{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:35:17Z","timestamp":1771018517719,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Sports and Performance Engineering grant and the John Hennessy Undergraduate Research Fund from Villanova University"},{"name":"Villanova University\u2019s Falvey Library Scholarship Open Access Reserve (SOAR) Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3661520","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:51:07Z","timestamp":1770411067000},"page":"20371-20381","source":"Crossref","is-referenced-by-count":0,"title":["Can Vision-Language Models Understand Construction Workers? An Exploratory Study"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6839-4401","authenticated-orcid":false,"given":"Hieu T.","family":"Bui","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Villanova University, Villanova, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8368-8060","authenticated-orcid":false,"given":"Nathaniel E.","family":"Chodosh","sequence":"additional","affiliation":[{"name":"Department of Computing Sciences, Villanova University, Villanova, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8675-8570","authenticated-orcid":false,"given":"Arash","family":"Tavakoli","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Villanova University, Villanova, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.214"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001708"},{"key":"ref4","volume-title":"Safety-RD-V1 Dataset, 2023","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1061\/JCCEE5.CPENG-5225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1108\/ECAM-06-2021-0481"},{"key":"ref7","volume-title":"PPE Detection Dataset","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0002038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1061\/JCEMD4.COENG-13100"},{"key":"ref10","volume-title":"PPE Detection Dataset, 2024","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2017.03.003"},{"key":"ref12","article-title":"Robotic deployment on construction sites: Considerations for safety and productivity impact","author":"Braga","year":"2024","journal-title":"arXiv:2404.13143"},{"key":"ref13","author":"Bui","year":"2023","journal-title":"Construction"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.658"},{"issue":"3","key":"ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641289","article-title":"Asurvey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2018.01.020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3158585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.895929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-04384-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9780429398100-15"},{"key":"ref21","article-title":"Soda dataset","author":"Saha","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21428\/e2759450.d3acfbfb"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.22260\/isarc2024\/0131"},{"key":"ref25","article-title":"Application of vision-language model to pedestrians behavior and scene understanding in autonomous driving","author":"Gao","year":"2025","journal-title":"arXiv:2501.06680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-021-00572-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2014.04.013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001884"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1061\/9780784480847.020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001506"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2017.06.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.22260\/isarc2020\/0092"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001729"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000719"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135"},{"key":"ref36","article-title":"Detect worker dataset","author":"Soonbin","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001406"},{"key":"ref38","first-page":"87874","article-title":"What matters when building vision-language models?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Lauren\u00e7on"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2017.06.012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105508"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3350773"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.103000"},{"key":"ref43","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/buildings11090409"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1139\/cjce-2021-0646"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/buildings12122057"},{"key":"ref47","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2024.102057"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1061\/9780784485262.065"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2014.03.076"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref52","volume-title":"Health and Safety PPE Compliance Dataset","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2022.101808"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.104099"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000898"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref58","first-page":"255","article-title":"Investigating the impact of construction robots autonomy level onworkers\u2019 cognitive load","volume-title":"Proc. Can. Soc. Civil Eng. Annu. Conf.","author":"Shayesteh"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1061\/9780784483985.043"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CO.1943-7862.0001843"},{"key":"ref61","volume-title":"PPE detection dataset","year":"2024"},{"key":"ref62","volume-title":"Output Merge Dataset","year":"2025"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2021.103777"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1525\/ae.2000.27.3.794"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2024.105555"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.02.020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.104812"},{"key":"ref70","first-page":"1","article-title":"Why are visually-grounded language models bad at image classification?","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11372767.pdf?arnumber=11372767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:51:21Z","timestamp":1771015881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11372767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3661520","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}