{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:46:36Z","timestamp":1748493996638,"version":"3.37.3"},"reference-count":83,"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2019R1A2C1006159","NRF-2021R1A6A1A03039493"],"award-info":[{"award-number":["NRF-2019R1A2C1006159","NRF-2021R1A6A1A03039493"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002649","name":"2023 Yeungnam University Research","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":[[2023]]},"DOI":"10.1109\/access.2023.3287783","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:12:26Z","timestamp":1687198346000},"page":"61437-61452","source":"Crossref","is-referenced-by-count":3,"title":["Spectral Representation Learning and Fusion for Autonomous Vehicles Trip Description Exploiting Recurrent Transformer"],"prefix":"10.1109","volume":"11","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, Republic of 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, Republic of 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, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503927"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/3125879"},{"key":"ref56","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume":"32","author":"herdade","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3153056"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3148401"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01190"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref55","first-page":"3143","article-title":"Geo-aware image caption generation","author":"nikiforova","year":"2021","journal-title":"Proc 28th Int Conf Comput Linguistics (COLING)"},{"key":"ref10","article-title":"A semantics-assisted video captioning model trained with scheduled sampling","author":"chen","year":"2019","journal-title":"arXiv 1909 00121"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00136"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app10124312"},{"key":"ref16","article-title":"Fourier neural operator for parametric partial differential equations","author":"li","year":"2020","journal-title":"arXiv 2010 08895"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref18","article-title":"Object relational graph with teacher-recommended learning for video captioning","author":"zha","year":"2020","journal-title":"arXiv 2002 11566"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/s20061702"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1146"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref7","article-title":"Delving deeper into the decoder for video captioning","author":"chen","year":"2020","journal-title":"arXiv 2001 05614"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INCET54531.2022.9824569"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146005"},{"key":"ref6","article-title":"Deep soccer captioning with transformer: Dataset, semantics-related losses, and multi-level evaluation","author":"hammoudeh","year":"2022","journal-title":"arXiv 2202 05728"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412898"},{"key":"ref82","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1002\/andp.19223712302"},{"key":"ref35","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume":"1","author":"chen","year":"2011","journal-title":"Proc 49th Annu Meeting Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref36","article-title":"Dense video captioning using unsupervised semantic information","author":"estevam","year":"2021","journal-title":"arXiv 2112 08455"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212745"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref74","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3108565"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref76","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00676"},{"key":"ref38","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"iashin","year":"2020","journal-title":"arXiv 2005 08271"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103996"},{"key":"ref73","article-title":"Multi-modal feature fusion with feature attention for VATEX captioning challenge 2020","author":"lin","year":"2020","journal-title":"arXiv 2006 03315"},{"key":"ref72","article-title":"Characterizing the impact of using features extracted from pre-trained models on the quality of video captioning sequence-to-sequence models","author":"hammad","year":"2019","journal-title":"arXiv 1911 09989"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475236"},{"key":"ref26","first-page":"2924","article-title":"Automatic video description generation via LSTM with joint two-stream encoding","author":"zhang","year":"2016","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref69","article-title":"Reduced-PINN: An integration-based physics-informed neural networks for stiff ODEs","author":"nasiri","year":"2022","journal-title":"arXiv 2208 12045"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894353"},{"journal-title":"Memory Augmented Recurrent Neural Networks for Dense Video Captioning","year":"2019","author":"muralidharan","key":"ref64"},{"key":"ref63","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref22","first-page":"6299","article-title":"Quo vadis, action recognition","author":"carreira","year":"2017","journal-title":"Proc CVPR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240651"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_22"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10414-6"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10155442.pdf?arnumber=10155442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:36:14Z","timestamp":1689017774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3287783","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}