• objects depicted in the media stream and their visible and known properties,
• spatial relationships between those objects,
• video segments or clusters that depict the events involving one or more of these objects, and
• the temporal order between those segments or clusters.
• Those who use automated image-tracking tools to identify objects in each segment and then use automated extraction tools to separate them from the background.
• Those who undertake the painstaking task of manual or semiautomated modeling.
• what's visible (height, weight, color of hair, color of eyes, clothes worn, and so on),
• what's not but can be made visible (a heart surgery scar on the chest),
• what we can derive (he may be running for governor of California), and
• what we already knew (he's Austrian, in his mid-50s, married with kids, and so on).
Marios C. Angelides is a professor of computing in the Department of Information Systems and Computing at Brunel University. He has more than 10 years of research experience in multimedia information systems. Angelides holds a BSc in computing and a PhD in information systems, both from the London School of Economics and Political Science. He's the author of Multimedia Information Systems (Kluwer, 1997). He's a member of the ACM, the IEEE Computer Society, and the British Computer Society.