Web pages are usually highly structured documents. In some documents, content with different functionality is laid out in blocks, some merely supporting the main discourse. In ot...
In this paper, we present a systematic framework for recognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as...
In this paper we present the results of an experiment made with our e-librarian service ”MatES”, an e-Learning tool on fractions in mathematics. MatES allows students to enter...