Type of Publication: | Contribution to a conference collection |
Publication status: | Published |
URI (citable link): | http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1qm6emstq26fw8 |
Author: | Men, Hui; Hosu, Vlad; Lin, Hanhe; Bruhn, Andres; Saupe, Dietmar |
Year of publication: | 2020 |
Conference: | 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX), May 26, 2020 - May 28, 2020, Athlone, Ireland |
Published in: | 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX). - Piscataway, NJ : IEEE, 2020. - eISSN 2472-7814. - ISBN 978-1-72815-965-2 |
DOI (citable link): | https://dx.doi.org/10.1109/QoMEX48832.2020.9123096 |
Summary: |
Professional video editing tools can generate slow-motion video by interpolating frames from video recorded at a standard frame rate. Thereby the perceptual quality of such interpolated slow-motion videos strongly depends on the underlying interpolation techniques. We built a novel benchmark database that is specifically tailored for interpolated slow-motion videos (KoSMo-1k). It consists of 1,350 interpolated video sequences, from 30 different content sources, along with their subjective quality ratings from up to ten subjective comparisons per video pair. Moreover, we evaluated the performance of twelve existing full-reference (FR) image/video quality assessment (I/VQA) methods on the benchmark. In this way, we are able to show that specifically tailored quality assessment methods for interpolated slow-motion videos are needed, since the evaluated methods - despite their good performance on real-time video databases - do not give satisfying results when it comes to frame interpolation.
|
Subject (DDC): | 004 Computer Science |
Keywords: | visual quality assessment, slow motion, optical flow, frame interpolation |
Link to License: | In Copyright |
Bibliography of Konstanz: | Yes |
MEN, Hui, Vlad HOSU, Hanhe LIN, Andres BRUHN, Dietmar SAUPE, 2020. Visual Quality Assessment for Interpolated Slow-motion Videos based on a Novel Database. 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX). Athlone, Ireland, May 26, 2020 - May 28, 2020. In: 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX). Piscataway, NJ:IEEE. eISSN 2472-7814. ISBN 978-1-72815-965-2. Available under: doi: 10.1109/QoMEX48832.2020.9123096
@inproceedings{Men2020Visua-53102, title={Visual Quality Assessment for Interpolated Slow-motion Videos based on a Novel Database}, year={2020}, doi={10.1109/QoMEX48832.2020.9123096}, isbn={978-1-72815-965-2}, address={Piscataway, NJ}, publisher={IEEE}, booktitle={2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)}, author={Men, Hui and Hosu, Vlad and Lin, Hanhe and Bruhn, Andres and Saupe, Dietmar} }
<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/rdf/resource/123456789/53102"> <dc:contributor>Lin, Hanhe</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-08T12:12:08Z</dcterms:available> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dcterms:abstract xml:lang="eng">Professional video editing tools can generate slow-motion video by interpolating frames from video recorded at a standard frame rate. Thereby the perceptual quality of such interpolated slow-motion videos strongly depends on the underlying interpolation techniques. We built a novel benchmark database that is specifically tailored for interpolated slow-motion videos (KoSMo-1k). It consists of 1,350 interpolated video sequences, from 30 different content sources, along with their subjective quality ratings from up to ten subjective comparisons per video pair. Moreover, we evaluated the performance of twelve existing full-reference (FR) image/video quality assessment (I/VQA) methods on the benchmark. In this way, we are able to show that specifically tailored quality assessment methods for interpolated slow-motion videos are needed, since the evaluated methods - despite their good performance on real-time video databases - do not give satisfying results when it comes to frame interpolation.</dcterms:abstract> <dc:contributor>Hosu, Vlad</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:title>Visual Quality Assessment for Interpolated Slow-motion Videos based on a Novel Database</dcterms:title> <dcterms:issued>2020</dcterms:issued> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-08T12:12:08Z</dc:date> <dc:creator>Lin, Hanhe</dc:creator> <dc:creator>Hosu, Vlad</dc:creator> <dc:creator>Saupe, Dietmar</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53102/1/Men_2-1qm6emstq26fw8.pdf"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53102/1/Men_2-1qm6emstq26fw8.pdf"/> <dc:creator>Men, Hui</dc:creator> <dc:language>eng</dc:language> <dc:contributor>Saupe, Dietmar</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53102"/> <dc:rights>terms-of-use</dc:rights> <dc:creator>Bruhn, Andres</dc:creator> <dc:contributor>Bruhn, Andres</dc:contributor> <dc:contributor>Men, Hui</dc:contributor> </rdf:Description> </rdf:RDF>
Men_2-1qm6emstq26fw8.pdf | 294 |