{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T18:14:56Z","timestamp":1793124896078,"version":"4.5.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001793","name":"Queensland University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001793","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Comput. Soc."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/ojcs.2025.3525560","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T19:46:27Z","timestamp":1735933587000},"page":"223-235","source":"Crossref","is-referenced-by-count":21,"title":["Leveraging Deep Learning and Multimodal Large Language Models for Near-Miss Detection Using Crowdsourced Videos"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6322-2792","authenticated-orcid":false,"given":"Shadi","family":"Jaradat","sequence":"first","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2634-4576","authenticated-orcid":false,"given":"Mohammed","family":"Elhenawy","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huthaifa I.","family":"Ashqar","sequence":"additional","affiliation":[{"name":"Arab American University, Jenin, Palestine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1217-9808","authenticated-orcid":false,"given":"Alexander","family":"Paz","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-0159","authenticated-orcid":false,"given":"Richi","family":"Nayak","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtte.2020.05.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3002079"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1061\/jtepbs.0000362"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.12955\/pns.v1.113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/15389588.2020.1762871"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app14146378"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/risa.12869"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2018.02.013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2019.123534"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE52691.2021.00016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICENCO49852.2021.9698968"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-021-12253-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles6030074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.56381\/jsaem.v5i2.173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12024-021-00382-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/8812740"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2010.02.001"},{"key":"ref18","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn., Res.","volume":"202","author":"Driess","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/0600000079"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/smartcities7050095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT57861.2023.10126213"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/math11132884"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.105973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.106162"},{"key":"ref25","article-title":"ViT-ReciproCAM: Gradient and attention-free visual explanations for vision transformer","author":"Byun","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2023.100830"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.psep.2012.06.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_54"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2023.3339016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1061\/41184(419)511"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1061\/41039(345)473"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/fi14080227"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2018.9010033"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3373647"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/15472450701653499"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/su142214859"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CYBERI.2018.8337551"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54190-7_9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569952"},{"key":"ref41","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1108\/JICV-03-2021-0004"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/GCITC60406.2023.10426462"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.10.003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s19184021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/computers10110148"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0361198119840611"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588802"},{"key":"ref50","article-title":"Out of distribution performance of state of art vision model","author":"Rahman","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1117\/12.2617779"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3147770"},{"key":"ref53","article-title":"ChatGPT is on the horizon: Could a large language model be suitable for intelligent traffic safety research and applications","author":"Zheng","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/app14041352"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.4018\/ijwsr.338222"},{"key":"ref56","article-title":"Leveraging Twitter data for sentiment analysis of transit user feedback: An NLP framework","author":"Das","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s42421-024-00090-5"},{"key":"ref58","article-title":"Transformer models in education: Summarizing science textbooks with AraBART, MT5, AraT5, and mBART","author":"Masri","year":"2024"},{"key":"ref59","article-title":"LanguageMPC: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023"},{"key":"ref60","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref61","article-title":"Object detection using oriented window learning vision transformer: Roadway assets recognition","author":"Alhadidi","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3354852"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"}],"container-title":["IEEE Open Journal of the Computer Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782664\/10834807\/10820995.pdf?arnumber=10820995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:48:28Z","timestamp":1738090108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10820995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/ojcs.2025.3525560","relation":{},"ISSN":["2644-1268"],"issn-type":[{"value":"2644-1268","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}