BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Visual search and mining of large scale image collections - Prof. 
 Andrew Zisserman\, University of Oxford
DTSTART:20090602T141000Z
DTEND:20090602T150000Z
UID:TALK18254@talks.cam.ac.uk
CONTACT:Dr Fabien Petitcolas
DESCRIPTION:*Abstract*: The first half of this talk will describe scalable
  methods for performing particular object search via visual queries in ver
 y large datasets of unordered images. We show how the combination of large
  visual vocabularies\, fast spatial verification\, query expansion and sof
 t assignment can dramatically boost the precision and recall of object ret
 rieval to give a fast and accurate system.\n\nThe second half will explore
  object mining in very large collections\, where the aim is to automatical
 ly discover and group images containing the same object. We use object sea
 rch to construct a matching graph over the collection where the strength o
 f the edges depends on the spatial consistency between the image nodes. St
 andard clustering techniques are then used to mine the objects.\n\nThese m
 ethods will be demonstrated on several large datasets of Flickr images.\n\
 nJoint work with Ondrej Chum\, Michael Isard\, James Philbin and Josef Siv
 ic.\n\n*Biography*: Andrew Zisserman is a Professor in the Department of E
 ngineering Science\, University of Oxford. He graduated from the Universit
 y of Cambridge with a degree in Theoretical Physics\, and for the last 20 
 years has carried out research in the area of Computer Vision. He has co-a
 uthored and co-edited several books on this area. The most recent\, "Multi
 ple View Geometry in Computer Vision" (with Richard Hartley)\, has now bee
 n published as a second edition in paperback and also translated into Chin
 ese. He has been a program co-chair and general co-chair of ICCV. Software
  from his research group was marketed by the spin out company 2d3 (www.2d3
 .com) as a camera tracker for the special effects industry. This was award
 ed a Technical Emmy in 2002. He has been awarded the IEEE Marr Prize three
  times.
LOCATION:Large public lecture room\, Microsoft Research\, Roger Needham Bu
 ilding\, 7 J J Thomson Avenue\, Cambridge CB3 0FB
END:VEVENT
END:VCALENDAR