{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:28:50Z","timestamp":1793377730095,"version":"4.5.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"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":["U1911401"],"award-info":[{"award-number":["U1911401"]}],"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":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong NSF","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong NSF","award":["2020B1515120085"],"award-info":[{"award-number":["2020B1515120085"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3302471","type":"journal-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:03:07Z","timestamp":1691431387000},"page":"2715-2728","source":"Crossref","is-referenced-by-count":16,"title":["TwinFormer: Fine-to-Coarse Temporal Modeling for Long-Term Action Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4760-9708","authenticated-orcid":false,"given":"Jiaming","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0013-3730","authenticated-orcid":false,"given":"Kun-Yu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9490-5502","authenticated-orcid":false,"given":"Yu-Kun","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3175374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127040"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref14","article-title":"Videograph: Recognizing minutes-long human activities in videos","author":"Hussein","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref32","article-title":"Spatial-temporal alignment network for action recognition and detection","author":"Liang","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref37","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3211423"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3189253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3148588"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01439"},{"key":"ref50","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3198011"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3198318"},{"key":"ref58","article-title":"Activity graph transformer for temporal action localization","author":"Nawhal","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref62","article-title":"MixConv: Mixed depthwise convolutional kernels","volume-title":"Proc. 30th Brit. Mach. Vis. Conf.","author":"Tan","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107671"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref67","article-title":"AssembleNet: Searching for multi-stream neural connectivity in video architectures","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Ryoo","year":"2020"},{"key":"ref68","article-title":"TokenLearner: What can 8 learned tokens do for images and videos","author":"Ryoo","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10210078.pdf?arnumber=10210078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:29:41Z","timestamp":1721928581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10210078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3302471","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}