Content Navigation Throughout The Content Life-Cycle
The profusion of digital content now available to an individual, average consumer/viewer/listener is over-whelming, potentially forcing consumers into increasingly narrow bands of media experience as they retreat to limiting choices as a coping strategy. Professional recommenders, such as newspaper film and TV reviewers, are similarly overwhelmed, and paradoxically, more relied upon by consumers whilst considered less relevant as alternative automated and semi-automated recommendation systems emerge: for movies (e.g. The Netflix competitions), music (e.g. last.fm), or books (e.g. Amazon).
The Semantic Media Network project addresses the challenge of time-based navigation in large collections of media documents. The project focuses on investigating new ways to empower users to find relevant content and exploring how industry and universities can work together in this field. In particular, one of the project's central ideas is that (highly sophisticated) annotation should occur within the production process, so that not only consumers benefit from the introduction of new search, browsing, and recommendation technologies but also the producers of content (composers, musicians, script-writers, directors, actors). Furthermore, annotating content as early as possible allows for integrating knowledge of the production workflow, which leads not only to simplified and hence more robust automatic procedures but also to more detailed metadata and richer user interfaces. Additionally, managing and exposing this metadata using modern semantic web and linked data technology allows for uniting various sources of information which enables users to more effectively identify relevant content and thus helps to widen the consumer's increasingly narrow bands of media experience. The project's scope is the whole life-cycle of content with the goal of empowering human producers and consumers to effectively reuse, re-purpose, and personalize material, whether for entertainment, news, documentaries, education, interviews, health-care, science or security.
Overall, the research agenda is based on several core strategies:
- Content-related metadata is an effective and scalable approach applicable to future large scale, automated and interactive information systems
- The point of creation is the best time and place to collect (and compute) metadata
- The best way to represent this metadata is one that is amenable to knowledge processing and management, linked data strategies and logical inference
- Significant challenges require a cross-disciplinary approach, ranging from fundamental theory to applied research set in the context of a real problem
In this context, the projects aims at bringing together an extended critical mass of skilled people (a) academic researchers and commercial players from across the ICT sector: semantic web, knowledge engineering, databases, machine learning, text mining; human interactivity and social computing; signal processing, image, audio and video analysis; with (b) media specialists and practitioners from the creative industries.
Why Joining The Network?
A major goal of the Semantic Media project is to establish an open network uniting industrial and academic research efforts. To this end, project workshops bring industrialists together with theoretical and applied researchers, to foster relationships, and encourage working together to find solutions to science and technology problems that are relevant to digital media. To support interesting collaboration opportunities between universities and industry partners, the semantic media project will fund several mini-projects and feasibility studies resulting from project meetings and sandpits, which might lead to full-scale follow-up projects and grant applications.