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
pp. 1878-1885

Decentralized particle filter for joint individual-group tracking (Abstract)

V. Murino , Univ. of Verona, Verona, Italy
M. Cristani , Univ. of Verona, Verona, Italy
L. Bazzani , Univ. of Verona, Verona, Italy
pp. 1886-1893

Efficient online structured output learning for keypoint-based object tracking (Abstract)

P. H. S. Torr , Oxford Brookes Univ., Oxford, UK
A. Saffari , Oxford Brookes Univ., Oxford, UK
S. Hare , Oxford Brookes Univ., Oxford, UK
pp. 1894-1901

Distribution fields for tracking (Abstract)

E. Learned-Miller , Univ. of Massachusetts Amherst, Amherst, MA, USA
L. Sevilla-Lara , Univ. of Massachusetts Amherst, Amherst, MA, USA
pp. 1910-1917

Multi-target tracking by online learning of non-linear motion patterns and robust appearance models (Abstract)

Bo Yang , 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
pp. 1918-1925

An optimized DBN-based mode-focussing particle filter (Abstract)

C. Gonzales , Lab. d'Inf. de Paris 6, Univ. Pierre et Marie Curie, Paris, France
S. Dubuisson , Lab. d'Inf. de Paris 6, Univ. Pierre et Marie Curie, Paris, France
pp. 1934-1939

Locally Orderless Tracking (Abstract)

S. Avidan , Tel Aviv Univ., Tel Aviv, Israel
D. Levi , Gen. Motors Adv. Tech. Center, Herzliya, Israel
A. Bar-Hillel , Gen. Motors Adv. Tech. Center, Herzliya, Israel
S. Oron , Tel Aviv Univ., Tel Aviv, Israel
pp. 1940-1947

Coupling detection and data association for multiple object tracking (Abstract)

M. Betke , Depts. of Comput. Sci., Boston Univ., Boston, MA, USA
S. Sclaroff , Depts. of Comput. Sci., Boston Univ., Boston, MA, USA
A. Thangali , Depts. of Comput. Sci., Boston Univ., Boston, MA, USA
Zheng Wu , Depts. of Comput. Sci., Boston Univ., Boston, MA, USA
pp. 1948-1955

Order determination and sparsity-regularized metric learning adaptive visual tracking (Abstract)

Ying Wu , Northwestern Univ., Evanston, IL, USA
Wenyu Liu , Huazhong Univ. of Sci. & Tech., Wuhan, China
Nan Jiang , Huazhong Univ. of Sci. & Tech., Wuhan, China
pp. 1956-1963

Robust visual tracking using autoregressive hidden Markov Model (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Junseok Kwon , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Dong Woo Park , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 1964-1971

Improving multi-target tracking via social grouping (Abstract)

C. R. Shelton , Univ. of California, Riverside, CA, USA
Zhen Qin , Univ. of California, Riverside, CA, USA
pp. 1972-1978

Growing a bag of systems tree for fast and accurate classification (Abstract)

G. R. G. Lanckriet , Dept. of ECE, Univ. of California, San Diego, CA, USA
A. B. Chan , Dept. of CS, City Univ. of Hong Kong, Hong Kong, China
A. Mumtaz , Dept. of CS, City Univ. of Hong Kong, Hong Kong, China
E. Coviello , Dept. of ECE, Univ. of California, San Diego, CA, USA
pp. 1979-1986

Branch-and-price global optimization for multi-view multi-target tracking (Abstract)

B. Rosenhahn , Inst. for Inf. Process. (TNT), Leibniz Univ., Hannover, Germany
G. Pons-Moll , Inst. for Inf. Process. (TNT), Leibniz Univ., Hannover, Germany
Laura Leal-Taixe , Inst. for Inf. Process. (TNT), Leibniz Univ., Hannover, Germany
pp. 1987-1994

A contextual maximum likelihood framework for modeling image registration (Abstract)

N. Navab , Comput. Aided Med. Procedures, Tech. Univ. Munchen, Garching, Germany
C. Wachinger , Comput. Aided Med. Procedures, Tech. Univ. Munchen, Garching, Germany
pp. 1995-2002

Monotonicity and error type differentiability in performance measures for target detection and tracking in video (Abstract)

E. Krupka , Adv. Technol. Labs. Israel, Microsoft Res., Herzelia, Israel
I. Leichter , Adv. Technol. Labs. Israel, Microsoft Res., Herzelia, Israel
pp. 2003-2009

Generalizing Wiberg algorithm for rigid and nonrigid factorizations with missing components and metric constraints (Abstract)

M. Okutomi , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
Shuicheng Yan , Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
S. Sugimoto , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
Yinqiang Zheng , Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan
pp. 2010-2017

A simple prior-free method for non-rigid structure-from-motion factorization (Abstract)

Mingyi He , Northwestern Polytech. Univ., Xi'an, China
Hongdong Li , Australian Nat. Univ., Canberra, ACT, Australia
Yuchao Dai , Northwestern Polytech. Univ., Xi'an, China
pp. 2018-2025

On template-based reconstruction from a single view: Analytical solutions and proofs of well-posedness for developable, isometric and conformal surfaces (Abstract)

T. Collins , ISIT, Univ. d'Auvergne, Clermont-Ferrand, France
F. Chadebecq , ISIT, Univ. d'Auvergne, Clermont-Ferrand, France
Y. Gerard , ISIT, Univ. d'Auvergne, Clermont-Ferrand, France
A. Bartoli , ISIT, Univ. d'Auvergne, Clermont-Ferrand, France
pp. 2026-2033

An online learned CRF model for multi-target tracking (Abstract)

R. Nevatia , Inst. for Robot. & Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
Bo Yang , Inst. for Robot. & Intell. Syst., Univ. of Southern California, Los Angeles, CA, USA
pp. 2034-2041

Robust visual tracking via multi-task sparse learning (Abstract)

N. Ahuja , Adv. Digital Sci. Center of Illinois, Singapore, Singapore
Si Liu , Inst. of Autom., Beijing, China
B. Ghanem , Adv. Digital Sci. Center of Illinois, Singapore, Singapore
Tianzhu Zhang , Adv. Digital Sci. Center of Illinois, Singapore, Singapore
pp. 2042-2049

Learning rotation-aware features: From invariant priors to equivariant descriptors (Abstract)

S. Roth , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
U. Schmidt , Dept. of Comput. Sci., Tech. Univ. Darmstadt, Darmstadt, Germany
pp. 2050-2057

Geodesic flow kernel for unsupervised domain adaptation (Abstract)

Fei Sha , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
Yuan Shi , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
Boqing Gong , Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
K. Grauman , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
pp. 2066-2073

Supervised hashing with kernels (Abstract)

Shih-Fu Chang , Electr. Eng. Dept., Columbia Univ., New York, NY, USA
Yu-Gang Jiang , Sch. of Comput. Sci., Fudan Univ., Shanghai, China
Rongrong Ji , Electr. Eng. Dept., Columbia Univ., New York, NY, USA
Jun Wang , T.J. Watson Res. Center, IBM, Yorktown Heights, NY, USA
Wei Liu , Electr. Eng. Dept., Columbia Univ., New York, NY, USA
pp. 2074-2081

