The Community for Technology Leaders
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. (2004)
Washington, D.C., USA
June 27, 2004 to July 2, 2004
ISSN: 1063-6919
ISBN: 0-7695-2158-4
TABLE OF CONTENTS

Welcome (PDF)

pp. 0_19

Automatic view recognition in echocardiogram videos using parts-based representation (PDF)

S. Ebadollahi , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Shih-Fu Chang , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
pp. II-2-II-9 Vol.2

Elastic-string models for representation and analysis of planar shapes (PDF)

W. Mio , Dept. of Math., Florida State Univ., Tallahassee, FL, USA
pp. II-10-II-15 Vol.2

View independent human body pose estimation from a single perspective image (PDF)

V. Parameswaran , Center for Autom. Res., Maryland Univ., College Park, MD, USA
R. Chellappa , Center for Autom. Res., Maryland Univ., College Park, MD, USA
pp. II-16-II-22 Vol.2

Distortion estimation techniques in solving visual CAPTCHAs (PDF)

G. Moy , Areto Associates, Sherman Oaks, CA, USA
N. Jones , Areto Associates, Sherman Oaks, CA, USA
C. Harkless , Areto Associates, Sherman Oaks, CA, USA
R. Potter , Areto Associates, Sherman Oaks, CA, USA
pp. II-23-II-28 Vol.2

Feature-centric evaluation for efficient cascaded object detection (PDF)

H. Schneiderman , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-29-II-36 Vol.2

Is bottom-up attention useful for object recognition? (PDF)

U. Rutishauser , Comput. & Neural Syst., California Inst. of Technol., Pasadena, CA, USA
D. Walther , Comput. & Neural Syst., California Inst. of Technol., Pasadena, CA, USA
C. Koch , Comput. & Neural Syst., California Inst. of Technol., Pasadena, CA, USA
P. Perona , Comput. & Neural Syst., California Inst. of Technol., Pasadena, CA, USA
pp. II-37-II-44 Vol.2

Cyclic articulated human motion tracking by sequential ancestral simulation (PDF)

Cheng Chang , Dept. of Electr. & Comput. Eng.,, Illinois Univ., Chicago, IL, USA
R. Ansari , Dept. of Electr. & Comput. Eng.,, Illinois Univ., Chicago, IL, USA
A. Khokhar , Dept. of Electr. & Comput. Eng.,, Illinois Univ., Chicago, IL, USA
pp. II-45-II-52 Vol.2

Learning object detection from a small number of examples: the importance of good features (PDF)

K. Levi , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
Y. Weiss , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
pp. II-53-II-60 Vol.2

Shape representation and classification using the Poisson equation (PDF)

L. Gorelick , Dept. of Comput. Sci. & Appl. Math, Weizmann Inst. of Sci., Rehovot, Israel
M. Galun , Dept. of Comput. Sci. & Appl. Math, Weizmann Inst. of Sci., Rehovot, Israel
pp. II-61-II-67 Vol.2

Models of large population recognition performance (PDF)

P. Grother , Image Group, Inf. Technol. Lab., Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
P.J. Phillips , Image Group, Inf. Technol. Lab., Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
pp. II-68-II-75 Vol.2

Searching the Web with mobile images for location recognition (PDF)

T. Yeh , MITCSAIL, Cambridge, MA, USA
K. Tollmar , MITCSAIL, Cambridge, MA, USA
T. Darrell , MITCSAIL, Cambridge, MA, USA
pp. II-76-II-81 Vol.2

Parts-based 3D object classification (PDF)

D. Huber , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Kapuria , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Donamukkala , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hebert , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-82-II-89 Vol.2

Scale-invariant shape features for recognition of object categories (PDF)

F. Jurie , GRAVIR, INRIA-CNRS, Montbonnot, France
C. Schmid , GRAVIR, INRIA-CNRS, Montbonnot, France
pp. II-90-II-96 Vol.2

Learning methods for generic object recognition with invariance to pose and lighting (PDF)

Y. LeCun , Courant Inst., New York Univ., NY, USA
Fu Jie Huang , Courant Inst., New York Univ., NY, USA
pp. II-97-104 Vol.2

Integrating multiple model views for object recognition (PDF)

V. Ferrari , Comput. Vision Group, ETH, Zurich, Switzerland
pp. II-105-II-112 Vol.2

Extraction and integration of window in a 3D building model from ground view images (PDF)

