Multimodal Search on Iconclass using Vision-Language Pre-Trained Models
Information Retrieval
2023-06-30 v1 Artificial Intelligence
Digital Libraries
Abstract
Terminology sources, such as controlled vocabularies, thesauri and classification systems, play a key role in digitizing cultural heritage. However, Information Retrieval (IR) systems that allow to query and explore these lexical resources often lack an adequate representation of the semantics behind the user's search, which can be conveyed through multiple expression modalities (e.g., images, keywords or textual descriptions). This paper presents the implementation of a new search engine for one of the most widely used iconography classification system, Iconclass. The novelty of this system is the use of a pre-trained vision-language model, namely CLIP, to retrieve and explore Iconclass concepts using visual or textual queries.
Cite
@article{arxiv.2306.16529,
title = {Multimodal Search on Iconclass using Vision-Language Pre-Trained Models},
author = {Cristian Santini and Etienne Posthumus and Mary Ann Tan and Oleksandra Bruns and Tabea Tietz and Harald Sack},
journal= {arXiv preprint arXiv:2306.16529},
year = {2023}
}