KOPS - The Institutional Repository of the University of Konstanz

Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features

Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

HOSU, Vlad, Bastian GOLDLÜCKE, Dietmar SAUPE, 2019. Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, California, Jun 16, 2019 - Jun 20, 2019. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019) : proceedings : 16-20 June 2019, Long Beach, California. Los Alamitos, CA:IEEE Computer Society, pp. 9367-9375. ISSN 1063-6919. eISSN 2575-7075. ISBN 978-1-72813-293-8. Available under: doi: 10.1109/CVPR.2019.00960

@inproceedings{Hosu2019-06Effec-50898, title={Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features}, year={2019}, doi={10.1109/CVPR.2019.00960}, isbn={978-1-72813-293-8}, issn={1063-6919}, address={Los Alamitos, CA}, publisher={IEEE Computer Society}, booktitle={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019) : proceedings : 16-20 June 2019, Long Beach, California}, pages={9367--9375}, author={Hosu, Vlad and Goldlücke, Bastian 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/123456789/50898"> <dcterms:issued>2019-06</dcterms:issued> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/50898"/> <dcterms:title>Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features</dcterms:title> <dc:creator>Saupe, Dietmar</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-18T13:24:17Z</dcterms:available> <dc:creator>Hosu, Vlad</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-18T13:24:17Z</dc:date> <dc:contributor>Hosu, Vlad</dc:contributor> <dcterms:abstract xml:lang="eng">We propose an effective deep learning approach to aesthetics quality assessment that relies on a new type of pre-trained features, and apply it to the AVA data set, the currently largest aesthetics database. While previous approaches miss some of the information in the original images, due to taking small crops, down-scaling or warping the originals during training, we propose the first method that efficiently supports full resolution images as an input, and can be trained on variable input sizes. This allows us to significantly improve upon the state of the art, increasing the Spearman rank-order correlation coefficient (SRCC) of ground-truth mean opinion scores (MOS) from the existing best reported of 0.612 to 0.756. To achieve this performance, we extract multi-level spatially pooled (MLSP) features from all convolutional blocks of a pre-trained InceptionResNet-v2 network, and train a custom shallow Convolutional Neural Network (CNN) architecture on these new features.</dcterms:abstract> <dc:contributor>Goldlücke, Bastian</dc:contributor> <dc:creator>Goldlücke, Bastian</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Saupe, Dietmar</dc:contributor> <dc:language>eng</dc:language> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


Browse

My Account