Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
SP-F2F: Machine learning and artificial intelligence
Time:
Friday, 14/July/2023:
11:00am - 12:30pm
Session Chair: Vayianos Pertsas, Athens University Of Economics and Business
Location:MCG-F
Presentations
A Model of Heaven: Tracing Images of Holiness in a Collection of 63.000 Lantern Slides (1880-1940)
Eleonora Paklons, Thomas Smits
University of Antwerp, Belgium
This paper explores representations of holiness in a collection of 63.000 lantern slides. Using the multimodal model CLIP, it sheds light on the transition between the real and the imaginary, the holy and the profane. It demonstrates how CLIP can help scholars deal with complex visual concepts such as holiness.
Towards a distant viewing of depicted materials in medieval paintings
Isabella Nicka, Andreas Uhl, Miriam Landkammer, Michael Linortner, Johannes Schuiki
University of Salzburg, Austria
The contribution highlights the importance of developing DH methods for large-scale investigation of depicted materials and surface qualities in medieval painting. Preliminary findings from our project, which is developing methods for AI-based recognition of materials in digitized paintings and evaluating their application to address art historical research questions, are presented.
Using Multimodal Machine Learning to Distant View the Illustrated World of the Illustrated London News, 1842-1900
Thomas Smits1, Ben Lee2, Paul Fyfe3
1University of Antwerp, Belgium; 2University of Washington, USA; 3North Carolina State University, USA
This paper applies multimodal machine learning (CLIP) to distant view the Illustrated London News. After extracting a sample of 874 illustrations, we use CLIP to identify maps and images of steamships. Without task- or data-specific training, CLIP can be used to quickly explore and analyze historical visual data at scale.
Probabilistic Modeling of Chronological Dates to Serve Machines and Scholars
Andreas Habring, Anguelos Nicolaou, Daniel Luger, Florian Atzenhofer-Baumgartner, Florian Lamminger, Franziska Decker, Sandy Aoun, Tamás Kovács, Georg Vogeler, Martin Holler
University of Graz, Austria
We present a modeling of document dates such that it can allow scholars to express uncertainty when annotating data, act as a differentiable loss function for training models and allow for unbiased interpretable performance evaluation under uncertainty.
They're veGAN but they almost taste the same: generating simili-manuscripts with artificial intelligence
Jean-Baptiste Camps, Chahan Vidal-Gorène
École nationale des chartes | Université PSL, France
The aim of our research is to artificially generate fake historical manuscripts using GAN. At this stage, these experiments pursue two objectives: evaluating feasibility of generating realistic fake manuscripts under certain conditions of layout, script, or date, and creating artificial data to augment HTR training. Examples are taken from Classical Armenian and Old French.
