Relaxed forced choice improves performance of visual quality assessment methods
Relaxed forced choice improves performance of visual quality assessment methods
Datum
2023
Herausgeber:innen
ISSN der Zeitschrift
eISSN
item.preview.dc.identifier.isbn
Bibliografische Daten
Verlag
Schriftenreihe
Internationale Patentnummer
Link zur Lizenz
EU-Projektnummer
Projekt
JND - basierte perzeptuelle Videoqualitätsanalyse und -modellierung
SFB TRR 161 TP A 05 Bild- und Video-Qualitätsbewertung: Benchmarks, hybride Methoden und perzeptuelle, dynamische Metriken
SFB TRR 161 TP C 01 Quantitative Messung von Interaktion
SFB TRR 161 TP A 05 Bild- und Video-Qualitätsbewertung: Benchmarks, hybride Methoden und perzeptuelle, dynamische Metriken
SFB TRR 161 TP C 01 Quantitative Messung von Interaktion
Open Access-Veröffentlichung
Sammlungen
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Accepted
Erschienen in
Zusammenfassung
In image quality assessment, a collective visual quality score for an image or video is obtained from the individual ratings of many subjects. One commonly used format for these experiments is the two-alternative forced choice method. Two stimuli with the same content but differing visual quality are presented sequentially or side-by-side. Subjects are asked to select the one of better quality, and when uncertain, they are required to guess. The relaxed alternative forced choice format aims to reduce the cognitive load and the noise in the responses due to the guessing by providing a third response option, namely, ``not sure''. This work presents a large and comprehensive crowdsourcing experiment to compare these two response formats: the one with the ``not sure'' option and the one without it. To provide unambiguous ground truth for quality evaluation, subjects were shown pairs of images with differing numbers of dots and asked each time to choose the one with more dots. Our crowdsourcing study involved 254 participants and was conducted using a within-subject design. Each participant was asked to respond to 40 pair comparisons with and without the ``not sure'' response option and completed a questionnaire to evaluate their cognitive load for each testing condition. The experimental results show that the inclusion of the ``not sure'' response option in the forced choice method reduced mental load and led to models with better data fit and correspondence to ground truth. We also tested for the equivalence of the models and found that they were different. The dataset is available at http://database.mmsp-kn.de/cogvqa-database.html.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
570 Biowissenschaften, Biologie
Schlagwörter
Konferenz
2023 15th International Conference on Quality of Multimedia Experience (QoMEX), 20. Juni 2023 - 22. Juni 2023, Ghent, Belgium
Rezension
undefined / . - undefined, undefined. - (undefined; undefined)
Zitieren
ISO 690
JENADELEH, Mohsen, Johannes ZAGERMANN, Harald REITERER, Ulf-Dietrich REIPS, Raouf HAMZAOUI, Dietmar SAUPE, 2023. Relaxed forced choice improves performance of visual quality assessment methods. 2023 15th International Conference on Quality of Multimedia Experience (QoMEX). Ghent, Belgium, 20. Juni 2023 - 22. Juni 2023BibTex
@inproceedings{Jenadeleh2023-06Relax-66792, year={2023}, title={Relaxed forced choice improves performance of visual quality assessment methods}, author={Jenadeleh, Mohsen and Zagermann, Johannes and Reiterer, Harald and Reips, Ulf-Dietrich and Hamzaoui, Raouf and Saupe, Dietmar}, note={Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) -- Project ID 496858717 and DFG Project ID 251654672 -- TRR 161 (Projects A05 and C01). This research was also kindly supported by the Zukunftskolleg, the University of Konstanz, with funding from the Excellence Strategy of the German Federal and State Governments.} }
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/123456789/66792"> <dc:contributor>Hamzaoui, Raouf</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52"/> <dc:contributor>Reiterer, Harald</dc:contributor> <dc:contributor>Reips, Ulf-Dietrich</dc:contributor> <dcterms:abstract>In image quality assessment, a collective visual quality score for an image or video is obtained from the individual ratings of many subjects. One commonly used format for these experiments is the two-alternative forced choice method. Two stimuli with the same content but differing visual quality are presented sequentially or side-by-side. Subjects are asked to select the one of better quality, and when uncertain, they are required to guess. The relaxed alternative forced choice format aims to reduce the cognitive load and the noise in the responses due to the guessing by providing a third response option, namely, ``not sure''. This work presents a large and comprehensive crowdsourcing experiment to compare these two response formats: the one with the ``not sure'' option and the one without it. To provide unambiguous ground truth for quality evaluation, subjects were shown pairs of images with differing numbers of dots and asked each time to choose the one with more dots. Our crowdsourcing study involved 254 participants and was conducted using a within-subject design. Each participant was asked to respond to 40 pair comparisons with and without the ``not sure'' response option and completed a questionnaire to evaluate their cognitive load for each testing condition. The experimental results show that the inclusion of the ``not sure'' response option in the forced choice method reduced mental load and led to models with better data fit and correspondence to ground truth. We also tested for the equivalence of the models and found that they were different. The dataset is available at http://database.mmsp-kn.de/cogvqa-database.html.</dcterms:abstract> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66792/1/Jenadeleh_2-13oqtgwzu92fb8.pdf"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/66792"/> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Zagermann, Johannes</dc:contributor> <dcterms:title>Relaxed forced choice improves performance of visual quality assessment methods</dcterms:title> <dc:creator>Reips, Ulf-Dietrich</dc:creator> <dc:rights>terms-of-use</dc:rights> <dc:creator>Zagermann, Johannes</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <dc:contributor>Saupe, Dietmar</dc:contributor> <dc:language>eng</dc:language> <dc:creator>Hamzaoui, Raouf</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <dc:creator>Reiterer, Harald</dc:creator> <dc:contributor>Jenadeleh, Mohsen</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-05-04T09:50:02Z</dcterms:available> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-05-04T09:50:02Z</dc:date> <dc:creator>Jenadeleh, Mohsen</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66792/1/Jenadeleh_2-13oqtgwzu92fb8.pdf"/> <dc:creator>Saupe, Dietmar</dc:creator> <dcterms:issued>2023-06</dcterms:issued> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52"/> </rdf:Description> </rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) -- Project ID 496858717 and DFG Project ID 251654672 -- TRR 161 (Projects A05 and C01). This research was also kindly supported by the Zukunftskolleg, the University of Konstanz, with funding from the Excellence Strategy of the German Federal and State Governments.