{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:22:39Z","timestamp":1769271759374,"version":"3.49.0"},"reference-count":69,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2021.3076522","type":"journal-article","created":{"date-parts":[[2021,4,29]],"date-time":"2021-04-29T19:52:05Z","timestamp":1619725925000},"page":"1-1","source":"Crossref","is-referenced-by-count":36,"title":["Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition"],"prefix":"10.1109","author":[{"given":"Sudhakar","family":"Kumawat","sequence":"first","affiliation":[]},{"given":"Manisha","family":"Verma","sequence":"additional","affiliation":[]},{"given":"Yuta","family":"Nakashima","sequence":"additional","affiliation":[]},{"given":"Shanmuganathan","family":"Raman","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.60"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and $<$<0.5 mb model size,","author":"Iandola","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.148"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref13","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications,","author":"Howard","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172374"},{"key":"ref24","first-page":"5843","article-title":"The","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Goyal"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref27","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild,","author":"Soomro","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00504"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref33","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref38","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Christoph"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref43","article-title":"Convnet architecture search for spatiotemporal feature learning,","author":"Tran","year":"2017"},{"key":"ref44","article-title":"The kinetics human action video dataset,","author":"Kay","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref46","first-page":"352","article-title":"A\u22272-Nets: Double attention networks,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"ref53","article-title":"Reducing overfitting in deep networks by decorrelating representations,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cogswell"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0063"},{"key":"ref56","article-title":"Regularizing CNNs with locally constrained decorrelations,","author":"Rodr\u00edguez","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref57","volume-title":"Fundamentals of Digital Image Processing","author":"Jain","year":"1989"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LNLA.2009.5278397"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21227-7_34"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053898"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref63","article-title":"Learning discriminative motion features through detection,","author":"Bertasius","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00302"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00687"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09419752.pdf?arnumber=9419752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:25:07Z","timestamp":1704846307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9419752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3076522","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}