Sung Chun Lee , Inst. for Robotics & Intelligent Syst., Southern California Univ., Los Angeles, CA, USA
R. Nevatia , Inst. for Robotics & Intelligent Syst., Southern California Univ., Los Angeles, CA, USA
pp. II-113-II-120 Vol.2

Linear model hashing and batch RANSAC for rapid and accurate object recognition (PDF)

Y. Shan , Sarnoff Corp., Princeton, NJ, USA
B. Matei , Sarnoff Corp., Princeton, NJ, USA
H.S. Sawhney , Sarnoff Corp., Princeton, NJ, USA
R. Kumar , Sarnoff Corp., Princeton, NJ, USA
pp. II-121-II-128 Vol.2

A model for dynamic shape and its applications (PDF)

Che-Bin Liu , Beckman Inst., Illinois Univ., Urbana, IL, USA
N. Ahuja , Beckman Inst., Illinois Univ., Urbana, IL, USA
pp. II-129-II-134 Vol.2

Jitter camera: high resolution video from a low resolution detector (PDF)

M. Ben-Ezra , Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
A. Zomet , Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
S.K. Nayar , Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
pp. II-135-II-142 Vol.2

The method of vector fields for catadioptric sensor design with applications to panoramic imaging (PDF)

R.A. Hicks , Dept. of Mathematics, Drexel Univ., Philadelphia, PA, USA
R.K. Perline , Dept. of Mathematics, Drexel Univ., Philadelphia, PA, USA
pp. II-143-II-150 Vol.2

High-zoom video hallucination by exploiting spatio-temporal regularities (PDF)

G. Dedeoglu , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. August , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-151-II-158 Vol.2

Eye typing off the shelf (PDF)

D.W. Hansen , Dept. of Innovation, IT Univ., Copenhagen, Denmark
pp. II-159-II-164 Vol.2

Probability models for high dynamic range imaging (PDF)

C. Pal , Microsoft Res., Redmond, WA, USA
R. Szeliski , Microsoft Res., Redmond, WA, USA
M. Uyttendaele , Microsoft Res., Redmond, WA, USA
N. Jojic , Microsoft Res., Redmond, WA, USA
pp. II-173-II-180 Vol.2

Improving object classification in far-field video (PDF)

B. Bose , Comput. Sci. & Artificial Intelligence Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
E. Grimson , Comput. Sci. & Artificial Intelligence Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. II-181-II-188 Vol.2

Brightness perception, dynamic range and noise: a unifying model for adaptive image sensors (PDF)

V. Brajovic , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-189-II-196 Vol.2

Uncontrolled modulation imaging (PDF)

Y.Y. Schechner , Dept. of Electr. Eng., Israel Inst. Technol., Haifa, Israel
pp. II-197-II-204 Vol.2

Bridging the gaps between cameras (PDF)

D. Makris , Digital Imaging Res. Centre, Kingston Univ., UK
T. Ellis , Digital Imaging Res. Centre, Kingston Univ., UK
J. Black , Digital Imaging Res. Centre, Kingston Univ., UK
pp. II-205-II-210 Vol.2

3D head tracking based on recognition and interpolation using a time-of-flight depth sensor (PDF)

S.B. Gokturk , Canesta Inc., San Jose, CA, USA
C. Tomasi , Canesta Inc., San Jose, CA, USA
pp. II-211-II-217 Vol.2

Calibrating an air-ground control system from motion correspondences (PDF)

R. Rao , Gen. Robotics & Active Sensory Perception Lab., Pennsylvania Univ., Philadelphia, PA, USA
C.J. Taylor , Gen. Robotics & Active Sensory Perception Lab., Pennsylvania Univ., Philadelphia, PA, USA
V. Kumar , Gen. Robotics & Active Sensory Perception Lab., Pennsylvania Univ., Philadelphia, PA, USA
pp. II-218-II-225 Vol.2

Recovering shape and reflectance model of non-lambertian objects from multiple views (PDF)

Tianli Yu , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Ning Xu , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
N. Ahuja , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
pp. II-226-II-233 Vol.2

Computing depth under ambient illumination using multi-shuttered light (PDF)

H. Gonzalez-Banos , Honda Res. Inst., Mountain View, CA, USA
J. Davis , Honda Res. Inst., Mountain View, CA, USA
pp. II-234-II-241 Vol.2

Point matching as a classification problem for fast and robust object pose estimation (PDF)

V. Lepetit , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
J. Pilet , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
P. Fua , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
pp. II-244-II-250 Vol.2

Feature selection for classifying high-dimensional numerical data (PDF)

