Search For:

Displaying 1-30 out of 30 total
Optimizing walking controllers for uncertain inputs and environments
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:July 2010
pp. 1-10
We introduce methods for optimizing physics-based walking controllers for robustness to uncertainty. Many unknown factors, such as external forces, control torques, and user control inputs, cannot be known in advance and must be treated as uncertain. These...
     
Likelihood Functions and Confidence Bounds for Total-Least-Squares Problems
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oscar Nestares, David J. Fleet, David J. Heeger
Issue Date:June 2000
pp. 1523
This paper addresses the derivation of likelihood functions and confidence bounds for problems involving over-determined linear systems with noise in all measurements, often referred to as total-least-squares (TLS). It has been shown previously that TLS pr...
 
Gaussian Process Dynamical Models for Human Motion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jack M. Wang, David J. Fleet, Aaron Hertzmann
Issue Date:February 2008
pp. 283-298
We introduce Gaussian process dynamical models (GPDM) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensionalmotion capture data. A GPDM is a latent variable model. It comprises a low-dimensio...
 
Physics-Based Person Tracking Using Simplified Lower-Body Dynamics
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Marcus A. Brubaker, David J. Fleet, Aaron Hertzmann
Issue Date:June 2007
pp. 1-8
We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact, generalizes naturally to...
 
Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oscar Nestares, David J. Fleet
Issue Date:December 2001
pp. 358
We describe a probabilistic framework for detecting and tracking motion boundaries. It builds on previous work [4] that used a particle filter to compute a posterior distribution over multiple, local motion models, one of which was specific for motion boun...
 
A Framework for Modeling Appearance Change in Image Sequences
Found in: Computer Vision, IEEE International Conference on
By Michael J. Black, David J. Fleet, Yaser Yacoob
Issue Date:January 1998
pp. 660
Image
 
Simultaneous Tracking and Activity Recognition
Found in: Tools with Artificial Intelligence, IEEE International Conference on
By Cristina Manfredotti,David J. Fleet,Howard J. Hamilton,Sandra Zilles
Issue Date:November 2011
pp. 189-196
Many tracking problems involve several distinct objects interacting with each other. We develop a framework that takes into account interactions between objects allowing the recognition of complex activities. In contrast to classic approaches that consider...
 
TurboPixels: Fast Superpixels Using Geometric Flows
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Alex Levinshtein, Adrian Stere, Kiriakos N. Kutulakos, David J. Fleet, Sven J. Dickinson, Kaleem Siddiqi
Issue Date:December 2009
pp. 2290-2297
We describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation ...
 
The Kneed Walker for human pose tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Marcus A. Brubaker, David J. Fleet
Issue Date:June 2008
pp. 1-8
The Kneed Walker is a physics-based model derived from a planar biomechanical characterization of human locomotion. By controlling torques at the knees, hips and torso, the model captures a full range of walking motions with foot contact and balance. Const...
 
Priors for People Tracking from Small Training Sets
Found in: Computer Vision, IEEE International Conference on
By Raquel Urtasun, David J. Fleet, Aaron Hertzmann, Pascal Fua
Issue Date:October 2005
pp. 403-410
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density fu...
 
Learning Parameterized Models of Image Motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael J. Black, Yaser Yacoob, Allan D. Jepson, David J. Fleet
Issue Date:June 1997
pp. 561
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many compl...
 
Computing Optical Flow with Physical Models of Brightness Variation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Horst W. Haussecker, David J. Fleet
Issue Date:June 2001
pp. 661-673
<p><b>Abstract</b>—Although most optical flow techniques presume brightness constancy, it is well-known that this constraint is often violated, producing poor estimates of image motion. This paper describes a generalized formulation of op...
 
Recursive Filters for Optical Flow
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David J. Fleet, Keith Langley
Issue Date:January 1995
pp. 61-67
<p><it>Abstract</it>—Working toward efficient (real-time) implementations of optical flow methods, we have applied simple recursive filters to achieve temporal smoothing and differentiation of image intensity, and to compute 2d flow from ...
 
Correction to
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jack M. Wang, David J. Fleet, Aaron Hertzmann
Issue Date:June 2008
pp. 1118
No summary available.
 
