{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:39:54Z","timestamp":1780519194927,"version":"3.54.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFE0110500"],"award-info":[{"award-number":["2021YFE0110500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072028"],"award-info":[{"award-number":["62072028"]}],"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":["62302391"],"award-info":[{"award-number":["62302391"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3390133","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:40:39Z","timestamp":1713375639000},"page":"8172-8187","source":"Crossref","is-referenced-by-count":14,"title":["GBC: Guided Alignment and Adaptive Boosting CLIP Bridging Vision and Language for Robust Action Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3676-4761","authenticated-orcid":false,"given":"Zhaoqilin","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2843-843X","authenticated-orcid":false,"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenxing","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0829-9230","authenticated-orcid":false,"given":"Shan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuqi","family":"Ruan","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01600-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref9","volume-title":"Constructivist Learning Theory","author":"Hein","year":"1991"},{"key":"ref10","volume-title":"An Advanced Textbook on Biodiversity: Principles and Practice","author":"Krishnamurthy","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11409-010-9060-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207518"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3173658"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076522"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235522"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250646"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00220"},{"key":"ref25","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","volume":"139","author":"Jia"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00127"},{"key":"ref27","article-title":"Temporal perceiving video-language pre-training","author":"Ma","year":"2023","journal-title":"arXiv:2301.07463"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref33","first-page":"1179","article-title":"Deep boosting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cortes"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.233"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9944-x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref41","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018","journal-title":"arXiv:1808.01340"},{"key":"ref42","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref46","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref52","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref53","first-page":"12786","article-title":"TokenLearner: Adaptive space-time tokenization for videos","volume-title":"Proc. NeurIPS","author":"Ryoo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103677"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref57","first-page":"1","article-title":"Can an image classifier suffice for action recognition?","volume-title":"Proc. ICLR","author":"Fan"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.09450"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3148588"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268134"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref65","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"Proc. NeurIPS","volume":"32","author":"Fan"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01465"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3100277"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/148"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228156"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_6"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.117"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00983"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_7"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272627"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50077-5_2"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref86","article-title":"All about knowledge graphs for actions","author":"Ghosh","year":"2020","journal-title":"arXiv:2008.12432"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10504260.pdf?arnumber=10504260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:53:13Z","timestamp":1727761993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":86,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3390133","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}