{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:29:50Z","timestamp":1778693390250,"version":"3.51.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11390-024-2978-y","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T14:59:12Z","timestamp":1746543552000},"page":"378-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Vision-Based Sign Language Translation via a Skeleton-Aware Neural Network"],"prefix":"10.1007","volume":"40","author":[{"given":"Shi-Wei","family":"Gan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-Feng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Wei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-Lu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"key":"2978_CR1","doi-asserted-by":"publisher","first-page":"3416","DOI":"10.1109\/CVPR.2017.364","volume-title":"Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"O Koller","year":"2017","unstructured":"Koller O, Zargaran S, Ney H. Re-sign: Re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMs. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.3416\u20133424. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.364."},{"key":"2978_CR2","doi-asserted-by":"publisher","first-page":"4160","DOI":"10.1109\/CVPR.2019.00429","volume-title":"Proc. the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Pu","year":"2019","unstructured":"Pu J, Zhou W, Li H. Iterative alignment network for continuous sign language recognition. In Proc. the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.4160\u20134169. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00429."},{"key":"2978_CR3","doi-asserted-by":"publisher","first-page":"13009","DOI":"10.1609\/aaai.v34i07.7001","volume-title":"Proc. the 34th AAAI Conference on Artificial Intelligence","author":"H Zhou","year":"2020","unstructured":"Zhou H, Zhou W, Zhou Y, Li H. Spatial-temporal multicue network for continuous sign language recognition. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.13009\u201313016. DOI: https:\/\/doi.org\/10.1609\/aaai.v34i07.7001."},{"key":"2978_CR4","doi-asserted-by":"publisher","first-page":"7784","DOI":"10.1109\/CVPR.2018.00812","volume-title":"Proc. the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"N C Camgoz","year":"2018","unstructured":"Camgoz N C, Hadfield S, Koller O, Ney H, Bowden R. Neural sign language translation. In Proc. the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp.7784\u20137793. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00812."},{"key":"2978_CR5","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504873","volume-title":"Proc. the 32nd AAAI Conference on Artificial Intelligence","author":"D Guo","year":"2018","unstructured":"Guo D, Zhou W, Li H, Wang M. Hierarchical LSTM for sign language translation. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018. DOI: https:\/\/doi.org\/10.5555\/3504035.3504873."},{"key":"2978_CR6","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1109\/FG47880.2020.00002","volume-title":"Proc. the 15th IEEE International Conference on Automatic Face and Gesture Recognition","author":"A Orbay","year":"2020","unstructured":"Orbay A, Akarun L. Neural sign language translation by learning tokenization. In Proc. the 15th IEEE International Conference on Automatic Face and Gesture Recognition, Nov. 2020, pp.222\u2013228. DOI: https:\/\/doi.org\/10.1109\/FG47880.2020.00002."},{"key":"2978_CR7","doi-asserted-by":"publisher","first-page":"4118","DOI":"10.1145\/3474085.3475544","volume-title":"Proc. the 29th ACM International Conference on Multimedia","author":"A Yin","year":"2021","unstructured":"Yin A, Zhao Z, Liu J, Jin W, Zhang M, Zeng X, He X. SimulSLT: End-to-end simultaneous sign language translation. In Proc. the 29th ACM International Conference on Multimedia, Oct. 2021, pp.4118\u20134127. DOI: https:\/\/doi.org\/10.1145\/3474085.3475544."},{"key":"2978_CR8","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1109\/WACV51458.2022.00219","volume-title":"Proc. the 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"J Kan","year":"2022","unstructured":"Kan J, Hu K, Hagenbuchner M, Tsoi A C, Bennamoun M, Wang Z. Sign language translation with hierarchical spatio-temporal graph neural network. In Proc. the 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision, Jan. 2022, pp.2131\u20132140. DOI: https:\/\/doi.org\/10.1109\/WACV51458.2022.00219."