We propose a new transductive learning algorithm for learning optimal linear representations that utilizes unlabeled data. We pose the problem of learning linear representations a...
In this paper, we propose an original framework for representing 2D and 3D face information using geodesic distances. This aims to define a representation enabling the direct com...
Stefano Berretti, Alberto Del Bimbo, Pietro Pala, ...
For decades, Hidden Markov Models (HMMs) have been the state-of-the-art technique for acoustic modeling despite their unrealistic independence assumptions and the very limited rep...
We describe a method for constructing a structural model of an unlabeled target two-dimensional line drawing by analogy to a known source model of a drawing with similar structure...
Abstract. A mobile robot that interacts with its environment needs a machineunderstandable representation of objects and their usages. We present an ontology of objects, with gener...
Eric Wang, Yong Se Kim, Hak Soo Kim, Jin Hyun Son,...