Sciweavers

2300 search results - page 44 / 460
» Learning Dialogue POMDP Models from Data
Sort
View
139
Voted
WACV
2005
IEEE
15 years 9 months ago
Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Thomas S. Stepleton, Tai Sing Lee
115
Voted
NAACL
2003
15 years 5 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
126
Voted
ACL
2006
15 years 5 months ago
Learning Transliteration Lexicons from the Web
This paper presents an adaptive learning framework for Phonetic Similarity Modeling (PSM) that supports the automatic construction of transliteration lexicons. The learning algori...
Jin-Shea Kuo, Haizhou Li, Ying-Kuei Yang
161
Voted
IEEEICCI
2009
IEEE
15 years 1 months ago
Learning from an ensemble of Receptive Fields
Abstract-In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encodi...
Hanlin Goh, Joo Hwe Lim, Chai Quek
119
Voted
MM
2000
ACM
98views Multimedia» more  MM 2000»
15 years 8 months ago
Determining computable scenes in films and their structures using audio-visual memory models
In this paper we present novel algorithms for computing scenes and within-scene structures in films. We begin by mapping insights from film-making rules and experimental results f...
Hari Sundaram, Shih-Fu Chang