ICVW Invited Talk: Prof. Dr. James Crowley, INRIA Rhones Alpes, France

Title of the Talk

Situated Observation of Human Activity

Abstract

Human social activities follow loosely defined scripts in which individuals assume roles. Social conventions establish stereotypical skeletons for such scripts, with details and variations determined by the circumstances and personalities of the individuals who play the roles. Encoding social scripts in a formal representation enables services based on observation and understanding of human activity.

This talk presents concepts and techniques for recognizing and observing human social interaction. We begin with a conceptual framework in which scripts for human activity are described with scenarios composed of actors and objects within a network of situations. We propose a layered, component-based software architecture for constructing systems that observe human activity. This framework and architecture are illustrated with examples from recent EC and national projects.

Unfortunately, the cost and complexity of handcrafting models for the variety of ways in which scripts can be enacted makes such an approach infeasible. We present a method for building systems that develop social scripts through incremental supervised learning. We begin with a conceptual framework in which scripts for human activity are described as scenarios composed of actors and objects within a network of situations. We then present methods to develop situation networks by incrementally building on an existing stereotypical script. We present supervised learning techniques for learning to discriminate new situations and for learning to recognize new roles. We illustrate our approach with results from experiments with situation and role learning in an office environment.

About the speaker

Prof. Dr. James L. Crowley is director of the GRAVIR laboratory at the INRIA Rhone-Alpes research center in Montbonnot, France and of the INRIA project PRIMA. He holds the post of Professor at the Institut National Polytechnique de Grenoble (INPG), where he teaches courses in Computer Vision, Signal Processing, Pattern Recognition and Artificial Intelligence at l'ENSIMAG (Ecole National Superieure d'Informatique et de Mathematiques Appliquées). Please have a look at his website for further information.