BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Part A: Non-parametric image optimization &amp\; Part B: Crowdsour
 cing gaze data collection - Dan Goldman\, Adobe Inc
DTSTART:20120724T130000Z
DTEND:20120724T140000Z
UID:TALK38922@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Part A: Non-parametric image optimization\nAbstract: Patch-bas
 ed methods have shown tremendous promise for solving a range of problems i
 n image analysis\, editing\, and synthesis. Until recently these methods w
 ere too costly for practical use. In this talk I'll describe the PatchMatc
 h nearest-neighbor search algorithm\, which accelerates these methods whil
 e using less memory than previous implementations. I will demonstrate comm
 ercial implementations of existing technology for hole filling in images a
 nd new approaches for image editing in Adobe Photoshop CS6\, made possible
  by our PatchMatch engine.  I will also discuss ongoing research in non-ri
 gid correspondence and multi-source synthesis techniques that employ the s
 ame underlying algorithms.\n\nPart B: Crowdsourcing gaze data collection\n
 Abstract: Knowing where people look is a useful tool in many various image
  and video applications. However\, traditional gaze tracking hardware is e
 xpensive and requires local study participants\, so acquiring gaze locatio
 n data from a large number of participants is very problematic. In this wo
 rk we propose a crowdsourced method for acquisition of gaze direction data
  from a virtually unlimited number of participants\, using a robust self-r
 eporting mechanism. Our system collects temporally sparse but spatially de
 nse points-of-attention in any visual information. We apply our approach t
 o an existing video data set and demonstrate that we obtain results simila
 r to traditional gaze tracking. We also explore the parameter ranges of ou
 r method\, and collect gaze tracking data for a large set of YouTube video
 s.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR