{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T22:10:18Z","timestamp":1769983818937,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557219","type":"print"},{"value":"9789819557226","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-5722-6_10","type":"book-chapter","created":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T08:13:50Z","timestamp":1769933630000},"page":"131-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Personalized Text-to-Image Generation Using Semantically Enhanced Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3489-6661","authenticated-orcid":false,"given":"Jing","family":"Dong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1790-9634","authenticated-orcid":false,"given":"Ping","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3902-0813","authenticated-orcid":false,"given":"Pengfei","family":"Yi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5200-640X","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"10_CR1","unstructured":"Zhao, B.N., Xiao, Y., Xu, J., et al.: DreamDistribution: prompt distribution learning for text-to-image diffusion models (2023)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Raj, A., Kaza, S., Poole, B., et al.: Dreambooth3D: subject-driven text-to-3D generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2349\u20132359 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, N., Tang, F., et al.: Inversion-based style transfer with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10146\u201310156. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"10_CR4","unstructured":"Wang, H., Spinelli, M., Wang, Q., et al.: InstantStyle: free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)"},{"key":"10_CR5","unstructured":"Guo, Y., Yang, C., Rao, A., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhou, D., Cheng, M.M., et al.: StoryDiffusion: consistent self-attention for long-range image and video generation. In: Advances in Neural Information Processing Systems, vol. 37, pp. 110315\u2013110340 (2025)","DOI":"10.52202\/079017-3501"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., et al.: GALIP: generative adversarial CLIPs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14214\u201314223. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"10_CR8","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"10_CR9","unstructured":"Radford, A., Kim, J. W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"10_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"10_CR11","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., et al.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22500\u201322510. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR14","unstructured":"Touvron, H., Lavril, T., Izacard, G., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Zhong, S., Huang, Z., Wen, W., et al.: Sur-adapter: enhancing text-to-image pre-trained diffusion models with large language models. In: Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), pp. 567\u2013578. ACM (2023)","DOI":"10.1145\/3581783.3611863"},{"issue":"7","key":"10_CR16","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., et al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR18","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"10_CR19","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9650\u20139660. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00951"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5722-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T08:13:54Z","timestamp":1769933634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5722-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557219","9789819557226"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5722-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"28 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb2025.sau.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}