{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:21:32Z","timestamp":1779340892986,"version":"3.51.4"},"reference-count":57,"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\/501100002635","name":"Inha University\u2019s Research Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002635","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.2023.3278974","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T17:56:07Z","timestamp":1684778167000},"page":"51930-51948","source":"Crossref","is-referenced-by-count":19,"title":["SSRT: A Sequential Skeleton RGB Transformer to Recognize Fine-Grained Human-Object Interactions and Action Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1507-8225","authenticated-orcid":false,"given":"Akash","family":"Ghimire","sequence":"first","affiliation":[{"name":"Department of Integrated System Engineering, School of Global Convergence Studies, Inha University, Incheon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4165-0021","authenticated-orcid":false,"given":"Vijay","family":"Kakani","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Inha University, Incheon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4232-3804","authenticated-orcid":false,"given":"Hakil","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Integrated System Engineering, School of Global Convergence Studies, Inha University, Incheon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3491228"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3070212"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3089705"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/s22155787"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00372"},{"key":"ref55","article-title":"MRI: Multi-modal 3D human pose estimation dataset using mmWave, RGB-D, and inertial sensors","author":"an","year":"2022","journal-title":"arXiv 2210 08394"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3362161"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206288"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3201227"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref45","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"bertasius","year":"2021","journal-title":"Proc ICML"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref47","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108487"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"ref49","first-page":"1146","article-title":"LCR-Net++: Multi-person 2D and 3D pose detection in natural images","volume":"42","author":"rogez","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3402447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.460"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00224"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref34","article-title":"Multimodal learning with transformers: A survey","author":"xu","year":"2022","journal-title":"arXiv 2206 06488"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app13042058"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS55662.2022.10003914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref30","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4018\/IJACI.2017100101"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref38","first-page":"9774","article-title":"TriBERT: Human-centric audio-visual representation learning","volume":"34","author":"rahman","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref23","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341160"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10130506.pdf?arnumber=10130506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:16:53Z","timestamp":1687198613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3278974","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}