StyleBabel: Artistic style tagging and captioning

Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2022
EditorsShai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella
PublisherSpringer
Pages219-236
Number of pages18
ISBN (Electronic)9783031200748
ISBN (Print)9783031200731
DOIs
Publication statusPublished - 12 Nov 2022
EventEuropean Conference on Computer Vision 2022 - Israel, Tel Aviv, Israel
Duration: 23 Oct 202227 Oct 2022
https://eccv2022.ecva.net/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2022
Abbreviated titleECCV 2022
Country/TerritoryIsrael
CityTel Aviv
Period23/10/2227/10/22
Internet address

Keywords

  • datasets and evaluation
  • image and video retrieval
  • vision and language
  • vision applications and systems

Fingerprint

Dive into the research topics of 'StyleBabel: Artistic style tagging and captioning'. Together they form a unique fingerprint.

Cite this