{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:38:43Z","timestamp":1776879523150,"version":"3.51.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07284-w","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T13:48:18Z","timestamp":1745848098000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Vision and LiDAR multi-modal fusion beam prediction method for millimeter-wave communication system"],"prefix":"10.1007","volume":"81","author":[{"given":"Wenyu","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changxing","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianze","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annan","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,28]]},"reference":[{"key":"7284_CR1","doi-asserted-by":"crossref","unstructured":"Alrabeiah M, Hredzak A, Alkhateeb A (2020) Millimeter wave base stations with cameras: vision-aided beam and blockage prediction. In: Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Online, 25 May\u201331 July 2020, pp 1\u20135","DOI":"10.1109\/VTC2020-Spring48590.2020.9129369"},{"key":"7284_CR2","doi-asserted-by":"crossref","unstructured":"Charan G, Alrabeiah M, Alkhateeb A (2021) Vision-aided dynamic blockage prediction for 6G wireless communication networks. In: Proceedings of the 2021 IEEE International Conference on Communications Workshops (ICC Workshops), Virtual, 14\u201323 June 2021, pp 1\u20136","DOI":"10.1109\/ICCWorkshops50388.2021.9473651"},{"key":"7284_CR3","unstructured":"Raha AD, Adhikary, A., Munir MS, Qiao Y, Hong CS (2023) Segment anything model aided beam prediction for the millimeter wave communication. In: Proceedings of the 2023 24st Asia-Pacific Network Operations and Management Symposium (APNOMS), IEEE, Sejong, Republic of Korea, 6\u20138 September 2023, pp 113\u2013118"},{"key":"7284_CR4","doi-asserted-by":"crossref","unstructured":"Marasinghe D, Jayaweera N, Rajatheva N, Hakola S, Koskela T, Tervo O, Karjalainen J, Tiirola E et al (2022) Lidar aided wireless networks-beam prediction for 5 g. In: Proceedings of the 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall), IEEE, Beijing, China, 26\u201329 September 2022, pp 1\u20137","DOI":"10.1109\/VTC2022-Fall57202.2022.10012751"},{"key":"7284_CR5","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1109\/TVT.2022.3142513","volume":"71","author":"M Zecchin","year":"2022","unstructured":"Zecchin M, Mashhadi MB, Jankowski M, Gunduz D, Kountouris M, Gesbert D (2022) LIDAR and position-aided mmWave beam selection with non-local CNNs and curriculum training. IEEE Trans Veh Technol 71:2979\u20132990","journal-title":"IEEE Trans Veh Technol"},{"key":"7284_CR6","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/LWC.2019.2899571","volume":"8","author":"A Klautau","year":"2019","unstructured":"Klautau A, Gonz\u00e1lez-Prelcic N (2019) Heath RW LIDAR data for deep learning-based mmWave beam-selection. IEEE Wirel Commun Lett 8:909\u2013912","journal-title":"IEEE Wirel Commun Lett"},{"key":"7284_CR7","doi-asserted-by":"publisher","first-page":"7704","DOI":"10.1109\/TWC.2020.3015735","volume":"19","author":"F Liu","year":"2020","unstructured":"Liu F, Yuan W, Masouros C, Yuan J (2020) Radar-assisted predictive beamforming for vehicular links: communication served by sensing. IEEE Trans Wirel Commun 19:7704\u20137719","journal-title":"IEEE Trans Wirel Commun"},{"key":"7284_CR8","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.3390\/electronics12071672","volume":"12","author":"K Chen","year":"2023","unstructured":"Chen K, Liu D, Zhang Z (2023) Radar-assisted multiple base station cooperative mmwave beam tracking. Electronics 