{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T03:43:34Z","timestamp":1790221414363,"version":"4.1.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["61772067"],"award-info":[{"award-number":["61772067"]}],"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":["61472030"],"award-info":[{"award-number":["61472030"]}],"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":["61471032"],"award-info":[{"award-number":["61471032"]}],"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":["2017JBZ108"],"award-info":[{"award-number":["2017JBZ108"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2978613","type":"journal-article","created":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T03:13:31Z","timestamp":1585624411000},"page":"334-347","source":"Crossref","is-referenced-by-count":53,"title":["Global and Local Knowledge-Aware Attention Network for Action Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6749-4952","authenticated-orcid":false,"given":"Zhenxing","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2843-843X","authenticated-orcid":false,"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dapeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuqi","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","article-title":"Hierarchical attention network for action recognition in videos","author":"wang","year":"2016","journal-title":"arXiv 1607 06416"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref33","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.12.008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref34","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2912357"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877936"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2740318"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.071"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2611485"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.05.058"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.236"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917283"},{"key":"ref68","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2669522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3772","DOI":"10.1109\/TNNLS.2017.2741598","article-title":"Efficient online learning algorithms based on LSTM neural networks","volume":"29","author":"ergen","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.086"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2866688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref11","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","author":"anderson","year":"1985","journal-title":"Cognitive Psychology and Its Implications"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref14","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"1","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2576761"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully convolutional networks for semantic segmentation","volume":"39","author":"long","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545710"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref45","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref47","first-page":"713","article-title":"ECO: Efficient convolutional network for online video understanding","author":"zolfaghari","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1477"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref43","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09050644.pdf?arnumber=9050644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:01Z","timestamp":1652194381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9050644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":70,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2978613","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}