{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:20:15Z","timestamp":1792790415090,"version":"4.5.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"2019 Zhejiang Provincial Philosophy and Social Science Planning Project","award":["19NDJC116YB"],"award-info":[{"award-number":["19NDJC116YB"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-20087-6","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:41:58Z","timestamp":1760607718000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Enhancing artistic style classification through a novel ArtFusionNet framework"],"prefix":"10.1038","volume":"15","author":[{"given":"Shuangsheng","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fallah","family":"Mohammadzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Khishe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teeba","family":"Ismail Kh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qusai Y.","family":"Shambour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taher M.","family":"Ghazal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"issue":"11","key":"20087_CR1","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1109\/TMM.2015.2477040","volume":"17","author":"X Lu","year":"2015","unstructured":"Lu, X., Lin, Z., Jin, H., Yang, J. & Wang, J. Z. Rating image aesthetics using deep learning. IEEE Trans. Multimed. 17(11), 2021\u20132034 (2015).","journal-title":"IEEE Trans. Multimed"},{"key":"20087_CR2","doi-asserted-by":"crossref","unstructured":"Dinesh Kumar, R. et al. Deep convolutional nets learning classification for artistic style transfer. Sci. Program. 1, 2038740 (2022).","DOI":"10.1155\/2022\/2038740"},{"key":"20087_CR3","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, P., Yang, C. F. & Tseng, H. W. Rapid local image style transfer method based on residual convolutional neural network. Sens. Mater  33  (2021).","DOI":"10.18494\/SAM.2021.3172"},{"issue":"1","key":"20087_CR4","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","volume":"22","author":"HE Kim","year":"2022","unstructured":"Kim, H. E. et al. Transfer learning for medical image classification: a literature review. BMC Med. Imaging. 22(1), 69 (2022).","journal-title":"BMC Med. Imaging"},{"key":"20087_CR5","doi-asserted-by":"publisher","first-page":"104743","DOI":"10.1016\/j.engappai.2022.104743","volume":"110","author":"AE Ezugwu","year":"2022","unstructured":"Ezugwu, A. E. et al. A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Eng. Appl. Artif. Intell. 110, 104743 (2022).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"20087_CR6","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1007\/s12559-021-09896-9","volume":"13","author":"W Jiang","year":"2021","unstructured":"Jiang, W. et al. MTFFNet: A multi-task feature fusion framework for Chinese painting classification. Cognit Comput. 13, 1287\u20131296 (2021).","journal-title":"Cognit Comput."},{"key":"20087_CR7","doi-asserted-by":"publisher","first-page":"103039","DOI":"10.1016\/j.infrared.2019.103039","volume":"102","author":"H Li","year":"2019","unstructured":"Li, H., Wu, X. & Durrani, T. S. Infrared and visible image fusion with ResNet and zero-phase component analysis. Infrared Phys. Technol. 102, 103039 (2019).","journal-title":"Infrared Phys. Technol."},{"key":"20087_CR8","doi-asserted-by":"publisher","first-page":"127434","DOI":"10.1016\/j.neucom.2024.127434","volume":"582","author":"T Shi","year":"2024","unstructured":"Shi, T., Chen, C., Li, X. & Hao, A. Semantic and style based multiple reference learning for artistic and general image aesthetic assessment. Neurocomputing 582, 127434 (2024).","journal-title":"Neurocomputing"},{"key":"20087_CR9","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv Prepr. arXiv.11929 (2010)."},{"key":"20087_CR10","doi-asserted-by":"crossref","unstructured":"Touvron, H. et al. Training data-efficient image transformers & distillation through attention. in International Conference on Machine Learning 10347\u201310357 (PMLR, 2021).","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"20087_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M. et al. Emerging properties in self-supervised vision transformers. in Proceedings of the IEEE\/CVF International Conference on Computer Vision 9650\u20139660 (2021).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"20087_CR12","first-page":"1","volume":"70","author":"J Xie","year":"2020","unstructured":"Xie, J., Li, Z., Zhou, Z. & Liu, S. A novel bearing fault classification method based on xgboost: the fusion of deep learning-based features and empirical features. IEEE Trans. Instrum. Meas. 70, 1\u20139 (2020).","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"5","key":"20087_CR13","first-page":"6575","volume":"45","author":"L Yuan","year":"2022","unstructured":"Yuan, L., Hou, Q., Jiang, Z., Feng, J. & Yan, S. Volo: vision outlooker for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 6575\u20136586 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20087_CR14","first-page":"1","volume":"60","author":"G Chen","year":"2022","unstructured":"Chen, G., Jiao, P., Hu, Q., Xiao, L. & Ye, Z. SwinSTFM: remote sensing Spatiotemporal fusion using Swin transformer. IEEE Trans. Geosci. Remote Sens. 60, 1\u201318 (2022).