{"id":6883,"date":"2026-05-17T22:52:19","date_gmt":"2026-05-17T14:52:19","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=6883"},"modified":"2026-05-19T11:36:43","modified_gmt":"2026-05-19T03:36:43","slug":"jase-202609-32-043","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202609-32-043","title":{"rendered":"Quantitative Aesthetic Evaluation of Visual Artworks Using Vision Transformer with Multi-Dimensional Artistic Feature Fusion"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 32<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Zeyu Gao<\/i><\/a> <\/p>\n\n\n\n

School of Art, Bangkok Thonburi University, Bangkok, 10170 Thailand<\/p>\n<\/div>\n\n\n\n

\n

Received: April 8, 2026
Accepted: May 1, 2026
Publication Date: May 17, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Qualitative Aesthetic Score Prediction on Sample Artworks <\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:\u00a0 BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202609_32.043<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Automated quantitative aesthetic evaluation of visual artworks is a challenging cross-disciplinary task involving computer vision and art history. Traditional aesthetic assessment methods rely on handcrafted features or single-branch deep learning models, which fail to comprehensively capture the multi-faceted artistic attributes (e.g., color harmony, composition balance, texture, and semantic style) and long-range global dependencies critical to artistic appreciation. To address these limitations, this paper proposes a novel framework: Vision Transformer with Multi-Dimensional Artistic Feature Fusion (MDAF-ViT). Our model integrates a hierarchical Vision Transformer (ViT) backbone for global context modeling with multi-branch feature extractors to capture low-level visual attributes, mid-level compositional rules, and high-level semantic style features. A key innovation is the Dynamic Multi-Dimensional Attention Fusion (MDAF) module, which adaptively weights and fuses heterogeneous artistic features. Extensive experiments on standard art aesthetic datasets (BAID, APDDv2, JenAesthetics) demonstrate that MDAF-ViT significantly outperforms state-of-the-art CNN and ViT based methods, achieving superior performance in terms of Pearson Linear Correlation Coefficient (PLCC), Spearman Rank Correlation Coefficient (SRCC), and Mean Squared Error (MSE). This work provides a robust, interpretable foundation for large-scale digital art analysis and curation.<\/p>\n\n\n\n

