{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T04:51:58Z","timestamp":1778647918970,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangdong Major Project of Basic and Applied Basic Research","award":["2023B0303000016"],"award-info":[{"award-number":["2023B0303000016"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372440"],"award-info":[{"award-number":["62372440"]}],"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":["U25A20477"],"award-info":[{"award-number":["U25A20477"]}],"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":["62206268"],"award-info":[{"award-number":["62206268"]}],"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":["62376261"],"award-info":[{"award-number":["62376261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Technology Project","award":["2023TX07Z126"],"award-info":[{"award-number":["2023TX07Z126"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515012957"],"award-info":[{"award-number":["2025A1515012957"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011754"],"award-info":[{"award-number":["2024A1515011754"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813154723031"],"award-info":[{"award-number":["JCYJ20240813154723031"]}]},{"name":"Shenzhen Technology Project","award":["GJHZ20240218112504008"],"award-info":[{"award-number":["GJHZ20240218112504008"]}]},{"name":"Shenzhen High-Tech Zone Development Special Plan Innovation Platform Construction Project"},{"name":"Proof of Concept Center for High Precision and High Resolution 4D Imaging"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3639218","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:25:50Z","timestamp":1764613550000},"page":"4609-4621","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion-Based Text-Guided Image Generation With Fine-Grained Spatial Object-Attribute Relationships"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-4486","authenticated-orcid":false,"given":"Fuxiang","family":"Wu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8128-2788","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1490-2235","authenticated-orcid":false,"given":"Fusheng","family":"Hao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7940-294X","authenticated-orcid":false,"given":"Ziliang","family":"Ren","sequence":"additional","affiliation":[{"name":"Dongguan University of Technology, Dongguan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6130-7821","authenticated-orcid":false,"given":"Xinyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-3275","authenticated-orcid":false,"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00087"},{"key":"ref10","article-title":"DiffBlender: Composable and versatile multimodal text-to-image diffusion models","author":"Kim","year":"2023","journal-title":"arXiv:2305.15194"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00444"},{"key":"ref13","article-title":"UniControl: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arXiv:2305.11147"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.398"},{"key":"ref19","article-title":"Don\u2019t stop learning: Towards continual learning for the CLIP model","author":"Ding","year":"2022","journal-title":"arXiv:2207.09248"},{"key":"ref20","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref21","first-page":"1681","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3256798"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367876"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3338459"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02504"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3589002"},{"key":"ref31","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Oord"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref33","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref34","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ding"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01758"},{"key":"ref38","first-page":"27196","article-title":"UFC-BERT: Unifying multi-modal controls for conditional image synthesis","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478561"},{"key":"ref40","article-title":"ERNIE-ViLG: Unified generative pre-training for bidirectional vision-language generation","author":"Zhang","year":"2021","journal-title":"arXiv:2112.15283"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01603"},{"key":"ref42","article-title":"NUWA-infinity: Autoregressive over autoregressive generation for infinite visual synthesis","author":"Wu","year":"2022","journal-title":"arXiv:2207.09814"},{"key":"ref43","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Esser"},{"key":"ref44","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref45","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref46","article-title":"Improved vector quantized diffusion models","author":"Tang","year":"2022","journal-title":"arXiv:2205.16007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref48","first-page":"23412","article-title":"MoVQ: Modulating quantized vectors for high-fidelity image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zheng"},{"key":"ref49","first-page":"1","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508844"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref54","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"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00367"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295094"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238554"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref65","first-page":"1","article-title":"R&B: Region and boundary aware zero-shot grounded text-to-image generation","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Xiao"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref67","first-page":"14940","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Tan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3545040"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02664"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356492"},{"key":"ref72","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol"},{"key":"ref73","first-page":"1","article-title":"Making text-to-image diffusion models zero-shot image-to-image editors by inferring \u2019random seeds","volume-title":"Proc. NeurIPS Workshop Score-Based Methods","author":"Wu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref75","first-page":"1","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25379"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref78","first-page":"85","article-title":"COCOAttributes: Attributes for people, animals, and objects","volume-title":"Proc. ECCV","author":"Patterson"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref81","first-page":"6626","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":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00390"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11271708.pdf?arnumber=11271708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:48:35Z","timestamp":1775764115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":83,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3639218","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}