{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:03:51Z","timestamp":1784131431443,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819235094","type":"print"},{"value":"9789819235100","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3510-0_24","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:05:54Z","timestamp":1784127954000},"page":"282-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Between Me and the World: Disentangling Foregrounds and Backgrounds in Personalized Text-to-Image Diffusion Models"],"prefix":"10.1007","author":[{"given":"Yifan","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaiguang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"24_CR1","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS. 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"key":"24_CR2","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint https:\/\/arxiv.org\/abs\/2010.02502 (2020)."},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR. pp. 10684\u201310695 (2022).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR4","unstructured":"Ning, M., et al.: Dctdiff: Intriguing properties of image generative modeling in the dct space (2025), https:\/\/arxiv.org\/abs\/2412.15032"},{"key":"24_CR5","volume-title":"Rmdm: Radio Map Diffusion Model with Physics Informed","author":"H Jia","year":"2025","unstructured":"Jia, H., et al.: Rmdm: Radio Map Diffusion Model with Physics Informed (2025)"},{"issue":"6","key":"24_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618322","volume":"42","author":"Y Alaluf","year":"2023","unstructured":"Alaluf, Y., et al.: A neural space-time representation for text-to-image personalization. ACM Trans. Graph. (TOG). 42(6), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR. pp. 22500\u201322510 (2023).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"24_CR8","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint https:\/\/arxiv.org\/abs\/2208.01618 (2022)."},{"key":"24_CR9","first-page":"39869","volume":"37","author":"L Pang","year":"2024","unstructured":"Pang, L., et al.: Attndreambooth: towards text-aligned personalized text-to-image generation. NeurIPS. 37, 39869\u201339900 (2024)","journal-title":"NeurIPS"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Ssr-encoder: Encoding selective subject representation for subject-driven generation. In: CVPR. pp. 8069\u20138078 (2024).","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Huang, M., Mao, Z., Liu, M., He, Q., Zhang, Y.: Realcustom: Narrowing real text word for real-time open-domain text-to-image customization. In: CVPR. pp. 7476--7485 (2024).","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Song, K., Zhu, Y., Liu, B., Yan, Q., Elgammal, A., & Yang, X.: Moma: Multimodal llm adapter for fast personalized image generation. In: ECCV. pp. 117\u2013132 (2024).","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"24_CR13","unstructured":"Huang, J., Liew, J. H., Yan, H., Yin, Y., Zhao, Y., & Wei, Y.: Classdiffusion: More aligned personalization tuning with explicit class guidance. arXiv preprint https:\/\/arxiv.org\/abs\/2405.17532 (2024)."},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, L., Weng, F., Pan, L., & Lan, Z.: Tailored visions: Enhancing text-to-image generation with personalized prompt rewriting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE\/CVF. pp. 7727\u20137736 (2024).","DOI":"10.1109\/CVPR52733.2024.00738"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: SATO: Stable Text-To-Motion Framework. In: ACM MM. pp. 6989--6997 (2024).","DOI":"10.1145\/3664647.3681034"},{"key":"24_CR16","unstructured":"Chen, W., et al.: Free-t2m: Frequency enhanced text-to-motion diffusion model with consistency loss (2025)."},{"key":"24_CR17","unstructured":"Chen, W., et al.: Ant: Adaptive neural temporal-aware text-to-motion model. arXiv preprint https:\/\/arxiv.org\/abs\/2506.02452 (2025)."},{"key":"24_CR18","unstructured":"Luo, M., et al.: Dr.v: A hierarchical perception-temporal-cognition framework to diagnose video hallucination by fine-grained spatial-temporal grounding. arXiv preprint https:\/\/arxiv.org\/abs\/2509.11866 (2025)."},{"key":"24_CR19","unstructured":"Wan, G., Huang, Z., Zhao, W., Luo, X., Sun, Y., & Wang, W.: Rethink graphode generalization within coupled dynamical system. In: ICML (2025)."},{"key":"24_CR20","unstructured":"Wan, G., et al.: Epidemiology-aware neural ode with continuous disease transmission graph. In: ICML (2025)."},{"key":"24_CR21","unstructured":"Wan, G., et al.: Energy-based backdoor defense against federated graph learning. In: ICLR (2025)."},{"key":"24_CR22","unstructured":"Wan, G., Tian, Y., Huang, W., Chawla, N.V., Ye, M.: S3gcl: Spectral, swift, spatial graph contrastive learning. In: ICML (2024)."