{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:45:53Z","timestamp":1775789153840,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006285","name":"Federal Highway Administration Exploratory Advanced Research Program","doi-asserted-by":"publisher","award":["693JJ31950022"],"award-info":[{"award-number":["693JJ31950022"]}],"id":[{"id":"10.13039\/100006285","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tits.2024.3381175","type":"journal-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:48:50Z","timestamp":1712342930000},"page":"11602-11616","source":"Crossref","is-referenced-by-count":49,"title":["Vision-Language Models Can Identify Distracted Driver Behavior From Naturalistic Videos"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3213-2719","authenticated-orcid":false,"given":"Md. Zahid","family":"Hasan","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0523-4132","authenticated-orcid":false,"given":"Jiajing","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6545-720X","authenticated-orcid":false,"given":"Jiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"given":"Mohammed Shaiqur","family":"Rahman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Iowa State University, Ames, IA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1211-3945","authenticated-orcid":false,"given":"Ameya","family":"Joshi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-1555","authenticated-orcid":false,"given":"Senem","family":"Velipasalar","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4574-8066","authenticated-orcid":false,"given":"Chinmay","family":"Hegde","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, USA"}]},{"given":"Anuj","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Civil Construction and Environmental Engineering, Iowa State University, Ames, IA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6775-9199","authenticated-orcid":false,"given":"Soumik","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Iowa State University, Ames, IA, USA"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Distracted Driving in 2021","year":"2023"},{"key":"ref2","volume-title":"Global Status Report on Road Safety 2023","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/e729192011-001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1513271113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/e729262011-001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.07.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105733"},{"key":"ref8","first-page":"379","article-title":"Driver distraction: A review of the literature","volume-title":"Distracted Driving","author":"Young","year":"2007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3073599"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3126231"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_23"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3063521"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3138137"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PRIA.2019.8786012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3166275"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3316203"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref20","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref21","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref23","first-page":"1","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bao"},{"key":"ref24","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cho"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/ppj2.20107"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"ref28","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Patrick"},{"key":"ref29","first-page":"22605","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. NIPS","author":"Ging"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"ref32","article-title":"CLIP2 Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3354506"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500523"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2939676"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477715"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3159602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2571067"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.364"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2873972"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2010.5548102"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3217342"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3270879"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00244"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917460"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916929"},{"key":"ref48","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2995555"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"ref59","article-title":"Real-time distracted driver posture classification","author":"Abouelnaga","year":"2017","journal-title":"arXiv:1706.09498"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001159"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/4125865"},{"key":"ref62","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":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref64","first-page":"1","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SCEECS48394.2020.184"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3055545"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00212"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.108793"},{"key":"ref77","volume-title":"State Farm Distracted Driver Detection","year":"2023"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00567"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3196410"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10659279\/10492662.pdf?arnumber=10492662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:43:49Z","timestamp":1733885029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10492662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":80,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3381175","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}