{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:07:34Z","timestamp":1756426054495,"version":"3.44.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019600","name":"Hanoi University of Science and Technology","doi-asserted-by":"crossref","award":["T2023-PC-028"],"award-info":[{"award-number":["T2023-PC-028"]}],"id":[{"id":"10.13039\/100019600","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3601235","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:31:04Z","timestamp":1755801064000},"page":"148170-148191","source":"Crossref","is-referenced-by-count":0,"title":["M\u00b3-SLR: Self-Supervised Pretraining With MaxFlow MaskFeat for Improved Multi-View Sign Language Representation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5818-6570","authenticated-orcid":false,"given":"Tran Tri Dung","family":"Nguyen","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3759-2827","authenticated-orcid":false,"given":"Thi Thuy Nga","family":"Do","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4603-1297","authenticated-orcid":false,"given":"Quang Huy","family":"Hoang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6547-7641","authenticated-orcid":false,"given":"Phi Le","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-6491","authenticated-orcid":false,"given":"Anh Vu","family":"Tran","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3305255"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3148132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"ref6","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref8","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref9","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018","journal-title":"arXiv:1808.01340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref13","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00766"},{"key":"ref15","article-title":"MM-WLAuslan: Multi-view multi-modal word-level Australian sign language recognition dataset","author":"Shen","year":"2024","journal-title":"arXiv:2410.19488"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409728"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01163"},{"issue":"11","key":"ref19","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1016\/j.patrec.2013.04.017","article-title":"Thai sign language translation using scale invariant feature transform and hidden Markov models","volume":"34","author":"Auephanwiriyakul","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iscv.1995.477012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1134\/s1054661816020164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2904749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990434"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3656046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151362"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00507"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02216"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.neucom.2020.03.126","article-title":"Adaptive multi-view graph convolutional networks for skeleton-based action recognition","volume":"444","author":"Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"issue":"5","key":"ref46","first-page":"4873","article-title":"DVANet: Disentangling view and action features for multi-view action recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Siddiqui"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612221"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_26"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032738"},{"key":"ref50","first-page":"2943","article-title":"MVFNet: Multi-view fusion network for efficient video recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Wu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00712"},{"article-title":"How do vision transformers work?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park","key":"ref52"},{"key":"ref53","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref56","first-page":"13193","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dao"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3436754"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"issue":"11","key":"ref62","first-page":"120","article-title":"The OpenCV library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s J. Softw. Tools"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3028072"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00383"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274783"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416881"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11132300.pdf?arnumber=11132300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:11:11Z","timestamp":1756404671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3601235","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}