{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:02:03Z","timestamp":1763535723790,"version":"3.37.3"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2017YFC0804402"],"award-info":[{"award-number":["2017YFC0804402"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672485","61379130"],"award-info":[{"award-number":["61672485","61379130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Systems Journal"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/jsyst.2020.3001680","type":"journal-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T21:30:07Z","timestamp":1593466207000},"page":"2322-2330","source":"Crossref","is-referenced-by-count":11,"title":["A Cross-Modal Learning Approach for Recognizing Human Actions"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1769-9335","authenticated-orcid":false,"given":"Hui","family":"Zheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8136-6834","authenticated-orcid":false,"given":"Xin-Ming","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref73","DOI":"10.1109\/TMM.2018.2887021"},{"year":"2017","author":"bian","article-title":"Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification","key":"ref72"},{"doi-asserted-by":"publisher","key":"ref71","DOI":"10.1109\/TCE.2019.2895050"},{"year":"2018","author":"kong","article-title":"Human action recognition and prediction: A survey","key":"ref70"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.1609\/aaai.v33i01.33018401"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"publisher","key":"ref75","DOI":"10.1016\/j.image.2018.09.003"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/TCE.2019.2908986"},{"key":"ref33","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/TPAMI.2015.2389824"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TPAMI.2018.2868668"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR.2017.337"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/CVPR.2017.113"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.21236\/ADA623249"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/IROS.2015.7353481"},{"year":"2012","author":"soomro","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","key":"ref60"},{"key":"ref62","first-page":"760","article-title":"Particle swarm optimization","author":"kennedy","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref63","first-page":"1","article-title":"Exploring strategies for training deep neural networks","volume":"1","author":"larochelle","year":"2019","journal-title":"J Mach Learn Res"},{"year":"2013","author":"lin","article-title":"Network in network","key":"ref28"},{"doi-asserted-by":"publisher","key":"ref64","DOI":"10.1016\/j.cviu.2016.03.013"},{"year":"2013","author":"goodfellow","article-title":"Maxout networks","key":"ref27"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/CVPR.2015.7299059"},{"doi-asserted-by":"publisher","key":"ref66","DOI":"10.1109\/JSYST.2014.2341597"},{"key":"ref29","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"hu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"year":"2016","author":"shi","article-title":"Joint network based attention for action recognition","key":"ref67"},{"key":"ref68","first-page":"7834","article-title":"Attention clusters: Purely attention based local feature integration for video classification","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref69","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref2","first-page":"3","article-title":"Deep learning for video classification and captioning","author":"wu","year":"2016","journal-title":"Frontiers of Multimedia Research"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.imavis.2009.11.014"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TPAMI.2013.50"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1098\/rstb.1997.0108"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1093\/brain\/119.2.593"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2011.5995407"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1006\/cviu.1998.0716"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICCV.2013.441"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/JSYST.2014.2322503"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1016\/j.neucom.2014.12.020"},{"key":"ref59","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","author":"rifai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/CVPR.2016.319"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1109\/TPAMI.2017.2670560"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/TSMCA.2012.2226575"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1109\/TNNLS.2018.2844464"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/TCSVT.2018.2823360"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1016\/j.inffus.2019.02.007"},{"key":"ref52","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2014.223"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref12","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"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TPAMI.2012.59"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-3-319-46484-8_2"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref16","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/2964284.2964328"},{"key":"ref18","first-page":"423","article-title":"Exploiting feature and class relationships in video categorization with regularized deep neural networks","volume":"40","author":"jiang","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICCV.2017.316"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1007\/11744047_33"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2005.177"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/3065386"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2009.5206821"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2015.7298594"},{"year":"2014","author":"simonyan","article-title":"Very deep convolutional networks for large-scale image recognition","key":"ref7"},{"key":"ref49","first-page":"2286","article-title":"Canonical time warping for alignment of human behavior","author":"zhou","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","first-page":"2121","article-title":"DeViSe: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/ICCV.2013.261"},{"year":"2008","author":"rabiner","journal-title":"Fundamentals of speech recognition","key":"ref48"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/TPAMI.2017.2753232"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ACCESS.2018.2863943"},{"year":"2014","author":"venugopalan","article-title":"Translating videos to natural language using deep recurrent neural networks","key":"ref41"},{"year":"2017","author":"aytar","article-title":"See, hear, and read: Deep aligned representations","key":"ref44"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICCVW.2019.00461"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4267003\/9447942\/09127470.pdf?arnumber=9127470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:44Z","timestamp":1652194364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9127470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":75,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsyst.2020.3001680","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"type":"print","value":"1932-8184"},{"type":"electronic","value":"1937-9234"},{"type":"electronic","value":"2373-7816"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}