Yimin Wu , Dept. of Comput. Sci. & Eng., SUNY, Buffalo, NY, USA
Aidong Zhang , Dept. of Comput. Sci. & Eng., SUNY, Buffalo, NY, USA
pp. II-251-II-258 Vol.2

Random sampling LDA for face recognition (PDF)

Xiaogang Wang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
pp. II-259-II-265 Vol.2

BoostMap: A method for efficient approximate similarity rankings (PDF)

V. Athitsos , Dept. of Comput. Sci., Boston Univ., MA, USA
J. Alon , Dept. of Comput. Sci., Boston Univ., MA, USA
S. Sclaroff , Dept. of Comput. Sci., Boston Univ., MA, USA
G. Kollios , Dept. of Comput. Sci., Boston Univ., MA, USA
pp. II-268-II-275 Vol.2

Automatic cascade training with perturbation bias (PDF)

Jie Sun , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
J.M. Rehg , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
A. Bobick , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
pp. II-276-II-283 Vol.2

A discriminative learning framework with pairwise constraints for video object classification (PDF)

Rong Yan , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Jian Zhang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Jie Yang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Hauptmann , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-284-II-291 Vol.2

High-speed videography using a dense camera array (PDF)

B. Wilburn , Dept. of Electr. Eng., Stanford Univ., CA, USA
pp. II-294-II-301 Vol.2

Motion-based background subtraction using adaptive kernel density estimation (PDF)

A. Mittal , Siemens Corp. Res., Princeton, NJ, USA
pp. II-302-II-309 Vol.2

Motion segmentation with missing data using PowerFactorization and GPCA (PDF)

R. Vidal , Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
pp. II-310-II-316 Vol.2

An unsupervised, online learning framework for moving object detection (PDF)

V. Nair , Centre for Intelligent Machines, McGiIl Univ., Montreal, Que., Canada
J.J. Clark , Centre for Intelligent Machines, McGiIl Univ., Montreal, Que., Canada
pp. II-317-II-324 Vol.2

Recovering human body configurations: combining segmentation and recognition (PDF)

G. Mori , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
Xiaofeng Ren , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
pp. II-326-II-333 Vol.2

Proposal maps driven MCMC for estimating human body pose in static images (PDF)

Mun Wai Lee , Inst. for Robotics & Intelligent Syst., Southern California Univ., Los Angeles, CA, USA
I. Cohen , Inst. for Robotics & Intelligent Syst., Southern California Univ., Los Angeles, CA, USA
pp. II-334-II-341 Vol.2

Representation and matching of articulated shapes (PDF)

Jiayong Zhang , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Collins , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Yanxi Liu , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-342-II-349 Vol.2

2D-shape analysis using conformal mapping (PDF)

E. Sharon , Div. of Appl. Math., Brown Univ., Providence, RI, USA
D. Mumford , Div. of Appl. Math., Brown Univ., Providence, RI, USA
pp. II-350-II-357 Vol.2

Faster graph-theoretic image processing via small-world and quadtree topologies (PDF)

L. Grady , Dept. of Imaging & Visualization, Siemens Corp. Res. Inc., Princeton, NJ, USA
pp. II-360-II-365 Vol.2

Detecting and reading text in natural scenes (PDF)

Xiangrong Chen , Dept. of Stat., California Univ., Los Angeles, CA, USA
A.L. Yuille , Dept. of Stat., California Univ., Los Angeles, CA, USA
pp. II-366-II-373 Vol.2

Bayesian face recognition using support vector machine and face clustering (PDF)

Zhifeng Li , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China
pp. II-374-II-380 Vol.2

Novel region-based modeling for human detection within highly dynamic aquatic environment (PDF)

How-Lung Eng , Inst. for Infocomm Res., Singapore, Singapore
Junxian Wang , Inst. for Infocomm Res., Singapore, Singapore
A.H. Kam , Inst. for Infocomm Res., Singapore, Singapore
Wei-Yun Yau , Inst. for Infocomm Res., Singapore, Singapore
pp. II-390-II-397 Vol.2

Tracking multiple humans in crowded environment (PDF)

Tao Zhao , Sarnoff Corp., Princeton, NJ, USA
pp. II-406-II-413 Vol.2

Efficient model-based linear head motion recovery from movies (PDF)

Jian Yao , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
Wai-Kuen Cham , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
pp. II-414-II-421 Vol.2

Multiobjective data clustering (PDF)

