{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T16:06:50Z","timestamp":1785773210528,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543977","type":"print"},{"value":"9789819543984","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4398-4_11","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T23:02:05Z","timestamp":1762642925000},"page":"149-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Training-Free Multi-style Fusion Through Reference-Based Adaptive Modulation"],"prefix":"10.1007","author":[{"given":"Xu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"11_CR2","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, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Song, L., Hu, Y., He, R.: Adversarial occlusion-aware face detection. In: 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp.\u00a01\u20139. IEEE (2018)","DOI":"10.1109\/BTAS.2018.8698572"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Hertz, A., Voynov, A., Fruchter, S., Cohen-Or, D.: Style aligned image generation via shared attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4775\u20134785 (2024)","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"11_CR5","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR6","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, J., Liao, J.: Style mixer: semantic-aware multi-style transfer network. In: Computer Graphics Forum. vol.\u00a038, pp. 469\u2013480. Wiley Online Library (2019)","DOI":"10.1111\/cgf.13853"},{"key":"11_CR9","unstructured":"Kulikov, V., Kleiner, M., Huberman-Spiegelglas, I., Michaeli, T.: FlowEdit: Inversion-free text-based editing using pre-trained flow models. arXiv preprint arXiv:2412.08629 (2024)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Kwon, G., Ye, J.C.: CLIPstyler: image style transfer with a single text condition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18048\u201318057. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"11_CR12","unstructured":"Pernias, P., Rampas, D., Richter, M.L., Pal, C.J., Aubreville, M.: W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models. arXiv preprint arXiv:2306.00637 (2023)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Qi, T., et al.: DEADiff: an efficient stylization diffusion model with disentangled representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8693\u20138702 (2024)","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"11_CR14","unstructured":"Qiu, L., et al.: VT-CLIP: Enhancing vision-language models with visual-guided texts. arXiv preprint arXiv:2112.02399 (2021)"},{"key":"11_CR15","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR16","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"11_CR17","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Rout, L., Chen, Y., Kumar, A., Caramanis, C., Shakkottai, S., Chu, W.S.: Beyond first-order tweedie: solving inverse problems using latent diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9472\u20139481 (2024)","DOI":"10.1109\/CVPR52733.2024.00905"},{"key":"11_CR20","unstructured":"Rout, L., Chen, Y., Ruiz, N., Caramanis, C., Shakkottai, S., Chu, W.S.: Semantic image inversion and editing using rectified stochastic differential equations. arXiv preprint arXiv:2410.10792 (2024)"},{"key":"11_CR21","unstructured":"Rout, L., et al.: RB-modulation: Training-free personalization of diffusion models using stochastic optimal control. arXiv preprint arXiv:2405.17401 (2024)"},{"key":"11_CR22","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR23","unstructured":"Sohn, K., et\u00a0al.: StyleDrop: Text-to-image generation in any style. arXiv preprint arXiv:2306.00983 (2023)"},{"key":"11_CR24","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"11_CR25","unstructured":"Wang, H., Spinelli, M., Wang, Q., Bai, X., Qin, Z., Chen, A.: InstantStyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Wang, L., Chen, Y., Tran, D., Boddeti, V.N., Chu, W.S.: SEAL: semantic attention learning for long video representation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26192\u201326201 (2025)","DOI":"10.1109\/CVPR52734.2025.02439"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11_CR28","unstructured":"Xu, Y., Wang, Z., Xiao, J., Liu, W., Chen, L.: FreeTuner: Any subject in any style with training-free diffusion. arXiv preprint arXiv:2405.14201 (2024)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Yan, J.N., Gu, J., Rush, A.M.: Diffusion models without attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8239\u20138249 (2024)","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"11_CR30","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"11_CR31","unstructured":"Zhang, H., Dana, K.J.: Multi-style generative network for real-time transfer. arXiv preprint arXiv:1703.06953 (2017)"},{"key":"11_CR32","unstructured":"Zhang, Z., et al.: U-StyDiT: Ultra-high quality artistic style transfer using diffusion transformers. arXiv preprint arXiv:2503.08157 (2025)"},{"key":"11_CR33","unstructured":"Zhong, M., et al.: Multi-LoRA composition for image generation. arXiv preprint arXiv:2402.16843 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4398-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T23:02:10Z","timestamp":1762642930000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4398-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819543977","9789819543984"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4398-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gold Coast, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}