{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T21:00:01Z","timestamp":1774558801303,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LQ23F030001"],"award-info":[{"award-number":["LQ23F030001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LZ23H180002"],"award-info":[{"award-number":["LZ23H180002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Autism Research Special Fund of Zhejiang Foundation for Disabled Persons","award":["2023008"],"award-info":[{"award-number":["2023008"]}]},{"name":"Cao Guangbiao High-Tech Development Fund","award":["2022RC009"],"award-info":[{"award-number":["2022RC009"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2024-00059"],"award-info":[{"award-number":["226-2024-00059"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52075530"],"award-info":[{"award-number":["52075530"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3431128","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T16:34:50Z","timestamp":1721752490000},"page":"5816-5827","source":"Crossref","is-referenced-by-count":3,"title":["Recognizing Video Activities in the Wild via View-to-Scene Joint Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-2481","authenticated-orcid":false,"given":"Jiahui","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, the MOE Key Laboratory of Biomedical Engineering, the State Key Laboratory of Modern Optical Instrumentation, and the Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing, University of Portsmouth, Portsmouth, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5099-482X","authenticated-orcid":false,"given":"Xuna","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5336-7952","authenticated-orcid":false,"given":"Xu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9524-7609","authenticated-orcid":false,"given":"Zhaojie","family":"Ju","sequence":"additional","affiliation":[{"name":"School of Computing, University of Portsmouth, Portsmouth, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8317-0608","authenticated-orcid":false,"given":"Yingke","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, the MOE Key Laboratory of Biomedical Engineering, the State Key Laboratory of Modern Optical Instrumentation, and the Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2967093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3203631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3129077"},{"key":"ref4","first-page":"1","article-title":"Can an image classifier suffice for action recognition?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3074873"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2819026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01301-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.ade7996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096209"},{"key":"ref16","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Patrick"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3524497"},{"key":"ref22","article-title":"TAda! Temporally-adaptive convolutions for video understanding","author":"Huang","year":"2021","journal-title":"arXiv:2110.06178"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat7544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3017866"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3161726"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3143133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01940"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053765"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19998"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216084"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref38","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3230249"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3157793"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235522"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12876"},{"key":"ref46","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tong"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3331841"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00933"},{"key":"ref50","first-page":"1","article-title":"CAST: Cross-attention in space and time for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lee"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3491228"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3227816"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109540"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00331"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS58004.2023.00221"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10608038.pdf?arnumber=10608038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:53:22Z","timestamp":1774554802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10608038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3431128","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}