Logo des Repositoriums
 
Textdokument

The Dissimilar in the Similar. An Attribute-guided Approach to the Subject-specific Classification of Art-historical Objects

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik, Bonn

Zusammenfassung

Due to the increasingly unmanageable number of art-historical inventories made available in digital form, methods that computationally arrange larger amounts of objects are becoming more important. The category of similarity, which is fundamental in all areas of art-historical description, gains new relevance in this context. In this paper, we propose a novel approach to the subject-specific classification of art-historical objects that utilizes expert-based attributes, i.e., significant figurative motifs. We evaluate our procedure on a concrete use case, representations of saints in the visual arts. A representative data set of saints images is collected and a semi-supervised learning technique applied to enrich the data set with neural style transfer as well as to improve the joint training of saints and their attributes. We show that this technique outperforms other approaches.

Beschreibung

Schneider, Stefanie; Springstein, Matthias; Rahnama, Javad; Hüllermeier, Eyke; Ewerth, Ralph; Kohle, Hubertus (2021): The Dissimilar in the Similar. An Attribute-guided Approach to the Subject-specific Classification of Art-historical Objects. INFORMATIK 2020. DOI: 10.18420/inf2020_127. Gesellschaft für Informatik, Bonn. PISSN: 1617-5468. ISBN: 978-3-88579-701-2. pp. 1355-1364. Methoden und Anwendungen der Computational Humanities. Karlsruhe. 28. September - 2. Oktober 2020

Zitierform

Tags