Building holistic descriptors for scene recognition: a multi-objective genetic programming approach

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{conf/mm/LiuSL13,
  author =       "Li Liu and Ling Shao and Xuelong Li",
  title =        "Building holistic descriptors for scene recognition: a
                 multi-objective genetic programming approach",
  booktitle =    "Proceedings of the 21st ACM international conference
                 on Multimedia",
  year =         "2013",
  editor =       "Alejandro Jaimes and Nicu Sebe and Nozha Boujemaa and 
                 Daniel Gatica-Perez and David A. Shamma and 
                 Marcel Worring and Roger Zimmermann",
  publisher =    "ACM",
  pages =        "997--1006",
  address =      "Barcelona, Spain",
  month =        oct # " 21-25",
  keywords =     "genetic algorithms, genetic programming",
  bibdate =      "2013-11-14",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/mm/mm2013.html#LiuSL13",
  isbn13 =       "978-1-4503-2404-5",
  URL =          "http://dl.acm.org/citation.cfm?id=2502081",
  URL =          "http://doi.acm.org/10.1145/2502081.2502095",
  DOI =          "doi:10.1145/2502081.2502095",
  acmid =        "2502095",
  size =         "10 pages",
  abstract =     "Real-world scene recognition has been one of the most
                 challenging research topics in computer vision, due to
                 the tremendous intra-class variability and the wide
                 range of scene categories. In this paper, we
                 successfully apply an evolutionary methodology to
                 automatically synthesise domain-adaptive holistic
                 descriptors for the task of scene recognition, instead
                 of using hand-tuned descriptors. We address this as an
                 optimisation problem by using multi-objective genetic
                 programming (MOGP). Specifically, a set of primitive
                 operators and filters are first randomly assembled in
                 the MOGP framework as tree-based combinations, which
                 are then evaluated by two objective fitness criteria
                 i.e., the classification error and the tree complexity.
                 Finally, the best-so-far solution selected by MOGP is
                 regarded as the (near-)optimal feature descriptor for
                 scene recognition. We have evaluated our approach on
                 three realistic scene datasets: MIT urban and nature,
                 SUN and UIUC Sport. Experimental results consistently
                 show that our MOGP-generated descriptors achieve
                 significantly higher recognition accuracies compared
                 with state-of-the-art hand-crafted and machine-learnt
                 features.",
}

Genetic Programming entries for Li Liu Ling Shao Xuelong Li

Citations