{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:57:09Z","timestamp":1743130629298,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729034"},{"type":"electronic","value":"9783031729041"}],"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_6","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:27:20Z","timestamp":1732109240000},"page":"93-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Lottery Ticket Hypothesis in\u00a0Denoising: Towards Semantic-Driven Initialization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0907-7522","authenticated-orcid":false,"given":"Jiafeng","family":"Mao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1009-1095","authenticated-orcid":false,"given":"Xueting","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2146-6275","authenticated-orcid":false,"given":"Kiyoharu","family":"Aizawa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: SpaText: spatio-textual representation for controllable image generation. In: CVPR, pp. 18370\u201318380 (2023)","key":"6_CR1","DOI":"10.1109\/CVPR52729.2023.01762"},{"doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR, pp. 18208\u201318218 (2022)","key":"6_CR2","DOI":"10.1109\/CVPR52688.2022.01767"},{"unstructured":"Balaji, Y., et\u00a0al.: eDiffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)","key":"6_CR3"},{"doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402 (2023)","key":"6_CR4","DOI":"10.1109\/CVPR52729.2023.01764"},{"unstructured":"Chen, K., Xie, E., Chen, Z., Hong, L., Li, Z., Yeung, D.Y.: Integrating geometric control into text-to-image diffusion models for high-quality detection data generation via text prompt. arXiv arXiv:2306.04607 (2023)","key":"6_CR5"},{"unstructured":"Cheng, J., Liang, X., Shi, X., He, T., Xiao, T., Li, M.: LayoutDiffuse: adapting foundational diffusion models for layout-to-image generation. arXiv arXiv:2302.08908 (2023)","key":"6_CR6"},{"key":"6_CR7","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. NeurIPS 34, 8780\u20138794 (2021)","journal-title":"NeurIPS"},{"key":"6_CR8","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. NeurIPS 34, 19822\u201319835 (2021)","journal-title":"NeurIPS"},{"unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: ICLR (2023)","key":"6_CR9"},{"unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2018)","key":"6_CR10"},{"doi-asserted-by":"publisher","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. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV, pp. 89\u2013106. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6","key":"6_CR11","DOI":"10.1007\/978-3-031-19784-0_6"},{"unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: ICLR (2023)","key":"6_CR12"},{"key":"6_CR13","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"},{"unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS Workshop (2021)","key":"6_CR14"},{"unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. In: ICML (2023)","key":"6_CR15"},{"doi-asserted-by":"crossref","unstructured":"Jia, C., et al.: SSMG: spatial-semantic map guided diffusion model for free-form layout-to-image generation. arXiv arXiv:2308.10156 (2023)","key":"6_CR16","DOI":"10.1609\/aaai.v38i3.28024"},{"doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","key":"6_CR17","DOI":"10.1109\/CVPR52729.2023.00582"},{"doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: DiffusionCLIP: text-guided diffusion models for robust image manipulation. In: CVPR, pp. 2426\u20132435 (2022)","key":"6_CR18","DOI":"10.1109\/CVPR52688.2022.00246"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR, pp. 22511\u201322521 (2023)","key":"6_CR19","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"6_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"unstructured":"Liu, L., Ren, Y., Lin, Z., Zhao, Z.: Pseudo numerical methods for diffusion models on manifolds. In: ICLR (2022)","key":"6_CR21"},{"doi-asserted-by":"publisher","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, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26","key":"6_CR22","DOI":"10.1007\/978-3-031-19790-1_26"},{"doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, X.: Training-free location-aware text-to-image synthesis. In: ICIP (2023)","key":"6_CR23","DOI":"10.1109\/ICIP49359.2023.10222616"},{"doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, X., Aizawa, K.: Guided image synthesis via initial image editing in diffusion model. In: ACM MM (2023)","key":"6_CR24","DOI":"10.1145\/3581783.3612191"},{"doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv e-prints arXiv:2302.08453 (2023)","key":"6_CR25","DOI":"10.1609\/aaai.v38i5.28226"},{"unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171. PMLR (2021)","key":"6_CR26"},{"unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, pp. 16784\u201316804. PMLR (2022)","key":"6_CR27"},{"unstructured":"Park, D.H., Azadi, S., Liu, X., Darrell, T., Rohrbach, A.: Benchmark for compositional text-to-image synthesis. In: NeurIPS Datasets and Benchmarks Track (Round 1) (2021)","key":"6_CR28"},{"unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)","key":"6_CR29"},{"unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)","key":"6_CR30"},{"unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831. PMLR (2021)","key":"6_CR31"},{"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)","key":"6_CR32","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR33","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"},{"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, pp. 22500\u201322510 (2023)","key":"6_CR34","DOI":"10.1109\/CVPR52729.2023.02155"},{"unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)","key":"6_CR35"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)","key":"6_CR36"},{"doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: SIGGRAPH (2023)","key":"6_CR37","DOI":"10.1145\/3588432.3591560"},{"issue":"3","key":"6_CR38","first-page":"691","volume":"39","author":"CY Wang","year":"2023","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: You only learn one representation: unified network for multiple tasks. J. Inf. Sci. Eng. 39(3), 691\u2013709 (2023)","journal-title":"J. Inf. Sci. Eng."},{"unstructured":"Wang, T., et al.: Pretraining is all you need for image-to-image translation. In: arXiv arXiv:2205.12952 (2022)","key":"6_CR39"},{"doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: BoxDiff: text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7452\u20137461 (2023)","key":"6_CR40","DOI":"10.1109\/ICCV51070.2023.00685"},{"doi-asserted-by":"crossref","unstructured":"Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis. In: CVPR, pp. 14256\u201314266 (2023)","key":"6_CR41","DOI":"10.1109\/CVPR52729.2023.01370"},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: ReCo: region-controlled text-to-image generation. In: CVPR, pp. 14246\u201314255 (2023)","key":"6_CR42","DOI":"10.1109\/CVPR52729.2023.01369"},{"doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","key":"6_CR43","DOI":"10.1109\/ICCV51070.2023.00355"},{"doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: LayoutDiffusion: controllable diffusion model for layout-to-image generation. In: CVPR, pp. 22490\u201322499 (2023)","key":"6_CR44","DOI":"10.1109\/CVPR52729.2023.02154"}],"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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T19:50:37Z","timestamp":1742068237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72904-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031729034","9783031729041"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72904-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}