Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial con guration. We introduce a simpli ed model of a deforma...
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...
In this paper, we present an efficient algorithm for 3D object recognition in presence of clutter and occlusions in noisy, sparse and unsegmented range data. The method uses a robu...
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...