ing Rainer Lienhart, Silvia Pfeiffer and Wolfgang Effelsberg University of Mannheim, 68131 Mannheim, Germany {lienhart, pfeiffer, effelsberg}@pi4.informatik.uni-mannheim.de 1. What is a Video Abstract? We all know what the abstract of an article is: a short summary of a document, often used to preselect material relevant to the user. The medium of the abstract and the document are the same, namely text. In the age of multimedia, it would be desirable to use video abstracts in very much the same way: as short clips containing the essence of a longer video, without a break in the presentation medium. However, the state of the art is to use textual abstracts for indexing and searching large video archives. This media break is harmful since it typically leads to considerable loss of information. For example it is unclear at what level of abstraction the textual description should be; if we see a famous politician at a dinner table with a group of other politicians, what should the text sa...

This paper considers the automated and semi-automated annotation of audiovisual media in a new type of production framework, A4SM (Authoring System for Syntactic, Semantic and Semiotic Modelling). We present the architecture of the framework and outline the underlying XML-Schema based content description structures of A4SM. We then describe tools for a news and demonstrate how video material can be annotated in real time and how this information can not only be used for retrieval but also can be used during the different phases of the production process itself. Finally, we discuss the pros and cons of our approach of evolving semantic networks as the basis for audio-visual content description.

This article discusses the state of the art in metadata for audio-visual media in large semantic networks, such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development. Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems regarding the semantic content description of media units.

In this article we claim that the linguistic-centred view within hypermedia systems needs refinement through a semioticbased approach before real interoperation between media can be achieved. We discuss the problems of visual signification for images and video in dynamic systems, in which users can access visual material in a non-linear fashion.

We present a model to support the design, analysis, and comparison of games through the use of game design patterns, descriptions of reoccurring interaction relevant to game play. The model consists of a structural framework to describe the components of games, and patterns of interaction that describes how components are used by players (or a computer) to affect various aspects of the game play. Focusing on the patterns and identified methods for using them, we describe the development of the model and how we are currently working to enlarge and validate the collection of patterns.

Abstract. We report how new types of games can be created using the possibilities of embedded computing, sensors, new output devices and ad-hoc wireless networks while keeping characteristics from traditional noncomputerized games. Applying both a technological and use-oriented research approach, we identified a number of new interaction acts made possible by the new technology. These are described using game mechanics, a concept developed by the game design community. The identified mechanics, together with examples of games using them, are described as well as the benefits and limitations of using the game mechanic concept. 1

Video production involves the process of capturing, editing, and composing video segments for delivery to a consumer. A composition must yield a coherent presentation of an event or narrative. This process can be automated if appropriate domainspecific metadata are associated with video segments and composition techniques are established. Automation leads to the support of dynamic composition and customization for applications such as news on demand. In this paper, we present techniques to achieve dynamic, real-time, and cohesive video composition and customization. We also identify metrics for evaluating our techniques with respect to existing manually produced video-based news. The results of such an evaluation show that the quality of automatic composition is comparable to#and in some cases, better than#broadcast news video composition. The results also validate the assertions on which the automatic composition techniques are based. Index Terms---Video production, automatic ...

This paper deals with the introduction of costume as a new feature for automatic video content indexing. We present in this paper an application of person recognition using costumes, in order to show the relevance of costume for indexation.

We use rhetorical annotations to specify a generation process that can assemble meaningful video sequences with a communicative goal and an argumentative progression. Our annotation schema encodes the verbal information contained in the audio channel, identifying the claims the interviewees make and the argumentation structures they use to make those claims. Based on this schema, we construct a semantic graph which is traversed by rhetoric-based strategies selecting video segments. The selected video segments are edited to form a meaningful video sequence. 1.

Rhetorical structure theory (RST) provides a model of textual function based upon rhetoric. Initially developed as a model of text coherence, RST has been used extensively in text generation research, and has more recently been proposed as a basis for multimedia presentation generation. This paper investigates the use of RST for generating video presentations having a rhetorical form, using models of the rhetorical roles of video components, together with rules for selecting components for presentation on the basis of their rhetorical functions. An RST model can provide a predefined link structure providing viewers with options for obtaining and dynamically modifying rhetorically coherent video presentations from video archives and databases. The use of an RST analysis for interactive presentation generation may provide a more powerful rhetorical device than conventional linear video presentation. Conversely, making alternative RST analyses of the same video data available to users can have the effect of encouraging closer and more independent viewer analysis of the material, and discourage taking any particular rhetorical presentation at face value. 1998 ACM Computing Classification System: H.5.2, I.3.4, I.3.8 Keywords and Phrases: interactive presentation generation, rhetorical structure theory, news, video, video archive Note: The work was carried out under the "ToKen200" and "Dynamo" projects 1.