{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:59:42Z","timestamp":1756310382984,"version":"3.37.3"},"reference-count":55,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Funds through the Portuguese Funding Agency through FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UIDB\/50014\/2020"],"award-info":[{"award-number":["UIDB\/50014\/2020"]}]},{"DOI":"10.13039\/501100001871","name":"Ph.D.","doi-asserted-by":"publisher","award":["2021.06945.BD","SFRH\/BD\/146400\/2019","SFRH\/BD\/137720\/2018"],"award-info":[{"award-number":["2021.06945.BD","SFRH\/BD\/146400\/2019","SFRH\/BD\/137720\/2018"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3210973","type":"journal-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:47:47Z","timestamp":1664567267000},"page":"104215-104225","source":"Crossref","is-referenced-by-count":7,"title":["Toward Vehicle Occupant-Invariant Models for Activity Characterization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5162-7124","authenticated-orcid":false,"given":"Leonardo","family":"Capozzi","sequence":"first","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-4136","authenticated-orcid":false,"given":"Vitor","family":"Barbosa","sequence":"additional","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]},{"given":"Carolina","family":"Pinto","sequence":"additional","affiliation":[{"name":"Bosch Car Multimedia, Hildesheim, Portugal"}]},{"given":"Joao Ribeiro","family":"Pinto","sequence":"additional","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1939-2126","authenticated-orcid":false,"given":"Americo","family":"Pereira","sequence":"additional","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]},{"given":"Pedro M.","family":"Carvalho","sequence":"additional","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-2473","authenticated-orcid":false,"given":"Jaime S.","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Centre for Telecommunications and Multimedia, INESC TEC, Porto, Portugal"}]}],"member":"263","reference":[{"article-title":"Automotive interior sensing: Human interaction recognition","year":"2021","author":"pinto","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS50080.2020.9334942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref31","first-page":"1","article-title":"The kinetics human action video dataset","volume":"abs 1705 6950","author":"kay","year":"2017","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref34","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00980"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref29","article-title":"Why can’t I dance in the mall? Learning to mitigate scene bias in action recognition","volume":"32","author":"choi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559534"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5220\/0010838900003124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref24","first-page":"1","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume":"28","author":"duvenaud","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Revisiting skeleton-based action recognition","author":"duan","year":"2021","journal-title":"arXiv 2104 13586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref51","first-page":"1","article-title":"A closer look at spatiotemporal convolutions for action recognition","volume":"abs 1711 11248","author":"tran","year":"2017","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","first-page":"1","article-title":"Rethinking spatiotemporal feature learning for video understanding","volume":"abs 1712 4851","author":"xie","year":"2017","journal-title":"CoRR"},{"key":"ref10","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref11","first-page":"3218","article-title":"P-CNN: Pose-based CNN features for action recognition","author":"cheron","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS50080.2020.9334943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref6","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref8","first-page":"3476","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref49","first-page":"1","article-title":"Evolving space-time neural architectures for videos","volume":"abs 1811 10636","author":"piergiovanni","year":"2018","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1097\/00003086-900000000-98477"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref48","first-page":"1","article-title":"Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet?","volume":"abs 1711 9577","author":"hara","year":"2017","journal-title":"CoRR"},{"key":"ref47","first-page":"1","article-title":"SlowFast networks for video recognition","volume":"abs 1812 3982","author":"feichtenhofer","year":"2018","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_38"},{"key":"ref44","first-page":"1","article-title":"C3D: Generic features for video analysis","volume":"abs 1412 767","author":"tran","year":"2014","journal-title":"CoRR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09906079.pdf?arnumber=9906079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T18:38:09Z","timestamp":1665772689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9906079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3210973","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}