The Community for Technology Leaders
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2009)
Miami, FL, USA
June 20, 2009 to June 25, 2009
ISBN: 978-1-4244-3994-2
TABLE OF CONTENTS
Papers

Egocentric recognition of handled objects: Benchmark and analysis (Abstract)

Xiaofeng Ren , Intel Res. Seattle, Seattle, WA, USA
M. Philipose , Intel Res. Seattle, Seattle, WA, USA
pp. 1-8

AWEAR 2.0 system: Omni-directional audio-visual data acquisition and processing (Abstract)

M. Havlena , Dept. of Cybern. Fac. of Elec. Eng., Czech Tech. Univ. in Prague, Prague, Czech Republic
T. Pajdla , Dept. of Cybern. Fac. of Elec. Eng., Czech Tech. Univ. in Prague, Prague, Czech Republic
A. Torii , Dept. of Cybern. Fac. of Elec. Eng., Czech Tech. Univ. in Prague, Prague, Czech Republic
M. Jancosek , Dept. of Cybern. Fac. of Elec. Eng., Czech Tech. Univ. in Prague, Prague, Czech Republic
pp. 49-56

EYEWATCHME (Abstract)

Li Sun , Sch. of Electron.&Inf. Eng., Xi'an Jiaotong Univ., Xi'an, China
pp. 9-16

Self lane assignment using egocentric smart mobile camera for intelligent GPS navigation (Abstract)

Tianshi Gao , Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
H. Aghajan , Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
pp. 57-62

Learning texton models for real-time scene context (Abstract)

A. Flint , Active Vision Lab., Oxford Univ., Oxford, UK
D. Murray , Active Vision Lab., Oxford Univ., Oxford, UK
I. Reid , Active Vision Lab., Oxford Univ., Oxford, UK
pp. 41-48

Image matching in large scale indoor environment (Abstract)

M. Hebert , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
A.A. Efros , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Hongwen Kang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 33-40

Temporal segmentation and activity classification from first-person sensing (Abstract)

F. De La Torre , Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hebert , Carnegie Mellon Univ., Pittsburgh, PA, USA
E.H. Spriggs , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 17-24

High level activity recognition using low resolution wearable vision (Abstract)

W.W.M. Cuevas , Dept. of Comput. Sci., Univ. of Bristol, Bristol, UK
S. Sundaram , Dept. of Comput. Sci., Univ. of Bristol, Bristol, UK
pp. 25-32

Table of contents (PDF)

pp. i-ii

Automatic detection of body parts in x-ray images (Abstract)

V. Jeanne , Philips Res. Labs., Eindhoven, Netherlands
D. Unay , Philips Res. Labs., Eindhoven, Netherlands
pp. 25-30

TIMER: Tensor Image Morphing for Elastic Registration (Abstract)

Dinggang Shen , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Weili Lin , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Guorong Wu , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Pew-Thian Yap , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
pp. 1-8

Automatic Multiple Sclerosis detection based on integrated square estimation (Abstract)

Jundong Liu , Sch. of Elec. Eng.&Comp. Sci., Ohio Univ., Athens, OH, USA
pp. 31-38

Cortical enhanced tissue segmentation of neonatal brain MR images acquired by a dedicated phased array coil (Abstract)

Yong Fan , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Dinggang Shen , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Weili Lin , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Pew-Thian Yap , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Jie-Zhi Cheng , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Feng Shi , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
pp. 39-45

Echocardiographic contour extraction with local and global priors through boosting and level sets (Abstract)

A.B. Oktay , Dept. of Comput. Eng., Gebze Inst. of Technol., Kocaeli, Turkey
Y.S. Akgul , Dept. of Comput. Eng., Gebze Inst. of Technol., Kocaeli, Turkey
pp. 46-51

Quasiconvex alignment of multimodal skin images for quantitative dermatology (Abstract)

K.J. Dana , Rutgers Univ., Piscataway, NJ, USA
S.K. Madan , Rutgers Univ., Piscataway, NJ, USA
pp. 117-124

An optimal control approach for deformable registration (Abstract)

M. Niethammer , Dept. of Comput. Sci., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
G.L. Hart , Dept. of Comput. Sci., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
C. Zach , Dept. of Comput. Sci., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
pp. 9-16

Image registration by minimization of Mapping Complexity (Abstract)

Xubo Song , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Portland, OR, USA
A. Myronenko , Dept. of Sci.&Eng., Oregon Health&Sci. Univ., Portland, OR, USA
pp. 17-24

Regularization of diffusion tensor field using coupled robust anisotropic diffusion filters (Abstract)

Weili Lin , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Dinggang Shen , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Yong Fan , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Songyuan Tang , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Pew-Thian Yap , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Wei Gao , Dept. of Radiol., Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, USA
pp. 52-57

Learning to segment using machine-learned penalized logistic models (Abstract)