M.H.C. Law , Dept. of Comput. Sci. & Eng., Michigan State Univ., MI, USA
A.P. Topchy , Dept. of Comput. Sci. & Eng., Michigan State Univ., MI, USA
A.K. Jain , Dept. of Comput. Sci. & Eng., Michigan State Univ., MI, USA
pp. II-424-II-430 Vol.2

An invariant, closed-form solution for matching sets of 3D lines (PDF)

B. Kamgar-Parsi , Office of Naval Res., Arlington, VA, USA
pp. II-431-II-436 Vol.2

Spatially coherent clustering using graph cuts (PDF)

R. Zabih , Cornell Univ., Ithaca, NY, USA
pp. II-437-II-444 Vol.2

A probabilistic framework for combining tracking algorithms (PDF)

I. Leichter , Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
M. Lindenbaum , Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
E. Rivlin , Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
pp. II-445-II-451 Vol.2

Local smoothing for manifold learning (PDF)

JinHyeong Park , Dept. of Comput. Sci. & Eng., Pennsylvania State Univ., University Park, PA, USA
pp. II-452-II-459 Vol.2

Grouping with bias revisited (PDF)

R. Nock , DSI, Antilles-Guyane Univ., Schoelcher, France
pp. II-460-II-465 Vol.2

Graphical models for graph matching (PDF)

T.S. Caetano , Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada
T. Caelli , Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada
pp. II-466-II-473 Vol.2

Linear projection methods in face recognition under unconstrained illuminations: a comparative study (PDF)

Qi Li , Dept. of Comput. Inf. & Sci., Delaware Univ., Newark, DE, USA
pp. II-474-II-481 Vol.2

Towards robust structure-based enhancement and horizon picking in 3-D seismic data (PDF)

S.M. O'Malley , Dept. of Comput. Sci., Houston Univ., TX, USA
I.A. Kakadiaris , Dept. of Comput. Sci., Houston Univ., TX, USA
pp. II-482-II-489 Vol.2

Object-based image retrieval using the statistical structure of images (PDF)

D. Hoiem , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-490-II-497 Vol.2

Generalized quotient image (PDF)

Haitao Wang , Inst. of Autom., Chinese Acad. of Sci., Beijing, China
pp. II-498-II-505 Vol.2

PCA-SIFT: a more distinctive representation for local image descriptors (PDF)

Yan Ke , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Sukthankar , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-506-II-513 Vol.2

Biventricular myocardial kinematics based on tagged MRI from anatomical NURBS models (PDF)

N.J. Tustison , Cardiovascular Image Anal. Lab., Washington Univ., St. Louis, MO, USA
D. Abendschein , Cardiovascular Image Anal. Lab., Washington Univ., St. Louis, MO, USA
A.A. Amini , Cardiovascular Image Anal. Lab., Washington Univ., St. Louis, MO, USA
pp. II-514-II-519 Vol.2

Probabilistic expression analysis on manifolds (PDF)

Ya Chang , California Univ., Santa Barbara, CA, USA
Changbo Hu , California Univ., Santa Barbara, CA, USA
M. Turk , California Univ., Santa Barbara, CA, USA
pp. II-520-II-527 Vol.2

Invariant operators, small samples, and the bias-variance dilemma (PDF)

X. Shi , Dept. of Comput. Eng., California Univ., Santa Cruz, CA, USA
R. Manduchi , Dept. of Comput. Eng., California Univ., Santa Cruz, CA, USA
pp. II-528-II-534 Vol.2

Real-time combined 2D+3D active appearance models (PDF)

Jing Xiao , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Baker , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
I. Matthews , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-535-II-542 Vol.2

On the distribution of saliency (PDF)

A. Berengolts , Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
M. Lindenbaum , Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
pp. II-543-II-549 Vol.2

Approximation of canonical sets and their applications to 2D view simplification (PDF)

T. Denton , Drexel Univ., Philadelphia, PA, USA
J. Abrahamson , Drexel Univ., Philadelphia, PA, USA
A. Shokoufandeh , Drexel Univ., Philadelphia, PA, USA
pp. II-550-II-557 Vol.2

Learning classifiers from imbalanced data based on biased minimax probability machine (PDF)

Kaizhu Huang , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
Haiqin Yang , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
I. King , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
M.R. Lyu , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
pp. II-558-II-563 Vol.2

Dual-space linear discriminant analysis for face recognition (PDF)

Xiaogang Wang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
pp. II-564-II-569 Vol.2

Learning distance functions for image retrieval (PDF)

