The paper investigates the recognition of group actions in meetings by modeling the joint behaviour of participants. Many meeting actions, such as presentations, discussions and consensus, are characterised by similar or complementary behaviour across participants. Recognising these meaningful actions is an important step towards the goal of providing effective browsing and summarisation of processed meetings. A corpus of meetings was collected in a room equipped with a number of microphones and cameras. The corpus was labeled in terms of a predefined set of meeting actions characterised by global behaviour. In experiments, audio and visual features for each participant are extracted from the raw data and the interaction of participants is modeled using HMM-based approaches. Initial results on the corpus demonstrate the ability of the system to recognise the set of meeting actions.

Before the advent of the personal workstation, office work practice revolved around the paper document. Today the electronic medium offers a number of advantages over paper, but it has not eradicated paper from the office. A growing problem for those who work primarily with paper is lack of direct access to the wide variety of interactive functions available on personal workstations. This paper describes a desk with a computer-controlled projector and camera above it. The result is a system that enables people to interact with ordinary paper documents in ways normally possible only with electronic documents on workstation screens. After discussing the motivation for this work, this paper describes the system and two sample applications that can benefit from this style of interaction: a desk calculator and a French to English translation system. We describe the design and implementation of the system, report on some user tests, and conclude with some general reflections on interacting w...