{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:59:45Z","timestamp":1780761585040,"version":"3.54.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":"publisher","award":["61972012"],"award-info":[{"award-number":["61972012"]}],"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":["62006060"],"award-info":[{"award-number":["62006060"]}],"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":["U2013210"],"award-info":[{"award-number":["U2013210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcsvt.2023.3274228","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T19:05:59Z","timestamp":1683572759000},"page":"7438-7451","source":"Crossref","is-referenced-by-count":22,"title":["Layout-Bridging Text-to-Image Synthesis"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2401-6635","authenticated-orcid":false,"given":"Jiadong","family":"Liang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8117-2696","authenticated-orcid":false,"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-7964","authenticated-orcid":false,"given":"Feng","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"ref5","first-page":"1","article-title":"DF-GAN: Deep fusion generative adversarial networks for text-to-image synthesis","volume-title":"Proc. CVPR","author":"Tao"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref8","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015","journal-title":"arXiv:1508.01991"},{"key":"ref9","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref10","article-title":"Learning layout and style reconfigurable GANs for controllable image synthesis","author":"Sun","year":"2020","journal-title":"arXiv:2003.11571"},{"key":"ref11","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref12","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. ICML","author":"Reed"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00766"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref20","first-page":"887","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","volume-title":"Proc. NIPS","volume":"32","author":"Qiao"},{"key":"ref21","article-title":"Benchmark for compositional text-to-image synthesis","volume-title":"Proc. NeurIPS Datasets Benchmarks Track","author":"Park"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref24","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16305"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01060"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013272"},{"key":"ref29","article-title":"Controllable text-to-image generation","author":"Li","year":"2019","journal-title":"arXiv:1909.07083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533527"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666791"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481540"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref39","article-title":"An image is worth 16 \u2717 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref40","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"arXiv:2102.12092"},{"key":"ref41","article-title":"CogView: Mastering text-to-image generation via transformers","author":"Ding","year":"2021","journal-title":"arXiv:2105.13290"},{"key":"ref42","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref43","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref44","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref52","article-title":"Semantic object accuracy for generative text-to-image synthesis","author":"Hinz","year":"2019","journal-title":"arXiv:1910.13321"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475363"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00687"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"ref56","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref57","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref62","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016","journal-title":"arXiv:1606.03498"},{"key":"ref63","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"Heusel","year":"2017","journal-title":"arXiv:1706.08500"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00280"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3116416"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075997"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10348119\/10121479.pdf?arnumber=10121479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:17:01Z","timestamp":1703035021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10121479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":72,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3274228","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}