We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by `Grounded Theory': a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.
Cite
@article{arxiv.2203.05321,
title = {StyleBabel: Artistic Style Tagging and Captioning},
author = {Dan Ruta and Andrew Gilbert and Pranav Aggarwal and Naveen Marri and Ajinkya Kale and Jo Briggs and Chris Speed and Hailin Jin and Baldo Faieta and Alex Filipkowski and Zhe Lin and John Collomosse},
journal= {arXiv preprint arXiv:2203.05321},
year = {2022}
}