{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T15:57:34Z","timestamp":1792079854640,"version":"4.4.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71910107002"],"award-info":[{"award-number":["71910107002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72231010"],"award-info":[{"award-number":["72231010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71932008"],"award-info":[{"award-number":["71932008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Social Science Foundation of China, 23BTJ040"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-024-03946-1","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T13:02:14Z","timestamp":1729083734000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Building a Chinese ancient architecture multimodal dataset combining image, annotation and style-model"],"prefix":"10.1038","volume":"11","author":[{"given":"Biao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyuan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Kou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4787-8406","authenticated-orcid":false,"given":"Kun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"3946_CR1","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10684\u201310695 (2022).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3946_CR2","unstructured":"Podell, D. et al. Sdxl: Improving latent diffusion models for high-resolution image synthesis. In The Twelfth International Conference on Learning Representations (2024)."},{"key":"3946_CR3","unstructured":"Betker, J. et al. Improving image generation with better captions. Computer Science https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (2023)."},{"key":"3946_CR4","unstructured":"OpenAI. Dall\u00a0\u22c5\u00a0e 3 system card. https:\/\/openai.com\/index\/dall-e-3-system-card\/ (2023)."},{"key":"3946_CR5","unstructured":"Midjourney v5.2. https:\/\/www.midjourney.com\/ Accessed: 2023-10-10 (2023)."},{"key":"3946_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Y., Abdul Aziz, A. & Mohd Arshard, W. N. R. Stable diffusion in architectural design: Closing doors or opening new horizons? International Journal of Architectural Computing 14780771241270257 (2024).","DOI":"10.1177\/14780771241270257"},{"key":"3946_CR7","doi-asserted-by":"crossref","unstructured":"Baudoux, G. The benefits and challenges of artificial intelligence image generators for architectural ideation: Study of an alternative human-machine co-creation exchange based on sketch recognition. International Journal of Architectural Computing 14780771241253438 (2024).","DOI":"10.1177\/14780771241253438"},{"key":"3946_CR8","unstructured":"Lin, K., Yang, Z., Li, L., Wang, J. & Wang, L. Designbench: Exploring and benchmarking dall-e 3 for imagining visual design. arXiv preprint arXiv:2310.15144 (2023)."},{"key":"3946_CR9","unstructured":"Barz, B. & Denzler, J. Wikichurches: A fine-grained dataset of architectural styles with real-world challenges. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)."},{"key":"3946_CR10","unstructured":"Pu, H. & Wang, X. The impact of environment on cultural relics. Scientific Culture 9 (2023)."},{"key":"3946_CR11","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.foar.2017.05.002","volume":"6","author":"M Banaei","year":"2017","unstructured":"Banaei, M., Ahmadi, A. & Yazdanfar, A. Application of ai methods in the clustering of architecture interior forms. Frontiers of Architectural Research 6, 360\u2013373 (2017).","journal-title":"Frontiers of Architectural Research"},{"key":"3946_CR12","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1126\/science.adl5907","volume":"382","author":"B Li","year":"2023","unstructured":"Li, B., Kou, G., Li, H., Guo, K. & Shi, Y. Document meaning behind china\u2019s cultural relics. Science 382, 1130\u20131130 (2023).","journal-title":"Science"},{"key":"3946_CR13","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1016\/j.foar.2023.08.007","volume":"12","author":"WA Albarqawi","year":"2023","unstructured":"Albarqawi, W. A. & Alburgawi, S. A. Mapping the approaches for investigating makkah\u2019s architectural vocabularies and ai: A literature review. Frontiers of Architectural Research 12, 1171\u20131179 (2023).","journal-title":"Frontiers of Architectural Research"},{"key":"3946_CR14","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1080\/15583058.2021.1894503","volume":"16","author":"C Wu","year":"2022","unstructured":"Wu, C., Xue, J., Song, D. & Zhang, Y. Seismic performance evaluation of a roof structure of a historic chinese timber frame building. International Journal of Architectural Heritage 16, 1474\u20131495 (2022).","journal-title":"International Journal of Architectural Heritage"},{"key":"3946_CR15","unstructured":"Hu, E. J. et al. