{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:13:37Z","timestamp":1780053217943,"version":"3.54.0"},"reference-count":425,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3183112","type":"journal-article","created":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T20:27:09Z","timestamp":1655238429000},"page":"1-20","source":"Crossref","is-referenced-by-count":420,"title":["Human Action Recognition From Various Data Modalities: A Review"],"prefix":"10.1109","author":[{"given":"Zehua","family":"Sun","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-3614","authenticated-orcid":false,"given":"Qiuhong","family":"Ke","sequence":"additional","affiliation":[{"name":"Monash University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1920-0371","authenticated-orcid":false,"given":"Hossein","family":"Rahmani","sequence":"additional","affiliation":[{"name":"Lancaster University, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"The University of Western Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1816-1457","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2008.4542023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01603-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.891352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.167"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.44"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00059"},{"key":"ref12","article-title":"Spatiotemporal filtering for event-based action recognition","author":"Ghosh","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3314404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4108\/icst.mobicase.2014.257786"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2491329"},{"key":"ref16","article-title":"Temporal unet: Sample level human action recognition using WiFi","author":"Wang","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref18","article-title":"A survey on 3D skeleton-based action recognition using learning method","author":"Ren","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.02.006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2019.0100311"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700082"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs11091068"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.333"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967577"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130379"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.05.094"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.09.028"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00217"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6474999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1964897.1964918"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09396-3_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.01.013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.24.97"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248093"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref44","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. 27th Int. Conf. Neural Informat. Process. Syst.","author":"Simonyan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104108"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.123"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.050"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12228"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref62","article-title":"Towards good practices for very deep two-stream convnets","author":"Wang","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00889"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.402"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.236"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00804"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref72","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01508-1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.10.095"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.118"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIA49625.2020.00028"},{"key":"ref78","article-title":"Action recognition using visual attention","author":"Sharma","year":"2015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7404-z"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref81","first-page":"33","article-title":"Attentional pooling for action recognition","volume-title":"Proc. 27th Int. Conf. Neural Informat. Process. Syst.","author":"Girdhar"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05144-7"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref87","first-page":"1","article-title":"Delving deeper into convolutional networks for learning video representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ballas"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.84"},{"key":"ref89","article-title":"Temporal reasoning in videos using convolutional gated recurrent units","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Dwibedi"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.037"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref92","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.27"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2611485"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_26"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_17"},{"key":"ref102","article-title":"Temporal 3D convnets: New architecture and transfer learning for video classification","author":"Diba","year":"2017"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_23"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref113","article-title":"Spatiotemporal residual networks for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107037"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00558"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00985"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01212"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00411"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01467-7"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691768"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref132","article-title":"CT-net: Channel tensorization network for video classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00332"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref142","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_40"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014683"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00748"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.24"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.460"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.387"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.115"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00572"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2628339"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967191"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"key":"ref177","first-page":"10","article-title":"Skepxels: Spatio-temporal image representation of human skeleton joints for action recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Liu"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2690339"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2017.8026282"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366569"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3472722"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2018.8439897"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935173"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_45"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_2"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01434"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00216"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018561"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018989"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053765"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/227"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2812099"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2841649"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00187"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3019293"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808682"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315191"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.11.017"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396382"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2504550"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12091-z"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14075-5"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_47"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2018.04.002"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078497"},{"key":"ref229","first-page":"249","article-title":"A spatio-temporal deep learning approach for human action recognition in infrared videos","volume-title":"Proc. Opt. Photon. Informat. Process. XII","author":"Shah"},{"issue":"4","key":"ref230","first-page":"43","article-title":"A new technique based on 3D convolutional neural networks and filtering optical flow maps for action classification in infrared video","volume":"21","author":"Meglouli","year":"2019","journal-title":"Control Eng. Appl. Inf."},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2823910"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-014-0677-9"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.30"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2019.103014"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-019-01239-9"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412632"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2533389"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.781"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00934"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00580"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3106101"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00381"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref247","first-page":"1","article-title":"PSTNet: Point spatio-temporal convolution on point cloud sequences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00073"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00199"},{"key":"ref250","article-title":"Event-based action recognition using timestamp image encoding network","author":"Huang","year":"2020"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181247"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412991"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_48"},{"key":"ref254","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. 