Citations from Google Scholar, August 6, 2010

Included: 49 papers with more than 49 citations.

[PDF] ►The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
MJ Black, P Anandan - COMPUTER VISION AND IMAGE UNDERSTANDING, 1996 - csd.uoc.gr
Page 1. COMPUTER VISION AND IMAGE UNDERSTANDING Vol. 63, No. 1, January, pp.
75–104, 1996 ARTICLE NO. 0006 The Robust Estimation of Multiple Motions: Parametric
and Piecewise-Smooth Flow Fields M ICHAEL J. B LACK * ...
Cited by 912 - Related articles - Web Search - BL Direct - All 6 versions

EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation - ►nus.edu.sg [PDF] 
MJ Black, AD Jepson - International Journal of Computer Vision, 1998 - Springer
Page 1. International Journal of Computer Vision 26(1), 63–84 (1998) c 1998 Kluwer
Academic Publishers. Manufactured in The Netherlands. EigenTracking: Robust Matching
and Tracking of Articulated Objects Using a View-Based Representation ...
Cited by 848 - Related articles - Web Search - BL Direct - All 24 versions

Robust anisotropic diffusion - ►nus.edu.sg [PDF] 
MJ Black, G Sapiro, DH Marimont, D Heeger - Image Processing, IEEE Transactions on, 1998 - ieeexplore.ieee.org
Abstract—Relations between anisotropic diffusion and robust statistics are
described in this paper. Specifically, we show that anisotropic diffusion can be
seen as a robust estimation procedure that estimates a piecewise smooth ...
Cited by 756 - Related articles - Web Search - BL Direct - All 23 versions

Stochastic Tracking of 3D Human Figures Using 2D Image Motion - ►brown.edu [PDF] 
H Sidenbladh, M Black, D Fleet - LECTURE NOTES IN COMPUTER SCIENCE, 2000 - Springer
Abstract. A probabilistic method for tracking 3D articulated human figures in
monocular image sequences is presented. Within a Bayesian framework, we define a
generative model of image appearance, a robust likelihood function based on ...
Cited by 507 - Related articles - Web Search - BL Direct - All 7 versions

On the Unification of Line Processes, Outlier Rejection, and Robust Statistics with Applications in … - ►jgaa.info [PDF] 
MJ Black, A Rangarajan - International Journal of Computer Vision, 1996 - ingentaconnect.com
Page 1. InternationalJournalofComputerVision 03˙BLK June6, 1996 19:56
International Journal of Computer Vision 19(1), 57–91 (1996) c 1996 Kluwer
Academic Publishers. Manufactured in The Netherlands. ...
Cited by 400 - Related articles - Web Search - BL Direct - All 19 versions

Cardboard people: a parameterized model of articulated image motion - ►brown.edu [PDF] 
SX Ju, MJ Black, Y Yacoob - Automatic Face and Gesture Recognition, 1996., Proceedings …, 1996 - ieeexplore.ieee.org
We extend the work of Black and Yucoob on the track- ing and recognition of
human facial expressions using parameterized models ($optical $ow to deal with
the articulated motion of human limbs. We define U "card- hoard perJon ...
Cited by 382 - Related articles - Web Search - All 19 versions

Tracking and recognizing rigid and non-rigid facial motions usinglocal parametric models of image … - ►nus.edu.sg [PDF] 
MJ Black, Y Yacoob - Computer Vision, 1995. Proceedings., Fifth International …, 1995 - ieeexplore.ieee.org
This paper explores the use of local parametrized mod- els of image motion for
recovering and recognizing the non-rigid and articulated morion of human faces.
Parametricjow models for example afine) are popu- lar for estimating motion ...
Cited by 371 - Related articles - Web Search - All 18 versions

Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion - ►nus.edu.sg [PDF] 
MJ Black, Y Yacoob - International Journal of Computer Vision, 1997 - Springer
Page 1. International Journal of Computer Vision KL480-02-Black August 9, 1997
14:33 International Journal of Computer Vision 25(1), 23–48 (1997) c 1997 Kluwer
Academic Publishers. Manufactured in The Netherlands. ...
Cited by 341 - Related articles - Web Search - BL Direct - All 17 versions

