This paper presents a framework for corpus based multimodal research. Part of this framework is applied in the context of meeting modelling. A generic model for di#erent aspects of meetings is discussed.

In this paper we survey our research on smart meeting rooms and its relevance for augmented reality meeting support and virtual reality generation of meetings in real-time or o#-line. Intelligent real-time and o#-line generation requires understanding of what is going on during a meeting. The research reported here takes place in the European 5th and 6th framework programme projects M4 (Multi-Modal Meeting Manager) and AMI (Augmented Multi-party Interaction). Both projects aim at building a smart meeting environment that is able to capture in a multimodal way the activities and discussions in a meeting room, with the aim to use this information as input to tools that allow real-time support, browsing, retrieval and summarization of meetings. In these projects many European research groups participate. Our aim is to research (semantic) representations of what takes place during meetings in order to allow generation, e.g. in virtual reality, of meeting activities (discussions, presentations, voting, etcetera). Being able to do so also allows us to look at tools that provide support during a meeting and at tools that allow those not able to be physically present during a meeting to take part in a virtual way. This may lead to situations where the di#erences between real meeting participants, human-controlled virtual participants and (semi-) autonomous virtual participants disappear. In this paper we introduce our research aims and ideas and we illustrate them with examples taken from many di#erent projects in related areas.

We survey the themes and the aims of a workshop devoted to the state-of-the-art virtuality continuum. In this continuum, ranging from fully virtual to real physical environments, allowing for mixed, augmented and desktop virtual reality, several perspectives can be taken. Originally, the emphasis was on display technologies. Here we take the perspective of the inhabited environment, that is, environments positioned somewhere on this continuum that are inhabited by virtual (embodied) agents, that interact with each other and with their human partners. Hence, we look at it from the multi-party interaction perspective. In this workshop we will investigate the current state of the art, its shortcomings and a future research agenda. Author Keywords Multi-party interaction, virtual reality, smart environments.

Abstract not found

Most of our research in human-computer interaction assumes that humans and computers cooperate. And

To gain insight into gaze behavior in meetings, this paper compares the results from a Naive Bayes classifier, Neural Networks and humans on speaker prediction in four-person meetings given solely the azimuth head angles.

In this abstract we outline new developments in HCI systems and identify challenges for design and evaluation of emerging systems. We illustrate these developments and challenges with examples from research projects we are involved in.

Abstract. In this research, we propose to incorporate intelligent 3D character into interface design to enhance the user experience on the interactive digital TV system. Based on the smart interactive digital TV system, call SITV, developed in our previous work, we consider several interactive scenarios in the design of the intelligent 3D animated character. We propose to design our intelligent 3D character with the concepts of mobility and expressiveness on body motion such that appropriate emotions can be presented according to TV watching scenarios and character configurations. We have designed experiments to evaluate different types of user interface design for various scenarios. We have found that although the interface with animated character can attract the attention of the user and enhance interactivity, the text-based dialog box interface is still the easiest to understand. We also have found that when the freshness of the new interface with animated character decays after some time of use, it is crucial for an animated character to have expressive motions.

In this article, we provide the nontechnical reader with a fundamental understanding of the components of virtual reality (VR) and a thorough discussion of the role VR has played in social science. First, we provide a brief overview of the hardware and equipment used to create VR and review common elements found within the virtual environment that may be of interest to social scientists, such as virtual humans and interactive, multisensory feedback. Then, we discuss the role of VR in existing social scientific research. Specifically, we review the literature on the study of VR as an object, wherein we discuss the effects of the technology on human users; VR as an application, wherein we consider real-world applications in areas such as medicine and education; and VR as a method, wherein we provide a comprehensive outline of studies in which VR technologies are used to study phenomena that have traditionally been studied in physical settings, such as nonverbal behavior and social interaction. We then present a content analysis of the literature, tracking the trends for this research over the last two decades. Finally, we present some possibilities for future research for interested social scientists.