},{"key":"2978_CR9","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.1109\/ICIP.2016.7532884","volume-title":"Proc. the 2016 IEEE International Conference on Image Processing","author":"T Liu","year":"2016","unstructured":"Liu T, Zhou W, Li H. Sign language recognition with long short-term memory. In Proc. the 2016 IEEE International Conference on Image Processing, Sept. 2016, pp.2871\u20132875. DOI: https:\/\/doi.org\/10.1109\/ICIP.2016.7532884."},{"key":"2978_CR10","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1145\/108844.108900","volume-title":"Proc. the SIGCHI Conference on Human Factors in Computing Systems","author":"K Murakami","year":"1991","unstructured":"Murakami K, Taguchi H. Gesture recognition using recurrent neural networks. In Proc. the SIGCHI Conference on Human Factors in Computing Systems, Apr. 1991, pp.237\u2013242. DOI: https:\/\/doi.org\/10.1145\/108844.108900."},{"key":"2978_CR11","doi-asserted-by":"publisher","first-page":"3563","DOI":"10.1609\/aaai.v35i4.16471","volume-title":"Proc. the 35th AAAI Conference on Artificial Intelligence","author":"B Zhou","year":"2021","unstructured":"Zhou B, Li Y, Wan J. Regional attention with architecture-rebuilt 3D network for RGB-D gesture recognition. In Proc. the 35th AAAI Conference on Artificial Intelligence, Feb. 2021, pp.3563\u20133571. DOI: https:\/\/doi.org\/10.1609\/aaai.v35i4.16471."},{"key":"2978_CR12","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1109\/CVPR.2017.175","volume-title":"Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"R Cui","year":"2017","unstructured":"Cui R, Liu H, Zhang C. Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.1610\u20131618. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.175."},{"key":"2978_CR13","doi-asserted-by":"publisher","first-page":"3075","DOI":"10.1109\/ICCV.2017.332","volume-title":"Proc. the 2017 IEEE International Conference on Computer Vision","author":"N C Camgoz","year":"2017","unstructured":"Camgoz N C, Hadfield S, Koller O, Bowden R. SubUNets: End-to-end hand shape and continuous sign language recognition. In Proc. the 2017 IEEE International Conference on Computer Vision, Oct. 2017, pp.3075\u20133084. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.332."},{"issue":"7","key":"2978_CR14","doi-asserted-by":"publisher","first-page":"1880","DOI":"10.1109\/TMM.2018.2889563","volume":"21","author":"R Cui","year":"2019","unstructured":"Cui R, Liu H, Zhang C. A deep neural framework for continuous sign language recognition by iterative training. IEEE Trans. Multimedia, 2019, 21(7):1880\u20131891. DOI: https:\/\/doi.org\/10.1109\/TMM.2018.2889563.","journal-title":"IEEE Trans. Multimedia"},{"key":"2978_CR15","doi-asserted-by":"publisher","first-page":"5975","DOI":"10.18653\/v1\/2020.coling-main.525","volume-title":"Proc. the 28th International Conference on Computational Linguistics","author":"K Yin","year":"2020","unstructured":"Yin K, Read J. Better sign language translation with STMC-transformer. In Proc. the 28th International Conference on Computational Linguistics, Dec. 2020, pp.5975\u20135989. DOI: https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.525."},{"key":"2978_CR16","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496733","volume-title":"Proc. the 34th International Conference on Neural Information Processing Systems","author":"D Li","year":"2020","unstructured":"Li D, Xu C, Yu X, Zhang K, Swift B, Suominen H, Li H. TSPNet: Hierarchical feature learning via temporal semantic pyramid for sign language translation. In Proc. the 34th International Conference on Neural Information Processing Systems, Dec. 2020, Article No. 1009. DOI: https:\/\/doi.org\/10.5555\/3495724.3496733."