Parameterized modeling and recognition of activities - ►weizmann.ac.il [PDF] 
Y Yacoob, MJ Black - Computer Vision, 1998. Sixth International Conference on, 1998 - ieeexplore.ieee.org
A framework for modeling and recognition of tem- poral activities is proposed.
The modeling of sets of exemplar activities is achieved by parameteriz- ing
their representation in the form of principal components. Recognition of ...
Cited by 321 - Related articles - Web Search - BL Direct - All 23 versions

A framework for the robust estimation of optical flow - ►jgaa.info [PS] 
MJ Black, P Anandan - Computer Vision, 1993. Proceedings., Fourth International …, 1993 - ieeexplore.ieee.org
Abstract We conszder the problem of robustly estzmatzng op- tical flow from a
paw of zinages uszng a new frame- work based on robust estimation whzch
addresses iizolatzons of the brzghtness constancy and spatzal smoothness ...
Cited by 309 - Related articles - Web Search - All 9 versions

Mixture models for optical flow computation - ►toronto.edu [PDF] 
A Jepson, MJ Black - Computer Vision and Pattern Recognition, 1993. Proceedings …, 1993 - ieeexplore.ieee.org
Abstract The coiiiputation of optical fiow relies on merg- ing infortnation
available over an image patch to foriri an estimate of 2D image velocity at a
point. This merging process raises a host of issue.^, which include the ...
Cited by 261 - Related articles - Web Search - Library Search - BL Direct - All 14 versions

Fields of Experts: A Framework for Learning Image Priors - ►ucl.ac.uk [PDF] 
S Roth, M Black - IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND …, 2005 - doi.ieeecomputersociety.org
We develop a framework for learning generic, expressive image priors that
capture the statistics of natural scenes and can be used for a variety of
machine vision tasks. The approach extends traditional Markov Random Field ...
Cited by 259 - Related articles - Web Search - BL Direct - All 20 versions

Tracking Loose-limbed People - ►jgaa.info [PDF] 
L Sigal, S Bhatia, S Roth, MJ Black, M Isard - time - doi.ieeecomputersociety.org
We pose the problem of 3D human tracking as one of in- ference in a graphical
model. Unlike traditional kinematic tree representations, our model of the body
is a collection of loosely-connected limbs. Conditional probabilities ...
Cited by 259 - Related articles - Web Search - BL Direct - All 20 versions

Implicit Probabilistic Models of Human Motion for Synthesis and Tracking - ►brown.edu [PDF] 
H Sidenbladh, MJ Black, L Sigal - LECTURE NOTES IN COMPUTER SCIENCE, 2002 - Springer
Abstract. This paper addresses the problem of probabilistically model- ing 3D
human motion for synthesis and tracking. Given the high dimen- sional nature of
human motion, learning an explicit probabilistic model from available ...
Cited by 235 - Related articles - Web Search - BL Direct - All 11 versions

Estimating optical flow in segmented images using variable-orderparametric models with local … - ►jgaa.info [PDF] 
MJ Black, AD Jepson - Pattern Analysis and Machine Intelligence, IEEE Transactions …, 1996 - ieeexplore.ieee.org
Abstract-This paper presents a new model for estimating optical flow based on
the motion of planar regions plus local deformations. The approach exploits
brightness information to organize and constrain the interpretation of the ...
Cited by 181 - Related articles - Web Search - BL Direct - All 15 versions

Robust dynamic motion estimation over time - ►brown.edu [PDF] 
MJ Black, P Anandan - Computer Vision and Pattern Recognition, 1991. Proceedings …, 1991 - ieeexplore.ieee.org
This paper presents a novel apprwch io incremen- tally estimating trisual moiion
over a sequence of images. We siad by formulaling conrimints on image moiion io
account for ibe possibility of mrl- iipk motions. This ir achieued by ...
Cited by 174 - Related articles - Web Search - All 10 versions

