{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T14:23:42Z","timestamp":1782570222245,"version":"3.54.5"},"reference-count":126,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFA1008503"],"award-info":[{"award-number":["2023YFA1008503"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470202"],"award-info":[{"award-number":["92470202"]}],"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":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong NSF Project","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tpami.2024.3429387","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T17:24:17Z","timestamp":1721150657000},"page":"679-696","source":"Crossref","is-referenced-by-count":14,"title":["Human-Centric Transformer for Domain Adaptive Action Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0013-3730","authenticated-orcid":false,"given":"Kun-Yu","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Zhou","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":"10.1007\/s11263-022-01594-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.001"},{"key":"ref13","article-title":"Deep domain adaptation in action space","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Jamal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref16","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01859"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00436"},{"key":"ref19","article-title":"ARID: A comprehensive study on recognizing actions in the dark and a new benchmark dataset","author":"Xu","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref21","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref22","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413897"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3212909"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref28","first-page":"851","article-title":"Why can\u2019t I dance in the mall? Learning to mitigate scene bias in action recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Choi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01446-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01823"},{"key":"ref32","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref33","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref41","first-page":"1","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref42","first-page":"1","article-title":"CT-Net: Channel tensorization network for video classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref53","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01578"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref57","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Gao"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_40"},{"key":"ref67","first-page":"23386","article-title":"Contrast and mix: Temporal contrastive video domain adaptation with background mixing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sahoo"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00966"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01431"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116945"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref75","article-title":"Diversifying spatial-temporal perception for video domain generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01256"},{"key":"ref77","article-title":"Rethinking CLIP-based video learners in cross-domain open-vocabulary action recognition","author":"Lin","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00920"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880750"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_9"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref83","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_28"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref89","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00151"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_28"},{"key":"ref92","first-page":"2988","article-title":"Asymmetric tri-training for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saito"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00875"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01636"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00288"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_31"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.88"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_10"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00283"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00963"},{"key":"ref101","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. Berkeley Symp. Math. Statist. Probability","author":"MacQueen"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref103","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548313"},{"key":"ref107","first-page":"753","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00229"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref113","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref116","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01361"},{"key":"ref120","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":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10835210\/10599825.pdf?arnumber=10599825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:27:06Z","timestamp":1736540826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10599825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":126,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3429387","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}