The unfold/fold transformation system defined by Tamaki and Sato was meant for definite programs. It transforms a program into an equivalent one in the sense of both the least tter...
This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hiera...
This paper addresses the problem of tracking objects which undergo rapid and significant appearance changes. We propose a novel coupled-layer visual model that combines the targe...
We present a model of a `gas of circles', the ensemble of regions in the image domain consisting of an unknown number of circles with approximately fixed radius and short ran...
Peter Horvath, Ian Jermyn, Zoltan Kato, and Josian...
Abstract. We describe a flexible object recognition and modelling system (FORMS) which represents and recognizes animate objects from their silhouettes. This consists of a model fo...