A probabilistic framework for matching temporal trajectories: CONDENSATION-based recognition of … - ►brown.edu [PDF] 
MJ Black, AD Jepson - LECTURE NOTES IN COMPUTER SCIENCE, 1998 - Springer
Abstract. The recognition of human gestures and facial expressions in image
sequences is an important and challenging problem that enables a host of
human-computer interaction applications. This paper describes a framework ...
Cited by 168 - Related articles - Web Search - BL Direct - All 9 versions

[PDF] ►A database and evaluation methodology for optical flow
… , D Scharstein, JP Lewis, S Roth, MJ Black, R … - Proc. ICCV, 2007 - research.microsoft.com
The quantitative evaluation of optical flow algorithms by Barron et al. led to
significant advances in the performance of optical flow methods. The challenges
for optical flow today go beyond the datasets and evaluation methods pro- ...
Cited by 167 - Related articles - View as HTML - All 18 versions

[PDF] ►Robust incremental optical flow
MJ Black - Yale University, New Haven, CT, 1992 - jgaa.info
This thesis addresses the problem of recovering 2D image velocity, or optical
flow, ro- bustly over long image sequences. We develop a robust estimation
framework for improv- ing the reliability of motion estimates and an ...
Cited by 159 - Related articles - View as HTML - Web Search - All 11 versions

[PDF] ►Skin and Bones: Multi-Layer, Locally Affine, Optical Flow and Regularization with Transparency
SX Ju, MJ Black, AD Jepson - IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND …, 1996 - cs.brown.edu
This paper describes a new method for estimating op- tical flow that strikes a
balance between the flexibil- ity of local dense computationsand the robustness
and accuracy of global parameterized flow models. An affine model of image ...
Cited by 135 - Related articles - View as HTML - Web Search - BL Direct - All 13 versions

[PDF] ►Robustly estimating changes in image appearance
MJ Black, DJ Fleet, Y Yacoob - Computer Vision and Image Understanding, 2000 - cs.brown.edu
Computer Vision and Image Understanding 78, 8–31 (2000)
doi:10.1006/cviu.1999.0825, available online at http://www.idealibrary.com on
... Xerox Palo Alto Research Center, 3333 Coyote Hill Rd., Palo Alto, ...
Cited by 134 - Related articles - Web Search - BL Direct - All 18 versions

[PDF] ►Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion
L Sigal, MJ Black - Brown Univertsity TR, 2006 - cs.brown.edu
Page 1. HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation
of Articulated Human Motion Leonid Sigal and Michael J. Black Department of Computer
Science Brown University Providence, Rhode Island 02912 ...
Cited by 122 - Related articles - View as HTML - Web Search - All 6 versions

Robust principal component analysis for computer vision - ►jgaa.info [PDF] 
F De la Torre, MJ Black - ICCV’01, 2001 - doi.ieeecomputersociety.org
Page 1. Robust Principal Component Analysis for Computer Vision Fernando
De la Torre £ Michael J. Black Ý £ Departament de Comunicacions i Teoria
del Senyal, Escola d’Enginyeria la Salle, Universitat ...
Cited by 120 - Related articles - Web Search - All 15 versions

Learning parameterized models of image motion - ►brown.edu [PDF] 
M Black, Y Yacoob, AD Jepson, DJ Fleet - Computer Vision and Pattern Recognition, 1997. Proceedings., …, 1997 - ieeexplore.ieee.org
A f?umeworkfor learning parumeterized models oj‘op- tical flow from image
sequences is presented. A class of motions is represented by U set of orthogonul
basis $ow fields that are computed froni a training set using priiicipal ...
Cited by 108 - Related articles - Web Search - BL Direct - All 20 versions

