We propose a novel method for automatically interpreting compound nouns based on a predefined set of semantic relations. First we map verb tokens in sentential contexts to a fixed...
This paper is a theoretical analysis of formal annotation and ontology for the expression of the semantics of document. They are found wanting in this respect, not only for techni...
This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source...
In this work we describe a set of visual routines, which support a novel sensor free interface between a human and virtual objects. The visual routines detect, track and interpret ...
Recognition of human actions is usually addressed in the scope of video interpretation. Meanwhile, common human actions such as "reading a book", "playing a guitar&...