{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:47:54Z","timestamp":1791686874333,"version":"4.3.4"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176236"],"award-info":[{"award-number":["62176236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109530","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T23:19:57Z","timestamp":1787181597000},"page":"109530","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["SignMamba: Sparse spatial\u2013temporal state-space modeling for continuous sign language recognition"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9437-262X","authenticated-orcid":false,"given":"Xu-Hua","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Xiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109530_bib0001","unstructured":"Alyami, S., & Luqman, H. (2024). A comparative study of continuous sign language recognition techniques. arXiv: 2406.12369."},{"key":"10.1016\/j.neunet.2026.109530_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129015","article-title":"Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognition","volume":"617","author":"Alyami","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109530_bib0003","doi-asserted-by":"crossref","unstructured":"Ben Slimane, F., & Bouguessa, M. (2021). Context matters: Self-attention for sign language recognition. arXiv: 2101.04632.","DOI":"10.1109\/ICPR48806.2021.9412916"},{"key":"10.1016\/j.neunet.2026.109530_bib0004","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7784","article-title":"Neural sign language translation","author":"Camgoz","year":"2018"},{"key":"10.1016\/j.neunet.2026.109530_bib0005","series-title":"Cvpr","article-title":"Sign language transformers: Joint end-to-end sign language recognition and translation","author":"Camgoz","year":"2020"},{"key":"10.1016\/j.neunet.2026.109530_bib0006","doi-asserted-by":"crossref","first-page":"17043","DOI":"10.52202\/068431-1240","article-title":"Two-stream network for sign language recognition and translation","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109530_bib0007","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.1016\/j.neunet.2026.109530_bib0008","series-title":"2009\u202fIEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2026.109530_bib0009","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale."},{"key":"10.1016\/j.neunet.2026.109530_bib0010","series-title":"Proceedings of the LREC 2014 workshop on the representation and processing of sign languages: Interactions between corpus and lexicon","first-page":"38","article-title":"Large vocabulary continuous sign language recognition using sub-units","author":"Forster","year":"2014"},{"key":"10.1016\/j.neunet.2026.109530_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13470","article-title":"Signgraph: A sign sequence is worth graphs of nodes","author":"Gan","year":"2024"},{"key":"10.1016\/j.neunet.2026.109530_bib0012","unstructured":"Gu, A., & Dao, T. (2024). Mamba: Linear-time sequence modeling with selective state spaces."},{"key":"10.1016\/j.neunet.2026.109530_bib0013","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"1474","article-title":"HiPPO: Recurrent memory with optimal polynomial projections","volume":"vol. 33","author":"Gu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109530_bib0014","unstructured":"Gu, A., Goel, K., & R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. arXiv: 2111.00396."},{"key":"10.1016\/j.neunet.2026.109530_bib0015","doi-asserted-by":"crossref","first-page":"8291","DOI":"10.52202\/068431-0603","article-title":"Vision gnn: An image is worth graph of nodes","volume":"35","author":"Han","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109530_bib0016","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"11303","article-title":"Self-mutual distillation learning for continuous sign language recognition","author":"Hao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109530_bib0017","unstructured":"Hasanaath, A. A., & Luqman, H. (2025). Ustm: Unified spatial and temporal modeling for continuous sign language recognition. arXiv: 2512.13415."},{"issue":"21","key":"10.1016\/j.neunet.2026.109530_bib0018","doi-asserted-by":"crossref","first-page":"6842","DOI":"10.3390\/s24216842","article-title":"Fusion attention for action recognition: Integrating sparse-dense and global attention for video action recognition","volume":"24","author":"He","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109530_bib0019","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109530_bib0020","series-title":"European conference on computer vision","first-page":"511","article-title":"Temporal lift pooling for continuous sign language recognition","author":"Hu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109530_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2529","article-title":"Continuous sign language recognition with correlation network","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109530_bib0022","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"854","article-title":"Self-emphasizing network for continuous sign language recognition","volume":"37","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109530_bib0023","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"709","article-title":"Adabrowse: Adaptive video browser for efficient continuous sign language recognition","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109530_bib0024","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"20676","article-title":"Cosign: Exploring co-occurrence signals in skeleton-based continuous sign language recognition","author":"Jiao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109530_bib0025","series-title":"NeurIPS","article-title":"Why warmup the learning rate? Underlying mechanisms and improvements","author":"Kalra","year":"2024"},{"key":"10.1016\/j.neunet.2026.109530_bib0026","series-title":"Computer analysis of images and patterns, 13th international conference, CAIP 2009, m\u00fcnster, Germany, september 2\u20134, 2009. proceedings","first-page":"697","article-title":"A framework for the recognition of live and captured sign language","volume":"5702","author":"Kelly","year":"2009"},{"issue":"9","key":"10.1016\/j.neunet.2026.109530_bib0027","doi-asserted-by":"crossref","first-page":"2306","DOI":"10.1109\/TPAMI.2019.2911077","article-title":"Weakly supervised learning with multi-stream CNN-LSTM-HMMs to discover sequential parallelism in sign language videos","volume":"42","author":"Koller","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109530_bib0028","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.cviu.2015.09.013","article-title":"Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers","volume":"141","author":"Koller","year":"2015","journal-title":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.neunet.2026.109530_bib0029","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"4445","article-title":"Re-sign: