Wednesday, 23 Aug 2017
You are here: Home VCE Grand Challenge VideoSense Grand Challenge 2013

Subscribe to our Newsletter

How many eyes has a typical person? (ex: 1)
Name:
Email:

Twitter Feed

VideoSense Grand Challenge 2013 PDF Print E-mail
Written by University of Reading   
Wednesday, 27 February 2013 09:48

This new VideoSense Grand Challenge builds on the results of the previous one (the 2012 MediaEval Privacy Task) and aims at finding ways to protect the privacy of people in videos. The insights arising from the Privacy Task as was run last year, showed that regardless of the methods used for filtering out the elements of the video image that can potentially reveal the identity of the data subject, the best results belonged to those using superior object detectors.  Hence this year the participants will be offered the object detections as given.

Accordingly, participants will be invited to propose methods whereby elements of the image of persons featured in video frames can be obscured so to render them unrecognisable. This is intended to ensure that a person appearing in a video frame will not be visually identifiable based on an image which is thus obscured.   This action is to be performed as a matter of privacy protection for any persons whose picture might happen to be knowingly or unknowingly captured in a video frame.  
The main elements to be obscured are as fallow: faces, ethnicity, gender, and accessories. You are free to filter other elements such distinctive clothing or gait, but should keep in mind that as much information as possible should be retained in order to keep the video understandable.

Since the resulting partly obscured videos would nonetheless have to remain available for viewing, an optimal balance should be struck so that despite the extent of such masking of the identity as may be necessary, the categorical identity of any masked data subject therein, i.e. as a human being, or the type of their activity as may have been evident in the original video frame, can still be recognisable to the viewer. Furthermore, the proposed obscuring techniques should take into consideration the acceptability and attractiveness of the resulting obscured and scrambled regions.

Participants are encouraged to present their results at the MediaEval 2013 workshop, which will take place in Barcelona, Catalunya, Spain, on Friday-Saturday 18-19 October 2013. Note that this is just before ACM Multimedia 2013 http://acmmm13.org/, which will be held Monday-Friday 21-25 October 2013, also in Barcelona.

Provisional Task schedule
June 3rd: data set release
September 13th: run submission
September 25th: results returned
October 18th: MediaEval workshop

Registration will soon be open for participants at http://www.multimediaeval.org/mediaeval2013/

Last Updated on Thursday, 28 February 2013 09:19