{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:50:16Z","timestamp":1771959016452,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":["61871435"],"award-info":[{"award-number":["61871435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2019kfyXKJC024"],"award-info":[{"award-number":["2019kfyXKJC024"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tmm.2019.2959425","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T20:44:46Z","timestamp":1576183486000},"page":"2610-2622","source":"Crossref","is-referenced-by-count":32,"title":["GLNet: Global Local Network for Weakly Supervised Action Localization"],"prefix":"10.1109","volume":"22","author":[{"given":"Shiwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-3920","authenticated-orcid":false,"given":"Changxin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9167-1496","authenticated-orcid":false,"given":"Nong","family":"Sang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref32","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref30","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref37","article-title":"Deep learning for detecting multiple space-time action tubes in videos","author":"saha","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.65"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00043-X"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.22"},{"key":"ref12","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"NIPS Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref15","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref19","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2814346"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.473"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2758524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1109\/TMM.2017.2772441","article-title":"Impact localization on rigid surfaces using hermitian angle distribution for human-computer interface applications","volume":"20","author":"nguyen","year":"2018","journal-title":"IEEE Trans Multimedia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.58"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.309"},{"key":"ref42","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.82"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.193"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/s19051085"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9204776\/08931624.pdf?arnumber=8931624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:42Z","timestamp":1651075002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8931624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2959425","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}