Sciweavers

5866 search results - page 301 / 1174
» An e-Process Selection Model
Sort
View
NAACL
2003
15 years 8 months ago
Active Learning for Classifying Phone Sequences from Unsupervised Phonotactic Models
This paper describes an application of active learning methods to the classification of phone strings recognized using unsupervised phonotactic models. The only training data req...
Shona Douglas
NPL
2000
146views more  NPL 2000»
15 years 6 months ago
Competitive and Temporal Inhibition Structures with Spiking Neurons
The paper describes the implementation of competitive neural structures based on a spiking neural model that includes multiplicative or shunting synapses enabling non-saturated sta...
Eduardo Ros Vidal, Francisco J. Pelayo, P. Martin-...
IVC
2002
192views more  IVC 2002»
15 years 6 months ago
Understanding visual behaviour
Modelling events is one of the key problems in dynamic scene analysis when salient and autonomous visual changes occuring in a scene need to be characterised effectively as meanin...
Shaogang Gong, Hilary Buxton
PAAPP
2007
112views more  PAAPP 2007»
15 years 6 months ago
A study on video viewing behavior: application to movie trailer miner
In this paper, we present a study on video viewing behavior. Based on a well-suited Markovian model, we have developed a clustering algorithm called K-Models and inspired by the K...
Sylvain Mongy
ACL
2010
15 years 4 months ago
Optimising Information Presentation for Spoken Dialogue Systems
We present a novel approach to Information Presentation (IP) in Spoken Dialogue Systems (SDS) using a data-driven statistical optimisation framework for content planning and attri...
Verena Rieser, Oliver Lemon, Xingkun Liu