{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:23:40Z","timestamp":1773779020139,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000140","name":"US Department of Transportation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000140","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10920066","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"468-475","source":"Crossref","is-referenced-by-count":7,"title":["ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving Using Vision Language Models"],"prefix":"10.1109","author":[{"given":"Shounak","family":"Sural","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"}]},{"family":"Naren","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"}]},{"given":"Ragunathan Raj","family":"Rajkumar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565073"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3147012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MFI55806.2022.9913867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901824"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588584"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.iatssr.2019.11.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref12","article-title":"DriveLM: Driving with Graph Visual Question Answering","author":"Sima","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref14","article-title":"Talk2BEV: Language-enhanced Bird\u2019s-eye View Maps for Autonomous Driving","author":"Choudhary","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636776"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref17","article-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","volume-title":"ICML","author":"Kim","year":"2021"},{"key":"ref18","article-title":"Visual Instruction Tuning","volume-title":"NeurIPS","author":"Liu","year":"2023"},{"key":"ref19","volume-title":"GPT-4 Technical Report","author":"Achiam","year":"2024"},{"key":"ref20","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref21","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231160195"},{"key":"ref25","volume-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422355"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10920066.pdf?arnumber=10920066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T20:01:26Z","timestamp":1742587286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10920066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10920066","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}