We introduce a neural network, known as SONNETMAP, capable of automatic segmentation, learning and retrieval of melodies. SONNET-MAP is a synthesis of the SONNET (Self-Organizing ...
This paper presents a novel segmentation method to assist the rigging of articulated bodies. The method computes a coarse-to-fine hierarchy of segments ordered by the level of det...
We introduce a new method for segmentation of 3D medical data based on geometric variational principles. A minimal variance criterion is coupled with a geometric edge alignment mea...
Michal Holtzman-Gazit, Dorith Goldsher, Ron Kimmel
We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Mar...
Samer A. Abdallah, Mark B. Sandler, Christophe Rho...
The integration of diverse forms of informative data by learning an optimal combination of base kernels in classification or regression problems can provide enhanced performance w...