Yong Yue , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
H.D. Tagare , Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
pp. 58-65

Groupwise morphometric analysis based on morphological appearance manifold (Abstract)

Nai-Xiang Lian , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
C. Davatzikos , Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 133-140

GPU-accelerated, gradient-free MI deformable registration for atlas-based MR brain image segmentation (Abstract)

V. Willcut , CMS Software, Elekta Inc., Maryland Heights, MO, USA
L.S. Hibbard , CMS Software, Elekta Inc., Maryland Heights, MO, USA
Xiao Han , CMS Software, Elekta Inc., Maryland Heights, MO, USA
pp. 141-148

3D stochastic completion fields for fiber tractography (Abstract)

P. Momayyez , Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada
K. Siddiqi , Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada
pp. 178-185

Robust estimation of stem cell lineages using local graph matching (Abstract)

A.K. Roy-Chowdhury , Dept. of Electr. Eng., Univ. of California, Riverside, CA, USA
Min Liu , Dept. of Electr. Eng., Univ. of California, Riverside, CA, USA
pp. 194-201

Tunable tensor voting improves grouping of membrane-bound macromolecules (Abstract)

B. Parvin , Lawrence Berkeley Nat. Lab., Berkeley, CA, USA
L.A. Loss , Lawrence Berkeley Nat. Lab., Berkeley, CA, USA
pp. 72-78

Distance guided selection of the best base classifier in an ensemble with application to cervigram image segmentation (Abstract)

Xiaolei Huang , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
Wei Wang , Dept. of Comput. Sci.&Eng., Lehigh Univ., Bethlehem, PA, USA
pp. 109-116

Deformable tree models for 2D and 3D branching structures extraction (Abstract)

L.D. Cohen , CEREMADE, Univ. Paris Dauphine, Paris, France
J. Mille , CEREMADE, Univ. Paris Dauphine, Paris, France
pp. 149-156

Accurate estimation of pulmonary nodule's growth rate in CT images with nonrigid registration and precise nodule detection and segmentation (Abstract)

C. Kambhamettu , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
Yuanjie Zheng , Dept. of Comput. Sci., Univ. of Delaware, Newark, DE, USA
pp. 101-108

3D segmentation of rodent brains using deformable models and variational methods (Abstract)

D.N. Metaxas , CBIM, Rutgers Univ., Piscataway, NJ, USA
Sukmoon Chang , CBIM, Rutgers Univ., Piscataway, NJ, USA
Xiaoxu Wang , CBIM, Rutgers Univ., Piscataway, NJ, USA
Shaoting Zhang , CBIM, Rutgers Univ., Piscataway, NJ, USA
Jinghao Zhou , CBIM, Rutgers Univ., Piscataway, NJ, USA
pp. 94-100

Automatic symmetry-integrated brain injury detection in MRI sequences (Abstract)

B. Bhanu , Center for Res. in Intell. Syst., Univ. of California, Riverside, CA, USA
Yu Sun , Center for Res. in Intell. Syst., Univ. of California, Riverside, CA, USA
pp. 79-86

Bicycle chain shape models (Abstract)

A. Tatu , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
D.R. Jurgensen , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
Chen Chen , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
M. Loog , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
F. Lauze , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
M. Nielsen , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
M. de Bruijne , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
S. Sommer , Dept. of Comput. Sci., Univ. of Copenhagen, Copenhagen, Denmark
pp. 157-163

Automatic estimation of left ventricular dysfunction from echocardiogram videos (Abstract)

A. Amir , Almaden Res. Center, IBM, San Jose, CA, USA
D. Beymer , Almaden Res. Center, IBM, San Jose, CA, USA
Fei Wang , Almaden Res. Center, IBM, San Jose, CA, USA
T. Syeda-Mahmood , Almaden Res. Center, IBM, San Jose, CA, USA
pp. 164-171

Dense iterative contextual pixel classification using Kriging (Abstract)

M. Ganz , DIKU, Univ. of Copenhagen, Copenhagen, Denmark
M. Nielsen , DIKU, Univ. of Copenhagen, Copenhagen, Denmark
pp. 87-93

3-D reconstruction and measurement of microtubules from multiple angle-total internal reflection fluorescence microscopy (Abstract)

A. Karpikov , Yale Univ., New Haven, CT, USA
D. Toomre , Yale Univ., New Haven, CT, USA
Qian Yang , Yale Univ., New Haven, CT, USA
J. Duncan , Yale Univ., New Haven, CT, USA
pp. 172-177

Tracking of cell populations to understand their spatio-temporal behavior in response to physical stimuli (Abstract)

M. Betke , Dept. of Comput. Sci., Boston Univ., Boston, MA, USA
D. House , Dept. of Comput. Sci., Boston Univ., Boston, MA, USA
Zheng Wu , Dept. of Comput. Sci., Boston Univ., Boston, MA, USA
pp. 186-193

