Sciweavers

357 search results - page 64 / 72
» A novel dependency-to-string model for statistical machine t...
Sort
View
PAMI
2010
161views more  PAMI 2010»
13 years 7 months ago
Nonstationary Shape Activities: Dynamic Models for Landmark Shape Change and Applications
—The goal of this work is to develop statistical models for the shape change of a configuration of “landmark” points (key points of interest) over time and to use these mode...
Samarjit Das, Namrata Vaswani
INFORMS
2007
123views more  INFORMS 2007»
13 years 9 months ago
Constructing Ensembles from Data Envelopment Analysis
It has been shown in prior work in management science, statistics and machine learning that using an ensemble of models often results in better performance than using a single ‘...
Zhiqiang Zheng, Balaji Padmanabhan
CVPR
2007
IEEE
14 years 11 months ago
What makes a good model of natural images?
Many low-level vision algorithms assume a prior probability over images, and there has been great interest in trying to learn this prior from examples. Since images are very non G...
Yair Weiss, William T. Freeman
ROBIO
2006
IEEE
129views Robotics» more  ROBIO 2006»
14 years 3 months ago
Learning Utility Surfaces for Movement Selection
— Humanoid robots are highly redundant systems with respect to the tasks they are asked to perform. This redundancy manifests itself in the number of degrees of freedom of the ro...
Matthew Howard, Michael Gienger, Christian Goerick...
ICFP
2005
ACM
14 years 9 months ago
Continuations from generalized stack inspection
Implementing first-class continuations can pose a challenge if the target machine makes no provisions for accessing and re-installing the run-time stack. In this paper, we present...
Greg Pettyjohn, John Clements, Joe Marshall, Shrir...