Exploring Naming Inventories for Architectural Elements for Use in Multi-modal Machine Learning Applications*

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

  • Ronja Utescher - , Friedrich-Schiller-Universität Jena, Universität Bielefeld (Autor:in)
  • Aaron Pattee - , Ludwig-Maximilians-Universität München (LMU) (Autor:in)
  • Ferdinand Maiwald - , Friedrich-Schiller-Universität Jena (Autor:in)
  • Jonas Bruschke - , Julius-Maximilians-Universität Würzburg (Autor:in)
  • Stephan Hoppe - , Ludwig-Maximilians-Universität München (LMU) (Autor:in)
  • Sander Münster - , Friedrich-Schiller-Universität Jena (Autor:in)
  • Florian Niebling - , Julius-Maximilians-Universität Würzburg (Autor:in)
  • Sina Zarrieß - , Universität Bielefeld (Autor:in)

Abstract

Computer vision models are increasingly relevant and useful to Digital History. Next to the increasingly complex neural models, data and data selection are an integral part of this process. In this paper, we examine and extend the data collection practices from a major recent paper in the domain of architectural element classification. We collected an image-text data set for a selection of 56 Baroque landmarks to be analysed in like manner. This different architectural domain yielded insights into the transferability of the original model and data collection procedures. Notably, the architectural domain also has an impact on the availability of classes of architectural elements as well as the performance of the models classifying them.

Details

OriginalspracheEnglisch
TitelComputational Methods in the Humanities 2022 (COMHUM 2022)
Seiten95-105
Seitenumfang11
PublikationsstatusVeröffentlicht - 2023
Peer-Review-StatusJa
Extern publiziertJa

Publikationsreihe

ReiheCEUR Workshop Proceedings
Band3602
ISSN1613-0073

Konferenz

Titel2nd Workshop on Computational Methods in the Humanities, COMHUM 2022
Dauer9 - 10 Juni 2022
StadtLausanne
LandSchweiz

Externe IDs

ORCID /0000-0002-2456-9731/work/155292070

Schlagworte

ASJC Scopus Sachgebiete

Schlagwörter

  • Architecture, Art History, Computer Vision, Machine Learning

Bibliotheksschlagworte