Table of contents (PDF)

pp. iii-v

Committee (PDF)

pp. vi

Vehicle matching and recognition under large variations of pose and illumination (Abstract)

Hong Qin , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
Tingbo Hou , Comput. Sci. Dept., Stony Brook Univ., Stony Brook, NY, USA
pp. 24-29

Background subtraction in varying illuminations using an ensemble based on an enlarged feature set (Abstract)

B. Klare , Dept of Comput. Sci.&Eng., Michigan State Univ., East Lansing, MI, USA
pp. 66-73

Feature based person detection beyond the visible spectrum (Abstract)

M. Arens , FGAN-FOM, Ettlingen, Germany
Kai Jungling , FGAN-FOM, Ettlingen, Germany
pp. 30-37

A rapidly deployable virtual presence extended defense system (Abstract)

C. Giron , Sandia Nat. Labs., Albuquerque, NM, USA
H.D. Nguyen , Sandia Nat. Labs., Albuquerque, NM, USA
M.W. Koch , Sandia Nat. Labs., Albuquerque, NM, USA
pp. 82-89

A smart sensor with hyperspectral/range fovea and panoramic peripheral view (Abstract)

Tao Wang , Dept. of Comput. Sci., City Coll. of New York, New York, NY, USA
Zhigang Zhu , Dept. of Comput. Sci., City Coll. of New York, New York, NY, USA
pp. 98-105

Fusion of a camera and a laser range sensor for vehicle recognition (Abstract)

S. Mohottala , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
S. Ono , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
K. Ikeuchi , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
M. Kagesawa , Inst. of Ind. Sci., Univ. of Tokyo, Tokyo, Japan
pp. 16-23

Robust real-time 3D modeling of static scenes using solely a Time-of-Flight sensor (Abstract)

J. Feulner , Dept. of Pattern Recognition, Friedrich-Alexander-Univ. Erlangen-Nuremberg, Erlangen, Germany
J. Penne , Dept. of Pattern Recognition, Friedrich-Alexander-Univ. Erlangen-Nuremberg, Erlangen, Germany
J. Hornegger , Dept. of Pattern Recognition, Friedrich-Alexander-Univ. Erlangen-Nuremberg, Erlangen, Germany
E. Kollorz , Dept. of Pattern Recognition, Friedrich-Alexander-Univ. Erlangen-Nuremberg, Erlangen, Germany
pp. 74-81

Fuzzy statistical modeling of dynamic backgrounds for moving object detection in infrared videos (Abstract)

T. Bouwmans , Lab. of Math., Images&Applic., Univ. of La Rochelle - France, La Rochelle, France
F. El Baf , Lab. of Math., Images&Applic., Univ. of La Rochelle - France, La Rochelle, France
B. Vachon , Lab. of Math., Images&Applic., Univ. of La Rochelle - France, La Rochelle, France
pp. 60-65

Object recognition in 3D lidar data with recurrent neural network (Abstract)

D.V. Prokhorov , TTC-TEMA, Toyota Res. Inst. NA, Ann Arbor, MI, USA
pp. 9-15

Pedestrian association and localization in monocular FIR video sequence (Abstract)

Shunguang Wu , Sarnoff Corp., Princeton, NJ, USA
J. Eledath , Sarnoff Corp., Princeton, NJ, USA
M. Bansal , Sarnoff Corp., Princeton, NJ, USA
pp. 38-45

Appearance learning by adaptive Kalman filters for FLIR tracking (Abstract)

Guoliang Fan , Sch. of Electr.&Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
Xin Fan , Sch. of Electr.&Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
V. Venkataraman , Sch. of Electr.&Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
pp. 46-53

Dual domain auxiliary particle filter with integrated target signature update (Abstract)

J.P. Havlicek , Sch. of Electr.&Comput. Eng., Univ. of Oklahoma, Norman, OK, USA
C.M. Johnston , Sch. of Electr.&Comput. Eng., Univ. of Oklahoma, Norman, OK, USA
N. Mould , Sch. of Electr.&Comput. Eng., Univ. of Oklahoma, Norman, OK, USA
pp. 54-59

The HFB Face Database for Heterogeneous Face Biometrics research (Abstract)

S.Z. Li , Center for Biometrics&Security Res., Chinese Acad. of Sci., Beijing, China
Meng Ao , Center for Biometrics&Security Res., Chinese Acad. of Sci., Beijing, China
Zhen Lei , Center for Biometrics&Security Res., Chinese Acad. of Sci., Beijing, China
pp. 1-8

Table of contents (PDF)

pp. vii-viii

Welcome message (PDF)

pp. ix-x

Page frame segmentation for contextual advertising in print on demand books (Abstract)

Hanning Zhou , Amazon Inc., Seattle, WA, USA
Zongyi Liu , Amazon Inc., Seattle, WA, USA
pp. 17-22

