leon.bottou.org

User Tools

Site Tools

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
papers:simard-99 [2007/02/02 08:35]
leonb 		papers:simard-99 [2018/12/06 10:04] (current)
leonb
Line 2: Line 2:
  
 //Abstract//: //Abstract//:
-Signal processing and pattern recognition algorithms make extensive use of convolution. In many cases, computational accuracy is+Signal processing and pattern recognition algorithms make extensive use of convolution.  
 +In many cases, computational accuracy is
 not as important as computational speed. In feature extraction, not as important as computational speed. In feature extraction,
 for instance, the features of interest in a signal are usually quite for instance, the features of interest in a signal are usually quite
Line 19: Line 20:
  
 <box 99% orange> <box 99% orange>
-Patrice Simard, Léon Bottou , Patrick Haffner and Yann Le Cun:  **Boxlets: a fast convolution algorithm for neural networks and signal processing**,  //Advances in Neural Information Processing Systems//, 11, MIT Press, Denver, 1999.+Patrice Simard, Léon Bottou , Patrick Haffner and Yann Le Cun:  **Boxlets: a fast convolution algorithm for neural networks and signal processing**,  //Advances in Neural Information Processing Systems 11 (NIPS 1998)//, 571-577, MIT Press, Denver, 1999.
  
 [[http://leon.bottou.org/publications/djvu/nips-1999.djvu|nips-1999.djvu]] [[http://leon.bottou.org/publications/djvu/nips-1999.djvu|nips-1999.djvu]]
Line 26: Line 27:
 </box> </box>
  
-  @inproceedings{simard-99,+  @incollection{simard-99,
     author = {Simard, Patrice and Bottou , L\'{e}on and Haffner, Patrick and  {LeCun}, Yann},     author = {Simard, Patrice and Bottou , L\'{e}on and Haffner, Patrick and  {LeCun}, Yann},
     title = {Boxlets: a fast convolution algorithm for neural networks and signal processing},     title = {Boxlets: a fast convolution algorithm for neural networks and signal processing},
-    booktitle = {Advances in Neural Information Processing Systems},+    booktitle = {Advances in Neural Information Processing Systems 11 (NIPS 1998)},
     address = {Denver},     address = {Denver},
-    volume = {11}, 
     publisher = {MIT Press},     publisher = {MIT Press},
     year = {1999},     year = {1999},
 +    pages = {571--577},
     url = {http://leon.bottou.org/papers/simard-99},     url = {http://leon.bottou.org/papers/simard-99},
   }   }
Line 40: Line 41:
 ==== Notes ==== ==== Notes ====
  
 +Maybe the most famous use of boxlets is the computation of the features of the Viola-Jones object recognition system [1,2]. The //integral image// representation is a boxlet of order zero. Such particular cases were also described in [3] (see the paper for details.)
  
-  * **[1]** Paul Viola, Michael Jones: Robust Real-time Object Detection, //International Journal of Computer Vision//, 57(2): 137-154, 2004 
  
 +  * **[1]**  Paul Viola, Michael Jones: Robust Real-time Object Detection, //Second International Workshop on Statistical and Computational Theories of Vision - Modeling, Learning, Computing, and Sampling//, Vancouver, July 2001.
 +  * **[2]** Paul Viola, Michael Jones: Robust Real-time Object Detection, //International Journal of Computer Vision//, 57(2):137-154, 2004
 +  * **[3]** Paul S. Heckberg:  Filtering by repeated integration. //ACM SlGGRAPH
 +conference on Computer graphics//, 20:315-321, Dallas, 1986
papers/simard-99.1170423345.txt.gz · Last modified: 2007/02/02 08:45 (external edit)

Page Tools