In this paper we describe a multi-strategy approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple fe...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...
Autoassociator is an important issue in concept learning, and the learned concept of a particular class can be used to distinguish the class from the others. For nonlinear autoass...
Abstract— The future of robots, as our companions is dependent on their ability to understand, interpret and represent the environment in a human compatible manner. Towards this ...
Abstract. This article presents an ego-centric approach for indexing and browsing meetings. The method considers two concepts: meetings’ data alignment with personal information ...
This paper discusses the extensions that we have made to Betty’s Brain teachable agent system to help students learn about dynamic processes in a river ecosystem. Students first ...