Geo-location inference from image content and user tags (Abstract)

D. Joshi , Kodak Res. Labs., Rochester, NY, USA
Jie Yu , Kodak Res. Labs., Rochester, NY, USA
A. Gallagher , Kodak Res. Labs., Rochester, NY, USA
Jiebo Luo , Kodak Res. Labs., Rochester, NY, USA
pp. 55-62

Finding iconic images (Abstract)

T.L. Berg , Comput. Sci. Dept., SUNY Stony Brook, Stony Brook, NY, USA
pp. 1-8

Towards automated large scale discovery of image families (Abstract)

P. Welinder , Comput. Vision Lab., Caltech, Pasadena, CA, USA
P. Perona , Comput. Vision Lab., Caltech, Pasadena, CA, USA
M. Aly , Comput. Vision Lab., Caltech, Pasadena, CA, USA
pp. 9-16

Alignment of 3D point clouds to overhead images (Abstract)

S.M. Seitz , Univ. of Washington, Seattle, WA, USA
R.S. Kaminsky , Univ. of Washington, Seattle, WA, USA
pp. 63-70

Adventures in archiving and using three years of webcam images (Abstract)

R. Speyer , Dept. of Comput. Sci.&Eng., Washington Univ., St. Louis, MO, USA
R. Pless , Dept. of Comput. Sci.&Eng., Washington Univ., St. Louis, MO, USA
D. Ross , Dept. of Comput. Sci.&Eng., Washington Univ., St. Louis, MO, USA
W. Burgin , Dept. of Comput. Sci.&Eng., Washington Univ., St. Louis, MO, USA
N. Jacobs , Dept. of Comput. Sci.&Eng., Washington Univ., St. Louis, MO, USA
pp. 39-46

Towards unlocking web video: Automatic people tracking and clustering (Abstract)

P. Moreels , Ooyala Inc., Mountain View, CA, USA
A. Holub , Ooyala Inc., Mountain View, CA, USA
A. Makhanov , Ooyala Inc., Mountain View, CA, USA
Rui Yang , Ooyala Inc., Mountain View, CA, USA
A. Islam , Ooyala Inc., Mountain View, CA, USA
pp. 47-54

Cutout-search: Putting a name to the picture (Abstract)

D. Batra , Carnegie Mellon Univ., Pittsburgh, PA, USA
D. Parikh , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 23-30

Computer vision on tap (Abstract)

K. Chiu , MIT Media Lab., Cambridge, MA, USA
R. Raskar , MIT Media Lab., Cambridge, MA, USA
pp. 31-38

Table of contents (PDF)

pp. xi-xii

Human action recognition with extremities as semantic posture representation (Abstract)

E. Yu , Comput.&Vision Res. Center, Univ. of Texas at Austin, Austin, TX, USA
J.K. Aggarwal , Comput.&Vision Res. Center, Univ. of Texas at Austin, Austin, TX, USA
pp. 1-8

Incremental on-line semantic indexing for image retrieval in dynamic databases (Abstract)

S. Karthik , Center for Visual Inf. Technol., Int. Inst. of Inf. Technol. Hyderabad, Hyderabad, India
C. Pulla , Center for Visual Inf. Technol., Int. Inst. of Inf. Technol. Hyderabad, Hyderabad, India
C.V. Jawahar , Center for Visual Inf. Technol., Int. Inst. of Inf. Technol. Hyderabad, Hyderabad, India
pp. 9-16

A level set-based global shape prior and its application to image segmentation (Abstract)

Lei Zhang , Rensselaer Polytech. Inst., Troy, NY, USA
Qiang Ji , Rensselaer Polytech. Inst., Troy, NY, USA
pp. 17-22

Table of contents (PDF)

pp. xiii

HALF-SIFT: High-Accurate Localized Features for SIFT (Abstract)

K. Cordes , Inst. fur Informationsverarbeitung (TNT), Leibniz Univ. Hannover, Hannover, Germany
O. Muller , Inst. fur Informationsverarbeitung (TNT), Leibniz Univ. Hannover, Hannover, Germany
J. Ostermann , Inst. fur Informationsverarbeitung (TNT), Leibniz Univ. Hannover, Hannover, Germany
B. Rosenhahn , Inst. fur Informationsverarbeitung (TNT), Leibniz Univ. Hannover, Hannover, Germany
pp. 31-38

Incremental Bayesian learning of feature points from natural images (Abstract)

M. Toivanen , Dept. of Biomed. Eng.&Comput. Sci., Helsinki Univ. of Technol., Helsinki, Finland
J. Lampinen , Dept. of Biomed. Eng.&Comput. Sci., Helsinki Univ. of Technol., Helsinki, Finland
pp. 39-46

Fast features for time constrained object detection (Abstract)

L. Petersson , NICTA, Canberra, ACT, Australia
G. Overett , NICTA, Canberra, ACT, Australia
pp. 23-30

SUSurE: Speeded Up Surround Extrema feature detector and descriptor for realtime applications (Abstract)

