{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:00:45Z","timestamp":1777874445348,"version":"3.51.4"},"reference-count":87,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2025YFHZ0162"],"award-info":[{"award-number":["2025YFHZ0162"]}],"id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Student Innovation and Entrepreneurship Training Program of Civil Aviation Flight University of China","award":["S20251062412"],"award-info":[{"award-number":["S20251062412"]}]},{"DOI":"10.13039\/501100012459","name":"Graduate Research Innovation Fund Project, in 2025","doi-asserted-by":"publisher","award":["25CAFUC10026"],"award-info":[{"award-number":["25CAFUC10026"]}],"id":[{"id":"10.13039\/501100012459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3686827","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:59:49Z","timestamp":1776974389000},"page":"62818-62833","source":"Crossref","is-referenced-by-count":0,"title":["STT-CL: A Unified Spatio-Temporal-Task Framework for Continual Learning in Gloss-Free Multilingual Sign Language Translation"],"prefix":"10.1109","volume":"14","author":[{"given":"AI","family":"Wang","sequence":"first","affiliation":[{"name":"School of Foreign Languages, Civil Aviation Flight University of China, Guanghan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9092-6872","authenticated-orcid":false,"given":"Zhipeng","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Civil Aviation Flight University of China, Guanghan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Civil Aviation Flight University of China, Guanghan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-7440-0_3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113794"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4324\/9780429280641-19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.136"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177428"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.525"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"ref10","first-page":"12034","article-title":"TSPNet: Hierarchical feature learning via temporal semantic pyramid for sign language translation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1163\/9789004495746"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353774"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00505"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0047507"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ELTECH.2019.8839587"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39431-8_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139163910"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref26","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fifty"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1017\/S1366728998000133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app9132683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3477498"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-demo.19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2007-668"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.364"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/123"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_3"},{"key":"ref38","article-title":"Data augmentation for sign language gloss translation","author":"Moryossef","year":"2021","journal-title":"arXiv:2105.07476"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1240"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3404869"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02216"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"},{"key":"ref49","article-title":"Towards robust evaluations of continual learning","author":"Farquhar","year":"2018","journal-title":"arXiv:1805.09733"},{"key":"ref50","article-title":"Three scenarios for continual learning","author":"van de Ven","year":"2019","journal-title":"arXiv:1904.07734"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"ref53","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lopez-Paz"},{"key":"ref54","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Buzzega"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref57","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref58","article-title":"Lifelong learning with dynamically expandable networks","author":"Yoon","year":"2017","journal-title":"arXiv:1708.01547"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500205"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10822-9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref65","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"issue":"120","key":"ref66","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref67","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv:2006.16668"},{"key":"ref68","first-page":"5547","article-title":"GLAM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Du"},{"key":"ref69","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Riquelme"},{"key":"ref70","first-page":"17555","article-title":"Hash layers for large sparse models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Roller"},{"key":"ref71","first-page":"6265","article-title":"Base layers: Simplifying training of large, sparse models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lewis"},{"key":"ref72","first-page":"18332","article-title":"DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rajbhandari"},{"key":"ref73","article-title":"Learning factored representations in a deep mixture of experts","author":"Eigen","year":"2013","journal-title":"arXiv:1312.4314"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref75","article-title":"No language left behind: Scaling human-centered machine translation","author":"Team","year":"2022","journal-title":"arXiv:2207.04672"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-short.43"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref79","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref80","article-title":"Efficient lifelong learning with A-GEM","author":"Chaudhry","year":"2018","journal-title":"arXiv:1812.00420"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref83","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref84","first-page":"4694","article-title":"When does label smoothing help?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"M\u00fcller"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"ref87","first-page":"348","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rolnick"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11493888.pdf?arnumber=11493888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:48:54Z","timestamp":1777578534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11493888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3686827","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}