A design for high-performance flash disks (2009)
Andrew Birrell, Michael Isard, Chuck Thacker, Ted Wobber
Most commodity flash disks exhibit very poor performance when presented with writes that are not sequentially ordered. We argue that performance can be significantly improved through the addition of...
Yuan Yu, Michael Isard, Dennis Fetterly, Mihai Budiu, Úlfar Erlingsson, Pradeep Kumar, ...
DryadLINQ is a system and a set of language extensions that enable a new programming model for large scale distributed computing. It generalizes previous execution environments such as SQL,...
University of Pennsylvania (2008)
Leonidas J. Guibas, Herbert Edelsbrunner, Jeff Erickson, Michael Isard, John Hershberger, Christian Jensen, ...
DIMITRIS METAXAS
Leonid Sigal, Benjamin H. Sigelman, Michael Isard, Michael J. Black
The detection and pose estimation of people in images and video is made challenging by the variability of human appearance, the complexity of natural scenes, and the high dimensionality of...
Leonid Sigal, Benjamin H. Sigelman, Michael Isard, Michael J. Black
The detection and pose estimation of people in images and video is made challenging by the variability of human appearance, the complexity of natural scenes, and the high dimensionality of...
Michael Isard, Andrew Birrell, Mihai Budiu, Dennis Fetterly, Yuan Yu
Dryad is a general-purpose distributed execution engine for coarse-grain data-parallel applications. A Dryad application combines computational “vertices ” with communication “channels ” to...
Semantics of transactional memory and automatic mutual exclusion (2008)
Martín Abadi, Andrew Birrell, Tim Harris, Michael Isard
Software Transactional Memory (STM) is an attractive basis for the development of language features for concurrent programming. However, the semantics of these features can be delicate and...
D Position, Attitude and Shape Input Using Video Tracking of Hands and Lips (2007)
Recent developments in video-tracking allow the outlines of moving, natural objects in a video-camera input stream to be tracked live, at full video-rate. Previous systems have been available to do...
John Maccormick, Michael Isard
Partitioned sampling is a technique which was introduced in [17] for avoiding the high cost of particle filters when tracking more than one object. In fact this technique can reduce the curse of...
Object retrieval with large vocabularies and fast spatial matching (2007)
James Philbin, Michael Isard, Josef Sivic, Andrew Zisserman
In this paper, we present a large-scale object retrieval system. The user supplies a query object by selecting a region of a query image, and the system returns a ranked list of images that contain...
A Design for High-Performance Flash Disks (2005)
Andrew Birrell, Michael Isard, Chuck Thacker, Ted Wobber
Most commodity flash disks exhibit very poor performance when presented with writes that are not sequentially ordered. We argue that performance can be significantly improved through the addition of...
Dense motion and disparity estimation via loopy belief propagation (2005)
Michael Isard, John Maccormick
Abstract. We describe a method for computing a dense estimate of motion and disparity, given a stereo video sequence containing moving non-rigid objects. In contrast to previous approaches, motion...
Tracking Loose-limbed People (2004)
Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michael J. Black, Michael Isard
We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loosely-connected limbs....
3D Human Limb Detection Using Space Carving and Multi-view Eigen Models (2004)
Sidharth Bhatia, Leonid Sigal, Michael Isard, Michael J. Black
In this paper, we integrate space carving and eigen detection methods to develop a bottom-up 3D human limb detector. We model the body in terms of its constituent body parts; here we focus on the...
3D Human Limb Detection Using Space Carving and Multi-view Eigen Models (2004)
Sidharth Bhatia, Leonid Sigal, Michael Isard, Michael J. Black
In this paper, we integrate space carving and eigen detection methods to develop a bottom-up 3D human limb detector. We model the body in terms of its constituent body parts; here we focus on the...
A cooperative Internet backup scheme (2003)
Mark Lillibridge, Sameh Elnikety, Andrew Birrell, Mike Burrows, Michael Isard
Permission is granted for noncommercial reproduction of the work for educational or research purposes.
Attractive People: Assembling Loose-Limbed Models Using Non-parametric Belief Propagation (2003)
Leonid Sigal, Michael Isard, Benjamin H. Sigelman, Michael J. Black
The detection and pose estimation of people in images and video is made challenging by the variability of human appearance, the complexity of natural scenes, and the high dimensionality of...
A Cooperative Internet Backup Scheme (2003)
Mark Lillibridge Sameh, Sameh Elnikety, Andrew Birrell, Mike Burrows, Michael Isard
We present a novel peer-to-peer backup technique that allows computers connected to the Internet to back up their data cooperatively: Each computer has a set of partner computers, which collectively...
Automatic camera calibration from a single manhattan image (2002)
Jonathan Deutscher, Michael Isard, John Maccormick
Abstract. We present a completely automatic method for obtaining the approximate calibration of a camera (alignment to a world frame and focal length) from a single image of an unknown scene,...
Automatic Camera Calibration from a Single Manhattan Image (2002)
Jonathan Deutscher, Michael Isard, John Maccormick
We present a completely automatic method for obtaining the approximate calibration of a camera (alignment to a world frame and focal length) from a single image of an unknown scene, provided only...
Learning and classification of complex dynamics (2000)
Ben North, Andrew Blake, Michael Isard, Jens Rittscher
AbstractÐStandard, exact techniques based on likelihood maximization are available for learning Auto-Regressive Process models of dynamical processes. The uncertainty of observations obtained from...
Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking (2000)
John Maccormick, Michael Isard
Partitioned sampling is a technique which was introduced in [17] for avoiding the high cost of particle lters when tracking more than one object. In fact this technique can reduce the curse of...
Learning and classification of complex dynamics (2000)
Ben North, Andrew Blake, Michael Isard, Jens Rittscher
AbstractÐStandard, exact techniques based on likelihood maximization are available for learning Auto-Regressive Process models of dynamical processes. The uncertainty of observations obtained from...
CONDENSATION - conditional density propagation for visual tracking (1998)
The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous...
Icondensation: Unifying low-level and high-level tracking in a stochastic framework (1998)
. Tracking research has diverged into two camps; low-level approaches which are typically fast and robust but provide little fine-scale information, and high-level approaches which track complex...
A mixed-state Condensation tracker with automatic model-switching (1998)
There is considerable interest in the computer vision community in representing and modelling motion. Motion models are used as predictors to increase the robustness and accuracy of visual trackers,...
A smoothing filter for Condensation (1998)
. Condensation, recently introduced in the computer vision literature, is a particle filtering algorithm which represents a tracked object 's state using an entire probability distribution....
Abstract. The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent...
Abstract. The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent...
Contour Tracking By Stochastic Propagation of Conditional Density (1996)
. In Proc. European Conf. Computer Vision, 1996, pp. 343--356, Cambridge, UK The problem of tracking curves in dense visual clutter is a challenging one. Trackers based on Kalman filters are of...
Learning to Track the Visual Motion of Contours (1995)
Andrew Blake, Michael Isard, David Reynard
A development of a method for tracking visual contours is described. Given an "un-trained" tracker, a training-motion of an object can be observed over some extended time and stored as an...
Lillibridge, Mark, Elnikety, Sameh, Birrell, Andrew, Burrows, Mike, Isard, Michael
We present a novel peer-to-peer backup technique that allows computers connected to the Internet to back up their data cooperatively: Each computer has a set of partner computers, which collectively...