{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:02:06Z","timestamp":1790154126223,"version":"4.0.1"},"reference-count":94,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476232"],"award-info":[{"award-number":["62476232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076211"],"award-info":[{"award-number":["62076211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11263-026-02978-x","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T18:55:34Z","timestamp":1787684134000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variational Sign Language Translation"],"prefix":"10.1007","volume":"134","author":[{"given":"Rui","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiquan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0243-7228","authenticated-orcid":false,"given":"Yidong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"issue":"1","key":"2978_CR1","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/S0004-3702(01)00141-2","volume":"133","author":"O Al-Jarrah","year":"2001","unstructured":"Al-Jarrah, O., & Halawani, A. (2001). Recognition of gestures in Arabic sign language using neuro-fuzzy systems. Artificial Intelligence., 133(1), 117\u2013138. https:\/\/doi.org\/10.1016\/S0004-3702(01)00141-2","journal-title":"Artificial Intelligence."},{"key":"2978_CR2","doi-asserted-by":"crossref","unstructured":"Asasi, S., Lakhal, M. I., Sincan, O. M., & Bowden, R. (2025). Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation. arXiv","DOI":"10.1145\/3742886.3756707"},{"issue":"12","key":"2978_CR3","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1016\/j.cpc.2008.11.005","volume":"180","author":"M Baboulin","year":"2009","unstructured":"Baboulin, M., Buttari, A., Dongarra, J., Kurzak, J., Langou, J., Langou, J., Luszczek, P., & Tomov, S. (2009). Accelerating scientific computations with mixed precision algorithms. Computer Physics Communications., 180(12), 2526\u20132533. https:\/\/doi.org\/10.1016\/j.cpc.2008.11.005","journal-title":"Computer Physics Communications."},{"key":"2978_CR4","doi-asserted-by":"crossref","unstructured":"Bao, Y., Zhou, H., Huang, S., Wang, D., Qian, L., Dai, X., Chen, J., & Li, L. (2022). Latent-GLAT: Glancing at Latent Variables for Parallel Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL) Dublin, Ireland: Association for Computational Linguistics; p. 8398\u20138409.","DOI":"10.18653\/v1\/2022.acl-long.575"},{"key":"2978_CR5","doi-asserted-by":"crossref","unstructured":"Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., &Bengio, S. (2016). Generating Sentences from a Continuous Space. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning Berlin, Germany: Association for Computational Linguistics. p. 10\u201321.","DOI":"10.18653\/v1\/K16-1002"},{"key":"2978_CR6","unstructured":"Burda, Y., Grosse, R., & Salakhutdinov, R. (2016). Importance Weighted Autoencoders. International Conference on Learning Representations (ICLR)."},{"key":"2978_CR7","doi-asserted-by":"crossref","unstructured":"Camgoz, N. C., Hadfield, S., Koller, O., Ney, H., & Bowden, R. (2018). Neural Sign Language Translation. In  Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 7784\u20137793.","DOI":"10.1109\/CVPR.2018.00812"},{"key":"2978_CR8","doi-asserted-by":"crossref","unstructured":"Camgoz, N. C., Koller, O., Hadfield, S., & Bowden, R. (2020). Multi-Channel Transformers for Multi-Articulatory Sign Language Translation. In Computer Vision \u2013 ECCV 2020 Workshops Lecture Notes in Computer Science, Cham: Springer International Publishing. p. 301\u2013319.","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"2978_CR9","doi-asserted-by":"crossref","unstructured":"Camgoz, N. C., Koller, O., Hadfield, S., & Bowden, R. (2020). Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Seattle, WA, USA: IEEE. p. 10020\u201310030.","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"2978_CR10","doi-asserted-by":"publisher","first-page":"19472","DOI":"10.52202\/079017-0614","volume":"37","author":"L Chen","year":"2024","unstructured":"Chen, L., Wei, X., Li, J., Dong, X., Zhang, P., Zang, Y., et al. (2024). ShareGPT4Video: Improving video understanding and generation with better captions. Advances in Neural Information Processing Systems, 37, 19472\u201319495.