{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T20:27:50Z","timestamp":1792614470225,"version":"4.5.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"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":["61906173"],"award-info":[{"award-number":["61906173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822701"],"award-info":[{"award-number":["61822701"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1109\/tcds.2020.3048883","type":"journal-article","created":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T20:51:21Z","timestamp":1609534281000},"page":"246-252","source":"Crossref","is-referenced-by-count":84,"title":["Trear: Transformer-Based RGB-D Egocentric Action Recognition"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8344-718X","authenticated-orcid":false,"given":"Xiangyu","family":"Li","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjing University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1676-5505","authenticated-orcid":false,"given":"Yonghong","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjing University, Tianjin, 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":"Alibaba Group, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2450-492X","authenticated-orcid":false,"given":"Zhimin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-3451","authenticated-orcid":false,"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-2687","authenticated-orcid":false,"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[{"name":"Advanced Multimedia Research Laboratory, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref2","volume-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"Sudhakaran","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2783944"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2768422"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12228"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.52"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298708"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875441"},{"key":"ref11","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Advances in Neural Information Processing Systems","author":"Simonyan"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.94"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.04.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref20","volume-title":"Image transformer","author":"Parmar","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref22","volume-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref23","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref26","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2337331"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.487"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9732511\/09312201.pdf?arnumber=9312201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:51:42Z","timestamp":1704840702000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9312201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":32,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2020.3048883","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}