},{"key":"2978_CR17","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/978-3030-66823-5_18","volume-title":"Proc. the European Conference on Computer Vision","author":"N C Camgoz","year":"2020","unstructured":"Camgoz N C, Koller O, Hadfield S, Bowden R. Multichannel transformers for multi-articulatory sign language translation. In Proc. the European Conference on Computer Vision, Aug. 2020, pp.301\u2013319. DOI: https:\/\/doi.org\/10.1007\/978-3030-66823-5_18."},{"key":"2978_CR18","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/TMM.2021.3059098","volume":"24","author":"H Zhou","year":"2022","unstructured":"Zhou H, Zhou W, Zhou Y, Li H. Spatial-temporal multicue network for sign language recognition and translation. IEEE Trans. Multimedia, 2022, 24: 768\u2013779. DOI: https:\/\/doi.org\/10.1109\/TMM.2021.3059098.","journal-title":"IEEE Trans. Multimedia"},{"key":"2978_CR19","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1109\/TIP.2019.2941267","volume":"29","author":"D Guo","year":"2020","unstructured":"Guo D, Zhou W, Li A, Li H, Wang M. Hierarchical recurrent deep fusion using adaptive clip summarization for sign language translation. IEEE Trans. Image Processing, 2020, 29: 1575\u20131590. DOI: https:\/\/doi.org\/10.1109\/TIP.2019.2941267.","journal-title":"IEEE Trans. Image Processing"},{"key":"2978_CR20","doi-asserted-by":"publisher","first-page":"4353","DOI":"10.1145\/3474085.3475577","volume-title":"Proc. the 29th ACM International Conference on Multimedia","author":"S Gan","year":"2021","unstructured":"Gan S, Yin Y, Jiang Z, Xie L, Lu S. Skeleton-aware neural sign language translation. In Proc. the 29th ACM International Conference on Multimedia, Oct. 2021, pp.4353\u20134361. DOI: https:\/\/doi.org\/10.1145\/3474085.3475577."},{"key":"2978_CR21","doi-asserted-by":"publisher","first-page":"4896","DOI":"10.1109\/BigData.2018.8622141","volume-title":"Proc. the 2018 IEEE International Conference on Big Data","author":"K Bantupalli","year":"2018","unstructured":"Bantupalli K, Xie Y. American sign language recognition using deep learning and computer vision. In Proc. the 2018 IEEE International Conference on Big Data, Dec. 2018, pp.4896\u20134899. DOI: https:\/\/doi.org\/10.1109\/BigData.2018.8622141."},{"issue":"9","key":"2978_CR22","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/TCSVT.2018.2870740","volume":"29","author":"J Huang","year":"2019","unstructured":"Huang J, Zhou W, Li H, Li W. Attention-based 3D-CNNs for large-vocabulary sign language recognition. IEEE Trans. Circuits and Systems for Video Technology, 2019, 29(9):2822\u20132832. DOI: https:\/\/doi.org\/10.1109\/TCSVT.2018.2870740.","journal-title":"IEEE Trans. Circuits and Systems for Video Technology"},{"key":"2978_CR23","doi-asserted-by":"publisher","unstructured":"Wang H, Chai X, Hong X, Zhao G, Chen X. Isolated sign language recognition with grassmann covariance matrices. ACM Trans. Accessible Computing (TACCESS), 2016, 8(4): Article No. 14. DOI: https:\/\/doi.org\/10.1145\/2897735.","DOI":"10.1145\/2897735"},{"key":"2978_CR24","doi-asserted-by":"publisher","DOI":"10.1145\/2674396.2674421","volume-title":"Proc. the 7th International Conference on Pervasive Technologies Related to Assistive Environments","author":"P Jangyodsuk","year":"2014","unstructured":"Jangyodsuk P, Conly C, Athitsos V. Sign language recognition using dynamic time warping and hand shape distance based on histogram of oriented gradient features. In Proc. the 7th International Conference on Pervasive Technologies Related to Assistive Environments, May 2014, Article No. 50. DOI: https:\/\/doi.org\/10.1145\/2674396.2674421."},{"key":"2978_CR25","doi-asserted-by":"publisher","first-page":"2876","DOI":"10.1109\/ICIP.2016.7532885","volume-title":"Proc. the 2016 IEEE International Conference on Image Processing","author":"D Guo","year":"2016","unstructured":"Guo D, Zhou W, Wang M, Li H. Sign language recognition based on adaptive HMMS with data augmentation. In Proc. the 2016 IEEE International Conference on Image Processing, Sept. 2016, pp.2876\u20132880. DOI: https:\/\/doi.org\/10.1109\/ICIP.2016.7532885."