Exploring the "Great Unseen" in Medieval Manuscripts: Instance-Level Labeling of Legacy Image Collections with Zero-Shot Models
This addresses the need for better training data in medieval manuscript analysis, but it appears incremental as it applies existing zero-shot models to a new domain without novel methodological breakthroughs.
The paper tackled the problem of holistically analyzing medieval manuscript pages by segmenting and describing entire folios to generate richer training data for computer vision tasks like instance segmentation and multimodal models, but no concrete results or numbers were provided.
We aim to theorize the medieval manuscript page and its contents more holistically, using state-of-the-art techniques to segment and describe the entire manuscript folio, for the purpose of creating richer training data for computer vision techniques, namely instance segmentation, and multimodal models for medieval-specific visual content.