Model-Based 3D Hand Pose Estimation from Monocular Video
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Martin de La Gorce, David J. Fleet, Nikos Paragios
Issue Date:September 2011
pp. 1793-1805
A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture, and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation,...
 
Dynamical binary latent variable models for 3D human pose tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Graham W. Taylor, Leonid Sigal, David J. Fleet, Geoffrey E. Hinton
Issue Date:June 2010
pp. 631-638
We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of the imCRBM are as follows: (1) learning is linear in the num...
 
3D People Tracking with Gaussian Process Dynamical Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2006
pp. 238-245
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of human motion data, with a density function that gives higher probability to pos...
 
Probabilistic Detection and Tracking of Motion Discontinuities
Found in: Computer Vision, IEEE International Conference on
By Michael J. Black, David J. Fleet
Issue Date:September 1999
pp. 551
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities are represented using a non-linear generative model that explicitly encodes t...
 
Optimizing walking controllers
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:December 2009
pp. 1-2
This paper describes a method for optimizing the parameters of a physics-based controller for full-body, 3D walking. A modified version of the SIMBICON controller [Yin et al. 2007] is optimized for characters of varying body shape, walking speed and step l...
     
Monocular 3D Tracking of the Golf Swing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2005
pp. 1199
No summary available.
   
Model-based hand tracking with texture, shading and self-occlusions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Martin de La Gorce, Nikos Paragios, David J. Fleet
Issue Date:June 2008
pp. 1-8
A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation, ...
 
Monocular 3-D Tracking of the Golf Swing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2005
pp. 932-938
<p>We propose an approach to incorporating dynamic models into the human body tracking process that yields full 3-D reconstructions from monocular sequences. We formulate the tracking problem in terms of minimizing a differentiable criterion whose di...
 
Computing Optical Flow with Physical Models of Brightness Variation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Horst W. Haussecker, David J. Fleet
Issue Date:June 2000
pp. 2760
This paper exploits physical models of time-varying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with genera...
 
Hybrid Monte Carlo Filtering: Edge-Based People Tracking
Found in: Motion and Video Computing, IEEE Workshop on
By Eunice Poon, David J. Fleet
Issue Date:December 2002
pp. 151
Statistical inefficiency often limits the effectiveness of particle filters for high-dimensional Bayesian tracking problems. To improve sampling efficiency on continuous domains, we propose the use of a particle filter with hybrid Monte Carlo (HMC), an MCM...
 
Robust Online Appearance Models for Visual Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Allan D. Jepson, David J. Fleet, Thomas F. El-Maraghi
Issue Date:December 2001
pp. 415
We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2-frame motion informatio...
 
Robust Online Appearance Models for Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Allan D. Jepson, David J. Fleet, Thomas F. El-Maraghi
Issue Date:October 2003
pp. 1296-1311
<p><b>Abstract</b>—We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the ...
 
People Tracking Using Hybrid Monte Carlo Filtering
Found in: Computer Vision, IEEE International Conference on
By Kiam Choo, David J. Fleet
Issue Date:July 2001
pp. 321
Particle filters are used for hidden state estimation with nonlinear dynamical systems. The inference of 3-d human motion is a natural application, given the nonlinear dynamics of the body and the nonlinear relation between states and image observations. H...
 
Cartesian K-Means
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Mohammad Norouzi,David J. Fleet
Issue Date:June 2013
pp. 3017-3024
A fundamental limitation of quantization techniques like the k-means clustering algorithm is the storage and run-time cost associated with the large numbers of clusters required to keep quantization errors small and model fidelity high. We develop new mode...
 
Optimizing walking controllers for uncertain inputs and environments
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:July 2010
pp. 10-18
We introduce methods for optimizing physics-based walking controllers for robustness to uncertainty. Many unknown factors, such as external forces, control torques, and user control inputs, cannot be known in advance and must be treated as uncertain. These...
     
Optimizing walking controllers
Found in: ACM SIGGRAPH Asia 2009 papers (SIGGRAPH Asia '09)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:December 2009
pp. 1-6
This paper describes a method for optimizing the parameters of a physics-based controller for full-body, 3D walking. A modified version of the SIMBICON controller [Yin et al. 2007] is optimized for characters of varying body shape, walking speed and step l...
     
 1