{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:19:38Z","timestamp":1780503578665,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72171013"],"award-info":[{"award-number":["72171013"]}],"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":["72222022"],"award-info":[{"award-number":["72222022"]}],"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":["72242101"],"award-info":[{"award-number":["72242101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JKF-2025017226182"],"award-info":[{"award-number":["JKF-2025017226182"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DiDi Gaia Collaborative Research Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tits.2025.3628271","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:40:23Z","timestamp":1764960023000},"page":"1248-1266","source":"Crossref","is-referenced-by-count":2,"title":["Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6243-1945","authenticated-orcid":false,"given":"Jingtian","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and the MOE Engineering Research Center of Advanced Computer Application Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0651-1592","authenticated-orcid":false,"given":"Jingyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, the School of Economics and Management, and the MIIT Key Laboratory of Data Intelligence and Management, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8333-6196","authenticated-orcid":false,"given":"Wayne Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoping","family":"Liu","sequence":"additional","affiliation":[{"name":"DiDi Global Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wen","sequence":"additional","affiliation":[{"name":"DiDi Global Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25555"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33280"},{"key":"ref4","article-title":"Seeing the unseen: Learning basis confounder representations for robust traffic prediction","author":"Ji","year":"2023","journal-title":"arXiv:2311.12472"},{"key":"ref5","first-page":"2216","article-title":"Full Bayesian significance testing for neural networks in traffic forecasting","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Liu"},{"key":"ref6","article-title":"Driving with LLMs: Fusing object-level vector modality for explainable autonomous driving","author":"Chen","year":"2023","journal-title":"arXiv:2310.01957"},{"key":"ref7","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023","journal-title":"arXiv:2311.10813"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330824"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3068479"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113313"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357907"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047091"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794137"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2018.2867526"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01537"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294654"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref23","first-page":"40924","article-title":"Exploring diverse in-context configurations for image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref24","article-title":"PLLaVA: Parameter-free LLaVA extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv:2404.16994"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00356"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6082921"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICT.2016.7991662"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranpol.2007.03.006"},{"key":"ref32","article-title":"Intelligent pothole detection and road condition assessment","author":"Bhatt","year":"2017","journal-title":"arXiv:1710.02595"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2345663"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1049"},{"key":"ref35","article-title":"VecCity: A taxonomy-guided library for map entity representation learning","author":"Zhang","year":"2024","journal-title":"arXiv:2411.00874"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00128"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403043"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00070"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref42","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref44","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021","journal-title":"arXiv:2101.10804"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/ail2.39"},{"key":"ref47","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Yi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02549"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref54","article-title":"CLIP-adapter: Better vision-language models with feature adapters","author":"Gao","year":"2021","journal-title":"arXiv:2110.04544"},{"key":"ref55","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","author":"Zhang","year":"2021","journal-title":"arXiv:2111.03930"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33252"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref60","article-title":"Prompt waywardness: The curious case of discretized interpretation of continuous prompts","author":"Khashabi","year":"2021","journal-title":"arXiv:2112.08348"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00334"},{"key":"ref62","article-title":"GPT understands, too","author":"Liu","year":"2021","journal-title":"arXiv:2103.10385"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1400548"},{"key":"ref68","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"86","key":"ref70","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11322649\/11278491.pdf?arnumber=11278491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:17:37Z","timestamp":1767377857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11278491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":70,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3628271","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}