BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Face Anonymity-Perceptibility Paradigm and an Application in Onlin
 e Dating Industry  - Dr. Shasha Lu\, Cambridge Judge Business School\, Uni
 versity of Cambridge
DTSTART:20161115T163000Z
DTEND:20161115T173000Z
UID:TALK69104@talks.cam.ac.uk
CONTACT:Xingjie Wei
DESCRIPTION:Whilst face image in the online dating profiles plays an impor
 tant role in screening for potential dates\, there is also a strong need t
 o protect the privacy of the dating site users. Consequently\, the dating 
 websites are in need of effective ways to incorporate user’s face prefer
 ence into the screening mechanism while reducing the risk of identificatio
 n from the use of face image. This problem belongs to a broad type of chal
 lenges where companies need to balance the two conflicting aspects (face a
 nonymization and face perception) when using face image\, such as customer
  relationship management\, hiring decision-making\, and perception-based f
 ace screening. Building upon the literature on face anonymity from compute
 r science and face perception from social psychology and neuropsychology\,
  the authors propose a Face Anonymity - Perceptibility (FAP) paradigm as a
  general framework when one attempts to solve three types of tradeoff prob
 lems (non-perception\, component perception and holistic perception). Four
  different methods can be applied to achieve particular type(s) of tradeof
 fs: feature reduction and feature replacement from the computer vision lit
 erature\, and two face abstraction methods (local abstraction and global a
 bstraction) proposed by the authors and grounded in the social psychology 
 and neuropsychology literature. The authors present an empirical study tha
 t tests the FAP paradigm by applying the local abstraction and global abst
 raction methods to online dating industry\, where Type III (holistic perce
 ption) tradeoff is desired. The results demonstrate that both methods are 
 effective in balancing the need for face anonymization with the need for m
 aintaining face perception. When evaluated on their predictive performance
  as online dating screening tool\, the proposed Face Abstraction-based Scr
 eening (FAS) models can generate an relative improvement of 38.6% (the med
 ian across all performance measures) over a model without the abstracted f
 acial information. 
LOCATION:KH107\, Cambridge Judge Business School\, University of Cambridge
END:VEVENT
END:VCALENDAR