{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:57:29Z","timestamp":1784300249264,"version":"3.55.0"},"reference-count":62,"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":"National Key Research and Development Project","award":["2020AAA0106200"],"award-info":[{"award-number":["2020AAA0106200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936005"],"award-info":[{"award-number":["61936005"]}],"id":[{"id":"10.13039\/501100001809","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.2023.3278992","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T18:34:35Z","timestamp":1684866875000},"page":"1255-1266","source":"Crossref","is-referenced-by-count":16,"title":["Semantic Distance Adversarial Learning for Text-to-Image Synthesis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8051-3070","authenticated-orcid":false,"given":"Bowen","family":"Yuan","sequence":"first","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2547-4646","authenticated-orcid":false,"given":"Yefei","family":"Sheng","sequence":"additional","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4122-3767","authenticated-orcid":false,"given":"Yi-Ping Phoebe","family":"Chen","sequence":"additional","affiliation":[{"name":"La Trobe University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref6","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref7","first-page":"195","article-title":"Augmented cycleGAN: Learning many-to-many mappings from unpaired data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Almahairi","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref9","article-title":"Cycle text-to-image GAN with BERT","author":"Tsue","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102761"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01240-1"},{"key":"ref13","article-title":"Generating informative and diverse conversational responses via adversarial information maximization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2018"},{"key":"ref14","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Reed","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09185-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026728"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","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":"ref30","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref32","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref33","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref38","article-title":"Upainting: Unified text-to-image diffusion generation with cross-modal guidance","author":"Li","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.085"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref43","first-page":"7476","article-title":"Adversarial mutual information for text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pan"},{"key":"ref44","first-page":"154","article-title":"Improving text-to-image synthesis using contrastive learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Ye","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref50","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref51","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref53","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref57","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01091"},{"issue":"8","key":"ref60","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref61","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10132043.pdf?arnumber=10132043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:48:39Z","timestamp":1705690119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3278992","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}