{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:20:37Z","timestamp":1776529237655,"version":"3.51.2"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Project of Liaoning Province","award":["2021JH2\/10300064"],"award-info":[{"award-number":["2021JH2\/10300064"]}]},{"name":"Youth Science and Technology Star Support Program of Dalian City","award":["2021RQ057"],"award-info":[{"award-number":["2021RQ057"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92167110"],"award-info":[{"award-number":["92167110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT22YG241"],"award-info":[{"award-number":["DUT22YG241"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3297769","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T17:34:52Z","timestamp":1689960892000},"page":"8323-8332","source":"Crossref","is-referenced-by-count":20,"title":["Multi-Sentence Complementarily Generation for Text-to-Image Synthesis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6706-2271","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Software Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3140-429X","authenticated-orcid":false,"given":"Pingda","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-3146","authenticated-orcid":false,"given":"Tengtuo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Reliability and Systems Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2494-7092","authenticated-orcid":false,"given":"Chunjiang","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Software Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0450-632X","authenticated-orcid":false,"given":"Qinghao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5085-0949","authenticated-orcid":false,"given":"Yangqianhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.741"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref4","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref5","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gregor","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.02.020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.01.023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"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":"10.1109\/CVPR.2019.00160"},{"key":"ref18","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref19","article-title":"ChatPainter: Improving text to image generation using dialogue","volume-title":"Proc. Int. Conf. Learn. Representations: Workshop","author":"Sharma","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00044"},{"key":"ref21","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Devlin","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104284"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-823519-5.00004-X"},{"key":"ref25","first-page":"2","article-title":"Deep contextualized word representations for detecting sarcasm and irony","volume-title":"WASSA","author":"Ili","year":"2018"},{"key":"ref26","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref31","article-title":"CalTech-UCSD birds 200","author":"Welinder","year":"2010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"ref35","first-page":"6629","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref37","first-page":"160","article-title":"DAC-GAN: Dual auxiliary consistency generative adversarial network for text-to-image generation","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Wang","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3217384"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98358-1_4"},{"key":"ref40","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10190148.pdf?arnumber=10190148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T07:55:47Z","timestamp":1722585347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10190148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3297769","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}