{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:39:14Z","timestamp":1783816754728,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62272096"],"award-info":[{"award-number":["62272096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jilin Provincial Science and Technology Department","award":["20210201077GX"],"award-info":[{"award-number":["20210201077GX"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3367599","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T18:56:23Z","timestamp":1708455383000},"page":"7398-7412","source":"Crossref","is-referenced-by-count":16,"title":["An Adaptive Dual Selective Transformer for Temporal Action Localization"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4955-8582","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4390-0508","authenticated-orcid":false,"given":"Guang","family":"Zu","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2970-3984","authenticated-orcid":false,"given":"Hui","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7095-2400","authenticated-orcid":false,"given":"Jun","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology and Key Laboratory of Applied Statistics of MOE, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4909-5077","authenticated-orcid":false,"given":"Yanni","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6867-3282","authenticated-orcid":false,"given":"Jianzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3252176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959977"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3166025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TDPVT.2002.1024148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_33"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0122-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01241"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref15","first-page":"988","article-title":"Single shot temporal action detection","volume-title":"Proc. ACM Multimedia Conf.","author":"Li","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103484"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref25","article-title":"TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization","author":"Tang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01171"},{"key":"ref28","article-title":"Vision transformers with patch diversification","author":"Gong","year":"2021"},{"key":"ref29","volume-title":"Pattern Classification","author":"Webb","year":"2001"},{"key":"ref30","article-title":"EIT: Enhanced interactive transformer","author":"Zheng","year":"2022"},{"key":"ref31","article-title":"Talking-heads attention","author":"Shazeer","year":"2020"},{"key":"ref32","first-page":"1","article-title":"Efficient token mixing for transformers via adaptive fourier neural operators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guibas","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102850"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_37"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3552458.3556443"},{"key":"ref51","article-title":"Temporal action proposal generation with transformers","author":"Wang","year":"2021"},{"key":"ref52","first-page":"9204","article-title":"Pay attention to MLPs","volume-title":"Proc. Int. Conf. 34th Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2021"},{"key":"ref53","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst., 34th Annu. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263824"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref57","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"ref59","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref63","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref64","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01326"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20277"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3180925"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945289"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00301"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00151"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"ref74","first-page":"15268","article-title":"Pointtad: Multi-label temporal action detection with learnable query points","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Tan","year":"2022"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_16"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10440542.pdf?arnumber=10440542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:54:07Z","timestamp":1725904447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3367599","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}