{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:29Z","timestamp":1775578649703,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1205001"],"award-info":[{"award-number":["2023YFF1205001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222209"],"award-info":[{"award-number":["62222209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250008"],"award-info":[{"award-number":["62250008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102222"],"award-info":[{"award-number":["62102222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","award":["BNR2023RC01003"],"award-info":[{"award-number":["BNR2023RC01003"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","award":["BNR2023TD03006"],"award-info":[{"award-number":["BNR2023TD03006"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Laboratory of Networked Multimedia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3369757","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T20:14:25Z","timestamp":1708978465000},"page":"6860-6873","source":"Crossref","is-referenced-by-count":41,"title":["DisenDreamer: Subject-Driven Text-to-Image Generation With Sample-Aware Disentangled Tuning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0943-2286","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0886-8296","authenticated-orcid":false,"given":"Yipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9108-9618","authenticated-orcid":false,"given":"Xuguang","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9582-7331","authenticated-orcid":false,"given":"Yuwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref4","article-title":"InstructPix2Pix: Learning to follow image editing instructions","author":"Brooks","year":"2022","journal-title":"arXiv:2211.09800"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref6","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv:2301.00704"},{"key":"ref7","first-page":"26924","article-title":"Curriculum disentangled recommendation with noisy multi-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref8","article-title":"Subject-driven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023","journal-title":"arXiv:2304.00186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3240024"},{"key":"ref10","article-title":"DreamArtist: Towards controllable one-shot text-to-image generation via positive-negative prompt-tuning","author":"Dong","year":"2022","journal-title":"arXiv:2211.11337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref12","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref14","first-page":"1294","article-title":"Image-to-image translation for cross-domain disentanglement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Gonzalez-Garcia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref16","first-page":"1","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"He"},{"key":"ref17","first-page":"1","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref19","first-page":"1","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1041"},{"key":"ref21","article-title":"Imagic: Text-based real image editing with diffusion models","author":"Kawar","year":"2022","journal-title":"arXiv:2210.09276"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref23","article-title":"Towards safe self-distillation of internet-scale text-to-image diffusion models","author":"Kim","year":"2023","journal-title":"arXiv:2307.05977"},{"key":"ref24","article-title":"Multi-concept customization of Text-to-Image diffusion","author":"Kumari","year":"2022","journal-title":"arXiv:2212.04488"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref26","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Locatello"},{"key":"ref27","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref28","first-page":"5712","article-title":"Learning disentangled representations for recommendation","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref30","article-title":"Unified multi-modal latent diffusion for joint subject and text conditional image generation","author":"Ma","year":"2023","journal-title":"arXiv:2303.09319"},{"key":"ref31","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref32","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"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref34","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref35","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref39","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref40","article-title":"InstantBooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023","journal-title":"arXiv:2304.03411"},{"key":"ref41","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref42","article-title":"Disentangled representation learning","author":"Wang","year":"2022","journal-title":"arXiv:2211.11695"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428193"},{"key":"ref44","first-page":"36174","article-title":"Curriculum co-disentangled representation learning across multiple environments for social recommendation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02065"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10445245.pdf?arnumber=10445245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:11:26Z","timestamp":1723525886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":52,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3369757","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}