{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:11:55Z","timestamp":1780675915936,"version":"3.54.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CBET-2115405"],"award-info":[{"award-number":["CBET-2115405"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2021ZD0111900"],"award-info":[{"award-number":["2021ZD0111900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201020"],"award-info":[{"award-number":["62201020"]}],"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":["61976040"],"award-info":[{"award-number":["61976040"]}],"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":["62272082"],"award-info":[{"award-number":["62272082"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20220025"],"award-info":[{"award-number":["BX20220025"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M700303"],"award-info":[{"award-number":["2021M700303"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005024","name":"Beijing Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022-ZZ-069"],"award-info":[{"award-number":["2022-ZZ-069"]}],"id":[{"id":"10.13039\/501100005024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3238554","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T18:48:25Z","timestamp":1674240505000},"page":"8620-8631","source":"Crossref","is-referenced-by-count":30,"title":["ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6915-8736","authenticated-orcid":false,"given":"Hongchen","family":"Tan","sequence":"first","affiliation":[{"name":"Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7228-5322","authenticated-orcid":false,"given":"Kun","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1712-6083","authenticated-orcid":false,"given":"Xiuping","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-9489","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Section of Visual Computing and Creative Media, School of Performance, Visualization, and Fine Arts, Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"ref3","first-page":"1","article-title":"VSE++: Improved visual-semantic embeddings","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref4","first-page":"17","article-title":"Leveraging visual question answering to improve text-to-image synthesis","volume-title":"Proc. 2nd Workshop Beyond Vis. Lang.: Integrating Real-world Knowl.","author":"Frolov","year":"2020"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2856256"},{"key":"ref8","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.","author":"Heusel","year":"2017"},{"key":"ref9","first-page":"1","article-title":"Generating multiple objects at spatially distinct locations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hinz","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref13","first-page":"2063","article-title":"Controllable text-to-image generation","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref17","first-page":"3950","article-title":"PasteGAN: A semi-parametric method to generate image from scene graph","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref20","first-page":"740","article-title":"Microsoft coco: Common objects in context","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Tsung","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413505"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390684"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3116416"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref26","first-page":"1060","article-title":"Generative adversarial text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref28","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref29","first-page":"1","article-title":"ChatPainter: Improving text to image generation using dialogue","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Sharma","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3078577"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"ref33","first-page":"842","article-title":"Spectral normalization for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026728"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3165573"},{"key":"ref38","first-page":"16494","article-title":"DF-GAN: Deep fusion generative adversarial networks for Text-to-image synthesis","author":"Tao","year":"2022","journal-title":"CVPR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_18"},{"key":"ref40","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00384"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/10016790\/10023990-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10023990.pdf?arnumber=10023990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:04:14Z","timestamp":1703030654000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3238554","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}