W.W. Mayol-Cuevas , Dept. of Comput. Sci., Univ. of Bristol, Bristol, UK
M. Ebrahimi , Dept. of Comput. Sci., Univ. of Bristol, Bristol, UK
pp. 9-14

Robust feature matching in 2.3 (Abstract)

T. Drummond , Dept. of Eng., Univ. of Cambridge, Cambridge, UK
E. Rosten , Dept. of Eng., Univ. of Cambridge, Cambridge, UK
S. Taylor , Dept. of Eng., Univ. of Cambridge, Cambridge, UK
pp. 15-22

Welcome (PDF)

pp. xv

A bottom-up and top-down optimization framework for learning a compositional hierarchy of object classes (Abstract)

S. Fidler , Fac. of Comput.&Inf. Sci., Univ. of Ljubljana, Ljubljana, Slovenia
M. Boben , Fac. of Comput.&Inf. Sci., Univ. of Ljubljana, Ljubljana, Slovenia
A. Leonardis , Fac. of Comput.&Inf. Sci., Univ. of Ljubljana, Ljubljana, Slovenia
pp. 3

Predicate logic based image grammars for complex pattern recognition (Abstract)

V. Shet , Corp. Res., Siemens, Princeton, NJ, USA
C. Bahlmann , Corp. Res., Siemens, Princeton, NJ, USA
V. Ramesh , Corp. Res., Siemens, Princeton, NJ, USA
M. Singh , Corp. Res., Siemens, Princeton, NJ, USA
pp. 7

Stochastic representation and recognition of high-level group activities: Describing structural uncertainties in human activities (Abstract)

J.K. Aggarwal , Dept. of ECE, Univ. of Texas at Austin, Austin, TX, USA
M.S. Ryoo , Dept. of ECE, Univ. of Texas at Austin, Austin, TX, USA
pp. 11

Image parsing with stochastic grammar: The Lotus Hill dataset and inference scheme (Abstract)

B. Yao , Comput. Vision&Inf. Sci., Lotus Hill Inst., Ezhou, China
Xiong Yang , Comput. Vision&Inf. Sci., Lotus Hill Inst., Ezhou, China
Tianfu Wu , Comput. Vision&Inf. Sci., Lotus Hill Inst., Ezhou, China
pp. 8

Beyond one-to-one feature correspondence: The need for many-to-many matching and image abstraction (Abstract)

S. Dickinson , Dept. of Comput. Sci., Univ. of Toronto, Toronto, ON, Canada
pp. 12

Is there a general structure for grammars? (Abstract)

D. Mumford , Div. of Appl. Math., Brown Univ., Providence, RI, USA
pp. 4

Generative hierarchical models for image analysis (Abstract)

S. Geman , Div. of Appl. Math., Brown Univ., Providence, RI, USA
pp. 1

Inference and learning with hierarchical compositional models (Abstract)

I. Kokkinos , Lab. MAS, Ecole Centrale de Paris, Orsay, France
pp. 6

A syntax for image understanding (Abstract)

N. Ahuja , Dept. of Electr.&Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
pp. 9-10

Table of contents (PDF)

pp. xvi-xvii

Synchronization and rolling shutter compensation for consumer video camera arrays (Abstract)

W. Heidrich , Univ. of British Columbia, Vancouver, BC, Canada
D. Bradley , Univ. of British Columbia, Vancouver, BC, Canada
B. Atcheson , Univ. of British Columbia, Vancouver, BC, Canada
I. Ihrke , Univ. of British Columbia, Vancouver, BC, Canada
pp. 1-8

Shadow multiplexing for real-time silhouette extraction (Abstract)

T. Cuypers , Expertise Centre for Digital Media, Hasselt Univ. - tUL - IBBT, Hasselt, Belgium
J. Taelman , Expertise Centre for Digital Media, Hasselt Univ. - tUL - IBBT, Hasselt, Belgium
Y. Francken , Expertise Centre for Digital Media, Hasselt Univ. - tUL - IBBT, Hasselt, Belgium
P. Bekaert , Expertise Centre for Digital Media, Hasselt Univ. - tUL - IBBT, Hasselt, Belgium
pp. 61-68

Illustrating motion through DLP photography (Abstract)

S.G. Narasimhan , Carnegie Mellon Univ., Pittsburgh, PA, USA
S.J. Kappal , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 9-16

A projector-camera system for creating a display with water drops (Abstract)

P. Barnum , Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Narasimhan , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 17-23

Geometric video projector auto-calibration (Abstract)

S. Roy , DIRO, Univ. de Montreal, Montreal, QC, Canada
J. Drareni , DIRO, Univ. de Montreal, Montreal, QC, Canada
pp. 39-46

Multi-view reconstruction for projector camera systems based on bundle adjustment (Abstract)

