{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:31:01Z","timestamp":1768293061137,"version":"3.49.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government (MSIT)","award":["2021-0-01341"],"award-info":[{"award-number":["2021-0-01341"]}]},{"name":"Korea Research Institute for Defense Technology Planning and Advancement through the Defense Innovation Vanguard Enterprise Project"},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration","doi-asserted-by":"publisher","award":["R230106"],"award-info":[{"award-number":["R230106"]}],"id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Field-Oriented Technology Development Project for Customs Administration through the National Research Foundation of Korea"},{"name":"Ministry of Science & ICT and Korea Customs Service","award":["2021M3I1A1097911"],"award-info":[{"award-number":["2021M3I1A1097911"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3477734","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T13:25:48Z","timestamp":1728566748000},"page":"186454-186465","source":"Crossref","is-referenced-by-count":2,"title":["Generating Diverse Image Variations With Diffusion Models by Combining Intra-Image Self-Attention and Decoupled Cross-Attention"],"prefix":"10.1109","volume":"12","author":[{"given":"Dasol","family":"Jeong","sequence":"first","affiliation":[{"name":"Department of Image, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6959-1361","authenticated-orcid":false,"given":"Donggoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Image, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwon","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8593-7155","authenticated-orcid":false,"given":"Joonki","family":"Paik","sequence":"additional","affiliation":[{"name":"Department of Image, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"arXiv:2011.13456","author":"Song","year":"2020"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref3","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"arXiv:2112.10741","author":"Nichol","year":"2021"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume-title":"arXiv:2204.06125","author":"Ramesh","year":"2022"},{"key":"ref5","article-title":"Investigating prompt engineering in diffusion models","volume-title":"arXiv:2211.15462","author":"Witteveen","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref7","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","volume-title":"arXiv:2308.06721","author":"Ye","year":"2023"},{"key":"ref8","first-page":"1","article-title":"Real-world image variation by aligning diffusion inversion chain","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref9","article-title":"Video-P2P: Video editing with cross-attention control","volume-title":"arXiv:2303.04761","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref17","first-page":"1","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/buildings14061528"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-53318-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/buildings13071861"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3347745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.11.049"},{"key":"ref25","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"arXiv:2208.01626","author":"Hertz","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref27","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Epstein"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3450842"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref31","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv:2108.01073","author":"Meng","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref33","first-page":"1","article-title":"Noisediffusion: Correcting noise for image interpolation with diffusion models beyond spherical linear interpolation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zheng"},{"key":"ref34","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv:2307.01952","author":"Podell","year":"2023"},{"key":"ref35","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"arXiv:2301.00704","author":"Chang","year":"2023"},{"key":"ref36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref38","article-title":"Denoising diffusion implicit models","volume-title":"arXiv:2010.02502","author":"Song","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref41","article-title":"Classifier-free diffusion guidance","volume-title":"arXiv:2207.12598","author":"Ho","year":"2022"},{"key":"ref42","volume-title":"Experiments With Stable Diffusion","author":"Pinkney"},{"key":"ref43","volume-title":"Controlnet 1.1 Shuffle"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref46","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref48","volume-title":"Kandinsky 2.2","author":"Shakhmatov","year":"2023"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10713367.pdf?arnumber=10713367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:05:36Z","timestamp":1761588336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10713367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3477734","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}