AI is transforming how we approach images of the past and present. This workshop is dedicated to the subject of AI-supported object detection, image classification and iconographic analysis, with a focus on drawn, painted and printed content. 

Contributions draw on large- and small-scale datasets and explore the current possibilities and limitations of AI in this area. Topics include, but are not limited to:

•    How AI is currently employed in art historical research and writing to detect, classify and analyse artworks
•    Challenges surrounding pretrained models (mostly trained on modern photographic material) and the creation of new training data and models
•    Controlled vocabularies and their application in AI-based art historical research
•    The development of AI tools specifically tailored to art history
•    Ethical and legal considerations surrounding the use of AI in art historical research.

The event is jointly organised by Doris Gruber, head of the Art History Research Unit of the Institute for Habsburg and Balkan Studies (IHB), Maria Theisen, head of the Department for Paleography and Codicology of the Institute for Medieval Research (IMAFO), and the thematic platform Machine Learning (MLA2S) at the Austrian Academy of Sciences in Vienna, Austria.

Registration

 

Program PDF

Subject to Change

Thursday,  April 16

08:45 – 09:00 Arrival and Registration

09:00 – 09:30 Introduction
Doris Gruber (IHB, Austrian Academy of Sciences
Maria Theisen (IMAFO, Austrian Academy of Sciences)
Jan Odstrčilík (MLA2S, Austrian Academy of Sciences)

09:30 – 11:00 Panel: Models
Chair: Matteo Valleriani (MPIWG Berlin)

Meta-Acervos
Thiago Hersan (Parsons School of Design)
Giselle Beiguelman (University of São Paulo)
Ana Gonçalves Magalhães (University of São Paulo)

A Benchmark Dilemma: Between Representativeness and Domain-Specificity
Marta Kipke (Center for Humanities Computing, Aarhus University)
Louise Brix Pilegaard Hansen (Center for Humanities Computing, Aarhus University)

Learning from Small Data: Adapting Pretrained Diffusion Models for 17th Century Painting
Katarina Mohar (Research Centre of the Slovenian Academy of Sciences and Arts, ZRC SAZU)
Rok Vrabič (University of Ljubljana)

11:00 – 11:30 Coffee Break

11:30 – 13:00 Panel: Augmented Data
Chair: Thomas Wallnig (University of Vienna)

Beyond Vision: Metadata-Augmented AI for Iconclass Classification in Medieval Manuscripts
Drew Thomas (University of Salzburg)
Julia Hintersteiner (University of Salzburg)

Digital Iconology. Classification and Association in Visual Knowledge Systems
Charles van den Heuvel (University of Amsterdam / Huygens Institute)
Etienne Posthumus (FIZ Karlsruhe)
Hans Brandhorst (ICONCLASS)

Exploring AI Approaches on Image Data Mining in Collections of the Austrian National Library
Carla Maria Schnedlitz (Austrian National Library)
Christoph Steindl (Austrian National Library)
Johannes Knüchel (Austrian National Library)
Simon Mayer (Austrian National Library)

13:00 –14:00 Lunch Break

14:00 - 15:30 Panel: Layout
Chair: Marion Romberg (University of Bonn)

Computational Analysis of Medieval Pen Flourishing
Markus Seidl (University of Applied Sciences St. Pölten)
Florian Kibler (University of Applied Sciences St. Pölten)
Martin Haltrich (Research Center Stift Klosterneuburg)
Max Theisen (Research Center Stift Klosterneuburg)
Victor-Adriel De-Jesus-Oliveira (University of Applied Sciences St. Pölten)

AI and Automatic Visual Recognition: Some Thoughts on the New Digital Methodologies for Image Retrieval
Barbara Tramelli (Freie Universität Bozen)

Large-scale Study of Text-Image Layout in 20th-Century Periodicals – As a Reaction to the Absence of Archival Documents
Marta Pizzagalli (Università della Svizzera italiana / Cambridge University)
Rocco Felici (Università della Svizzera italiana / Scuola universitaria professionale della Svizzera italiana)

15:30 – 15:45 Coffee Break

15:45 – 16:30 Poster Session

Artificially Intelligent Art History? A Transcultural Evaluation of Algorithmic Systems Building on Aby Warburg’s Mnemosyne Atlas
Mert Özdemir (Heinrich Heine University Düsseldorf)

Faces of Nobility. AI-Assisted Image Analysis of the Wiener Salonblatt (1870–1938)
Christian Lendl (Austrian Academy of Sciences)

Toward Digital Iconologies in Architecture
Nick Mols (Royal Museums of Art and History, Brussels)

16:30 – 16:45 Coffee Break

16:45 – 17:45 Panel: Bias
Chair: Chiara Zuanni (University for Continuing Education Krems)

Disentangling Bias – Model, Corpus, or Both?
Ellen Charlesworth (University of Luxembourg)
Ludovica Schaerf (University of Zurich)

The Algorithmic Canon and the Politics of Non-Western Visibility in the Age of AI
Elham Etemadi (Arkin University of Creative Arts and Design)

17:45 – 18:00 Coffee Break

18:00 – 19:00 Keynote
Chair: Doris Gruber (IHB, Austrian Academy of Sciences)

The Stables of Augeas: Standardizing Metadata with Iconclass Will Benefit AI
Etienne Posthumus (FIZ Karlsruhe)
Hans Brandhorst (ICONCLASS)

Friday,  April 17

09:00 – 10:00 Keynote
Chair: Maria Theisen (IMAFO, Austrian Academy of Sciences)

Attributes, Objects, Poses, Scenes and Bias: Retrospective and Future Challenges of Art History and Computer Vision
Peter Bell (Philipps-University Marburg)

10:00 – 10:20 Coffee Break

10:20 – 11:20 Panel: Relations
Chair: Doris Gruber (IHB, Austrian Academy of Sciences)

From Data to Context: AI-Based Style Attribution in Art History
Teresa Kamencek (University of Vienna)
Velitchko Filipov (Technical University of Vienna)
Michaela Tuscher (Technical University of Vienna)
Silvia Miksch (Technical University of Vienna)
Raphael Rosenberg (University of Vienna)

Embedding-Based Image Analysis for Art Historical Research: Integrating AI into Digital Catalogues Raisonnés
Kiersten Thamm (HPF Innovations GmbH / Navigating.art)

11:20 – 11:40 Coffee Break

11:40 – 13:10 Panel: Collections
Chair: Maria Theisen (IMAFO, Austrian Academy of Sciences)

Object Detection for Visual Analysis of Medieval Charters: Decoration and ItsMakers in Papal Documents
Florian Atzenhofer-Baumgartner (University of Graz)
Martin Roland (Austrian Academy of Sciences)

Between Potential and Practicality: Exploring AI’s Potential in an Incomplete, Low-Resource Art Collection
Zsuzsa Sidó (Institute of Art History, ELTE / Research Center for the Humanities – Art Collection of the Hungarian Academy of Sciences)

Using AI for Icon Analysis
Ljudmila Djukic (Belgrade)