{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:17:19Z","timestamp":1783315039443,"version":"3.54.6"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02248-3","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:56:36Z","timestamp":1773150996000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EFE-SDG: efficient feature extraction of finetuning-free model in subject-driven generation"],"prefix":"10.1007","volume":"32","author":[{"given":"Hao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhen","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yemeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2248_CR1","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Adv. Neural Inform. Process. Syst. (2022)","DOI":"10.52202\/068431-2643"},{"key":"2248_CR2","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. In: Int. Conf. Learn. Represent. (2024)"},{"key":"2248_CR3","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP Latents (2022)"},{"key":"2248_CR4","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., et al.: Laion-5b: An open large-scale dataset for training next generation image-text models. In: Adv. Neural Inform. Process. Syst. (2022)","DOI":"10.52202\/068431-1833"},{"issue":"4","key":"2248_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530164","volume":"41","author":"R Gal","year":"2022","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-Or, D.: An image is worth one word: personalizing text-to-image generation using textual inversion. ACM Trans. Graph. 41(4), 1\u201319 (2022)","journal-title":"ACM Trans. Graph."},{"key":"2248_CR6","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2248_CR7","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.-Y.: Multi-concept customization of text-to-image diffusion. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 5796\u20135805 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"2248_CR8","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. In: Int. Conf. Comput. Vis., pp. 15943\u201315953 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"2248_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Song, Y., Liu, J., Wang, R., Yu, J., Tang, H., et al.: Ssr-encoder: Encoding selective subject representation for subject-driven generation. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 7421\u20137430 (2024)","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"2248_CR10","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: FastComposer: tuning-free multi-subject image generation with localized attention (2023)","DOI":"10.1007\/s11263-024-02227-z"},{"key":"2248_CR11","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, J., Chen, C., Lu, H.: Subject-Diffusion: open domain personalized text-to-image generation without test-time fine-tuning (2023)","DOI":"10.1145\/3641519.3657469"},{"key":"2248_CR12","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-Adapter: text compatible image prompt adapter for Text-to-Image diffusion models (2023)"},{"key":"2248_CR13","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2248_CR14","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Adv. Neural Inform. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"In: Adv. Neural Inform. Process. Syst."},{"key":"2248_CR15","unstructured":"Lai, Z., Zhu, X., Dai, J., Qiao, Y., Wang, W.: Mini-dalle3: interactive text to image by prompting large language models. In: Int. Conf. Learn. Represent. (2024)"},{"issue":"4","key":"2248_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530164","volume":"41","author":"R Gal","year":"2022","unstructured":"Gal, R., Patashnik, O., Maron, H., Chechik, G., Cohen-Or, D.: Stylegan-nada: Clip-guided domain adaptation of image generators. ACM Trans. Graph. 41(4), 1\u201313 (2022)","journal-title":"ACM Trans. Graph."},{"key":"2248_CR17","doi-asserted-by":"crossref","unstructured":"Huang, M., Mao, Z., Wang, P., Wang, Q., Zhang, Y.: Dse-gan: Dynamic semantic evolution generative adversarial network for text-to-image generation. In: ACM Int. Conf. Multimedia, pp. 4345\u20134354 (2022)","DOI":"10.1145\/3503161.3547881"},{"key":"2248_CR18","first-page":"2506","volume":"130","author":"K Hu","year":"2022","unstructured":"Hu, K., Liao, W., Yang, M.Y., Rosenhahn, B.: Text to image generation with semantic-spatial aware gan. Int. J. Comput. Vis. 130, 2506\u20132522 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"2248_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110078","volume":"192","author":"S Umirzakova","year":"2025","unstructured":"Umirzakova, S., Shakhnoza, M., Sevara, M., Whangbo, T.K.: Deep learning for multiple sclerosis lesion classification and stratification using mri. Comput. Biol. Med. 192, 110078 (2025)","journal-title":"Comput. Biol. Med."