{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T06:09:38Z","timestamp":1775887778721,"version":"3.50.1"},"reference-count":75,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0106200"],"award-info":[{"award-number":["2020AAA0106200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["62236008"],"award-info":[{"award-number":["62236008"]}],"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":["U21B2044"],"award-info":[{"award-number":["U21B2044"]}],"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":["62102415"],"award-info":[{"award-number":["62102415"]}],"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":["61721004"],"award-info":[{"award-number":["61721004"]}],"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":["62072286"],"award-info":[{"award-number":["62072286"]}],"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":["62072455"],"award-info":[{"award-number":["62072455"]}],"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":["62002355"],"award-info":[{"award-number":["62002355"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L201001"],"award-info":[{"award-number":["L201001"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Lab","award":["2022RC0AB02"],"award-info":[{"award-number":["2022RC0AB02"]}]},{"name":"CCF-Hikvision Open Fund","award":["20210004"],"award-info":[{"award-number":["20210004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3252275","type":"journal-article","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T13:24:32Z","timestamp":1677849872000},"page":"9464-9478","source":"Crossref","is-referenced-by-count":13,"title":["Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Yangbo","family":"Feng","sequence":"first","affiliation":[{"name":"Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-5497","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9260-1334","authenticated-orcid":false,"given":"Shicai","family":"Yang","sequence":"additional","affiliation":[{"name":"Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref3","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2005.224"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5610-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3106743"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.030"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486601"},{"key":"ref14","article-title":"BAR: Bayesian activity recognition using variational inference","author":"Krishnan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"ref16","article-title":"Dynamic routing between capsules","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sabour","year":"2017"},{"key":"ref17","article-title":"Matrix capsules with EM routing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hinton","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01080"},{"key":"ref20","first-page":"8465","article-title":"Found a reason for me? weakly-supervised grounded visual question answering using capsules","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Urooj","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00017"},{"issue":"3","key":"ref22","first-page":"4","article-title":"Is space-time attention all you need for video understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"2","author":"Bertasius","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2613924"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3016126"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.42"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00085"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01183"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00438"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01505"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-63649-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00366"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3045079"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5875"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00640"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880750"},{"key":"ref43","article-title":"Self-routing capsule networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hahn","year":"2019"},{"key":"ref44","first-page":"2020","article-title":"Capsules with inverted dot-product attention routing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsai"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00043"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00400"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3156938"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00110"},{"key":"ref50","article-title":"Stacked capsule autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kosiorek","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00400"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104226"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060280"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412057"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683720"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3021980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2176110"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3039329"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142413"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2905157"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"ref68","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Guo","year":"2019"},{"key":"ref69","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref70","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126682"},{"key":"ref73","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal","year":"2016"},{"key":"ref74","article-title":"Bayesian active learning for classification and preference learning","author":"Houlsby","year":"2011"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00920"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10058554.pdf?arnumber=10058554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:39:51Z","timestamp":1773862791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10058554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3252275","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}