A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and ma...
For many supervised learning tasks it is very costly to produce training data with class labels. Active learning acquires data incrementally, at each stage using the model learned...
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...