{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T13:39:23Z","timestamp":1771076363553,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2021R1A6A1A03039493"],"award-info":[{"award-number":["NRF-2021R1A6A1A03039493"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2018R1D1A1B07048414"],"award-info":[{"award-number":["NRF-2018R1D1A1B07048414"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2022R1A2C1011404"],"award-info":[{"award-number":["2022R1A2C1011404"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002649","name":"2022 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":[[2022]]},"DOI":"10.1109\/access.2022.3212745","type":"journal-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T19:30:35Z","timestamp":1665084635000},"page":"107361-107375","source":"Crossref","is-referenced-by-count":7,"title":["DeepRide: Dashcam Video Description Dataset for Autonomous Vehicle Location-Aware Trip Description"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1045-8715","authenticated-orcid":false,"given":"Ghazala","family":"Rafiq","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6713-8766","authenticated-orcid":false,"given":"Muhammad","family":"Rafiq","sequence":"additional","affiliation":[{"name":"Department of Game and Mobile Engineering, Keimyung University, Daegu, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6929-3188","authenticated-orcid":false,"given":"Byung-Won","family":"On","sequence":"additional","affiliation":[{"name":"Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5807-6719","authenticated-orcid":false,"given":"Mankyu","family":"Sung","sequence":"additional","affiliation":[{"name":"Department of Game and Mobile Engineering, Keimyung University, Daegu, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0854-768X","authenticated-orcid":false,"given":"Gyu Sang","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"328","article-title":"Natural language processing (almost) from scratch","volume-title":"Proc. IEEE 3rd Int. Conf. Collaboration Internet Comput. (CIC)","author":"Bhatt"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref3","first-page":"1","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. NeurIPS","author":"Ging"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref9","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol. (ACL-HLT)","volume":"1","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref16","article-title":"Multimodal pretraining for dense video captioning","author":"Huang","year":"2020","journal-title":"arXiv:2011.11760"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413880"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2791533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3108565"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.475767"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref34","article-title":"Empirical autopsy of deep video captioning frameworks","author":"Aafaq","year":"2019","journal-title":"arXiv:1911.09345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412898"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app10124312"},{"key":"ref38","article-title":"Object relational graph with teacher-recommended learning for video captioning","author":"Zhan","year":"2020","journal-title":"arXiv:2002.11566"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.096"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref42","article-title":"OmniNet: A unified architecture for multi-modal multi-task learning","author":"Pramanik","year":"2019","journal-title":"arXiv:1907.07804"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref44","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3454167"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1285"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018626"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2920899"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002669"},{"key":"ref54","article-title":"ROAD: The ROad event awareness dataset for autonomous driving","author":"Singh","year":"2021","journal-title":"arXiv:2102.11585"},{"key":"ref55","article-title":"A2D2: Audi autonomous driving dataset","author":"Geyer","year":"2020","journal-title":"arXiv:2004.06320"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref59","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/andp.19223712302"},{"key":"ref62","first-page":"4566","article-title":"CIDEr: Consensus-based image description evaluation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Tech"},{"key":"ref63","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref64","first-page":"223","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"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09913431.pdf?arnumber=9913431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:50:49Z","timestamp":1705963849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9913431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3212745","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}