홈 › Papers

StyleBabel: Artistic Style Tagging and Captioning

2022-03-10 · Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse

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.

📄 PDF Abstract BibTeX arXiv:2203.05321

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeFormRepresentation Learning RetrievalTAG

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Adam 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Sketch-to-Art: Synthesizing Stylized Art Images From Sketches

2020-02-26 · Bingchen Liu, Kunpeng Song, Ahmed Elgammal

We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningful detail…

Neural Style Representations and the Large-Scale Classification of Artistic Style

2016-11-16 · Jeremiah Johnson

The artistic style of a painting is a subtle aesthetic judgment used by art historians for grouping and classifying artwork. The recently introduced `neural-style' algorithm substantially succeeds in merging the perceive…

General Classification

Opt-In Art: Learning Art Styles Only from Few Examples

2024-11-29 · Hui Ren, Joanna Materzynska, Rohit Gandikota, David Bau 외

We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, wit…

Image Generation Text-to-Image Generation

Recognizing Art Style Automatically in painting with deep learning

2017-12-21 · Proceedings of the Ninth Asian Conference on Machine Learning 2017 12 · Adrian Lecoutre, Benjamin Negrevergne, Florian Yger

The artistic style (or artistic movement) of a painting is a rich descriptor that captures both visual and historical information about the painting. Correctly identifying the artistic style of a paintings is crucial f…

Artistic style classification Deep Learning

FolkTalent: Enhancing Classification and Tagging of Indian Folk Paintings

2024-05-14 · Nancy Hada, Aditya Singh, Kavita Vemuri

Indian folk paintings have a rich mosaic of symbols, colors, textures, and stories making them an invaluable repository of cultural legacy. The paper presents a novel approach to classifying these paintings into distinct…

image-classification Image Classification Multi-Label Image Classification