1.1 --- /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.2 +++ b/org/notes.org	Tue Mar 05 18:55:21 2013 +0000
     1.3 @@ -0,0 +1,50 @@
     1.4 +
     1.5 +
     1.6 +* scribbles 
     1.7 +
     1.8 +scratch.mit.edu
     1.9 +
    1.10 +fredkin 
    1.11 +ef@cmu.edu
    1.12 +
    1.13 +gary Drescher logo papert lab
    1.14 +
    1.15 +* stuff for thesis from Winston 2/22
    1.16 +
    1.17 +Shimon Ullman tank -- a 3D model vision thing
    1.18 +
    1.19 +Paul Viola MIT PHD thesis (intensity -> surface)
    1.20 +
    1.21 +Grimson -- multiple scales
    1.22 +
    1.23 +Winston -- "most effective way to find papers is to ask someone."
    1.24 +
    1.25 +Talk to Poggio/Ullman/Finlayson to get moar papers
    1.26 +
    1.27 +
    1.28 +* Notes from Vision meeting Wednesday, 2/20
    1.29 +
    1.30 +David Clemems, PHG Thesis
    1.31 +Arizona university mind's eye project used model based vision
    1.32 +
    1.33 +"Model based vision" -> "generative vision"
    1.34 +
    1.35 +Microsoft Research flickr city square
    1.36 +
    1.37 +celiu -- M$ motion guy 
    1.38 +
    1.39 +prakesh -- read paper
    1.40 +
    1.41 +from ADK:
    1.42 +
    1.43 +I wasn't able to find much in an hour but I probably just don't know
    1.44 +the magic keywords.  You should look at David Clemens's thesis as I
    1.45 +mentioned. Also I believe it is Paul Cohen from Arizona State
    1.46 +University who initially worked on the simulation-driven activity
    1.47 +recognition in Mind's Eye, and then afaik changed tack completely.
    1.48 +
    1.49 +http://w3.sista.arizona.edu/~cohen/Publications/
    1.50 +
    1.51 +There is also Michael Burl of JPL whose page seems unavailable right
    1.52 +now. The JPL team also used 3D models of pose along with some kind of
    1.53 +scripts to recognize events.