We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...
Abstract. Dynamic Pushdown Networks (DPNs) are a model for parallel programs with (recursive) procedures and process creation. The goal of this paper is to develop generic techniqu...
We present an object recognition system that locates an object, identifies its parts, and segments out its contours. A key distinction of our approach is that we use long, salien...
In this paper an approach is described to estimate 3D pose using a part based stochastic method. A proposed representation of the human body is explored defined over joints that e...
This paper summarises a tutorial entitled Analysis by Contract. Using fragments from a simple case study concerning a video store, the paper shows how a type model can provide the...