Sciweavers

1716 search results - page 182 / 344
» Generating models for temporal representations
Sort
View
NN
1997
Springer
174views Neural Networks» more  NN 1997»
15 years 8 months ago
Learning Dynamic Bayesian Networks
Bayesian networks are directed acyclic graphs that represent dependencies between variables in a probabilistic model. Many time series models, including the hidden Markov models (H...
Zoubin Ghahramani
UAI
2004
15 years 5 months ago
Factored Latent Analysis for far-field Tracking Data
This paper uses Factored Latent Analysis (FLA) to learn a factorized, segmental representation for observations of tracked objects over time. Factored Latent Analysis is latent cl...
Chris Stauffer
NIPS
2004
15 years 5 months ago
Integrating Topics and Syntax
Statistical approaches to language learning typically focus on either short-range syntactic dependencies or long-range semantic dependencies between words. We present a generative...
Thomas L. Griffiths, Mark Steyvers, David M. Blei,...
WOSP
1998
ACM
15 years 8 months ago
Poems: end-to-end performance design of large parallel adaptive computational systems
The POEMS project is creating an environment for end-to-end performance modeling of complex parallel and distributed systems, spanning the domains of application software, runti...
Ewa Deelman, Aditya Dube, Adolfy Hoisie, Yong Luo,...
CVPR
1999
IEEE
16 years 6 months ago
A Multiple Hypothesis Approach to Figure Tracking
This paper describes a probabilistic multiple-hypothesis framework for tracking highly articulated objects. In this framework, the probability density of the tracker state is repr...
Tat-Jen Cham, James M. Rehg