{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:13:42Z","timestamp":1778530422299,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"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":["2018YFB1802004"],"award-info":[{"award-number":["2018YFB1802004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B08038"],"award-info":[{"award-number":["B08038"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,5,15]]},"DOI":"10.1109\/jiot.2026.3669716","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:57:02Z","timestamp":1772485022000},"page":"22130-22148","source":"Crossref","is-referenced-by-count":0,"title":["MSET: Multimodal Semantic-Enhanced Real-World Beam Prediction via Temporal Modeling With Visual Foundation Models"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9944-1862","authenticated-orcid":false,"given":"Feixiang","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0589-3712","authenticated-orcid":false,"given":"Xiaohui","family":"Li","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4852-9265","authenticated-orcid":false,"given":"Wenhui","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Xiong","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0571-2571","authenticated-orcid":false,"given":"Guanchong","family":"Niu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7702-2369","authenticated-orcid":false,"given":"Chung Shue","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Machine Learning and Systems, Nokia Bell Labs, Massy, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3383093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3556091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3274175"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3088264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3319354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-015-0942-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3045084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2831697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3361991"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2973859"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2907119"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2730878"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2713357"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2449860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3275613"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3541104"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2025.3548021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2024-Spring62846.2024.10683225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3506948"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops50388.2021.9473733"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3506283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.006.2200730"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3280966"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops57953.2023.10283602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3509453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3573711"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511414"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2016.7905941"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2523924"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3003670"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9129369"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3107526"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2014.2334278"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.011714.130846"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2748938"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2773532"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3372060"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3390611"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.018.2100713"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3219409"},{"key":"ref44","article-title":"Multi-modal beam prediction challenge 2022: Towards generalization","author":"Charan","year":"2022","journal-title":"arXiv:2209.07519"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180803"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3213541"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771564"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3401686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3405859"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM61039.2024.10773747"},{"key":"ref52","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning? (Provably)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref53","volume-title":"Ultralytics YOLO11","author":"Jocher","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref55","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14289"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771835"},{"key":"ref59","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13132656"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3420455"},{"key":"ref62","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref63","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3142513"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2024.3431790"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11513275\/11418645.pdf?arnumber=11418645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:49:17Z","timestamp":1778528957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11418645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":67,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3669716","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]}}}