{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T21:45:47Z","timestamp":1768686347255,"version":"3.49.0"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101524"],"award-info":[{"award-number":["62101524"]}],"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":["U21B2026"],"award-info":[{"award-number":["U21B2026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406703"],"award-info":[{"award-number":["2020YFB1406703"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2021-009"],"award-info":[{"award-number":["GXXT-2021-009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3221292","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T20:40:29Z","timestamp":1668544829000},"page":"7279-7291","source":"Crossref","is-referenced-by-count":14,"title":["Spatio-Temporal Collaborative Module for Efficient Action Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"first","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science, School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4881-9344","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science, School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}]},{"given":"Yi","family":"Tan","sequence":"additional","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science, School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science, School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-9873","authenticated-orcid":false,"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Zhejiang University, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, Anhui, China"}]}],"member":"263","reference":[{"key":"ref39","article-title":"SlowFast networks for video recognition","author":"feichtenhofer","year":"2018","journal-title":"arXiv 1812 03982"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref33","first-page":"214","article-title":"A duality based approach for realtime TV-L1 optical flow","author":"zach","year":"2007","journal-title":"Proc Pattern Recognition Symp"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2896529"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2740318"},{"key":"ref34","article-title":"V4D:4D convolutional neural networks for video-level representation learning","author":"zhang","year":"2020","journal-title":"arXiv 2002 07442"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890749"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref58","first-page":"1","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"sudhakaran","year":"2018","journal-title":"Proc BMVC"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref14","article-title":"TAM: Temporal adaptive module for video recognition","author":"liu","year":"2020","journal-title":"arXiv 2005 06803"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref16","first-page":"695","article-title":"ECO: Efficient convolutional network for online video understanding","author":"zolfaghari","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref8","article-title":"TSM: Temporal shift module for efficient video understanding","author":"lin","year":"2018","journal-title":"arXiv 1811 08383"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984904"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978613"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref47","article-title":"On the effectiveness of task granularity for transfer learning","author":"mahdisoltani","year":"2018","journal-title":"arXiv 1804 09235"},{"key":"ref42","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","author":"fan","year":"2019","journal-title":"arXiv 1912 00869"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00806"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09952204.pdf?arnumber=9952204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:46:34Z","timestamp":1670874394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9952204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3221292","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}