Sciweavers

2036 search results - page 14 / 408
» From Sampling to Model Counting
Sort
View
ACL
1993
15 years 1 months ago
How do we count? The Problem of Tagging Phrasal Verbs in Parts
This paper examines the current performance of the stochastic tagger PARTS (Church 88) in handling phrasal verbs, describes a problem that arises from the statistical model used, ...
Nava A. Shaked
79
Voted
SMC
2007
IEEE
15 years 6 months ago
ADtrees for sequential data and n-gram Counting
Abstract— We consider the problem of efficiently storing ngram counts for large n over very large corpora. In such cases, the efficient storage of sufficient statistics can ha...
Robert Van Dam, Dan Ventura
81
Voted
ICASSP
2008
IEEE
15 years 6 months ago
Satellite image reconstruction from an irregular sampling
We propose a new method to solve a problem of image restoration with many different aspects: reconstruction from irregular samples, deconvolution and denoising. The model we propo...
Eric Bughin, Laure Blanc-Féraud, Josiane Ze...
ICDAR
2005
IEEE
15 years 5 months ago
Enhancing Training Data for Handwriting Recognition of Whiteboard Notes with Samples from a Different Database
Recognition of unconstrained handwritten text is still a challenge. In this paper we consider a new problem, which is the recognition of notes written on a whiteboard. Our recogni...
Marcus Liwicki, Horst Bunke
ICMCS
2005
IEEE
172views Multimedia» more  ICMCS 2005»
15 years 5 months ago
A Study of Synthesizing New Human Motions from Sampled Motions Using Tensor Decomposition
This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional stat...
Rovshan Kalanov, Jieun Cho, Jun Ohya