{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:13:50Z","timestamp":1783491230108,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Program of Hubei Provincial Natural Science Foundation of China","award":["JCZRMS202600468"],"award-info":[{"award-number":["JCZRMS202600468"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3697647","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:09:12Z","timestamp":1780430952000},"page":"7149-7164","source":"Crossref","is-referenced-by-count":0,"title":["MaPPA: Multimodal Controllable Person Image Generation With Pose and Appearance Guidance"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9037-9391","authenticated-orcid":false,"given":"Yuran","family":"Dong","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daiguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xiaomi Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1434-7021","authenticated-orcid":false,"given":"Qingxiong","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computer Science and the Institute for Math and AI, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3329358"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref3","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref4","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3559995"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02081"},{"key":"ref11","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref14","article-title":"Humandiffusion: A coarse-to-fine alignment diffusion framework for controllable text-driven person image generation","author":"Zhang","year":"2022","journal-title":"arXiv:2211.06235"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref20","first-page":"406","article-title":"Pose guided person image generation","volume-title":"Proc. NeurIPS","volume":"30","author":"Ma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00923"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00381"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01066"},{"key":"ref31","article-title":"Style and pose control for image synthesis of humans from a single monocular view","author":"Sarkar","year":"2021","journal-title":"arXiv:2102.11263"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01130"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00530"},{"key":"ref38","article-title":"Optimizing id consistency in multimodal large models: Facial restoration via alignment, entanglement, and disentanglement","author":"Dong","year":"2026","journal-title":"arXiv:2602.18752"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01468"},{"key":"ref40","article-title":"Cross-view masked diffusion transformers for person image synthesis","author":"Pham","year":"2024","journal-title":"arXiv:2402.01516"},{"key":"ref41","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","author":"Shen","year":"2023","journal-title":"arXiv:2310.06313"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33032"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3820046"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00451"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref46","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref48","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref49","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv:2408.12528"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref51","article-title":"Multi-modal pose diffuser: A multimodal generative conditional pose prior","author":"Ta","year":"2024","journal-title":"arXiv:2410.14540"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02676"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref54","article-title":"Multimodal elbo with diffusion decoders","author":"Wesego","year":"2024","journal-title":"arXiv:2408.16883"},{"key":"ref55","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. ICML","author":"Sohl-Dickstein"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref57","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. ICML","author":"Nichol"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref60","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Proc. TMLR","author":"Oquab"},{"key":"ref61","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_10"},{"key":"ref66","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0202"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01493"},{"key":"ref70","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NeurIPS","volume":"30","author":"Heusel"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00134"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2098"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11547889.pdf?arnumber=11547889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:23:05Z","timestamp":1783488185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11547889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3697647","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}