In this paper we describe an application which takes a video shot as input and produces a compact representation composed by a background layer and segmented moving objects. We de...
Andrea Fusiello, M. Aprile, Roberto Marzotto, Vitt...
We present a method for parameterizing irregularly triangulated input models over polyhedral domains with quadrilateral faces. A combination of center-based clustering techniques ...
Ioana M. Boier-Martin, Holly E. Rushmeier, Jingyi ...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
In this paper we propose a set of algorithms that combine the anisotropic smoothing using the heat kernel with the outlier rejection capability of robust statistics. The proposed ...
Boolean operations and feature-based modeling are closely linked domains. For example, several, sometimes many Boolean operations are involved during a feature instantiation or mo...