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).
Please note that all times are shown in the time zone of the conference. The current conference time is: 14th June 2025, 06:28:56pm WEST
Knowledge Graphs for Digitized Manuscripts in Jagiellonian Digital Library Application
Jan Ignatowicz, Krzysztof Kutt, Grzegorz J. Nalepa
Jagiellonian University, Poland
Digitizing cultural heritage preserves artifacts and improves accessability. Libraries like the Jagiellonian Digital Library offer datasets via OAI-PMH, but incomplete metadata limits searchability. We propose using computer vision, AI, and semantic web technologies to enrich metadata and construct knowledge graphs for digitized manuscripts and incunabula.
Developing AI-Enhanced Search Database with RAG: A Case Study of the Collection of Historical Archives of Sino-Russian Relations
1Department of Applied History, National Chiayi University, Taiwan; 2Institute of Modern History, Academia Sinica, Taiwan; 3Institute of History and Philology, Academia Sinica, Taiwan; 4Institute of History, National Tsing Hua University, Taiwan
This study explores how Generative AI and Retrieval Augmented Generation (RAG) enhance archival research by developing an AI-enhanced database for the Collection of Historical Archives on Sino-Russian Relations. Integrating metadata and thematic search capabilities, the methodology improves retrieval precision and accessibility, offering transformative potential for historical research across diverse domains.
Developing Structured Open Access Data for Ottoman Turkish: Methodology and Applications
Enes Yılandiloğlu
University of Helsinki, Finland
This study introduces the process of creating a corpus of Ottoman Turkish poems written between 15th and 19th century and gives a use case for the corpus on the adaptation of the aruz meter in Ottoman Turkish poetry via using the corpus.
Less is More? Experiments on Active Learning in Vision Models
Stefanie Schneider
LMU Munich, Germany
This paper examines Active Learning (AL) in vision models by asking: which data to train on, and how much? Using a case study on person detection in art-historical images, it discusses the potential of AL to improve model performance while providing broadly applicable insights for disciplines within image science.