R. Furuakwa , Fac. of Inf. Sci., Hiroshima City Univ., Hiroshima, Japan
pp. 69-76

A user-friendly method to geometrically calibrate projector-camera systems (Abstract)

S. Audet , Tokyo Inst. of Technol., Tokyo, Japan
M. Okutomi , Tokyo Inst. of Technol., Tokyo, Japan
pp. 47-54

Data handling displays (Abstract)

M. Lazarov , Univ. of California, Irvine, CA, USA
H. Pirsiavash , Univ. of California, Irvine, CA, USA
U. Mukherjee , Univ. of California, Irvine, CA, USA
B. Sajadi , Univ. of California, Irvine, CA, USA
A. Majumder , Univ. of California, Irvine, CA, USA
pp. 24-30

Transparent watermarking using bidirectional imaging (Abstract)

K.J. Dana , Dept. of Electr.&Comput. Eng., Rutgers Univ., Piscataway, NJ, USA
R. Makonahalli , Dept. of Electr.&Comput. Eng., Rutgers Univ., Piscataway, NJ, USA
G. Livescu , Dept. of Electr.&Comput. Eng., Rutgers Univ., Piscataway, NJ, USA
pp. 31-38

Color calibration of multi-projector displays through automatic optimization of hardware settings (Abstract)

Ruigang Yang , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Mao Ye , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
R.M. Steele , Center for Visualization&Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
pp. 55-60

Table of contents (PDF)

pp. xxi-xxii

Impact of involuntary subject movement on 3D face scans (Abstract)

P. Flynn , Univ. of Notre Dame, Notre Dame, IN, USA
C. Boehnen , Univ. of Notre Dame, Notre Dame, IN, USA
pp. 1-6

Remote audio/video acquisition for human signature detection (Abstract)

Tao Wang , Dept. of Comput. Sci., City Coll. of New York, New York, NY, USA
Zhigang Zhu , Dept. of Comput. Sci., City Coll. of New York, New York, NY, USA
Yufu Qu , Dept. of Comput. Sci., City Coll. of New York, New York, NY, USA
pp. 66-71

Posture invariant gender classification for 3D human models (Abstract)

M. Rioux , Nat. Res. Council of Canada, Ottawa, ON, Canada
Chang Shu , Nat. Res. Council of Canada, Ottawa, ON, Canada
S. Wuhrer , Nat. Res. Council of Canada, Ottawa, ON, Canada
pp. 33-38

Recognition of walking humans in 3D: Initial results (Abstract)

K. Yamauchi , Center for Res. in Intell. Syst., Univ. of California, Riverside, CA, USA
B. Bhanu , Center for Res. in Intell. Syst., Univ. of California, Riverside, CA, USA
pp. 45-52

In between 3D Active Appearance Models and 3D Morphable Models (Abstract)

M. Savvides , Biometrics Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
Jingu Heo , Biometrics Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 20-26

Face recognition at-a-distance based on sparse-stereo reconstruction (Abstract)

A. Ali , Univ. of Louisville, Louisville, KY, USA
A. Farag , Univ. of Louisville, Louisville, KY, USA
M. Miller , Univ. of Louisville, Louisville, KY, USA
T. Starr , Univ. of Louisville, Louisville, KY, USA
H. Rara , Univ. of Louisville, Louisville, KY, USA
S. Elhabian , Univ. of Louisville, Louisville, KY, USA
pp. 27-32

Measuring changes in face appearance through aging (Abstract)

M. Ortega , VARPA Group, Univ. of A Coruna, A Corua, Spain
pp. 107-113

A case for the average-half-face in 2D and 3D for face recognition (Abstract)

J.K. Aggarwal , Dept. of ECE, Univ. of Texas at Austin, Austin, TX, USA
J. Harguess , Dept. of ECE, Univ. of Texas at Austin, Austin, TX, USA
pp. 7-12

Evaluation of spatio-temporal regional features For 3D face analysis (Abstract)

Lijun Yin , Dept. of Comput. Sci., State Univ. of New York at Binghamton, Binghamton, NY, USA
Yi Sun , Dept. of Comput. Sci., State Univ. of New York at Binghamton, Binghamton, NY, USA
pp. 13-19

Combining 2D and 3D hand geometry features for biometric verification (Abstract)

D. Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Kowloon, China
V. Kanhangad , Dept. of Comput., Hong Kong Polytech. Univ., Kowloon, China
A. Kumar , Dept. of Comput., Hong Kong Polytech. Univ., Kowloon, China
pp. 39-44

Square Loss based regularized LDA for face recognition using image sets (Abstract)

Pengwei Hao , Center for Inf. Sci., Peking Univ., Beijing, China
Yanlin Geng , Center for Inf. Sci., Peking Univ., Beijing, China
pp. 99-106

Biometric data hiding: A 3 factor authentication approach to verify identity with a single image using steganography, encryption and matching (Abstract)

