<?xml version="1.0"?>
<api>
  <query-continue>
    <allpages gapcontinue="SNU_Dataset_for_Online_Music_Symbol_Recognition" />
  </query-continue>
  <query>
    <pages>
      <page pageid="59" ns="0" title="Repository">
        <revisions>
          <rev contentformat="text/x-wiki" contentmodel="wikitext" xml:space="preserve">== Slides &amp; Material ==
* [[Media:PCAL1_tutorial.pdf| PCA-L1]]
* [[Media:NPT_tutorial.pdf| Nonlinear Projection Trick]]
* [[Media:Intro2CNNsRNNs.pdf| Introduction to Convolutional Neural Networks &amp; Recurrent Neural Networks]]
* [https://github.com/soo89/Rainbow-SSD Rainbow SSD for Object Detection]
* [https://github.com/soo89/CSD-RFCN CSD: Consistency-Based Semi-Supervised Learning for Object Detection]

== Datasets ==
* [[Labels of Strokes in HOMUS Dataset]]
* [[SNU Dataset for Online Music Symbol Recognition]]

== Useful links ==
* [[Optimization]]
* [[Machine Learning]]
* [[Computer Vision]]
* [[Neural Networks]]
* [[Math]]

== Tex related ==
* [http://wiki.ktug.org/wiki/wiki.php/HangulAndMiKTeX Hangul in Miktex]</rev>
        </revisions>
      </page>
      <page pageid="58" ns="0" title="Research">
        <revisions>
          <rev contentformat="text/x-wiki" contentmodel="wikitext" xml:space="preserve">
== Feature Selection and Extraction ==
In many machine learning and pattern recognition problems, the number of attributes are too large that the learning process becomes complicated with degraded performance.
To alleviate this problem, depending on the problems to be solved, one may '''select good attributes''' from the available input attributes or '''extract new features''' by combining the existing attributes.
The former is known as '''input feature selection''' while the latter is called as '''feature extraction'''. 

We have tackled the ''feature selection and extraction problems'' extensively and proposed the following algorithms.

* Feature selection for classification problems
** [[Media:MIFSU_TNN.pdf| TMFS (Taguchi Method for Feature Selection)]]
** [[Media:MIFSU_TNN.pdf| PWFS (Feature Selection based on Parzen Window)]]

* Feature extraction for classification problems
** [[Media:ICA_FX_TKDE.pdf| ICA-FX (Feature eXtraction based on Independent Component Analysis)]]
** [[Media:PWFX_IJPRAI.pdf| PWFX (Feature eXtraction based on Parzen Window)]]

* Feature extraction for regression problems
** [[Media:ICAFX_R_NEUCOM.pdf| ICA-FXr (Feature eXtraction based on Independent Component Analysis for regression problems)]]
** [[Media:NEUCOM11762_final.pdf| LDAr (Linear Discriminant Analysis for regression problems)]]
** [[Media:KDAr.pdf|  KDAr (Kernel Discriminant Analysis for regression problems)]]
** [[Media:TVT_gaze_rec_final.pdf| 2D-LDAr (2-Dimensional Linear Discriminant Analysis for regression problems)]]

* Robust feature extraction using non-L2 norm
** [[Media:L1PCA_TPAMI.pdf| PCA-L1 (Principal Component Analysis based on L1-norm maximization)]]
*** a [[Media:PCAL1_tutorial.pdf| short tutorial]] is also available
** [[Media:PCA_Lp.pdf| PCA-Lp (Principal Component Analysis based on L1-norm maximization)]]
** [[Media:LDA_Lp_final.pdf| LDA-Lp (Linear Discriminant Analysis by Lp-norm)]]
** [[Media:SL1BDA_PR.pdf| L1BDA (L1-norm based Biased Discriminant Analysis)]]
** [[Media:BDAGM_PR.pdf|BDAGM (Biased Discriminant Analysis using Generalized Mean)]]

* Theory in kernel methods
** [[Media:NPT.pdf| NPT (Nonlinear Projection Trick)]]
*** a [[Media:NPT_tutorial.pdf| short tutorial]] is also available

== Object Recognition ==

== Object Detection ==

* Rainbow SSD &quot;[https://arxiv.org/pdf/1705.09587.pdf Enhancement of SSD by concatenating feature maps for object detection]&quot;, BMVC2017, London, UK, Sep. 2017. ([https://github.com/soo89/Rainbow-SSD Code available])

* RUN &quot;[http://www.insticc.org/Primoris/Resources/PaperPdf.ashx?idPaper=73068 Two-Layer Residual Feature Fusion for Object Detection]&quot;, 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019), Prague, Czech Republic, February 2019. ([https://arxiv.org/abs/1707.05031v4 arXiv])

* MMOD &quot;[https://arxiv.org/abs/1911.12721 Mixture-Model-based Bounding Box Density Estimation for Object Detection]&quot;, arXiv, Nov. 2019.

== Object Tracking ==</rev>
        </revisions>
      </page>
    </pages>
  </query>
</api>