MediaEval 2011 Working notes proceedings
The MediaEval 2011 Working Notes proceedings has been published by CEUR.WS and is online at: http://ceur-ws.org/Vol-807/
Cite a MediaEval paper following this example:
Hintsa, T., Vainikainen, S. and Melin, M. Leveraging linked data in Social Event Detection. Working Notes Proceedings of the MediaEval 2011 Workshop, Pisa, Italy, September 1-2, 2011, CEUR-WS.org, ISSN 1613-0073, http://ceur-ws.org/Vol-807/Hintsa_SED_VTT_me11wn.pdf
MediaEval 2011 Workshop
The MediaEval 2011 workshop was held 1-2 September in Pisa, Italy. Thank you to everyone that participated in the workshop for making the event a successful one.
The program of the workshop is available here. It consisted of presentations by MediaEval 2011 participants on the best solutions that they have developed for the tasks. It also included presentations on application areas, benchmarking best practices and discussion of proposed tasks for 2012. The workshop was an official satellite event of Interspeech 2011.
Photos of the workshop are available on Flickr and the videos are available on YouTube.
Overview of MediaEval 2011 Tasks
The following tasks were offered in 2011:
Genre Tagging Task
This task requires participants to automatically assign tags to Internet videos using features derived from speech, audio, visual content or associated textual or social information. This year we will focus on tags that reflect the genre of the video ("tutorial", "sport", "spoof"). Read more...
Rich Speech Retrieval Task
This task goes beyond conventional spoken content retrieval by requiring participants to deploy spoken content and its context in order to find jump-points in an audiovisual collection given a set of queries. Read more...
Spoken Web Search
This task involves searching FOR audio content WITHIN audio content USING an audio content query. This task is particularly interesting for speech researchers in the area of spoken term detection. Read more...
Affect Task: Violence Detection Task
This task requires participants to deploy multimodal features to automatically detect of portions of movies containing violent material. Read more...
Social Event Detection
This task requires participants to discover events and detect media items that are related to either a specific social event or an event-class of interest. Read more...
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...
For more information on the individual tasks, please contact the task organizers (listed on the task page) or alternatively write to m.a.larson (at) tudelft.nl.