{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:47:52Z","timestamp":1775069272966,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["2022ZD0160402"],"award-info":[{"award-number":["2022ZD0160402"]}],"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":["U21A20514"],"award-info":[{"award-number":["U21A20514"]}],"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":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3262670","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T19:20:45Z","timestamp":1680031245000},"page":"5932-5946","source":"Crossref","is-referenced-by-count":27,"title":["Task-Aware Dual-Representation Network for Few-Shot Action Recognition"],"prefix":"10.1109","volume":"33","author":[{"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}]},{"given":"Weirong","family":"Ye","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}]},{"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"Applied Research Center (ARC), Tencent PCG, Shenzhen, China"}]},{"given":"Guangge","family":"Wang","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}]},{"given":"Jianping","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Applied Research Center (ARC), Tencent PCG, Shenzhen, China"}]},{"given":"Xiaohu","family":"Qie","sequence":"additional","affiliation":[{"name":"Applied Research Center (ARC), Tencent PCG, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-9786","authenticated-orcid":false,"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587598"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref56","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref15","first-page":"4847","article-title":"Adaptive cross-modal few-shot learning","author":"xing","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/100"},{"key":"ref58","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00894"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475232"},{"key":"ref54","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00160"},{"key":"ref16","article-title":"Baby steps towards few-shot learning with multiple semantics","author":"schwartz","year":"2019","journal-title":"arXiv 1906 01905"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475560"},{"key":"ref51","article-title":"Few-shot action recognition with prototype-centered attentive learning","author":"zhu","year":"2021","journal-title":"arXiv 2101 08085"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475253"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475216"},{"key":"ref45","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref44","first-page":"4080","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475243"},{"key":"ref7","first-page":"2371","article-title":"MetaGAN: An adversarial approach to few-shot learning","author":"zhang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475532"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2914137"},{"key":"ref40","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475200"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478873"},{"key":"ref37","article-title":"Meta-learning with differentiable closed-form solvers","author":"bertinetto","year":"2018","journal-title":"arXiv 1805 08136"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/409"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2746092"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2818151"},{"key":"ref39","article-title":"Learning to learn: Meta-critic networks for sample efficient learning","author":"sung","year":"2017","journal-title":"arXiv 1706 09529"},{"key":"ref38","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"2017","journal-title":"arXiv 1707 03141"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref72","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00828"},{"key":"ref25","first-page":"1","article-title":"Look more but care less in video recognition","author":"zhang","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103677"},{"key":"ref64","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"bishay","year":"2019","journal-title":"arXiv 1907 09021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978855"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3175923"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015051"},{"key":"ref65","article-title":"Weakly-supervised compositional feature aggregation for few-shot recognition","author":"hu","year":"2019","journal-title":"arXiv 1906 04833"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref60","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10083098.pdf?arnumber=10083098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:31:53Z","timestamp":1698085913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10083098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":72,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3262670","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}