{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:25Z","timestamp":1761898045880,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031728969"},{"type":"electronic","value":"9783031728976"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72897-6_3","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:36:39Z","timestamp":1733088999000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Text-to-Sticker: Style Tailoring Latent Diffusion Models for\u00a0Human Expression"],"prefix":"10.1007","author":[{"given":"Animesh","family":"Sinha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anmol","family":"Kalia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arantxa","family":"Casanova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elliot","family":"Blanchard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Winnie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Nelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hardik","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitesh Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankit","family":"Ramchandani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maziar","family":"Sanjabi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonal","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amy","family":"Bearman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhruv","family":"Mahajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"3_CR1","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 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"3_CR2","unstructured":"Balaji, Y., et al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers (2023)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"3_CR5","unstructured":"Casanova, A., Careil, M., Verbeek, J., Drozdzal, M., Romero-Soriano, A.: Instance-conditioned GAN. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"3_CR6","unstructured":"Chen, L., et\u00a0al.: Photoverse: tuning-free image customization with text-to-image diffusion models (2023)"},{"key":"3_CR7","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models (2022)"},{"key":"3_CR8","unstructured":"Dai, X., et al.: EMU: enhancing image generation models using photogenic needles in a haystack (2023)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR10","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis (2021)"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618. https:\/\/arxiv.org\/abs\/2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"3_CR12","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium (2018)"},{"key":"3_CR13","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Kim, S.W., et al.: Neuralfield-LDM: scene generation with hierarchical latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8496\u20138506 (2023)","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3_CR17","unstructured":"Lee, K., et al.: Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192 (2023)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: AVA: a large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2408\u20132415. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"3_CR19","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"3_CR20","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"3_CR21","unstructured":"Pressman, J.D., Crowson, K., Contributors, S.C.: Simulacra aesthetic captions (2023)"},{"key":"3_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"3_CR23","unstructured":"Rae, J.W., et\u00a0al.: Scaling language models: methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)"},{"key":"3_CR24","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"3_CR25","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"3_CR26","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"3_CR28","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 (CVPR), pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: Hyperdreambooth: hypernetworks for fast personalization of text-to-image models (2023)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"3_CR30","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)"},{"key":"3_CR31","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs (2016)"},{"key":"3_CR32","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=TIdIXIpzhoI"},{"key":"3_CR33","unstructured":"Sheynin, S., et al.: KNN-diffusion: image generation via large-scale retrieval (2022)"},{"key":"3_CR34","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, Lille, France, vol.\u00a037, pp. 2256\u20132265. PMLR (2015). https:\/\/proceedings.mlr.press\/v37\/sohl-dickstein15.html"},{"key":"3_CR35","unstructured":"Sohn, K., et al.: Styledrop: text-to-image generation in any style (2023)"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Takagi, Y., Nishimoto, S.: High-resolution image reconstruction with latent diffusion models from human brain activity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14453\u201314463 (2023)","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"3_CR38","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"3_CR39","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. arXiv preprint arXiv:2303.14420 (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"3_CR40","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.: Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00878"}],"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\/978-3-031-72897-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:17:33Z","timestamp":1733095053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72897-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031728969","9783031728976"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72897-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}