Online content-aware video condensation (Abstract)

Dong Yi , Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Zhen Lei , Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Shikun Feng , Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
S. Z. Li , Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
pp. 2082-2087

Active attentional sampling for speed-up of background subtraction (Abstract)

Jin Young Choi , Perception & Intell. Lab., Seoul Nat. Univ., Seoul, South Korea
Hawook Jeong , Perception & Intell. Lab., Seoul Nat. Univ., Seoul, South Korea
Hyung Jin Chang , Perception & Intell. Lab., Seoul Nat. Univ., Seoul, South Korea
pp. 2088-2095

Bridging the past, present and future: Modeling scene activities from event relationships and global rules (Abstract)

J. Odobez , Idiap Res. Inst., Martigny, Switzerland
R. Emonet , Idiap Res. Inst., Martigny, Switzerland
J. Varadarajan , Idiap Res. Inst., Martigny, Switzerland
pp. 2096-2103

Background modeling using adaptive pixelwise kernel variances in a hybrid feature space (Abstract)

E. Learned-Miller , Univ. of Massachusetts, Amherst, MA, USA
A. Hanson , Univ. of Massachusetts, Amherst, MA, USA
M. Narayana , Univ. of Massachusetts, Amherst, MA, USA
pp. 2104-2111

Video anomaly detection based on local statistical aggregates (Abstract)

Zhu Chen , Dept. of Electr. & Comput. Eng., Boston Univ., Boston, MA, USA
V. Saligrama , Dept. of Electr. & Comput. Eng., Boston Univ., Boston, MA, USA
pp. 2112-2119

Sharing features in multi-class boosting via group sparsity (Abstract)

A. van den Hengel , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
S. Paisitkriangkrai , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
C. Shen , Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
pp. 2128-2135

Power SVM: Generalization with exemplar classification uncertainty (Abstract)

Shang-Hua Teng , Univ. of Southern California, Los Angeles, CA, USA
S. X. Yu , ICSI, UC Berkeley, Berkeley, CA, USA
Weiyu Zhang , Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 2144-2151

Active image clustering: Seeking constraints from humans to complement algorithms (Abstract)

D. Jacobs , Comput. Sci. Dept., Univ. of Maryland, College Park, MD, USA
A. Biswas , Comput. Sci. Dept., Univ. of Maryland, College Park, MD, USA
pp. 2152-2159

Generalized Multiview Analysis: A discriminative latent space (Abstract)

D. W. Jacobs , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
H. Daume , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
A. Kumar , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
A. Sharma , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
pp. 2160-2167

Robust visual domain adaptation with low-rank reconstruction (Abstract)

Shih-Fu Chang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
D. T. Lee , Dept. of CSIE, Nat. Taiwan Univ., Taipei, Taiwan
Dong Liu , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
I-Hong Jhuo , Dept. of CSIE, Nat. Taiwan Univ., Taipei, Taiwan
pp. 2168-2175

Image categorization using Fisher kernels of non-iid image models (Abstract)

C. Schmid , LEAR, INRIA Grenoble, Grenoble, France
J. Verbeek , LEAR, INRIA Grenoble, Grenoble, France
R. G. Cinbis , LEAR, INRIA Grenoble, Grenoble, France
pp. 2184-2191

Matrix completion by Truncated Nuclear Norm Regularization (Abstract)

Xuelong Li , State Key Lab. of Transient Opt. & Photonics, Xi'an Inst. of Opt. & Precision Mech., Xi'an, China
Jieping Ye , Arizona Univ. Tempe, Tempe, AZ, USA
Yao Hu , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Debing Zhang , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Xiaofei He , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
pp. 2192-2199

Sign Language Recognition using Sequential Pattern Trees (Abstract)

R. Bowden , Centre for Vision, Speech & Signal Process., Univ. of Surrey, Guildford, UK
N. Pugeault , Centre for Vision, Speech & Signal Process., Univ. of Surrey, Guildford, UK
H. Cooper , Centre for Vision, Speech & Signal Process., Univ. of Surrey, Guildford, UK
Eng-Jon Ong , Centre for Vision, Speech & Signal Process., Univ. of Surrey, Guildford, UK
pp. 2200-2207

Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (Abstract)

Quan Pan , Northwestern Polytech. Univ., Xi'an, China
Yan Liang , Northwestern Polytech. Univ., Xi'an, China
Lei Zhang , Hong Kong Polytech. Univ., Hong Kong, China
Shenlong Wang , Northwestern Polytech. Univ., Xi'an, China
pp. 2216-2223

Relaxed collaborative representation for pattern classification (Abstract)

Shenlong Wang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
D. Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Lei Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Meng Yang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
pp. 2224-2231

Efficient discriminative learning of parametric nearest neighbor classifiers (Abstract)

P. H. S. Torr , Oxford Brookes Univ., Oxford, UK
N. Crook , Oxford Brookes Univ., Oxford, UK
S. Sengupta , Oxford Brookes Univ., Oxford, UK
P. Sturgess , Oxford Brookes Univ., Oxford, UK
Ziming Zhang , Oxford Brookes Univ., Oxford, UK
pp. 2232-2239

Multi-feature metric learning with knowledge transfer among semantics and social tagging (Abstract)

Qi Tian , Dept. of Comput. Sci., Univ. of Texas at San Antonio, San Antonio, TX, USA
Qingming Huang , Key Lab. of Intell. Inf. Process, Inst. of Comput. Tech., Beijing, China
Shuqiang Jiang , Key Lab. of Intell. Inf. Process, Inst. of Comput. Tech., Beijing, China
Shuhui Wang , Key Lab. of Intell. Inf. Process, Inst. of Comput. Tech., Beijing, China
pp. 2240-2247

A constrained latent variable model (Abstract)

R. Urtasun , Toyota Technol. Inst. at Chicago, Chicago, IL, USA
P. Fua , CVLab, Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
M. Salzmann , NICTA, Canberra, ACT, Australia
A. Varol , CVLab, Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
pp. 2248-2255

Nonparametric learning for layered segmentation of natural images (Abstract)

E. B. Sudderth , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
S. Ghosh , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
pp. 2272-2279

Large scale metric learning from equivalence constraints (Abstract)

P. M. Roth , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
P. Wohlhart , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Hirzer , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Kostinger , 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. 2288-2295

Top-down visual saliency via joint CRF and dictionary learning (Abstract)

Ming-Hsuan Yang , Univ. of California at Merced, Merced, CA, USA
Jimei Yang , Univ. of California at Merced, Merced, CA, USA
pp. 2296-2303

Complex loss optimization via dual decomposition (Abstract)

G. Mori , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
A. Vahdat , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
M. Ranjbar , Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
pp. 2304-2311

