{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T07:16:56Z","timestamp":1774163816017,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2022R1A2C1008743"],"award-info":[{"award-number":["NRF-2022R1A2C1008743"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IITP","award":["IITP-2023-2020-0-01741"],"award-info":[{"award-number":["IITP-2023-2020-0-01741"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3279816","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T17:45:18Z","timestamp":1684950318000},"page":"51949-51959","source":"Crossref","is-referenced-by-count":12,"title":["Step by Step: A Gradual Approach for Dense Video Captioning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-6460","authenticated-orcid":false,"given":"Wangyu","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering (Major in Bio Artificial Intelligence), Hanyang University, Ansan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9923-9027","authenticated-orcid":false,"given":"Jiasi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California at Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9052-243X","authenticated-orcid":false,"given":"Jongwon","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering (Major in Bio Artificial Intelligence), Hanyang University, Ansan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref3","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021857"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3160451"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref29","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879642"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942000"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref37","first-page":"1","article-title":"A Better use of audio-visual cues: Dense video captioning with bi-modal transformer","volume-title":"Proc. 31st Brit. Mach. Vis. Virtual Conf.","author":"Iashin"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.685"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref44","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref48","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3228821"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6881"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10132459.pdf?arnumber=10132459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:56:37Z","timestamp":1710381397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3279816","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}