12:1672","journal-title":"Electronics"},{"key":"7284_CR9","first-page":"3163","volume":"68","author":"Q Zhou","year":"2024","unstructured":"Zhou Q, Gong Y, Nallanathan A (2024) Radar-aided beam selection in MIMO communication systems: a federated transfer learning approach. IEEE Trans Veh Technol 68:3163\u20133173","journal-title":"IEEE Trans Veh Technol"},{"key":"7284_CR10","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TCCN.2021.3078147","volume":"7","author":"Y Heng","year":"2021","unstructured":"Heng Y, Andrews JG (2021) Machine learning-assisted beam alignment for mmWave systems. IEEE Trans Cogn Commun Netw 7:1142\u20131155","journal-title":"IEEE Trans Cogn Commun Netw"},{"key":"7284_CR11","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/MCOM.006.2200730","volume":"61","author":"A Alkhateeb","year":"2023","unstructured":"Alkhateeb A, Charan G, Osman T, Hredzak A, Morasis J, Demirham U, Srinivas N (2023) DeepSense 6G: a large-scale real-world multi-modal sensing and communication dataset. IEEE Commun Mag 61:122\u2013128","journal-title":"IEEE Commun Mag"},{"key":"7284_CR12","doi-asserted-by":"crossref","unstructured":"Prakash A, Chitta K, Geiger A (2021) Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20\u201325 June 2021, pp 7077\u20137087","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"7284_CR13","doi-asserted-by":"crossref","unstructured":"Li J, Dai H, Han H, Ding Y (2023). Mseg3d: multi-modal 3d semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 17\u201321 June 2023, pp 21694\u201321704","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"7284_CR14","doi-asserted-by":"publisher","first-page":"5628","DOI":"10.1109\/TVT.2022.3230265","volume":"72","author":"L Wang","year":"2022","unstructured":"Wang L, Zhang X, Li J, Xv X, Fu R, Che R, Yang L, Jin D, Zhao L (2022) Multi-modal and multi-scale fusion 3D object detection of 4D radar and LiDAR for autonomous driving. IEEE Trans Veh Technol 72:5628\u20135641","journal-title":"IEEE Trans Veh Technol"},{"key":"7284_CR15","doi-asserted-by":"crossref","unstructured":"Wang TH, Maalouf A, Xiao W, Ban Y, Amini Y, Rosman G, Kraman S, Rus D (2023) Drive anywhere: Generalizable end-to-end autonomous driving with multi-modal foundation models. arXiv 2023, arXiv:2310.17642","DOI":"10.1109\/ICRA57147.2024.10611590"},{"key":"7284_CR16","doi-asserted-by":"crossref","unstructured":"Charan G, Hredzak A, Stoddard C, Berrey B, Seth M, Nunez H, Alkhateeb A (2022) Towards real-world 6G drone communication: position and camera aided beam prediction. In: Proceedings of the GLOBECOM 2022\u20132022 IEEE Global Communications Conference, IEEE, Rio de Janeiro, Brazil, 4\u20138 December 2022, pp 2951\u20132956.","DOI":"10.1109\/GLOBECOM48099.2022.10000718"},{"key":"7284_CR17","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/JSAC.2009.091009","volume":"27","author":"J Wang","year":"2009","unstructured":"Wang J, Lan Z, Pyo C-W, Baykas T, Sum C-S, Rahman M, Gao J, Funada R, Kojima F, Harada H et al (2009) Beam codebook based beamforming protocol for multi-Gbps millimeter-wave WPAN systems. IEEE J Sel Areas Commun 27:1390\u20131399","journal-title":"IEEE J Sel Areas Commun"},{"key":"7284_CR18","doi-asserted-by":"crossref","unstructured":"Va V, Vikalo H, Heath RW (2016) Beam tracking for mobile millimeter wave communication systems. In: Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), IEEE, Ottawa, ON, Canada, 11\u201314 November 2016, pp 743\u2013747.","DOI":"10.1109\/GlobalSIP.2016.7905941"},{"key":"7284_CR19","doi-asserted-by":"publisher","first-page":"6374764","DOI":"10.1155\/2019\/6374764","volume":"2019","author":"A Waseem","year":"2019","unstructured":"Waseem A, Naveed