Despite the hype surrounding enterprise architectures, they have delivered little on their promise. In this paper, we argue that enterprise architectures built using component-bas...
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...
We use cluster analysis as a unifying principle for problems from low, middle and high level vision. The clustering problem is viewed as graph partitioning, where nodes represent ...
We present and experimentally evaluate a new model of pronunciation by analogy: the paradigmatic cascades model. Given a pronunciation lexicon, this algorithm first extracts the m...