{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:05:21Z","timestamp":1790111121055,"version":"4.0.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109412","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:24:42Z","timestamp":1784388282000},"page":"109412","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["Zero-shot cross-domain image composition via self attention injection"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8772-7875","authenticated-orcid":false,"given":"Xiangrui","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Si","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianming","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1648-0227","authenticated-orcid":false,"given":"Haijun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109412_bib0001","series-title":"Special interest group on computer graphics and interactive techniques (ACM SIGGRAPH)","first-page":"1","article-title":"Cross-image attention for zero-shot appearance transfer","author":"Alaluf","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0002","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18208","article-title":"Blended diffusion for text-driven editing of natural images","author":"Avrahami","year":"2022"},{"key":"10.1016\/j.neunet.2026.109412_bib0003","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18521","article-title":"Deep image-based illumination harmonization","author":"Bao","year":"2022"},{"issue":"4","key":"10.1016\/j.neunet.2026.109412_bib0004","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1145\/245.247","article-title":"A multiresolution spline with application to image mosaics","volume":"2","author":"Burt","year":"1983","journal-title":"ACM Trans on Graphics (TOG)"},{"key":"10.1016\/j.neunet.2026.109412_bib0005","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"22503","article-title":"Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0006","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"6593","article-title":"AnyDoor: Zero-shot object-level image customization","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0007","series-title":"European conferenceon computer vision (ECCV)","first-page":"70","article-title":"FreeCompose: Generic zero-shot image composition with diffusion prior","author":"Chen","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0008","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"8795","article-title":"Style injection in diffusion: A training-free approach for adapting large-scale diffusion models for style transfer","author":"Chung","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0009","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"DoveNet: Deep image harmonization via domain verification","author":"Cong","year":"2020"},{"key":"10.1016\/j.neunet.2026.109412_bib0010","series-title":"Neural information processing systems (NIPS)","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021"},{"key":"10.1016\/j.neunet.2026.109412_bib0011","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","first-page":"2969","article-title":"Dit4edit: Diffusion transformer for image editing","volume":"vol. 39","author":"Feng","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0012","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"key":"10.1016\/j.neunet.2026.109412_bib0013","article-title":"Multi-scale spatial diffusion under frequency information-guidance for low-light image enhancement","volume":"196","author":"Guan","year":"2026","journal-title":"Neural Networks (NN)"},{"key":"10.1016\/j.neunet.2026.109412_bib0014","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"1947","article-title":"StyleBooth: Image style editing with multimodal instruction","author":"Han","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0015","series-title":"International conference on learning representations (ICLR)","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0016","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"4775","article-title":"Style aligned image generation via shared attention","author":"Hertz","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0017","series-title":"Neural information processing systems (NIPS)","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"vol. 33","author":"Ho","year":"2020"},{"key":"10.1016\/j.neunet.2026.109412_bib0018","series-title":"NeurIPS 2021 workshop on deep generative models and downstream applications (NIPS workshop)","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021"},{"key":"10.1016\/j.neunet.2026.109412_bib0019","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"1510","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109412_bib0020","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","first-page":"3958","article-title":"DesignEdit: Unify spatial-aware image editing via training-free inpainting with a multi-layered latent diffusion framework","volume":"vol. 39","author":"Jia","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0021","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"1931","article-title":"Multi-concept customization of text-to-image diffusion","author":"Kumari","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0022","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"16840","article-title":"AIComposer: Any style and content image composition via feature integration","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0023","series-title":"European conference on computer vision (ECCV)","article-title":"Tuning-free image customization with image and text guidance","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0024","series-title":"ACM international conference on multimedia (ACM MM)","first-page":"7464","article-title":"FreePIH: Training-free painterly image harmonization with diffusion model","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0025","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"ST-GAN: Spatial transformer generative adversarial networks for image compositing","author":"Lin","year":"2018"},{"key":"10.1016\/j.neunet.2026.109412_bib0026","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"7817","article-title":"Towards understanding cross and self-attention in stable diffusion for text-guided