Sciweavers

144 search results - page 12 / 29
» On Deep Generative Models with Applications to Recognition
Sort
View
CVPR
2012
IEEE
11 years 11 months ago
The Shape Boltzmann Machine: A strong model of object shape
A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constra...
S. M. Ali Eslami, Nicolas Heess, John M. Winn
ICASSP
2009
IEEE
14 years 3 months ago
Language model transformation applied to lightly supervised training of acoustic model for congress meetings
For effective training of acoustic and language models for spontaneous speech such as meetings, it is significant to exploit the texts available in a large scale, which may not b...
Tatsuya Kawahara, Masato Mimura, Yuka Akita
SIGPRO
2008
155views more  SIGPRO 2008»
13 years 8 months ago
Recognition of off-line printed Arabic text using Hidden Markov Models
This paper describes a technique for automatic recognition of off-line printed Arabic text using Hidden Markov Models. In this work different sizes of overlapping and non-overlapp...
Husni A. Al-Muhtaseb, Sabri A. Mahmoud, Rami Qahwa...
SAC
2008
ACM
13 years 8 months ago
Towards automatic feature vector optimization for multimedia applications
We systematically evaluate a recently proposed method for unsupervised discrimination power analysis for feature selection and optimization in multimedia applications. A series of...
Tobias Schreck, Dieter W. Fellner, Daniel A. Keim
DCC
1995
IEEE
14 years 4 days ago
An Automatic System for Model-Based Coding of Faces
We present a fully automatic system for 2D model-based image coding of human faces for potential applications such as video telephony, database image compression, and face recogni...
Baback Moghaddam, Alex Pentland