What is MediaEval? MediaEval is a benchmarking initiative that was launched by the PetaMedia Network of Excellence in late 2009. It serves as an umbrella organization to run multimedia benchmarking evaluations. It is a continuation and extension of VideoCLEF, which ran as a track in the CLEF Campaign in 2008 and 2009.
The 2010 cycle for MediaEval kicked off with the data release in June and will conclude with the Mediaeval 2010 workshop on 24 October 2010. If you would like to organize a task within MediaEval, please contact Martha Larson (m.a.larson at tudelft.nl).
How do I participate in MediaEval 2010? Participation is open and any group who wishes to participate may sign up. Sign up closed 31 May, 2010. In individual cases, late sign-up may be possible. Please contact Martha Larson (m.a.larson at tudelft.nl).
Is VideoCLEF the same as TRECVid? No, not at all. In fact, VideoCLEF takes great pains to complement rather than duplicate tasks running in the TRECVid video retrieval evaluation. Traditionally, TRECVid tasks are directed at finding objects and entities depicted in the visual channel. VideoCLEF concentrates on what a video is about as a whole.
How are the MediaEval tasks chosen? We chose tasks by first formulating a list of proposed tasks and then ascertaining which tasks are popular enough to run. If you would like to propose or organize a task, please contact Martha Larson (m.a.larson at tudelft.nl).
Are there intellectual property rights (IPR) issues with the data? No. MediaEval uses creative commons data or data from the Netherlands Institute of Sound and Vision. Sound and Vision is a partner of MediaEval and licenses data collections to MediaEval participants. MediaEval has invested a great deal of effort in ensuring that the data sets it uses can be made available to the community at large.
Who sponsors MediaEval 2010? MediaEval is an official activity of the PetaMedia Network of Excellence.
I’m looking for CLEF 2010. Is this the right site? No. Please visit http://clef2010.org/