A Framework for Robust Subspace Learning - ►brown.edu [PDF] 
F De la Torre, MJ Black - International Journal of Computer Vision, 2003 - Springer
Page 1. International Journal of Computer Vision 54(1/2/3), 117–142,
2003 c 2003 Kluwer Academic Publishers. Manufactured in The Netherlands.
A Framework for Robust Subspace Learning FERNANDO ...
Cited by 107 - Related articles - Web Search - BL Direct - All 14 versions

Learning image statistics for Bayesian tracking - ►nus.edu.sg [PDF] 
H Sidenbladh, MJ Black - Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE …, 2001 - ieeexplore.ieee.org
Abstract This paper describes a framework for learning probabilistic models of
objects and scenes and for exploiting these mod- els for tracking complex,
deformable, or articulated objects in image sequences. We focus on the ...
Cited by 104 - Related articles - Web Search - All 16 versions

Learning the Statistics of People in Images and Video - ►jgaa.info [PDF] 
H Sidenbladh, MJ Black - International Journal of Computer Vision, 2003 - Springer
Page 1. International Journal of Computer Vision 54(1/2/3), 183–209, 2003 c 2003
Kluwer Academic Publishers. Manufactured in The Netherlands. Learning the Statistics
of People in Images and Video HEDVIG SIDENBLADH ∗ ...
Cited by 102 - Related articles - Web Search - BL Direct - All 13 versions

Bayesian population decoding of motor cortical activity using a Kalman filter- ►brown.edu [PDF] 
W Wu, Y Gao, E Bienenstock, JP Donoghue, MJ Black - Neural Computation, 2006 - MIT Press
Page 1. LETTER Communicated by Garrett Stanley Bayesian Population Decoding
of Motor Cortical Activity Using a Kalman Filter Wei Wu weiwu@dam.brown.
edu Yun Gao gao@dam.brown.edu Division of Applied ...
Cited by 100 - Related articles - Web Search - BL Direct - All 18 versions

[PDF] ►A quantitative evaluation of video-based 3D person tracking
AO Balan, L Sigal, MJ Black - IEEE Workshop on VSPETS, 2005 - citeseerx.ist.psu.edu
The Bayesian estimation of 3D human motion from video sequences is
quantitatively evaluated using synchronized, multi-camera, calibrated video and
3D ground truth poses acquired with a commercial motion capture system. ...
Cited by 90 - Related articles - View as HTML - Web Search - All 13 versions

Design and Use of Linear Models for Image Motion Analysis - ►brown.edu [PDF] 
DJ Fleet, MJ Black, Y Yacoob, AD Jepson - International Journal of Computer Vision, 2000 - Springer
International Journal of Computer Vision 36(3), 171–193, 2000 c 2000 Kluwer
Academic Publishers. Manufactured in The Netherlands. ... Design and Use of
Linear Models for Image Motion Analysis ... DAVID J. FLEET Department of ...
Cited by 86 - Related articles - Web Search - BL Direct - All 16 versions

Combining intensity and motion for incremental segmentation and tracking over long image sequences - ►brown.edu [PDF] 
MJ Black - Proc. European Conf. Computer Vision, 1992 - Springer
Abstract. This paper presents a method for incrementally segmenting images over
time using both intensity and motion information. This is done by formulating a
model of physically significant image resgions using local constraints on ...
Cited by 83 - Related articles - Web Search - All 11 versions

[PDF] ►Attractive people: Assembling loose-limbed models using non-parametric belief propagation
L Sigal, M Isard, BH Sigelman, MJ Black - Advances in Neural Information Processing Systems, 2003 - atcp07.cs.brown.edu
Page 1. Attractive People: Assembling Loose-Limbed Models using
Non-parametric Belief Propagation Leonid Sigal Department of Computer
Science Brown University Providence, RI 02912 ls@cs.brown.edu ...
Cited by 80 - Related articles - View as HTML - Web Search - All 12 versions

Recursive non-linear estimation of discontinuous flow fields - ►jgaa.info [PDF] 
MJ Black - Third European Conference on Computer Vision, 1994 - Springer
Many approaches for estimating optical flow have focused on the analysis of
motion between two frames in an image sequence while others have attempted to
deal with spatiotemporal information by processing long sequences in batch ...
Cited by 80 - Related articles - Web Search - All 9 versions

