Differences

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

--- papers:simard-99 [2006/04/20 10:57]
127.0.0.1 (old revision restored)
+++ papers:simard-99 [2018/12/06 10:04] (current)
leonb
@@ Line 1: / Line 1: @@
-===== Boxlets: a fast convolution algorithm for neural networks and signal processing =====
+===== Boxlets: a Fast Convolution Algorithm for Neural Networks and Signal Processing =====
+//Abstract//:
+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,
+for instance, the features of interest in a signal are usually quite
+distorted. This form of noise justifies some level of quantization in
+order to achieve faster feature extraction. Our approach consists
+of approximating regions of the signal with low degree polynomials,
+and then differentiating the resulting signals in order to obtain
+impulse functions (or derivatives of impulse functions). With this
+representation, convolution becomes extremely simple and can be
+implemented quite effectively. The true convolution can be recov-
+ered by integrating the result of the convolution. This method
+yields substantial speed up in feature extraction and is applicable
+to convolutional neural networks.
 <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]]
@@ Line 11: / Line 27: @@
 </box>
-  @inproceedings{simard-99,
+  @incollection{simard-99,
-    author = {Simard, Patrice and Bottou , L\'{e}on and Haffner, Patrick and Cun}, Yann {Le},
+    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},
-    booktitle = {Advances in Neural Information Processing Systems},
+    booktitle = {Advances in Neural Information Processing Systems 11 (NIPS 1998)},
     address = {Denver},
-    volume = {11},
     publisher = {MIT Press},
     year = {1999},
+    pages = {571--577},
     url = {http://leon.bottou.org/papers/simard-99},
   }
+==== 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, //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

User Tools

Site Tools

Differences

Page Tools