M. Savvides , Carnegie Mellon Univ., Pittsburgh, PA, USA
N. Agrawal , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 85-92

A method for selecting and ranking quality metrics for optimization of biometric recognition systems (Abstract)

N.A. Schmid , Dept. of Comput. Sci.&Electr. Eng., West Virginia Univ., Morgantown, WV, USA
F. Nicolo , Dept. of Comput. Sci.&Electr. Eng., West Virginia Univ., Morgantown, WV, USA
pp. 126-133

Global and local quality measures for NIR iris video (Abstract)

Jinyu Zuo , Lane Dept. of Comput. Sci.&Electr. Eng., West Virginia Univ., Morgantown, WV, USA
N.A. Schmid , Lane Dept. of Comput. Sci.&Electr. Eng., West Virginia Univ., Morgantown, WV, USA
pp. 120-125

A coding scheme for indexing multimodal biometric databases (Abstract)

A. Ross , West Virginia Univ., Morgantown, WV, USA
A. Gyaourova , West Virginia Univ., Morgantown, WV, USA
pp. 93-98

Identifying sensors from fingerprint images (Abstract)

N. Kalka , West Virginia Univ., Morgantown, WV, USA
B. Cukic , West Virginia Univ., Morgantown, WV, USA
A. Ross , West Virginia Univ., Morgantown, WV, USA
N. Bartlow , West Virginia Univ., Morgantown, WV, USA
pp. 78-84

Effect of plastic surgery on face recognition: A preliminary study (Abstract)

R. Singh , IIIT Delhi, Delhi, India
M. Vatsa , IIIT Delhi, Delhi, India
pp. 72-77

Table of contents (PDF)

pp. xxiii-xxiv

Welcome (PDF)

pp. xxv-xxvi

Social Signal Processing: Understanding social interactions through nonverbal behavior analysis (Abstract)

A. Vinciarelli , Idiap Res. Inst., Martigny, Switzerland
H. Salamin , Idiap Res. Inst., Martigny, Switzerland
pp. 42-49

Automatic recognition of fingerspelled words in British Sign Language (Abstract)

S. Liwicki , Sch. of Comput., Univ. of Leeds, Leeds, UK
M. Everingham , Sch. of Comput., Univ. of Leeds, Leeds, UK
pp. 50-57

Automatically detecting action units from faces of pain: Comparing shape and appearance features (Abstract)

P. Lucey , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. Cohn , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Lucey , Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 12-18

Robust facial action recognition from real-time 3D streams (Abstract)

S. Malassiotis , Centre for Res.&Technol. Hellas, Inf.&Telematics Inst., Thessaloniki, Greece
F. Tsalakanidou , Centre for Res.&Technol. Hellas, Inf.&Telematics Inst., Thessaloniki, Greece
pp. 4-11

Physiological modelling for improved reliability in silhouette-driven gradient-based hand tracking (Abstract)

J. Lasenby , Dept. of Eng., Univ. of Cambridge, Cambridge, UK
P. Kaimakis , Dept. of Eng., Univ. of Cambridge, Cambridge, UK
pp. 19-26

Action recognition via local descriptors and holistic features (Abstract)

Xinghua Sun , Nanjing Univ. of Sci.&Technol., Nanjing, China
pp. 58-65

Fusion by optimal dynamic mixtures of proposal distributions (Abstract)

T.X. Han , ECE Dept., Univ. of Missouri, Columbia, MO, USA
pp. 66-73

A framework for automated measurement of the intensity of non-posed Facial Action Units (Abstract)

M.H. Mahoor , Dept. of Electr.&Comput. Eng., Univ. of Denver, Denver, CO, USA
pp. 74-80

Head pose estimation using Spectral Regression Discriminant Analysis (Abstract)

Wei Chen , Philips Res., Eindhoven, Netherlands
Caifeng Shan , Philips Res., Eindhoven, Netherlands
pp. 116-123

An implicit spatiotemporal shape model for human activity localization and recognition (Abstract)

M. Pantic , Comput. Dept., Imperial Coll. London, London, UK
A. Oikonomopoulos , Comput. Dept., Imperial Coll. London, London, UK
pp. 27-33

Audiovisual event detection towards scene understanding (Abstract)

C. Segura , Tech. Univ. of Catalonia, Barcelona, Spain
C. Canton-Ferrer , Tech. Univ. of Catalonia, Barcelona, Spain
X. Giro , Tech. Univ. of Catalonia, Barcelona, Spain
J. Hernando , Tech. Univ. of Catalonia, Barcelona, Spain
T. Butko , Tech. Univ. of Catalonia, Barcelona, Spain
C. Nadeu , Tech. Univ. of Catalonia, Barcelona, Spain
J.R. Casas , Tech. Univ. of Catalonia, Barcelona, Spain
pp. 81-88

Auditory dialog analysis and understanding by generative modelling of interactional dynamics (Abstract)

