Active learning (AL) is an increasingly popular strategy for mitigating the amount of labeled data required to train classifiers, thereby reducing annotator effort. We describe ...
Byron C. Wallace, Kevin Small, Carla E. Brodley, T...
User-provided object bounding box is a simple and
popular interaction paradigm considered by many existing
interactive image segmentation frameworks. However,
these frameworks t...
Victor Lempitsky, Pushmeet Kohli, Carsten Rother, ...
Abstract. In this paper we propose a novel approach to define task-driven regularization constraints in deformable image registration using learned deformation priors. Our method ...
Ben Glocker, Nikos Komodakis, Nassir Navab, Georgi...
Process network problems can be formulated as Generalized Disjunctive Programs where a logicbased representation is used to deal with the discrete and continuous decisions. A new ...
We present novel grid coverage strategies for effective surveillance and target location in distributed sensor networks. We represent the sensor field as a grid (two or three-dimen...
Krishnendu Chakrabarty, S. Sitharama Iyengar, Hair...