27th Int. Conf. Neural Informat. Process. Syst.","author":"Qi"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2007.914337"},{"key":"ref257","first-page":"C186","article-title":"A 240 \u00d7 180 10mw 12us latency sparse-output vision sensor for mobile applications","volume-title":"Proc. Symp. VLSI Circuits","author":"Berner"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.136"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00594"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206681"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023597"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242609"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref266","article-title":"Audiovisual slowfast networks for video recognition","author":"Xiao","year":"2020"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21257-4_36"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.07.009"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/FUTURETECH.2010.5482729"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2006.6"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2015.263"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2017.8037349"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.09.027"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.2991\/cnci-19.2019.95"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2911204"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1142\/9789812833709_0030"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.3390\/s19071644"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2007.4441754"},{"key":"ref279","first-page":"149","article-title":"Modern FMCW radar-techniques and applications","volume-title":"Proc. 1st Eur. Radar Conf.","author":"Stove"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.3390\/s16121990"},{"key":"ref281","first-page":"81","article-title":"Multi-target human gait classification using deep convolutional neural networks on micro-doppler spectrograms","volume-title":"Proc. Eur. Radar Conf.","author":"Trommel"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1117\/12.2262719"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/COMPEM.2018.8496654"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR41533.2019.171307"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2872849"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR41533.2019.171243"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4163-6_3"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2019.01.013"},{"key":"ref289","article-title":"Action recognition using indoor radar systems","author":"Yang","year":"2019"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00056"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2878754"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1145\/2639108.2639143"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2679658"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2635161"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00026"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2973272"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2878233"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2737553"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00875"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-011-9430-9"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00096"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2017.23023"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3035045"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00018"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732038"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.52"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00631"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965299"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.3390\/s20113305"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08576-z"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.77"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206288"},{"key":"ref316","article-title":"Pose-conditioned spatio-temporal attention for human action recognition","author":"Baradel","year":"2017"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486486"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107356"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00278"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.621"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2850149"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.3390\/app9040716"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2020.09.052"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.04.035"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-7895-8_32"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749340"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659539"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023599"},{"key":"ref334","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727435"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.001"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2018.2878572"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2018.8444326"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.3390\/s19173680"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2947446"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3028561"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11058-w"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806333"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2985628"},{"key":"ref345","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341699"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298708"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0982-6"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1109\/34.910878"},{"key":"ref349","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. 27th Int. Conf. Neural Informat. Process. Syst.","author":"Shi"},{"key":"ref350","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"ref351","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836044"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505295"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299172"},{"issue":"1998","key":"ref354","first-page":"175","article-title":"Multi-criteria decision making: An operations research approach","volume":"15","author":"Triantaphyllou","year":"1998","journal-title":"Encyclopedia Elect. Electron. Eng."},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2682280"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2875510"},{"key":"ref357","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_7"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00280"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929038"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802909"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_24"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683606"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296630"},{"key":"ref364","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086590"},{"key":"ref365","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093307"},{"key":"ref366","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NeurIPS Deep Learn. Representation Learn. Workshop","author":"Hinton"},{"key":"ref367","article-title":"Self-supervised learning by cross-modal audio-video clustering","author":"Alwassel","year":"2019"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref369","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. 27th Int. Conf. Neural Informat. Process. Syst.","author":"Korbar"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref373","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref374","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref375","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref376","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"ref377","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref378","first-page":"753","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref379","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"Gorban","year":"2015"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref381","first-page":"5843","article-title":"The \u201csomething something","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Goyal"},{"key":"ref382","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref383","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.013"},{"issue":"CG-2007-2","key":"ref384","article-title":"Documentation mocap database HDM05","author":"M\u00fcller","year":"2007"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref386","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref387","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"ref388","first-page":"47","article-title":"Human activity detection from RGBD images","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Sung"},{"key":"ref389","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33868-7_6"},{"key":"ref390","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396381"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref392","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref393","doi-asserted-by":"publisher","DOI":"10.1016\/j.bica.2013.05.008"},{"key":"ref394","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref395","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0550-7"},{"key":"ref396","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2347057"},{"key":"ref397","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.03.008"},{"key":"ref398","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.604"},{"key":"ref399","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.08.038"},{"key":"ref400","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref401","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref402","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref403","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref404","doi-asserted-by":"publisher","DOI":"10.3390\/app7101101"},{"key":"ref405","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref406","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"},{"key":"ref407","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877429"},{"key":"ref408","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref409","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923743"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref411","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341160"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref413","article-title":"RareAct: A video dataset of unusual interactions","author":"Miech","year":"2020"},{"key":"ref414","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref415","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref416","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref417","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref418","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_25"},{"key":"ref419","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00871"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01302"},{"key":"ref421","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref422","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463643"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref424","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"ref425","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00966"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09795869.pdf?arnumber=9795869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:55:51Z","timestamp":1706766951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9795869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":425,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3183112","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":[[2022]]}}}