{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:08:47Z","timestamp":1780517327453,"version":"3.54.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"name":"Guangdong Science and Technology Programme","award":["2024B0101030002"],"award-info":[{"award-number":["2024B0101030002"]}]},{"name":"Basic Research of Hetao Shenzhen-HK Science and Technology Cooperation Zone","award":["HZQB-KCZYZ-2021067"],"award-info":[{"award-number":["HZQB-KCZYZ-2021067"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293482"],"award-info":[{"award-number":["62293482"]}],"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":["62471423"],"award-info":[{"award-number":["62471423"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20241202124021028"],"award-info":[{"award-number":["JCYJ20241202124021028"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20230807114204010"],"award-info":[{"award-number":["JCYJ20230807114204010"]}]},{"name":"Guangdong Special Support Program","award":["2024TQ08X346"],"award-info":[{"award-number":["2024TQ08X346"]}]},{"name":"Shenzhen Outstanding Talents Training","award":["202002"],"award-info":[{"award-number":["202002"]}]},{"name":"Young Elite Scientists Sponsorship Program of CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"name":"Guangdong Provincial Key Laboratory of Future Networks of Intelligence","award":["2022B1212010001"],"award-info":[{"award-number":["2022B1212010001"]}]},{"name":"Shenzhen Key Laboratory of Big Data and Artificial Intelligence","award":["SYSPG20241211173853027"],"award-info":[{"award-number":["SYSPG20241211173853027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/jsac.2025.3644826","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:46:53Z","timestamp":1765997213000},"page":"2750-2764","source":"Crossref","is-referenced-by-count":0,"title":["Live High-Fidelity Semantic Communication via Cross-Modal Fusion for Volumetric Video"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4818-3091","authenticated-orcid":false,"given":"Tianyi","family":"Gong","sequence":"first","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) and the School of Science and Engineering (SSE), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7887-5432","authenticated-orcid":false,"given":"Zijian","family":"Cao","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) and the School of Science and Engineering (SSE), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9015-8907","authenticated-orcid":false,"given":"Zhicheng","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) and the School of Science and Engineering (SSE), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7944-0198","authenticated-orcid":false,"given":"Dayou","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-045X","authenticated-orcid":false,"given":"Fangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering (SSE), Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen), and Guangdong Provincial Key Laboratory of Future Networks of Intelligence, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) and the School of Science and Engineering (SSE), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221999"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3266656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icc52391.2025.11161787"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3429295"},{"key":"ref6","article-title":"Generative semantic communication: Diffusion models beyond bit recovery","author":"Grassucci","year":"2023","journal-title":"arXiv:2306.04321"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2500084"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3564543"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3535714"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.12.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.511"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.11316"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2987203"},{"key":"ref18","first-page":"3879","article-title":"Deep joint source-channel coding with iterative source error correction","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lee"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DASC\/PiCom\/CBDCom\/Cy55231.2022.9927900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS56560.2022.9940401"},{"key":"ref21","article-title":"Promptus: Can prompts streaming replace video streaming with stable diffusion","author":"Wu","year":"2024","journal-title":"arXiv:2405.20032"},{"key":"ref22","article-title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv:2410.13848"},{"key":"ref23","first-page":"69925","article-title":"VisionLLM v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref24","article-title":"Show-O: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv:2408.12528"},{"key":"ref25","article-title":"DreamLLM: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023","journal-title":"arXiv:2309.11499"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref28","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref29","article-title":"Planting a SEED of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv:2307.08041"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref33","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref34","article-title":"UniTok: A unified tokenizer for visual generation and understanding","author":"Ma","year":"2025","journal-title":"arXiv:2502.20321"},{"key":"ref35","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"ref38","article-title":"MV-DUSt3R$: Single-stage scene reconstruction from sparse views in 2 seconds","author":"Tang","year":"2024","journal-title":"arXiv:2412.06974"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/0470869615"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref42","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref45","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv:2312.17090"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref47","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mentzer"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/49\/11372474\/11301851.pdf?arnumber=11301851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:42:00Z","timestamp":1780515720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11301851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/jsac.2025.3644826","relation":{},"ISSN":["1558-0008","0733-8716"],"issn-type":[{"value":"1558-0008","type":"electronic"},{"value":"0733-8716","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}