{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:58:25Z","timestamp":1776887905624,"version":"3.51.2"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032113160","type":"print"},{"value":"9783032113177","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-11317-7_43","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:31Z","timestamp":1767322471000},"page":"524-544","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Have Large Vision-Language Models Mastered Art History?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5258-8534","authenticated-orcid":false,"given":"Ombretta","family":"Strafforello","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-6711","authenticated-orcid":false,"given":"Derya","family":"Soydaner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6548-2334","authenticated-orcid":false,"given":"Michiel","family":"Willems","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2710-0936","authenticated-orcid":false,"given":"Anne-Sofie","family":"Maerten","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7551-2444","authenticated-orcid":false,"given":"Stefanie","family":"De Winter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"43_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"43_CR2","unstructured":"Amirshahi, S.A., Denzler, J., Redies, C.: JenAesthetics\u2014a public dataset of paintings for aesthetic research. Technical report, University of Jena Germany (2013)"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Amirshahi, S.A., Redies, C., Denzler, J.: How self-similar are artworks at different levels of spatial resolution? In: Proceedings of the Symposium on Computational Aesthetics (2013)","DOI":"10.1145\/2487276.2487282"},{"key":"43_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-16178-5_1","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"SA Amirshahi","year":"2015","unstructured":"Amirshahi, S.A., Hayn-Leichsenring, G.U., Denzler, J., Redies, C.: JenAesthetics subjective dataset: analyzing paintings by subjective scores. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 3\u201319. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16178-5_1"},{"key":"43_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-319-16178-5_5","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"Y Bar","year":"2015","unstructured":"Bar, Y., Levy, N., Wolf, L.: Classification of artistic styles using binarized features derived from a deep neural network. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014, Part I. LNCS, vol. 8925, pp. 71\u201384. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16178-5_5"},{"issue":"3","key":"43_CR6","doi-asserted-by":"publisher","first-page":"380","DOI":"10.3390\/bioengineering10030380","volume":"10","author":"Y Bazi","year":"2023","unstructured":"Bazi, Y., et al.: Vision-language model for visual question answering in medical imagery. Bioengineering 10(3), 380 (2023)","journal-title":"Bioengineering"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Bin, Y., et\u00a0al.: GalleryGPT: analyzing paintings with large multimodal models. In: the 32nd ACM International Conference on Multimedia, pp. 7734\u20137743 (2024)","DOI":"10.1145\/3664647.3681656"},{"key":"43_CR8","unstructured":"Bordes, F., et\u00a0al.: An introduction to vision-language modeling. arXiv preprint arXiv:2405.17247 (2024)"},{"key":"43_CR9","unstructured":"Cao, S., Young, S.: Predicting winning captions for weekly new Yorker comics. arXiv preprint arXiv:2407.18949 (2024)"},{"key":"43_CR10","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.eswa.2018.07.026","volume":"114","author":"E Cetinic","year":"2018","unstructured":"Cetinic, E., Lipic, T., Grgic, S.: Fine-tuning convolutional neural networks for fine art classification. Expert Syst. Appl. 114, 107\u2013118 (2018)","journal-title":"Expert Syst. Appl."},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Conde, M.V., Turgutlu, K.: CLIP-art: contrastive pre-training for fine-grained art classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3956\u20133960 (2021)","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Dombrowski, A.: Impressionism and globalization. In: Historical Narratives of Global Modern Art, pp. 19\u201330. Routledge (2023)","DOI":"10.4324\/9781003247678-4"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Dorkenwald, M., et\u00a0al.: Pin: Positional insert unlocks object localisation abilities in VLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13548\u201313558 (2024)","DOI":"10.1109\/CVPR52733.2024.01286"},{"key":"43_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Elgammal, A., et\u00a0al.: The shape of art history in the eyes of the machine. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11894"},{"key":"43_CR16","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.jvcir.2018.09.015","volume":"56","author":"C Florea","year":"2018","unstructured":"Florea, C., Gieseke, F.: Artistic movement recognition by consensus of boosted SVM based experts. J. Vis. Commun. Image Represent. 56, 220\u2013233 (2018)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"43_CR17","unstructured":"Hook, P.: The Ultimate Trophy: How the Impressionist Painting Conquered the World. Prestel Verlag (2012)"},{"issue":"406","key":"43_CR18","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida. J. Am. Stat. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"J. Am. Stat. Assoc."