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2978_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wei, F., Sun, X., Wu, Z., & Lin, S. (2022). A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 5110\u20135120.","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"2978_CR12","doi-asserted-by":"publisher","first-page":"17043","DOI":"10.52202\/068431-1240","volume":"35","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Zuo, R., Wei, F., Wu, Y., Liu, S., & Mak, B. (2022). Two-stream network for sign language recognition and translation. Advances in Neural Information Processing Systems (NeurIPS), 35, 17043\u201317056.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2978_CR13","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhou, B., Huang, Y., Wan, J., Hu, Y., & Shi, H., et\u00a0al. (2025). C2RL: Content and Context Representation Learning for Gloss-Free Sign Language Translation and Retrieval. IEEE Transactions on Circuits and Systems for Video Technology. p. 1\u20131. https:\/\/doi.org\/10.1109\/TCSVT.2025.3553052.","DOI":"10.1109\/TCSVT.2025.3553052"},{"key":"2978_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhou, B., Li, J., Wan, J., Lei, Z., & Jiang, N., et\u00a0al. (2024). Factorized Learning Assisted with Large Language Model for Gloss-Free Sign Language Translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) Torino, Italia: ELRA and ICCL. p. 7071\u20137081.","DOI":"10.63317\/4qo2dsetvyk8"},{"key":"2978_CR15","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wei, F., Bao, J., Chen, D., & Zhang, W. (2023). CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19016\u201319026.","DOI":"10.1109\/CVPR52729.2023.01823"},{"key":"2978_CR16","unstructured":"Darcet, T., Oquab, M., Mairal, J., & Bojanowski, P. (2023). Vision Transformers Need Registers. The Twelfth International Conference on Learning Representations (ICLR)."},{"key":"2978_CR17","doi-asserted-by":"crossref","unstructured":"De\u00a0Sisto, M., Vandeghinste, V., Egea\u00a0G\u00f3mez, S., De\u00a0Coster, M., Shterionov, D., & Saggion, H. (2022). Challenges with Sign Language Datasets for Sign Language Recognition and Translation. In Proceedings of the Thirteenth Language Resources and Evaluation Conference Marseille, France: European Language Resources Association. pp. 2478\u20132487.","DOI":"10.63317\/4naj43uhhdys"},{"key":"2978_CR18","doi-asserted-by":"crossref","unstructured":"Desai, A., De\u00a0Meulder, M., Hochgesang, J. A., Kocab, A., & Lu, A. X. (2024). Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendas. In Proceedings of the LREC-COLING 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources Torino, Italia: ELRA and ICCL. pp. 54\u201365.","DOI":"10.63317\/4qt6t64rxwd2"},{"key":"2978_CR19","doi-asserted-by":"crossref","unstructured":"Duarte, A., Albanie, S., Gir\u00f3-I-Nieto, X., & Varol, G. (2022). Sign Language Video Retrieval with Free-Form Textual Queries. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 14074\u201314084.","DOI":"10.1109\/CVPR52688.2022.01370"},{"key":"2978_CR20","doi-asserted-by":"crossref","unstructured":"Duarte, A., Palaskar, S., Ventura, L., Ghadiyaram, D., DeHaan, K., Metze, F., Torres, J., & Giro-i-Nieto, X. (2021). How2Sign: A Large-Scale Multimodal Dataset for Continuous American Sign Language. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2735\u20132744.","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"2978_CR21","doi-asserted-by":"crossref","unstructured":"Fish, E., Bowden, R., & Geo-Sign. (2025). Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation. The Thirty-Ninth Annual Conference on Neural Information Processing Systems.","DOI":"10.52202\/085713-3317"},{"key":"2978_CR22","doi-asserted-by":"crossref","unstructured":"Fu, B., Ye, P., Zhang, L., Yu, P., Hu, C., Shi, X., & Chen, Y. (2023). A Token-Level Contrastive Framework for Sign Language Translation. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095466"},{"key":"2978_CR23","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.1109\/TASLPRO.2025.3546817","volume":"33","author":"B Fu","year":"2025","unstructured":"Fu, B., Zhang, L., Ye, P., Yu, P., Hu, C., Shi, X., et al. (2025). Improving end-to-end sign language translation via multi-level contrastive learning. IEEE Transactions on Audio, Speech and Language Processing., 33, 1230\u20131242. https:\/\/doi.org\/10.1109\/TASLPRO.2025.3546817","journal-title":"IEEE Transactions on Audio, Speech and Language Processing."