{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:36:05Z","timestamp":1778258165861,"version":"3.51.4"},"reference-count":117,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["U54EB020404"],"award-info":[{"award-number":["U54EB020404"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intel Science of Technology Center for Pervasive Computing","award":["ISTC-PC"],"award-info":[{"award-number":["ISTC-PC"]}]}],"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.2021.3051319","type":"journal-article","created":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T20:47:30Z","timestamp":1610743650000},"page":"6731-6747","source":"Crossref","is-referenced-by-count":54,"title":["In the Eye of the Beholder: Gaze and Actions in First Person Video"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4173-9453","authenticated-orcid":false,"given":"Yin","family":"Li","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6650-9972","authenticated-orcid":false,"given":"Miao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James M.","family":"Rehg","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2200554"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_28"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299110"},{"key":"ref13","first-page":"422","article-title":"3D social saliency from head-mounted cameras","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299061"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0794-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299109"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref20","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref21","article-title":"Charades-Ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2986648"},{"key":"ref27","first-page":"704","article-title":"Forecasting human object interaction: Joint prediction of motor attention and egocentric activity","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2003.09.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(75)90290-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.30"},{"key":"ref32","article-title":"Learning embodied models of actions from first person video","author":"Li","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005594"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref38","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00188"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref58","article-title":"Attention distillation for learning video representations","volume-title":"Proc. British Mach. Vis. Conf.","author":"Liu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.296"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.101"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_60"},{"key":"ref65","first-page":"2409","article-title":"Action is in the eye of the beholder: Eye-gaze driven model for spatio-temporal action localization","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Shapovalova"},{"key":"ref66","article-title":"Action recognition using visual attention","volume-title":"Proc. Int. Conf. Learn. Representations Workshops","author":"Sharma"},{"key":"ref67","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.326"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298666"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.443"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2470657"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MOBIHEALTH.2014.7015908"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.721"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.464"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16811-1_21"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299183"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2409731"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.377"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00812"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477708"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_13"},{"key":"ref95","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","volume-title":"Proc. British Mach. Vis. Conf.","author":"Sudhakaran"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00540"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462002"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.235"},{"key":"ref99","first-page":"1556","article-title":"ELAN: A professional framework for multimodality research","volume-title":"Proc. 5th Int. Conf. Lang. Resour. Eval.","author":"Wittenburg"},{"key":"ref100","article-title":"Guide to the carnegie mellon university multimodal activity (CMU-MMAC) database","author":"la Torre Frade","year":"2008"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref103","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref104","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref105","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref106","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison"},{"key":"ref107","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref108","first-page":"10727","article-title":"Dropblock: A regularization method for convolutional networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ghiasi"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref112","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref117","article-title":"Baidu-UTS submission to the EPIC-kitchens action recognition challenge 2019","author":"Wang","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09325929.pdf?arnumber=9325929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:25:07Z","timestamp":1704846307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9325929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":117,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3051319","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]]}}}