T. Hertz , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
A. Bar-Hillel , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
D. Weinshall , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
pp. II-570-II-577 Vol.2

Cue integration through discriminative accumulation (PDF)

M.E. Nilsback , Dept. of Numerical Anal. & Comput. Sci., KTH, Stockholm, Sweden
B. Caputo , Dept. of Numerical Anal. & Comput. Sci., KTH, Stockholm, Sweden
pp. II-578-II-585 Vol.2

Orthogonal complement component analysis for positive samples in SVM based relevance feedback image retrieval (PDF)

Dacheng Tao , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
pp. II-586-II-591 Vol.2

Robust subspace clustering by combined use of kNND metric and SVD algorithm (PDF)

Qifa Ke , Dept. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kanade , Dept. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-592-II-599 Vol.2

Direct super-resolution and registration using raw CFA images (PDF)

T. Gotoh , Graduate Sch. of Sci. & Eng., Tokyo Inst. of Technol., Japan
M. Okutomi , Graduate Sch. of Sci. & Eng., Tokyo Inst. of Technol., Japan
pp. II-600-II-607 Vol.2

Variational mixture smoothing for non-linear dynamical systems (PDF)

C. Sminchisescu , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
A. Jepson , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
pp. II-608-II-615 Vol.2

Self-normalized linear tests (PDF)

S. Gangputra , Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
pp. II-616-II-622 Vol.2

Bayesian fusion of camera metadata cues in semantic scene classification (PDF)

M. Boutell , Dept. of Comput. Sci., Rochester Univ., NY, USA
pp. II-623-II-630 Vol.2

Minimum effective dimension for mixtures of subspaces: a robust GPCA algorithm and its applications (PDF)

Kun Huang , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Yi Ma , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
pp. II-631-II-638 Vol.2

Learning a restricted Bayesian network for object detection (PDF)

H. Schneiderman , Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-639-II-646 Vol.2

Random sampling based SVM for relevance feedback image retrieval (PDF)

Dacheng Tao , Dept. of Information Eng., Chinese Univ. of Hong Kong, China
Xiaoou Tang , Dept. of Information Eng., Chinese Univ. of Hong Kong, China
pp. II-647-II-652 Vol.2

Reconstructing open surfaces from unorganized data points (PDF)

J.E. Solem , Sch. of Technol. & Soc., Malmo Univ., Sweden
A. Heyden , Sch. of Technol. & Soc., Malmo Univ., Sweden
pp. II-653-II-660 Vol.2

Inference of multiple subspaces from high-dimensional data and application to multibody grouping (PDF)

Zhimin Fan , Dept. of Autom., Tsinghua Univ., China
Jie Zhou , Dept. of Autom., Tsinghua Univ., China
pp. II-661-II-666 Vol.2

Efficient graphical models for processing images (PDF)

M.F. Tappen , Comput. Sci. & Artificial Intelligence Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
B.C. Russell , Comput. Sci. & Artificial Intelligence Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
W.T. Freeman , Comput. Sci. & Artificial Intelligence Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. II-673-II-680 Vol.2

Inferring 3D body pose from silhouettes using activity manifold learning (PDF)

A. Elgammal , Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA
Chan-Su Lee , Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA
pp. II-681-II-688 Vol.2

A fast multigrid implicit algorithm for the evolution of geodesic active contours (PDF)

G. Papandreou , Sch. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece
P. Maragos , Sch. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece
pp. II-689-II-694 Vol.2

Multiscale conditional random fields for image labeling (PDF)

Xuming He , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
R.S. Zemel , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
M.A. Carreira-Perpinan , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
pp. II-695-II-702 Vol.2

Studies on silhouette quality and gait recognition (PDF)

Zongyi Liu , Comput. Sci. & Eng., South Florida Univ., Tampa, FL, USA
L. Malave , Comput. Sci. & Eng., South Florida Univ., Tampa, FL, USA
S. Sarkar , Comput. Sci. & Eng., South Florida Univ., Tampa, FL, USA
pp. II-704-II-711 Vol.2

Face localization via hierarchical CONDENSATION with Fisher boosting feature selection (PDF)

Jilin Tu , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Zhenqui Zhang , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Zhihong Zeng , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
T. Huang , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
pp. II-719-II-724 Vol.2

Shaping receptive fields for affine invariance (PDF)

S. Ravela , Massachusetts Inst. of Technol., Cambridge, MA, USA
pp. II-725-II-730 Vol.2

Multigrid and multi-level Swendsen-Wang cuts for hierarchic graph partition (PDF)

