We propose a ray-based segmentation method for color images. A segment is represented by a centroid and evenlydistributed rays shooting out from it. First, a bottom-up low-level b...
Recent research in machine learning has focused on breaking audio spectrograms into separate sources of sound using latent variable decompositions. These methods require that the ...
When envisaging new digital instruments, designers do not have to limit themselves to their sonic capabilities (which can be absolutely any), not even to their algorithmic power; ...
In this paper we compare performance of several heuristics in generating informative generic/query-oriented extracts for newspaper articles in order to learn how topic prominence ...
Learning to converge to an efficient, i.e., Pareto-optimal Nash equilibrium of the repeated game is an open problem in multiagent learning. Our goal is to facilitate the learning ...