{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:11:35Z","timestamp":1759331495655,"version":"build-2065373602"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tits.2025.3562058","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:05:14Z","timestamp":1746536714000},"page":"14303-14312","source":"Crossref","is-referenced-by-count":0,"title":["Text-Scene Retrieval for Driving Scenes in Transportation Cyber-Physical Systems"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9361-4803","authenticated-orcid":false,"given":"Tianqi","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8080-9525","authenticated-orcid":false,"given":"Zhenping","family":"Mou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Big Data and Internet of Things, Chongqing Vocational Institute of Engineering, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuye","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00704"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01332"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3424189"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32782"},{"key":"ref6","article-title":"Dolphins: Multimodal language model for driving","author":"Ma","year":"2023","journal-title":"arXiv:2312.00438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01392"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00480"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref11","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"issue":"140","key":"ref13","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286710"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02523"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00236"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27077-2_57"},{"key":"ref28","first-page":"2389","article-title":"Heliophysics events knowledgebase support for space weather research","volume-title":"Proc. 43rd COSPAR Sci. Assem.","volume":"43","author":"Hurlburt"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.111207"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2024.3502512"},{"key":"ref31","article-title":"Bev-clip: Multimodal bev retrieval methodology for complex scene in autonomous driving","author":"Tang","year":"2024","journal-title":"arXiv:2401.01065"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.110166"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275071"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref36","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Patrick"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671662"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCER55570.2022.00042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53308-2_4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3448615"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3151766"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref43","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11178161\/10988726.pdf?arnumber=10988726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:59:13Z","timestamp":1759237153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10988726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":44,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3562058","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"type":"print","value":"1524-9050"},{"type":"electronic","value":"1558-0016"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}