{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:31:51Z","timestamp":1793377911798,"version":"4.5.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62376186"],"award-info":[{"award-number":["62376186"]}],"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":["61932009"],"award-info":[{"award-number":["61932009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese Association for Artificial Intelligence -Huawei MindSpore Open Fund","doi-asserted-by":"publisher","award":["CAAIXSJLJJ-2022-017A"],"award-info":[{"award-number":["CAAIXSJLJJ-2022-017A"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2024.3525187","type":"journal-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T15:41:00Z","timestamp":1736523660000},"page":"14664-14677","source":"Crossref","is-referenced-by-count":4,"title":["A Static-Dynamic Composition Framework for Efficient Action Recognition"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1805-5435","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Machine Learning, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-1398","authenticated-orcid":false,"given":"Yahong","family":"Han","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Machine Learning, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-7482","authenticated-orcid":false,"given":"Changlin","family":"Li","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[{"name":"Baidu Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2997020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067028"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref13","first-page":"1","article-title":"Liteeval: A coarse-to-fine framework for resource efficient video recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref14","first-page":"1","article-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Meng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref22","first-page":"1","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref23","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3243246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190367"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref33","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Akbari"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076522"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191461"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_38"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310661"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3321141"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_14"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00336"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00620"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475216"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00837"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref58","first-page":"1","article-title":"Meta-weight-Net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"ref60","first-page":"37865","article-title":"Rethinking resolution in the context of efficient video recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ma"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref67","volume-title":"Mindspore","year":"2024"},{"key":"ref68","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01320"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10836808.pdf?arnumber=10836808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:01:25Z","timestamp":1754503285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10836808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":74,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3525187","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}