6 search results - page 1 / 2 » Modeling pixel means and covariances using factorized third-... |
CVPR
2010
IEEE
13 years 11 months ago
2010
IEEE
Learning a generative model of natural images is a useful way of extracting features that capture interesting regularities. Previous work on learning such models has focused on me...
JMLR
2010
13 years 6 months ago
2010
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
NECO
2010
13 years 9 months ago
2010
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
JMLR
2012
12 years 1 months ago
2012
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating m...
ICASSP
2011
IEEE
13 years 2 months ago
2011
IEEE
Gaussian mixture models (GMMs) are commonly used to model the spectral distribution of speech signals for text-independent speaker verification. Mean vectors of the GMM, used in c...