{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:51:15Z","timestamp":1770227475485,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["NO.2024M752378"],"award-info":[{"award-number":["NO.2024M752378"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Natural Science Foundation","doi-asserted-by":"crossref","award":["NO.23JCQNJC00990"],"award-info":[{"award-number":["NO.23JCQNJC00990"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s10489-025-06751-4","type":"journal-article","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:59:56Z","timestamp":1753491596000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Style-Content progressive aggregation network with stable diffusion"],"prefix":"10.1007","volume":"55","author":[{"given":"Tiebiao","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Yangyang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"issue":"23","key":"6751_CR1","doi-asserted-by":"publisher","first-page":"28675","DOI":"10.1007\/s10489-023-04993-8","volume":"53","author":"Y Sun","year":"2023","unstructured":"Sun Y, Liu J, Zhang R (2023) Large capacity generative image steganography via image style transfer and feature-wise deep fusion. Appl Intell 53(23):28675\u201328693","journal-title":"Appl Intell"},{"key":"6751_CR2","doi-asserted-by":"crossref","unstructured":"Shirakawa T, Uchida S (2024) NoiseCollage: A layout-aware text-to-image diffusion model based on noise cropping and merging. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8921\u20138930","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"6751_CR3","doi-asserted-by":"crossref","unstructured":"Qu L, Wu S, Fei H, Nie L, Chua TS (2023) Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation. In Proceedings of the 31st ACM International Conference on Multimedia 643\u2013654","DOI":"10.1145\/3581783.3612012"},{"issue":"11","key":"6751_CR4","doi-asserted-by":"publisher","first-page":"12533","DOI":"10.1007\/s10489-021-03154-z","volume":"52","author":"Z Huo","year":"2022","unstructured":"Huo Z, Li X, Qiao Y, Zhou P, Wang J (2022) Efficient photorealistic style transfer with multi-order image statistics. Appl Intell 52(11):12533\u201312545","journal-title":"Appl Intell"},{"key":"6751_CR5","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia C, Chan W, Saxena S, Li L, Whang J, Denton EL et al (2022) Photorealistic text-to-image diffusion models with deep language understanding. Adv Neural Inf Process Syst 35:36479\u201336494","journal-title":"Adv Neural Inf Process Syst"},{"key":"6751_CR6","unstructured":"Li D, Li J, Hoi S (2024) Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. Adv Neural Inf Process Syst 36"},{"issue":"8","key":"6751_CR7","doi-asserted-by":"publisher","first-page":"5187","DOI":"10.1109\/TCSVT.2021.3136857","volume":"32","author":"J Cheng","year":"2021","unstructured":"Cheng J, Wu F, Tian Y, Wang L, Tao D (2021) RiFeGAN2: Rich feature generation for text-to-image synthesis from constrained prior knowledge. IEEE Trans Circ Syst Video Technol 32(8):5187\u20135200","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"6751_CR8","unstructured":"Radford A, Kim JW, Hallacy C et al (2021) Learning transferable visual models from natural language supervision. In International conference on machine learning 8748\u20138763. PMLR"},{"key":"6751_CR9","unstructured":"Ramesh A, Dhariwal P, Nichol A, Chu C, Chen M (2022) Hierarchical text-conditional image generation with clip latents 1(2):3. arXiv preprint arXiv:2204.06125"},{"issue":"3","key":"6751_CR10","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1007\/s10489-023-05229-5","volume":"54","author":"S Li","year":"2024","unstructured":"Li S, Pu Y, Zhao Z, Yang Q, Gu J, Li Y, Xu D (2024) Dual-path hypernetworks of style and text for one-shot domain adaptation. Appl Intell 54(3):2614\u20132630","journal-title":"Appl Intell"},{"issue":"5","key":"6751_CR11","first-page":"4296","volume":"38","author":"C Mou","year":"2024","unstructured":"Mou C, Wang X, Xie L, Wu Y, Zhang J, Qi Z, Shan Y (2024) T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. Proc AAAI Conf Artif Intell 38(5):4296\u20134304","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6751_CR12","unstructured":"Zhao S, Chen D, Chen YC, Bao J, Hao S, Yuan L, Wong KYK (2024) Uni-controlnet: All-in-one control to text-to-image diffusion models. Adv Neural Inf Process Syst 36"},{"key":"6751_CR13","unstructured":"Gal R, Alaluf Y, Atzmon Y, Patashnik O, Bermano AH, Chechik G, Cohen-Or D (2022) An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618"},{"key":"6751_CR14","doi-asserted-by":"crossref","unstructured":"Zhang Y, Huang N, Tang F, Huang H, Ma C, Dong W, Xu C (2023) Inversion-based style transfer with diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 10146\u201310156","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"6751_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inf Process Syst"},{"key":"6751_CR16","unstructured":"Song J, Meng C, Ermon S (2020) Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502"},{"key":"6751_CR17","unstructured":"Ramesh A, Pavlov M, Goh G et al (2021) Zero-shot text-to-image generation. In International conference on machine learning 