{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:36:08Z","timestamp":1778258168023,"version":"3.51.4"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N013964\/1"],"award-info":[{"award-number":["EP\/N013964\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project LOCATE","award":["EP\/N033779\/1"],"award-info":[{"award-number":["EP\/N033779\/1"]}]},{"name":"Fellowship UMPIRE","award":["EP\/T004991\/1"],"award-info":[{"award-number":["EP\/T004991\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,11,1]]},"DOI":"10.1109\/tpami.2020.2991965","type":"journal-article","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T20:18:27Z","timestamp":1588364307000},"page":"4125-4141","source":"Crossref","is-referenced-by-count":160,"title":["The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"first","affiliation":[]},{"given":"Hazel","family":"Doughty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6034-0432","authenticated-orcid":false,"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6911-0302","authenticated-orcid":false,"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[]},{"given":"Evangelos","family":"Kazakos","sequence":"additional","affiliation":[]},{"given":"Davide","family":"Moltisanti","sequence":"additional","affiliation":[]},{"given":"Jonathan","family":"Munro","sequence":"additional","affiliation":[]},{"given":"Toby","family":"Perrett","sequence":"additional","affiliation":[]},{"given":"Will","family":"Price","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Wray","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545058"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref39","article-title":"CMU sphinx","year":"0"},{"key":"ref38","article-title":"IBM watson speech to text","year":"0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.234"},{"key":"ref32","first-page":"7590","article-title":"Towards automatic learning of procedures from web instructional videos","author":"zhou","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref37","article-title":"Google cloud speech API","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01255-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00805"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.508"},{"key":"ref61","article-title":"Audiovisual SlowFast networks for video recognition","author":"xiao","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.10.004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.399"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.06.006"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref68","first-page":"9216","article-title":"Sequence level semantics aggregation for video object detection","author":"haiping","year":"2019","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref2","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"Extended GTEA gaze+","year":"2018"},{"key":"ref22","article-title":"You-do, I-learn: Discovering task relevant objects and their modes of interaction from multi-user egocentric video","author":"damen","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref23","article-title":"Guide to the Carnegie Mellon University Multimodal Activity (CMU-MMAC) database","author":"de la torre","year":"2008","journal-title":"Technical Report CMU-RI-TR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref25","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"sigurdsson","year":"2018","journal-title":"ArXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref51","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref59","first-page":"922","article-title":"Egocentric hand track and object-based human action recognition","author":"kapidis","year":"2019","journal-title":"Proc IEEE SmartWorld Ubiquitous Intell Comput"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref57","article-title":"Learning to learn words from narrated video","author":"suris","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.219"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref11","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref12","article-title":"SLAC: A sparsely labeled dataset for action classification and localization","author":"zhao","year":"2017","journal-title":"arXiv 1712 09374"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref15","article-title":"A short note on the kinetics-700 human action dataset","author":"carreira","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref8","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","article-title":"English senseval: Report and results","author":"kilgarriff","year":"2000","journal-title":"Proc 2nd Int Conf Lang Resour Eval"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref46","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/318723.318728"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45715-1_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.314"},{"key":"ref44","article-title":"Bbox-annotator","author":"yamaguchi","year":"0"},{"key":"ref43","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"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9556112\/09084270.pdf?arnumber=9084270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:25Z","timestamp":1652194165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9084270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":72,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.2991965","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":[[2021,11,1]]}}}