{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:13:26Z","timestamp":1777655606886,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729034","type":"print"},{"value":"9783031729041","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72904-1_23","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:29:28Z","timestamp":1732109368000},"page":"391-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ViPer: Visual Personalization of\u00a0Generative Models via\u00a0Individual Preference Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5429-6624","authenticated-orcid":false,"given":"Sogand","family":"Salehi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1097-0803","authenticated-orcid":false,"given":"Mahdi","family":"Shafiei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-9246","authenticated-orcid":false,"given":"Teresa","family":"Yeo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5324-2474","authenticated-orcid":false,"given":"Roman","family":"Bachmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-1843","authenticated-orcid":false,"given":"Amir","family":"Zamir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Chung, J., Hyun, S., Heo, J.P.: Style injection in diffusion: a training-free approach for adapting large-scale diffusion models for style transfer (2023)","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"23_CR3","unstructured":"Clark, K., Vicol, P., Swersky, K., Fleet, D.J.: Directly fine-tuning diffusion models on differentiable rewards (2023)"},{"key":"23_CR4","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis (2021)"},{"key":"23_CR5","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022)"},{"key":"23_CR6","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation (2023)"},{"key":"23_CR7","unstructured":"He, F., Li, G., Zhang, M., Yan, L., Si, L., Li, F.: FreeStyle: free lunch for text-guided style transfer using diffusion models (2024)"},{"key":"23_CR8","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574 (2022)"},{"key":"23_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"23_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance (2022)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"23_CR12","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-Pic: an open dataset of user preferences for text-to-image generation (2023)"},{"key":"23_CR13","unstructured":"Lauren\u00e7on, H., et al.: OBELICS: an open web-scale filtered dataset of interleaved image-text documents (2023)"},{"key":"23_CR14","unstructured":"Lauren\u00e7on, H., Tronchon, L., Cord, M., Sanh, V.: What matters when building vision-language models? (2024)"},{"key":"23_CR15","unstructured":"Li, W., et al.: UPainting: unified text-to-image diffusion generation with cross-modal guidance (2022)"},{"key":"23_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"Computer Vision - ECCV 2022","author":"N Liu","year":"2023","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Luo, E., Hao, M., Wei, L., Zhang, X.: scDiffusion: conditional generation of high-quality single-cell data using diffusion model (2024)","DOI":"10.1093\/bioinformatics\/btae518"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"23_CR19","unstructured":"OpenAI, et al.: GPT-4 technical report (2024)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Parmar, G., Singh, K.K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"23_CR21","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"23_CR22","unstructured":"Prabhudesai, M., Goyal, A., Pathak, D., Fragkiadaki, K.: Aligning text-to-image diffusion models with reward backpropagation (2023)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR24","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 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"23_CR25","unstructured":"Ruta, D., Tarr\u00e9s, G.C., Gilbert, A., Shechtman, E., Kolkin, N., Collomosse, J.: DIFF-NST: diffusion interleaving for deformable neural style transfer (2023)"},{"key":"23_CR26","unstructured":"von R\u00fctte, D., Fedele, E., Thomm, J., Wolf, L.: FABRIC: personalizing diffusion models with iterative feedback (2023)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Sar\u0131y\u0131ld\u0131z, M.B., Alahari, K., Larlus, D., Kalantidis, Y.: Fake it till you make it: learning transferable representations from synthetic ImageNet clones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8011\u20138021 (2023)","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"23_CR28","unstructured":"Schuhmann, C., Beaumont, R.: Laion-aesthetics. https:\/\/laion.ai\/blog\/laion-aesthetics"},{"key":"23_CR29","unstructured":"Sohn, K., et al.: StyleDrop: text-to-image generation in any style (2023)"},{"key":"23_CR30","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations (2021)"},{"key":"23_CR31","unstructured":"Tang, Z., Rybin, D., Chang, T.H.: Zeroth-order optimization meets human feedback: provable learning via ranking oracles (2024)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization (2023)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"23_CR33","unstructured":"Wen, Y., Jain, N., Kirchenbauer, J., Goldblum, M., Geiping, J., Goldstein, T.: Hard prompts made easy: gradient-based discrete optimization for prompt tuning and discovery (2023)"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Human preference score: Better aligning text-to-image models with human preference (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"23_CR35","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation (2023)"},{"key":"23_CR36","unstructured":"Yeo, T., et al.: Controlled training data generation with diffusion models. arXiv preprint arXiv:2403.15309 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72904-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T19:51:43Z","timestamp":1742068303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72904-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031729034","9783031729041"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72904-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}