},{"key":"2978_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177428","volume-title":"Proc. the 2015 IEEE International Conference on Multimedia and Expo","author":"J Huang","year":"2015","unstructured":"Huang J, Zhou W, Li H, Li W. Sign language recognition using 3D convolutional neural networks. In Proc. the 2015 IEEE International Conference on Multimedia and Expo, Jun. 29-Jul. 3, 2015. DOI: https:\/\/doi.org\/10.1109\/ICME.2015.7177428."},{"key":"2978_CR27","doi-asserted-by":"publisher","unstructured":"Tang A, Lu K, Wang Y, Huang J, Li H. A real-time hand posture recognition system using deep neural networks. ACM Trans. Intelligent Systems and Technology (TIST), 2015, 6(2): Article No. 21. DOI: https:\/\/doi.org\/10.1145\/2735952.","DOI":"10.1145\/2735952"},{"key":"2978_CR28","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504310","volume-title":"Proc. the 32nd AAAI Conference on Artificial Intelligence","author":"J Huang","year":"2018","unstructured":"Huang J, Zhou W, Zhang Q, Li H, Li W. Video-based sign language recognition without temporal segmentation. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018, Article No. 275. DOI: https:\/\/doi.org\/10.5555\/3504035.3504310."},{"issue":"9","key":"2978_CR29","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1109\/TPAMI.2019.2911077","volume":"42","author":"O Koller","year":"2020","unstructured":"Koller O, Camgoz N C, Ney H, Bowden R. Weakly supervised learning with multi-stream CNN-LSTM-HMMs to discover sequential parallelism in sign language videos. IEEE Trans. Pattern Analysis and Machine Intelligence, 2020, 42(9):2306\u20132320. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2019.2911077.","journal-title":"IEEE Trans. Pattern Analysis and Machine Intelligence"},{"key":"2978_CR30","volume-title":"Proc. the IEEE International Conference on Automatic Face and Gesture Recognition","author":"X Chai","year":"2013","unstructured":"Chai X, Li G, Lin Y, Xu Z, Tang Y, Chen X, Zhou M. Sign language recognition and translation with kinect. In Proc. the IEEE International Conference on Automatic Face and Gesture Recognition, Apr. 2013, Article No. 4."},{"key":"2978_CR31","doi-asserted-by":"publisher","first-page":"763","DOI":"10.24963\/ijcai.2023\/85","volume-title":"Proc. the 32nd International Joint Conference on Artificial Intelligence","author":"S Gan","year":"2023","unstructured":"Gan S, Yin Y, Jiang Z, Xia K, Xie L, Lu S. Contrastive learning for sign language recognition and translation. In Proc. the 32nd International Joint Conference on Artificial Intelligence, Aug. 2023, pp.763\u2013772. DOI: https:\/\/doi.org\/10.24963\/ijcai.2023\/85."},{"key":"2978_CR32","doi-asserted-by":"publisher","first-page":"5686","DOI":"10.1109\/CVPR.2019.00584","volume-title":"Proc. the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K Sun","year":"2019","unstructured":"Sun K, Xiao B, Liu D, Wang J. Deep high-resolution representation learning for human pose estimation. In Proc. the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.5686\u20135696. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00584."},{"key":"2978_CR33","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1109\/CVPR.2017.143","volume-title":"Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"Z Cao","year":"2017","unstructured":"Cao Z, Simon T, Wei S E, Sheikh Y. Realtime multi-person 2D pose estimation using part affinity fields. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.1302\u20131310. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.143."},{"key":"2978_CR34","volume-title":"Proc. the 3rd International Conference on Learning Representations","author":"K Simonyan","year":"2015","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In Proc. the 3rd International Conference on Learning Representations, May 2015."},{"key":"2978_CR35","doi-asserted-by":"publisher","first-page":"5534","DOI":"10.1109\/ICCV.2017.590","volume-title":"Proc. the 2017 IEEE International Conference on Computer Vision","author":"Z Qiu","year":"2017","unstructured":"Qiu Z, Yao T, Mei T. Learning spatio-temporal representation with pseudo-3D residual networks. In Proc. the 2017 IEEE International Conference on Computer Vision, Oct. 2017, pp.5534\u20135542. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.590."