Conference paper Open Access

Fusion of Compound Queries with Multiple Modalities for Known Item Video Search

Ilias Gialampoukidis; Anastasia Moumtzidou; Stefanos Vrochidis; Ioannis Kompatsiaris


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20200120171455.0</controlfield>
  <controlfield tag="001">2581316</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">10-12 June 2018</subfield>
    <subfield code="g">IVMSP</subfield>
    <subfield code="a">2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="0">(orcid)0000-0001-7615-8400</subfield>
    <subfield code="a">Anastasia Moumtzidou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="0">(orcid)0000-0002-2505-9178</subfield>
    <subfield code="a">Stefanos Vrochidis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="0">(orcid)0000-0001-6447-9020</subfield>
    <subfield code="a">Ioannis Kompatsiaris</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">673671</subfield>
    <subfield code="z">md5:1ccd838dd16ecf6bae4f72372495cba1</subfield>
    <subfield code="u">https://zenodo.org/record/2581316/files/2018-ieee-image_.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://ivmsp2018.org/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-06-10</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:2581316</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="0">(orcid)0000-0002-5234-9795</subfield>
    <subfield code="a">Ilias Gialampoukidis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Fusion of Compound Queries with Multiple Modalities for Known Item Video Search</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">700475</subfield>
    <subfield code="a">Enhancing decision support and management services in extreme weather climate events</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">779962</subfield>
    <subfield code="a">Visual and textual content re-purposing FOR(4) architecture, Design and video virtual reality games</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://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;Multimedia collections are ubiquitous and very often contain hundreds of hours of video information. The retrieval of a particular scene of a video (Known Item Search) in a large collection is a difficult problem, considering the multimodal character of all video shots and the complexity of the query, either visual or textual. We tackle these challenges by fusing, first, multiple modalities in a nonlinear graph-based way for each subtopic of the query. In addition, we fuse the top retrieved video shots per sub-query to provide the final list of retrieved shots, which is then re-ranked using temporal information. The framework is evaluated in popular Known Item Search tasks in the context of video shot retrieval and provides the largest Mean Reciprocal Rank scores.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/IVMSPW.2018.8448876</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
155
98
views
downloads
Views 155
Downloads 98
Data volume 66.0 MB
Unique views 143
Unique downloads 97

Share

Cite as