VideoSense Grand Challenge 2014
Participant in this year Visual Privacy Task are invited to implement a combination of several privacy filters to protect various personal information regions in videos, by optimising the privacy filtering so as to: i) obscure such personal information effectively whilst, ii) keeping as much as possible of the ‘useful’ information that would enable a human viewer to interpret the obscured video frame. Personal visual information is subjective human-perceived information that can expose a person’s identity to a human viewer. This can include richly detailed image regions such as distinctive facial features or personal jewellery as well as less rich uniform regions e.g. skin regions (that expose racial identity) or body silhouette showing a person’s gait (that generally helps to differentiate women from men and in some cases it may even enable a close friend or a spouse to identify the person).
In order to simulate context–aware privacy protection solutions, both Low or High information regions, and, unusual events e.g. fighting, stealing, and dropping a bag are annotated in the datset to be provided. The participants are thus encouraged to exploit this information to achieve the appropriate level of privacy filtering for each person, object, and Low/High information regions -to optimise their privacy filtering mix according to criteria described under evaluation.
Task description: http://www.multimediaeval.org/mediaeval2014/visualprivacy2014/
Registration form: https://www.aanmelder.nl/mediaeval2014/subscribe
Those working in image/video processing and video-analytics for privacy protection applications.
6 May: Development data release
2 June: Test data release
11 August: Run submission due
15 September: Results returned
28 September: Working notes paper deadline
Atta Badii (UoR), Touradj Ebrahimi (EPFL), Christian Fedorczak (Thales Communications & Security), Pavel Korshunov (EPFL), Tomas Piatrik (QMUL), Volker Eiselein (TUB), Ahmed Al-Obaidi (UoR).