{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:33:30Z","timestamp":1769186010982,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","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\/978-981-95-5567-3_16","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:43Z","timestamp":1769116423000},"page":"226-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiscoIB: Disentangled Subject Customization via\u00a0Information Bottleneck"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0283-7092","authenticated-orcid":false,"given":"Yifan","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3717-1732","authenticated-orcid":false,"given":"Kaiwen","family":"Qian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7085-8876","authenticated-orcid":false,"given":"Yuchun","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"16_CR1","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. In: International Conference on Learning Representations (2017)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: extracting multiple concepts from a single image. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201312 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: The chosen one: consistent characters in text-to-image diffusion models. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657430"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., Wei, Y., Ji, Z., Bai, J., Han, H., Zuo, W.: Decoupled textual embeddings for customized image generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 909\u2013917 (2024)","DOI":"10.1609\/aaai.v38i2.27850"},{"key":"16_CR5","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":"16_CR6","unstructured":"Chen, H., et al.: DisenBooth: identity-preserving disentangled tuning for subject-driven text-to-image generation. In: ICLR (2024)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Ding, G., et al.: FreeCustom: tuning-free customized image generation for multi-concept composition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9089\u20139098 (2024)","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"16_CR8","unstructured":"Esser, P., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"16_CR9","unstructured":"Feng, H., Huang, Z., Li, L., Lv, H., Sheng, L.: Personalize anything for free with diffusion transformer. arXiv preprint arXiv:2503.12590 (2025)"},{"key":"16_CR10","unstructured":"Fu, S., et al.: DreamSim: learning new dimensions of human visual similarity using synthetic data. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 50742\u201350768 (2023)"},{"key":"16_CR11","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"16_CR12","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":"16_CR13","unstructured":"Jin, C., Tanno, R., Saseendran, A., Diethe, T., Teare, P.A.: An image is worth multiple words: discovering object level concepts using multi-concept prompt learning. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"16_CR14","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"16_CR15","unstructured":"Black Forest Labs: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"16_CR16","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8640\u20138650 (2024)","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"16_CR17","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"16_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"16_CR19","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":"16_CR20","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":"16_CR21","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125, 1(2), 3 (2022)"},{"key":"16_CR22","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":"16_CR23","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"16_CR24","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":"16_CR25","unstructured":"Schuhmann, C., et al.: LAION-400m: open dataset of clip-filtered 400 million image-text pairs. In: NeurIPS Workshop Datacentric AI. No. FZJ-2022-00923, J\u00fclich Supercomputing Center (2021)"},{"key":"16_CR26","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8543\u20138552 (2024)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"16_CR27","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"16_CR28","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method (2000)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gu, T., Chen, W., Chen, A.: OOTDiffusion: outfitting fusion based latent diffusion for controllable virtual try-on. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 8996\u20139004 (2025)","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et\u00a0al.: SSR-encoder: encoding selective subject representation for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8069\u20138078 (2024)","DOI":"10.1109\/CVPR52733.2024.00771"}],"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\/978-981-95-5567-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:50Z","timestamp":1769116430000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_16","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":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}