{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:36Z","timestamp":1783542516195,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"Wenzhou Major Science and Technology Innovation Project","doi-asserted-by":"publisher","award":["ZG2024012"],"award-info":[{"award-number":["ZG2024012"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3674923","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:25:41Z","timestamp":1773779141000},"page":"9406-9417","source":"Crossref","is-referenced-by-count":0,"title":["Action Recognition in RGB-D Videos via an End-to-End Cross-Modal Attention Transformer"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8014-0067","authenticated-orcid":false,"given":"Yujun","family":"Ma","sequence":"first","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4883-5552","authenticated-orcid":false,"given":"Benjia","family":"Zhou","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Taipa, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-9841","authenticated-orcid":false,"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2261-5973","authenticated-orcid":false,"given":"Xizheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hunan Institute of Engineering, Xiangtan, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8962-540X","authenticated-orcid":false,"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7117-2772","authenticated-orcid":false,"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[{"name":"Geriatrics Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274783"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975845"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2021.05.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00153"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.36"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/bme2.12002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121503"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109905"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127027"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109884"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109231"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3207577"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3226410"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612301"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01952"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.04.007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268446"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3558939"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076165"},{"key":"ref33","first-page":"9938","article-title":"Mitigating modality collapse in multimodal VAEs via impartial optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Javaloy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.189"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12228"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.05.092"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965299"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109741"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3048883"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00331"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01917"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007534"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00942"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3529989"},{"key":"ref49","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Nagrani"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2104.10858"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112531"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/app14031190"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-025-01493-y"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88217-3_24"},{"key":"ref56","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20191"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378886"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2024.117244"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16430"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177813"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875441"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087348"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3295811"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12597"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11436021.pdf?arnumber=11436021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:46:05Z","timestamp":1783539965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11436021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":75,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3674923","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}