The DOI matches its Crossref record; 89 of the 89 references it cites were found in a registry or an index.
Compression ensembles quantify aesthetic complexity and the evolution of visual art
Open accessAbstract
To the human eye, different images appear more or less complex, but capturing this intuition in a single aesthetic measure is considered hard. Here, we propose a computationally simple, transparent method for modeling aesthetic complexity as a multidimensional algorithmic phenomenon, which enables the systematic analysis of large image datasets. The approach captures visual family resemblance via a multitude of image transformations and subsequent compressions, yielding explainable embeddings. It aligns well with human judgments of visual complexity, and performs well in authorship and style recognition tasks. Showcasing the functionality, we apply the method to 125,000 artworks, recovering trends and revealing new insights regarding historical art, artistic careers over centuries, and emerging aesthetics in a contemporary NFT art market. Our approach, here applied to images but applicable more broadly, provides a new perspective to quantitative aesthetics, connoisseurship, multidimensional meaning spaces, and the study of cultural complexity.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Ensuring that AI models, such as LLMs, reflect the beliefs and values of a given community requires mechanisms for societal decision-making about what knowledge goes into the models 181 .”
From Machine culture (2023) · cites this paper as [181]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
The Cultural Origins of Human Cognition
Tomasello, M. (2009) · doi:10.2307/j.ctvjsf4jc · Cited by 6,368
Family resemblances: Studies in the internal structure of categories
Rosch, E., & Mervis, C. B. (1975) · Cognitive Psychology · doi:10.1016/0010-0285(75)90024-9 · Cited by 5,933
Popular Ensemble Methods: An Empirical Study
Opitz, D., & Maclin, R. (1999) · Journal of Artificial Intelligence Research · doi:10.1613/jair.614 · Cited by 2,953
Language Is a Complex Adaptive System: Position Paper
The “Five Graces Group”, Beckner, C., Blythe, R. A., Bybee, J., Christiansen, M. H., Croft, W., Ellis, N. C., Holland, J. H., Ke, J., Larsen‐Freeman, D., et al. (2009) · Language Learning · doi:10.1111/j.1467-9922.2009.00533.x · Cited by 1,235
Cilibrasi, R., & Vitanyi, P. M. B. (2005) · IEEE Transactions on Information Theory · doi:10.1109/tit.2005.844059 · Cited by 1,198
Gärdenfors, P. (2000) · The MIT Press eBooks · doi:10.7551/mitpress/2076.001.0001 · Cited by 1,139
Li, M., Chen, D., Li, X., Ma, B., & Vitanyi, P. M. B. (2004) · IEEE Transactions on Information Theory · doi:10.1109/tit.2004.838101 · Cited by 1,069
Algorithmic Information Theory
Chaitin, G. J. (1977) · IBM Journal of Research and Development · doi:10.1147/rd.214.0350 · Cited by 982
Research works printed but not linked: 9
- Bense M (1969) Einführung in Die Informationstheoretische Ästhetik Grundlegung Und Anwendung in Der Texttheorie. Rowolt Verlag, Reinbeks
- Galanter P (2003) What is generative art? Complexity theory as a context for art theory. In: GA2003–6th generative art conference. Citeseer
- Elgammal A, Liu B, Kim D, Elhoseiny M, Mazzone M (2018) The shape of art history in the eyes of the machine. In: 32nd AAAI conference on artificial intelligence, AAAI 2018. AAAI Press, Menlo Park, pp 2183–2191
- Rigau J, Feixas M, Sbert M (2007) Conceptualizing Birkhoff’s aesthetic measure using Shannon entropy and Kolmogorov complexity. In: Proceedings of the third eurographics conference on computational aesthetics in graphics, visualization and imaging. Computational Aesthetics’07. Eurographics Assoc., Goslar, pp 105–112
- Han SJ, Kelly P, Winters J, Kemp C (2021) Chinese characters have increased in visual complexity over three millennia. PsyArXiv preprint
- Taylor R (2004) Pollock, Mondrian and the nature: recent scientific investigations. Chaos Complex Letters 1(3):265–277
- Vasari G, Bondanella JC, Bondanella P (1998) The lives of the artists. Oxford University Press, Oxford
- Cassirer E (1927) Das Symbolproblem Und Seine Stellung Im System der Philosophie. Z Ästhet Allg Kunstwiss 21:295–322
- Srinivasa Desikan B, Evans J (2022) Aggregate, integrate and align to embed everything: a multi-modal framework for measuring cultural dynamics. In: Cultures in AI/AI in culture. A NeurIPS 2022 workshop
Cited by
Sorted by citations
Brinkmann, L., Baumann, F., Bonnefon, J.-F., Derex, M., Müller, T. F., Nussberger, A.-M., Czaplicka, A., Acerbi, A., Griffiths, T. L., Henrich, J., et al. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01742-2 · Cited by 132
Karjus, A. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04503-w · Cited by 99
Self-citationDesikan, B. S., Shimao, H., & Miton, H. (2022) · Entropy · doi:10.3390/e24091175 · Cited by 13
Quantifying the global film festival circuit: Networks, diversity, and public value creation
Zemaityte, V., Karjus, A., Rohn, U., Schich, M., & Ibrus, I. (2024) · PLoS ONE · doi:10.1371/journal.pone.0297404 · Cited by 13
Self-citationConwell, C., Graham, D., Boccagno, C. E., & Vessel, E. A. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2306025121 · Cited by 31
Collection Space Navigator: An Interactive Visualization Interface for Multidimensional Datasets
