Publikation:

PraK Tool V3 : Enhancing Video Item Search Using Localized Text and Texture Queries

Vorschaubild

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2025

Autor:innen

Kloda, Vojtěch
Verner, Benjamin
Vopálková, Zuzana
Hajko, Jakub
Lokoč, Jakub

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

URI (zitierfähiger Link)
DOI (zitierfähiger Link)
https://doi.org/10.1007/978-981-96-2074-6_39
ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung

Sammlungen

Informatik und Informationswissenschaft: Publikationen
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

IDE, Ichiro, Hrsg., Ioannis KOMPATSIARIS, Hrsg., Changsheng XU, Hrsg. und andere. MultiMedia Modeling : 31st International Conference on Multimedia Modeling, MMM 2025, Proceedings, Part V. Singapore: Springer Nature, 2025, S. 326-333. Lecture Notes in Computer Science (LNCS). 15524. Verfügbar unter: doi: 10.1007/978-981-96-2074-6_39

Zusammenfassung

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

31st International Conference on Multimedia Modeling, MMM 2025, 8. Jan. 2025 - 10. Jan. 2025, Nara, Japan
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690STROH, Michael, Vojtěch KLODA, Benjamin VERNER, Zuzana VOPÁLKOVÁ, Raphael BUCHMÜLLER, Bastian JÄCKL, Jakub HAJKO, Jakub LOKOČ, 2025. PraK Tool V3 : Enhancing Video Item Search Using Localized Text and Texture Queries. 31st International Conference on Multimedia Modeling, MMM 2025. Nara, Japan, 8. Jan. 2025 - 10. Jan. 2025. In: IDE, Ichiro, Hrsg., Ioannis KOMPATSIARIS, Hrsg., Changsheng XU, Hrsg. und andere. MultiMedia Modeling : 31st International Conference on Multimedia Modeling, MMM 2025, Proceedings, Part V. Singapore: Springer Nature, 2025, S. 326-333. Lecture Notes in Computer Science (LNCS). 15524. Verfügbar unter: doi: 10.1007/978-981-96-2074-6_39
BibTex
@inproceedings{Stroh2025Enhan-76423,
  title={PraK Tool V3 : Enhancing Video Item Search Using Localized Text and Texture Queries},
  year={2025},
  doi={10.1007/978-981-96-2074-6_39},
  number={15524},
  address={Singapore},
  publisher={Springer Nature},
  series={Lecture Notes in Computer Science (LNCS)},
  booktitle={MultiMedia Modeling : 31st International Conference on Multimedia Modeling, MMM 2025, Proceedings, Part V},
  pages={326--333},
  editor={Ide, Ichiro and Kompatsiaris, Ioannis and Xu, Changsheng},
  author={Stroh, Michael and Kloda, Vojtěch and Verner, Benjamin and Vopálková, Zuzana and Buchmüller, Raphael and Jäckl, Bastian and Hajko, Jakub 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/123456789/76423">
    <dc:language>eng</dc:language>
    <dc:creator>Hajko, Jakub</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2026-03-02T15:29:00Z</dc:date>
    <dcterms:abstract>We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views.</dcterms:abstract>
    <dc:creator>Stroh, Michael</dc:creator>
    <dc:contributor>Buchmüller, Raphael</dc:contributor>
    <dc:contributor>Kloda, Vojtěch</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Kloda, Vojtěch</dc:creator>
    <dc:contributor>Lokoč, Jakub</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Vopálková, Zuzana</dc:contributor>
    <dc:contributor>Hajko, Jakub</dc:contributor>
    <dc:creator>Jäckl, Bastian</dc:creator>
    <dc:creator>Verner, Benjamin</dc:creator>
    <dcterms:title>PraK Tool V3 : Enhancing Video Item Search Using Localized Text and Texture Queries</dcterms:title>
    <dc:creator>Lokoč, Jakub</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/76423"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Vopálková, Zuzana</dc:creator>
    <dc:contributor>Verner, Benjamin</dc:contributor>
    <dc:contributor>Stroh, Michael</dc:contributor>
    <dc:contributor>Jäckl, Bastian</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2026-03-02T15:29:00Z</dcterms:available>
    <dc:creator>Buchmüller, Raphael</dc:creator>
    <dcterms:issued>2025</dcterms:issued>
  </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