},{"key":"2978_CR36","doi-asserted-by":"publisher","first-page":"6000","DOI":"10.5555\/3295222.3295349","volume-title":"Proc. the 31st International Conference on Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention is all you need. In Proc. the 31st International Conference on Neural Information Processing Systems, Dec. 2017, pp.6000\u20136010. DOI: https:\/\/doi.org\/10.5555\/3295222.3295349."},{"key":"2978_CR37","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp.770\u2013778. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"key":"2978_CR38","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.cviu.2015.09.013","volume":"141","author":"O Koller","year":"2015","unstructured":"Koller O, Forster J, Ney H. Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers. Computer Vision and Image Understanding, 2015, 141: 108\u2013125. DOI: https:\/\/doi.org\/10.1016\/j.cviu.2015.09.013.","journal-title":"Computer Vision and Image Understanding"},{"key":"2978_CR39","first-page":"74","volume-title":"Proc. the Text Summarization Branches Out","author":"C Y Lin","year":"2004","unstructured":"Lin C Y. ROUGE: A package for automatic evaluation of summaries. In Proc. the Text Summarization Branches Out, Jul. 2004, pp.74\u201381."},{"key":"2978_CR40","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","volume-title":"Proc. the 40th Annual Meeting on Association for Computational Linguistics","author":"K Papineni","year":"2002","unstructured":"Papineni K, Roukos S, Ward T, Zhu W J. BLEU: A method for automatic evaluation of machine translation. In Proc. the 40th Annual Meeting on Association for Computational Linguistics, Jul. 2002, pp.311\u2013318. DOI: https:\/\/doi.org\/10.3115\/1073083.1073135."},{"key":"2978_CR41","doi-asserted-by":"publisher","first-page":"10020","DOI":"10.1109\/CVPR42600.2020.01004","volume-title":"Proc. the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"N C Camg\u00f6z","year":"2020","unstructured":"Camg\u00f6z N C, Koller O, Hadfield S, Bowden R. Sign language transformers: Joint end-to-end sign language recognition and translation. In Proc. the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.10020\u201310030. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01004."},{"key":"2978_CR42","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-030-58517-4_11","volume-title":"Proc. the 16th European Conference on Computer Vision","author":"Z Niu","year":"2020","unstructured":"Niu Z, Mak B. Stochastic fine-grained labeling of multistate sign glosses for continuous sign language recognition. In Proc. the 16th European Conference on Computer Vision, Aug. 2020, pp.172\u2013186. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58517-4_11."},{"key":"2978_CR43","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-030-58586-0_41","volume-title":"Proc. the 16th European Conference on Computer Vision","author":"K L Cheng","year":"2020","unstructured":"Cheng K L, Yang Z, Chen Q, Tai Y W. Fully convolutional networks for continuous sign language recognition. In Proc. the 16th European Conference on Computer Vision, 2020, pp.697\u2013714. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58586-0_41."},{"key":"2978_CR44","doi-asserted-by":"publisher","first-page":"11283","DOI":"10.1109\/ICCV48922.2021.01111","volume-title":"Proc. the 2021 IEEE\/CVF International Conference on Computer Vision","author":"A Hao","year":"2021","unstructured":"Hao A, Min Y, Chen X. Self-mutual distillation learning for continuous sign language recognition. In Proc. the 2021 IEEE\/CVF International Conference on Computer Vision, Oct. 2021, pp.11283\u201311292. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01111."},{"key":"2978_CR45","doi-asserted-by":"publisher","first-page":"5121","DOI":"10.1109\/CVPR52688.2022.00507","volume-title":"Proc. the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"R Zuo","year":"2022","unstructured":"Zuo R, Mak B. C2SLR: Consistency-enhanced continuous sign language recognition. In Proc. the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp.5121\u20135130. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00507."