{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:19:04Z","timestamp":1792797544186,"version":"4.5.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2021YFE0205700"],"award-info":[{"award-number":["2021YFE0205700"]}]},{"name":"External cooperation key project of Chinese Academy Sciences","award":["173211KYSB20200002"],"award-info":[{"award-number":["173211KYSB20200002"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0123\/2022\/A3"],"award-info":[{"award-number":["0123\/2022\/A3"]}],"id":[{"id":"https:\/\/ror.org\/05vna4324","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Science and Technology Development Fund of Macau","award":["0070\/2020\/AMJ"],"award-info":[{"award-number":["0070\/2020\/AMJ"]}],"id":[{"id":"https:\/\/ror.org\/05vna4324","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Science and Technology Development Fund of Macau","award":["0004\/2020\/A1"],"award-info":[{"award-number":["0004\/2020\/A1"]}],"id":[{"id":"https:\/\/ror.org\/05vna4324","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Guangdong Provincial Key R&D Programme","award":["2019B010148001"],"award-info":[{"award-number":["2019B010148001"]}]},{"name":"Open Research Projects of Zhejiang Lab","award":["2021KH0AB07"],"award-info":[{"award-number":["2021KH0AB07"]}],"id":[{"id":"https:\/\/ror.org\/02m2h7991","id-type":"ROR","asserted-by":"crossref"}]},{"name":"CCF-Zhipu AI Large Model OF","award":["202219"],"award-info":[{"award-number":["202219"]}],"id":[{"id":"https:\/\/ror.org\/005dzvw93","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Alibaba Group","id":[{"id":"https:\/\/ror.org\/00k642b80","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3274783","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T20:49:25Z","timestamp":1683751765000},"page":"11428-11442","source":"Crossref","is-referenced-by-count":36,"title":["A Unified Multimodal De- and Re-Coupling Framework for RGB-D Motion Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4883-5552","authenticated-orcid":false,"given":"Benjia","family":"Zhou","sequence":"first","affiliation":[{"name":"Macau University of Science and Technology, Taipa, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-0237","authenticated-orcid":false,"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group (U.S.) Inc., Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4735-2885","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-8540","authenticated-orcid":false,"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Taipa, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-1119","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group (U.S.) Inc., Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16471"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3048883"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3012092"},{"key":"ref14","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12279"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2749509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087348"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref10","first-page":"13286","article-title":"MMTM: Multimodal transfer module for CNN fusion","author":"joze","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref17","first-page":"3376","article-title":"Spatiotemporal joint filter decomposition in 3D convolutional neural networks","author":"miao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01952"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919764"},{"key":"ref51","article-title":"A tutorial on principal component analysis","author":"shlens","year":"2014"},{"key":"ref50","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref46","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref48","first-page":"30 392","article-title":"Early convolutions help transformers see better","author":"xiao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref41","article-title":"Hierarchically decoupled spatial-temporal contrast for self-supervised video representation learning","author":"zhang","year":"2020"},{"key":"ref44","article-title":"How does mixup help with robustness and generalization?","author":"zhang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","article-title":"On mixup regularization","author":"carratino","year":"2020"},{"key":"ref49","article-title":"KVT: K-NN attention for boosting vision transformers","author":"wang","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2513479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023599"},{"key":"ref4","first-page":"2549","article-title":"One-shot learning gesture recognition from RGB-D data using bag of features","volume":"14","author":"wan","year":"2013","journal-title":"JMLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3131343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.370"},{"key":"ref82","first-page":"1","article-title":"Real-time hand gesture detection and classification using convolutional neural networks","author":"k\u00f6p\u00fckl\u00fc","year":"2019","journal-title":"Proc IEEE 14th Int Conf Autom Face Gesture Recognit"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00072"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298708"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00677"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2684186"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00040"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.52"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112829"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.12.003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.054"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.369"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899603"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.360"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3390\/s22062405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00126"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.142"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2021.05.003"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.knosys.2017.01.035","article-title":"The spatial Laplacian and temporal energy pyramid representation for human action recognition using depth sequences - sciencedirect","volume":"122","author":"xiaopeng","year":"2017","journal-title":"Knowl -Based Syst"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"ref24","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"yue-hei","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"ref23","article-title":"A comprehensive survey of image augmentation techniques for deep learning","author":"xu","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref25","first-page":"3","article-title":"Improving human action recognition using score distribution and ranking","author":"hoai","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref63","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016"},{"key":"ref22","article-title":"The effects of regularization and data augmentation are class dependent","author":"balestriero","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref21","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref27","article-title":"Video augmentation techniques for deep learning","year":"2021"},{"key":"ref29","article-title":"VideoMix: Rethinking data augmentation for video classification","author":"yun","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875441"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00333"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/s20113305"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10122710.pdf?arnumber=10122710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T13:13:43Z","timestamp":1717679623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":83,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3274783","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}