C. Drioli , Dipt. di Inf., Univ. of Verona, Verona, Italy
A. Pesarin , Dipt. di Inf., Univ. of Verona, Verona, Italy
V. Murino , Dipt. di Inf., Univ. of Verona, Verona, Italy
A. Perina , Dipt. di Inf., Univ. of Verona, Verona, Italy
M. Cristani , Dipt. di Inf., Univ. of Verona, Verona, Italy
pp. 103-109

An alignment based similarity measure for hand detection in cluttered sign language video (Abstract)

S. Sclaroff , Dept. of Coumputer Sci., Boston Univ., Boston, MA, USA
A. Thangali , Dept. of Coumputer Sci., Boston Univ., Boston, MA, USA
pp. 89-96

Dominance detection in face-to-face conversations (Abstract)

J. Vitria , Dept. Mat., Univ. de Barcelona, Barcelona, Spain
S. Escalera , Dept. Mat., Univ. de Barcelona, Barcelona, Spain
P. Radeva , Dept. Mat., Univ. de Barcelona, Barcelona, Spain
pp. 97-102

Multi-modal laughter recognition in video conversations (Abstract)

E. Puertas , Univ. de Barcelona, Barcelona, Spain
O. Pujol , Univ. de Barcelona, Barcelona, Spain
P. Radeva , Univ. de Barcelona, Barcelona, Spain
S. Escalera , Univ. de Barcelona, Barcelona, Spain
pp. 110-115

Table of contents (PDF)

pp. xxvii-xxviii

Adaptive object classification in surveillance system by exploiting scene context (Abstract)

Zhen Lei , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Shengcai Liao , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Jitao Sang , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
S.Z. Li , Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
pp. 1-7

Multiple label prediction for image annotation with multiple Kernel correlation models (Abstract)

V. Honavar , Comput. Sci. Dept., Iowa State Univ., Ames, IA, USA
O. Yakhnenko , Comput. Sci. Dept., Iowa State Univ., Ames, IA, USA
pp. 8-15

Combining appearance and motion for human action classification in videos (Abstract)

P.S. Dhillon , CIS, Univ. of Pennsylvania, Philadelphia, PA, USA
pp. 22-29

Using closed captions to train activity recognizers that improve video retrieval (Abstract)

S. Gupta , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
R.J. Mooney , Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
pp. 30-37

Event detection using local binary pattern based dynamic textures (Abstract)

Yunqian Ma , Honeywell Int. Inc., Golden Valley, MN, USA
pp. 38-44

Nonparametric bottom-up saliency detection by self-resemblance (Abstract)

P. Milanfar , Electr. Eng. Dept., Univ. of California, Santa Cruz, Santa Cruz, CA, USA
Hae Jong Seo , Electr. Eng. Dept., Univ. of California, Santa Cruz, Santa Cruz, CA, USA
pp. 45-52

Categorization in natural time-varying image sequences (Abstract)

D. Estrin , Vision Lab., UCLA, Los Angeles, CA, USA
T. Ko , Vision Lab., UCLA, Los Angeles, CA, USA
S. Soatto , Vision Lab., UCLA, Los Angeles, CA, USA
pp. 53-60

Content and context-based multi-label image annotation (Abstract)

Xiangyang Xue , Shanghai Key Lab. of Intell. Inf. Process., Fudan Univ., Shanghai, China
Yuejie Zhang , Shanghai Key Lab. of Intell. Inf. Process., Fudan Univ., Shanghai, China
Yingbin Zheng , Shanghai Key Lab. of Intell. Inf. Process., Fudan Univ., Shanghai, China
Hong Lu , Shanghai Key Lab. of Intell. Inf. Process., Fudan Univ., Shanghai, China
pp. 61-68

Head and gaze dynamics in visual attention and context learning (Abstract)

A. Doshi , Lab. for Intell.&Safe Automobiles, Univ. of California, San Diego, CA, USA
M.M. Trivedi , Lab. for Intell.&Safe Automobiles, Univ. of California, San Diego, CA, USA
pp. 77-84

Efficient acquisition of human existence priors from motion trajectories (Abstract)

M. Kidode , Grad. Sch. of Inf. Sci., Nara Inst. of Sci.&Technol., Ikoma, Japan
H. Nakagawa , Grad. Sch. of Inf. Sci., Nara Inst. of Sci.&Technol., Ikoma, Japan
H. Habe , Grad. Sch. of Inf. Sci., Nara Inst. of Sci.&Technol., Ikoma, Japan
pp. 85-91

Mining discriminative adjectives and prepositions for natural scene recognition (Abstract)

Bangpeng Yao , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
Li Fei-Fei , Dept. of Comput. Sci., Princeton Univ., Princeton, NJ, USA
pp. 100-106

Table of contents (PDF)

pp. xxx-xxxii
104 ms
(Ver )