},{"issue":"140","key":"2248_CR20","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"2248_CR21","first-page":"1","volume":"42","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Dong, W., Tang, F., et al.: Prospect: prompt spectrum for attribute-aware personalization of diffusion models. ACM Trans. Graph. 42(6), 1\u201314 (2023)","journal-title":"ACM Trans. Graph."},{"key":"2248_CR22","doi-asserted-by":"crossref","unstructured":"Zeng, W., Yan, Y., Zhu, Q., et al.: Infusion: preventing customized text-to-image diffusion from overfitting. In: ACM Int. Conf. Multimedia, pp. 3568\u20133577 (2024)","DOI":"10.1145\/3664647.3680894"},{"key":"2248_CR23","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: P+: extended textual conditioning in text-to-image generation. ACM Trans. Graph. 42(6) (2023)"},{"key":"2248_CR24","unstructured":"Zhang, Y., Kers, J., Cassol, C.A., Roelofs, J.J., Idrees, N., et al.: U-Net-and-a-half: convolutional network for biomedical image segmentation using multiple expert-driven annotations. arXiv preprint arXiv:2105.00898 (2021)"},{"key":"2248_CR25","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Wei, W., Hou, T., Pritch, Y., Wadhwa, N., Rubinstein, M., Aberman, K.: Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models. In: Int. Conf. Comput. Vis., pp. 6527\u20136536 (2023)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"2248_CR26","unstructured":"Li, D., Li, J., Hoi, S.C.H.: Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 15181\u201315190 (2024)"},{"issue":"7","key":"2248_CR27","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., Duerig, T., Ferrari, V.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"2248_CR28","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: Personalized text-to-image generation without test-time finetuning. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 6894\u20136904 (2024)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"2248_CR29","unstructured":"Jia, X., Zhao, Y., Chan, K.C.K., Li, Y., Zhang, H., Gong, B., Hou, T., Wang, H., Su, Y.-C.: Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 4268\u20134278 (2024)"},{"key":"2248_CR30","unstructured":"Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Adv. Neural Inform. Process. Syst. (2017)"},{"key":"2248_CR31","doi-asserted-by":"crossref","unstructured":"Qin, X., Dai, H., Hu, X., Fan, D.-P., Shao, L., Gool, L.V.: Highly accurate dichotomous image segmentation. In: Eur. Conf. Comput. Vis., pp. 38\u201356 (2022)","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"2248_CR32","doi-asserted-by":"crossref","unstructured":"Cheung, T.-H., Fung, K.-C., Lai, S., Lin, K.-H., Ng, V., Lam, K.-M.: Automatic prompt generation and grounding object detection for zero-shot image anomaly detection (2024)","DOI":"10.1109\/APSIPAASC63619.2025.10848778"},{"key":"2248_CR33","unstructured":"OpenAI: GPT-4o System Card (2023). https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"2248_CR34","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., et al.: Learning transferable visual models from natural language supervision. In: Int. Conf. Mach. Learn., pp. 8748\u20138763 (2021)"},{"key":"2248_CR35","doi-asserted-by":"crossref","unstructured":"Chari, P., Ma, S., Ostashev, D., Kadambi, A., Krishnan, G., Wang, J., Aberman, K.: Personalized restoration via dual-pivot tuning. In: IEEE Conf. Comput. Vis. Pattern Recog., pp. 4279\u20134288 (2024)","DOI":"10.1109\/TIP.2025.3586141"},{"key":"2248_CR36","doi-asserted-by":"crossref","unstructured":"Tang, L., Ruiz, N., Chu, Q., Li, Y., Holynski, A., Jacobs, D.E., et al.: Realfill: Reference-driven generation for authentic image completion. ACM Trans. Graph. 43(4) (2024)","DOI":"10.1145\/3658237"},{"key":"2248_CR37","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In: IEEE Conf. Comput. Vis. Pattern Recog. (2024)"},{"key":"2248_CR38","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., Ge, Y., Wang, X., Lei, W., Gu, Y., Shi, Y., Hsu, W., Shan, Y., Qie, X., Shou, M.Z.: Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: Int. Conf. Comput. Vis., pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"2248_CR39","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: Int. Conf. Comput. Vis., pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02248-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02248-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02248-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:00:06Z","timestamp":1783314006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02248-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2248"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02248-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7499053\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"31 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","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 that they have no conflict of interest on this work. The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"194"}}