Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
We propose to combine two approaches for modeling data admitting sparse representations: on the one hand, dictionary learning has proven effective for various signal processing ta...
This paper addresses the design and development of MediaPick [1], an interactive multi-touch system for semantic search of multimedia contents. Our solution provides an intuitive,...
Gianpaolo D'Amico, Andrea Ferracani, Lea Landucci,...
We propose a new method for imaging sound speed in breast tissue from measurements obtained by ultrasound tomography (UST) scanners. Given the measurements, our algorithm finds a...
Ivana Tosic, Ivana Jovanovic, Pascal Frossard, Mar...
In this paper we review the acoustic features used for music-to-score alignment and study their influence on the performance in a challenging alignment task, where the audio data...