{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T05:13:06Z","timestamp":1778303586009,"version":"3.51.4"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62006240"],"award-info":[{"award-number":["62006240"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s13042-025-02935-z","type":"journal-article","created":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T11:38:49Z","timestamp":1772278729000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cdmm: learning a conditional diffusion model from multi-single images"],"prefix":"10.1007","volume":"17","author":[{"given":"Xianjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"key":"2935_CR1","doi-asserted-by":"crossref","unstructured":"Abdal R, Qin Y, Wonka P (2019) Image2stylegan: How to embed images into the stylegan latent space? In: IEEE International Conference on Computer Vision (ICCV), pp. 4431\u20134440","DOI":"10.1109\/ICCV.2019.00453"},{"key":"2935_CR2","unstructured":"Bao F, Nie S, Xue K, Li C, Pu S, Wang Y, Yue G, Cao Y, Su H, Zhu J (2023) One transformer fits all distributions in multi-modal diffusion at scale. In: International Conference on Machine Learning, vol. 202, p. 1692\u20131717"},{"key":"2935_CR3","unstructured":"Benaim S, Wolf L (2018) One-shot unsupervised cross domain translation. In: Advances in Neural Information Processing Systems, vol.\u00a031, p. 2108\u20132118"},{"issue":"4","key":"2935_CR4","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1109\/TSMC.2023.3331227","volume":"54","author":"J Chen","year":"2024","unstructured":"Chen J, Xu Q, Kang Q, Zhou M (2024) Mogan: morphologic-structure-aware generative learning from a single image. IEEE Trans Syst Man Cybern Syst 54(4):2021\u20132033","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"2935_CR5","doi-asserted-by":"crossref","unstructured":"Chen X, Zhao H, Yang D, Li Y, Kang Q, Lu H (2021) Sa-singan: self-attention for single-image generation adversarial networks. Mach. Vision Appl. 32(4)","DOI":"10.1007\/s00138-021-01228-z"},{"key":"2935_CR6","doi-asserted-by":"crossref","unstructured":"Chong MJ, Forsyth D (2022) Jojogan: One shot face stylization. In: European Conference on Computer Vision, p. 128\u2013152","DOI":"10.1007\/978-3-031-19787-1_8"},{"key":"2935_CR7","doi-asserted-by":"crossref","unstructured":"Cohen T, Wolf L (2019) Bidirectional one-shot unsupervised domain mapping. In: IEEE International Conference on Computer Vision (ICCV), pp. 1784\u20131792","DOI":"10.1109\/ICCV.2019.00187"},{"key":"2935_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal P, Nichol A (2021) Diffusion models beat gans on image synthesis. Adv Neural Inform Process Syst 34:8780\u20138794","journal-title":"Adv Neural Inform Process Syst"},{"key":"2935_CR9","unstructured":"Gal R, Alaluf Y, Atzmon Y, Patashnik O, Bermano AH, Chechik G, Cohen-or D (2023) An image is worth one word: Personalizing text-to-image generation using textual inversion. In: International Conference on Learning Representations"},{"key":"2935_CR10","first-page":"2672","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. Adv Neural Inform Process Syst 27:2672\u20132680","journal-title":"Adv Neural Inform Process Syst"},{"issue":"4","key":"2935_CR11","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1007\/s40747-022-00924-1","volume":"9","author":"Y Gou","year":"2023","unstructured":"Gou Y, Li M, Song Y, He Y, Wang L (2023) Multi-feature contrastive learning for unpaired image-to-image translation. Complex Intell Syst 9(4):4111\u20134122","journal-title":"Complex Intell Syst"},{"key":"2935_CR12","doi-asserted-by":"crossref","unstructured":"Granot N, Feinstein B, Shocher A, Bagon S, Irani M (2022) Drop the gan: In defense of patches nearest neighbors as single image generative models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13450\u201313459","DOI":"10.1109\/CVPR52688.2022.01310"},{"key":"2935_CR13","first-page":"16761","volume":"33","author":"S Gur","year":"2020","unstructured":"Gur S, Benaim S, Wolf L (2020) Hierarchical patch vae-gan: generating diverse videos from a single sample. Adv Neural Inform Process Syst 33:16761\u201316772","journal-title":"Adv Neural Inform Process Syst"},{"key":"2935_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2935_CR15","doi-asserted-by":"crossref","unstructured":"Hinz T, Fisher M, Wang O, Wermter S (2021) Improved techniques for training single-image gans. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1300\u20131309","DOI":"10.1109\/WACV48630.2021.00134"},{"key":"2935_CR16","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inform Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inform Process Syst"},{"key":"2935_CR17","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4396\u20134405","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2935_CR18","doi-asserted-by":"crossref","unstructured":"Kim G, Kwon T, Ye JC (2022) Diffusionclip: Text-guided diffusion models for robust image manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2416\u20132425","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"2935_CR19","unstructured":"Kulikov V, Yadin S, Kleiner M, Michaeli T (2023) Sinddm: A single image denoising diffusion model. International Conference on Machine Learning 202:17920\u201317930"},{"key":"2935_CR20","doi-asserted-by":"crossref","unstructured":"Li B, Xue K, Liu B, Lai YK (2023) Bbdm: Image-to-image translation with brownian bridge diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1952\u20131961","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"2935_CR21","doi-asserted-by":"crossref","unstructured":"Lin J, Pang Y, Xia Y, Chen Z, Luo J (2020) Tuigan: Learning versatile image-to-image translation with two unpaired images. In: European Conference on Computer Vision, p. 18\u201335","DOI":"10.1007\/978-3-030-58548-8_2"},{"key":"2935_CR22","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S A (2022)convnet for the 2020s. