Background and Motivations
The workshop aims at exploring the application and evaluation of automated information extraction techniques and audiovisual content analysis tools to support future media production for novel TV services. This proposal follows in a series of previous events, the first in conjunction with DEXA 2008 (AIEMPro08), the second in conjunction with WIAMIS 2009 (AIEMPro09), and the third in conjunction with ACM Multimedia 2010 (AIEMPro10). This year, following a successful merge with the CBTV workshop (held in 2009 in conjunction with the IEEE International Symposium on Multimedia), the full title of the workshop changed to reflect the broader domain addressed.
The significant increase in the amount of digital video content (TV channels in particular), and the diversification of broadcast possibilities and storage devices, have recently given rise to the emergence of many new services and novel TV programmes consumption schemes and usage trends. These new services are aimed at making broadcast content available to consumers according to their needs, i.e. without any constraint on location and/or time and with the possibility to cherry pick and navigate according to the viewers desire. These services have been proven to be very effective in significantly increasing the content audience and open new niches for profitable use of broadcast content. Examples of such services are TV-on-demand, interactive TV, Personal Video Recorders, Catch-Up TV. This explosion of new media distribution and consumption paradigms and the corresponding new production workflows based on digital computer-based tools require an immediate revision of the traditional ways of making business in media industry. These evolutions are progressively substituting the traditional one-to-many broadcasting model. To cope with these trends, broadcasters are revolutionizing their point of view, trying to embrace these new models into their facilities.
Leading experts all agree in recognizing automation of processes as one of the key for success in this scenario, because of the potential costs reduction introduced by it. This concept is grounded on several concurring factors in the media sector: a) switch over to Digital Television introduces more channels (meaning ore content items are produced/published); b) cross media production (web TV, Hybrid Broadcast/Broadband, 2nd screen applications) means reuse of the same material in many different ways; c) improvements in infrastructure (IT) allows better content accessibility; d) recovery of Cultural Heritage implies archive digitization, annotation and multi-platform dissemination; e) budget limitations and shorter time-to-market mean number of media professionals cannot increase.
The cumulative effect of these factors can be summarized as follows: a lot more digital media items need to be produced by the same or reduced staff, and in a quicker and more cost-efficient way.
As a consequence, the adoption of tools for intelligent analysis and synthesis of multimedia data are seen as substantial enabling factors in making interactive, multi-channel and multi-purpose productions value-returning.
Technical and Scientific issues
In order to build innovative services, crucial and highly time-consuming pre-processing steps of TV content are required. As an industrial environment, however, the media sector is characterized by challenging requirements to teams who aim at creating suitable information extraction and indexing tools, e.g. high accuracy and real-time constraints during the production of live events. Therefore, the ability to efficiently index multimedia streams during real-time acquisition/generation of multimedia content is a general requirement for any technology in this domain. In addition, some other outstanding technical issues are relevant as well:
- how to repurpose material originally produced for the one-to-many broadcasting paradigm on new interactive distribution channels?
- how to protect intellectual property from potential abuses in an useful timeframe?
- how to efficiently index existing multimedia archives w.r.t. new production paradigms?
- how to organize and run integrated cross-media production platforms in an efficient way?
In addition to the above aspects, another aspect characterizes the media production environment: the huge amount of produced data. Differently from controlled experimental conditions, in real-life scenarios the variability of productions and assortment of content genres are elements to be studied scientifically in order to evaluate theoretical and practical limitations of existing or to be developed techniques. This implies the existence of several connected problems:
- which are the best practices in multimedia object annotation which maximize the efficiency of search and retrieval systems for very large repositories?
- which new multimedia description models have to be adopted to represent the complexity introduced by interactivity with large communities of users and by cross-media interaction?
- how to deal with description/annotation systems when the observation time of a live repository of multimedia objects becomes large (e.g. decades)?
- how to capture the semantic evolution of categorization concepts over time and over large repositories of objects?
- how to assess systems for future-proof quality?
- how to robustly evaluate the validity of experimental results on real-life scenarios?
- how to develop techniques to automate metadata translation and interoperability?
- which are the best ways to index extremely large amount of data obtained from diverse sources, such as modern high quality production and old digitized b/w films?
Being positioned in this highly challenging context, the primary significance of the proposed workshop is fostering exchange of ideas and of practices between leading experts in research and leading actors in the media community, in order to catalyze the migration towards new ways of producing media content, aided by large scale introduction of tools for automated multimedia analysis and understanding. On the other hand, the workshop should help researchers in better understanding what are some real-life key requirements which would enable their scientific developments come into wider adoption.
If you have further inquires please feel free to contact us: