rlm@327: 
rlm@327: 
rlm@327: * scribbles 
rlm@327: 
rlm@327: scratch.mit.edu
rlm@327: 
rlm@327: fredkin 
rlm@327: ef@cmu.edu
rlm@327: 
rlm@327: gary Drescher logo papert lab
rlm@327: 
rlm@327: * stuff for thesis from Winston 2/22
rlm@327: 
rlm@327: Shimon Ullman tank -- a 3D model vision thing
rlm@327: 
rlm@327: Paul Viola MIT PHD thesis (intensity -> surface)
rlm@327: 
rlm@327: Grimson -- multiple scales
rlm@327: 
rlm@327: Winston -- "most effective way to find papers is to ask someone."
rlm@327: 
rlm@327: Talk to Poggio/Ullman/Finlayson to get moar papers
rlm@327: 
rlm@327: 
rlm@327: * Notes from Vision meeting Wednesday, 2/20
rlm@327: 
rlm@327: David Clemems, PHG Thesis
rlm@327: Arizona university mind's eye project used model based vision
rlm@327: 
rlm@327: "Model based vision" -> "generative vision"
rlm@327: 
rlm@327: Microsoft Research flickr city square
rlm@327: 
rlm@369: Ce Liu -- M$ motion guy 
rlm@327: 
rlm@327: prakesh -- read paper
rlm@327: 
rlm@327: from ADK:
rlm@327: 
rlm@327: I wasn't able to find much in an hour but I probably just don't know
rlm@327: the magic keywords.  You should look at David Clemens's thesis as I
rlm@327: mentioned. Also I believe it is Paul Cohen from Arizona State
rlm@327: University who initially worked on the simulation-driven activity
rlm@327: recognition in Mind's Eye, and then afaik changed tack completely.
rlm@327: 
rlm@327: http://w3.sista.arizona.edu/~cohen/Publications/
rlm@327: 
rlm@327: There is also Michael Burl of JPL whose page seems unavailable right
rlm@327: now. The JPL team also used 3D models of pose along with some kind of
rlm@327: scripts to recognize events.