A novel method is described for obtaining superior classification performance over a variable range of classification costs. By analysis of a set of existing classifiers using a r...
Martin J. J. Scott, Mahesan Niranjan, Richard W. P...
In this paper a fast method of selecting a neural network architecture for pattern recognition tasks is presented. We demonstrate that our proposed method of selecting both input ...
We consider the problem of obtaining the 3D trajectory of a ball from a sequence of images taken with a camera which is possibly rotating and zooming (but not translating). Techni...
This paper presents a model based approach to human body tracking in which the 2D silhouette of a moving human and the corresponding 3D skeletal structure are encapsulated within ...
We introduce an object recognition system in which objects are represented as a sparse and spatially organized set of local (bent) line segments. The line segments correspond to b...