{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:50:07Z","timestamp":1743094207703,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755998"},{"type":"electronic","value":"9789819756001"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5600-1_27","type":"book-chapter","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T15:03:47Z","timestamp":1722265427000},"page":"312-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoupling Control in Text-to-Image Diffusion Models"],"prefix":"10.1007","author":[{"given":"Shitong","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,30]]},"reference":[{"key":"27_CR1","unstructured":"Shi, J., Wu, C., Liang, J., Liu, X., Duan, N.: DiVAE: photorealistic images synthesis with denoising diffusion decoder. arXiv preprint arXiv:2206.00386 (2022)"},{"key":"27_CR2","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":"27_CR3","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":"27_CR4","doi-asserted-by":"crossref","unstructured":"Liu, V., Chilton, L.B.: Design guidelines for prompt engineering text-to-image generative models. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201323 (2022)","DOI":"10.1145\/3491102.3501825"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Pavlichenko, N., Ustalov, D.: Best prompts for text-to-image models and how to find them. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2067\u20132071 (2023)","DOI":"10.1145\/3539618.3592000"},{"key":"27_CR6","unstructured":"Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: International Conference on Machine Learning, pp. 4114\u20134124. PMLR (2019)"},{"issue":"8","key":"27_CR7","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR8","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":"27_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"27_CR10","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 preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Tov, O., Mokady, R., Gal, R., Bermano, A.: HyperStyle: StyleGAN inversion with hyper networks for real image editing. In: Proceedings of the IEEE\/CVF conference on computer Vision and pattern recognition, pp. 18511\u201318521 (2022)","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Dinh, T.M., Tran, A.T., Nguyen, R., Hua, B.S.: HyperInverter: improving StyleGAN inversion via hyper network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11389\u201311398 (2022)","DOI":"10.1109\/CVPR52688.2022.01110"},{"key":"27_CR13","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)"},{"key":"27_CR14","unstructured":"Stickland, A.C., Murray, I.: BERT and PALs: projected attention layers for efficient adaptation in multi-task learning. In: International Conference on Machine Learning, pp. 5986\u20135995. PMLR (2019)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Mallya, A., Davis, D., Lazebnik, S.: Piggyback: adapting a single network to multiple tasks by learning to mask weights. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 67\u201382 (2018)","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"27_CR16","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR17","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"key":"27_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR19","unstructured":"Liu, Y., et al.: ROBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Wu, J., Koh, I., Tang, Y., Sun, L.: Image synthesis from layout with locality aware mask adaption. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13819\u201313828 (2021)","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"27_CR21","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, pp. 8584\u20138593 (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"27_CR22","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: European Conference on Computer Vision, pp. 89\u2013106. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1511\u20131520 (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5600-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T06:06:07Z","timestamp":1727417167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5600-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755998","9789819756001"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5600-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}