Abstract. In this paper we discuss the use of knowledge for the automatic extraction of semantic metadata from multimedia content. For the representation of knowledge we extended and enriched current general-purpose ontologies to include low-level visual features. More specifically, we implemented a tool that links MPEG-7 visual descriptors to high-level, domain-specific concepts. For the exploitation of this knowledge infrastructure we developed an experimentation platform, that allows us to analyze multimedia content and automatically create the associated semantic metadata, as well as to test, validate and refine the ontologies built. We pursued a tight and functional integration of the knowledge base and the analysis modules putting them in a loop of constant interaction instead of being the one just a pre- or post-processing step of the other. 1

Abstract. Annotations of multimedia documents typically have been pursued in two different directions. Either previous approaches have focused on low level descriptors, such as dominant color, or they have focused on the content dimension and corresponding annotations, such as person or vehicle. In this paper, we present a software environment to bridge between the two directions. M-OntoMat-Annotizer allows for linking low level MPEG-7 visual descriptions to conventional Semantic Web ontologies and annotations. We use M-OntoMat-Annotizer in order to construct ontologies that include prototypical instances of high-level domain concepts together with a formal specification of corresponding visual descriptors. Thus, we formalize the interrelationship of high- and low-level multimedia concept descriptions allowing for new kinds of multimedia content analysis, reasoning and retrieval. 1

Abstract. Knowledge representation and annotation of multimedia documents typically have been pursued in two different directions. Previous approaches have focused either on low level descriptors, such as dominant color, or on the seman-tic content dimension and corresponding manual annotations, such as person or vehicle. In this paper, we present a knowledge infrastructure and a experimen-tation platform for semantic annotation to bridge the two directions. Ontologies are being extended and enriched to include low-level audiovisual features and de-scriptors. Additionally, we present a tool that allows for linking low-level MPEG-7 visual descriptions to ontologies and annotations. This way we construct on-tologies that include prototypical instances of high-level domain concepts to-gether with a formal specification of the corresponding visual descriptors. This infrastructure is exploited by a knowledge-assisted analysis framework that may handle problems like segmentation, tracking, feature extraction and matching in order to classify scenes, identify and label objects, thus automatically create the associated semantic metadata. 1

Abstract not found

A key to the Web's success is the power of search. The elegant way in which search results are returned is usually remarkably effective. However, for exploratory search in which users need to learn, discover, and understand novel or complex topics, there is substantial room for improvement. Human computer interaction researchers and web browser designers have developed novel strategies to improve Web search by enabling users to conveniently visualize, manipulate, and organize their Web search results. This monograph offers fresh ways to think about search-related cognitive processes and describes innovative design approaches to browsers and related tools. For instance, while key word search presents users with results for specific information (e.g., what is the capitol of Peru), other methods may let users see and explore the contexts of their requests for information (related or previous work, conflicting information), or the properties that associate groups of information assets (group legal decisions by lead attorney).

Abstract. As the volume of digital images available on the Web continues to increase, there is a clear need for more advanced techniques for their effective retrieval and management. In this paper, we present a domain independent framework for both annotating and managing images on the Semantic Web. We introduce a tool that facilitates creating and publishing OWL annotations of image content to the Semantic Web. This is loosely coupled with a Semantic Web portal with provenance tracking. We illustrate the effectiveness of this system with an implementation of the approach and describe a hypothetical use case that resulted in a proof-of-concept designed in collaboration with NASA. 1

Abstract. As the volume of digital images available on the Web continues to increase, there is a clear need for more advanced techniques for their effective retrieval and management. Recently, there has been an interest in applying Semantic Web technologies to represent the high level content of digital images in a machine processable format. While progress has been made, through a representative use case, we provide motivation for further work in developing more domain independent techniques for both annotating and managing images on the Web. Following this, we present an approach for publishing (OWL) annotations of image content to the Semantic Web, through the loose coupling of an annotation environment with a Semantic Web portal. Additionally, we present an implementation of the approach and describe a hypothetical use case that resulted in a proof-of-concept designed in collaboration with NASA. 1

Personalized multimedia access aims at enhancing the retrieval process by complementing explicit user requests with implicit user preferences. We propose and discuss the benefits of the introduction of ontologies for an enhanced representation of the relevant knowledge about the user, the context, and the domain of discourse, as a means to enable improvements in the retrieval process and the performance of adaptive capabilities. We develop our proposal by describing techniques in several areas that exemplify the explotation of the richness and power of formal and explicit semantics descriptions, and the improvements therein. 1.

Abstract. We present a systematic approach to the design of multimedia ontologies based on the MPEG-7 standard and domain-specific vocabularies. The limitations of MPEG-7 in describing the semantics of highly structured domains like sports or medicine has led to an upsurge of interest in adopting an integrated approach to the design of ontologies. We follow suit and use MPEG-7 to model structural and low-level aspects of multimedia documents. The high-level semantics are modeled using a domain-specific ontology designed for soccer games. The integration of these ontologies is achieved by providing appropriate links to the individual ontologies. As a proof-of-concept, we describe a video annotation tool implemented as a plugin for the widely used Protégé ontology editor. The advantage of our methodologies lies in the fact that we use semantic web compliant languages and tools that results in alleviating the interoperability issues currently plaguing the multimedia and the semantic web communities. 1

Abstract. Semantic annotation of multimedia data for improving search engine performance is an important issue. We have focused on the automated annotation of video recordings of university lectures. Most times these lectures are supported by a desktop presentation provided by the lecturer. This presentation in general contains an outline of the given lecture and thus, enables automated annotation of the corresponding video recording. We have implemented a tool for automated MPEG-7 annotation of video recorded lectures, which enables efficient content based search within a video database. Given a particular search term our search engine prototype is able to deliver only the relevant sequences of the matching video recordings. 1