{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:41:09Z","timestamp":1777322469057,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB3311602"],"award-info":[{"award-number":["2024YFB3311602"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272144"],"award-info":[{"award-number":["62272144"]}],"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":["62576131"],"award-info":[{"award-number":["62576131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Natural Science Foundation","award":["2408085MF157"],"award-info":[{"award-number":["2408085MF157"]}]},{"name":"Major Project of Anhui Province","award":["2408085J040"],"award-info":[{"award-number":["2408085J040"]}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2023-015"],"award-info":[{"award-number":["GXXT-2023-015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651108","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"3121-3134","source":"Crossref","is-referenced-by-count":0,"title":["Mask-Aware Kernel Learning for Action Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7332-5653","authenticated-orcid":false,"given":"Kewei","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer and Information, the Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6540-1159","authenticated-orcid":false,"given":"Chongjia","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer and Information, the Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9834-4730","authenticated-orcid":false,"given":"Zhao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer and Information, the Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4116-4477","authenticated-orcid":false,"given":"Kun","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Computer and Information, the Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer and Information, the Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688973"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3712012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085755"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01754"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02085"},{"key":"ref9","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref14","first-page":"12786","article-title":"Tokenlearner: Adaptive space-time tokenization for videos","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst.","author":"Ryoo","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref16","first-page":"79399","article-title":"CAST: Cross-attention in space and time for video action recognition","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2023"},{"key":"ref17","first-page":"1","article-title":"Uniformer: Unified transformer for efficient spatial-temporal representation learning","volume-title":"Proc. 10th Int. Conf Learn. Representations","author":"Li","year":"2022"},{"key":"ref18","article-title":"Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer","author":"Li","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref23","first-page":"1","article-title":"AIM: Adapting image models for efficient video action recognition","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_25"},{"key":"ref25","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning for action recognition","author":"Pan","year":"2022"},{"key":"ref26","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319140"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_40"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01261"},{"key":"ref31","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst.","author":"Patrick","year":"2021"},{"key":"ref32","first-page":"13627","article-title":"Alignment-guided temporal attention for video action recognition","volume-title":"Proc. 35th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhao","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref35","article-title":"Temporally-adaptive models for efficient video understanding","author":"Huang","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3224327"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref43","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. 35th Annu. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263288"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01768"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01784"},{"key":"ref49","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28361"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25923"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00572"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28291"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00972"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243615"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263952"},{"key":"ref60","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803153"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329506.pdf?arnumber=11329506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:50:29Z","timestamp":1777319429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651108","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}