I spent about five minutes googling around and didn't notice any description of the algorithm used to defined google sets. I assume it is done by finding things that occur either together or singularly in the same context.
Does anybody know or having any links to how google sets are defined? Ed Porter -----Original Message----- From: Neil H. [mailto:[EMAIL PROTECTED] Sent: Saturday, November 10, 2007 5:05 PM To: [email protected] Subject: [agi] Using Google Sets for "common sense" in computer vision I came across a paper the other day by Serge Belongie's group at UCSD which has a simple, yet clever, solution of how to incorporate "common sense" information about what objects belong in a scene to improve computer vision algorithms. Basically, if you have an idea of some of the objects detected in a scene, you can use Google Sets to increase the probability of detecting related objects. For example, it's easier to determining if an object is a lemon or a tennis ball if you're also detecting a tennis racket and person in the same image. http://www.cs.ucsd.edu/~sjb/iccv2007a.pdf http://www.sciencedaily.com/releases/2007/10/071017174328.htm http://labs.google.com/sets The research is still quite early, but could Google Sets also be useful for more general AI tasks? -- Neil ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=63974557-a8c720
