The Konstanz natural video database (KoNViD-1k)

Kurzanzeige
dc.contributor.authorHosu, Vlad
dc.contributor.authorHahn, Franz
dc.contributor.authorJenadeleh, Mohsen
dc.contributor.authorLin, Hanhe
dc.contributor.authorMen, Hui
dc.contributor.authorSziranyi, Tamas
dc.contributor.authorLi, Shujun
dc.contributor.authorSaupe, Dietmar
dc.date.accessioned2017-06-01T09:41:07Z
dc.date.available2017-06-01T09:41:07Z
dc.date.issued2017eng
dc.description.abstractSubjective video quality assessment (VQA) strongly depends on semantics, context, and the types of visual distortions. Currently, all existing VQA databases include only a small num- ber of video sequences with artificial distortions. The development and evaluation of objective quality assessment methods would benefit from having larger datasets of real-world video sequences with corresponding subjective mean opinion scores (MOS), in particular for deep learning purposes. In addition, the training and validation of any VQA method intended to be ‘general purpose’ requires a large dataset of video sequences that are representative of the whole spectrum of available video content and all types of distortions. We report our work on KoNViD-1k, a subjectively annotated VQA database consisting of 1,200 public- domain video sequences, fairly sampled from a large public video dataset, YFCC100m. We present the challenges and choices we have made in creating such a database aimed at ‘in the wild’ authentic distortions, depicting a wide variety of content.eng
dc.description.versionpublishedeng
dc.identifier.doi10.1109/QoMEX.2017.7965673
dc.identifier.ppn505523396
dc.identifier.urihttps://kops.uni-konstanz.de/handle/123456789/39103
dc.language.isoengeng
dc.rightsterms-of-use
dc.rights.urihttps://rightsstatements.org/page/InC/1.0/
dc.subjectVideo database, authentic video, video qualitiy assessment, fair samling, crowdsourcingeng
dc.subject.ddc004eng
dc.titleThe Konstanz natural video database (KoNViD-1k)eng
dc.typeINPROCEEDINGSeng
dspace.entity.typePublication
kops.citation.bibtex
@inproceedings{Hosu2017Konst-39103,
  year={2017},
  doi={10.1109/QoMEX.2017.7965673},
  title={The Konstanz natural video database (KoNViD-1k)},
  url={https://www.uni-konstanz.de/mmsp/pubsys/publishedFiles/HoHaJe17.pdf},
  isbn={978-1-5386-4024-1},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)},
  author={Hosu, Vlad and Hahn, Franz and Jenadeleh, Mohsen and Lin, Hanhe and Men, Hui and Sziranyi, Tamas and Li, Shujun and Saupe, Dietmar}
}
kops.citation.iso690HOSU, Vlad, Franz HAHN, Mohsen JENADELEH, Hanhe LIN, Hui MEN, Tamas SZIRANYI, Shujun LI, Dietmar SAUPE, 2017. The Konstanz natural video database (KoNViD-1k). International Conference on Quality of Multimedia Experience (QoMEX 2017). Erfurt, 31. Mai 2017 - 2. Juni 2017. In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX). Piscataway, NJ: IEEE, 2017. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965673deu
kops.citation.iso690HOSU, Vlad, Franz HAHN, Mohsen JENADELEH, Hanhe LIN, Hui MEN, Tamas SZIRANYI, Shujun LI, Dietmar SAUPE, 2017. The Konstanz natural video database (KoNViD-1k). International Conference on Quality of Multimedia Experience (QoMEX 2017). Erfurt, May 31, 2017 - Jun 2, 2017. In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX). Piscataway, NJ: IEEE, 2017. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965673eng
kops.citation.rdf
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39103">
    <dc:contributor>Hosu, Vlad</dc:contributor>
    <dcterms:title>The Konstanz natural video database (KoNViD-1k)</dcterms:title>