Probabilistic detection and tracking of motion discontinuities - ►brown.edu [PDF] 
MJ Black, DJ Fleet - iccv 1999- doi.ieeecs.org
We propose a Bayesian framework for representing and recognizing local image
motion in terms of two primitive models: translation and motion discontinu- ity.
Motion discontinuities are represented using a non-linear generative model ...
Cited by 80 - Related articles - Web Search - All 17 versions

Probabilistic Detection and Tracking of Motion Boundaries - ►brown.edu [PDF] 
MJ Black, DJ Fleet - International Journal of Computer Vision, 2000 - Springer
International Journal of Computer Vision 38(3), 231–245, 2000 c 2000 Kluwer
Academic Publishers. Manufactured in The Netherlands. ... Probabilistic
Detection and Tracking of Motion Boundaries ... MICHAEL J. BLACK Xerox ...
Cited by 79 - Related articles - Web Search - BL Direct - All 14 versions

Recognizing temporal trajectories using the condensation algorithm - ►brown.edu [PDF] 
MJ Black, AD Jepson - Automatic Face and Gesture Recognition, 1998. Proceedings. …, 1998 - ieeexplore.ieee.org
The recognitionof humangestures in image sequences
isanimportantandchallengingproblemthatenablesa hostof
human-computerinteractionapplications. This paper describes an incremental ...
Cited by 78 - Related articles - Web Search - All 14 versions

Modeling and decoding motor cortical activity using a switching Kalman filter - ►brown.edu [PDF] 
W Wu, MJ Black, D Mumford, Y Gao, E Bienenstock, … - Biomedical Engineering, IEEE Transactions on, 2004 - ieeexplore.ieee.org
Abstract—We present a switching Kalman filter model for the real-time
inference of hand kinematics from a population of motor cortical neurons. Firing
rates are modeled as a Gaussian mixture where the mean of each Gaussian ...
Cited by 76 - Related articles - Web Search - All 17 versions

On the spatial statistics of optical flow- ►brown.edu [PDF] 
S Roth, MJ Black - International Journal of Computer Vision, 2007 - Springer
International Journal of Computer Vision 74(1), 33–50, 2007 c 2007 Springer
Science + Business Media, LLC. Manufactured in the United States. DOI:
10.1007/s11263-006-0016-x ... On the Spatial Statistics of Optical Flow
Cited by 76 - Related articles - Web Search - BL Direct - All 31 versions

Automatic Detection and Tracking of Human Motion with a View-Based Representation - ►brown.edu [PDF] 
R Fablet, MJ Black - LECTURE NOTES IN COMPUTER SCIENCE, 2002 - Springer
Abstract. This paper proposes a solution for the automatic detection and
tracking of human motion in image sequences. Due to the complexity of the human
body and its motion, automatic detection of 3D human motion remains an ...
Cited by 68 - Related articles - Web Search - BL Direct - All 13 versions

[PDF] ►Learning and tracking cyclic human motion
D Ormoneit, H Sidenbladh, MJ Black, T Hastie - Advances in Neural Information Processing Systems, 2001 - cs.brown.edu
Page 1. Learning and Tracking Cyclic Human Motion D. Ormoneit Dept. of
Computer Science Stanford University Stanford, CA 94305 ormoneit@cs.stanford.
edu H. Sidenbladh Royal Institute of Technology ...
Cited by 66 - Related articles - View as HTML - Web Search - BL Direct - All 27 versions

[PDF] Measure locally, reason globally: Occlusion-sensitive articulated pose …
L Sigal, MJ Black - CVPR [9] MW Lee and I. Cohen.“Human upper body …, 2004 - Citeseer
Part-based tree-structured models have been widely used for 2D articulated human
pose-estimation. These ap- proaches admit efficient inference algorithms while captur- ing the
important kinematic constraints of the human body as a graphical model. These methods ...
Cited by 66 - Related articles - View as HTML - All 13 versions