A, Ali S, Arshad M, Anis H, Qureshi IM (2019) Compressive sensing based channel estimation for massive MIMO communication systems. Wirel Commun Mob Comput 2019:6374764","journal-title":"Wirel Commun Mob Comput"},{"key":"7284_CR20","doi-asserted-by":"publisher","first-page":"141104","DOI":"10.1109\/ACCESS.2019.2944308","volume":"7","author":"S Shaham","year":"2019","unstructured":"Shaham S, Ding M, Kokshoorn M, Lin Z, Dang S, Abbas R (2019) Fast channel estimation and beam tracking for millimeter wave vehicular communications. IEEE Access 7:141104\u2013141118","journal-title":"IEEE Access"},{"key":"7284_CR21","doi-asserted-by":"crossref","unstructured":"Jiang S, Alkhateeb A (2022) Computer Vision Aided Beam Tracking in a Real-World Millimeter Wave Deployment. In: Proceedings of the 2022 IEEE Globecom Workshops (GC Wkshps), IEEE, Washington, DC, USA, 7\u20139 December 2022, pp 142\u2013147","DOI":"10.1109\/GCWkshps56602.2022.10008648"},{"key":"7284_CR22","doi-asserted-by":"crossref","unstructured":"Demirhan U, Alkhateeb A (2022) Radar aided 6G beam prediction: Deep learning algorithms and real-world demonstration. In: Proceedings of the 2022 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, Austin, TX, USA, 10\u201313 April 2022, pp 2655\u20132660.","DOI":"10.1109\/WCNC51071.2022.9771564"},{"key":"7284_CR23","doi-asserted-by":"crossref","unstructured":"Morais J, Bchboodi A, Pezeshki H, Alkhateeb A (2023) Position-aided beam prediction in the real world: How useful GPS locations actually are? In: Proceedings of the ICC 2023-IEEE International Conference on Communications, IEEE, Austin, TX, USA, 10\u201313 April 2023, pp 1824\u20131829","DOI":"10.1109\/ICC45041.2023.10278998"},{"key":"7284_CR24","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1109\/LWC.2022.3219409","volume":"12","author":"S Jiang","year":"2022","unstructured":"Jiang S, Charan G, Alkhateeb A (2022) LiDAR aided future beam prediction in real-world millimeter wave V2I communications. IEEE Wirel Commun Lett 12:212\u2013216","journal-title":"IEEE Wirel Commun Lett"},{"key":"7284_CR25","unstructured":"Charan G, Alrabeiah M, Osman T, Alkhateeb O (2023) Camera based mmWave beam prediction: towards multi-candidate real-world scenarios. arXiv 2023, arXiv:2308.06868"},{"key":"7284_CR26","doi-asserted-by":"crossref","unstructured":"Luo H, Demirhan U, Alkhateeb A (2023) Millimeter wave V2V beam tracking using radar: Algorithms and real-world demonstration. In: Proceedings of the 2023 31st European Signal Processing Conference (EUSIPCO), IEEE, Helsinki, Finland, 4\u20138 September 2023, pp 740\u2013744","DOI":"10.23919\/EUSIPCO58844.2023.10289752"},{"key":"7284_CR27","doi-asserted-by":"crossref","unstructured":"Charan G, Osman T, Hredzak A, Thawdar N, Alkhateeb A (2022) Vision-position multi-modal beam prediction using real millimeter wave datasets. In: IEEE Wireless Communications and Networking Conference (WCNC), IEEE, Austin, TX, USA, 10\u201313 April 2022, pp 2727\u20132731","DOI":"10.1109\/WCNC51071.2022.9771835"},{"key":"7284_CR28","doi-asserted-by":"publisher","first-page":"23441","DOI":"10.1109\/JIOT.2022.3191386","volume":"9","author":"X Cheng","year":"2022","unstructured":"Cheng X, Duan D, Gao S, Yang L (2022) Integrated sensing and communications (ISAC) for vehicular communication networks (VCN). IEEE Internet Things J 9:23441\u201323451","journal-title":"IEEE Internet Things J"},{"key":"7284_CR29","doi-asserted-by":"crossref","unstructured":"Salehi B, Gu J, Roy D, Chowdhurry K (2022) Flash: Federated learning for automated selection of high-band mmwave sectors. In: Proceedings of the IEEE INFOCOM 2022-IEEE Conference on Computer