Sparse kernel approximations for efficient classification and detection (Abstract)

A. Zisserman , Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
A. Vedaldi , Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
pp. 2320-2327

Non-negative low rank and sparse graph for semi-supervised learning (Abstract)

Xin Zhang , Dept. of Comput. Sci. & Tech., Tsinghua Univ., Beijing, China
Yi Ma , Microsoft Res. Asia, Beijing, China
Zhouchen Lin , Microsoft Res. Asia, Beijing, China
Haoyuan Gao , MOE-Microsoft Key Lab., Univ. of Sci. & Technol. of China, Hefei, China
Liansheng Zhuang , MOE-Microsoft Key Lab., Univ. of Sci. & Technol. of China, Hefei, China
Nenghai Yu , MOE-Microsoft Key Lab., Univ. of Sci. & Technol. of China, Hefei, China
pp. 2328-2335

Learning 3D object templates by hierarchical quantization of geometry and appearance spaces (Abstract)

Wenze Hu , Dept. of Stat., UCLA, Los Angeles, CA, USA
pp. 2336-2343

Power mean SVM for large scale visual classification (Abstract)

Jianxin Wu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
pp. 2344-2351

Multi-label ReliefF and F-statistic feature selections for image annotation (Abstract)

Heng Huang , Dept. of CSE, Univ. of Texas at Arlington, Arlington, TX, USA
C. Ding , Dept. of CSE, Univ. of Texas at Arlington, Arlington, TX, USA
Deguang Kong , Dept. of CSE, Univ. of Texas at Arlington, Arlington, TX, USA
Haifeng Zhao , Sch. of CSE, Anhui Univ., Hefei, China
pp. 2352-2359

Bilevel sparse coding for coupled feature spaces (Abstract)

T. Huang , Beckman Inst., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Zhe Lin , Adobe Syst. Inc., San Jose, CA, USA
Xianbiao Shu , Beckman Inst., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Zhaowen Wang , 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. 2360-2367

Batch mode Adaptive Multiple Instance Learning for computer vision tasks (Abstract)

Dong Xu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
I. W. Tsang , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Lixin Duan , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Wen Li , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
pp. 2368-2375

A regularized spectral algorithm for Hidden Markov Models with applications in computer vision (Abstract)

V. Murino , Ist. Italiano di Tecnol. (IIT), Genoa, Italy
A. Perina , Microsoft Res., Redmond, WA, USA
M. Cristani , Ist. Italiano di Tecnol. (IIT), Genoa, Italy
Ha Quang Minh , Ist. Italiano di Tecnol. (IIT), Genoa, Italy
pp. 2384-2391

Image denoising: Can plain neural networks compete with BM3D? (Abstract)

S. Harmeling , Max Planck Inst. for Intell. Syst., Tubingen, Germany
C. J. Schuler , Max Planck Inst. for Intell. Syst., Tubingen, Germany
H. C. Burger , Max Planck Inst. for Intell. Syst., Tubingen, Germany
pp. 2392-2399

AVA: A large-scale database for aesthetic visual analysis (Abstract)

F. Perronnin , Xerox Res. Centre Eur., Meylan, France
L. Marchesotti , Xerox Res. Centre Eur., Meylan, France
N. Murray , Comput. Vision Center, Univ. Autonoma de Barcelona, Barcelona, Spain
pp. 2408-2415

Learning structural element patch models with hierarchical palettes (Abstract)

Inmar Givoni , Univ. of Toronto, Toronto, ON, Canada
Jeroen Chua , Univ. of Toronto, Toronto, ON, Canada
Ryan Adams , Harvard Univ., Cambridge, MA, USA
Brendan Frey , Univ. of Toronto, Toronto, ON, Canada
pp. 2416-2423

Revisiting uncertainty in graph cut solutions (Abstract)

R. P. Adams , Sch. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA
D. Tarlow , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
pp. 2440-2447

Boosting algorithms for simultaneous feature extraction and selection (Abstract)

N. Vasconcelos , Dept. of Electr. & Comput. Eng., Univ. of California, San Diego, CA, USA
M. J. Saberian , Dept. of Electr. & Comput. Eng., Univ. of California, San Diego, CA, USA
pp. 2448-2455

Iterative Nearest Neighbors for classification and dimensionality reduction (Abstract)

L. Van Gool , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
R. Timofte , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
pp. 2456-2463

Robust Non-negative Graph Embedding: Towards noisy data, unreliable graphs, and noisy labels (Abstract)

Meng Wang , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
Shuicheng Yan , Electr. Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Zheng-Jun Zha , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
Hanwang Zhang , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
Tat-Seng Chua , Sch. of Comput., Nat. Univ. of Singapore, Singapore, Singapore
pp. 2464-2471

Hierarchical face parsing via deep learning (Abstract)

Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Xiaogang Wang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Ping Luo , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 2480-2487

Discriminately decreasing discriminability with learned image filters (Abstract)

J. Movellan , Machine Perception Lab., Univ. of California, San Diego, CA, USA
J. Whitehill , Machine Perception Lab., Univ. of California, San Diego, CA, USA
pp. 2488-2495

Covariance discriminative learning: A natural and efficient approach to image set classification (Abstract)

Qionghai Dai , Dept. of Autom., Tsinghua Univ., Beijing, China
L. S. Davis , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Huimin Guo , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Ruiping Wang , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
pp. 2496-2503

l2, 1 Regularized correntropy for robust feature selection (Abstract)

Wei-Shi Zheng , Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
Liang Wang , NLPR, Inst. of Autom., Beijing, China
Tieniu Tan , NLPR, Inst. of Autom., Beijing, China
Ran He , NLPR, Inst. of Autom., Beijing, China
pp. 2504-2511

Discriminant image filter learning for face recognition with local binary pattern like representation (Abstract)

Zhen Lei , Center for Biometrics & Security Res., Nat. Lab. of Pattern Recognition, Beijing, China
Dong Yi , Center for Biometrics & Security Res., Nat. Lab. of Pattern Recognition, Beijing, China
S. Z. Li , Center for Biometrics & Security Res., Nat. Lab. of Pattern Recognition, Beijing, China
pp. 2512-2517

Learning hierarchical representations for face verification with convolutional deep belief networks (Abstract)

E. Learned-Miller , Univ. of Massachusetts, Amherst, MA, USA
Honglak Lee , Univ. of Michigan, Ann Arbor, MI, USA
G. B. Huang , Univ. of Massachusetts, Amherst, MA, USA
pp. 2518-2525

Linear discriminative image processing operator analysis (Abstract)

K. Kaneda , Hiroshima Univ., Hiroshima, Japan
B. Raytchev , Hiroshima Univ., Hiroshima, Japan
K. Harada , Hiroshima Univ., Hiroshima, Japan
Bingzhi Yuan , Hiroshima Univ., Hiroshima, Japan
T. Tamaki , Hiroshima Univ., Hiroshima, Japan
pp. 2526-2532

