{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T22:43:40Z","timestamp":1774478620272,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Xi\u2019an Jiaotong-Liverpool University (XJTLU) AI University Research Centre and Jiangsu Province Engineering Research Centre of Data Science and Cognitive Computation, XJTLU"},{"name":"Suzhou Municipal Key Laboratory for Intelligent Virtual Engineering","award":["SZS2022004"],"award-info":[{"award-number":["SZS2022004"]}]},{"name":"Suzhou Municipal Key Laboratory for Intelligent Virtual Engineering","award":["XJTLU-REF-21-01-002"],"award-info":[{"award-number":["XJTLU-REF-21-01-002"]}]},{"name":"Suzhou Municipal Key Laboratory for Intelligent Virtual Engineering","award":["XJTLU-RDF-22-01-062"],"award-info":[{"award-number":["XJTLU-RDF-22-01-062"]}]},{"name":"XJTLU Key Program Special Fund","award":["KSF-A-17"],"award-info":[{"award-number":["KSF-A-17"]}]},{"name":"Jiangsu Industrial Technology Research Institute (JITRI) and Wuxi National Hi-Tech District"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tits.2025.3527011","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T14:03:23Z","timestamp":1737381803000},"page":"7275-7291","source":"Crossref","is-referenced-by-count":13,"title":["WaterVG: Waterway Visual Grounding Based on Text-Guided Vision and mmWave Radar"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4013-2107","authenticated-orcid":false,"given":"Runwei","family":"Guan","sequence":"first","affiliation":[{"name":"Faculty of Science and Engineering, University of Liverpool, Liverpool, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3205-2656","authenticated-orcid":false,"given":"Liye","family":"Jia","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, University of Liverpool, Liverpool, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-3598","authenticated-orcid":false,"given":"Shanliang","family":"Yao","sequence":"additional","affiliation":[{"name":"Institute of Deep Perception Technology, Jiangsu Industrial Technology Research Institute (JITRI), Nanjing, China"}]},{"given":"Fengyufan","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, University of Liverpool, Liverpool, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2823-3441","authenticated-orcid":false,"given":"Sheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Jiangsu Industrial Technology Research Institute, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6497-6721","authenticated-orcid":false,"given":"Erick","family":"Purwanto","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1024-5442","authenticated-orcid":false,"given":"Xiaohui","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5787-4716","authenticated-orcid":false,"given":"Ka Lok","family":"Man","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0199-7386","authenticated-orcid":false,"given":"Eng Gee","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"given":"Jeremy","family":"Smith","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, University of Liverpool, Liverpool, U.K."}]},{"given":"Xuming","family":"Hu","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[{"name":"Institute of Deep Perception Technology, Jiangsu Industrial Technology Research Institute (JITRI), Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3307157"},{"key":"ref2","article-title":"Exploring radar data representations in autonomous driving: A comprehensive review","author":"Yao","year":"2023","journal-title":"arXiv:2312.04861"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3415772"},{"key":"ref4","article-title":"ASY-VRNet: Waterway panoptic driving perception model based on asymmetric fair fusion of vision and 4D mmWave radar","author":"Guan","year":"2023","journal-title":"arXiv:2308.10287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422325"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3077679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3067271"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17456-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3381652"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3158584"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01498"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3375300"},{"key":"ref15","article-title":"Achelous++: Power-oriented water-surface panoptic perception framework on edge devices based on vision-radar fusion and pruning of heterogeneous modalities","author":"Guan","year":"2023","journal-title":"arXiv:2312.08851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3124192"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3419585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.14257\/ijsia.2018.12.5.05"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12967"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3309100"},{"key":"ref31","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Choromanski"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21983"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2023.103835"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01857"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918694"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967909"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00374"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3165803"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.119011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285415"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111630"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2023.3265742"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231191145"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref52","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018","journal-title":"arXiv:1812.03426"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref57","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref60","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref61","article-title":"Albert: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2020","journal-title":"arXiv:1909.11942"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00532"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976"},{"key":"ref65","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Li"},{"key":"ref66","volume-title":"Ultralytics YOLO","author":"Jocher"},{"key":"ref67","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref68","article-title":"PP-LiteSeg: A superior real-time semantic segmentation model","author":"Peng","year":"2022","journal-title":"arXiv:2204.02681"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref73","article-title":"What goes beyond multi-modal fusion in one-stage referring expression comprehension: An empirical study","author":"Luo","year":"2022","journal-title":"arXiv preprint arXiv:2204.07913"},{"issue":"8","key":"ref74","first-page":"1","article-title":"Lightweight traffic referring expression comprehension system based on sparse cross-modal attention and multi-modal joint augmentation","volume":"14","author":"Guan","year":"2023","journal-title":"J. Latex Class Files"},{"key":"ref75","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01225"},{"key":"ref80","first-page":"1","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10988578\/10847630.pdf?arnumber=10847630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:51:49Z","timestamp":1770411109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10847630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":84,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3527011","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}