Computer Vision for Digital Humanities

The DiDip-project co-organised to the Winter School (8–10 February 2023) at the Zentrum für Informationsmodellierung. ZIM members Anguelos Nicolaou, Sean Winslow, Sarah Lang, Suzana Sagadin, Daniel Luger, Niklas Tscherne, and Nicolas Renet, as well as Germaine Götzelmann (Karlsruhe Institute of Technology) as an external expert, took part in planning the program and taught several lessons. The event included theoretical introductions into the topic and several hands-on activities. The school covered the history of computer vision, data acquistion, demonstrations of off-the-shelve tools, result exploration, data augmentation, and PyTorch based neural networks.

18 scholars from 5 countries (Austria, Germany, Balkan region, Ghana) participated. They brought topics ranging from analysis of archeological artefacts to classification of news videos into the school. The feedback received from the participants was overwhelmingly positive, underscoring the need for such teaching materials in DH. As an associated outcome of this week, a whole playlist of comprehensive teaching videos (more than 10 hours of video material in total) was created, covering a range of topics from the basics of computer vision and machine learning to training custom deep learning models for one’s own historical data. Additionally, a number of slide decks and Jupyter notebooks were created, filled with hands-on exercises based on the workshops. These materials, in conjunction with the videos, provide a comprehensive self-learning course in Computer Vision for Digital Humanists. They are now available on relevant platforms DARIAH Campus (slide decks and Jupyter Notebooks) and Youtube (videos). You can find results of the hackathon in https://github.com/anguelos/graz_cv_ws2023 and videos of the lessons in https://www.youtube.com/playlist?list=PLWNohMNguM_nO3SG9UrzPpbybV_UoCg5w.

We express our gratitude to CLARIAH-AT for their funding support.



Cite this blog post
Nicolas Renet (2023, November 2). Computer Vision for Digital Humanities. DiDip. Retrieved May 17, 2024, from https://didip.hypotheses.org/1574

You may also like...

Search OpenEdition Search

You will be redirected to OpenEdition Search