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"20087_CR15","first-page":"1","volume":"60","author":"C Zhang","year":"2022","unstructured":"Zhang, C. et al. Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery. IEEE Trans. Geosci. Remote Sens. 60, 1\u201320 (2022).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"20087_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, K., Huang, D., Liu, Z. & Zhao, J. Dual head-wise coattention network for machine comprehension with multiple-choice questions. in Proceedings of the 29th ACM International Conference on Information & Knowledge Management 1015\u20131024  (2020).","DOI":"10.1145\/3340531.3412013"},{"issue":"1","key":"20087_CR17","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1186\/s12859-022-04702-1","volume":"23","author":"X Zhang","year":"2022","unstructured":"Zhang, X. et al. A deep learning approach for orphan gene identification in Moso bamboo (Phyllostachys edulis) based on the CNN\u2009+\u2009Transformer model. BMC Bioinform. 23(1), 162 (2022).","journal-title":"BMC Bioinform."},{"key":"20087_CR18","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/j.isprsjprs.2023.07.001","volume":"202","author":"W Liu","year":"2023","unstructured":"Liu, W., Lin, Y., Liu, W., Yu, Y. & Li, J. An attention-based multiscale transformer network for remote sensing image change detection. ISPRS J. Photogramm Remote Sens. 202, 599\u2013609 (2023).","journal-title":"ISPRS J. Photogramm Remote Sens."},{"key":"20087_CR19","doi-asserted-by":"publisher","first-page":"125064","DOI":"10.1016\/j.eswa.2024.125064","volume":"258","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Weng, Y. & Wang, B. Cwt-vit: A time\u2013frequency representation and vision transformer-based framework for automated robotic surgical skill assessment. Expert Syst. Appl. 258, 125064 (2024).","journal-title":"Expert Syst. Appl."},{"key":"20087_CR20","doi-asserted-by":"publisher","first-page":"118193","DOI":"10.1016\/j.carbon.2023.118193","volume":"213","author":"KL Huo","year":"2023","unstructured":"Huo, K. L. et al. Carbon-based EM functional materials and multi-band microwave devices: current progress and perspectives. Carbon N Y. 213, 118193 (2023).","journal-title":"Carbon N Y"},{"key":"20087_CR21","doi-asserted-by":"crossref","unstructured":"Li, W., Xue, L., Wang, X. & Li, G. ConvTransNet: A CNN\u2013transformer network for change detection with multiscale global\u2013local representations. IEEE Trans. Geosci. Remote Sens. 61, 1\u201315 (2023).","DOI":"10.1109\/TGRS.2023.3272694"},{"issue":"6","key":"20087_CR22","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.1109\/TCDS.2024.3405573","volume":"16","author":"D Sharma","year":"2024","unstructured":"Sharma, D., Dhiman, C. & Kumar, D. Control with style: style embedding-based variational autoencoder for controlled stylized caption generation framework. IEEE Trans. Cogn. Dev. Syst. 16(6), 2032\u20132042 (2024).","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"20087_CR23","doi-asserted-by":"crossref","unstructured":"Sharma, D., Dhiman, C. & Kumar, D. Unma-capsumt: unified and multi-head attention-driven caption summarization transformer. arXiv Prepr. arXiv2412.11836  (2024).","DOI":"10.1016\/j.jvcir.2025.104600"},{"key":"20087_CR24","doi-asserted-by":"crossref","unstructured":"Sharma, D., Dhiman, C. & Kumar, D. A review of stylized image captioning techniques, evaluation parameters, and datasets. in 4th International Conference on Artificial Intelligence and Speech Technology (AIST) 1\u20135 (IEEE, 2022).","DOI":"10.1109\/AIST55798.2022.10064842"},{"issue":"3","key":"20087_CR25","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1109\/83.366474","volume":"4","author":"M Unser","year":"1995","unstructured":"Unser, M., Aldroubi, A. & Eden, M. Enlargement or reduction of digital images with minimum loss of information. IEEE Trans. Image Process. 4(3), 247\u2013258 (1995).","journal-title":"IEEE Trans. Image Process."},{"key":"20087_CR26","unstructured":"Akilli, A. Effect of normalization techniques on data. VER\u0130 MADENC\u0130L\u0130\u011e\u0130 Y\u00d6NTEMLER\u0130 TARIM ALANINDA UYGULAMALARI 127 (2020)."},{"issue":"1","key":"20087_CR27","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/TCBB.2020.2986544","volume":"18","author":"X Yu","year":"2020","unstructured":"Yu, X. et al. ResNet-SCDA-50 for breast abnormality classification. IEEE\/ACM Trans. Comput. Biol. Bioinforma. 18(1), 94\u2013102 (2020).","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinforma"},{"issue":"1","key":"20087_CR28","first-page":"40","volume":"20","author":"I Namat\u0113vs","year":"2017","unstructured":"Namat\u0113vs, I. Deep convolutional neural networks: structure, feature extraction and training. Inf. Technol. Manag Sci. 20(1), 40\u201347 (2017).","journal-title":"Inf. Technol. Manag Sci."},{"key":"20087_CR29","doi-asserted-by":"publisher","first-page":"767836","DOI":"10.3389\/fmedt.2021.767836","volume":"3","author":"D Luo","year":"2021","unstructured":"Luo, D., Zeng, W., Chen, J. & Tang, W. Deep learning for automatic image segmentation in stomatology and its clinical application. Front. Med. Technol. 3, 767836 (2021).","journal-title":"Front. Med. Technol."},{"issue":"3","key":"20087_CR30","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1007\/s40747-021-00637-x","volume":"8","author":"W Jia","year":"2022","unstructured":"Jia, W., Sun, M., Lian, J. & Hou, S. Feature dimensionality reduction: a review. Complex. Intell. Syst. 8(3), 2663\u20132693 (2022).","journal-title":"Complex. Intell. Syst."