Although computers are far better at for instance computational tasks than humans, in other areas like object recognition we still have an advantage. When we combine human and computer capacities we can benefits from the best of both worlds.
The ICT-science challenge of SEALINCMedia is exactly this: modeling and evaluating human input for multimedia content access for the purpose of integrating this input with automatic data analysis. The project emphasizes the integration of large crowds, high quality of human input and appropriate use of CPU-power. This leads to the notion of human computation power, defined as crowd size * quality of input * CPU power, optimized in the project for creating large-scale multimedia content access.
The inspiration for SEALINCMedia comes from the emerging trend of digital heritage going social. Digital cultural heritage is immersing itself in dedicated user communities on the web to increase the accessibility and value of the collection, both as economic asset and merit good. To reach these benefits, the challenge is to let the public participate via the full social media paradigm as it is the de facto standard users expect. The project aims to achieve a virtuous circle, in which social network users interact with the heritage collection to enrich the collection, to improve its value, and to enhance interaction even further.
Significant results have been reached in 2012 along all five COMMIT/dimensions. We mention here two highlights: the Dutch Prize for ICT Research for Cees Snoek and the CATCH Symposium organized by SEALINCMedia at Prinsenhof in Delft. The first highlight indicates the quality, significance and impacts of the research in the project and the second one the tendency of more and more embedding of the project in the Dutch heritage community with increasing opportunities to make a difference by addressing relevant problems and use cases there.