Ohm, T., Solà, M. C., Karjus, A., & Schich, M. (2023) · International Symposium on Visual Information Communication and Interaction (VINCI) · doi:10.1145/3615522.3615546 · Cited by 16
Self-citationRodighiero, D., Derry, L., Duhaime, D., Kruguer, J., Mueller, M. C., Pietsch, C., Schnapp, J. T., Steward, J., & metaLAB (2022) · Information Design Journal · doi:10.1075/idj.22013.rod · Cited by 9
Two-by-two ordinal patterns in art paintings
Tarozo, M. M., Pessa, A. A. B., Zunino, L., Rosso, O. A., Perc, M., & Ribeiro, H. V. (2025) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf092 · Cited by 8
Toward cross‐domain object detection in artwork images using improved YoloV5 and XGBoosting
Ahmad, T., & Schich, M. (2023) · IET Image Processing · doi:10.1049/ipr2.12806 · Cited by 6
Self-citationSeiler, J. P.-H., Elpelt, J., Mashkov, V., Ghobadi, A., Kapoor, A., Turner, D., Kaschube, M., Tuescher, O., & Rumpel, S. (2025) · Communications Psychology · doi:10.1038/s44271-025-00233-6 · Cited by 7
Zhang, D., Chen, Y., Gao, X., Zeng, X., Xia, R., Jiang, Y., Feng, Y., Zhang, W., & Chen, W. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104330 · Cited by 4
fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
Ohm, T., Karjus, A., Tamm, M. V., & Schich, M. (2025) · Scientific Data · doi:10.1038/s41597-025-04529-4 · Cited by 4
Self-citationNode attribute analysis for cultural data analytics: a case study on Italian XX–XXI century music
Coscia, M. (2024) · Applied Network Science · doi:10.1007/s41109-024-00669-5 · Cited by 3
Perceived gendered self-representation on Tinder using machine learning
Asadchy, Y., Karjus, A., Mukhina, K. D., & Schich, M. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03801-z · Cited by 3
Self-citationArt in context: A multi-level analysis of art
Busch, L. P. A., Malkin, A., & Belisle, J. (2025) · Journal of Contextual Behavioral Science · doi:10.1016/j.jcbs.2025.100890 · Cited by 3
Kim, S., Lee, B., & Lee, W.-J. (2025) · Scientific Reports · doi:10.1038/s41598-025-04448-9 · Cited by 3
The Impact of Short-Video Platform Algorithms on Social Aesthetics and Public Cognition
Li, W. (2025) · Interdisciplinary Humanities and Communication Studies · doi:10.61173/fa0je598 · Cited by 1
Oiva, M., Ohm, T., Mukhina, K. D., Solà, M. C., & Schich, M. (2024) · Journal of Cultural Analytics · doi:10.22148/001c.118495 · Cited by 1
Self-citationNon-fungible tokens (NFT) market: investigation and prospects
Iljinaitė, M., & Maknickienė, N. (2024) · Business and management · doi:10.3846/bm.2024.1232
Structural stability and thermodynamics of artistic composition
Chan, S. T., & Fried, E. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2406735121
Carvalho, V. M. F. A., & Freitas, D. (2024) · International Conference on Education Technology and Computer · doi:10.1145/3702163.3702438
Utilization of Complexity to Quantify the Regularity and Stochasticity of Nanocrystal Structure
Guo, Q., Song, B., Xie, F., Xie, M., & Jiao, X. (2025) · Acta Physica Polonica A · doi:10.12693/aphyspola.147.422
Understanding rhythmic structures, novelty, and influence in classical music from data
Kim, H., & Park, J. M. (2025) · EPJ Data Science · doi:10.1140/epjds/s13688-025-00586-2
Multifractal luminance and aesthetic complexity in van Gogh’s paintings
Domínguez-Monterroza, A. (2025) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0307352
Zhang, Y., & Mokhtar, M. (2026) · Arts · doi:10.3390/arts15030050
Li, W., Li, S., Zhao, X., Lai, M., Cascarano, P., & Marfia, G. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · doi:10.1109/vrw70859.2026.00099
Викторовна, В. В. (2026) · ΠΡΑΞΗMΑ Journal of Visual Semiotics · doi:10.23951/2312-7899-2026-2-196-211
Style transfer of digital painting images based on GAN and invertible neural flow
Chen, X., & Zhang, W. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117646
Context-aware multimodal AI navigates hidden pathways in five centuries of art evolution
Kim, J., Lee, B., You, T., & Yun, J. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2517969123 · Cited by 2
Anglada-Tort, M., & Lee, H. (2026) · Current Opinion in Psychology · doi:10.1016/j.copsyc.2026.102429
Aesthetic taste in humans and machines
Piovesan, F., Frascaroli, J., & de Cruys, S. V. (2026) · Current Opinion in Psychology · doi:10.1016/j.copsyc.2026.102461
Metadata
- Authors
- Karjus, A., Canet Solà, M., Ohm, T., Ahnert, S. E., & Schich, M.
- Affiliations
- Tallinn University (EE)
- University of Cambridge (GB)
- Corresponding author
- Karjus, Andres
- Venue
- EPJ Data Science
- Published
- 2023-06-14
- Volume
- 12
- Issue
- 1
- ISSN
- 2193-1127 (ISSN-L)
- OpenAlex
- W4380685139
- Cited by
- 32
- References
- 85
- Citations by year
- 2026: 8 · 2025: 12 · 2024: 7 · 2023: 3
- FWCI
- 4.50
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- EPJ Data Science (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Horizon 2020 Framework Programme (810961)
- Royal Society
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Aesthetic Perception and Analysis
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Art, Technology, and Culture
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- image compression, algorithmic complexity, visual arts, art style recognition, authorship attribution, image transformation, NFT art, art history, artistic career, cultural complexity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