Metric learning with two-dimensional smoothness for visual analysis (Abstract)

Haifeng Liu , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Deng Cai , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Zifei Tong , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Xinlei Chen , State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
pp. 2533-2538

A study on human age estimation under facial expression changes (Abstract)

Xiaolong Wang , West Virginia Univ., Morgantown, WV, USA
Guodong Guo , West Virginia Univ., Morgantown, WV, USA
pp. 2547-2553

Improved facial expression recognition via uni-hyperplane classification (Abstract)

J. F. Conn , Dept. of Psychol., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Sridharan , SAIVT Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
P. Lucey , Disney Res. Pittsburgh, Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Lucey , Commonwealth Sci. & Ind. Res. Organ. (CSIRO), Kenmore, QLD, Australia
S. W. Chew , SAIVT Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
pp. 2554-2561

Learning active facial patches for expression analysis (Abstract)

D. N. Metaxas , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
Junzhou Huang , Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX, USA
Bo Liu , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
Peng Yang , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
Qingshan Liu , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
Lin Zhong , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
pp. 2562-2569

Learning ordinal discriminative features for age estimation (Abstract)

Hanqing Lu , Inst. of Autom., NLPR, Beijing, China
Jing Liu , Inst. of Autom., NLPR, Beijing, China
Changsheng Li , Inst. of Autom., NLPR, Beijing, China
Qingshan Liu , CICE, Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
pp. 2570-2577

Real-time facial feature detection using conditional regression forests (Abstract)

G. Fanelli , ETH Zurich, Zurich, Switzerland
J. Gall , ETH Zurich, Zurich, Switzerland
M. Dantone , ETH Zurich, Zurich, Switzerland
L. Van Gool , ETH Zurich, Zurich, Switzerland
pp. 2578-2585

Sparse representation for face recognition based on discriminative low-rank dictionary learning (Abstract)

Long Ma , State Key Lab. of Manage. & Control for Complex Syst., Inst. of Autom., Beijing, China
Chunheng Wang , State Key Lab. of Manage. & Control for Complex Syst., Inst. of Autom., Beijing, China
Baihua Xiao , State Key Lab. of Manage. & Control for Complex Syst., Inst. of Autom., Beijing, China
Wen Zhou , State Key Lab. of Manage. & Control for Complex Syst., Inst. of Autom., Beijing, China
pp. 2586-2593

Neighborhood repulsed metric learning for kinship verification (Abstract)

Gang Wang , Adv. Digital Sci. Center, Singapore, Singapore
Yap-Peng Tan , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
Yuanyuan Shang , Sch. of Inf. Eng., Capital Normal Univ., Beijing, China
Xiuzhuang Zhou , Sch. of Inf. Eng., Capital Normal Univ., Beijing, China
Junlin Hu , Coll. of Inf. Sci. & Technol., Beijing Normal Univ., Beijing, China
Jiwen Lu , Adv. Digital Sci. Center, Singapore, Singapore
pp. 2594-2601

On partial least squares in head pose estimation: How to simultaneously deal with misalignment (Abstract)

L. S. Davis , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
J. Gonzalez , Centre de Visio per Computador, Univ. Autonoma de Barcelona, Barcelona, Spain
M. A. Haj , Centre de Visio per Computador, Univ. Autonoma de Barcelona, Barcelona, Spain
pp. 2602-2609

Low-rank matrix recovery with structural incoherence for robust face recognition (Abstract)

Y.-C F. Wang , Res. Center for Inf. Technol. Innovation, Acad. Sinica, Taipei, Taiwan
Chia-Po Wei , Res. Center for Inf. Technol. Innovation, Acad. Sinica, Taipei, Taiwan
Chih-Fan Chen , Res. Center for Inf. Technol. Innovation, Acad. Sinica, Taipei, Taiwan
pp. 2618-2625

Image sets alignment for Video-Based Face Recognition (Abstract)

Shiguang Shan , Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China
Zhen Cui , Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China
Haihong Zhang , Omron Social Solutions Co., Ltd., Kyoto, Japan
Shihong Lao , Omron Social Solutions Co., Ltd., Kyoto, Japan
Xilin Chen , Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China
pp. 2626-2633

Multi-output Laplacian dynamic ordinal regression for facial expression recognition and intensity estimation (Abstract)

M. Pantic , Comp. Dept., Imperial Coll. London, London, UK
V. Pavlovic , Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
O. Rudovic , Comp. Dept., Imperial Coll. London, London, UK
pp. 2634-2641

Feature-domain super-resolution framework for Gabor-based face and iris recognition (Abstract)

C. Fookes , Image & Video Res. Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
S. Denman , Image & Video Res. Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
K. Nguyen , Image & Video Res. Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
S. Sridharan , Image & Video Res. Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
pp. 2642-2649

Transfer re-identification: From person to set-based verification (Abstract)

Tao Xiang , 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
Wei-Shi Zheng , Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
pp. 2650-2657

“Knock! Knock! Who is it?” probabilistic person identification in TV-series (Abstract)

R. Stiefelhagen , Karlsruhe Inst. of Technol., Karlsruhe, Germany
M. Bauml , Karlsruhe Inst. of Technol., Karlsruhe, Germany
M. Tapaswi , Karlsruhe Inst. of Technol., Karlsruhe, Germany
pp. 2658-2665

PCCA: A new approach for distance learning from sparse pairwise constraints (Abstract)

F. Jurie , GREYC, Univ. de Caen, Caen, France
A. Mignon , GREYC, Univ. de Caen, Caen, France
pp. 2666-2672

Single image 3D human pose estimation from noisy observations (Abstract)

F. Moreno-Noguer , Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
C. Torras , Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
G. Alenya , Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
E. Simo-Serra , Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
A. Ramisa , Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
pp. 2673-2680

Customizing biometric authentication systems via discriminative score calibration (Abstract)

M. Tistarelli , Univ. di Sassari, Alghero, Italy
N. Poh , FEPS, Univ. of Surrey, Guildford, UK
pp. 2681-2686

Top-down and bottom-up cues for scene text recognition (Abstract)

C. V. Jawahar , CVIT, IIIT Hyderabad, Hyderabad, India
K. Alahari , INRIA - WILLOW, Ecole Normale Super., Paris, France
A. Mishra , CVIT, IIIT Hyderabad, Hyderabad, India
pp. 2687-2694

Recognizing scene viewpoint using panoramic place representation (Abstract)

A. Oliva , Massachusetts Inst. of Technol., Cambridge, MA, USA
K. A. Ehinger , Massachusetts Inst. of Technol., Cambridge, MA, USA
Jianxiong Xiao , Massachusetts Inst. of Technol., Cambridge, MA, USA
A. Torralba , Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. 2695-2702

Semantic structure from motion with points, regions, and objects (Abstract)

S. Savarese , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
Yu-Wei Chao , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
M. Bagra , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
Sid Yingze Bao , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
pp. 2703-2710

Small sample scene categorization from perceptual relations (Abstract)

