In order to perform object recognition it is necessary to learn representations of the underlying components of images. Such components correspond to objects, object-parts, or fea...
Traditional information retrieval systems aim at satisfying most users for most of their searches, leaving aside the context in which the search takes place. We propose to model tw...
Nathalie Hernandez, Josiane Mothe, Claude Chrismen...
The multidimensional, heterogeneous, and temporal nature of speech databases raises interesting challenges for representation and query. Recently, annotation graphs have been prop...
Abstract: In this paper we present a multi-scale method for the detection of small targets embedded in noisy background. The multiscale representation is built using a weighted und...
Giuseppe Boccignone, Angelo Chianese, Antonio Pica...
The composition of the example set has a major impact on the quality of neural learning. The popular approach is focused on extensive preprocessing to bridge the representation ga...