Many intelligent interfaces must recognize patterns of user activity that cross a variety of different input channels. These multimodal interfaces offer significant challenges to both the designer and the software engineer. The designer needs a method of expressing interaction patterns that has the power to capture real use cases and a clear semantics. The software engineer needs a processing model that can identify the described interaction patterns efficiently while maintaining meaningful intermediate state to aid in debugging and system maintenance.

Abstract not found

Abstract. Ambient Intelligence will change the way people interact with devices. In order to support users best user studies must be performed to collect pools of possible goals and to choose the kind of assistance that is accepted at most. In parallel technologies for Ambient Intelligence must be enhanced to guarantee the application of assistance technologies 1. 1 Ambient Intelligence effects a Metaphor Change Up to now, it has been the user’s responsibility to manage her personal environment and to control the various appliances and devices that are available for her support (see Figure 1 left). The more options a bundle of devices offers to their users, the greater is the challenge not to get lost in an abundance of possibilities. Because technology as it exists today forces its metaphors upon the user. He must find an appropriate strategy that combines functions of the offered devices in order to reach his goal (in general a change of the current environment state). At best the functions could be executed successively without any side effects that have to be considered (see Figure 1 bottom left). Unwanted side effects (e.g. room lights that decrease the contrast of the display screen of a TV set)

Abstract not found

We present a system which allows users to draw on arbitrary display surfaces. The system is implemented using consumer electronics; data is gathered with a webcam, and most video analysis is done on a desktop graphics card. Two variants of the core system are discussed. In the first, users draw on a computer monitor using a laser pointer. In the second, a light pen is used to draw on a display surface created by back-projecting onto a plexiglass plate. The laser pointer system presents a more challenging data filtering problem. These challenges may be addressed through additional processing, though the results from the back-projection system remain superior.

Classroom 2000, now named eClass, is a huge research project. This work could not have occurred without the efforts of many undergraduate and graduate students along with many visiting and resident researchers. It would also not be possible without the support of Dean Freeman, the instructors, and all of the students who have used eClass. I also want to thank researchers at Kennesaw State University, Brown University, and McGill University who have helped legitimize my research by applying it at their own schools. We have had the fortune of being in the public eye, and I want to thank all the people responsible for getting us in the newspapers and on TV, especially the public relations department here at Georgia Tech. Of course, I would like to thank my Advisor, Gregory Abowd, for allowing me to run freely with his vision so that I could take it and make it my own. I could not overstate the value of his guidance, patience, and support over the past four years. I’m afraid I’ve been more trouble than he anticipated, but then again, I don’t think eClass hurt his tenure campaign either, so maybe we’re even? Hmm … probably not. I am deeply indebted to my colleagues and fellow researchers for their work and

Workshop Scientific Committee:

The tremendous growth in video data calls for efficient and flexible access mechanisms. In this paper, we propose an ontology-driven framework for presentation video annotation and access. The goal is to integrate ontology into video systems to improve users ’ video access experience. To realize ontology-driven video annotation, the first and foremost step is video segmentation. Current research in video segmentation has mainly focused on the visual and/or auditory modalities. In this paper, we investigate how to combine visual and textual information in the hierarchical segmentation of presentation video data. With average F-scores over 0.92, our experiments show that the proposed segmentation procedure is effective. After a video is segmented, video annotation data can be extracted. To extract annotation data from a video and its segments, and to organize them in a way that facilitates video access, we propose a multiontology based multimedia annotation model. In this model, a domain-independent multimedia ontology is integrated with multiple domain ontologies. The goal is to provide multiple, domain-specific views of the same multimedia content and, thus, better address different users ’ information needs. With extracted annotation data, ontology-driven video access explores domain knowledge embedded in domain ontologies and tailors the video access to the specific needs of individual users from different domains. Our experience suggests that ontology-driven video access can improve video retrieval relevancy and, thus, enhance users ’ video access experience.