Re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMs","author":"Koller","year":"2017"},{"key":"10.1016\/j.neunet.2026.109530_bib0030","series-title":"2011 International conference on computer vision (ICCV)","first-page":"2556","article-title":"Hmdb: A large video database for human motion recognition","author":"Kuehne","year":"2011"},{"issue":"12","key":"10.1016\/j.neunet.2026.109530_bib0031","doi-asserted-by":"crossref","first-page":"4558","DOI":"10.3390\/s22124558","article-title":"Spatial attention-based 3d graph convolutional neural network for sign language recognition","volume":"22","author":"Li","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109530_bib0032","doi-asserted-by":"crossref","unstructured":"Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., & Qiao, Y. (2024). Videomamba: State space model for efficient video understanding.","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"10.1016\/j.neunet.2026.109530_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102438","article-title":"Tb-net: Intra- and inter-video correlation learning for continuous sign language recognition","volume":"109","author":"Liu","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109530_bib0034","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., & Liu, Y. (2024b). Vmamba: Visual state space model. arXiv: 2401.10166.","DOI":"10.52202\/079017-3273"},{"key":"10.1016\/j.neunet.2026.109530_bib0035","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109530_bib0036","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3891","article-title":"Tcnet: Continuous sign language recognition from trajectories and correlated regions","volume":"38","author":"Lu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109530_bib0037","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCVW)","article-title":"Interpretable spatio-temporal attention for video action recognition","author":"Meng","year":"2018"},{"key":"10.1016\/j.neunet.2026.109530_bib0038","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"11542","article-title":"Visual alignment constraint for continuous sign language recognition","author":"Min","year":"2021"},{"key":"10.1016\/j.neunet.2026.109530_bib0039","unstructured":"Pei, X., Huang, T., & Xu, C. (2024). Efficientvmamba: Atrous selective scan for light weight visual mamba. arXiv: 2403.09977."},{"key":"10.1016\/j.neunet.2026.109530_bib0040","series-title":"IEEE International conference on automatic face and gesture recognition (FG)","article-title":"Sign, attend and tell: Spatial attention for sign language recognition","author":"Sarhan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109530_bib0041","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv: 1212.0402."},{"key":"10.1016\/j.neunet.2026.109530_bib0042","article-title":"Spatial-temporal pyramid graph reasoning for action recognition","volume":"139","author":"Wang","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109530_bib0043","doi-asserted-by":"crossref","first-page":"7354","DOI":"10.1109\/TCSVT.2025.3544212","article-title":"Cross-modal adaptive prototype learning for continuous sign language recognition","volume":"35","author":"Wei","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109530_bib0044","series-title":"Linear state-space control systems","author":"Williams","year":"2007"},{"key":"10.1016\/j.neunet.2026.109530_bib0045","series-title":"ICASSP 2025-2025 IEEE International conference on acoustics, speech and signal processing (ICASSP)","first-page":"1","article-title":"Hierarchical spatial-temporal enhancement network for continuous sign language recognition","author":"Xu","year":"2025"},{"issue":"4","key":"10.1016\/j.neunet.2026.109530_bib0046","doi-asserted-by":"crossref","first-page":"483","DOI":"10.20965\/jaciii.2018.p0483","article-title":"Research on continuous sign language sentence recognition algorithm based on weighted key-frame","volume":"22","author":"Xu","year":"2018","journal-title":"Journal of Advanced Computational Intelligence and Intelligent Informatics"},{"key":"10.1016\/j.neunet.2026.109530_bib0047","series-title":"ICASSP 2026 - 2026 IEEE International conference on acoustics, speech and signal processing (ICASSP)","first-page":"9907","article-title":"Saka: Spatially-adaptive and keyframe-anchored graph network for continuous sign language recognition","author":"Ye","year":"2026"},{"key":"10.1016\/j.neunet.2026.109530_bib0048","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11973","article-title":"Hypersign: Saliency-aware spatial graphs and temporal hypergraphs for continuous sign language recognition","volume":"40","author":"Ye","year":"2026"},{"key":"10.1016\/j.neunet.2026.109530_bib0049","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1109\/TCSVT.2023.3296668","article-title":"Spatial temporal enhanced network for continuous sign language recognition","volume":"34","author":"Yin","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"10.1016\/j.neunet.2026.109530_bib0050","doi-asserted-by":"crossref","first-page":"2399","DOI":"10.32604\/cmes.2023.045731","article-title":"Recent advances on deep learning for sign language recognition","volume":"139","author":"Zhang","year":"2024","journal-title":"Computer Modeling in Engineering & Sciences"},{"key":"10.1016\/j.neunet.2026.109530_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1316","article-title":"Improving sign language translation with monolingual data by sign back-translation","author":"Zhou","year":"2021"},{"key":"10.1016\/j.neunet.2026.109530_bib0052","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13009","article-title":"Spatial-temporal multi-cue network for continuous sign language recognition","volume":"34","author":"Zhou","year":"2020"},{"key":"10.1016\/j.neunet.2026.109530_bib0053","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv: 2401.09417."},{"key":"10.1016\/j.neunet.2026.109530_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9308","article-title":"Deformable convnets v2: More deformable, better results","author":"Zhu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109530_bib0055","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5131","article-title":"C2slr: Consistency-enhanced continuous sign language recognition","author":"Zuo","year":"2022"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009883?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009883?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:26:33Z","timestamp":1791685593000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":55,"alternative-id":["S0893608026009883"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109530","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SignMamba: Sparse spatial\u2013temporal state-space modeling for continuous sign language recognition","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109530","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109530"}}