{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T08:53:27Z","timestamp":1782982407024,"version":"3.54.5"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42327901"],"award-info":[{"award-number":["42327901"]}],"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":["62321005"],"award-info":[{"award-number":["62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BNRist project","award":["BNR2024TD03003"],"award-info":[{"award-number":["BNR2024TD03003"]}]},{"name":"Tsinghua University-China Mobile Communications Group Company, Ltd. Joint Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3514654","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T18:55:44Z","timestamp":1733770544000},"page":"1782-1799","source":"Crossref","is-referenced-by-count":14,"title":["Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoji","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3155-1336","authenticated-orcid":false,"given":"Yang","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlan","family":"Feng","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864770"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13740-016-0060-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123433"},{"issue":"1\/68","key":"ref4","first-page":"1","article-title":"A system for video surveillance and monitoring","volume":"2000","author":"Collins","year":"2000","journal-title":"VSAM Final Rep."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2909473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383168"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01508-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01352"},{"key":"ref20","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263826"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref33","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref41","article-title":"AdaFuse: Adaptive temporal fusion network for efficient action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00793"},{"key":"ref44","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_40"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_42"},{"key":"ref60","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00908"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00188"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062644"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref71","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_16"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref75","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref76","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284"},{"key":"ref79","first-page":"552","article-title":"Better mixing via deep representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bengio"},{"key":"ref80","article-title":"Implicit semantic data augmentation for deep networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2964173"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237740"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01944-1"},{"key":"ref84","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref85","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref86","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref90","article-title":"Look more but care less in video recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIS46948.2019.9014714"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref100","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00610"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref108","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32205-4"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)00218-X"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00568-3"},{"key":"ref114","first-page":"8046","article-title":"Relational self-attention: What\u2019s missing in attention for video understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889096"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107110"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM47256.2019.8983000"},{"key":"ref118","article-title":"Med3D: Transfer learning for 3D medical image analysis","author":"Chen","year":"2019"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3197845"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50347-5_14"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.4114\/intartif.vol24iss67pp40-50"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/COMNETSAT53002.2021.9530829"},{"key":"ref124","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10787270.pdf?arnumber=10787270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:11Z","timestamp":1738821611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10787270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":121,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3514654","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":[[2025,3]]}}}