1.1 --- a/org/literature-review.org	Thu Apr 11 06:19:59 2013 +0000
     1.2 +++ b/org/literature-review.org	Thu Apr 11 06:46:01 2013 +0000
     1.3 @@ -211,7 +211,10 @@
     1.4  nifty, relevant, realistic ideas
     1.5  He doesn't confine himself to unplasaubile assumptions
     1.6  
     1.7 +** Our Reading
     1.8 +*** 2002 Visual features of intermediate complexity and their use in classification
     1.9  
    1.10 +    
    1.11  
    1.12  
    1.13  ** Getting around the dumb "fixed training set" methods
    1.14 @@ -250,10 +253,6 @@
    1.15  
    1.16  ** Non Parametric Models
    1.17  
    1.18 -*** 2002 Visual features of intermediate complexity and their use in classification
    1.19 -
    1.20 -    
    1.21 -
    1.22  *** 2010 The chains model for detecting parts by their context
    1.23  
    1.24      Like the constelation method for rigid objects, but extended to
    1.25 @@ -320,4 +319,10 @@
    1.26  
    1.27      Allows you to trasfer the "gestalt" of a similiar class to a new
    1.28      class, by adapting all the features of the learned class that have
    1.29 -    correspondance to the new class.
    1.30 \ No newline at end of file
    1.31 +    correspondance to the new class.
    1.32 +
    1.33 +*** 2007 Semantic Hierarchies for Recognizing Objects and Parts
    1.34 +
    1.35 +    Better learning of complex objects like faces by learning each
    1.36 +    piece (like nose, mouth, eye, etc) separately, then making sure
    1.37 +    that the features are in plausable positions.
    1.38 \ No newline at end of file