Catálogo de publicaciones - libros

A feasibility study was conducted within the confines of the DELOS Network of Excellence with the aim of investigating possible approaches to extend The European Library (TEL) with multilingual information access, i.e. the ability to use queries in one language to retrieve items in different languages. TEL uses a loose coupling of different search systems, and deals with very short information items. We address these two characteristics with two different approaches: the “isolated query translation” approach, and the “pseudo-translated expanded records” approach. The former approach has been studied together with its implications on the user interface, while the latter approach has been evaluated using a test collection of over 150,000 records from the TEL central index. We find that both approaches address the specific characteristics of TEL well, and that there is considerable potential for a combination of the two alternatives.

We present in this paper the design and implementation of the OntoNL Framework, a natural language interface generator for knowledge repositories, as well as a natural language system for interactions with multimedia repositories which was built using the OntoNL Framework. The system allows the users to specify natural language requests about the multimedia content with rich semantics that result to digital content delivery. We propose and evaluate a semantic relatedness measure for OWL domain ontologies that concludes to the semantic ranking of ontological, grammatically-related structures. This procedure is used to disambiguate in a particular domain of context and represent in an ontology query language, natural language expressions. The ontology query language that we use is the SPARQL. The construction of the queries is automated and also dependent on the semantic relatedness measurement of ontology concepts. We also present the results of experimentation with the system.

Digital preservation has turned into a pressing challenge for institutions having the obligation to preserve digital objects over years. A range of tools exist today to support the variety of preservation strategies such as migration or emulation. Heterogeneous content, complex preservation requirements and goals, and untested tools make the selection of a preservation strategy very difficult. The Austrian National Library will have to preserve electronic theses and dissertations provided as PDF files and are thus investigating potential preservation solutions. The DELOS Digital Preservation Testbed is used to evaluate various alternatives with respect to specific requirements. It provides an approach to make informed and accountable decisions on which solution to implement in order to preserve digital objects for a given purpose. We analyse the performance of various preservation strategies with respect to the specified requirements for the preservation of master theses and present the results.

H.3 Information Storage and Retrieval: H.3.7 Digital Libraries.

This paper examines genre classification of documents and its role in enabling the effective automated management of digital documents by digital libraries and other repositories. We have previously presented genre classification as a valuable step toward achieving automated extraction of descriptive metadata for digital material. Here, we present results from experiments using human labellers, conducted to assist in genre characterisation and the prediction of obstacles which need to be overcome by an automated system, and to contribute to the process of creating a solid testbed corpus for extending automated genre classification and testing metadata extraction tools across genres. We also describe the performance of two classifiers based on image and stylistic modeling features in labelling the data resulting from the agreement of three human labellers across fifteen genre classes.

The present work shows a system for compressing and streaming of live videos over networks with low bandwidths (radio mobile networks), with the objective to design an effective solution for mobile video access. We present a mobile ready-to-use streaming system, that encodes video using h264 codec (offering good quality and frame rate at very low bit-rates) and streams it over the network using UDP protocol. A dynamic frame rate control has been implemented in order to obtain the best trade off between playback fluency and latency.

In this work, we analyze the effectiveness of perceptual features to automatically annotate video clips in domain-specific video digital libraries. Typically, automatic annotation is provided by computing clip similarity with respect to given examples, which constitute the knowledgebase, in accordance with a given ontology or a classification scheme. Since the amount of training clips is normally very large, we propose to automatically extract some prototypes, or visual concepts, for each class instead of using the whole knowledge base. The prototypes are generated after a Complete Link clustering based on perceptual features with an automatic selection of the number of clusters. Context based information are used in an intra-class clustering framework to provide selection of more discriminative clips. Reducing the number of samples makes the matching process faster and lessens the storage requirements. Clips are annotated following the MPEG-7 directives to provide easier portability. Results are provided on videos taken from sports and news digital libraries.

The objective of the work reported here is to provide an automatic, context-of-capture categorization, structure detection and segmentation of news broadcasts employing a multimodal semantic based approach. We assume that news broadcasts can be described with context-free grammars that specify their structural characteristics. We propose a system consisting of two main types of interoperating units: The recognizer unit consisting of several modules and a parser unit. The recognizer modules (audio, video and semantic recognizer) analyze the telecast and each one identifies hypothesized instances of features in the audiovisual input. A probabilistic parser analyzes the identifications provided by the recognizers. The grammar represents the possible structures a news telecast may have, so the parser can identify the exact structure of the analyzed telecast.

In this work, we report on three research results achieved during the first three years of activities carried out under the task 3.8 of the DELOS Network of Excellence.

First, two approaches for 3D objects description and matching for the purpose of 3D objects retrieval have been defined. An approach based on is used to globally represent and compare 3D objects according to the local similarity of their surface curvature. Differently, a view based approach using is used to capture local and global information of 3D models by using a large number of views of the object which are then grouped according to their similarities. These approaches have been integrated in task prototypes and are now under integration into the DELOS DLMS.

To open the way to 3D objects retrieval based on similarity of object parts, a method for the automatic decomposition of 3D objects has been defined. This approach exploits Reeb-graphs in order to capture topological information identifying the main protrusions of a 3D object.

3D-mesh models are widely used to represent real objects in synthesized scenes for multimedia or cultural heritage applications, medical or military simulations, video games and so on. Indexing and analyzing these 3D data is a key issue to enable an effective usage of 3D-mesh model for designers and even for final users.

The researches of our group mainly focus on these problems. In this paper, we present the work of our group for the DELOS NoE during the year 2006. We have worked on two approaches for 3D-model indexing and analyzing: view-based approach and structural approach. View-based approaches for 3D-model indexing are a very intuitive way to retrieve 3D-models among wide collections by using 2D natural views (as a human uses to represent 3D-objects). Structural analysis of a 3D-mesh model gives a structural decomposition of the object from a raw boundary representation of it, then this decomposition can be used to segment or index 3D-models.

In this work, we describe in detail the new MPEG-7 Perceptual 3D Shape Descriptor and provide a set of tests with different 3D objects databases, mainly with the Princeton Shape Benchmark. With this purpose we created a function library called Retrieval-3D and fixed some bugs of the MPEG-7 eXperimentation Model (XM). We explain how to match the Attributed Relational Graph (ARG) of every 3D model with the modified nested Earth Mover’s Distance (mnEMD). Finally we compare our results with the best found in literature, including the first MPEG-7 3D descriptor, i.e. the Shape Spectrum Descriptor.