Known-Item Search in Video : An Eye Tracking-Based Study

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2024
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Institutionen der Bundesrepublik Deutschland: VIKING (13N16242)
Deutsche Forschungsgemeinschaft (DFG): 251654672
Projekt
Open Access-Veröffentlichung
Open Access Bookpart
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
GURRIN, Cathal, Hrsg., Rachada KONGKACHANDRA, Hrsg., Klaus SCHOEFFMANN, Hrsg. und andere. ICMR '24: Proceedings of the 2024 International Conference on Multimedia Retrieval. New York, NY: ACM, 2024, S. 311-319. ISBN 979-8-4007-0619-6. Verfügbar unter: doi: 10.1145/3652583.3658119
Zusammenfassung

Deep learning has revolutionized multimedia retrieval, yet effectively searching within large video collections remains a complex challenge. This paper focuses on the design and evaluation of known-item search systems, leveraging the strengths of CLIP-based deep neural networks for ranking. At events like the Video Browser Showdown, these models have shown promise in effectively ranking the video frames. While ranking models can be pre-selected automatically based on a benchmark collection, the selection of an optimal browsing interface, crucial for refining top-ranked items, is complex and heavily influenced by user behavior. Our study addresses this by presenting an eye tracking-based analysis of user interaction with different image grid layouts. This approach offers novel insights into search patterns and user preferences, particularly examining the trade-off between displaying fewer but larger images versus more but smaller images. Our findings reveal a preference for grids with fewer images and detail how image similarity and grid position affect user search behavior. These results not only enhance our understanding of effective video retrieval interface design but also set the stage for future advancements in the field.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
ICMR '24: International Conference on Multimedia Retrieval, 10. Juni 2024 - 14. Juni 2024, Phuket, Thailand
Rezension
undefined / . - undefined, undefined
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Datensätze
Zitieren
ISO 690JOOS, Lucas, Bastian JÄCKL, Daniel A. KEIM, Maximilian T. FISCHER, Ladislav PESKA, Jakub LOKOČ, 2024. Known-Item Search in Video : An Eye Tracking-Based Study. ICMR '24: International Conference on Multimedia Retrieval. Phuket, Thailand, 10. Juni 2024 - 14. Juni 2024. In: GURRIN, Cathal, Hrsg., Rachada KONGKACHANDRA, Hrsg., Klaus SCHOEFFMANN, Hrsg. und andere. ICMR '24: Proceedings of the 2024 International Conference on Multimedia Retrieval. New York, NY: ACM, 2024, S. 311-319. ISBN 979-8-4007-0619-6. Verfügbar unter: doi: 10.1145/3652583.3658119
BibTex
@inproceedings{Joos2024-05-30Known-70160,
  year={2024},
  doi={10.1145/3652583.3658119},
  title={Known-Item Search in Video : An Eye Tracking-Based Study},
  isbn={979-8-4007-0619-6},
  publisher={ACM},
  address={New York, NY},
  booktitle={ICMR '24: Proceedings of the 2024 International Conference on Multimedia Retrieval},
  pages={311--319},
  editor={Gurrin, Cathal and Kongkachandra, Rachada and Schoeffmann, Klaus},
  author={Joos, Lucas and Jäckl, Bastian and Keim, Daniel A. and Fischer, Maximilian T. and Peska, Ladislav and Lokoč, Jakub}
}
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/123456789/70160">
    <dcterms:abstract>Deep learning has revolutionized multimedia retrieval, yet effectively searching within large video collections remains a complex challenge. This paper focuses on the design and evaluation of known-item search systems, leveraging the strengths of CLIP-based deep neural networks for ranking. At events like the Video Browser Showdown, these models have shown promise in effectively ranking the video frames. While ranking models can be pre-selected automatically based on a benchmark collection, the selection of an optimal browsing interface, crucial for refining top-ranked items, is complex and heavily influenced by user behavior. Our study addresses this by presenting an eye tracking-based analysis of user interaction with different image grid layouts. This approach offers novel insights into search patterns and user preferences, particularly examining the trade-off between displaying fewer but larger images versus more but smaller images. Our findings reveal a preference for grids with fewer images and detail how image similarity and grid position affect user search behavior. These results not only enhance our understanding of effective video retrieval interface design but also set the stage for future advancements in the field.</dcterms:abstract>
    <dcterms:title>Known-Item Search in Video : An Eye Tracking-Based Study</dcterms:title>
    <dc:language>eng</dc:language>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Peska, Ladislav</dc:contributor>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:creator>Joos, Lucas</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Jäckl, Bastian</dc:creator>
    <dc:contributor>Fischer, Maximilian T.</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/70160"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Lokoč, Jakub</dc:contributor>
    <dc:creator>Fischer, Maximilian T.</dc:creator>
    <dcterms:issued>2024-05-30</dcterms:issued>
    <dc:contributor>Joos, Lucas</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-06-19T08:21:56Z</dcterms:available>
    <dc:creator>Peska, Ladislav</dc:creator>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:contributor>Jäckl, Bastian</dc:contributor>
    <dc:creator>Lokoč, Jakub</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-06-19T08:21:56Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </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
Diese Publikation teilen