Conference paper Open Access

Image Aesthetics Assessment using Fully Convolutional Neural Networks

Apostolidis, Konstantinos; Mezaris, Vasileios


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Image Aesthetics</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Deep Learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Fully Convolutional Neural Networks</subfield>
  </datafield>
  <controlfield tag="005">20191114191028.0</controlfield>
  <controlfield tag="001">2539133</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">8-11 January 2019</subfield>
    <subfield code="g">MMM 2019</subfield>
    <subfield code="a">25th International Conference on Multimedia Modeling</subfield>
    <subfield code="c">Thessaloniki, Greece</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute / Centre for Research &amp; Technology - Hellas</subfield>
    <subfield code="a">Mezaris, Vasileios</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1021290</subfield>
    <subfield code="z">md5:643f704a349dad189342a67807bd3c22</subfield>
    <subfield code="u">https://zenodo.org/record/2539133/files/mmm19_lncs11295_1_preprint.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">http://mmm2019.iti.gr/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-01-10</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-emma-h2020</subfield>
    <subfield code="p">user-invid-h2020</subfield>
    <subfield code="o">oai:zenodo.org:2539133</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute / Centre for Research &amp; Technology - Hellas</subfield>
    <subfield code="a">Apostolidis, Konstantinos</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Image Aesthetics Assessment using Fully Convolutional Neural Networks</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-emma-h2020</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-invid-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">687786</subfield>
    <subfield code="a">In Video Veritas – Verification of Social Media Video Content for the News Industry</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">732665</subfield>
    <subfield code="a">Enriching Market solutions for content Management and publishing with state of the art multimedia Analysis techniques</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This paper presents a new method for assessing the aesthetic quality of images. Based on the findings of previous works on this topic, we propose a method that addresses the shortcomings of existing ones, by: a) Making possible to feed higher-resolution images in the network, by introducing a fully convolutional neural network as the classier. b) Maintaining the original aspect ratio of images in the input of the network, to avoid distortions caused by re-scaling. And c) combining local and global features from the image for making the assessment of its aesthetic quality. The proposed method is shown to achieve state of the art results on a standard large-scale benchmark dataset.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/978-3-030-05710-7_30</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
74
57
views
downloads
Views 74
Downloads 57
Data volume 58.2 MB
Unique views 71
Unique downloads 48

Share

Cite as