},{"key":"24_CR23","doi-asserted-by":"publisher","first-page":"15429","DOI":"10.1609\/aaai.v38i14.29468","volume":"38","author":"G Wan","year":"2024","unstructured":"Wan, G., Huang, W., Ye, M.: Federated graph learning under domain shift with generalizable prototypes. AAAI. 38, 15429\u201315437 (2024)","journal-title":"AAAI"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Tan, Z., Wan, G., Huang, W., Ye, M.: Fedssp: Federated graph learning with spectral knowledge and personalized preference. In: NeurIPS (2024).","DOI":"10.52202\/079017-1090"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Huang, W., Wan, G., Ye, M., Du, B.: Federated graph semantic and structural learning. In: IJCAI. pp. 3830\u20133838 (2023).","DOI":"10.24963\/ijcai.2023\/426"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wan, G., Prakash, B. A., Lau, M. S. Y., Jin, W.: A review of graph neural networks in epidemic modeling. In: SIGKDD. pp. 6577\u20136587 (2024).","DOI":"10.1145\/3637528.3671455"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Chen, S.X., et al.: Tino-edit: Timestep and noise optimization for robust diffusion-based image editing. arXiv preprint https:\/\/arxiv.org\/abs\/2404.11120 (2024).","DOI":"10.1109\/CVPR52733.2024.00606"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, J., Cui, M., Li, J., Yang, H., Huang, D.: InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), 9380\u20139389 (2024).","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Shao, S., Bai, L., Xu, Z., Han, B., & Xie, Z.: Golden noise for diffusion models: A learning framework. arXiv preprint https:\/\/arxiv.org\/abs\/2411.09502 (2025).","DOI":"10.1109\/ICCV51701.2025.01643"},{"key":"24_CR30","first-page":"30146","volume":"36","author":"D Li","year":"2023","unstructured":"Li, D., Li, J., Hoi, S.: BLIP-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. NeurIPS. 36, 30146\u201330166 (2023)","journal-title":"NeurIPS"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Ding, G., et al.: FreeCustom: Tuning-Free Customized Image Generation For Multi-Concept Composition. In: CVPR. pp. 9089--9098 (2024).","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"24_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)","journal-title":"Pattern Recogn."},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M.-M., Shan, Y.: Photomaker: Customizing realistic human photos via stacked id embedding. In: CVPR. pp. 8640--8650 (2024).","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"24_CR34","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 https:\/\/arxiv.org\/abs\/2308.06721 (2023)."},{"key":"24_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML. pp. 8748\u20138763 (2021)."},{"issue":"4","key":"24_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM Transactions on Graphics (TOG). 42(4), 1\u201310 (2023)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Fukuda, K., Zhang, G., Zhang, Z., Sui, Y., Zhao, J.: Adaptive branch-and-bound tree exploration for neural network verification. In: DATE. pp. 1\u20137. IEEE (2025).","DOI":"10.23919\/DATE64628.2025.10992738"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, G., Xu, F., Bandara, H. M. N. D., Chen, S., Sui, Y.: Understanding the robustness of machine-unlearning models. In: ACISP. pp. 307\u2013326. Springer (2025).","DOI":"10.1007\/978-981-96-9101-2_16"},{"key":"24_CR39","first-page":"36","volume-title":"ECOOP","author":"G Zhang","year":"2025","unstructured":"Zhang, G., et al.: Efficient neural network verification via order leading exploration of branch-and-bound trees. In: ECOOP, p. 36. Schloss Dagstuhl-Leibniz-Zentrum f\u00fcr Informatik (2025)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Luo, M., et al.: Panosent: A panoptic sextuple extraction benchmark for multimodal conversational aspect-based sentiment analysis. In: ACM MM. pp. 7667\u20137676 (2024).","DOI":"10.1145\/3664647.3680705"},{"key":"24_CR41","unstructured":"Li, J., et al.: A survey on benchmarks of multimodal large language models. arXiv preprint https:\/\/arxiv.org\/abs\/2408.08632 (2024)."},{"key":"24_CR42","unstructured":"Oquab, M., et al.: Dinov2: Learning robust visual features without supervision. arXiv preprint https:\/\/arxiv.org\/abs\/2304.07193 (2023)."},{"key":"24_CR43","volume-title":"Clip-score: Clip score for pytorch","author":"Z Sun","year":"2023","unstructured":"Sun, Z.: Clip-score: Clip score for pytorch (2023)"},{"key":"24_CR44","first-page":"15903","volume":"36","author":"J Xu","year":"2023","unstructured":"Xu, J., et al.: ImageReward: Learning and Evaluating Human Preferences For Text-To-Image Generation. NeurIPS. 36, 15903\u201315935 (2023)","journal-title":"NeurIPS"},{"key":"24_CR45","unstructured":"Podell, D., et al.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. In: To Appear (2024)."},{"key":"24_CR46","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint https:\/\/arxiv.org\/abs\/2207.12598 (2022)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3510-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:06:01Z","timestamp":1784127961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3510-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819235094","9789819235100"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3510-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}