{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:12:03Z","timestamp":1787011923077,"version":"build-2736575974"},"reference-count":60,"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":[{"name":"Basic Science Research Program through the National Research Foundation of Korea"},{"name":"Ministry of Education","award":["NRF-2021R1A6A1A03039493"],"award-info":[{"award-number":["NRF-2021R1A6A1A03039493"]}]},{"DOI":"10.13039\/501100002649","name":"2025 Yeungnam University Research Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002649","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3570711","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:46:01Z","timestamp":1747403161000},"page":"90144-90162","source":"Crossref","is-referenced-by-count":1,"title":["Camscribe: Enhanced Dashcam Video Descriptions Through Multimodal Spatiotemporal and Object Detection for Autonomous Vehicles"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6713-8766","authenticated-orcid":false,"given":"Muhammad","family":"Rafiq","sequence":"first","affiliation":[{"name":"Department of Game Software, Keimyung University, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5807-6719","authenticated-orcid":false,"given":"Mankyu","family":"Sung","sequence":"additional","affiliation":[{"name":"Department of Game Software, Keimyung University, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1045-8715","authenticated-orcid":false,"given":"Ghazala","family":"Rafiq","sequence":"additional","affiliation":[{"name":"Information and Communication Engineering Department, Yeungnam University, Gyeongsan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0854-768X","authenticated-orcid":false,"given":"Gyu","family":"Sang Choi","sequence":"additional","affiliation":[{"name":"Information and Communication Engineering Department, Yeungnam University, Gyeongsan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref4","first-page":"795","article-title":"Weather-impaired autonomous driving scene regeneration using local self-attention","volume-title":"Proc. Korean Inst. Commun. Sci. Conf.","author":"Rafiq"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s20061702"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.17577\/ijertv9is010026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref10","first-page":"328","article-title":"Natural language processing (almost) from scratch","volume-title":"Proc. IEEE 3rd Int. Conf. Collaboration Internet Comput. (CIC)","author":"Collobert"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/faia200204"},{"key":"ref13","article-title":"Attention is all you need for videos: Self-attention based video summarization using universal transformers","author":"Bilkhu","year":"2019","journal-title":"arXiv:1906.02792"},{"key":"ref14","article-title":"Bridging vision and language from the video-to-text perspective: A comprehensive review","author":"Perez-Martin","year":"2021","journal-title":"arXiv:2103.14785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412898"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref18","article-title":"Feed-forward networks with attention can solve some long-term memory problems","author":"Raffel","year":"2015","journal-title":"arXiv:1512.08756"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"issue":"1997","key":"ref21","first-page":"847","article-title":"TVT: Two-view transformer network for video captioning","volume":"95","author":"Chen","year":"2018","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref22","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","author":"Ging","year":"2020","journal-title":"arXiv:2011.00597"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3378568"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18872-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/andp.19223712302"},{"key":"ref28","first-page":"23","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. 2nd Workshop Stat. Mach. Transl.","author":"Lavie"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"61437","DOI":"10.1109\/ACCESS.2023.3287783","article-title":"Spectral representation learning and fusion for autonomous vehicles trip description exploiting recurrent transformer","volume":"11","author":"Rafiq","year":"2023","journal-title":"IEEE Access"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref34","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"ACL-HLT - Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3148401"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3153056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240651"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/s25030707"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3535394"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref46","article-title":"Using descriptive video services to create a large data source for video annotation research","author":"Torabi","year":"2015","journal-title":"arXiv:1503.01070"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3304816"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3414269"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128835"},{"key":"ref56","first-page":"1","article-title":"Memory augmented recurrent neural networks for dense video captioning","author":"Muralidharan","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475236"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212745"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.23919\/OCEANS44145.2021.9706125"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11006041.pdf?arnumber=11006041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:37:42Z","timestamp":1748479062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3570711","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}