Uncovering Biases Through Faceted Image Retrieval: Wikidata as a Data Provider for Art-Historical Research

Vision-Language Models (VLMs) are increasingly employed in art-historical research and teaching infrastructures to enhance the discovery of images in large visual collections. Unlike traditional metadata-based systems—where retrieval depends on human-curated textual descriptors—VLM-based approaches...

Descripción completa

Detalles Bibliográficos

Autores principales:	Stefanie Schneider, Matthias Springstein, Julian Stalter, Daniel Ritter, Ralph Ewerth, Eric Müller-Budack
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	Ubiquity Press 2026-01-01
Colección:	Journal of Open Humanities Data
Materias:	vision–language models multimodal retrieval faceted search art history visual culture
Acceso en línea:	https://account.openhumanitiesdata.metajnl.com/index.php/up-j-johd/article/view/436
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!