A framework for modeling the appearance of 3D articulated figures - ►brown.edu [PDF] 
H Sidenbladh, F De la Torre, MJ Black - Automatic Face and Gesture Recognition, 2000. Proceedings. …, 2000 - ieeexplore.ieee.org
This paper describes a framework for constructing a lin- ear subspace model of
image appearance for complex ar- ticulated 3D figures such as humans and other
animals. A commercial motion capture system provides 3D data that is ...
Cited by 64 - Related articles - Web Search - All 20 versions

[PDF] ►On the variability of manual spike sorting
F Wood, MJ Black, C Vargas-Irwin, M … - IEEE Transactions on Biomedical Engineering, 2004 - cs.brown.edu
Abstract—The analysis of action potentials, or “spikes,” is central to
systems neuroscience research. Spikes are typically identified from raw
waveforms manually for off-line analysis or automatically by ...
Cited by 57 - Related articles - View as HTML - All 20 versions

Summarization of videotaped presentations: automatic analysis ofmotion and gesture - ►brown.edu [PDF] 
SX Ju, MJ Black, S Minneman, D Kimber - Circuits and Systems for Video Technology, IEEE Transactions …, 1998 - ieeexplore.ieee.org
Abstract— This paper presents an automatic system for an- alyzing and
annotating video sequences of technical talks. Our method uses a robust motion
estimation technique to detect key frames and segment the video sequence ...
Cited by 62 - Related articles - Web Search - BL Direct - All 8 versions

Probabilistic inference of hand motion from neural activity in motor cortex- ►nips.cc [PDF] 
Y Gao, MJ Black, E Bienenstock, S Shoham, JP … - Advances in Neural Information Processing Systems 14: …, 2002 - books.google.com
Probabilistic Inference of Hand Motion from Neural Activity in Motor Cortex Y.
Gao* MJ Blackt E. Bienenstock*§ S. Shoham 11 JP Donoghue §'Division of Applied
Mathematics, Brown University, Providence, RI 029 1 2 . of Computer ...
Cited by 53 - Related articles - Web Search - BL Direct - All 26 versions

[PDF] ►A Computational and Evolutionary Perspective on the Role of Representation in Vision
MJ Tarr, MJ Black - CVGIP IMAGE UNDERSTANDING, 1994 - jgaa.info
66 DIALOGUE where successes have led to useful and robust vision sys- tems.
Moreover, this is not at the exclusion of the purpos- ive approach, but rather
suggests a common ground that we believe to be more fertile than either ...
Cited by 55 - Related articles - Web Search - BL Direct - All 6 versions

Detailed human shape and pose from images
AO Balan, L Sigal, MJ Black, JE Davis, HW … - 2007 IEEE Conference …, 2007 - computer.org
Much of the research on video-based human motion cap- ture assumes the body shape is known
a priori and is rep- resented coarsely (eg using cylinders or superquadrics to model limbs). These
body models stand in sharp contrast to the richly detailed 3D body models used by the ...
Cited by 53 - Related articles - All 7 versions

[PDF] Explaining optical flow events with parameterized spatio-temporal models
MJ Black - Proceedings of the IEEE Computer Society Conference …, 1999 - Citeseer
A spatio-temporal representation for complex optical flow events is developed that generalizes
traditional parameterized motion models (eg affine). These gen- erative spatio-temporal models
may be non-linear or stochastic and are event-specific in that they charac- terize a ...
Cited by 51 - Related articles - View as HTML - BL Direct - All 18 versions

Edges as outliers: Anisotropic smoothing using local image statistics  
MJ Black, G Sapiro - Lecture notes in computer science, 1999 - Springer
Abstract. Edges are viewed as statistical outliers with respect to local image gradient
magnitudes. Within local image regions we compute a robust statistical measure of the gradient
variation and use this in an anisotropic diffusion framework to determine a spatially ...
Cited by 50 - Related articles - BL Direct - All 5 versions