{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:57:51Z","timestamp":1732042671288},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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","62021001"],"id":[{"id":"10.13039\/501100001809","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"}]},{"name":"Supercomputing Center of the USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3269220","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T18:30:01Z","timestamp":1682533801000},"page":"11221-11239","source":"Crossref","is-referenced-by-count":27,"title":["SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-0327-1562","authenticated-orcid":false,"given":"Hezhen","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science of Electrical and Computer Engineering, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7098-1690","authenticated-orcid":false,"given":"Weichao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science of Electrical and Computer Engineering, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science of Electrical and Computer Engineering, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science of Electrical and Computer Engineering, University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"263","reference":[{"key":"ref57","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref59","first-page":"1","article-title":"BEiT: Bert pre-training of image transformers","author":"bao","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref53","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref54","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref50","first-page":"4739","article-title":"3D human action representation learning via cross-view consistency pursuit","author":"linguo","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis Pattern Recognit"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029801"},{"key":"ref45","first-page":"1069","article-title":"3D human pose machines with self-supervised learning","volume":"42","author":"wang","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref42","first-page":"3791","article-title":"Self-supervised video representation learning by uncovering spatio-temporal statistics","volume":"44","author":"wang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref43","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref4","first-page":"5999","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"1","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","article-title":"Quantitative survey of the state of the art in sign language recognition","author":"koller","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109665"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059098"},{"key":"ref34","first-page":"1","article-title":"TSPNet: Hierarchical feature learning via temporal semantic pyramid for sign language translation","author":"li","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00550"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413931"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3132668"},{"key":"ref39","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"liu","year":"2023","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref23","first-page":"31","article-title":"Pose-based sign language recognition using GCN and BERT","author":"tunga","year":"2020","journal-title":"Proc IEEE Winter Conf Appl Comput Vis Workshops"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1121-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.364"},{"key":"ref20","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"2015","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis Pattern Recognit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00580"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2889563"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3143074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.013"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/123"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240671"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.123"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_41"},{"key":"ref10","first-page":"1","article-title":"Large-scale learning of sign language by watching TV (using co-occurrences)","author":"pfister","year":"2013","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00429"},{"key":"ref17","first-page":"1","article-title":"MS-ASL: A large-scale data set and benchmark for understanding american sign language","author":"joze","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870740"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.412"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475544"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.175"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.136"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00378"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/2735952"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref82","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3436754"},{"key":"ref83","article-title":"OpenMMLab pose estimation toolbox and benchmark","author":"contributors","year":"2020"},{"key":"ref80","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref79","article-title":"The 2017 hands in the million challenge on 3D hand pose estimation","author":"yuan","year":"2017"},{"key":"ref78","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1053427.1053429"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref77","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref102","article-title":"Deafness and hearing loss","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.332"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref1","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00510"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0895-4"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344862"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980226"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.145"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_46"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.101"},{"key":"ref60","article-title":"Masked autoencoders are scalable vision learners","author":"he","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.437"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.305"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10109128.pdf?arnumber=10109128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:58:08Z","timestamp":1693245488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10109128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":102,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3269220","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":[[2023,9,1]]}}}