Conference Agenda
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).
|
Daily Overview |
| Session | |
|
Freitag 2:3: Freitag 2:3 – Multimodalität Location: Hörsaal 2 lecture hall Session Chair: Florian Windhager, Universität für Weiterbildung Krems | |
    | |
Transcribing the Untranscribable: Automating Recognition of Text and Image in Multimodal Medieval Manuscripts from Law to Divination Universität zu Köln, Deutschland The transcription of medieval manuscripts with non-linear, non-sequential layouts in multimodal sources is a challenge where traditional Handwritten Text Recognition fails. This paper presents a methodology using Multimodal Large Language Models (MLLMs) for a holistic analysis of both text and image. Through case studies on an illustrated legal text (Sachsenspiegel) and a manuscript belonging to the "sortes" genre, we demonstrate MLLM-centric workflows for knowledge extraction and transcription. Our methods use MLLMs to describe and link illustrations to text, and to segment, rotate, complex layouts to transcribe illegible text to standard systems. | |