Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled indep...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
: This paper addresses the inference of probabilistic classification models using weakly supervised learning. The main contribution of this work is the development of learning meth...
This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...