We present an algorithm for color classification with explicit illuminant estimation and compensation. A Gaussian classifier is trained with color samples from just one training im...
In biomedical articles, terms with the same surface forms are often used to refer to different entities across a number of model organisms, in which case determining the species b...
Recently, "epitomes" were introduced as patch-based probability models that are learned by compiling together a large number of examples of patches from input images. In...
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...
Abstract. In the field of the architectural heritage, the representation of artefacts, particularly for communication purposes, has benefited from the development of computer-based...