{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:10Z","timestamp":1778171050804,"version":"3.51.4"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["2021ZD0110503"],"award-info":[{"award-number":["2021ZD0110503"]}],"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":["62022011"],"award-info":[{"award-number":["62022011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011347","name":"Research Program of the State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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":[[2023,12]]},"DOI":"10.1109\/tcsvt.2023.3283282","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T03:06:51Z","timestamp":1686107211000},"page":"7803-7818","source":"Crossref","is-referenced-by-count":26,"title":["Key Role Guided Transformer for Group Activity Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1584-5180","authenticated-orcid":false,"given":"Duoxuan","family":"Pei","sequence":"first","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2412-9330","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-4579","authenticated-orcid":false,"given":"Longteng","family":"Kong","sequence":"additional","affiliation":[{"name":"Intelligent Recognition and Image Processing Laboratory, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Intelligent Recognition and Image Processing Laboratory, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw.2009.5457461"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156634"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00808"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16437"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref15","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref20","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3232373"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3227172"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6247821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.228"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.783"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0944-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936410"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2914137"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461770"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref40","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref41","first-page":"1037","article-title":"Learning to propagate for graph meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015051"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3124562"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3043084"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3247103"},{"key":"ref48","article-title":"Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition","author":"Xu","year":"2023","journal-title":"arXiv:2302.02327"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3261659"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975671"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109665"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3211197"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3192661"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3164787"},{"key":"ref58","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref59","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3225549"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref66","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bulat"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3219339"},{"key":"ref68","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref69","first-page":"10750","article-title":"DropBlock: A regularization method for convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ghiasi"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref71","article-title":"DropBlock: A regularization method for convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ghiasi"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref74","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref78","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"ref80","article-title":"SaliencyMix: A saliency guided data augmentation strategy for better regularization","author":"Uddin","year":"2020","journal-title":"arXiv:2006.01791"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"ref82","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_27"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref87","article-title":"SAG-GAN: Semi-supervised attention-guided GANs for data augmentation on medical images","author":"Qi","year":"2020","journal-title":"arXiv:2011.07534"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3053460"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01324"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2019.8757971"},{"key":"ref95","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"issue":"11","key":"ref99","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10348119\/10144797.pdf?arnumber=10144797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:25:45Z","timestamp":1705026345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10144797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":99,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3283282","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}