{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T07:17:55Z","timestamp":1779002275311,"version":"3.51.4"},"reference-count":66,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52272344"],"award-info":[{"award-number":["52272344"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2023802"],"award-info":[{"award-number":["BE2023802"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","award":["KYCX24_0455"],"award-info":[{"award-number":["KYCX24_0455"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tits.2026.3654084","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:30:33Z","timestamp":1769545833000},"page":"5804-5819","source":"Crossref","is-referenced-by-count":1,"title":["Pedestrian Crossing Intention Prediction Based on Cross-Modal Motion Query and Global\u2013Local Context Co-Learning for Autonomous Driving"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7734-6761","authenticated-orcid":false,"given":"Chenxi","family":"Lin","sequence":"first","affiliation":[{"name":"Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5799-0568","authenticated-orcid":false,"given":"Xiaojian","family":"Hu","sequence":"additional","affiliation":[{"name":"Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3162719"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901817"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3173537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/itsc.2019.8917118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3074829"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3398252"},{"key":"ref9","article-title":"PIP-Net: Pedestrian intention prediction in the wild","author":"Azarmi","year":"2024","journal-title":"arXiv:2402.12810"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341607"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2024.3360966"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref14","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Ngiam"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.33"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00636"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00130"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3524117"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref22","article-title":"Gemma 3 technical report","volume-title":"arXiv:2503.19786","author":"Team","year":"2025"},{"key":"ref23","article-title":"Phi-4-reasoning technical report","volume-title":"arXiv:2504.21318","author":"Abdin","year":"2025"},{"key":"ref24","article-title":"Qwen3-VL technical report","volume-title":"arXiv:2511.21631","author":"Bai","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124701"},{"key":"ref26","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref28","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111366"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3576327"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3588967"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3690931.3690982"},{"key":"ref34","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv:2402.12289"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588373"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2929257"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-0964-1"},{"key":"ref42","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":"ref43","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref45","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. NIPS","author":"Shi"},{"key":"ref46","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304591"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00441"},{"key":"ref52","article-title":"Pedestrian action anticipation using contextual feature fusion in stacked RNNs","author":"Rasouli","year":"2020","journal-title":"arXiv:2005.06582"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443552"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01531"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3309309"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161318"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3557125"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105203"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2025.3554387"},{"key":"ref60","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811664"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827084"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS57111.2022.00073"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3449046"},{"key":"ref66","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"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11512109\/11366050.pdf?arnumber=11366050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:13Z","timestamp":1778528893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11366050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":66,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tits.2026.3654084","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}