Improving bag of visual words representations with genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{Escalante:2015:IJCNN,
  author =       "Hugo Jair Escalante and Jose Martinez-Carraza and 
                 Sergio Escalera and Victor Ponce-Lopez and 
                 Xavier Baro",
  booktitle =    "2015 International Joint Conference on Neural Networks
                 (IJCNN)",
  title =        "Improving bag of visual words representations with
                 genetic programming",
  year =         "2015",
  abstract =     "The bag of visual words is a well established
                 representation in diverse computer vision problems.
                 Taking inspiration from the fields of text mining and
                 retrieval, this representation has proved to be very
                 effective in a large number of domains. In most cases,
                 a standard term-frequency weighting scheme is
                 considered for representing images and videos in
                 computer vision. This is somewhat surprising, as there
                 are many alternative ways of generating bag of words
                 representations within the text processing community.
                 This paper explores the use of alternative weighting
                 schemes for landmark tasks in computer vision: image
                 categorization and gesture recognition. We study the
                 suitability of using well-known supervised and
                 unsupervised weighting schemes for such tasks. More
                 importantly, we devise a genetic program that learns
                 new ways of representing images and videos under the
                 bag of visual words representation. The proposed method
                 learns to combine term-weighting primitives trying to
                 maximize the classification performance. Experimental
                 results are reported in standard image and video data
                 sets showing the effectiveness of the proposed
                 evolutionary algorithm.",
  keywords =     "genetic algorithms, genetic programming",
  DOI =          "doi:10.1109/IJCNN.2015.7280799",
  ISSN =         "2161-4393",
  month =        jul,
  notes =        "Also known as \cite{7280799}",
}

Genetic Programming entries for Hugo Jair Escalante Jose Martinez-Carraza Sergio Escalera Victor Ponce-Lopez Xavier Baro

Citations