Many domains in the field of Inductive Logic Programming (ILP) involve highly unbalanced data. Our research has focused on Information Extraction (IE), a task that typically invol...
Abstract. We use a simple yet powerful higher-order conditional random field (CRF) to model optical flow. It consists of a standard photoconsistency cost and a prior on affine mo...
In this paper we introduce a novel approach for inferring articulated spine models from images. A low-dimensional manifold embedding is created from a training set of prior mesh mo...
: We study a random graph model which is a superposition of bond percolation on Zd with parameter p, and a classical random graph G(n, c/n). We show that this model, being a homoge...
Constraint Propagation can be speeded up significantly by choosing a good execution order for propagators. A propagator is an implicit representation of a constraint which is wide...