A novel speaker-adaptive learning algorithm is developed and evaluated for a hidden trajectory model of speech coarticulation and reduction. Central to this model is the process o...
The adaptive TAP Gibbs free energy for a general densely connected probabilistic model with quadratic interactions and arbritary single site constraints is derived. We show how a ...
Unseeded region growing is a versatile and fullyautomatic segmentation technique suitable for multispectral and 3D images. This approach integrates region-based segmentation with ...
In nonrigid motion analysis, deformation fields are often modeled using splines defined on a control-point grid. Inspired by recent development of meshfree methods, we propose a no...
Most algorithms for extracting illuminant chromaticity from arbitrary images, such as the images found on the web, are based on machine learning techniques. We will show how a phy...