MediaEval 2010 Results
Working notes proceedings: Access the complete MediaEval 2010 working notes on the proceedings page. See also the MediaEval 2010 workshop page.
Workshop video: For video of the workshop, check out the MediaEval 2010 workshop video and the MediaEval trailer.
Special Session: A special session called Automatic Tagging and Geo-Tagging in Video Collections and Communities was held at ACM ICMR 2011 (17-20 April 2011 Trento, Italy)
Overview of MediaEval 2010 Tasks
Four tasks were offered that placed emphasis on speech, language and context aspects of video. Tasks and results are described below.
The Tagging Task (Professional Version): Prediction of semantic theme
Required participants to automatically assign subject labels to Dutch-language television content using features derived from speech, audio, visual content or associated archival metadata. Read more...
The Tagging Task (Wild Wild Web Version): Prediction of user tags
Required participants to automatically assign tags to Internet videos using features derived from speech, audio, visual content or associated textual or social information. Read more...
The Placing Task: Geo-tagging (co-sponsored by PetaMedia and Glocal)
Where in the world? Participants 'place Flickr videos on a map,' i.e., assign geo-coordinates to videos using one or more of: Flickr metadata, visual content, audio content, social information. Read more...
The Affect Task: Boredom Detection
Involved automatically identifying videos that viewers report are boring. Participants can make use of spoken, visual, and audio content as well as accompanying metadata. Read more...
In late 2009, sponsorship of VideoCLEF was assumed by PetaMedia and we adopted the name MediaEval. Tasks for MediaEval 2010 were chosen on the basis of a survey: results are available on the survey page.