Many collective labeling tasks require inference on graphical models where the clique potentials depend only on the number of nodes that get a particular label. We design efficien...
Belief propagation (BP) is an increasingly popular method of performing approximate inference on arbitrary graphical models. At times, even further approximations are required, wh...
Alexander T. Ihler, John W. Fisher III, Alan S. Wi...
We present a sampling strategy and rendering framework for intersectable models, whose surface is implicitly defined by a black box intersection test that provides the location a...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
This paper presents a flight rnanageiiient system (FhIS) iinpleniented as on-board intelligence for rotorcraft-based unmanned aerial vehicles (RUAVs), in order to gradually ilen a...