Model-based image recognition requires a general model of the object that should be detected in an image. In many applications such models are not known a-priori instead of they mu...
The present paper addresses pedestrian detection using local boosted features that are learned from a small set of training images. Our contribution is to use two boosting steps. T...
Michael Villamizar, Alberto Sanfeliu, Juan Andrade...
Abstract. We address the problem of term normalisation modulo associativecommutative (AC) theories, and describe several techniques for compiling many-to-one AC matching and reduce...
Many approaches to Information Extraction (IE) have been proposed in literature capable of finding and extract specific facts in relatively unstructured documents. Their applicatio...
Kernel methods offer a flexible toolbox for pattern analysis and machine learning. A general class of kernel functions which incorporates known pattern invariances are invariant d...