{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:10:01Z","timestamp":1782828601359,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62201020"],"award-info":[{"award-number":["62201020"]}],"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"}]},{"name":"Chaoyang Postdoctoral Science Foundation","award":["2022ZZ-34"],"award-info":[{"award-number":["2022ZZ-34"]}]},{"DOI":"10.13039\/100000001","name":"U.S. 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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2023.3347971","type":"journal-article","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T19:58:26Z","timestamp":1703793506000},"page":"5400-5413","source":"Crossref","is-referenced-by-count":20,"title":["Attention-Bridged Modal Interaction for Text-to-Image Generation"],"prefix":"10.1109","volume":"34","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\/0000-0001-6124-6328","authenticated-orcid":false,"given":"Kaiqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9290-8445","authenticated-orcid":false,"given":"Huasheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"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\/ICCV.2019.00466"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/9789812797926_0003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref5","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Dhariwal"},{"key":"ref6","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref7","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref8","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Esser"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","article-title":"VSE++: Improved visual-semantic embeddings","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Faghri"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075997"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref16","first-page":"6626","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. (NIPS)","author":"Heusel"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ho"},{"issue":"47","key":"ref19","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref22","first-page":"10236","article-title":"Glow: Generative flow with invertible 1\u00d71x1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Kingma"},{"key":"ref23","first-page":"2063","article-title":"Controllable text-to-image generation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"ref26","article-title":"M6: A Chinese multimodal pretrainer","author":"Lin","year":"2021","journal-title":"arXiv:2103.00823"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref30","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Nichol"},{"key":"ref31","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Nichol"},{"key":"ref32","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Diederik"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"issue":"140","key":"ref35","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref37","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Ramesh"},{"key":"ref38","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Razavi"},{"key":"ref39","first-page":"1060","article-title":"Generative adversarial text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Reed"},{"key":"ref40","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Reed"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref43","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Saharia"},{"key":"ref44","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016","journal-title":"arXiv:1606.03498"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01060"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref49","article-title":"DF-GAN: Deep fusion generative adversarial networks for text-to-image synthesis","volume-title":"arXiv:2008.05865","author":"Tao","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102761"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref59","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/76\/10582818\/10375579-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10375579.pdf?arnumber=10375579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T04:45:07Z","timestamp":1720241107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10375579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":65,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3347971","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}