O. Ben-Shahar , Dept. of Comput. Sci., Ben-Gurion Univ., Beer-Sheva, Israel
I. Kadar , Dept. of Comput. Sci., Ben-Gurion Univ., Beer-Sheva, Israel
pp. 2711-2718

Bayesian geometric modeling of indoor scenes (Abstract)

B. Kermgard , Univ. of Arizona, Tucson, AZ, USA
D. Fried , Univ. of Arizona, Tucson, AZ, USA
J. Bowdish , Univ. of Arizona, Tucson, AZ, USA
L. Del Pero , Univ. of Arizona, Tucson, AZ, USA
E. Hartley , Univ. of Arizona, Tucson, AZ, USA
K. Barnard , Univ. of Arizona, Tucson, AZ, USA
pp. 2719-2726

Learning object relationships via graph-based context model (Abstract)

Kyoung Mu Lee , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Ju Yong Chang , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Heesoo Myeong , Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
pp. 2727-2734

Automatic discovery of groups of objects for scene understanding (Abstract)

D. Parikh , Toyota Technol. Inst. (Chicago), Chicago, IL, USA
pp. 2735-2742

Context aware topic model for scene recognition (Abstract)

Xinbo Gao , Xidian Univ., Xi'an, China
Zhenxing Niu , Xidian Univ., Xi'an, China
Qi Tian , Univ. of Texas at San Antonio, San Antonio, TX, USA
pp. 2743-2750

RGB-(D) scene labeling: Features and algorithms (Abstract)

D. Fox , Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA
Liefeng Bo , Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA
pp. 2759-2766

Learning sparse covariance patterns for natural scenes (Abstract)

J. M. Rehg , Georgia Inst. of Technol., Atlanta, GA, USA
Jiaya Jia , Chinese Univ. of Hong Kong, Hong Kong, China
Yin Li , Georgia Inst. of Technol., Atlanta, GA, USA
Liwei Wang , Chinese Univ. of Hong Kong, Hong Kong, China
pp. 2767-2774

Multiclass pixel labeling with non-local matching constraints (Abstract)

S. Gould , Res. Sch. of Comput. Sci., Australian Nat. Univ., Canberra, ACT, Australia
pp. 2783-2790

Nonparametric image parsing using adaptive neighbor sets (Abstract)

R. Fergus , Dept. of Comput. Sci., New York Univ., New York, NY, USA
D. Eigen , Dept. of Comput. Sci., New York Univ., New York, NY, USA
pp. 2799-2806

Recovering free space of indoor scenes from a single image (Abstract)

David Forsyth , University of Illinois at Urbana Champaign
Derek Hoiem , University of Illinois at Urbana Champaign
Varsha Hedau , Nokia Research, Palo Alto, CA
pp. 2807-2814

Joint 2D-3D temporally consistent semantic segmentation of street scenes (Abstract)

B. Leibe , UMIC Res. Centre, RWTH Aachen Univ., Aachen, Germany
G. Floros , UMIC Res. Centre, RWTH Aachen Univ., Aachen, Germany
pp. 2823-2830

Robust camera self-calibration from monocular images of Manhattan worlds (Abstract)

A. Hanbury , Inst. of Software Technol. & Interactive Syst., Vienna Univ. of Technlology, Vienna, Austria
H. Wildenauer , Inst. of Software Technol. & Interactive Syst., Vienna Univ. of Technlology, Vienna, Austria
pp. 2831-2838

Detecting activities of daily living in first-person camera views (Abstract)

D. Ramanan , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
H. Pirsiavash , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
pp. 2847-2854

Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents (Abstract)

Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Xiaogang Wang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Bolei Zhou , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 2871-2878

Face detection, pose estimation, and landmark localization in the wild (Abstract)

D. Ramanan , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
Xiangxin Zhu , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
pp. 2879-2886

Contextual boost for pedestrian detection (Abstract)

Jing Xiao , Epson R&D, Inc., San Jose, CA, USA
Yuanyuan Ding , Epson R&D, Inc., San Jose, CA, USA
pp. 2895-2902

Pedestrian detection at 100 frames per second (Abstract)

L. Van Gool , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
M. Mathias , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
R. Timofte , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
R. Benenson , ESAT-PSI-VISICS/IBBT, Katholieke Univ. Leuven, Leuven, Belgium
pp. 2903-2910

Robust and discriminative distance for Multi-Instance Learning (Abstract)

Heng Huang , Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX, USA
Feiping Nie , Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX, USA
Hua Wang , Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX, USA
pp. 2919-2924

Towards compact topical descriptors (Abstract)

Wen Gao , Nat. Eng. Lab. for Video Technol., Peking Univ., Beijing, China
Jie Chen , Nat. Eng. Lab. for Video Technol., Peking Univ., Beijing, China
Ling-Yu Duan , Nat. Eng. Lab. for Video Technol., Peking Univ., Beijing, China
Rongrong Ji , Nat. Eng. Lab. for Video Technol., Peking Univ., Beijing, China
pp. 2925-2932

D-Nets: Beyond patch-based image descriptors (Abstract)

R. Sukthankar , Google Res. & The Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. von Hundelshausen , Inst. for Autonomous Syst. Technol. (TAS), Univ. of the Bundeswehr, Munich, Germany
pp. 2941-2948

Weak attributes for large-scale image retrieval (Abstract)

Shih-Fu Chang , Columbia Univ., New York, NY, USA
Guangnan Ye , Columbia Univ., New York, NY, USA
Ming-Hen Tsai , Columbia Univ., New York, NY, USA
Rongrong Ji , Columbia Univ., New York, NY, USA
F. X. Yu , Columbia Univ., New York, NY, USA
pp. 2949-2956

Auto face re-ranking by mining the web and video archives (Abstract)

Duy-Dinh Le , Nat. Inst. of Inf., Tokyo, Japan
S. Satoh , Nat. Inst. of Inf., Tokyo, Japan
pp. 2965-2972

WhittleSearch: Image search with relative attribute feedback (Abstract)

D. Parikh , Toyota Technol. Inst. Chicago (TTIC), Chicago, IL, USA
A. Kovashka , Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
pp. 2973-2980

Graph-guided sparse reconstruction for region tagging (Abstract)

Qi Tian , Dept. of Comput. Sci., Univ. of Texas at San Antonio, San Antonio, TX, USA
Jian Shao , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Fei Wu , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Yahong Han , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Yueting Zhuang , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
pp. 2981-2988

Nonparametric kernel estimators for image classification (Abstract)

J. Schneider , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
D. J. Sutherland , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Liang Xiong , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
B. Poczos , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 2989-2996

Unsupervised metric fusion by cross diffusion (Abstract)

Zhuowen Tu , Lab. of Neuro Imaging, Univ. of California, Los Angeles, CA, USA
Zhi-Hua Zhou , Nat. Key Lab. for Novel Software Jechnologv, Nanjing Univ., Nanjing, China
Wei Wang , Nat. Key Lab. for Novel Software Jechnologv, Nanjing Univ., Nanjing, China
Jiayan Jiang , Lab. of Neuro Imaging, Univ. of California, Los Angeles, CA, USA
Bo Wang , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
pp. 2997-3004

