The characteristic methods are known to be very efficient for convection-diffusion problems including the Navier-Stokes equations. Convergence is established when the integrals ar...
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recogn...
Marcus Rohrbach, Michael Stark, Gyö Szarvas, Bern...
Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which...
The reassembly of fragments to reconstruct images and objects is a problem often encountered in several applications, ranging from archeology to medicine. In this paper we present...
RMT (Research Methods Tutor) is a dialog-based tutoring system that has a dual role. Its modular architecture enables the interchange and evaluation of different tools and techniq...
Peter M. Wiemer-Hastings, David Allbritton, Elizab...