},{"key":"2978_CR24","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L. G., He, Y., Rahmani, H., & Liu, J. (2024). LLMs Are Good Sign Language Translators. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18362\u201318372.","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"2978_CR25","doi-asserted-by":"publisher","first-page":"22506","DOI":"10.18653\/v1\/2025.findings-acl.1157","volume-title":"Findings of the Association for Computational Linguistics: ACL 2025 Vienna","author":"S Gueuwou","year":"2025","unstructured":"Gueuwou, S., Du, X., Shakhnarovich, G., & Livescu, K. (2025). SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale. In W. Che, J. Nabende, E. Shutova, & M. T. Pilehvar (Eds.), Findings of the Association for Computational Linguistics: ACL 2025 Vienna (pp. 22506\u201322521). Austria: Association for Computational Linguistics."},{"key":"2978_CR26","doi-asserted-by":"crossref","unstructured":"Gueuwou, S., Du, X., Shakhnarovich, G., Livescu, K., & Liu, A. H. (2025). SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction. In: Che W, Nabende J, Shutova E, Pilehvar MT, editors. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Vienna, Austria: Association for Computational Linguistics. p. 28792\u201328810.","DOI":"10.18653\/v1\/2025.acl-long.1397"},{"key":"2978_CR27","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., & Botvinick, M. (2017). Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations (ICLR)."},{"key":"2978_CR28","doi-asserted-by":"publisher","unstructured":"Hu, H., Zhao, W., Zhou, W., & Li H. (2023). SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence;p. 1\u201320. https:\/\/doi.org\/10.1109\/TPAMI.2023.3269220. arXiv:2305.04868 [cs].","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"2978_CR29","doi-asserted-by":"crossref","unstructured":"Hu, J., Yi, X., Li, W., Sun, M., & Xie, X. (2022). Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022 Abu Dhabi, United Arab Emirates: Association for Computational Linguistics. pp. 6306\u20136320.","DOI":"10.18653\/v1\/2022.findings-emnlp.470"},{"key":"2978_CR30","unstructured":"Hu, L., Feng, W., Gao, L., Liu, Z., & Wan, L. (2024). CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation. arXiv."},{"key":"2978_CR31","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhou, W., Zhang, Q., Li, H., & Li, W. (2018). Video-Based Sign Language Recognition without Temporal Segmentation. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI) AAAI\u201918, New Orleans, Louisiana, USA: AAAI Press. pp. 2257\u20132264.","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"2978_CR32","doi-asserted-by":"crossref","unstructured":"Huffman, S., Chen, S., Mack, K. A., Su, H., Wang, Q., & Kushalnagar, R. (2025). \"We Do Use It, but Not How Hearing People Think\": How the Deaf and Hard of Hearing Community Uses Large Language Model Tools. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems CHI EA \u201925, New York, NY, USA: Association for Computing Machinery. p. 1\u20139.","DOI":"10.1145\/3706599.3719785"},{"key":"2978_CR33","unstructured":"Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., & Zhang, L., et\u00a0al. (2024). Qwen2.5-Coder Technical Report. arXiv."},{"key":"2978_CR34","doi-asserted-by":"crossref","unstructured":"Hwang, E.J., Cho, S., Lee, J., & Park, J. C. (2025). An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs. In: Chiruzzo, L., Ritter, A., Wang, L (eds). Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Albuquerque, New Mexico: Association for Computational Linguistics. pp. 3901\u20133920.","DOI":"10.18653\/v1\/2025.naacl-long.197"},{"key":"2978_CR35","doi-asserted-by":"crossref","unstructured":"Jang, Y., Raajesh, H., Momeni, L., Varol, G., & Zisserman, A. (2025). Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8742\u20138752.","DOI":"10.1109\/CVPR52734.2025.00817"},{"key":"2978_CR36","doi-asserted-by":"crossref","unstructured":"Jiao, P., Min, Y., & Chen, X. (2024). Visual Alignment Pre-Training for Sign Language Translation. In Proceedings of the European Conference on Computer Vision (ECCV) Cham: Springer Nature Switzerland. pp. 349\u2013367.","DOI":"10.1007\/978-3-031-72946-1_20"},{"key":"2978_CR37","unstructured":"Joze, H., & Koller, O. (2019). MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language. arXiv"},{"key":"2978_CR38","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., Suleyman, M., & Zisserman, A. (2017). The Kinetics Human Action Video Dataset. arXiv."