{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:39:55Z","timestamp":1785512395388,"version":"3.56.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"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":[],"published-print":{"date-parts":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588373","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"1580-1587","source":"Crossref","is-referenced-by-count":24,"title":["Semantic Understanding of Traffic Scenes with Large Vision Language Models"],"prefix":"10.1109","author":[{"given":"Sandesh","family":"Jain","sequence":"first","affiliation":[{"name":"Virginia Tech,Bradley Department of Electrical and Computer Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surendrabikram","family":"Thapa","sequence":"additional","affiliation":[{"name":"Virginia Tech Transportation Institute,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan-Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"Virginia Tech Transportation Institute,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Lynn","family":"Abbott","sequence":"additional","affiliation":[{"name":"Virginia Tech,Bradley Department of Electrical and Computer Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Virginia Tech Transportation Institute,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA59364.2023.10401518"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2009.5378380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICAEM.2019.8853721"},{"key":"ref8","article-title":"Region-based segmentation and object detection","volume":"22","author":"Gould","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref13","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023"},{"key":"ref14","first-page":"10421","article-title":"Bevfusion: A simple and robust lidar-camera fusion framework","volume":"35","author":"Liang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref18","article-title":"Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models","author":"Xu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref22","article-title":"Hilm-d: Towards high-resolution understanding in multimodal large language models for autonomous driving","author":"Ding","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191714"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00104"},{"key":"ref26","article-title":"Video-llava: Learning united visual representation by alignment before projection","author":"Lin","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9341164"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","location":"Jeju Island, Korea, Republic of","start":{"date-parts":[[2024,6,2]]},"end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588373.pdf?arnumber=10588373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T04:51:39Z","timestamp":1721364699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588373","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}