image editing","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0027","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"2294","article-title":"TF-ICON: Diffusion-based training-free cross-domain image composition","author":"Lu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0028","series-title":"IEEE\/CVF winter conference on applications of computer vision (WACV)","first-page":"2063","article-title":"Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models","author":"Miyake","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0029","series-title":"IEEE international conference on computer vision (ICCV)","article-title":"Zero-shot depth-aware image editing with diffusion models","author":"Parihar","year":"2025"},{"issue":"3","key":"10.1016\/j.neunet.2026.109412_bib0030","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1145\/882262.882269","article-title":"Poisson image editing","volume":"22","author":"P\u00e9rez","year":"2003","journal-title":"ACM Trans on Graphics (TOG)"},{"key":"10.1016\/j.neunet.2026.109412_bib0031","series-title":"ACM international conference on multimedia (ACM MM)","first-page":"3160","article-title":"TALE: Training-free cross-domain image composition via adaptive latent manipulation and energy-guided optimization","author":"Pham","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0032","series-title":"International conference on learning representations (ICLR)","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0033","series-title":"International conference on machine learning (ICML)","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"5","key":"10.1016\/j.neunet.2026.109412_bib0034","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/38.946629","article-title":"Color transfer between images","volume":"21","author":"Reinhard","year":"2001","journal-title":"IEEE Computer Graphics and Applications (CGA)"},{"key":"10.1016\/j.neunet.2026.109412_bib0035","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109412_bib0036","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"22500","article-title":"DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0037","series-title":"European conferenceon computer vision (ECCV)","first-page":"422","article-title":"ZiploRA: Any subject in any style by effectively merging loRAs","author":"Shah","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0038","series-title":"IEEE international conference on computer vision (ICCV)","first-page":"19492","article-title":"Exploring multimodal diffusion transformers for enhanced prompt-based image editing","author":"Shin","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0039","series-title":"Neural information processing systems (NIPS)","first-page":"66860","article-title":"StyleDrop: Text-to-image synthesis of any style","volume":"vol. 36","author":"Sohn","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0040","series-title":"European conferenceon computer vision (ECCV)","first-page":"143","article-title":"Investigating style similarity in diffusion models","author":"Somepalli","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0041","series-title":"International conference on learning representations (ICLR)","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.109412_bib0042","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18310","article-title":"ObjectStitch: Object compositing with diffusion model","author":"Song","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0043","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"2799","article-title":"Deep image harmonization","author":"Tsai","year":"2017"},{"key":"10.1016\/j.neunet.2026.109412_bib0044","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"1921","article-title":"Plug-and-play diffusion features for text-driven image-to-image translation","author":"Tumanyan","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0045","series-title":"ACM international conference on multimedia (ACM MM)","first-page":"10824","article-title":"PrimeComposer: Faster progressively combined diffusion for image composition with attention steering","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109412_bib0046","series-title":"ACM international conference on multimedia (ACM MM)","first-page":"2487","article-title":"GP-GAN: Towards realistic high-resolution image blending","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109412_bib0047","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18381","article-title":"Paint by example: Exemplar-based image editing with diffusion models","author":"Yang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109412_bib0048","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"26125","article-title":"AnyEdit: Mastering unified high-quality image editing for any idea","author":"Yu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109412_bib0049","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"issue":"2","key":"10.1016\/j.neunet.2026.109412_bib0050","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1109\/TPAMI.2024.3487361","article-title":"Noise self-regression: A new learning paradigm to enhance low-light images without task-related data","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2026.109412_bib0051","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"1889","article-title":"Deep color consistent network for low-light image enhancement","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109412_bib0052","article-title":"Cut-and-paste: Subject-driven video editing with attention control","volume":"181","author":"Zuo","year":"2025","journal-title":"Neural Networks (NN)"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008701?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008701?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:06:59Z","timestamp":1790107619000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":52,"alternative-id":["S0893608026008701"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109412","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Zero-shot cross-domain image composition via self attention injection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109412","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109412"}}