{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:05:17Z","timestamp":1784041517157,"version":"3.55.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62471036"],"award-info":[{"award-number":["62471036"]}],"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":["U223320067"],"award-info":[{"award-number":["U223320067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022YQ62"],"award-info":[{"award-number":["ZR2022YQ62"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242011"],"award-info":[{"award-number":["L242011"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["YQ24167"],"award-info":[{"award-number":["YQ24167"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tvt.2025.3595688","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:44:52Z","timestamp":1754333092000},"page":"1701-1706","source":"Crossref","is-referenced-by-count":12,"title":["Generative Video Semantic Communication via Multimodal Semantic Fusion With Large Model"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2065-7239","authenticated-orcid":false,"given":"Hang","family":"Yin","sequence":"first","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0586-189X","authenticated-orcid":false,"given":"Li","family":"Qiao","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8303-6486","authenticated-orcid":false,"given":"Yu","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8221-6324","authenticated-orcid":false,"given":"Shuo","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3528-4739","authenticated-orcid":false,"given":"Kan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2709-0216","authenticated-orcid":false,"given":"Zhen","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3219363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2200157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.34133\/space.0176"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3460084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1986.1057145"},{"key":"ref8","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2923676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref11","first-page":"4006","article-title":"Adversarial feature matching for text generation","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Zhang","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3288243"},{"key":"ref13","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref14","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734812"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3429295"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP62071.2024.10827256"},{"key":"ref19","article-title":"${\\mathrm{I}}^{2}$VC: A unified framework for intra- & inter-frame video compression","author":"Liu","year":"2024"},{"key":"ref20","volume-title":"Digital Communications","author":"Proakis","year":"2008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180802"},{"key":"ref25","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref26","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref27","article-title":"Open-Sora","year":"2024"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Careil","year":"2023"},{"key":"ref30","article-title":"Text $+$ Sketch: Image compression at ultra low rates","volume-title":"Proc. Workshop Neural Compression, Inf. Theory Appl.","author":"Lei","year":"2023"},{"key":"ref31","article-title":"Semantic feature decomposition based semantic communication system of images with large-scale visual generation models","author":"Fan","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3515874"},{"key":"ref33","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Zhang","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/11358811\/11112664.pdf?arnumber=11112664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:39:56Z","timestamp":1768941596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11112664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2025.3595688","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}