},{"issue":"1","key":"20087_CR31","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s10618-023-00948-2","volume":"38","author":"NM Foumani","year":"2024","unstructured":"Foumani, N. M., Tan, C. W., Webb, G. I. & Salehi, M. Improving position encoding of Transformers for multivariate time series classification. Data Min. Knowl. Discov. 38(1), 22\u201348 (2024).","journal-title":"Data Min. Knowl. Discov"},{"key":"20087_CR32","doi-asserted-by":"crossref","unstructured":"Hu, K. et al. An overview: attention mechanisms in multi-agent reinforcement learning. Neurocomputing 128015 (2024).","DOI":"10.1016\/j.neucom.2024.128015"},{"issue":"3","key":"20087_CR33","first-page":"1","volume":"31","author":"B Lin","year":"2022","unstructured":"Lin, B., Wang, S., Wen, M. & Mao, X. Context-aware code change embedding for better patch correctness assessment. ACM Trans. Softw. Eng. Methodol. 31(3), 1\u201329 (2022).","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"20087_CR34","unstructured":"Sankar, A., Wu, Y., Gou, L., Zhang, W. & Yang, H. Dynamic graph representation learning via self-attention networks. arXiv Prepr. arXiv1812.09430  (2018)."},{"key":"20087_CR35","doi-asserted-by":"publisher","first-page":"108374","DOI":"10.1109\/ACCESS.2022.3212767","volume":"10","author":"KT Chitty-Venkata","year":"2022","unstructured":"Chitty-Venkata, K. T., Emani, M., Vishwanath, V. & Somani, A. K. Neural architecture search for transformers: A survey. IEEE Access. 10, 108374\u2013108412 (2022).","journal-title":"IEEE Access."},{"issue":"10","key":"20087_CR36","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1109\/TCSVT.2018.2874312","volume":"29","author":"C Li","year":"2018","unstructured":"Li, C. et al. Learning local-global multi-graph descriptors for RGB-T object tracking. IEEE Trans. Circuits Syst. Video Technol. 29(10), 2913\u20132926 (2018).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"20087_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhang, P., Qi, J. & Lu, H. Hat: Hierarchical aggregation transformers for person re-identification. in Proceedings of the 29th ACM International Conference on Multimedia 516\u2013525 (2021).","DOI":"10.1145\/3474085.3475202"},{"key":"20087_CR38","doi-asserted-by":"publisher","first-page":"39243","DOI":"10.1109\/ACCESS.2023.3267492","volume":"11","author":"H Malik","year":"2023","unstructured":"Malik, H. et al. A novel fusion model of hand-crafted features with deep convolutional neural networks for classification of several chest diseases using X-ray images. IEEE Access. 11, 39243\u201339268 (2023).","journal-title":"IEEE Access."},{"issue":"2","key":"20087_CR39","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1007\/s10462-021-09992-0","volume":"55","author":"B Akay","year":"2022","unstructured":"Akay, B., Karaboga, D. & Akay, R. A comprehensive survey on optimizing deep learning models by metaheuristics. Artif. Intell. Rev. 55(2), 829\u2013894 (2022).","journal-title":"Artif. Intell. Rev."},{"key":"20087_CR40","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P. et al. Supervised contrastive learning. Adv. Neural Inf. Process. Syst. 33, 18661\u201318673 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"20087_CR41","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2021","unstructured":"Wang, L. & Yoon, K. J. Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3048\u20133068 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20087_CR42","unstructured":"WikiArt & Dataset (2025). https:\/\/www.wikiart.org\/(accessed"},{"key":"20087_CR43","doi-asserted-by":"crossref","unstructured":"Karayev, S. et al. Recognizing Image Style (BMVC, 2014).","DOI":"10.5244\/C.28.122"},{"key":"20087_CR44","doi-asserted-by":"crossref","unstructured":"Wilber, M. J. et al. Bam! the behance artistic media dataset for recognition beyond photography. in Proceedings of the IEEE International Conference on Computer Vision 1202\u20131211 (2017).","DOI":"10.1109\/ICCV.2017.136"},{"key":"20087_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. in Proceedings of the IEEE\/CVF International Conference on Computer Vision 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20087_CR46","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. in International Conference on Machine Learning 8748\u20138763 (PmLR, 2021)."},{"issue":"4","key":"20087_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3608446","volume":"17","author":"C Zhao","year":"2023","unstructured":"Zhao, C. & Caragea, C. Deep gated multi-modal fusion for image privacy prediction. ACM Trans. Web. 17(4), 1\u201324 (2023).","journal-title":"ACM Trans. Web"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20087-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20087-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20087-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:42:09Z","timestamp":1760607729000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20087-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["20087"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-20087-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"17 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"36178"}}