---
res:
  bibo_abstract:
  - Fisher Kernels and Deep Learning were two developments with significant impact
    on large-scale object categorization in the last years. Both approaches were shown
    to achieve state-of-the-art results on large-scale object categorization datasets,
    such as ImageNet. Conceptually, however, they are perceived as very different
    and it is not uncommon for heated debates to spring up when advocates of both
    paradigms meet at conferences or workshops. In this work, we emphasize the similarities
    between both architectures rather than their differences and we argue that such
    a unified view allows us to transfer ideas from one domain to the other. As a
    concrete example we introduce a method for learning a support vector machine classifier
    with Fisher kernel at the same time as a task-specific data representation. We
    reinterpret the setting as a multi-layer feed forward network. Its final layer
    is the classifier, parameterized by a weight vector, and the two previous layers
    compute Fisher vectors, parameterized by the coefficients of a Gaussian mixture
    model. We introduce a gradient descent based learning algorithm that, in contrast
    to other feature learning techniques, is not just derived from intuition or biological
    analogy, but has a theoretical justification in the framework of statistical learning
    theory. Our experiments show that the new training procedure leads to significant
    improvements in classification accuracy while preserving the modularity and geometric
    interpretability of a support vector machine setup.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Vladyslav
      foaf_name: Sydorov, Vladyslav
      foaf_surname: Sydorov
  - foaf_Person:
      foaf_givenName: Mayu
      foaf_name: Sakurada, Mayu
      foaf_surname: Sakurada
  - foaf_Person:
      foaf_givenName: Christoph
      foaf_name: Lampert, Christoph
      foaf_surname: Lampert
      foaf_workInfoHomepage: http://www.librecat.org/personId=40C20FD2-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0001-8622-7887
  bibo_doi: 10.1109/CVPR.2014.182
  dct_date: 2014^xs_gYear
  dct_identifier:
  - UT:000361555601057
  dct_language: eng
  dct_publisher: IEEE@
  dct_title: Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters@
...