{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:52Z","timestamp":1775578612352,"version":"3.50.1"},"reference-count":74,"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 R&D Program of China","award":["2022YFC2009903\/2022YFC2009900"],"award-info":[{"award-number":["2022YFC2009903\/2022YFC2009900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61872064"],"award-info":[{"award-number":["61872064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004806","name":"Fok Ying Tong Education Foundation","doi-asserted-by":"publisher","award":["171106"],"award-info":[{"award-number":["171106"]}],"id":[{"id":"10.13039\/501100004806","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SongShan Laboratory","award":["YYJC012022019"],"award-info":[{"award-number":["YYJC012022019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3295094","type":"journal-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:48:03Z","timestamp":1689616083000},"page":"2354-2366","source":"Crossref","is-referenced-by-count":7,"title":["Utilizing Greedy Nature for Multimodal Conditional Image Synthesis in Transformers"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7406-116X","authenticated-orcid":false,"given":"Sitong","family":"Su","sequence":"first","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3872-6689","authenticated-orcid":false,"given":"Junchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Neurology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186752"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01673-x"},{"key":"ref4","article-title":"Semantic image synthesis with semantically coupled vq-model","volume-title":"Proc. ICLR Workshop Deep Generative Models Highly Structured Data","author":"Alaniz","year":"2022"},{"key":"ref5","article-title":"Semantic image synthesis via diffusion models","author":"Wang","year":"2022"},{"key":"ref6","article-title":"Learning to predict layout-to-image conditional convolutions for semantic image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506651"},{"key":"ref9","article-title":"Interactive image generation using scene graphs","volume-title":"Proc. Deep Generative Models Highly Structured Data Workshop","author":"Mittal","year":"2019"},{"key":"ref10","article-title":"MIGS: Meta image generation from scene graphs","volume-title":"Proc. Brit. Mach. Vis. Conf.,","author":"Farshad","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2705122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123431"},{"key":"ref16","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":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","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":"ref20","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref21","first-page":"16 784","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":"ref22","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238554"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3160360"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref30","first-page":"27196","article-title":"UFC-BERT: Unifying multi-modal controls for conditional image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_6"},{"key":"ref32","article-title":"Image generation with multimodal priors using denoising diffusion probabilistic models","author":"Nair","year":"2022"},{"key":"ref33","article-title":"Rubi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cadene","year":"2019"},{"key":"ref34","first-page":"3197","article-title":"Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gat","year":"2020"},{"key":"ref35","article-title":"On modality bias in the TVQA dataset","volume-title":"Proc. Brit. Mach. Vis. Conf.,","author":"Winterbottom","year":"2020"},{"key":"ref36","article-title":"Improving multi-modal learning with uni-modal teachers","author":"Du","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref38","first-page":"24043","article-title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2022"},{"key":"ref39","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2022"},{"key":"ref40","first-page":"23 318","article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref43","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref44","article-title":"Ernie-vilg: Unified generative pre-training for bidirectional vision-language generation","author":"Zhang","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01603"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481540"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref48","first-page":"18433","article-title":"The image local autoregressive transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3187290"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548180"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/224"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3235495"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3246796"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3243659"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3211197"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164190"},{"key":"ref59","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2020"},{"key":"ref60","article-title":"CATER: A diagnostic dataset for compositional actions & temporal reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Girdhar","year":"2020"},{"key":"ref61","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01281"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00094"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00656"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01594"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref71","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":"ref72","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10184483.pdf?arnumber=10184483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:25:02Z","timestamp":1707251102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10184483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3295094","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}