Sciweavers

3020 search results - page 351 / 604
» Human dialogue modelling using machine learning
Sort
View
NIPS
2007
15 years 8 months ago
Combined discriminative and generative articulated pose and non-rigid shape estimation
Estimation of three-dimensional articulated human pose and motion from images is a central problem in computer vision. Much of the previous work has been limited by the use of cru...
Leonid Sigal, Alexandru O. Balan, Michael J. Black
TVCG
2010
126views more  TVCG 2010»
15 years 4 months ago
Modeling Repetitive Motions Using Structured Light
— Obtaining models of dynamic 3D objects is an important part of content generation for computer graphics. Numerous methods have been extended from static scenarios to model dyna...
Yi Xu, Daniel G. Aliaga
ICML
2009
IEEE
16 years 7 months ago
The Bayesian group-Lasso for analyzing contingency tables
Group-Lasso estimators, useful in many applications, suffer from lack of meaningful variance estimates for regression coefficients. To overcome such problems, we propose a full Ba...
Sudhir Raman, Thomas J. Fuchs, Peter J. Wild, Edga...
CORR
1998
Springer
153views Education» more  CORR 1998»
15 years 6 months ago
Identifying Discourse Markers in Spoken Dialog
In this paper, we present a method for identifying discourse marker usage in spontaneous speech based on machine learning. Discourse markers are denoted by special POS tags, and t...
Peter A. Heeman, Donna K. Byron, James F. Allen
EWRL
2008
15 years 8 months ago
Regularized Fitted Q-Iteration: Application to Planning
We consider planning in a Markovian decision problem, i.e., the problem of finding a good policy given access to a generative model of the environment. We propose to use fitted Q-i...
Amir Massoud Farahmand, Mohammad Ghavamzadeh, Csab...