Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
Service Oriented Architectures and Web Services are emerging technologies, which have overall inherited problems and advantages from the component-based approach, but exacerbated ...
This paper explores timing anomalies in WCET analysis. Timing anomalies add to the complexity of WCET analysis and make it hard to apply divide-and-conquer strategies to simplify ...
Raimund Kirner, Albrecht Kadlec, Peter P. Puschner
In this paper we study the following problem: given two source images A and A , and a target image B, can we learn to synthesize a new image B which relates to B in the same way t...
Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...