KOPS - The Institutional Repository of the University of Konstanz

From Technical to Aesthetics Quality Assessment and Beyond : Challenges and Potential

From Technical to Aesthetics Quality Assessment and Beyond : Challenges and Potential

Cite This

Files in this item

Checksum: MD5:d10e79a2d17a3f1387b6ebec7b8d961f

HOSU, Vlad, Dietmar SAUPE, Bastian GOLDLUECKE, Weisi LIN, Wen-Huang CHENG, John SEE, Lai-Kuan WONG, 2020. From Technical to Aesthetics Quality Assessment and Beyond : Challenges and Potential. MM '20: The 28th ACM International Conference on Multimedia. Seattle, Oct 12, 2020 - Oct 16, 2020. In: HOSU, Vlad, ed. and others. ATQAM/MAST'20: Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends. New York:ACM, pp. 19-20. ISBN 978-1-4503-8154-3. Available under: doi: 10.1145/3423268.3423589

@inproceedings{Hosu2020Techn-51421, title={From Technical to Aesthetics Quality Assessment and Beyond : Challenges and Potential}, year={2020}, doi={10.1145/3423268.3423589}, isbn={978-1-4503-8154-3}, address={New York}, publisher={ACM}, booktitle={ATQAM/MAST'20: Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends}, pages={19--20}, editor={Hosu, Vlad}, author={Hosu, Vlad and Saupe, Dietmar and Goldluecke, Bastian and Lin, Weisi and Cheng, Wen-Huang and See, John and Wong, Lai-Kuan} }

<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/123456789/51421"> <dc:language>eng</dc:language> <dc:creator>Wong, Lai-Kuan</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-10-19T13:37:22Z</dcterms:available> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:creator>Lin, Weisi</dc:creator> <dc:creator>Goldluecke, Bastian</dc:creator> <dcterms:title>From Technical to Aesthetics Quality Assessment and Beyond : Challenges and Potential</dcterms:title> <dc:creator>Hosu, Vlad</dc:creator> <dc:contributor>See, John</dc:contributor> <dcterms:issued>2020</dcterms:issued> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Lin, Weisi</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/51421"/> <dc:contributor>Wong, Lai-Kuan</dc:contributor> <dc:contributor>Saupe, Dietmar</dc:contributor> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-10-19T13:37:22Z</dc:date> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:creator>Saupe, Dietmar</dc:creator> <dc:rights>terms-of-use</dc:rights> <dc:contributor>Cheng, Wen-Huang</dc:contributor> <dcterms:abstract xml:lang="eng">Every day 1.8+ billion images are being uploaded to Facebook, Instagram, Flickr, Snapchat, and WhatsApp [6]. The exponential growth of visual media has made quality assessment become increasingly important for various applications, from image acquisition, synthesis, restoration, and enhancement, to image search and retrieval, storage, and recognition. There have been two related but different classes of visual quality assessment techniques: image quality assessment (IQA) and image aesthetics assessment (IAA). As perceptual assessment tasks, subjective IQA and IAA share some common underlying factors that affect user judgments. Moreover, they are similar in methodology (especially NR-IQA in-the-wild and IAA). However, the emphasis for each is different: IQA focuses on low-level defects e.g. processing artefacts, noise, and blur, while IAA puts more emphasis on abstract and higher-level concepts that capture the subjective aesthetics experience, e.g. established photographic rules encompassing lighting, composition, and colors, and personalized factors such as personality, cultural background, age, and emotion. IQA has been studied extensively over the last decades [3, 14, 22]. There are three main types of IQA methods: full-reference (FR), reduced-reference (RR), and no-reference (NR). Among these, NRIQA is the most challenging as it does not depend on reference images or impose strict assumptions on the distortion types and level. NR-IQA techniques can be further divided into those that predict the global image score [1, 2, 10, 17, 26] and patch-based IQA [23, 25], naming a few of the more recent approaches.</dcterms:abstract> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/51421/1/Hosu_2-3gz5dg09sllp3.pdf"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:contributor>Hosu, Vlad</dc:contributor> <dc:creator>See, John</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/51421/1/Hosu_2-3gz5dg09sllp3.pdf"/> <dc:contributor>Goldluecke, Bastian</dc:contributor> <dc:creator>Cheng, Wen-Huang</dc:creator> </rdf:Description> </rdf:RDF>

Downloads since Oct 19, 2020 (Information about access statistics)

Hosu_2-3gz5dg09sllp3.pdf 15

This item appears in the following Collection(s)

Search KOPS


Browse

My Account