A. Barbu , Dept. of Comput. Sci., California Univ., Los Angeles, CA, USA
pp. II-731-II-738 Vol.2

A graphical model framework for coupling MRFs and deformable models (PDF)

Rui Huang , Div. of Comput. & Inf. Sci., Rutgers Univ., New Brunswick, NJ, USA
V. Pavlovic , Div. of Comput. & Inf. Sci., Rutgers Univ., New Brunswick, NJ, USA
D.N. Metaxas , Div. of Comput. & Inf. Sci., Rutgers Univ., New Brunswick, NJ, USA
pp. II-739-II-746 Vol.2

Flexible spatial models for grouping local image features (PDF)

G. Carneiro , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
A.D. Jepson , Dept. of Comput. Sci., Toronto Univ., Ont., Canada
pp. II-747-II-754 Vol.2

Asymmetrically boosted HMM for speech reading (PDF)

Pei Yin , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
I. Essa , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
J.M. Rehg , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
pp. II-755-II-761 Vol.2

Sharing features: efficient boosting procedures for multiclass object detection (PDF)

A. Torralba , Comput. Sci. & Artificial Intelligence Lab., MIT, Cambridge, MA, USA
K.P. Murphy , Comput. Sci. & Artificial Intelligence Lab., MIT, Cambridge, MA, USA
W.T. Freeman , Comput. Sci. & Artificial Intelligence Lab., MIT, Cambridge, MA, USA
pp. II-762-II-769 Vol.2

Scalable discriminant feature selection for image retrieval and recognition (PDF)

N. Vasconcelos , Stat. Visual Comput. Lab., California Univ., San Diego, CA, USA
pp. II-770-II-775 Vol.2

What image information is important in silhouette-based gait recognition? (PDF)

G.V. Veres , Sch. of Electron. & Comput. Sci., Southampton Univ., UK
L. Gordon , Sch. of Electron. & Comput. Sci., Southampton Univ., UK
J.N. Carter , Sch. of Electron. & Comput. Sci., Southampton Univ., UK
M.S. Nixon , Sch. of Electron. & Comput. Sci., Southampton Univ., UK
pp. II-776-II-782 Vol.2

Modelling the effects of walking speed on appearance-based gait recognition (PDF)

R. Tanawongsuwan , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
A. Bobick , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
pp. II-783-II-790 Vol.2

Efficient search of faces from complex line drawings (PDF)

Jianzhuang Liu , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
pp. II-791-II-796 Vol.2

A discriminative feature space for detecting and recognizing faces (PDF)

A. Hadid , Dept. of Electr. & Inf. Eng., Oulu Univ., Finland
M. Pietikainen , Dept. of Electr. & Inf. Eng., Oulu Univ., Finland
T. Ahonen , Dept. of Electr. & Inf. Eng., Oulu Univ., Finland
pp. II-797-II-804 Vol.2

Probabilistic identity characterization for face recognition (PDF)

S.K. Zhou , Dept. of Electr. & Comput. Eng., Maryland Univ., College Park, MD, USA
R. Chellappa , Dept. of Electr. & Comput. Eng., Maryland Univ., College Park, MD, USA
pp. II-805-II-812 Vol.2

Effect of colorspace transformation, the illuminance component, and color modeling on skin detection (PDF)

S. Jayaram , Dept. of Comput. Sci., North Carolina Univ., Charlotte, NC, USA
S. Schmugge , Dept. of Comput. Sci., North Carolina Univ., Charlotte, NC, USA
M.C. Shin , Dept. of Comput. Sci., North Carolina Univ., Charlotte, NC, USA
pp. II-813-II-818 Vol.2

Detecting unusual activity in video (PDF)

Hua Zhong , Dept. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-819-II-826 Vol.2

A cognitive vision system for action recognition in office environments (PDF)

C. Bauckhage , Fac. of Technol., Bielefeld Univ., Germany
M. Hanheide , Fac. of Technol., Bielefeld Univ., Germany
S. Wrede , Fac. of Technol., Bielefeld Univ., Germany
G. Sagerer , Fac. of Technol., Bielefeld Univ., Germany
pp. II-827-II-833 Vol.2

"Corefaces" - robust shift invariant PCA based correlation filter for illumination tolerant face recognition (PDF)

M. Sawides , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
B.V.K.V. Kumar , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
P.K. Khosla , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-834-II-841 Vol.2

Statistical feature fusion for gait-based human recognition (PDF)

