{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:10:10Z","timestamp":1760119810190,"version":"build-2065373602"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003453","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500600"],"award-info":[{"award-number":["2022YFB4500600"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202020"],"award-info":[{"award-number":["62202020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012568","2025A1515010454"],"award-info":[{"award-number":["2023A1515012568","2025A1515010454"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3614000","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:40:07Z","timestamp":1759772407000},"page":"6577-6588","source":"Crossref","is-referenced-by-count":0,"title":["Neural Scene Designer: Self-Styled Semantic Image Manipulation"],"prefix":"10.1109","volume":"34","author":[{"given":"Jianman","family":"Lin","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5848-5624","authenticated-orcid":false,"given":"Tianshui","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4733-306X","authenticated-orcid":false,"given":"Chunmei","family":"Qing","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8336-5109","authenticated-orcid":false,"given":"Zhijing","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5544-4544","authenticated-orcid":false,"given":"Shuangping","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Ren","sequence":"additional","affiliation":[{"name":"Digital Industry College, Jimei University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","first-page":"26561","article-title":"Artistic style transfer with internal-external learning and contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02127-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3448248"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02358-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3298560"},{"key":"ref12","first-page":"107604","article-title":"Causal deciphering and inpainting in spatio-temporal dynamics via diffusion model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref17","article-title":"Masked vision and language modeling for multi-modal representation learning","author":"Kwon","year":"2022","journal-title":"arXiv:2208.02131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3299278"},{"key":"ref20","article-title":"Geometry-editable and appearance-preserving object compositon","author":"Lin","year":"2025","journal-title":"arXiv:2505.20914"},{"key":"ref21","article-title":"StyleCrafter: Enhancing stylized text-to-video generation with style adapter","author":"Liu","year":"2023","journal-title":"arXiv:2312.00330"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref24","article-title":"HD-painter: High-resolution and prompt-faithful text-guided image inpainting with diffusion models","author":"Manukyan","year":"2023","journal-title":"arXiv:2312.14091"},{"key":"ref25","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3152624"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann"},{"key":"ref31","article-title":"Measuring style similarity in diffusion models","author":"Somepalli","year":"2024","journal-title":"arXiv:2404.01292"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","article-title":"InstantStyle-plus: Style transfer with content-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2407.00788"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048629"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01755"},{"key":"ref39","article-title":"GODIVA: Generating open-domaIn videos from nAtural descriptions","author":"Wu","year":"2021","journal-title":"arXiv:2104.14806"},{"key":"ref40","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref43","first-page":"1","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681017"},{"journal-title":"IEEE Trans. Multimedia","article-title":"Exploiting temporal audio-visual correlation embedding for audio-driven one-shot talking head animation","author":"Xu","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref50","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv:2304.06790"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_14"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108415"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"ref56","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021","journal-title":"arXiv:2103.10428"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_16"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076310"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11185327.pdf?arnumber=11185327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T17:39:07Z","timestamp":1760117947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3614000","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}