Sciweavers

1786 search results - page 119 / 358
» Domain Independent Generative Modeling
Sort
View
127
Voted
ICML
2005
IEEE
16 years 4 months ago
Learning predictive representations from a history
Predictive State Representations (PSRs) have shown a great deal of promise as an alternative to Markov models. However, learning a PSR from a single stream of data generated from ...
Eric Wiewiora
152
Voted
KDD
2008
ACM
183views Data Mining» more  KDD 2008»
16 years 4 months ago
Knowledge transfer via multiple model local structure mapping
The effectiveness of knowledge transfer using classification algorithms depends on the difference between the distribution that generates the training examples and the one from wh...
Jing Gao, Wei Fan, Jing Jiang, Jiawei Han
138
Voted
VLC
2008
129views more  VLC 2008»
15 years 3 months ago
Proposing a speech to gesture translation architecture for Spanish deaf people
This article describes an architecture for translating speech into Spanish Sign Language (SSL). The architecture proposed is made up of four modules: speech recognizer, semantic a...
Rubén San Segundo, Juan Manuel Montero, Jav...
148
Voted
TCSV
2008
148views more  TCSV 2008»
15 years 3 months ago
Modeling Background and Segmenting Moving Objects from Compressed Video
Abstract--Modeling background and segmenting moving objects are significant techniques for video surveillance and other video processing applications. Most existing methods of mode...
Weiqiang Wang, Jie Yang, Wen Gao
ECML
2005
Springer
15 years 9 months ago
Multi-view Discriminative Sequential Learning
Discriminative learning techniques for sequential data have proven to be more effective than generative models for named entity recognition, information extraction, and other task...
Ulf Brefeld, Christoph Büscher, Tobias Scheff...