810 search results - page 160 / 162 » Learning to Segment Document Images |
TSD
2004
Springer
13 years 11 months ago
2004
Springer
A significant challenge in Text-to-Speech (TtS) synthesis is the formulation of the prosodic structures (phrase breaks, pitch accents, phrase accents and boundary tones) of uttera...
CVPR
2006
IEEE
14 years 8 months ago
2006
IEEE
"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are mo...
ICPR
2010
IEEE
13 years 6 months ago
2010
IEEE
Abstract—Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images using automatic adaptation to improve accuracy. ...
CVPR
2006
IEEE
14 years 8 months ago
2006
IEEE
We consider the general problem of learning from both labeled and unlabeled data. Given a set of data points, only a few of them are labeled, and the remaining points are unlabele...
CVPR
2008
IEEE
14 years 8 months ago
2008
IEEE
Pairwise constraints specify whether or not two samples should be in one cluster. Although it has been successful to incorporate them into traditional clustering methods, such as ...