Ju Han , Center for Res. in Intelligent Syst., California Univ., Riverside, CA, USA
B. Bhanu , Center for Res. in Intelligent Syst., California Univ., Riverside, CA, USA
pp. II-842-II-847 Vol.2

Names and faces in the news (PDF)

T.L. Berg , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
A.C. Berg , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
J. Edwards , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
M. Maire , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
R. White , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
Yee-Whye Teh , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
E. Learned-Miller , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
D.A. Forsyth , Div. of Comput. Sci., California Univ., Berkeley, CA, USA
pp. II-848-II-854 Vol.2

A GMM parts based face representation for improved verification through relevance adaptation (PDF)

S. Lucey , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Tsuhan Chen , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-855-II-861 Vol.2

Propagation networks for recognition of partially ordered sequential action (PDF)

Yifan Shi , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
Yan Huang , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
D. Minnen , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
A. Bobick , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
I. Essa , GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
pp. II-862-II-869 Vol.2

Facial event classification with task oriented dynamic Bayesian network (PDF)

Haisong Gu , Dept. of Comput. Sci., Nevada Univ., Reno, NV, USA
pp. II-870-II-875 Vol.2

Probabilistic data association methods in visual tracking of groups (PDF)

G. Gennari , Inf. Eng., Padova Univ., Italy
pp. II-876-II-881 Vol.2

3D human pose from silhouettes by relevance vector regression (PDF)

A. Agarwal , GRAVIR-INRIA-CNRS, Montbonnot, France
B. Triggs , GRAVIR-INRIA-CNRS, Montbonnot, France
pp. II-882-II-888 Vol.2

Local facial asymmetry for expression classification (PDF)

S. Mitra , Dept. of Stat., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. II-889-II-894 Vol.2

Extraction and recognition of periodically deforming objects by continuous, spatio-temporal shape description (PDF)

S.D. Mowbray , Dept. of Electron. & Comput. Sci., Southampton Univ., UK
M.S. Nixon , Dept. of Electron. & Comput. Sci., Southampton Univ., UK
pp. II-895-II-901 Vol.2

Frame synchronization and multi-level subspace analysis for video based face recognition (PDF)

Xiaoou Tang , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China
Zhifeng Li , Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China
pp. II-902-II-907 Vol.2

Hierarchical decision making scheme for sports video categorisation with temporal post-processing (PDF)

E. Jaser , Centre for Vision, Speech & Signal Process., Surrey Univ., Guildford, UK
J. Kittler , Centre for Vision, Speech & Signal Process., Surrey Univ., Guildford, UK
W. Christmas , Centre for Vision, Speech & Signal Process., Surrey Univ., Guildford, UK
pp. II-908-II-913 Vol.2

Segmenting, modeling, and matching video clips containing multiple moving objects (PDF)

F. Rothganger , Dept. of Comput. Sci., Illinois Univ., Urbana, IL, USA
S. Lazebnik , Dept. of Comput. Sci., Illinois Univ., Urbana, IL, USA
pp. II-914-II-921 Vol.2

From facial expression to level of interest: a spatio-temporal approach (PDF)

M. Yeasin , Comput. Sci., State Univ. of New York, NY, USA
pp. II-922-II-927 Vol.2

Integrating and employing multiple levels of zoom for activity recognition (PDF)

P. Smith , Comput. Vision Lab., Central Florida Univ., Orlando, FL, USA
M. Shah , Comput. Vision Lab., Central Florida Univ., Orlando, FL, USA
N. da Vitoria Lobo , Comput. Vision Lab., Central Florida Univ., Orlando, FL, USA
pp. II-928-II-935 Vol.2

Radiometric calibration from a single image (PDF)

S. Lin , Microsoft Res. Asia, Beijing, China
pp. II-938-II-945 Vol.2

Color lines: image specific color representation (PDF)

I. Omer , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
M. Werman , Sch. of Comput. Sci. & Eng., Hebrew Univ., Jerusalem, Israel
pp. II-946-II-953 Vol.2

Learning to segment images using region-based perceptual features (PDF)

J. Kaufhold , Visualization & Comput. Vision Lab., Gen. Electr. Global Res. Center, Niskayuna, NY, USA
A. Hoogs , Visualization & Comput. Vision Lab., Gen. Electr. Global Res. Center, Niskayuna, NY, USA
pp. II-954-II-961 Vol.2

Alignment of continuous video onto 3D point clouds (Abstract)

