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