{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:17:03Z","timestamp":1766578623600,"version":"3.37.3"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771440","41776113"],"award-info":[{"award-number":["61771440","41776113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201806335022"],"award-info":[{"award-number":["201806335022"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010870","name":"Qingdao Municipal Science and Technology Bureau","doi-asserted-by":"publisher","award":["17-1-1-5-jch"],"award-info":[{"award-number":["17-1-1-5-jch"]}],"id":[{"id":"10.13039\/501100010870","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["201861007"],"award-info":[{"award-number":["201861007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2968024","type":"journal-article","created":{"date-parts":[[2020,1,20]],"date-time":"2020-01-20T20:43:47Z","timestamp":1579553027000},"page":"16785-16794","source":"Crossref","is-referenced-by-count":12,"title":["Learning Attention-Enhanced Spatiotemporal Representation for Action Recognition"],"prefix":"10.1109","volume":"8","author":[{"given":"Zhensheng","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangjie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8027-0734","authenticated-orcid":false,"given":"Haiyong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaorui","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-1767","authenticated-orcid":false,"given":"Zhibin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545710"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00126"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref28","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"2017","journal-title":"Proc NIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref27","article-title":"Attend and interact: Higher-order object interactions for video understanding","author":"ma","year":"2017","journal-title":"arXiv 1711 06330"},{"key":"ref29","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref22","first-page":"805","article-title":"Multi-attention multi-class constraint for fine-grained image recognition","author":"sun","year":"2018","journal-title":"Proc ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref23","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref51","first-page":"42","article-title":"Hierarchical vision-language alignment for video captioning","author":"zhang","year":"2019","journal-title":"Proc MMM"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00687"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref54","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"2018","journal-title":"Proc ECCV"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.873157"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref11","first-page":"7794","article-title":"Non-local neural networks","author":"wang","year":"2017","journal-title":"Proc CVPR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref13","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc NIPS"},{"key":"ref14","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref16","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref18","first-page":"4278","article-title":"Inception-V4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref5","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","first-page":"849","article-title":"Webly-supervised video recognition by mutually voting for relevant Web images and Web video frames","author":"gan","year":"2016","journal-title":"Proc ECCV"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref47","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08963915.pdf?arnumber=8963915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T20:09:54Z","timestamp":1643314194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8963915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2968024","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}