Conference paper Open Access

Temporal Lecture Video Fragmentation using Word Embeddings

Damianos Galanopoulos; Vasileios Mezaris


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="653" ind1=" " ind2=" ">
    <subfield code="a">Lecture  Video  Fragmentation,</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Word  Embeddings</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Video Segmentation</subfield>
  </datafield>
  <controlfield tag="005">20190410032305.0</controlfield>
  <controlfield tag="001">2539272</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">08-11 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/CERTH</subfield>
    <subfield code="a">Vasileios Mezaris</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2840367</subfield>
    <subfield code="z">md5:a35e6b610e7e6c2ef81cb8d449f0be1d</subfield>
    <subfield code="u">https://zenodo.org/record/2539272/files/mmm19_lncs11296_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">2019-01-08</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-moving-h2020</subfield>
    <subfield code="o">oai:zenodo.org:2539272</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute/CERTH</subfield>
    <subfield code="a">Damianos Galanopoulos</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Temporal Lecture Video Fragmentation using Word Embeddings</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-moving-h2020</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;In this work the problem of temporal video lecture fragmentation in meaningful parts is addressed. The visual content of lecture video can not be effectively used for this task due to its extremely homogeneous content. A new method for lecture video fragmentation in which only automatically generated speech transcripts of a video are exploited, is proposed. Contrary to previously proposed works that employ visual, audio and textual features and use time-consuming supervised methods which require annotated training data, we present a method that analyses the transcripts&amp;rsquo; text with the help of word embeddings that are generated from pre-trained state-of-the-art neural networks. Furthermore,we address a major problem of video lecture fragmentation research, which is the lack of large-scale datasets for evaluation, by presenting a new artificially- generated dataset of synthetic video lecture transcripts that we make publicly available. Experimental comparisons document the merit of the proposed approach.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.2539271</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.2539272</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
17
14
views
downloads
All versions This version
Views 1717
Downloads 1414
Data volume 39.8 MB39.8 MB
Unique views 1414
Unique downloads 1212

Share

Cite as