Sciweavers

2211 search results - page 82 / 443
» Comparing Approaches to Implement Feature Model Composition
Sort
View
CVPR
2003
IEEE
15 years 12 months ago
An Efficient Approach to Learning Inhomogeneous Gibbs Model
Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...
Ziqiang Liu, Hong Chen, Heung-Yeung Shum
ICASSP
2010
IEEE
14 years 10 months ago
Comparison of modulation features for phoneme recognition
In this paper, we compare several approaches for the extraction of modulation frequency features from speech signal using a phoneme recognition system. The general framework in th...
Sriram Ganapathy, Samuel Thomas, Hynek Hermansky
ANLP
1997
80views more  ANLP 1997»
14 years 11 months ago
Sequential Model Selection for Word Sense Disambiguation
Statistical models of word-sense disambiguation are often based on a small number of contextual features or on a model that is assumed to characterize the interactions among a set...
Ted Pedersen, Rebecca F. Bruce, Janyce Wiebe
ICML
2008
IEEE
15 years 10 months ago
Extracting and composing robust features with denoising autoencoders
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
ISM
2006
IEEE
129views Multimedia» more  ISM 2006»
14 years 9 months ago
A Graph-Based Approach for Modeling and Indexing Video Data
In this work, we propose new graph-based data model and indexing to organize and manage video data. To consider spatial and temporal characteristics of video, we introduce a new g...
JeongKyu Lee