},{"key":"43_CR19","unstructured":"Karayev, S., et\u00a0al.: Recognizing image style. arXiv preprint arXiv:1311.3715 (2013)"},{"key":"43_CR20","unstructured":"Khadangi, A., et\u00a0al.: CognArtive: large language models for automating art analysis and decoding aesthetic elements. arXiv preprint arXiv:2502.04353 (2025)"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Kim, D., Elgammal, A., Mazzone, M.: Formal analysis of art: proxy learning of visual concepts from style through language models. arXiv:2201.01819 (2022)","DOI":"10.1609\/aaai.v36i4.20374"},{"key":"43_CR22","unstructured":"Lecoutre, A., Negrevergne, B., Yger, F.: Recognizing art style automatically in painting with deep learning. In: Asian Conference on Machine Learning, pp. 327\u2013342. PMLR (2017)"},{"issue":"1","key":"43_CR23","doi-asserted-by":"publisher","first-page":"7319","DOI":"10.1038\/s41598-025-91671-z","volume":"15","author":"W Li","year":"2025","unstructured":"Li, W.: Enhanced automated art curation using supervised modified CNN for art style classification. Sci. Rep. 15(1), 7319 (2025)","journal-title":"Sci. Rep."},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., et\u00a0al.: VILA: on pre-training for visual language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"43_CR25","unstructured":"Liu, H., et\u00a0al.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Mendes, E., et\u00a0al.: Granular privacy control for geolocation with vision language models. arXiv preprint arXiv:2407.04952 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.957"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Menis-Mastromichalakis, O., Sofou, N., Stamou, G.: Deep ensemble art style recognition. In: International Joint Conference on Neural Networks, pp.\u00a01\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207645"},{"key":"43_CR28","unstructured":"Meta, A.: Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. Meta AI Blog. Retrieved December 20 (2024)"},{"key":"43_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"issue":"22","key":"43_CR30","doi-asserted-by":"publisher","first-page":"12462","DOI":"10.3390\/app132212462","volume":"13","author":"A Rahhal","year":"2023","unstructured":"Rahhal, A.: Vision-language models for zero-shot classification of remote sensing images. Appl. Sci. 13(22), 12462 (2023)","journal-title":"Appl. Sci."},{"key":"43_CR31","unstructured":"Saleh, B., Elgammal, A.: Large-scale classification of fine-art paintings: learning the right metric on the right feature. arXiv preprint arXiv:1505.00855 (2015)"},{"key":"43_CR32","doi-asserted-by":"publisher","first-page":"41770","DOI":"10.1109\/ACCESS.2019.2907986","volume":"7","author":"C Sandoval","year":"2019","unstructured":"Sandoval, C., Pirogova, E., Lech, M.: Two-stage deep learning approach to the classification of fine-art paintings. IEEE Access 7, 41770\u201341781 (2019)","journal-title":"IEEE Access"},{"key":"43_CR33","unstructured":"Snider, L.: A lasting impression: French painters revolutionize the art world. History Teacher, pp. 89\u2013101 (2001)"},{"key":"43_CR34","doi-asserted-by":"crossref","unstructured":"Springstein, M., et\u00a0al.: Visual narratives: large-scale hierarchical classification of art-historical images. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7220\u20137230 (2024)","DOI":"10.1109\/WACV57701.2024.00705"},{"key":"43_CR35","doi-asserted-by":"crossref","unstructured":"Tan, W.R., et\u00a0al.: Ceci n\u2019est pas une pipe: a deep convolutional network for fine-art paintings classification. In: IEEE International Conference on Image Processing, pp. 3703\u20133707 (2016)","DOI":"10.1109\/ICIP.2016.7533051"},{"key":"43_CR36","doi-asserted-by":"crossref","unstructured":"Tojima, T., Yoshida, M.: Zero-shot classification of art with large language models. IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3532995"},{"key":"43_CR37","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"43_CR38","unstructured":"Winkler, W.E.: String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage (1990)"},{"key":"43_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Y., Nakashima, Y., Garcia, N.: Not only generative art: stable diffusion for content-style disentanglement in art analysis. In: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, pp. 199\u2013208 (2023)","DOI":"10.1145\/3591106.3592262"},{"key":"43_CR40","unstructured":"Yuan, Z., et\u00a0al.: ArtGPT-4: towards artistic-understanding large vision-language models with enhanced adapter. arXiv preprint arXiv:2305.07490 (2023)"},{"issue":"1","key":"43_CR41","first-page":"1764606","volume":"2022","author":"W Zhao","year":"2022","unstructured":"Zhao, W., Jiang, W., Qiu, X.: Big transfer learning for fine art classification. Comput. Intell. Neurosci. 2022(1), 1764606 (2022)","journal-title":"Comput. Intell. Neurosci."},{"key":"43_CR42","doi-asserted-by":"crossref","unstructured":"Zhong, S.H., Huang, X., Xiao, Z.: Fine-art painting classification via two-channel dual path networks. Int. J. Mach. Learn. Cybern. 11, 137\u2013152 (2020)","DOI":"10.1007\/s13042-019-00963-0"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing - ICIAP 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11317-7_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:34Z","timestamp":1767322474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11317-7_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032113160","9783032113177"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11317-7_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}