Communications, IEEE, London, UK, 2\u20135 May 2022, pp 1719\u20131728","DOI":"10.1109\/INFOCOM48880.2022.9796865"},{"key":"7284_CR30","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 4\u20139 December 2017"},{"key":"7284_CR31","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27\u201330 June 2016, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7284_CR32","doi-asserted-by":"crossref","unstructured":"Ainslie J, Lee-Thorp J, de Jong M, Zemlyanskiy Y, Lebron F, Sanghai S (2023) GQA: training generalized multi-query transformer models from multi-head checkpoints. arXiv 2023, arXiv:2305.13245","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"7284_CR33","first-page":"32897","volume":"35","author":"H Bao","year":"2022","unstructured":"Bao H, Wang W, Dong L, Liu W, Mohammed WK, Aggarwal K, Som S, Wei F (2022) VLMO: unified vision-language pre-training with mixture-of-modality-experts. Adv Neural Inf Process Syst 35:32897\u201332912","journal-title":"Adv Neural Inf Process Syst"},{"key":"7284_CR34","unstructured":"Zhang B, Sennrich R (2019) Root mean square layer normalization. In: Advances in Neural Information Processing Systems, vol 32"},{"key":"7284_CR35","unstructured":"Shazeer N (2020) Glu variants improve transformer. arXiv preprint arXiv:2002.05202"},{"key":"7284_CR36","doi-asserted-by":"crossref","unstructured":"Ainslie J, Lee-Thorp J, De Jong M et al (2023) GQA: training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"7284_CR37","doi-asserted-by":"crossref","unstructured":"Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H, Shao L (2020) Learning enriched features for real image restoration and enhancement. In: Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XXV 16, Springer International Publishing: Berlin, 2020, pp 492\u2013511","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"7284_CR38","unstructured":"Charan G, Demirhan U, Morais J et al (2022) Multi-modal beam prediction challenge 2022: Towards generalization. arXiv preprint arXiv:2209.07519"},{"key":"7284_CR39","doi-asserted-by":"crossref","unstructured":"Tian Y, Zhao Q, Boukhalfa F, Wu B, Bader F (2023) Multimodal transformers for wireless communications: a case study in beam prediction. arXiv 2023, arXiv:2309.11811","DOI":"10.52953\/JWRA8095"},{"issue":"12","key":"7284_CR40","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/MCOM.2014.6979964","volume":"52","author":"T Nitsche","year":"2014","unstructured":"Nitsche T et al (2014) IEEE 802.11 ad: directional 60 GHz communication for multi-Gigabit-per-second Wi-Fi. IEEE Commun Mag 52(12):132\u2013141","journal-title":"IEEE Commun Mag"},{"issue":"5","key":"7284_CR41","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1109\/JSTSP.2014.2334278","volume":"8","author":"A Alkhateeb","year":"2014","unstructured":"Alkhateeb A, El-Ayach O, Leus G et al (2014) Channel estimation and hybrid precoding for millimeter wave cellular systems. IEEE J Sel Topics Signal Process 8(5):831\u2013846","journal-title":"IEEE J Sel Topics Signal Process"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07284-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07284-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07284-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T13:48:36Z","timestamp":1745848116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07284-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":41,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["7284"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07284-w","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,28]]},"assertion":[{"value":"2 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"789"}}