A non-parametric (NP) sampling method is introduced for obtaining the joint distribution of a pair of images. This method is called NP windowing and is equivalent to sampling the ...
Abstract. We consider the problem of learning stochastic tree languages, i.e. probability distributions over a set of trees T(F), from a sample of trees independently drawn accordi...
In this paper, we study the optimal way of distributing sensors in a random field to minimize the estimation distortion. We show that this problem is equivalent to certain proble...
The recognition of text in everyday scenes is made difficult by viewing conditions, unusual fonts, and lack of linguistic context. Most methods integrate a priori appearance info...
David Smith, Jacqueline Feild, Eric Learned-Miller
We consider the problem of learning a similarity function from a set of positive equivalence constraints, i.e. 'similar' point pairs. We define the similarity in informa...