{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T21:57:35Z","timestamp":1774735055776,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST 109-2221-E-011-116"],"award-info":[{"award-number":["MOST 109-2221-E-011-116"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST 109-2221-E-011-131"],"award-info":[{"award-number":["MOST 109-2221-E-011-131"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3056892","type":"journal-article","created":{"date-parts":[[2021,2,8]],"date-time":"2021-02-08T23:23:20Z","timestamp":1612826600000},"page":"625-639","source":"Crossref","is-referenced-by-count":16,"title":["Spatial-Temporal Action Localization With Hierarchical Self-Attention"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-5167","authenticated-orcid":false,"given":"Rizard Renanda Adhi","family":"Pramono","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-1603","authenticated-orcid":false,"given":"Yie-Tarng","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6402-2688","authenticated-orcid":false,"given":"Wen-Hsien","family":"Fang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71607-7_23"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6811"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00044"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_19"},{"key":"ref39","first-page":"6299","author":"carreira","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref38","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350978"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref36","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref60","first-page":"1961","article-title":"Oncel tuzel, and ming shao. a. multi-stream bi-directional recurrent neural network for fine-grained action detection","author":"singh","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref62","author":"mcguire","year":"1982","journal-title":"Matrix Structural Analysis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref63","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref64","first-page":"6489","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"},{"key":"ref67","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"12","author":"soomro","year":"2012","journal-title":"Computer and Vision Research Center"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref69","first-page":"181","article-title":"Action recognition in realistic sports","author":"soomro","year":"0","journal-title":"Proc Int Workshop Comput Vis Sports"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-010-0501-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8625004"},{"key":"ref20","first-page":"7610","article-title":"VideoCapsuleNet: A simplified network for action detection","author":"duarte","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.12.019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_30"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref56","first-page":"104","article-title":"Deep affinity network for multiple object tracking","volume":"43","author":"sun","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922125"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.534"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2887283"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.95"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref19","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.58"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.296"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899910"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2749125"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2919434"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2900649"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930344"},{"key":"ref44","first-page":"71","article-title":"Empowering relational network by self-attention augmented conditional random fields for group activity recognition","author":"renanda","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2953814"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09349142.pdf?arnumber=9349142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T17:57:17Z","timestamp":1649440637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9349142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3056892","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}