The objective of this special issue is to collect and report on recent work that aims at narrowing the large disparity between the low-level descriptors that can be computed automatically from multimedia content and the richness of subjectivity of semantics in user queries and human interpretations of audiovisual data. It represents a step towards bridging the gap between research cultures at extreme ends of the semantic multimedia spectrum. At one end, the semantic web and its supporting technologies are becoming established in both the open data environment and within specialist domains, such as corporate intranet search, e-Science (particularly life sciences), and cultural heritage. To facilitate the world-wide sharing of media, W3C is developing standard ways of denoting fragments of audiovisual content and of specifying and associating semantics with these. At the other end of the spectrum, media analysis tools continue to grow in sophistication, identifying features that can then be associated with explicit semantics expressed formally or informally, using proprietary formats or open standards. Recent progress at these two fronts of the spectrum means that research spanning the semantic gap is now of vital importance to feed the real applications that are emerging.

In this issue of Multimedia Tools and Applications one may find eleven contributions:

  • A Framework for Video Abstraction Systems Analysis and Modelling from an Operational Point of View” by Victor Valdes and Jose M Martinez presents a unified taxonomy and a generic architectural model aimed for the study of existing abstraction systems computational performance and characteristics.

  • A Semantic Management Model to enable the integrated management of media and devices” by Paula Viana and Artur Pimenta Alves proposes a new ontology that aggregates information from different sources and enables a top level business oriented view of multimedia archives.

  • Automatic Summarization of Rushes Video using Bipartite Graphs” by Alan F. Smeaton, Liang Bai, Songyang Lao, and Noel E O′Connor presents a new approach for automatic summarization of rushes, or unstructured video.

  • Automatic Tag Expansion using Visual Similarity for Photo Sharing Websites” by Sare Gul Sevil, Onur Kucuktunc, Pinar Duygulu, and Fazli Can describes an automatic photo tag expansion method designed for photo sharing websites.

  • Enlightening the Sun: A User Interface to Explore Music Artists via Multimedia Content” by Markus Schedl and Tim Pohle proposes an approach to browse collections of web pages about music artists by means of descriptive terms and multimedia content.

  • Everyday Concept Detection in Visual Lifelogs: Validation, Relationships and Trends” by Daragh Byrne, Aiden R Doherty, Cees G. M Snoek, Gareth J. F Jones, and Alan F. Smeaton explores the applicability of semantic concept detection, a method often used within video retrieval, on the domain of visual lifelogs.

  • GameSense: Game-like In-Image Advertising” by Lusong Li, Tao Mei, and Xian-Sheng Hua presents a novel game-like advertising system called GameSense, which is driven by the compelling contents of online images.

  • Investigating Fuzzy DLs-Based Reasoning in Semantic Image Analysis” by Stamatia Dasiopoulou, Ioannis Kompatsiaris, and Michael G. Strintzis investigates a fuzzy DLs-based reasoning framework, which enables the integration of scene and object classifications into a semantically consistent interpretation by capturing and utilising the underlying semantic associations.

  • Performing Content-based Retrieval of Humans using Gait Biometrics” by Sina Samangooei and Mark S Nixon explores the content-based retrieval of videos containing walking subjects, using semantic queries. It evaluates current research in gait biometrics, unique in its effectiveness at recognising people at a distance.

  • Semantic-driven Multimedia Retrieval with the MPEG Query Format” by Ruben Tous and Jaime Delgado describes extensions which will allow MPQF to manage metadata modelled with Semantic Web languages like RDF and OWL, and query constructs based on SPARQL. The suggested modifications include the definition of a new MPQF query type, and a generalization of the MPQF metadata processing model.

  • Thesaurus Enrichment for Query Expansion in Audiovisual Archives” by Laura Hollink, Veronique Malaise, and Guus Schreiber aims at finding out whether retrieval of audiovisual resources from a collection indexed with an in-house thesaurus can be improved by enriching the thesaurus structure. It proposes propose a method to add structure to a thesaurus by anchoring it to an external, semantically richer thesaurus.