},{"key":"2978_CR39","doi-asserted-by":"crossref","unstructured":"Kim, J., Jeon, H., Bae, J., & Kim, H. Y. (2025). Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation. In  Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21048\u201321058.","DOI":"10.1109\/ICCV51701.2025.01956"},{"key":"2978_CR40","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR)"},{"key":"2978_CR41","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. (2015). Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers. Computer Vision and Image Understanding., 141, 108\u2013125. https:\/\/doi.org\/10.1016\/j.cviu.2015.09.013","journal-title":"Computer Vision and Image Understanding."},{"key":"2978_CR42","doi-asserted-by":"crossref","unstructured":"Lai, C., Zhao, R., Zhong, X., Su, J., & Chen, Y. (2026). Selective Contrastive Learning For Gloss Free Sign Language Translation. arXiv","DOI":"10.18653\/v1\/2026.acl-long.2116"},{"key":"2978_CR43","unstructured":"Li, B., Zhang, Y., Guo, D., Zhang, R., Li, F., Zhang, H., Zhang, K., Zhang, P., Li, Y., Liu, Z., & Li, C. (2024). LLaVA-OneVision: Easy Visual Task Transfer. Transactions on Machine Learning Research."},{"key":"2978_CR44","doi-asserted-by":"crossref","unstructured":"Li, D., Opazo, C. R., Yu, X., & Li, H. (2020). Word-Level Deep Sign Language Recognition from Video: A New Large-Scale Dataset and Methods Comparison. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). pp. 1448\u20131458.","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"2978_CR45","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023). BLIP-2: Bootstrapping Language-Image Pre-Training with Frozen Image Encoders and Large Language Models. In Proceedings of the 40th International Conference on Machine Learning PMLR. pp. 19730\u201319742."},{"key":"2978_CR46","unstructured":"Li, Z., Zhou, W., Zhao, W., Wu, K., Hu, H., & Li, H. (2024). Uni-Sign: Toward Unified Sign Language Understanding at Scale. In The Thirteenth International Conference on Learning Representations (ICLR)."},{"key":"2978_CR47","unstructured":"Liang, H., Huang, C., Xu, Y., Tang, C., Ye, W., & Zhang, J. (2024). LLaVA-SLT: Visual Language Tuning for Sign Language Translation. arXiv"},{"key":"2978_CR48","unstructured":"Lin, C. Y. (2004). ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out Barcelona, Spain: Association for Computational Linguistics. pp. 74\u201381."},{"key":"2978_CR49","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, X., Zhu, L., Sun, K., Zhang, B., & Yang, Y. (2023). Gloss-Free End-to-End Sign Language Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL) Toronto, Canada: Association for Computational Linguistics. pp. 12904\u201312916.","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"2978_CR50","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Gu, J., Goyal, N., Li, X., Edunov, S., Ghazvininejad, M., Lewis, M., & Zettlemoyer, L. (2020). Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics., 8, 726\u2013742. https:\/\/doi.org\/10.1162\/tacl_a_00343","journal-title":"Transactions of the Association for Computational Linguistics."},{"issue":"86","key":"2978_CR51","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., & Hinton, G. (2008). Visualizing data using T-SNE. Journal of Machine Learning Research., 9(86), 2579\u20132605.","journal-title":"Journal of Machine Learning Research."},{"key":"2978_CR52","doi-asserted-by":"crossref","unstructured":"Moon, J., Park, J., Kim, J., Bae, J., Jeon, H., & Kim, H. Y. (2024). DiffSLT: Enhancing Diversity in Sign Language Translation via Diffusion Model. arXiv.","DOI":"10.2139\/ssrn.5144736"},{"key":"2978_CR53","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H. V., Szafraniec, M., Khalidov, V., et\u00a0al. (2023). DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research."},{"key":"2978_CR54","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). Bleu: A Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL) Philadelphia, Pennsylvania, USA: Association for Computational Linguistics. pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"2978_CR55","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning. PMLR. p. 8748\u20138763."