Scalable approaches to video content classification are limited by an inability to automatically generate representations of events ode abstract temporal structure. This paper pre...
With the rise of the Internet, virtual communities of practice are gaining importance as a mean of sharing and exchanging information. In such environments, information reuse is of...
Abstract. In set-based face recognition, each set of face images is often represented as a linear/nonlinear manifold and the Principal Angles (PA) or Kernel PAs are exploited to me...
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
In this work, we present a constrained-based representation for specifying the goals of “course design”, that we call curricula model, and introduce a graphical language, groun...