},{"key":"2978_CR46","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1109\/ICME.2019.00223","volume-title":"Proc. the 2019 IEEE International Conference on Multimedia and Expo","author":"H Zhou","year":"2019","unstructured":"Zhou H, Zhou W, Li H. Dynamic pseudo label decoding for continuous sign language recognition. In Proc. the 2019 IEEE International Conference on Multimedia and Expo, Jul. 2019, pp.1282\u20131287. DOI: https:\/\/doi.org\/10.1109\/ICME.2019.00223."},{"issue":"3","key":"2978_CR47","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TCSVT.2020.2999384","volume":"31","author":"C Wei","year":"2021","unstructured":"Wei C, Zhao J, Zhou W, Li H. Semantic boundary detection with reinforcement learning for continuous sign language recognition. IEEE Trans. Circuits and Systems for Video Technology, 2021, 31(3):1138\u20131149. DOI: https:\/\/doi.org\/10.1109\/TCSVT.2020.2999384.","journal-title":"IEEE Trans. Circuits and Systems for Video Technology"},{"key":"2978_CR48","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1145\/3394171.3413931","volume-title":"Proc. the 28th ACM International Conference on Multimedia","author":"J Pu","year":"2020","unstructured":"Pu J, Zhou W, Hu H, Li H. Boosting continuous sign language recognition via cross modality augmentation. In Proc. the 28th ACM International Conference on Multimedia, Oct. 2020, pp.1497\u20131505. DOI: https:\/\/doi.org\/10.1145\/3394171.3413931."},{"key":"2978_CR49","doi-asserted-by":"publisher","first-page":"11522","DOI":"10.1109\/ICCV48922.2021.01134","volume-title":"Proc. the 2021 IEEE\/CVF International Conference on Computer Vision","author":"Y Min","year":"2021","unstructured":"Min Y, Hao A, Chai X, Chen X. Visual alignment constraint for continuous sign language recognition. In Proc. the 2021 IEEE\/CVF International Conference on Computer Vision, Oct. 2021, pp.11522\u201311531. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01134."},{"key":"2978_CR50","doi-asserted-by":"publisher","first-page":"4534","DOI":"10.1109\/ICCV.2015.515","volume-title":"Proc. the 2015 IEEE International Conference on Computer Vision","author":"S Venugopalan","year":"2015","unstructured":"Venugopalan S, Rohrbach M, Donahue J, Mooney R, Darrell T, Saenko K. Sequence to sequence\u2014Video to text. In Proc. the 2015 IEEE International Conference on Computer Vision, Dec. 2015, pp.4534\u20134542. DOI: https:\/\/doi.org\/10.1109\/ICCV.2015.515."},{"key":"2978_CR51","doi-asserted-by":"publisher","first-page":"4433","DOI":"10.1109\/TMM.2021.3117124","volume":"24","author":"S Tang","year":"2022","unstructured":"Tang S, Guo D, Hong R, Wang M. Graph-based multimodal sequential embedding for sign language translation. IEEE Trans. Multimedia, 2022, 24: 4433\u20134445. DOI: https:\/\/doi.org\/10.1109\/TMM.2021.3117124.","journal-title":"IEEE Trans. Multimedia"},{"key":"2978_CR52","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1109\/CVPR46437.2021.00137","volume-title":"Proc. the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Zhou","year":"2021","unstructured":"Zhou H, Zhou W, Qi W, Pu J, Li H. Improving sign language translation with monolingual data by sign backtranslation. In Proc. the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2021, pp.1316\u20131325. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00137."}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-024-2978-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11390-024-2978-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-024-2978-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T16:03:37Z","timestamp":1746547417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11390-024-2978-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2978"],"URL":"https:\/\/doi.org\/10.1007\/s11390-024-2978-y","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"value":"1000-9000","type":"print"},{"value":"1860-4749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"18 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Conflict of Interest The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}]}}