{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:46:24Z","timestamp":1793205984242,"version":"4.5.0"},"reference-count":71,"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":"Zhejiang Basic Public Welfare Research Program","award":["LGG22F020027"],"award-info":[{"award-number":["LGG22F020027"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFC3604003"],"award-info":[{"award-number":["2023YFC3604003"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFE0114900"],"award-info":[{"award-number":["2023YFE0114900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3358086","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:40:49Z","timestamp":1706121649000},"page":"6956-6967","source":"Crossref","is-referenced-by-count":18,"title":["DMF-GAN: Deep Multimodal Fusion Generative Adversarial Networks for Text-to-Image Synthesis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0585-0579","authenticated-orcid":false,"given":"Bing","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqin","family":"Xiang","sequence":"additional","affiliation":[{"name":"Rokid, Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0113-6968","authenticated-orcid":false,"given":"Wangzeng","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1727-7463","authenticated-orcid":false,"given":"Jianhai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1208-972X","authenticated-orcid":false,"given":"Yong","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1345"},{"key":"ref2","article-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref4","article-title":"SegAttnGAN: Text to image generation with segmentation attention","author":"Gou","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref6","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref9","first-page":"887","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref11","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref15","first-page":"38","article-title":"Evaluating human aesthetic and emotional aspects of 3D generated content through extended reality","author":"Stacchio","year":"2023","journal-title":"Proc. AI*IA, Workshop Artif. Intell. Creativity"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia53811.2021.9641929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533527"},{"key":"ref21","first-page":"22020","article-title":"Lightweight generative adversarial networks for text-guided image manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00391"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102237"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00350"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"ref31","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.374"},{"key":"ref33","first-page":"2912","article-title":"Parallel multiscale autoregressive density estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref39","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","year":"2021"},{"key":"ref40","article-title":"M6: A Chinese multimodal pretrainer","author":"Lin","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.08.038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2023.9010023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3297769"},{"key":"ref44","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","volume":"1","author":"Devlin","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01368"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref47","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref48","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3266607"},{"key":"ref53","first-page":"1","article-title":"Mogrifier LSTM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Melis","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref56","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird","year":"2009"},{"key":"ref57","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans","year":"2016"},{"key":"ref60","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.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238554"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"ref64","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref65","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16305"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10413630.pdf?arnumber=10413630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:52:36Z","timestamp":1714762356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3358086","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}