{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:17:49Z","timestamp":1782317869450,"version":"3.54.5"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730269","type":"print"},{"value":"9783031730276","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"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\/978-3-031-73027-6_21","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:54:15Z","timestamp":1732557255000},"page":"363-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LogoSticker: Inserting Logos Into Diffusion Models for\u00a0Customized Generation"],"prefix":"10.1007","author":[{"given":"Mingkang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongdao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"21_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. arXiv:2305.16311 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"21_CR2","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/openai.com\/dall-e-3"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser-2: unleashing the power of language models for text rendering. arXiv:2311.16465 (2023)","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"21_CR5","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser: diffusion models as text painters. In: NeurIPS (2023)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. arXiv:2203.13131 (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"21_CR8","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021)","DOI":"10.23915\/distill.00030"},{"key":"21_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"21_CR11","unstructured":"Huang, Z., Wu, T., Jiang, Y., Chan, K.C.K., Liu, Z.: Reversion: diffusion-based relation inversion from images. arXiv:2303.13495 (2023)"},{"key":"21_CR12","unstructured":"Joshi, S., Yang, Y., Xue, Y., Yang, W., Mirzasoleiman, B.: Towards mitigating spurious correlations in the wild: a benchmark and a more realistic dataset. arXiv:2306.11957 (2023)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. arXiv:2303.05511 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"21_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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"21_CR15","unstructured":"Liu, Z., et al.: Cones 2: customizable image synthesis with multiple subjects. arXiv:2305.19327 (2023)"},{"key":"21_CR16","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. arXiv:2211.09794 (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"21_CR17","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741 (2022)"},{"key":"21_CR18","unstructured":"OpenAI: GPT-4 technical report. arXiv:2303.08774 (2023)"},{"key":"21_CR19","unstructured":"von Platen, P., et al.: Diffusers: state-of-the-art diffusion models (2022). https:\/\/github.com\/huggingface\/diffusers"},{"key":"21_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"issue":"140","key":"21_CR21","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21(140), 1\u201367 (2020)","journal-title":"JMLR"},{"key":"21_CR22","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 (2022)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. arXiv:2112.10752 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. arXiv:1505.04597 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21_CR25","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"21_CR26","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Sarukkai, V., Li, L., Ma, A., R\u00e9, C., Fatahalian, K.: Collage diffusion. arXiv:2303.00262 (2023)","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"21_CR28","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: Stylegan-t: unlocking the power of GANs for fast large-scale text-to-image synthesis. arXiv:2301.09515 (2023)"},{"key":"21_CR29","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv:2111.02114 (2021)"},{"key":"21_CR30","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. arXiv:1503.03585 (2015)"},{"key":"21_CR31","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"21_CR32","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"21_CR33","unstructured":"Tuo, Y., Xiang, W., He, J.Y., Geng, Y., Xie, X.: Anytext: multilingual visual text generation and editing. arXiv:2311.03054 (2024)"},{"key":"21_CR34","unstructured":"Yang, Y., et al.: Glyphcontrol: glyph conditional controllable visual text generation. In: NeurIPS (2023)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"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\/978-3-031-73027-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T18:15:12Z","timestamp":1732558512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73027-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"ISBN":["9783031730269","9783031730276"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73027-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"26 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"}}]}}