Mercurial > cortex
annotate org/notes.org @ 371:9c37a55e1cd2
moar literature review.
author | Robert McIntyre <rlm@mit.edu> |
---|---|
date | Tue, 12 Mar 2013 03:54:30 +0000 |
parents | 2d8a8422ff59 |
children |
rev | line source |
---|---|
rlm@327 | 1 |
rlm@327 | 2 |
rlm@327 | 3 * scribbles |
rlm@327 | 4 |
rlm@327 | 5 scratch.mit.edu |
rlm@327 | 6 |
rlm@327 | 7 fredkin |
rlm@327 | 8 ef@cmu.edu |
rlm@327 | 9 |
rlm@327 | 10 gary Drescher logo papert lab |
rlm@327 | 11 |
rlm@327 | 12 * stuff for thesis from Winston 2/22 |
rlm@327 | 13 |
rlm@327 | 14 Shimon Ullman tank -- a 3D model vision thing |
rlm@327 | 15 |
rlm@327 | 16 Paul Viola MIT PHD thesis (intensity -> surface) |
rlm@327 | 17 |
rlm@327 | 18 Grimson -- multiple scales |
rlm@327 | 19 |
rlm@327 | 20 Winston -- "most effective way to find papers is to ask someone." |
rlm@327 | 21 |
rlm@327 | 22 Talk to Poggio/Ullman/Finlayson to get moar papers |
rlm@327 | 23 |
rlm@327 | 24 |
rlm@327 | 25 * Notes from Vision meeting Wednesday, 2/20 |
rlm@327 | 26 |
rlm@327 | 27 David Clemems, PHG Thesis |
rlm@327 | 28 Arizona university mind's eye project used model based vision |
rlm@327 | 29 |
rlm@327 | 30 "Model based vision" -> "generative vision" |
rlm@327 | 31 |
rlm@327 | 32 Microsoft Research flickr city square |
rlm@327 | 33 |
rlm@369 | 34 Ce Liu -- M$ motion guy |
rlm@327 | 35 |
rlm@327 | 36 prakesh -- read paper |
rlm@327 | 37 |
rlm@327 | 38 from ADK: |
rlm@327 | 39 |
rlm@327 | 40 I wasn't able to find much in an hour but I probably just don't know |
rlm@327 | 41 the magic keywords. You should look at David Clemens's thesis as I |
rlm@327 | 42 mentioned. Also I believe it is Paul Cohen from Arizona State |
rlm@327 | 43 University who initially worked on the simulation-driven activity |
rlm@327 | 44 recognition in Mind's Eye, and then afaik changed tack completely. |
rlm@327 | 45 |
rlm@327 | 46 http://w3.sista.arizona.edu/~cohen/Publications/ |
rlm@327 | 47 |
rlm@327 | 48 There is also Michael Burl of JPL whose page seems unavailable right |
rlm@327 | 49 now. The JPL team also used 3D models of pose along with some kind of |
rlm@327 | 50 scripts to recognize events. |