Object retrieval and localization with spatially-constrained similarity measure and k-NN re-ranking (Abstract)

Ying Wu , Northwestern Univ., Evanston, IL, USA
S. Avidan , Tel-Aviv Univ., Tel-Aviv, Israel
J. Brandt , Adobe Syst. Inc., San Jose, CA, USA
Zhe Lin , Adobe Syst. Inc., San Jose, CA, USA
Xiaohui Shen , Northwestern Univ., Evanston, IL, USA
pp. 3013-3020

Robust late fusion with rank minimization (Abstract)

I-Hong Jhuo , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Dong Liu , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Guangnan Ye , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Shih-Fu Chang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
pp. 3021-3028

Leveraging category-level labels for instance-level image retrieval (Abstract)

E. Valveny , Comput. Vision Center, Univ. Autonoma de Barcelona, Barcelona, Spain
F. Perronnin , Textual & Visual Pattern Anal., Xerox Res. Center Eur., Meylan, France
J. A. Rodriguez-Serrano , Textual & Visual Pattern Anal., Xerox Res. Center Eur., Meylan, France
A. Gordoa , Textual & Visual Pattern Anal., Xerox Res. Center Eur., Meylan, France
pp. 3045-3052

A fast nearest neighbor search algorithm by nonlinear embedding (Abstract)

Hee-Kap Ahn , Dept. of Comput. Sci. & Eng., POSTECH, Pohang, South Korea
Bohyung Han , Dept. of Comput. Sci. & Eng., POSTECH, Pohang, South Korea
Yoonho Hwang , Dept. of Comput. Sci. & Eng., POSTECH, Pohang, South Korea
pp. 3053-3060

(Unseen) event recognition via semantic compositionality (Abstract)

F. Giunchiglia , Univ. of Trento, Trento, Italy
N. Sebe , Univ. of Trento, Trento, Italy
A. K. Pandey , Univ. of Trento, Trento, Italy
J. R. R. Uijlings , Univ. of Trento, Trento, Italy
J. Stottinger , Univ. of Trento, Trento, Italy
pp. 3061-3068

Fast computation of min-Hash signatures for image collections (Abstract)

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. 3077-3084

Meta-class features for large-scale object categorization on a budget (Abstract)

L. Torresani , Dartmouth Coll., Hanover, NH, USA
A. Bergamo , Dartmouth Coll., Hanover, NH, USA
pp. 3085-3092

On the regularization of image semantics by modal expansion (Abstract)

N. Vasconcelos , Dept. of Electr. & Comput. Eng., Univ. of California, San Diego, CA, USA
J. C. Pereira , Dept. of Electr. & Comput. Eng., Univ. of California, San Diego, CA, USA
pp. 3093-3099

Randomized visual phrases for object search (Abstract)

Junsong Yuan , Sch. of EEE, Nanyang Technol. Univ., Singapore, Singapore
Jingjing Meng , Sch. of EEE, Nanyang Technol. Univ., Singapore, Singapore
Yuning Jiang , Sch. of EEE, Nanyang Technol. Univ., Singapore, Singapore
pp. 3100-3107

Fast search in Hamming space with multi-index hashing (Abstract)

D. J. Fleet , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
A. Punjani , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
M. Norouzi , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
pp. 3108-3115

Augmenting deformable part models with irregular-shaped object patches (Abstract)

R. Mottaghi , Univ. of California, Los Angeles, CA, USA
pp. 3116-3123

Multi-pedestrian detection in crowded scenes: A global view (Abstract)

Junjie Yan , Center for Biometrics & Security Res. & Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Zhen Lei , Center for Biometrics & Security Res. & Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Dong Yi , Center for Biometrics & Security Res. & Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Stan Z. Li , Center for Biometrics & Security Res. & Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
pp. 3124-3129

Learning shared body plans (Abstract)

D. Hoiem , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Ming-Wei Chang , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
V. Srikumar , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
I. Endres , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 3130-3137

Efficient object detection using cascades of nearest convex model classifiers (Abstract)

B. Triggs , Lab. Jean Kuntzmann, Grenoble, France
H. Cevikalp , Eskisehir Osmangazi Univ., Eskisehir, Turkey
pp. 3138-3145

Occlusion reasoning for object detection under arbitrary viewpoint (Abstract)

M. Hebert , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
E. Hsiao , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 3146-3153

Active learning for semantic segmentation with expected change (Abstract)

V. Ferrari , Univ. of Edinburgh, Edinburgh, UK
J. M. Buhmann , ETH Zurich, Zurich, Switzerland
A. Vezhnevets , ETH Zurich, Zurich, Switzerland
pp. 3162-3169

Learning an object class representation on a continuous viewsphere (Abstract)

R. Lienhart , Univ. of Augsburg, Augsburg, Germany
J. Liebelt , EADS Innovation Works, München, Germany
J. Schels , EADS Innovation Works, München, Germany
pp. 3170-3177

Articulated people detection and pose estimation: Reshaping the future (Abstract)

B. Schiele , Max Planck Inst. for Inf., Saarbrucken, Germany
T. Thormahlen , Max Planck Inst. for Inf., Saarbrucken, Germany
M. Andriluka , Max Planck Inst. for Inf., Saarbrucken, Germany
A. Jain , Max Planck Inst. for Inf., Saarbrucken, Germany
L. Pishchulin , Max Planck Inst. for Inf., Saarbrucken, Germany
pp. 3178-3185

Vector array based Multi-View Face Detection with compound exemplars (Abstract)

J. Ben-Arie , Univ. of Illinois at Chicago, Chicago, IL, USA
Kai Ma , Univ. of Illinois at Chicago, Chicago, IL, USA
pp. 3186-3193

Salient object detection for searched web images via global saliency (Abstract)

Hongbin Zha , Key Lab. on Machine Perception, Peking Univ., Beijing, China
Jie Feng , Key Lab. on Machine Perception, Peking Univ., Beijing, China
Gang Zeng , Key Lab. on Machine Perception, Peking Univ., Beijing, China
Peng Wang , Key Lab. on Machine Perception, Peking Univ., Beijing, China
pp. 3194-3201

Large-scale knowledge transfer for object localization in ImageNet (Abstract)

V. Ferrari , Univ. of Edinburgh, Edinburgh, UK
M. Guillaumin , ETH Zurich, Zurich, Switzerland
pp. 3202-3209

Foreground detection using spatiotemporal projection kernels (Abstract)

Y. Hel-Or , Sch. of Comput. Sci., Interdiscipl. Center, Herzliya, Israel
H. Hel-Or , Dept. of Comput. Sci., Univ. of Haifa, Haifa, Israel
Y. Moshe , Dept. of Comput. Sci., Univ. of Haifa, Haifa, Israel
pp. 3210-3217

