{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T17:42:21Z","timestamp":1726249341149},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Netherlands Organization for Scientific Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2021.3061479","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T21:18:02Z","timestamp":1614115082000},"page":"6618-6630","source":"Crossref","is-referenced-by-count":12,"title":["Multi-Dataset, Multitask Learning of Egocentric Vision Tasks"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-4424-9591","authenticated-orcid":false,"given":"Georgios","family":"Kapidis","sequence":"first","affiliation":[{"name":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-0843-7878","authenticated-orcid":false,"given":"Ronald","family":"Poppe","sequence":"additional","affiliation":[{"name":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1934-7170","authenticated-orcid":false,"given":"Remco C.","family":"Veltkamp","sequence":"additional","affiliation":[{"name":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.176"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00625"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.54"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.159"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239188"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2438540"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.87"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2808486"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16634-6_33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472171"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.02.016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom.2014.6813944"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.10.004"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.288"},{"key":"ref8","article-title":"Charades-Ego: A large-scale dataset of paired third and first person videos","author":"sigurdsson","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref3","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","article-title":"VideoLSTM convolves, attends and flows for action recognition","volume":"166","author":"li","year":"2018","journal-title":"Comput Vis Image Understanding"},{"key":"ref30","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00540"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540074"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477708"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.739"},{"key":"ref12","first-page":"5889","article-title":"Egocentric basketball motion planning from a single first-person image","author":"bertasius","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.721"},{"key":"ref14","first-page":"639","article-title":"In the eye of beholder: Joint learning of gaze and actions in first person video","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref97","article-title":"Numerical coordinate regression with convolutional neural networks","author":"nibali","year":"2018"},{"key":"ref96","article-title":"Distill-2MD-MTL: Data distillation based on multi-dataset multi-domain multi-task frame work to solve face related tasksks, multi task learning, semi-supervised learning","author":"hosseini","year":"2019"},{"key":"ref11","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_28"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.458"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref19","first-page":"753","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0794-5"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11012-3_17"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_24"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058606"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.161"},{"key":"ref91","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_39"},{"key":"ref89","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00146"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref87","article-title":"One model to learn them all","author":"kaiser","year":"2017"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00039"},{"key":"ref80","first-page":"525","article-title":"Multi-task learning as multi-objective optimization","author":"sener","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.219"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350896"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00035"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref1","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref70","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"sudhakaran","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00548"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-25590-9_6"},{"key":"ref69","article-title":"Audiovisual slowfast networks for video recognition","author":"xiao","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00185"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_13"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73600-6_14"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_58"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09361177.pdf?arnumber=9361177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:10:37Z","timestamp":1686593437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9361177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":99,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3061479","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":[[2023,6,1]]}}}