{"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":1775578649311,"version":"3.50.1"},"reference-count":57,"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":"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20487"],"award-info":[{"award-number":["U21A20487"]}],"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":["U1913202"],"award-info":[{"award-number":["U1913202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Australian Research Council Project","award":["DP-180103424"],"award-info":[{"award-number":["DP-180103424"]}]},{"name":"National Natural Science Foundation of Guangdong Province","award":["2022A1515140119"],"award-info":[{"award-number":["2022A1515140119"]}]},{"name":"Shenzhen Technology Project","award":["JCYJ20200109113416531"],"award-info":[{"award-number":["JCYJ20200109113416531"]}]},{"name":"Shenzhen Technology Project","award":["JCYJ20220818101206014"],"award-info":[{"award-number":["JCYJ20220818101206014"]}]},{"DOI":"10.13039\/501100012658","name":"3D Digital Media Technology Engineering Laboratory","doi-asserted-by":"publisher","award":["[2017]476"],"award-info":[{"award-number":["[2017]476"]}],"id":[{"id":"10.13039\/501100012658","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAS Key Technology Talent Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3256798","type":"journal-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T17:35:42Z","timestamp":1678815342000},"page":"8279-8293","source":"Crossref","is-referenced-by-count":2,"title":["InDecGAN: Learning to Generate Complex Images From Captions via Independent Object-Level Decomposition and Enhancement"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-3275","authenticated-orcid":false,"given":"Jun","family":"Cheng","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-4486","authenticated-orcid":false,"given":"Fuxiang","family":"Wu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, 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":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6358-1840","authenticated-orcid":false,"given":"Qieshi","family":"Zhang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6960-9525","authenticated-orcid":false,"given":"Leszek","family":"Rutkowski","sequence":"additional","affiliation":[{"name":"Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5979-578X","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1681","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref3","article-title":"Chatpainter: Improving text to image generation using dialogue","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Sharma","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00687"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240559"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2824816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503927"},{"key":"ref11","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121987"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105725"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3147425"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2100"},{"key":"ref18","first-page":"491","article-title":"CPGAN: Full-spectrum content-parsing generative adversarial networks for text-to-image synthesis","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liang","year":"2020"},{"key":"ref19","article-title":"Generating multiple objects at spatially distinct locations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hinz","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref22","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref23","first-page":"3294","article-title":"Skip-thought vectors","volume-title":"Proc. Adv. Neural Inf. Process. System","author":"Kiros","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2774007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00044"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2979258"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00432"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_29"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00839"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01300-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref37","first-page":"885","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qiao","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102761"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"ref40","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref41","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bahdanau","year":"2015"},{"key":"ref42","first-page":"224","article-title":"Generalization and equilibrium in generative adversarial nets (GANs)","volume-title":"Proc. 34th Int. Conf. Mach. Learn.-Volume","author":"Arora","year":"2017"},{"key":"ref43","article-title":"On the discrimination-generalization tradeoff in GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref44","article-title":"Spectral norm regularization for improving the generalizability of deep learning","author":"Yoshida","year":"2017"},{"key":"ref45","article-title":"Spectral normalization for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00813"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3005574"},{"key":"ref49","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref50","article-title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","author":"Ding","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475363"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","article-title":"A note on the inception score","author":"Barratt","year":"2018"},{"key":"ref55","first-page":"2234","article-title":"Improved techniques for training gans","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref57","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10068791.pdf?arnumber=10068791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:03:21Z","timestamp":1703030601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10068791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3256798","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}