8821\u20138831. Pmlr"},{"key":"6751_CR18","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6751_CR19","doi-asserted-by":"crossref","unstructured":"Huang R, Han J, Lu G, Liang X, Zeng Y, Zhang W, Xu H (2023) DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability. In Proceedings of the IEEE\/CVF International Conference on Computer Vision 15713\u201315723","DOI":"10.1109\/ICCV51070.2023.01440"},{"issue":"15","key":"6751_CR20","doi-asserted-by":"publisher","first-page":"18666","DOI":"10.1007\/s10489-022-04375-6","volume":"53","author":"C Li","year":"2023","unstructured":"Li C, Taniguchi Y, Lu M, Konomi SI, Nagahara H (2023) Cross-language font style transfer. Appl Intell 53(15):18666\u201318680","journal-title":"Appl Intell"},{"key":"6751_CR21","doi-asserted-by":"crossref","unstructured":"Zhou L, Zhang T (2023) Multi-scale Attention Enhancement for Arbitrary Style Transfer via Contrast Learning. In Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence 650\u2013656","DOI":"10.1145\/3594315.3594386"},{"key":"6751_CR22","doi-asserted-by":"crossref","unstructured":"Zhang C, Dai Z, Cao P, Yang J (2023) Edge enhanced image style transfer via transformers. In Proceedings of the 2023 ACM International Conference on Multimedia Retrieval 105\u2013114","DOI":"10.1145\/3591106.3592257"},{"issue":"2","key":"6751_CR23","first-page":"674","volume":"38","author":"N Ahn","year":"2024","unstructured":"Ahn N, Lee J, Lee C, Kim K, Kim D, Nam SH, Hong K (2024) Dreamstyler: Paint by style inversion with text-to-image diffusion models. Proc AAAI Conf Artif Intell 38(2):674\u2013681","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6751_CR24","doi-asserted-by":"crossref","unstructured":"Qi T, Fang S, Wu Y et al (2024) DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8693\u20138702","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"6751_CR25","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139, 2015, proceedings, part III 18, 234\u2013241. Springer International Publishing","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"6751_CR26","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S et al (2014) Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, 740\u2013755. Springer International Publishing","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6751_CR27","doi-asserted-by":"crossref","unstructured":"Karayev S, Trentacoste M, Han H, Agarwala A, Darrell T, Hertzmann A, Winnemoeller H (2013) Recognizing image style. arXiv preprint arXiv:1311.3715","DOI":"10.5244\/C.28.122"},{"key":"6751_CR28","doi-asserted-by":"crossref","unstructured":"Wu X, Sun K, Zhu F, Zhao R, Li H (2023) Better aligning text-to-image models with human preference, 1(3). arXiv preprint arXiv:2303.14420","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"6751_CR29","unstructured":"Chen W, Zhang J, Wu J, Wu H, Xiao X, Lin L (2024) ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning. arXiv preprint arXiv:2404.15449"},{"key":"6751_CR30","doi-asserted-by":"crossref","unstructured":"Deng Y, Tang F, Dong W, Ma C, Pan X, Wang L, Xu C (2022) Stytr2: Image style transfer with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 11326\u201311336","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"6751_CR31","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhang Z, Zhao L, Zuo Z, Li A, Xing W, Lu D (2022) AesUST: towards aesthetic-enhanced universal style transfer. In Proceedings of the 30th ACM International Conference on Multimedia 1095\u20131106","DOI":"10.1145\/3503161.3547939"},{"issue":"5","key":"6751_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605548","volume":"42","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Tang F, Dong W, Huang H, Ma C, Lee TY, Xu C (2023) A unified arbitrary style transfer framework via adaptive contrastive learning. ACM Trans Graph 42(5):1\u201316","journal-title":"ACM Trans Graph"},{"issue":"3","key":"6751_CR33","first-page":"2742","volume":"37","author":"Z Wang","year":"2023","unstructured":"Wang Z, Zhao L, Zuo Z, Li A, Chen H, Xing W, Lu D (2023) MicroAST: towards super-fast ultra-resolution arbitrary style transfer. Proc AAAI Conf Artif Intell 37(3):2742\u20132750","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6751_CR34","unstructured":"Zhao H, Xiao C, Yang J, Jin G, Li M (2024) MccSTN: Multi-Scale Contrast and Fine-Grained Feature Fusion Networks for Subject-driven Style Transfer. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) 11090\u201311100"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06751-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06751-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06751-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T15:56:53Z","timestamp":1758297413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06751-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,26]]},"references-count":34,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["6751"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06751-4","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,26]]},"assertion":[{"value":"21 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2025","order":2,"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 conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"890"}}