view org/notes.org @ 359:744ae7ef9b14

gabor filter looks right.
author Robert McIntyre <rlm@mit.edu>
date Thu, 07 Mar 2013 02:37:49 +0000
parents eb7c94a03188
children 2d8a8422ff59
line wrap: on
line source


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