{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:39:59Z","timestamp":1775839199858,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3134694","type":"journal-article","created":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T20:37:07Z","timestamp":1639168627000},"page":"164887-164902","source":"Crossref","is-referenced-by-count":27,"title":["Deep Neural Networks Using Residual Fast-Slow Refined Highway and Global Atomic Spatial Attention for Action Recognition and Detection"],"prefix":"10.1109","volume":"9","author":[{"given":"Manh-Hung","family":"Ha","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5172-9913","authenticated-orcid":false,"given":"Oscal Tzyh-Chiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref32","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00301"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180826"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00677"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.82"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00627"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01017"},{"key":"ref21","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.103"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093617"},{"key":"ref51","first-page":"106","article-title":"Predicting action tubes","author":"singh","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","year":"2021","journal-title":"Datasheet Brio Ultra HD Pro Business Webcam"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078546"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00828"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2887283"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802979"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref14","article-title":"Highway networks","author":"kumar srivastava","year":"2015","journal-title":"arXiv 1505 00387"},{"key":"ref15","first-page":"2741","article-title":"Character-aware neural language models","author":"kim","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191290"},{"key":"ref18","article-title":"An end-to-end 3D convolutional neural network for action detection and segmentation in videos","author":"hou","year":"2017","journal-title":"arXiv 1712 01111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048741"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00811"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.402"},{"key":"ref46","article-title":"A short note about kinetics-600","author":"carreira","year":"2018","journal-title":"arXiv 1808 01340"},{"key":"ref45","article-title":"You only watch once: A unified CNN architecture for real-time spatiotemporal action localization","author":"k\u00f6p\u00fckl\u00fc","year":"2019","journal-title":"arXiv 1911 06644"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09646928.pdf?arnumber=9646928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T20:53:02Z","timestamp":1649105582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9646928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3134694","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}