{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T20:57:15Z","timestamp":1767646635625,"version":"3.48.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372452"],"award-info":[{"award-number":["62372452"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3588882","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:07:54Z","timestamp":1753207674000},"page":"12607-12621","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Inserting: Learning Subject Embedding for Semantic-Fidelity Personalized Diffusion Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2364-3346","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"given":"Songlin","family":"Yang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8598-0831","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2763-7832","authenticated-orcid":false,"given":"Jing","family":"Dong","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gal"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/3618342"},{"key":"ref3","first-page":"1","article-title":"Inserting anybody in diffusion models via celeb basis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref4","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","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":"ref7","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref8","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR52729.2023.02155"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TCSVT.2024.3369757"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR52729.2023.00192"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2019.00453"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TCSVT.2021.3136857"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP49357.2023.10094932"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TCSVT.2023.3347971"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1145\/3581783.3611765"},{"key":"ref17","article-title":"Is it possible to backdoor face forgery detection with natural triggers?","author":"Han","year":"2023","journal-title":"arXiv:2401.00414"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1609\/aaai.v38i7.28473"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TCSVT.2023.3348471"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref21","first-page":"6306","article-title":"Neural discrete learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPRW59228.2023.00107"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/978-3-030-86608-2_3"},{"key":"ref24","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref26","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref27","article-title":"NICE: Non-linear independent components estimation","author":"Dinh","year":"2014","journal-title":"arXiv:1410.8516"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1145\/3528223.3530164"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICCV48922.2021.00209"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TPAMI.2023.3345866"},{"key":"ref31","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/3503161.3548282"},{"key":"ref33","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref34","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv:2301.00704"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/CVPR52688.2022.00246"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICME57554.2024.10687566"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR52733.2024.00875"},{"key":"ref38","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022","journal-title":"arXiv:2209.14491"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR52688.2022.01767"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/TCSVT.2023.3286841"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref42","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hertz"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR52729.2023.00585"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1145\/3588432.3591513"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/ICCV51070.2023.01460"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1609\/aaai.v38i7.28565"},{"key":"ref47","article-title":"ViCo: Plug-and-play visual condition for personalized text-to-image generation","author":"Hao","year":"2023","journal-title":"arXiv:2306.00971"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1109\/TPAMI.2022.3181070"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref50","article-title":"PuLID: Pure and lightning ID customization via contrastive alignment","author":"Guo","year":"2024","journal-title":"arXiv:2404.16022"},{"key":"ref51","article-title":"AttnDreamBooth: Towards text-aligned personalized text-to-image generation","author":"Pang","year":"2024","journal-title":"arXiv:2406.05000"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1145\/3588432.3591506"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1145\/3610548.3618173"},{"key":"ref54","article-title":"InstantBooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023","journal-title":"arXiv:2304.03411"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1145\/3592133"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1145\/3610548.3618249"},{"key":"ref57","article-title":"FaceStudio: Put your face everywhere in seconds","author":"Yan","year":"2023","journal-title":"arXiv:2312.02663"},{"key":"ref58","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv:2401.07519"},{"key":"ref59","article-title":"FastComposer: Tuning-free multi-subject image generation with localized attention","author":"Xiao","year":"2023","journal-title":"arXiv:2305.10431"},{"key":"ref60","article-title":"PhotoMaker: Customizing realistic human photos via stacked ID embedding","author":"Li","year":"2023","journal-title":"arXiv:2312.04461"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref64","first-page":"1","article-title":"Progressive growing of gans for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Karras"},{"key":"ref65","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref66","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"doi-asserted-by":"publisher","key":"ref67","DOI":"10.1109\/ICCV48922.2021.00951"},{"doi-asserted-by":"publisher","key":"ref68","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref69","article-title":"DisEnvisioner: Disentangled and enriched visual prompt for customized image generation","author":"He","year":"2024","journal-title":"arXiv:2410.02067"},{"key":"ref70","article-title":"An image is worth multiple words: Multi-attribute inversion for constrained text-to-image synthesis","author":"Agarwal","year":"2023","journal-title":"arXiv:2311.11919"},{"key":"ref71","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref72","article-title":"MetaMorph: Multimodal understanding and generation via instruction tuning","author":"Tong","year":"2024","journal-title":"arXiv:2412.14164"},{"key":"ref73","article-title":"Enhancing MMDiT-based text-to-image models for similar subject generation","author":"Wei","year":"2024","journal-title":"arXiv:2411.18301"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11087639.pdf?arnumber=11087639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:00Z","timestamp":1767638460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11087639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":73,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3588882","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}