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11966\u201311976","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2935_CR23","doi-asserted-by":"crossref","unstructured":"Lugmayr A, Danelljan M, Romero A, Yu F, Timofte R, Gool LV (2022) Repaint: Inpainting using denoising diffusion probabilistic models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11451\u201311461","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2935_CR24","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784"},{"key":"2935_CR25","unstructured":"Nichol AQ, Dhariwal P (2021) Improved denoising diffusion probabilistic models. International Conference on Machine Learning 139:8162\u20138171"},{"key":"2935_CR26","unstructured":"Nichol AQ, Dhariwal P, Ramesh A, Shyam P, Mishkin P, Mcgrew B, Sutskever I, Chen M (2022) GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. International Conference on Machine Learning 162:16784\u201316804"},{"key":"2935_CR27","unstructured":"Nikankin Y, Haim N, Irani M (2023) Sinfusion: Training diffusion models on a single image or video. International Conference on Machine Learning 202:26199\u201326214"},{"issue":"6","key":"2935_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417826","volume":"39","author":"Y Nitzan","year":"2020","unstructured":"Nitzan Y, Bermano A, Li Y, Cohen-Or D (2020) Face identity disentanglement via latent space mapping. ACM Trans Graph 39(6):1\u201314","journal-title":"ACM Trans Graph"},{"issue":"11","key":"2935_CR29","doi-asserted-by":"publisher","first-page":"7474","DOI":"10.1109\/TPAMI.2021.3115428","volume":"44","author":"X Pan","year":"2022","unstructured":"Pan X, Zhan X, Dai B, Lin D, Loy CC, Luo P (2022) Exploiting deep generative prior for versatile image restoration and manipulation. IEEE Trans Pattern Anal Mach Intell 44(11):7474\u20137489","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2935_CR30","doi-asserted-by":"crossref","unstructured":"Park T, Efros AA, Zhang R, Zhu JY (2020) Contrastive learning for unpaired image-to-image translation. In: European Conference on Computer Vision, p. 319\u2013345","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"2935_CR31","doi-asserted-by":"crossref","unstructured":"Preechakul K, Chatthee N, Wizadwongsa S, Suwajanakorn S (2022) Diffusion autoencoders: Toward a meaningful and decodable representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10619\u201310629","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"2935_CR32","first-page":"97766","volume":"37","author":"H Qiyuan","year":"2024","unstructured":"Qiyuan H, Wang J, Liu Z, Yao A (2024) Aid: attention interpolation of text-to-image diffusion. Adv Neural Inform Process Syst 37:97766\u201397799","journal-title":"Adv Neural Inform Process Syst"},{"key":"2935_CR33","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. International Conference on Machine Learning 139:8748\u20138763"},{"key":"2935_CR34","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2935_CR35","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T(2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015, pp. 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2935_CR36","doi-asserted-by":"crossref","unstructured":"Rouhsedaghat M, Monajatipoor M, Kuo CCJ, Masi I (2023) Magic: mask-guided image synthesis by inverting a quasi-robust classifier. Proceedings of the AAAI Conference on Artificial Intelligence 37:2172\u20132179","DOI":"10.1609\/aaai.v37i2.25311"},{"key":"2935_CR37","doi-asserted-by":"crossref","unstructured":"Saharia C, Chan W, Chang H, Lee C, Ho J, Salimans T, Fleet D, Norouzi M(2022) Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310","DOI":"10.1145\/3528233.3530757"},{"issue":"4","key":"2935_CR38","first-page":"4713","volume":"45","author":"C Saharia","year":"2023","unstructured":"Saharia C, Ho J, Chan W, Salimans T, Fleet DJ, Norouzi M (2023) Image super-resolution via iterative refinement. IEEE Trans Pattern Anal Mach Intell 45(4):4713\u20134726","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2935_CR39","unstructured":"Sauer A, Karras T, Laine S, Geiger A, Aila T (2023) StyleGAN-t: Unlocking the power of GANs for fast large-scale text-to-image synthesis. International Conference on Machine Learning 202:30105\u201330118"},{"key":"2935_CR40","doi-asserted-by":"crossref","unstructured":"Shaham TR, Dekel T, Michaeli T (2019) Singan: Learning a generative model from a single natural image. In: IEEE International Conference on Computer Vision (ICCV), pp. 