Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
History based models, introduced by Parikh and Ramanujam, provide a natural mathematical model of social interactive situations. These models offer a ”low level” description ...
The agent paradigm can be seen as an extension of the notion of (active) objects by concepts like autonomy and cooperation. Mainstream object-oriented modeling techniques do not a...
We present a framework for the automatic recognition of complex multi-agent events in settings where structure is imposed by rules that agents must follow while performing activit...
Example-based learning of codes that statistically encode general image classes is of vital importance for computational vision. Recently, non-negative matrix factorization (NMF) ...