98 search results - page 18 / 20 » Gaussian Mixture Modeling by Exploiting the Mahalanobis Dist... |
ECCV
2008
Springer
14 years 10 months ago
2008
Springer
In this paper we are interested in finding images of people on the web, and more specifically within large databases of captioned news images. It has recently been shown that visua...
ICASSP
2010
IEEE
13 years 8 months ago
2010
IEEE
This paper considers the enhancement of noisy speech. Earlier studies have revealed that an approach that enhances spectral envelopes by using prior knowledge about the all-pole (...
PAMI
2007
13 years 8 months ago
2007
—We propose an automatic approach to soft color segmentation, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesiz...
ICPR
2010
IEEE
13 years 6 months ago
2010
IEEE
This paper is aimed at evaluating the semantic information content of multiscale, low-level image segmentation. As a method of doing this, we use selected features of segmentation...
CVPR
2003
IEEE
14 years 10 months ago
2003
IEEE
Videotext recognition is challenging due to low resolution, diverse fonts/styles, and cluttered background. Past methods enhanced recognition by using multiple frame averaging, im...