W. Zhao , Sarnoff Corp., Princeton, NJ, USA
D. Nister , Sarnoff Corp., Princeton, NJ, USA
S. Hsu , Sarnoff Corp., Princeton, NJ, USA
pp. 0

Motion layer extraction in the presence of occlusion using graph cut (PDF)

Jiangjian Xiao , Comput. Vision Lab, Central Florida Univ., Orlando, FL, USA
M. Shah , Comput. Vision Lab, Central Florida Univ., Orlando, FL, USA
pp. II-972-II-979 Vol.2

A Rao-Blackwellized particle filter for EigenTracking (PDF)

Zia Khan , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
T. Balch , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
F. Dellaert , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
pp. II-980-II-986 Vol.2

Unsupervised learning of image manifolds by semidefinite programming (PDF)

K.Q. Weinberger , Dept. of Comput. & Inf. Sci., Pennsylvania Univ., Philadelphia, PA, USA
L.K. Saul , Dept. of Comput. & Inf. Sci., Pennsylvania Univ., Philadelphia, PA, USA
pp. II-988-II-995 Vol.2

Hidden semantic concept discovery in region based image retrieval (PDF)

Ruofei Zhang , Dept. of Comput. Sci., State Univ. of New York, Binghamton, NY, USA
Zhongfei Zhang , Dept. of Comput. Sci., State Univ. of New York, Binghamton, NY, USA
pp. II-996-II-1001 Vol.2

Multiple Bernoulli relevance models for image and video annotation (PDF)

S.L. Feng , Multimedia Indexing & Retrieval Group, Massachusetts Univ., Amherst, MA, USA
R. Manmatha , Multimedia Indexing & Retrieval Group, Massachusetts Univ., Amherst, MA, USA
V. Lavrenko , Multimedia Indexing & Retrieval Group, Massachusetts Univ., Amherst, MA, USA
pp. II-1002-II-1009 Vol.2

Thermal face recognition in an operational scenario (PDF)

D.A. Socolinsky , Equinox Corp., Baltimore, MD, USA
pp. II-1012-II-1019 Vol.2

Audio-visual based emotion recognition - a new approach (PDF)

Mingli Song , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Jiajun Bu , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Chun Chen , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Nan Li , Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
pp. II-1020-II-1025 Vol.2

Value directed learning of gestures and facial displays (PDF)

J. Hoey , Dept. of Comput. Sci., British Columbia Univ., Vancouver, BC, Canada
J.J. Little , Dept. of Comput. Sci., British Columbia Univ., Vancouver, BC, Canada
pp. II-1026-II-1033 Vol.2

Accurate face models from uncalibrated and ill-lit video sequences (PDF)

M. Dimitrijevic , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
S. Ilic , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
P. Fua , Comput. Vision Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
pp. II-1034-II-1041 Vol.2
Session 8A: Retrieval/Annotation

Unsupervised Learning of Image Manifolds by Semidefinite Programming (Abstract)

Kilian Q. Weinberger , University of Pennsylvania
Lawrence K. Saul , University of Pennsylvania
pp. 988-995

Hidden Semantic Concept Discovery in Region Based Image Retrieval (Abstract)

Ruofei Zhang , State University of New York at Binghamton
Zhongfei (Mark) Zhang , State University of New York at Binghamton
pp. 996-1001

Multiple Bernoulli Relevance Models for Image and Video Annotation (Abstract)

S. L. Feng , University of Massachusetts at Amherst
R. Manmatha , University of Massachusetts at Amherst
V. Lavrenko , University of Massachusetts at Amherst
pp. 1002-1009
Session 8B: Applications - 2

Thermal Face Recognition in an Operational Scenario (Abstract)

Diego A. Socolinsky , Equinox Corporation
Andrea Selinger , Equinox Corporation
pp. 1012-1019

Audio-Visual Based Emotion Recognition — A New Approach (Abstract)

Mingli Song , Zhejiang University
Jiajun Bu , Zhejiang University
Chun Chen , Zhejiang University
Nan Li , Zhejiang University
pp. 1020-1025

Value Directed Learning of Gestures and Facial Displays (Abstract)

Jesse Hoey , University of British Columbia
James J. Little , University of British Columbia
pp. 1026-1033

Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences (Abstract)

M. Dimitrijevic , Swiss Federal Institute of Technology
S. Ilic , Swiss Federal Institute of Technology
P. Fua , Swiss Federal Institute of Technology
pp. 1034-1041
Author Index

Author Index (PDF)

pp. 1043-1049
80 ms
(Ver 3.3 (11022016))