Conference paper Open Access

ADVERSARIAL UNSUPERVISED VIDEO SUMMARIZATION AUGMENTED WITH DICTIONARY LOSS

Kaseris, Michail; Mademlis, Ioannis; Pitas, Ioannis


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.4899284">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.4899284</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4899284"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Kaseris, Michail</foaf:name>
        <foaf:givenName>Michail</foaf:givenName>
        <foaf:familyName>Kaseris</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Aristotle University of Thessaloniki</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Mademlis, Ioannis</foaf:name>
        <foaf:givenName>Ioannis</foaf:givenName>
        <foaf:familyName>Mademlis</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Aristotle University of Thessaloniki</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Pitas, Ioannis</foaf:name>
        <foaf:givenName>Ioannis</foaf:givenName>
        <foaf:familyName>Pitas</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Aristotle University of Thessaloniki</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>ADVERSARIAL UNSUPERVISED VIDEO SUMMARIZATION AUGMENTED WITH DICTIONARY LOSS</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-09-30</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4899284"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4899284</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4899283"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/ai4media"/>
    <dct:description>&lt;p&gt;Automated unsupervised video summarization by key-frame extraction consists in identifying representative video frames, best abridging a complete input sequence, and temporally ordering them to form a video summary, without relying on manually constructed ground-truth key-frame sets. State-of-the-art unsupervised deep neural approaches consider the desired summary to be a subset of the original sequence, composed of video frames that are sufficient to visually reconstruct the entire input. They typically employ a pre-trained CNN for extracting a vector representation per RGB video frame and a baseline LSTM adversarial learning framework for identifying key-frames. In this paper, to better guide the network towards properly selecting video frames that can faithfully reconstruct the original video, we augment the baseline framework with an additional LSTM autoencoder, which learns in parallel a fixed-length representation of the entire original input sequence. This is exploited during training, where a novel loss term inspired by dictionary learning is added to the network optimization objectives, further biasing key-frame selection towards video frames which are collectively able to recreate the original video. Empirical evaluation on two common public relevant datasets indicates highly favourable results.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4899284">https://doi.org/10.5281/zenodo.4899284</dcat:accessURL>
        <dcat:byteSize>179095</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4899284/files/kaseris.pdf">https://zenodo.org/record/4899284/files/kaseris.pdf</dcat:downloadURL>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
75
65
views
downloads
All versions This version
Views 7575
Downloads 6565
Data volume 11.6 MB11.6 MB
Unique views 6464
Unique downloads 5656

Share

Cite as