{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:23:08Z","timestamp":1783056188250,"version":"3.54.6"},"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0509700"],"award-info":[{"award-number":["2024YFF0509700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62371063"],"award-info":[{"award-number":["62371063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62471290"],"award-info":[{"award-number":["62471290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62321001"],"award-info":[{"award-number":["62321001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["L232047"],"award-info":[{"award-number":["L232047"]}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20250810"],"award-info":[{"award-number":["GZB20250810"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2025M783515"],"award-info":[{"award-number":["2025M783515"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"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. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tccn.2026.3705826","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:57:51Z","timestamp":1782158271000},"page":"9247-9262","source":"Crossref","is-referenced-by-count":0,"title":["DiT-JSCC: Rethinking Deep JSCC With Diffusion Transformers and Semantic Representations"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5802-0753","authenticated-orcid":false,"given":"Kailin","family":"Tan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-568X","authenticated-orcid":false,"given":"Jincheng","family":"Dai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sixian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2872-795X","authenticated-orcid":false,"given":"Shuo","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8076-1867","authenticated-orcid":false,"given":"Kai","family":"Niu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-1182","authenticated-orcid":false,"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-104X","authenticated-orcid":false,"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.938080"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2987203"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3090048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3424842"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3304140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3151935"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3288243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3511960"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2208"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref15","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC53906.2023.10304477"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3379244"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3591456"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmlcn.2025.3628535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559158"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref23","first-page":"1","article-title":"PIXART-$\\delta$\n: Fast and controllable image generation with latent consistency models","volume-title":"Proc. ICML Workshop Theor. Found. Found. Models","author":"Chen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref26","article-title":"What matters for representation alignment: Global information or spatial structure?","author":"Singh","year":"2025","journal-title":"arXiv:2512.10794"},{"key":"ref27","first-page":"1","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01697"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-49820-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref35","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.","volume":"30","author":"Heusel"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"1","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref38","first-page":"11517","article-title":"Universal rate-distortion-perception representations for lossy compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref39","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700839"},{"key":"ref42","volume-title":"BPG Image Format","author":"Bellard"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3043399"},{"key":"ref44","first-page":"1","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Careil"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref49","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025","journal-title":"arXiv:2508.10104"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687307\/11304002\/11573817.pdf?arnumber=11573817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:12:54Z","timestamp":1783055574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11573817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tccn.2026.3705826","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}