In this paper we propose a feedforward neural network for syllable recognition. The core of the recognition system is based on a hierarchical architecture initially developed for ...
Xavier Domont, Martin Heckmann, Heiko Wersing, Fra...
Incorporating shape priors in image segmentation has become a key problem in computer vision. Most existing work is limited to a linearized shape space with small deformation modes...
Patrick Etyngier, Renaud Keriven, Jean-Philippe Po...
This work investigates the use of nonlinear dependencies in natural image sequence statistics to learn higher-order structures in natural videos. We propose a two-layer model that...
Shape clustering can significantly facilitate the automatic labeling of objects present in image collections. For example, it could outline the existing groups of pathological ce...
There is a growing need to extract features from point sets for purposes like model classification, matching, and exploration. We introduce a technique for segmenting a point-sam...