4569\u20134579","DOI":"10.1109\/ICCV.2019.00467"},{"issue":"3","key":"2935_CR41","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1145\/325165.325242","volume":"19","author":"K Shoemake","year":"1985","unstructured":"Shoemake K (1985) Animating rotation with quaternion curves. SIGGRAPH Comput Graph 19(3):245\u2013254","journal-title":"SIGGRAPH Comput Graph"},{"key":"2935_CR42","first-page":"3483","volume":"28","author":"K Sohn","year":"2015","unstructured":"Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. Adv Neural Inform Process Syst 28:3483\u20133491","journal-title":"Adv Neural Inform Process Syst"},{"key":"2935_CR43","unstructured":"Song J, Meng C, Ermon S (2021) Denoising diffusion implicit models. In: International Conference on Learning Representations"},{"key":"2935_CR44","doi-asserted-by":"crossref","unstructured":"Vinker Y, Horwitz E, Zabari N, Hoshen, Y (2021) Image shape manipulation from a single augmented training sample. In: IEEE International Conference on Computer Vision (ICCV), pp. 13749\u201313758","DOI":"10.1109\/ICCV48922.2021.01351"},{"key":"2935_CR45","unstructured":"Wang CJ, Golland P (2023) Interpolating between images with diffusion models. In: International Conference on Machine Learning Workshop, pp. 1\u201310"},{"key":"2935_CR46","unstructured":"Wang W, Bao J, Zhou W, Chen D, Chen D, Yuan L, Li H (2022) Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050"},{"issue":"5","key":"2935_CR47","doi-asserted-by":"publisher","first-page":"3412","DOI":"10.1109\/TPAMI.2025.3532956","volume":"47","author":"W Wang","year":"2025","unstructured":"Wang W, Bao J, Zhou W, Chen D, Chen D, Yuan L, Li H (2025) Sindiffusion: learning a diffusion model from a single natural image. IEEE Trans Pattern Anal Mach Intell 47(5):3412\u20133423","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"2935_CR48","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1109\/TPAMI.2022.3181070","volume":"45","author":"W Xia","year":"2023","unstructured":"Xia W, Zhang Y, Yang Y, Xue JH, Zhou B, Yang MH (2023) Gan inversion: a survey. IEEE Trans Pattern Anal Mach Intell 45(3):3121\u20133138","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2935_CR49","unstructured":"Yang R, Gamper H, Braun S (2023) Cmmd: Contrastive multi-modal diffusion for video-audio conditional modeling. arXiv preprint arXiv:2312.05412"},{"key":"2935_CR50","unstructured":"Yang Z, Yu Z, Xu Z, Singh J, Zhang J, Campbell D, Tu P, Hartley R (2024) Impus: Image morphing with perceptually-uniform sampling using diffusion models. In: International Conference on Learning Representations"},{"key":"2935_CR51","doi-asserted-by":"crossref","unstructured":"Zhang K, Zhou Y, Xu X, Dai B, Pan X (2024) Diffmorpher: Unleashing the capability of diffusion models for image morphing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7912\u20137921","DOI":"10.1109\/CVPR52733.2024.00756"},{"key":"2935_CR52","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2935_CR53","doi-asserted-by":"publisher","first-page":"111840","DOI":"10.1016\/j.engappai.2025.111840","volume":"160","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Xiao Y, Zhang Y, Zhang T (2025) Video saliency prediction via single feature enhancement and temporal recurrence. Eng Appl Artif Intell 160:111840","journal-title":"Eng Appl Artif Intell"},{"key":"2935_CR54","doi-asserted-by":"publisher","first-page":"109806","DOI":"10.1016\/j.engappai.2024.109806","volume":"141","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Zhang T, Wang S, Yu P (2025) An efficient perceptual video compression scheme based on deep learning-assisted video saliency and just noticeable distortion. Eng Appl Artif Intell 141:109806","journal-title":"Eng Appl Artif Intell"},{"key":"2935_CR55","doi-asserted-by":"publisher","first-page":"128564","DOI":"10.1016\/j.eswa.2025.128564","volume":"292","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Zhang Y, Xiao Y, Wang T (2025) Spatiotemporal dual-branch feature-guided fusion network for driver attention prediction. Expert Syst Appl 292:128564","journal-title":"Expert Syst Appl"},{"key":"2935_CR56","doi-asserted-by":"crossref","unstructured":"Zhang Z. Han C, Guo T (2021) Exsingan: learning an explainable generative model from a single image. In: British Machine Vision Conference, pp. 1\u201314","DOI":"10.5244\/C.35.97"},{"issue":"6","key":"2935_CR57","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2018","unstructured":"Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba A (2018) Places: a 10 million image database for scene recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1452\u20131464","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02935-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02935-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02935-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:55:25Z","timestamp":1778302525000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02935-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2935"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02935-z","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]},"assertion":[{"value":"24 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"143"}}