mlsanityData to 7 Oct 2026

StyleBabel: Artistic Style Tagging and Captioning

arXiv 2203.05321 ↗First posted 10 Mar 2022cs.CV cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

34 of 57 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  12. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
22 more
  1. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  2. 2019Unified Vision-Language Pre-Training for Image Captioning and VQAcited by 494
  3. 2015A Neural Algorithm of Artistic Stylecited by 480
  4. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  5. 2017Universal Style Transfer via Feature Transformscited by 352
  6. 2019Meshed-Memory Transformer for Image Captioningcited by 343
  7. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  8. 2019Attention on Attention for Image Captioningcited by 289
  9. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  10. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
  11. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
  12. 2021ArtEmis: Affective Language for Visual Artcited by 103
  13. 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
  14. 2018How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrievalcited by 73
  15. 2013Recognizing Image Stylecited by 64
  16. 2016Artistic style transfer for videoscited by 54
  17. 2016Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrievalcited by 44
  18. 2017BAM! The Behance Artistic Media Dataset for Recognition Beyond Photographycited by 43
  19. 2021ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similaritycited by 34
  20. 2016Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfercited by 30
  21. 2021Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generationcited by 30
  22. 2019Aesthetic Image Captioning From Weakly-Labelled Photographscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 3; 2025: 1; 2026: 2.

12 papers.

  1. 2023UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Trainingcited by 14
  2. 2022HyperNST: Hyper-Networks for Neural Style Transfercited by 7
  3. 2024A LoRA is Worth a Thousand Picturescited by 7
  4. 2023PARASOL: Parametric Style Control for Diffusion Image Synthesiscited by 5
  5. 2023DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfercited by 5
  6. 2023NeAT: Neural Artistic Tracing for Beautiful Style Transfercited by 4
  7. 2024Training A Small Emotional Vision Language Model for Visual Art Comprehensioncited by 4
  8. 2023ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfercited by 3
  9. 2025Online In-Context Distillation for Low-Resource Vision Language Modelscited by 2
  10. 2024Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysiscited by 0
  11. 2026M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discoverycited by 0
  12. 2026MegaStyle++: Scaling Image Style Space through Hierarchical Style Definitioncited by 0