In this poster we intend to outline the approach adopted by the ACOM (COMputing For All) courses, which are intended to provide a comprehensive introduction to Information Technology for undergraduates from a non-computing ...

This paper describes a method for building semantic scene models from video data using observed motion. We do this through unsupervised clustering of simple yet novel motion descriptors, which provide a quantized representation ...

The problem of automated visual surveillance has spawned a lively research area, with 2005 seeing three conferences or workshops and special issues of two major journals devoted to the topic. These alone are responsible ...

This paper describes the conception, motivation, organization, and evaluation of a national, one-day event for women students of computing: the BCSWomen Lovelace Colloquium. The aim of this paper is to demonstrate that ...

This paper describes a method for building visual “maps” from video data using quantized descriptions of motion. This enables unsupervised classification of scene regions based upon the motion patterns observed within them. ...

We propose a new method that treats visible human behaviour at the level of navigational strategies. By inferring intentions in terms of known goals, it is possible to explain the behaviour of people moving around within ...