Difference between revisions of "Research"

From MIPAL
Jump to: navigation, search
(Created page with " == Feature Selection and Extraction == In many machine learning and pattern recognition problems, the number of attributes are too large that the learning process becomes com...")
 
(Object Detection)
 
(5 intermediate revisions by one user not shown)
Line 36: Line 36:
  
 
== Object Detection ==
 
== Object Detection ==
 +
 +
* Rainbow SSD "[https://arxiv.org/pdf/1705.09587.pdf Enhancement of SSD by concatenating feature maps for object detection]", BMVC2017, London, UK, Sep. 2017. ([https://github.com/soo89/Rainbow-SSD Code available])
 +
 +
* RUN "[http://www.insticc.org/Primoris/Resources/PaperPdf.ashx?idPaper=73068 Two-Layer Residual Feature Fusion for Object Detection]", 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019), Prague, Czech Republic, February 2019. ([https://arxiv.org/abs/1707.05031v4 arXiv])
 +
 +
* MMOD "[https://arxiv.org/abs/1911.12721 Mixture-Model-based Bounding Box Density Estimation for Object Detection]", arXiv, Nov. 2019.
  
 
== Object Tracking ==
 
== Object Tracking ==

Latest revision as of 02:52, 19 February 2020

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.

Object Recognition

Object Detection

Object Tracking