{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:26:27Z","timestamp":1770917187337,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673270"],"award-info":[{"award-number":["61673270"]}],"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":["61973212"],"award-info":[{"award-number":["61973212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017599","name":"Science and Technology Project of Zhejiang Province","doi-asserted-by":"publisher","award":["2022C01013"],"award-info":[{"award-number":["2022C01013"]}],"id":[{"id":"10.13039\/501100017599","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Key Laboratory of Artificial Intelligence","award":["2022RZY02"],"award-info":[{"award-number":["2022RZY02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tcsvt.2022.3207518","type":"journal-article","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T19:39:16Z","timestamp":1663357156000},"page":"977-987","source":"Crossref","is-referenced-by-count":27,"title":["A Progressive Difference Method for Capturing Visual Tempos on Action Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5031-795X","authenticated-orcid":false,"given":"Xiaoxiao","family":"Sheng","sequence":"first","affiliation":[{"name":"Advanced Avionics and Intelligent Information Laboratory, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Kunchang","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Science, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3749-3115","authenticated-orcid":false,"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9259-6790","authenticated-orcid":false,"given":"Gang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Advanced Avionics and Intelligent Information Laboratory, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref12","volume-title":"Digital Image Processing","author":"Gonzalez","year":"2002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref14","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume-title":"arXiv:1212.0402","author":"Soomro","year":"2012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref24","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feichtenhofer"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.01.020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref31","article-title":"CT-Net: Channel tensorization network for video classification","volume-title":"arXiv:2106.01603","author":"Li","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103677"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093500"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref37","article-title":"Video representation learning with visual tempo consistency","volume-title":"arXiv:2006.15489","author":"Yang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2854176"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2883825"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00531"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3124562"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00311"},{"key":"ref44","article-title":"Searching multi-rate and multi-modal temporal enhanced networks for gesture recognition","volume-title":"arXiv:2008.09412","author":"Yu","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00534"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109517"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref51","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"arXiv:1912.00869","author":"Fan","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_22"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01661-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00090"},{"key":"ref57","first-page":"11026","article-title":"Dynamic normalization and relay for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cai"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00346"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10061510\/09894401.pdf?arnumber=9894401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:20:25Z","timestamp":1705958425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9894401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3207518","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}