{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:34Z","timestamp":1792786894335,"version":"4.5.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU"},{"name":"MCC Lab of Information Science and Technology Institution"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021520","name":"National Supercomputing Center, Korea Institute of Science and Technology Information","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021520","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3599313","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:47:32Z","timestamp":1755197252000},"page":"11753-11767","source":"Crossref","is-referenced-by-count":15,"title":["Scaling up Multimodal Pre-Training for Sign Language Understanding"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7098-1690","authenticated-orcid":false,"given":"Weichao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hezhen","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zecheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870740"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00378"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.150"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3436754"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"ref17","first-page":"1","article-title":"MS-ASL: A large-scale data set and benchmark for understanding american sign language","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Joze"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"ref21","article-title":"BBC-Oxford british sign language dataset","author":"Albanie","year":"2021"},{"key":"ref22","article-title":"Quantitative survey of the state of the art in sign language recognition","author":"Koller","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113794"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118993"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.112"},{"key":"ref26","first-page":"1","article-title":"Large-scale learning of sign language by watching TV (using co-occurrences)","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Pfister"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01896"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321502"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2999384"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409728"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.364"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1121-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12235"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941267"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2889563"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413931"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00507"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00429"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059098"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref47","first-page":"12034","article-title":"TSPNet: Hierarchical feature learning via temporal semantic pyramid for sign language translation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01823"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681237"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.427"},{"key":"ref51","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref52","article-title":"OpenMMLab pose estimation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01633"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref60","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref61","first-page":"17043","article-title":"Two-stream network for sign language recognition and translation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01890"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref65","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref66","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref67","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref68","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref69","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00392"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00008"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416881"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02265"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_14"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01925"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.619"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111716"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"ref87","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087006"},{"key":"ref90","article-title":"Sign2GPT: Leveraging large language models for gloss-free sign language translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wong"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_22"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_18"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3553052"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11125948.pdf?arnumber=11125948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:11Z","timestamp":1762455191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":95,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3599313","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}