Steerable part models (Abstract)

D. Ramanan , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
H. Pirsiavash , Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
pp. 3226-3233

Visual stem mapping and Geometric Tense coding for Augmented Visual Vocabulary (Abstract)

Ke Gao , Adv. Comput. Res. Lab., Inst. of Comput. Technol., Beijing, China
Yongdong Zhang , Adv. Comput. Res. Lab., Inst. of Comput. Technol., Beijing, China
Ping Luo , Hewlett-Packard Labs., China
Wei Zhang , Adv. Comput. Res. Lab., Inst. of Comput. Technol., Beijing, China
Junhai Xia , Adv. Comput. Res. Lab., Inst. of Comput. Technol., Beijing, China
Shouxun Lin , Adv. Comput. Res. Lab., Inst. of Comput. Technol., Beijing, China
pp. 3234-3241

Interactive object detection (Abstract)

C. Leistner , ETH Zurich, Zurich, Switzerland
J. Gall , ETH Zurich, Zurich, Switzerland
A. Yao , ETH Zurich, Zurich, Switzerland
L. Van Gool , ETH Zurich, Zurich, Switzerland
pp. 3242-3249

A discriminative deep model for pedestrian detection with occlusion handling (Abstract)

Xiaogang Wang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Wanli Ouyang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 3258-3265

Superedge grouping for object localization by combining appearance and shape information (Abstract)

Song Wang , Dept. of Comput. Sci. & Eng., Univ. of South Carolina, Columbia, SC, USA
J. M. Siskind , Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
S. Dickinson , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
Yu Cao , Dept. of Comput. Sci. & Eng., Univ. of South Carolina, Columbia, SC, USA
J. Waggoner , Dept. of Comput. Sci. & Eng., Univ. of South Carolina, Columbia, SC, USA
S. Fidler , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
Zhiqi Zhang , Dept. of Comput. Sci. & Eng., Univ. of South Carolina, Columbia, SC, USA
pp. 3266-3273

Transferring a generic pedestrian detector towards specific scenes (Abstract)

Xiaogang Wang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Wei Li , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Meng Wang , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
pp. 3274-3281

Mobile object detection through client-server based vote transfer (Abstract)

S. Savarese , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
Min Sun , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
S. S. Kumar , Dept. of Electr. & Comput. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
pp. 3290-3297

Unsupervised incremental learning for improved object detection in a video (Abstract)

R. Nevatia , Univ. of Southern California, Los Angeles, CA, USA
Chang Huang , NEC Labs., Cupertino, CA, USA
P. Sharma , Univ. of Southern California, Los Angeles, CA, USA
pp. 3298-3305

Color attributes for object detection (Abstract)

A. M. Lopez , CS Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
M. Vanrell , CS Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
A. D. Bagdanov , CS Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
J. van de Weijer , CS Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
Rao Muhammad Anwer , CS Dept., Univ. Autonoma de Barcelona, Barcelona, Spain
Fahad Shahbaz Khan , Comput. Vision Lab., Linkoping Univ., Linkoping, Sweden
pp. 3306-3313

A data driven method for feature transformation (Abstract)

T. S. Huang , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
D. Hoiem , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
M. Dikmen , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 3314-3321

Learning to localize detected objects (Abstract)

D. Hoiem , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Qieyun Dai , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 3322-3329

Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set (Abstract)

Hanqing Lu , NLPR, Inst. of Autom., Beijing, China
Changsheng Xu , NLPR, Inst. of Autom., Beijing, China
Guangcan Liu , ECE Dept., Nat. Univ. of Singapore, Singapore, Singapore
Zheng Song , ECE Dept., Nat. Univ. of Singapore, Singapore, Singapore
Si Liu , ECE Dept., Nat. Univ. of Singapore, Singapore, Singapore
Shuicheng Yan , ECE Dept., Nat. Univ. of Singapore, Singapore, Singapore
pp. 3330-3337

Autonomous cleaning of corrupted scanned documents — A generative modeling approach (Abstract)

J. Lucke , Dept. of Phys., Goethe-Univ. Frankfurt, Frankfurt am Main, Germany
Zhenwen Dai , Dept. of Phys., Goethe-Univ. Frankfurt, Frankfurt am Main, Germany
pp. 3338-3345

Are we ready for autonomous driving? The KITTI vision benchmark suite (Abstract)

R. Urtasun , Toyota Technol. Inst. at Chicago, Chicago, IL, USA
P. Lenz , Karlsruhe Inst. of Technol., Karlsruhe, Germany
A. Geiger , Karlsruhe Inst. of Technol., Karlsruhe, Germany
pp. 3354-3361

Beyond spatial pyramids: Receptive field learning for pooled image features (Abstract)

T. Darrell , UC Berkeley EECS & ICSI, Berkeley, CA, USA
Chang Huang , NEC Labs. America, Princeton, NJ, USA
Yangqing Jia , UC Berkeley EECS & ICSI, Berkeley, CA, USA
pp. 3370-3377

Semantic segmentation using regions and parts (Abstract)

J. Malik , Univ. of California, Berkeley, Berkeley, CA, USA
L. Bourdev , Univ. of California, Berkeley, Berkeley, CA, USA
S. Gupta , Univ. of California, Berkeley, Berkeley, CA, USA
Chunhui Gu , Univ. of California, Berkeley, Berkeley, CA, USA
B. Hariharan , Univ. of California, Berkeley, Berkeley, CA, USA
P. Arbelaez , Univ. of California, Berkeley, Berkeley, CA, USA
pp. 3378-3385

Contour-based recognition (Abstract)

D. Dementhon , Appl. Phys. Lab., Johns Hopkins Univ., Baltimore, MD, USA
M. Nishigaki , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
C. Fermuller , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Hui Ji , Dept. of Math., Nat. Univ. of Singapore, Singapore, Singapore
Zhuming Zhang , Sch. of Comput. Sci. & Eng., South China Univ. of Tech., Guangzhou, China
Yuhui Quan , 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. 3402-3409

Estimating the aspect layout of object categories (Abstract)

S. Savarese , Dept. of Comput. Sci. & Electr. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
Yu Xiang , Dept. of Comput. Sci. & Electr. Eng., Univ. of Michigan at Ann Arbor, Ann Arbor, MI, USA
pp. 3410-3417

Submodular dictionary learning for sparse coding (Abstract)

L. S. Davis , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Guangxiao Zhang , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
Zhuolin Jiang , Inst. for Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA
pp. 3418-3425

Hierarchical matching with side information for image classification (Abstract)

Shuicheng Yan , Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Zhongyang Huang , Panasonic Singapore Labs., Singapore, Singapore
Yang Hua , Panasonic Singapore Labs., Singapore, Singapore
Zheng Song , Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Qiang Chen , Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
pp. 3426-3433

Discriminative feature fusion for image classification (Abstract)

