{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:37:24Z","timestamp":1781109444044,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["2023YFF0725001"],"award-info":[{"award-number":["2023YFF0725001"]}],"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":"publisher","award":["92370204"],"award-info":[{"award-number":["92370204"]}],"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":["52422111"],"award-info":[{"award-number":["52422111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515120057"],"award-info":[{"award-number":["2023B1515120057"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Hong Kong University of Science and Technology (Guangzhou) [HKUST(GZ)] Joint Funding Program","award":["2023A03J0008"],"award-info":[{"award-number":["2023A03J0008"]}]},{"DOI":"10.13039\/501100010819","name":"Education Bureau of Guangzhou Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3651269","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:37:39Z","timestamp":1767724659000},"page":"6168-6183","source":"Crossref","is-referenced-by-count":2,"title":["Da Yu: Toward ASV-Based Image Captioning for Waterway Surveillance and Scene Understanding"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4013-2107","authenticated-orcid":false,"given":"Runwei","family":"Guan","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningwei","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4809-0943","authenticated-orcid":false,"given":"Tianhao","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8134-2188","authenticated-orcid":false,"given":"Shaofeng","family":"Liang","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software, China University of Petroleum (East China), Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9877-6363","authenticated-orcid":false,"given":"Wei","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yafeng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9597-6350","authenticated-orcid":false,"given":"Shang","family":"Gao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3132-9414","authenticated-orcid":false,"given":"Songning","family":"Lai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-3598","authenticated-orcid":false,"given":"Shanliang","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Yancheng Institute of Technology, Yancheng, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuming","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1591-5583","authenticated-orcid":false,"given":"Ryan","family":"Wen Liu","sequence":"additional","affiliation":[{"name":"School of Navigation, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4532-0924","authenticated-orcid":false,"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2775524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246786"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3067271"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422325"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3527011"},{"key":"ref8","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref11","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ord\u00f3\u00f1ez"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2721945"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3415772"},{"key":"ref19","volume-title":"Navigation Rules and Regulations Handbook: International\u2014Inland","author":"Guard","year":"2018"},{"key":"ref20","article-title":"MobileVLM v2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024","journal-title":"arXiv:2402.03766"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref23","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref26","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Yang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155795"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.599"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref36","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref37","article-title":"TinyLLaVA: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv:2402.14289"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104572"},{"key":"ref39","article-title":"NanoMVG: USV-centric low-power multi-task visual grounding based on prompt-guided camera and 4D mmWave radar","author":"Guan","year":"2024","journal-title":"arXiv:2408.17207"},{"key":"ref40","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref41","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"ref44","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref46","article-title":"SmolVLM: Redefining small and efficient multimodal models","author":"Marafioti","year":"2025","journal-title":"arXiv:2504.05299"},{"key":"ref47","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref53","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref54","article-title":"MultiWay-adapater: Adapting large-scale multi-modal models for scalable image-text retrieval","author":"Long","year":"2023","journal-title":"arXiv:2309.01516"},{"key":"ref55","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11333354.pdf?arnumber=11333354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:32Z","timestamp":1778269352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":59,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3651269","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}