{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:45:05Z","timestamp":1782405905748,"version":"3.54.5"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"15","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellent Science and Technology Creative Talent Training Program of Shenzhen Municipality","award":["RCBS20221008093224017"],"award-info":[{"award-number":["RCBS20221008093224017"]}]},{"name":"Key Scientific Research Project of the Department of Education of Guangdong Province","award":["2024ZDZX3012"],"award-info":[{"award-number":["2024ZDZX3012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,8,1]]},"DOI":"10.1109\/jiot.2025.3574456","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T14:10:03Z","timestamp":1748441403000},"page":"31856-31868","source":"Crossref","is-referenced-by-count":5,"title":["Skeleton-Based Pretraining With Discrete Labels for Emotion Recognition in IoT Environments"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9955-0916","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"first","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8542-9871","authenticated-orcid":false,"given":"Feng","family":"Liang","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1717-5785","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3529-2640","authenticated-orcid":false,"given":"Victor C. M.","family":"Leung","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3430368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.06.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3246993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700728"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/KBEI.2017.8324974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.03.065"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144804"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3332814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.125016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1096"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2339834"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2688239"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105515"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014842"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.84.3.231"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.1224313"},{"key":"ref19","article-title":"Self-supervised gait-based emotion representation learning from selective strongly augmented skeleton sequences","author":"Song","year":"2024","journal-title":"arXiv:2405.04900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3223251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2874986"},{"key":"ref23","first-page":"1447","article-title":"Understanding emotional body expressions via large language models","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"39","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3603618"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2637343"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IC3D.2016.7823448"},{"key":"ref29","article-title":"Identifying emotions from walking using affective and deep features","author":"Randhavane","year":"2019","journal-title":"arXiv:1906.11884"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5490"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340710"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746047"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3229478"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3508259.3508266"},{"key":"ref37","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref38","article-title":"BEiT: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref39","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022","journal-title":"arXiv:2212.09058"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128645"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref43","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref44","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/135"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2106\/00004623-196446020-00009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2818740"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_49"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925532"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/icis.2018.8466522"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2022.3233597"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107868"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/s21010205"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00156"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.278"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref60","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168137"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00471"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3247103"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"ref69","article-title":"Skeleton2vec: A self-supervised learning framework with contextualized target representations for skeleton sequence","author":"Xu","year":"2024","journal-title":"arXiv:2401.00921"},{"key":"ref70","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Naacl-HLT","volume":"1","author":"Kenton"},{"key":"ref71","article-title":"Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID","author":"Yixiao","year":"2020","journal-title":"arXiv:2006.02713"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00716"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3307933"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01864-0"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363831"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386777"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.57.1.100"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1037\/a0025737"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1002\/9780470549148"},{"key":"ref80","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume-title":"Proc. KDD","volume":"96","author":"Ester"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00344"},{"key":"ref82","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2021","journal-title":"arXiv:2105.04906"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612449"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2016.2591039"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05792-3_15"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00635-7"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28409"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11096042\/11016703.pdf?arnumber=11016703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T21:34:20Z","timestamp":1764711260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":90,"journal-issue":{"issue":"15"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3574456","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,1]]}}}