M. Sebban , Lab. Hubert Curien, St. Étienne, France
D. Muselet , Lab. Hubert Curien, St. Étienne, France
E. Fromont , Lab. Hubert Curien, St. Étienne, France
B. Fernando , ESAT-PSI, K.U. Leuven, Leuven, Belgium
pp. 3434-3441

Building a dictionary of image fragments (Abstract)

D. Forsyth , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
I. Endres , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Yang Wang , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Ali Farhadi , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Zicheng Liao , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 3442-3449

SURFing the point clouds: Selective 3D spatial pyramids for category-level object recognition (Abstract)

S. Maldonado-Bascon , Dept. of Signal Theor. & Commun., Univ. of Alcala, Alcala de Henares, Spain
J. Acevedo-Rodriguez , Dept. of Signal Theor. & Commun., Univ. of Alcala, Alcala de Henares, Spain
R. J. Lopez-Sastre , Dept. of Signal Theor. & Commun., Univ. of Alcala, Alcala de Henares, Spain
C. Redondo-Cabrera , Dept. of Signal Theor. & Commun., Univ. of Alcala, Alcala de Henares, Spain
pp. 3458-3465

A codebook-free and annotation-free approach for fine-grained image categorization (Abstract)

Li Fei-Fei , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
G. Bradski , Ind. Perception Inc., Palo Alto, CA, USA
Bangpeng Yao , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
pp. 3466-3473

Discovering localized attributes for fine-grained recognition (Abstract)

K. Grauman , Univ. of Texas, Austin, TX, USA
D. Crandall , Indiana Univ., Bloomington, IN, USA
D. Parikh , TTI-Chicago Chicago, Chicago, IL, USA
Kun Duan , Indiana Univ., Bloomington, IN, USA
pp. 3474-3481

Towards good practice in large-scale learning for image classification (Abstract)

C. Schmid , LEAR Team, INRIA, Grenoble, France
Z. Harchaoui , LEAR Team, INRIA, Grenoble, France
Z. Akata , TVPA Team, XRCE, France
F. Perronnin , TVPA Team, XRCE, France
pp. 3482-3489

Learning inter-related visual dictionary for object recognition (Abstract)

Jianping Fan , Dept. of Comput. Sci., Univ. of North Carolina, Charlotte, NC, USA
Jinye Peng , Sch. of Inf. Sci. & Technol., Northwest Univ., Xi'an, China
Yi Shen , Dept. of Comput. Sci., Univ. of North Carolina, Charlotte, NC, USA
Ning Zhou , Dept. of Comput. Sci., Univ. of North Carolina, Charlotte, NC, USA
pp. 3490-3497

Cats and dogs (Abstract)

C. V. Jawahar , Center for Visual Inf. Technol., Int. Inst. of Inf. Technol., Hyderabad, India
A. Zisserman , Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
A. Vedaldi , Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
O. M. Parkhi , Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
pp. 3498-3505

Discriminative spatial saliency for image classification (Abstract)

C. Schmid , LEAR, INRIA Grenoble, Grenoble, France
F. Jurie , GREYC, Univ. de Caen, Caen, France
G. Sharma , GREYC, Univ. de Caen, Caen, France
pp. 3506-3513

Omni-range spatial contexts for visual classification (Abstract)

Shuicheng Yan , Nat. Univ. of Singapore, Singapore, Singapore
Jinhui Tang , Nanjing Univ. of Sci. & Technol., Nanjing, China
Mengdi Xu , Nat. Univ. of Singapore, Singapore, Singapore
Bingbing Ni , Adv. Digital Sci. Center, Singapore, Singapore
P. Moulin , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 3514-3521

Structured Local Predictors for image labelling (Abstract)

H. Bischof , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Pelillo , Dipt. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari Venezia, Venezia, Italy
P. Kontschieder , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
S. R. Bulo , Dipt. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari Venezia, Venezia, Italy
pp. 3530-3537

Real-time scene text localization and recognition (Abstract)

L. Neumann , Dept. of Cybern., Czech Tech. Univ., Prague, Czech Republic
J. Matas , Dept. of Cybern., Czech Tech. Univ., Prague, Czech Republic
pp. 3538-3545

From Pictorial Structures to deformable structures (Abstract)

M. J. Black , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
O. Freifeld , Div. of Appl. Math., Brown Univ., Providence, RI, USA
S. Zuffi , Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
pp. 3546-3553

DCMSVM: Distributed parallel training for single-machine multiclass classifiers (Abstract)

A. C. Berg , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
Xufeng Han , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
pp. 3554-3561

Parsing clothing in fashion photographs (Abstract)

T. L. Berg , Stony Brook Univ., Stony Brook, NY, USA
L. E. Ortiz , Stony Brook Univ., Stony Brook, NY, USA
M. H. Kiapour , Stony Brook Univ., Stony Brook, NY, USA
K. Yamaguchi , Stony Brook Univ., Stony Brook, NY, USA
pp. 3570-3577

What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection (Abstract)

Lei Wang , Sch. of Comput. Sci. & Software Eng., Univ. of Wollongong, Wollongong, NSW, Australia
Lingqiao Liu , CECS, Australian Nat. Univ., Canberra, ACT, Australia
pp. 3586-3593

3D visual phrases for landmark recognition (Abstract)

Feng Wu , Microsoft Res. Asia, Beijing, China
Yanwei Pang , Tianjin Univ., Tianjin, China
Lei Zhang , Microsoft Res. Asia, Beijing, China
Zhiwei Li , Microsoft Res. Asia, Beijing, China
Rui Cai , Microsoft Res. Asia, Beijing, China
Qiang Hao , Tianjin Univ., Tianjin, China
pp. 3594-3601

Convex reduction of high-dimensional kernels for visual classification (Abstract)

A. W. M. Smeulders , Inf. Inst., Univ. of Amsterdam, Amsterdam, Netherlands
C. G. M. Snoek , Inf. Inst., Univ. of Amsterdam, Amsterdam, Netherlands
Efstratios Gavves , Inf. Inst., Univ. of Amsterdam, Amsterdam, Netherlands
pp. 3610-3617

Locality-constrained and spatially regularized coding for scene categorization (Abstract)

H. LeBorgne , Vision & Content Eng. Lab., CEA, Gif-sur-Yvettes, France
A. Shabou , Vision & Content Eng. Lab., CEA, Gif-sur-Yvettes, France
pp. 3618-3625

RALF: A reinforced active learning formulation for object class recognition (Abstract)

B. Schiele , Max Planck Inst. for Inf., Saarbrucken, Germany
M. Fritz , Max Planck Inst. for Inf., Saarbrucken, Germany
S. Ebert , Max Planck Inst. for Inf., Saarbrucken, Germany
pp. 3626-3633

A 3D extension to cortex like mechanisms for 3D object class recognition (Abstract)

N. Megherbi , Sch. of Eng., Cranfield Univ., Cranfield, UK
T. P. Breckon , Sch. of Eng., Cranfield Univ., Cranfield, UK
G. Flitton , Sch. of Eng., Cranfield Univ., Cranfield, UK