{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:48:32Z","timestamp":1781621312169,"version":"3.54.5"},"reference-count":85,"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\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","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":["U21B2043"],"award-info":[{"award-number":["U21B2043"]}],"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":["62072026"],"award-info":[{"award-number":["62072026"]}],"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":["62102419"],"award-info":[{"award-number":["62102419"]}],"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":["62120106009"],"award-info":[{"award-number":["62120106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["JQ20022"],"award-info":[{"award-number":["JQ20022"]}]},{"name":"Chinese Association for Artificial Intelligence (CAAI)-Compute Architecture for Neural Networks (CANN) Open Fund, developed on OpenI Community"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3413599","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T18:10:52Z","timestamp":1718734252000},"page":"4002-4015","source":"Crossref","is-referenced-by-count":23,"title":["Learnable Feature Augmentation Framework for Temporal Action Localization"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4314-7550","authenticated-orcid":false,"given":"Yepeng","family":"Tang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology and the Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7299-6431","authenticated-orcid":false,"given":"Weining","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-8995","authenticated-orcid":false,"given":"Chunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology and the Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology and the Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185485"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3078324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3182866"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00104"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00151"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3222623"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01320"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"issue":"1","key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103141","article-title":"Anchor-free temporal action localization via progressive boundary-aware boosting","volume":"60","author":"Tang","year":"2023","journal-title":"Inf. Process. Manage."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.04.004"},{"issue":"3","key":"ref28","first-page":"1","article-title":"Dynamic hand gesture recognition using multi-direction 3D convolutional neural networks","volume":"27","author":"Li","year":"2019","journal-title":"Eng. Lett."},{"key":"ref29","article-title":"VideoMix: Rethinking data augmentation for video classification","author":"Yun","year":"2020","journal-title":"arXiv:2012.03457"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2947442"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917867"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413860"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00194"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/96"},{"key":"ref36","article-title":"Convex combination consistency between neighbors for weakly-supervised action localization","author":"Liu","year":"2022","journal-title":"arXiv:2205.00400"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref38","first-page":"14290","article-title":"Semmae: Semantic-guided masking for learning masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8543-2_31"},{"key":"ref40","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Rao"},{"key":"ref41","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_37"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01238"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00951"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01806"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103692"},{"key":"ref61","article-title":"Adapting short-term transformers for action detection in untrimmed videos","author":"Yang","year":"2023","journal-title":"arXiv:2312.01897"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref63","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv: 2212.03191"},{"key":"ref64","article-title":"TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization","author":"Tang","year":"2023","journal-title":"arXiv:2303.09055"},{"key":"ref65","article-title":"End-to-end temporal action detection with 1B parameters across 1000 frames","author":"Liu","year":"1000","journal-title":"arXiv:2311.17241"},{"key":"ref66","volume-title":"THUMOS Challenge: Action Recognition With a Large Number of Classes","author":"Jiang","year":"2014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217368"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref71","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref73","article-title":"ActivityNet challenge 2017 summary","author":"Ghanem","year":"2017","journal-title":"arXiv:1710.08011"},{"key":"ref74","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"arXiv:2203.12602"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109560"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_16"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295090"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01351"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref85","volume-title":"MAFM","year":"2024"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10562229.pdf?arnumber=10562229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T17:52:23Z","timestamp":1719856343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10562229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3413599","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}