This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert clas...
Markus Enzweiler, Angela Eigenstetter, Bernt Schie...
Kernel machines rely on an implicit mapping of the data such that non-linear classification in the original space corresponds to linear classification in the new space. As kernel ...
Multiple surface searching with only image intensity information is a difficult job in the presence of high noise and weak edges. We present in this paper a novel method for global...
Linear pushbroom cameras are widely used in passive remote sensing from space as they provide high resolution images. In earth observation applications, where several pushbroom se...
Regis Perrier, Elise Arnaud, Peter F. Sturm, Mathi...
Conventional subspace learning-based face recognition aims to attain low recognition errors and assumes same loss from all misclassifications. In many real-world face recognition...