},{"key":"2978_CR56","unstructured":"Rezende, D. J., Mohamed, S., & Wierstra, D. (2014). Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In International Conference on Machine Learning (ICML). PMLR; p. 1278\u20131286."},{"key":"2978_CR57","doi-asserted-by":"crossref","unstructured":"Rust, P., Shi, B., Wang, S., Camgoz, N. C., & Maillard, J. (2024). Towards Privacy-Aware Sign Language Translation at Scale. In: Ku LW, Martins A, Srikumar V, editors. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Bangkok, Thailand: Association for Computational Linguistics. p. 8624\u20138641.","DOI":"10.18653\/v1\/2024.acl-long.467"},{"key":"2978_CR58","doi-asserted-by":"crossref","unstructured":"Shen, D., Qin, C., Wang, C., Zhu, H., Chen, E., Xiong, H. (2021). Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness. In International Joint Conference on Artificial Intelligence (IJCAI), vol.\u00a03; pp. 2964\u20132970.","DOI":"10.24963\/ijcai.2021\/408"},{"key":"2978_CR59","doi-asserted-by":"crossref","unstructured":"Shi, B., Brentari, D., Shakhnarovich, G., & Livescu, K. (2022). Open-Domain Sign Language Translation Learned from Online Video. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) Abu Dhabi, United Arab Emirates: Association for Computational Linguistics; p. 6365\u20136379.","DOI":"10.18653\/v1\/2022.emnlp-main.427"},{"key":"2978_CR60","doi-asserted-by":"crossref","unstructured":"Shu, R., Lee, J., Nakayama, H., & Cho, K. (2020). Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a034. p. 8846\u20138853.","DOI":"10.1609\/aaai.v34i05.6413"},{"key":"2978_CR61","unstructured":"Sohn, K., Lee, H., & Yan, X. (2015). Learning Structured Output Representation Using Deep Conditional Generative Models. In Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a028 Curran Associates, Inc.; p. 3483 \u2013 3491."},{"key":"2978_CR62","doi-asserted-by":"crossref","unstructured":"Su, J., Wu, S., Xiong, D., Lu, Y., Han, X., & Zhang, B. (2018). Variational Recurrent Neural Machine Translation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) No.\u00a01.","DOI":"10.1609\/aaai.v32i1.11985"},{"key":"2978_CR63","doi-asserted-by":"crossref","unstructured":"Tan, S., Miyazaki, T., Itoyama, K., Nakadai, K. (2024). SEDA: Simple and Effective Data Augmentation for Sign Language Understanding. In Proceedings of the LREC-COLING 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources Torino, Italia: ELRA and ICCL. p. 370\u2013375.","DOI":"10.63317\/28bctqifudvv"},{"key":"2978_CR64","doi-asserted-by":"crossref","unstructured":"Tanzer, G. (2025). Fingerspelling within Sign Language Translation. In: Chiruzzo L, Ritter A, Wang L, editors. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Albuquerque, New Mexico: Association for Computational Linguistics; p. 385\u2013464.","DOI":"10.18653\/v1\/2025.naacl-long.19"},{"key":"2978_CR65","unstructured":"Tanzer, G., & Zhang, B. (2024). YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus. The Thirteenth International Conference on Learning Representations ICLR."},{"key":"2978_CR66","doi-asserted-by":"crossref","unstructured":"Tarr\u00e9s, L., G\u00e1llego, G. I., Duarte, A., Torres, J., Gir\u00f3-i-Nieto, X. (2023). Sign Language Translation from Instructional Videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 5625\u20135635.","DOI":"10.1109\/CVPRW59228.2023.00596"},{"key":"2978_CR67","doi-asserted-by":"crossref","unstructured":"Uthus, D., Tanzer, G., & Georg, M. (2023). YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus. Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track","DOI":"10.52202\/075280-1264"},{"key":"2978_CR68","unstructured":"Vahdat, A., & Kautz, J. (2020). NVAE: A Deep Hierarchical Variational Autoencoder. In Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a033 Curran Associates, Inc.. p. 19667\u201319679."},{"key":"2978_CR69","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention Is All You Need. In Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a030 Curran Associates, Inc.; p. 6000 \u2013 6010."},{"key":"2978_CR70","unstructured":"Wong, R., Camgoz, N. C., & Bowden, R. (2023). Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation. In The Twelfth International Conference on Learning Representations ICLR."},{"key":"2978_CR71","doi-asserted-by":"publisher","first-page":"3908","DOI":"10.1109\/TMM.2021.3109665","volume":"24","author":"P Xie","year":"2022","unstructured":"Xie, P., Zhao, M., & Hu, X. (2022). PiSLTRc: Position-informed sign language transformer with content-aware convolution. IEEE Transactions on Multimedia., 24, 3908\u20133919. https:\/\/doi.org\/10.1109\/TMM.2021.3109665","journal-title":"IEEE Transactions on Multimedia."},{"key":"2978_CR72","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018). Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-Offs in Video Classification. In Proceedings of the European Conference on Computer Vision (ECCV); p. 305\u2013321.","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"2978_CR73","unstructured":"Yang, A., Yang, B., Hui, B., Zheng, B., Yu, B., Zhou, C., et\u00a0al. (2024). Qwen2 Technical Report. arXiv."},{"key":"2978_CR74","doi-asserted-by":"crossref","unstructured":"Ye, J., Jiao, W., Wang, X., Tu, Z., & Xiong, H. (2023). Cross-Modality Data Augmentation for End-to-End Sign Language Translation. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore: Association for Computational Linguistics; p. 13558\u201313571.","DOI":"10.18653\/v1\/2023.findings-emnlp.904"},{"key":"2978_CR75","doi-asserted-by":"publisher","first-page":"107379","DOI":"10.52202\/079017-3411","volume":"37","author":"J Ye","year":"2024","unstructured":"Ye, J., Wang, X., Jiao, W., Liang, J., & Xiong, H. (2024). Improving gloss-free sign language translation by reducing representation density. Advances in Neural Information Processing Systems (NeurIPS), 37, 107379\u2013107402.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2978_CR76","doi-asserted-by":"crossref","unstructured":"Yin, A., Zhong, T., Tang, L., Jin, W., Jin, T., & Zhao, Z. (2023). Gloss Attention for Gloss-Free Sign Language Translation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 2551\u20132562.","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"2978_CR77","doi-asserted-by":"crossref","unstructured":"Yin, K., & Read, J. (2020). Better Sign Language Translation with STMC-Transformer. In Proceedings of the 28th International Conference on Computational Linguistics (COLING) Barcelona, Spain (Online): International Committee on Computational Linguistics. p. 5975\u20135989.","DOI":"10.18653\/v1\/2020.coling-main.525"},{"key":"2978_CR78","doi-asserted-by":"crossref","unstructured":"Yu, P., Zhang, L., Fu, B., & Chen, Y. (2023). Efficient Sign Language Translation with a Curriculum-Based Non-Autoregressive Decoder. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI) Macau, SAR China: International Joint Conferences on Artificial Intelligence Organization. p. 5260\u20135268.","DOI":"10.24963\/ijcai.2023\/584"},{"key":"2978_CR79","unstructured":"Zhang, B., M\u00fcller, M., & Sennrich, R. (2023). SLTUNET: A Simple Unified Model for Sign Language Translation. In: International Conference on Learning Representations ICLR."},{"key":"2978_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, B., Tanzer, G., & Firat, O. (2024). Scaling Sign Language Translation. The Thirty-Eighth Annual Conference on Neural Information Processing Systems","DOI":"10.52202\/079017-3621"},{"key":"2978_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiong, D., Su, J., Duan, H., & Zhang, M. (2016). Variational Neural Machine Translation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) Austin, Texas: Association for Computational Linguistics; p. 521\u2013530.","DOI":"10.18653\/v1\/D16-1050"},{"key":"2978_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhao, R., Wu, Z., Zhang, L., Zhang, H., & Chen, Y. (2025). Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks. In Findings of the Association for Computational Linguistics: NAACL 2025 Albuquerque, New Mexico: Association for Computational Linguistics; p. 6227\u20136239.","DOI":"10.18653\/v1\/2025.findings-naacl.348"},{"key":"2978_CR83","doi-asserted-by":"publisher","first-page":"2662","DOI":"10.1109\/TMM.2021.3087006","volume":"24","author":"J Zhao","year":"2022","unstructured":"Zhao, J., Qi, W., Zhou, W., Duan, N., Zhou, M., & Li, H. (2022). Conditional sentence generation and cross-modal reranking for sign language translation. IEEE Transactions on Multimedia., 24, 2662\u20132672. https:\/\/doi.org\/10.1109\/TMM.2021.3087006","journal-title":"IEEE Transactions on Multimedia."