Keywords: Computational Aesthetics; Artwork Evaluation; Vision Transformer<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] D. Jonauskaite, N. Dael, L. Baboulaz, L. Ch\u00e8vre, I. Cierny, N. Ducimeti\u00e8re, A. Fekete, P. Gabioud, H. Leder, M. Vetterli, et al., (2024) \u201cInteractive digital engagement with visual artworks and cultural artefacts enhances user aesthetic experiences in the laboratory and museum\u201d International Journal of Human\u2013Computer Interaction 40(6): 1369\u20131382. DOI: 10.1080\/10447318.2022.2143767.<\/li>\n
  2. [2] E. Stamkou, D. Keltner, R. Corona, E. Aksoy, and A. S. Cowen, (2024) \u201cEmotional palette: A computational mapping of aesthetic experiences evoked by visual art\u201d Scientific Reports 14(1): 19932. DOI: 10.1038\/s41598-024-69686-9.<\/li>\n
  3. [3] E. A. Vessel and H. Ovadia, (2025) \u201cThe role of the default mode network in aesthetic appeal\u201d Current Opinion in Behavioral Sciences 66: 101608. DOI: 10.1016\/j.cobeha.2025.101608.<\/li>\n
  4. [4] T. Shi, C. Chen, X. Li, and A. Hao, (2024) \u201cSemantic and style based multiple reference learning for artistic and general image aesthetic assessment\u201d Neurocomputing 582: 127434. DOI: 10.1016\/j.neucom.2024.127434.<\/li>\n
  5. [5] X. Zhang, Y. Xiao, J. Peng, X. Gao, and B. Hu, (2024) \u201cConfidence-based dynamic cross-modal memory network for image aesthetic assessment\u201d Pattern Recognition 149: 110227. DOI: 10.1016\/j.patcog.2023.110227.<\/li>\n
  6. [6] X. Lu, Z. Lin, H. Jin, J. Yang, and J. Z. Wang, (2015) \u201cRating image aesthetics using deep learning\u201d IEEE Transactions on Multimedia 17(11): 2021\u20132034. DOI: 10.1109\/TMM.2015.2477040.<\/li>\n
  7. [7] H. Jang and J.-S. Lee, (2021) \u201cAnalysis of deep features for image aesthetic assessment\u201d IEEE Access 9: 29850\u201329861. DOI: 10.1109\/ACCESS.2021.3060171.<\/li>\n
  8. [8] J. McCormack and A. Lomas. \u201cUnderstanding aesthetic evaluation using deep learning\u201d. In: International conference on computational intelligence in music, sound, art and design (part of EvoStar). Springer. 2020, 118\u2013133. DOI: 10.1007\/978-3-030-43859-3_9.<\/li>\n
  9. [9] X. Tian, Z. Dong, K. Yang, and T. Mei, (2015) \u201cQuery-dependent aesthetic model with deep learning for photo quality assessment\u201d IEEE Transactions on Multimedia 17(11): 2035\u20132048. DOI: 10.1109\/TMM.2015.2479916.<\/li>\n
  10. [10] Y. Deng, C. C. Loy, and X. Tang, (2017) \u201cImage aesthetic assessment: An experimental survey\u201d IEEE Signal Processing Magazine 34(4): 80\u2013106. DOI: 10.1109\/MSP.2017.2696576.<\/li>\n
  11. [11] Y. Ke, Y. Wang, K. Wang, F. Qin, J. Guo, and S. Yang, (2023) \u201cImage aesthetics assessment using composite features from transformer and CNN\u201d Multimedia Systems 29(5): 2483\u20132494. DOI: 10.1007\/s00530-023-01141-7.<\/li>\n
  12. [12] M. Carrasco, C. Gonz\u00e1lez-Mart\u00edn, J. Aranda, and L. Oliveros, (2026) \u201cVision Transformer attention alignment with human visual perception in aesthetic object evaluation\u201d Plos one 21(4): e0344006. DOI: 10.1371\/journal.pone.0344006.<\/li>\n
  13. [13] S. Li, H. Liang, M. Xie, and X. He. \u201cMulti-scale and multi-patch aggregation network based on dual-column vision fusion for image aesthetics assessment\u201d. In: 2024 IEEE International Conference on Multimedia and Expo (ICME). IEEE. 2024, 1\u20136. DOI: 10.1109\/ICME57554.2024.10687850.<\/li>\n
  14. [14] H. Takimoto, F. Omori, and A. Kanagawa, (2021) \u201cImage aesthetics assessment based on multi-stream CNN architecture and saliency features\u201d Applied Artificial Intelligence 35(1): 25\u201340. DOI: 10.1080\/08839514.2020.1839197.<\/li>\n
  15. [15] D. Soydaner and J. Wagemans, (2024) \u201cMulti-task convolutional neural network for image aesthetic assessment\u201d Ieee Access 12: 4716\u20134729. DOI: 10.1109\/ACCESS.2024.3349961.<\/li>\n
  16. [16] C.-H. Lee, J.-L. Shih, W.-L. Su, C.-C. Lien, and C.-C. Han. \u201cCombination of Global Maximum Pooling and Local Average Pooling for Unsupervised Fine-Grained Image Retrieval\u201d. In: Proceedings of the 2024 7th Artificial Intelligence and Cloud Computing Conference. 2024, 299\u2013307. DOI: 10.1145\/3719384.3719427.<\/li>\n
  17. [17] J. Yao, J. Yao, Y. Yang, and C. Huang. \u201cHierarchical Adaptive Position Encoding-Based Transformer for Point Cloud Analysis\u201d. In: International Conference on Neural Information Processing. Springer. 2024, 197\u2013210. DOI: 10.1007\/978-981-96-6576-1_14.<\/li>\n
  18. [18] R. Egele, J. Junior, J. CS, J. N. van Rijn, I. Guyon, X. Bar\u00f3, A. Clap\u00e9s, P. Balaprakash, S. Escalera, T. Moeslund, et al., (2024) \u201cAi competitions and benchmarks: Dataset development\u201d arXiv preprint arXiv:2404.09703: DOI: 10.48550\/arXiv.2404.09703.<\/li>\n
  19. [19] U. Lee, Y. Son, J. Shin, G. Byun, Y. Lee, J. Koh, M. Jeon, and H. Kim. \u201cLLaVA-Docent-V2: Improving Data Quality and Pedagogical Data Generation to Train Large Multimodal Models for Art Appreciation Education\u201d. In: International Conference on Intelligent Tutoring Systems. Springer. 2025, 213\u2013228. DOI: 10.1007\/978-3-031-98284-2_17.<\/li>\n
  20. [20] S. A. Amirshahi, G. U. Hayn-Leichsenring, J. Denzler, and C. Redies. \u201cJenaesthetics subjective dataset: analyzing paintings by subjective scores\u201d. In: European Conference on Computer Vision. Springer. 2014, 3\u201319. DOI: 10.1007\/978-3-319-16178-5_1.<\/li>\n<\/ol>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,720,6],"tags":[1452],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:\u00a0 BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202609_32.043\u00a0\u00a0 Download PDF Automated quantitative aesthetic evaluation of visual artworks is a challenging cross-disciplinary…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/6883"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6883"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6883"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6883"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}