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations (2022)."},{"key":"3946_CR16","unstructured":"Dai, X. et al. Emu: Enhancing image generation models using photogenic needles in a haystack. arXiv preprint arXiv:2309.15807 (2023)."},{"key":"3946_CR17","unstructured":"Shen, J. et al. Cross-modal fine-tuning: Align then refine. In International Conference on Machine Learning, 31030\u201331056 (PMLR, 2023)."},{"key":"3946_CR18","first-page":"11763","volume":"35","author":"T Dinh","year":"2022","unstructured":"Dinh, T. et al. Lift: Language-interfaced fine-tuning for non-language machine learning tasks. Advances in Neural Information Processing Systems 35, 11763\u201311784 (2022).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"3946_CR19","doi-asserted-by":"crossref","unstructured":"Lu, H. et al. Specialist diffusion: Plug-and-play sample-efficient fine-tuning of text-to-image diffusion models to learn any unseen style. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14267\u201314276 (2023).","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"3946_CR20","first-page":"38176","volume":"35","author":"M Bakker","year":"2022","unstructured":"Bakker, M. et al. Fine-tuning language models to find agreement among humans with diverse preferences. Advances in Neural Information Processing Systems 35, 38176\u201338189 (2022).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"3946_CR21","doi-asserted-by":"crossref","unstructured":"Hu, Z. et al. LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. In The 2023 Conference on Empirical Methods in Natural Language Processing (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"3946_CR22","unstructured":"Reid, M., Yamada, Y. & Gu, S. S. Can wikipedia help offline reinforcement learning? arXiv preprint arXiv:2201.12122 (2022)."},{"key":"3946_CR23","unstructured":"Radford, A., Narasimhan, K., Salimans, T. & Sutskever, I. Improving language understanding with unsupervised learning. Technical report, OpenAI (2018)."},{"key":"3946_CR24","first-page":"1","volume":"006","author":"H Li","year":"2021","unstructured":"Li, H. Distribution and regional characteristics of wooden-frame buildings before yuan dynasty in shanxi province. Study on Natural and Cultural Heritage 006, 1\u201328 (2021).","journal-title":"Study on Natural and Cultural Heritage"},{"key":"3946_CR25","unstructured":"Wang, T. et al. Caption anything: Interactive image description with diverse multimodal controls. arXiv preprint arXiv:2305.02677 (2023)."},{"key":"3946_CR26","unstructured":"Li, J., Li, D., Xiong, C. & Hoi, S. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning, 12888\u201312900 (PMLR, 2022)."},{"key":"3946_CR27","unstructured":"Shanxi culture relics bureau. https:\/\/wwj.shanxi.gov.cn\/ (2024)."},{"key":"3946_CR28","doi-asserted-by":"publisher","unstructured":"Li, B., Feng, J., Yan, Y., Shi, Y. & Kou, G. Chinese ancient building multimodal dataset https:\/\/doi.org\/10.7910\/DVN\/NR7A5P (2024).","DOI":"10.7910\/DVN\/NR7A5P"},{"key":"3946_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A. & Agrawala, M. Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3836\u20133847 (2023).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3946_CR30","doi-asserted-by":"crossref","unstructured":"Liang, J. et al. Swinir: Image restoration using swin transformer. In Proceedings of the IEEE\/CVF international conference on computer vision, 1833\u20131844 (2021).","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"3946_CR31","unstructured":"bmaltais. khoya-ss. https:\/\/github.com\/bmaltais\/kohya_ss, Last accessed on 2023-9-29 (2023)."},{"key":"3946_CR32","doi-asserted-by":"crossref","unstructured":"Kirillov, A. et al. Segment anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 4015\u20134026 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-024-03946-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-024-03946-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-024-03946-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T13:04:11Z","timestamp":1729083851000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-024-03946-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["3946"],"URL":"https:\/\/doi.org\/10.1038\/s41597-024-03946-1","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"assertion":[{"value":"18 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1137"}}