A visual and relational scientific dataset of contemporary artists for
unsupervised learning and pattern recognition

Painting culture in Germany

The dataset consists of 14'404 paintings made by 442 art students at 15 major art universities in Germany. By focusing on localized, contemporary art we created a unique snapshot of painting culture that may be used for scientific analysis.

Beautiful graph-style visualisation of the artists connections on Instagram with art university affiliation as colours.

Social Media Network

Contains large-scale graph networks of Instagram connections between artists themselves and who else they are connected to. This relational data can be translated into artist-level features with algorithms such as node2vec (Grover and Leskovec 2016).

Beautiful graph-style visualisation of the artists connections on Instagram with art university affiliation as colours.

Detailed Data on Artists

From nationality, gender and class membership to Instagram specific meta-data; the images and graphs are enriched with various information collected on the artists.

Beautiful graph-style visualisation of the artists connections on Instagram with art university affiliation as colours.

Downloadable Content

Digitized Paintings

as compressed folder structure including further image-level data

Instagram Network Graphs

  • artist-only network, and
  • unrestricted network
in .graphml-format

Demographic Information

as csv-file

Artist Sample

The Paper

Title

Demographic Influences on Contemporary Art with Unsupervised Style Embeddings

Abstract

Computational art analysis has, through its reliance on classification tasks, prioritised historical datasets in which the artworks are already well sorted with the necessary annotations. Art produced today, on the other hand, is numerous and easily accessible, through the internet and social networks that are used by professional and amateur artists alike to display their work. Although this art, yet unsorted in terms of style and genre, is less suited for supervised analysis, the data sources come with novel information that may help frame the visual content in equally novel ways. As a first step in this direction, we present contempArt, a multi-modal dataset of exclusively contemporary artworks. contempArt is a collection of paintings and drawings, a detailed graph network based on social connections on Instagram and additional socio-demographic information — all attached to 442 artists at the beginning of their career. We evaluate three methods suited for generating unsupervised style embeddings of images and correlate them with the remaining data. We find no connections between visual style on the one hand and social proximity, gender, and nationality on the other.

Citation

@InProceedings{Huckle2020Demographic,
   author    = {Nikolai Huckle and Noa Garcia and Yuta Nakashima},
   title     = {Demographic Influences on Contemporary Art with Unsupervised Style Embeddings},
   booktitle = {Proceedings of the European Conference in Computer Vision Workshops},
   year      = {2020},
}