CUDAS : Distortion-Aware Saliency Benchmark

Lade...
Vorschaubild
Dateien
Zhao_2-zfiyul4ms70x2.pdf
Zhao_2-zfiyul4ms70x2.pdfGröße: 4.83 MBDownloads: 5
Datum
2023
Autor:innen
Zhao, Xin
Lou, Jianxun
Wu, Xinbo
Wu, Yingying
Lévêque, Lucie
Liu, Xiaochang
Guo, Pengfei
Qin, Yipeng
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Gold
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
IEEE Access. IEEE. 2023, 11, pp. 58025-58036. eISSN 2169-3536. Available under: doi: 10.1109/access.2023.3283344
Zusammenfassung

Visual saliency prediction remains an academic challenge due to the diversity and complexity of natural scenes as well as the scarcity of eye movement data on where people look in images. In many practical applications, digital images are inevitably subject to distortions, such as those caused by acquisition, editing, compression or transmission. A great deal of attention has been paid to predicting the saliency of distortion-free pristine images, but little attention has been given to understanding the impact of visual distortions on saliency prediction. In this paper, we first present the CUDAS database - a new distortion-aware saliency benchmark, where eye-tracking data was collected for 60 pristine images and their corresponding 540 distorted formats. We then conduct a statistical evaluation to reveal the behaviour of state-of-the-art saliency prediction models on distorted images and provide insights on building an effective model for distortion-aware saliency prediction. The new database is made publicly available to the research community.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Distortion, Databases, Graphics processing units, Visualization, Benchmark testing, Gaze tracking, Computational modeling
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690ZHAO, Xin, Jianxun LOU, Xinbo WU, Yingying WU, Lucie LÉVÊQUE, Xiaochang LIU, Pengfei GUO, Yipeng QIN, Hanhe LIN, Dietmar SAUPE, Hantao LIU, 2023. CUDAS : Distortion-Aware Saliency Benchmark. In: IEEE Access. IEEE. 2023, 11, pp. 58025-58036. eISSN 2169-3536. Available under: doi: 10.1109/access.2023.3283344
BibTex
@article{Zhao2023CUDAS-67086,
  year={2023},
  doi={10.1109/access.2023.3283344},
  title={CUDAS : Distortion-Aware Saliency Benchmark},
  volume={11},
  journal={IEEE Access},
  pages={58025--58036},
  author={Zhao, Xin and Lou, Jianxun and Wu, Xinbo and Wu, Yingying and Lévêque, Lucie and Liu, Xiaochang and Guo, Pengfei and Qin, Yipeng and Lin, Hanhe and Saupe, Dietmar and Liu, Hantao}
}
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/123456789/67086">
    <dc:creator>Lévêque, Lucie</dc:creator>
    <dc:contributor>Wu, Xinbo</dc:contributor>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-06-12T07:09:54Z</dcterms:available>
    <dc:creator>Zhao, Xin</dc:creator>
    <dc:contributor>Lou, Jianxun</dc:contributor>
    <dc:contributor>Liu, Xiaochang</dc:contributor>
    <dc:creator>Guo, Pengfei</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67086/1/Zhao_2-zfiyul4ms70x2.pdf"/>
    <dc:creator>Wu, Xinbo</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-06-12T07:09:54Z</dc:date>
    <dc:creator>Lou, Jianxun</dc:creator>
    <dc:contributor>Qin, Yipeng</dc:contributor>
    <dc:creator>Wu, Yingying</dc:creator>
    <dcterms:title>CUDAS : Distortion-Aware Saliency Benchmark</dcterms:title>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/4.0/"/>
    <dc:contributor>Liu, Hantao</dc:contributor>
    <dc:contributor>Guo, Pengfei</dc:contributor>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dc:creator>Liu, Xiaochang</dc:creator>
    <dc:rights>Attribution-NonCommercial-NoDerivatives 4.0 International</dc:rights>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67086/1/Zhao_2-zfiyul4ms70x2.pdf"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Liu, Hantao</dc:creator>
    <dc:contributor>Wu, Yingying</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2023</dcterms:issued>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/67086"/>
    <dc:creator>Qin, Yipeng</dc:creator>
    <dc:contributor>Zhao, Xin</dc:contributor>
    <dcterms:abstract>Visual saliency prediction remains an academic challenge due to the diversity and complexity of natural scenes as well as the scarcity of eye movement data on where people look in images. In many practical applications, digital images are inevitably subject to distortions, such as those caused by acquisition, editing, compression or transmission. A great deal of attention has been paid to predicting the saliency of distortion-free pristine images, but little attention has been given to understanding the impact of visual distortions on saliency prediction. In this paper, we first present the CUDAS database - a new distortion-aware saliency benchmark, where eye-tracking data was collected for 60 pristine images and their corresponding 540 distorted formats. We then conduct a statistical evaluation to reveal the behaviour of state-of-the-art saliency prediction models on distorted images and provide insights on building an effective model for distortion-aware saliency prediction. The new database is made publicly available to the research community.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dc:language>eng</dc:language>
    <dc:contributor>Lévêque, Lucie</dc:contributor>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
Diese Publikation teilen