{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T22:42:36Z","timestamp":1768084956212,"version":"3.49.0"},"reference-count":72,"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":[{"name":"LiaoNing Province Higher Education Innovative Talents Program Support Project","award":["LR2019058"],"award-info":[{"award-number":["LR2019058"]}]},{"name":"LiaoNing Revitalization Talents Program","award":["XLYC1902095"],"award-info":[{"award-number":["XLYC1902095"]}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["JCTD-2018-11"],"award-info":[{"award-number":["JCTD-2018-11"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DREAM project of EU FP7-ICT","award":["611391"],"award-info":[{"award-number":["611391"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51575412"],"award-info":[{"award-number":["51575412"]}],"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":["51575338"],"award-info":[{"award-number":["51575338"]}],"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":["51575407"],"award-info":[{"award-number":["51575407"]}],"id":[{"id":"10.13039\/501100001809","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.2020.2977856","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T20:52:20Z","timestamp":1583182340000},"page":"43243-43255","source":"Crossref","is-referenced-by-count":39,"title":["A Discriminative Deep Model With Feature Fusion and Temporal Attention for Human Action Recognition"],"prefix":"10.1109","volume":"8","author":[{"given":"Jiahui","family":"Yu","sequence":"first","affiliation":[]},{"given":"Hongwei","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yueqiu","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Weihong","family":"Chin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8829-037X","authenticated-orcid":false,"given":"Naoyuki","family":"Kubota","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9524-7609","authenticated-orcid":false,"given":"Zhaojie","family":"Ju","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2014.6932656"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2015.7358903"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2015.0189"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CCST.2016.7815695"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/GET.2016.7916717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5370\/JEET.2016.11.6.1857"},{"key":"ref34","first-page":"1856","article-title":"Dense RGB-D map-based human tracking and activity recognition using skin joints features and self-organizing map","volume":"9","author":"farooq","year":"2015","journal-title":"KSII Trans Internet Inf Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00065-7_27"},{"key":"ref62","first-page":"656","article-title":"Convolutional-recursive deep learning for 3D object classification","author":"socher","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806296"},{"key":"ref63","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.498"},{"key":"ref64","article-title":"Pose-conditioned spatio-temporal attention for human action recognition","author":"baradel","year":"2017","journal-title":"arXiv 1703 10106"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.10.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691768"},{"key":"ref66","article-title":"Histogram of oriented displacements (HOD): Describing trajectories of human joints for action recognition","author":"gowayyed","year":"2013","journal-title":"Proc 23rd Int Joint Conf Artif Intell"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.07.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4563176"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2014.6890714"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2011.07.001"},{"key":"ref20","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.52"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537340"},{"key":"ref50","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.342"},{"key":"ref58","first-page":"332","article-title":"Combining 3D joints moving trend and geometry property for human action recognition","author":"liu","year":"2016","journal-title":"Proc IEEE Int Conf Syst Man Cybern (SMC)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.137"},{"key":"ref56","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv 1412 4729"},{"key":"ref55","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref53","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref52","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","first-page":"473","article-title":"Joint camera pose estimation and 3D human pose estimation in a multi-camera setup","author":"puwein","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref11","first-page":"455","article-title":"Human interaction recognition based on the co-occurence of visual words","author":"nour el houda slimani","year":"2014","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.04.038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT.2014.6963015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.08.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEV.2015.7334030"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref18","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2302558"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2014.6918647"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2015.38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.03.011"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s140711735"},{"key":"ref9","first-page":"1","article-title":"Human activity recognition using the labeled depth body parts information of depth silhouettes","volume":"27","author":"jalal","year":"2012","journal-title":"Proc 6th Int Symp Sustain Healthy Buildings"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2829-5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.03.024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref47","first-page":"525","article-title":"Histogram of oriented normal vectors for object recognition with a depth sensor","author":"tang","year":"2012","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952430"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.07.021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.03.001"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09020148.pdf?arnumber=9020148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:08:10Z","timestamp":1641949690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9020148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2977856","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}