{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:33:54Z","timestamp":1770834834947,"version":"3.50.1"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1911401"],"award-info":[{"award-number":["U1911401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong NSF","award":["2020B1515120085"],"award-info":[{"award-number":["2020B1515120085"]}]},{"name":"Guangdong NSF","award":["2018B030312002"],"award-info":[{"award-number":["2018B030312002"]}]},{"name":"Guangzhou Research Project","award":["201902010037"],"award-info":[{"award-number":["201902010037"]}]},{"name":"Key-Area Research and Development Program of Guangzhou","award":["202007030004"],"award-info":[{"award-number":["202007030004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3148790","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T21:04:55Z","timestamp":1644267895000},"page":"489-507","source":"Crossref","is-referenced-by-count":17,"title":["Egocentric Action Recognition by Automatic Relation Modeling"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7671-5609","authenticated-orcid":false,"given":"Haoxin","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9317-0268","authenticated-orcid":false,"given":"Jianguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Lab of Intelligent Technologies and Systems, Beijing National Research Center for Information Science and Technology (BNRist), Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jian-Huang","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00035"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093353"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00185"},{"key":"ref30","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.210"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00548"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.063"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref101","first-page":"100","article-title":"Learning covariant feature detectors","author":"lenc","year":"2016","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00537"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.306"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","volume":"41","author":"l","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref53","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc 27th Conf Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.54"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.82"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.10.015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952632"},{"key":"ref46","first-page":"753","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.288"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00812"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref72","first-page":"346","article-title":"Long-term activity forecasting using first-person vision","author":"bokhari","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00792"},{"key":"ref76","article-title":"Domain-specific priors and meta learning for low-shot first-person action recognition","author":"coskun","year":"2019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016481"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2019.8730673"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-019-0612-x"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref79","article-title":"Skip RNN: Learning to skip state updates in recurrent neural networks","author":"campos","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2832121"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.05.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00369"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref109","article-title":"An evaluation of action recognition models on epic-kitchens","author":"price","year":"2019"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref108","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":"ref94","article-title":"Relational long short-term memory for video action recognition","author":"chen","year":"2018"},{"key":"ref107","first-page":"214","article-title":"A duality based approach for realtime TV-L1 optical flow","author":"zach","year":"2007","journal-title":"Proc Pattern Recognition Symp"},{"key":"ref93","first-page":"7299","article-title":"Relational recurrent neural networks","author":"santoro","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref106","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref105","first-page":"3814","article-title":"Unsupervised keypoint learning for guiding class-conditional video prediction","author":"kim","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00440"},{"key":"ref104","first-page":"92","article-title":"Unsupervised learning of object structure and dynamics from videos","author":"minderer","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref111","first-page":"5843","article-title":"The “something something","author":"goyal","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.181"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2469286"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7429-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2901707"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.650"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00461"},{"key":"ref84","first-page":"2654","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","author":"narasimhan","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref19","article-title":"Joint encoding of appearance and motion features with self-supervision for first person action recognition","author":"planamente","year":"2020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00147"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00402"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09706375.pdf?arnumber=9706375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:14:04Z","timestamp":1672082044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9706375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":111,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3148790","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":[[2023,1,1]]}}}