Data and embeddings for "The Visual World of Martí Massafont: Using Multimodal AI to Analyse Commercial Street Photography in Girona, 1947–1997

This dataset contains the data files accompanying the article The Visual World of Martí Massafont: Using Multimodal AI to Analyse Commercial Street Photography in Girona, 1947–1997 (Smits, forthcoming). It includes OpenCLIP image embeddings, UMAP dimensionality reductions, HDBSCAN cluster labels, and metadata for all 9,021 digitised photographs in the Fons Martí Massafont Costals collection, held by the Centre for Image Research and Dissemination (CRDI) of Girona City Council and made publicly available through Europeana. The embeddings were extracted using the OpenCLIP ViT-L/14 model pretrained on LAION-2B. The code used to produce these files is available at https://github.com/tpsmi/streetphotography-visual-grammar.