{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:29:16Z","timestamp":1771882156862,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62203294"],"award-info":[{"award-number":["62203294"]}],"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":["U22A20100"],"award-info":[{"award-number":["U22A20100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tits.2025.3633488","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:44:49Z","timestamp":1763750689000},"page":"1894-1907","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Robotaxi Pick-Up Through Vision-Language-Model-Based Passenger Identification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6059-4722","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1194-6390","authenticated-orcid":false,"given":"Shaojing","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer and Informational Engineering, Shanghai Polytechnic University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4114-497X","authenticated-orcid":false,"given":"QingE","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer and Informational Engineering, Shanghai Polytechnic University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2635-5005","authenticated-orcid":false,"given":"Zhiqing","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0017-9605","authenticated-orcid":false,"given":"Xiang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-9523","authenticated-orcid":false,"given":"Hanyang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Global College, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2024.103615"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8461212"},{"key":"ref3","article-title":"Development of a safe, profitable, and fair robotaxi deployment strategy","author":"Zhao","year":"2021"},{"key":"ref4","article-title":"The future of mobility impact of robotaxis on the European passenger transportation industry","author":"Mische","year":"2020"},{"key":"ref5","article-title":"Sustainable urban mobility: Dimensioning robotaxi fleet and public transportation for future cities","author":"Carbonara","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2886585"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3071512"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3486152"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2020.3014099"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3181045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s12650-024-00968-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/03611981221104690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3402136"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref17","article-title":"On the road with GPT-4V(ision): Early explorations of visual-language model on autonomous driving","author":"Wen","year":"2023","journal-title":"arXiv:2311.05332"},{"key":"ref18","article-title":"DriveLM: Driving with graph visual question answering","author":"Sima","year":"2023","journal-title":"arXiv:2312.14150"},{"key":"ref19","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv:2402.12289"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128743"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251727"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3135251"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3304816"},{"key":"ref26","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref27","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref28","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref29","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"ref31","first-page":"72096","article-title":"Language is not all you need: Aligning perception with language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref32","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref33","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref34","article-title":"VisionLLM v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","author":"Wu","year":"2024","journal-title":"arXiv:2406.08394"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref38","article-title":"DiLu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv:2309.16292"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3484528"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.03.039"},{"key":"ref46","article-title":"YOLOv10: Real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv:2405.14458"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11404362\/11264497.pdf?arnumber=11264497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:49:41Z","timestamp":1771879781000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3633488","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}