},{"key":"2978_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zhang, L., Fu, B., Hu, C., Su, J., & Chen, Y. (2024). Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a038; p. 19643\u201319651.","DOI":"10.1609\/aaai.v38i17.29937"},{"key":"2978_CR85","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zhang, R., Zhang, L., Zhang, C., Fu, H., & Chen, Y. (2026). Variational Nearest Neighbor Sign Language Translation. In ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) p. 5946\u20135950.","DOI":"10.1109\/ICASSP55912.2026.11462910"},{"key":"2978_CR86","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zhong, X., Zheng, X., Su, J., & Chen, Y. (2026). CNSL-Bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language. arXiv","DOI":"10.18653\/v1\/2026.acl-long.1896"},{"key":"2978_CR87","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/j.neucom.2021.08.079","volume":"464","author":"J Zheng","year":"2021","unstructured":"Zheng, J., Chen, Y., Wu, C., Shi, X., & Kamal, S. M. (2021). Enhancing neural sign language translation by highlighting the facial expression information. Neurocomputing., 464, 462\u2013472. https:\/\/doi.org\/10.1016\/j.neucom.2021.08.079","journal-title":"Neurocomputing."},{"key":"2978_CR88","doi-asserted-by":"crossref","unstructured":"Zheng, J., Wang, Y., Tan, C., Li, S., Wang, G., Xia, J., Chen, Y., & Li, S.Z. (2023). CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 23141\u201323150.","DOI":"10.1109\/CVPR52729.2023.02216"},{"key":"2978_CR89","doi-asserted-by":"crossref","unstructured":"Zhou, B., Chen, Z., Clap\u00e9s, A., Wan, J., Liang, Y., Escalera, S., Lei, Z., & Zhang, D. (2023). Gloss-Free Sign Language Translation: Improving from Visual-Language Pretraining. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). p. 20871\u201320881.","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"2978_CR90","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Qi, W., Pu, J., & Li, H. (2021). Improving Sign Language Translation with Monolingual Data by Sign Back-Translation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 1316\u20131325.","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"2978_CR91","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. (2022). Spatial-temporal multi-cue network for sign language recognition and translation. IEEE Transactions on Multimedia., 24, 768\u2013779. https:\/\/doi.org\/10.1109\/TMM.2021.3059098","journal-title":"IEEE Transactions on Multimedia."},{"key":"2978_CR92","unstructured":"Zhou, W., Zhao, W., Hu, H., Li, Z., & Li, H. (2024). Scaling up Multimodal Pre-Training for Sign Language Understanding. arXiv."},{"key":"2978_CR93","doi-asserted-by":"crossref","unstructured":"Zhu, M., Wang, J., & Yan, C. (2022). Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework. In Proceedings of the 2022 conference of the north american chapter of the association for computational linguistics (naacl): human language technologies seattle, United States: Association for Computational Linguistics; p. 607\u2013617.","DOI":"10.18653\/v1\/2022.naacl-main.45"},{"key":"2978_CR94","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Bi, W., Liu, X., Ma, X., Li, X., & Wu, D. (2020). A Batch Normalized Inference Network Keeps the KL Vanishing Away. In Proceedings of the 58th annual meeting of the association for computational linguistics (acl) online: association for computational linguistics. pp. 2636\u20132649.","DOI":"10.18653\/v1\/2020.acl-main.235"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02978-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02978-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02978-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:11:02Z","timestamp":1790151062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02978-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":94,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["2978"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02978-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"4 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"408"}}