Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
In discretization of a continuous variable its numerical value range is divided into a few intervals that are used in classification. For example, Na¨ıve Bayes can benefit from...
In this paper we propose a new approach to compute the scale space of any omnidirectional image acquired with a central catadioptric system. When these cameras are central they ar...
One of the main drawbacks of the Semantic Web is the lack of semantically rich data, since most of the information is still stored in relational databases. In this paper, we presen...
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase feature [3]) in terms of their distinctiveness, detectability, and robustness to i...