BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Combining Social Media with Sensor Data for Situation Awareness an
 d Photography
DTSTART:20150605T100000
DTEND:20150605T110000
DTSTAMP:20260415T061222Z
UID:d2dd3995d2dd011c66da2e6dc78105217e636de7d09540f6cf6f867f
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mohan S Kankanhalli\, National University of Singapore\nWith t
 he spread of physical sensors and social sensors\, we are living in a worl
 d of big sensor data. Though they generate heterogeneous data\, they often
  provide complementary information. Combining these two types of sensors t
 ogether enables sensor-enhanced social media analysis which can lead to a 
 better understanding of dynamically occurring situations.\nWe present two 
 works that illustrate this general theme.\nIn the first work\, we utilize 
 event related information detected from physical sensors to filter and the
 n mine the geo-located social media data\, to obtain high-level semantic i
 nformation. Specifically\, we apply a suite of visual concept detectors on
  video cameras to generate "camera tweets" and develop a novel multi-layer
  tweeting cameras framework.\nWe fuse "camera tweets" and social media twe
 ets via a "Concept Image"\n(Cmage). Cmages\nare 2-D maps of concept signal
 s\, which serve as common data representation to facilitate event detectio
 n. We define a set of operators and analytic functions that can be applied
  on Cmages by the user not only to discover occurrences of events but also
  to analyze patterns of evolving situations. The feasibility and effective
 ness of our framework is demonstrated with a large-scale dataset containin
 g feeds from 150 CCTV cameras in New York City and Twitter data. We also d
 escribe our preliminary "Tweeting Camera" prototype in which a smart camer
 a can tweet semantic information through Twitter such that people can foll
 ow and get updated about events around the camera location.\nOur second wo
 rk combines photography knowledge learned from social media with the camer
 a sensors data to provide real-time photography assistance. Professional p
 hotographers use their knowledge and exploit the current context to take h
 igh quality photographs. However\, it is often challenging for an amateur 
 user to do that. Social media and physical sensors provide us an opportuni
 ty to improve the photo-taking experience for such users. We have develope
 d a photography model based on machine learning which is augmented with co
 ntextual information such as time\, geo-location\, environmental condition
 s and type of image\, that influence the quality of photo capture. The sen
 sors available in a camera system are utilized to infer the current scene 
 context. As scene composition and camera parameters play a vital role in t
 he aesthetics of a captured image\, our method addresses the problem of le
 arning photographic composition and camera parameters. We also propose the
  idea of computing the photographic composition bases\, eigenrules and bas
 erules\, to illustrate the proposed composition learning. Thus\, the propo
 sed system can be used to provide real-time feedback to the user regarding
  scene composition and camera parameters while the scene is being captured
 .\nBIOGRAPHY:\nMohan Kankanhalli is a Professor at the Department of Compu
 ter Science of the National University of Singapore. He is also the Vice P
 rovost for Graduate Education at NUS. Before becoming the Vice Provost in 
 2014\, he was the Associate Provost (Graduate Education) during 2011-2013.
  Earlier\, he was the Vice-Dean for Academic Affairs & Graduate Studies at
  the NUS School of Computing during 2008-2010 and Vice-Dean for Research d
 uring 2001-2007.\nMohan obtained his BTech from IIT Kharagpur and MS & PhD
  from the Rensselaer Polytechnic Institute.\nHis current research interest
 s are in Multimedia Systems (content processing\,\nretrieval) and Multimed
 ia Security (surveillance and privacy). He directs SeSaMe - the Centre for
  "Sensor-enhanced Social Media"\n(sesame.comp.nus.edu.sg).\nMohan is activ
 ely involved in organizing of many major conferences in the area of Multim
 edia. He was also the Director of Conferences for ACM SIG Multimedia durin
 g 2009-2013. He is on the editorial boards of several journals including t
 he ACM Transactions on Multimedia\, Springer Multimedia Systems Journal\, 
 Pattern Recognition Journal and Springer Multimedia Tools & Applications J
 ournal. He is a Fellow of IEEE.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR