A method is proposed for semiparametric estimation where parametric and nonparametric criteria are exploited in density estimation and unsupervised learning. This is accomplished ...
This paper presents a maximum likelihood approach to multiple fundamental frequency (F0) estimation for a mixture of harmonic sound sources, where the power spectrum of a time fra...
In the context of large databases, data preparation takes a greater importance : instances and explanatory attributes have to be carefully selected. In supervised learning, instanc...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Online image repositories such as Flickr contain hundreds of millions of images and are growing quickly. Along with that the needs for supporting indexing, searching and browsing ...