    <dc:creator>Jenadeleh, Mohsen</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:abstract xml:lang="eng">Subjective video quality assessment (VQA) strongly depends on semantics, context, and the types of visual distortions. Currently, all existing VQA databases include only a small num- ber of video sequences with artificial distortions. The development and  evaluation  of  objective  quality  assessment  methods  would benefit from having larger datasets of real-world video sequences with  corresponding  subjective  mean  opinion  scores  (MOS),  in particular  for  deep  learning  purposes.  In  addition,  the  training and  validation  of  any  VQA  method  intended  to  be  ‘general purpose’  requires  a  large  dataset  of  video  sequences  that  are representative  of  the  whole  spectrum  of  available  video  content and all types of distortions. We report our work on KoNViD-1k, a subjectively annotated VQA database consisting of 1,200 public- domain video sequences, fairly sampled from a large public video dataset,  YFCC100m.  We  present  the  challenges  and  choices  we have  made  in  creating  such  a  database  aimed  at  ‘in  the  wild’ authentic  distortions,  depicting  a  wide  variety  of  content.</dcterms:abstract>
    <dc:creator>Men, Hui</dc:creator>
    <dc:creator>Hahn, Franz</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/39103"/>
    <dc:creator>Hosu, Vlad</dc:creator>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/39103/1/Hosu_2-e7mh9z8d8u09.pdf"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Hahn, Franz</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dcterms:issued>2017</dcterms:issued>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <dc:contributor>Li, Shujun</dc:contributor>
    <dc:contributor>Jenadeleh, Mohsen</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-06-01T09:41:07Z</dcterms:available>
    <dc:creator>Li, Shujun</dc:creator>
    <dc:creator>Sziranyi, Tamas</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:rights>terms-of-use</dc:rights>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/39103/1/Hosu_2-e7mh9z8d8u09.pdf"/>
    <dc:contributor>Men, Hui</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-06-01T09:41:07Z</dc:date>
    <dc:contributor>Sziranyi, Tamas</dc:contributor>
  </rdf:Description>
</rdf:RDF>
kops.conferencefieldInternational Conference on Quality of Multimedia Experience (QoMEX 2017), 31. Mai 2017 - 2. Juni 2017, Erfurtdeu
kops.date.conferenceEnd2017-06-02eng
kops.date.conferenceStart2017-05-31eng
kops.description.openAccessopenaccessgreen
kops.flag.knbibliographytrue
kops.identifier.nbnurn:nbn:de:bsz:352-2-e7mh9z8d8u09
kops.location.conferenceErfurteng
kops.sourcefield<i>2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)</i>. Piscataway, NJ: IEEE, 2017. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965673deu
kops.sourcefield.plain2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX). Piscataway, NJ: IEEE, 2017. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965673deu
kops.sourcefield.plain2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX). Piscataway, NJ: IEEE, 2017. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965673eng
kops.title.conferenceInternational Conference on Quality of Multimedia Experience (QoMEX 2017)eng
kops.urlhttps://www.uni-konstanz.de/mmsp/pubsys/publishedFiles/HoHaJe17.pdfeng
kops.urlDate2017-05-11eng
relation.isAuthorOfPublication46e43f0d-5589-4060-b110-18519cbf61e0
relation.isAuthorOfPublication795d4363-9c48-49d0-8f2a-4b9fe3ecea1a
relation.isAuthorOfPublication6a68664e-96d9-4ff1-847a-536c58f26500
relation.isAuthorOfPublication72057485-5f84-41aa-b6cb-8d616362e6a8
relation.isAuthorOfPublicationd41ed246-e2d3-4ec4-bdd7-24e073930e56
relation.isAuthorOfPublicationa28da8dd-b635-4125-ad86-10cedb27efba
relation.isAuthorOfPublicationfffb576d-6ec6-4221-8401-77f1d117a9b9
relation.isAuthorOfPublication.latestForDiscovery46e43f0d-5589-4060-b110-18519cbf61e0
source.identifier.isbn978-1-5386-4024-1
source.publisherIEEE
source.publisher.locationPiscataway, NJ
source.title2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)

Dateien

Originalbündel

Gerade angezeigt 1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
Hosu_2-e7mh9z8d8u09.pdf
Größe:
208.42 KB
Format:
Adobe Portable Document Format
Beschreibung:
Hosu_2-e7mh9z8d8u09.pdf
Hosu_2-e7mh9z8d8u09.pdfGröße: 208.42 KBDownloads: 995

Sammlungen

Informatik und Informationswissenschaft: Publikationen