{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:29:20Z","timestamp":1768408160653,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557394","type":"print"},{"value":"9789819557400","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5740-0_37","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:23:10Z","timestamp":1768220590000},"page":"536-549","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to\u00a0Combine Latent Basis for\u00a0Diffusion-Based Image Attribute Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5919-620X","authenticated-orcid":false,"given":"Qingyang","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3627-0681","authenticated-orcid":false,"given":"Haonan","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"issue":"4","key":"37_CR1","first-page":"1","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM TOG 42(4), 1\u201311 (2023)","journal-title":"Blended latent diffusion. ACM TOG"},{"key":"37_CR2","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":"37_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. NeurIPS 33, 1877\u20131901 (2020)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: Diverse image synthesis for multiple domains. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Dekel, T., Gan, C., Krishnan, D., Liu, C., Freeman, W.T.: Sparse, smart contours to represent and edit images. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00370"},{"key":"37_CR6","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Dong, W., Xue, S., Duan, X., Han, S.: Prompt tuning inversion for text-driven image editing using diffusion models. CoRR abs\/2305.04441 (2023)","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"37_CR9","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. NeurIPS 30 (2017)"},{"key":"37_CR10","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":"Denoising diffusion probabilistic models. NeurIPS"},{"key":"37_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. CoRR abs\/2207.12598 (2022)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"37_CR13","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. CoRR abs\/1710.10196 (2017)"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: Diffusionclip: text-guided diffusion models for robust image manipulation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"37_CR15","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. CoRR abs\/2210.10960 (2022)"},{"key":"37_CR16","unstructured":"Lyu, Y., Zhao, K., Peng, B., Jiang, Y., Zhang, Y., Dong, J.: Deltaspace: a semantic-aligned feature space for flexible text-guided image editing. CoRR abs\/2310.08785 (2023)"},{"key":"37_CR17","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. CoRR abs\/2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"37_CR18","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR abs\/1807.03748 (2018)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"37_CR20","unstructured":"Park, Y.H., Kwon, M., Choi, J., Jo, J., Uh, Y.: Understanding the latent space of diffusion models through the lens of riemannian geometry. NeurIPS 36 (2024)"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"37_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Shi, J., Xu, N., Zheng, H., Smith, A., Luo, J., Xu, C.: Spaceedit: learning a unified editing space for open-domain image color editing. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01911"},{"key":"37_CR24","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. CoRR abs\/2010.02502 (2020)"},{"key":"37_CR25","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. CoRR abs\/2011.13456 (2020)"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Uncovering the disentanglement capability in text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Yang, S., Jiang, L., Liu, Z., Loy, C.C.: Styleganex: stylegan-based manipulation beyond cropped aligned faces. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21000\u201321010 (2023)","DOI":"10.1109\/ICCV51070.2023.01920"},{"key":"37_CR28","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. CoRR abs\/1506.03365 (2015)"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Yu, Y., et al.: Towards counterfactual image manipulation via clip. In: ACM MM (2022)","DOI":"10.1145\/3503161.3547935"},{"key":"37_CR30","unstructured":"Yue, D., Guo, Q., Ning, M., Cui, J., Zhu, Y., Yuan, L.: Chatface: chat-guided real face editing via diffusion latent space manipulation. CoRR abs\/2305.14742 (2023)"},{"key":"37_CR31","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: Magicbrush: A manually annotated dataset for instruction-guided image editing. NeurIPS 36 (2024)"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"37_CR33","unstructured":"Zhu, Y., Wu, Y., Deng, Z., Russakovsky, O., Yan, Y.: Boundary guided learning-free semantic control with diffusion models. NeurIPS 36 (2024)"},{"key":"37_CR34","unstructured":"Zuo, Z., et al.: Generative image inpainting with segmentation confusion adversarial training and contrastive learning. CoRR abs\/2303.13133 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5740-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:23:39Z","timestamp":1768220619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5740-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557394","9789819557400"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5740-0_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}