{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:23:32Z","timestamp":1783437812749,"version":"3.54.6"},"reference-count":168,"publisher":"Informa UK Limited","issue":"23","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Tateishi Research Grant","award":["2241011"],"award-info":[{"award-number":["2241011"]}]},{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["JP19KK0260"],"award-info":[{"award-number":["JP19KK0260"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["JP20H00475"],"award-info":[{"award-number":["JP20H00475"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1080\/01691864.2024.2442721","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T05:01:39Z","timestamp":1735016499000},"page":"1649-1667","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":11,"title":["A review of deep learning-based approaches to sign language processing"],"prefix":"10.1080","volume":"38","author":[{"given":"Sihan","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nabeela","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyi","family":"An","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshitaka","family":"Ando","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rei","family":"Kawakami","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhiro","family":"Nakadai","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.anthro.31.020402.101302"},{"key":"e_1_3_4_3_1","unstructured":"World Federation of the Deaf. https:\/\/wfdeaf.org\/our-work\/. [Accessed 2024 June]"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/0142723719834102"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10995-017-2287-y"},{"key":"e_1_3_4_6_1","doi-asserted-by":"crossref","unstructured":"Min Y Hao A Chai X et\u00a0al. Visual alignment constraint for continuous sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV); 2021. p. 11542\u201311551.","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"e_1_3_4_7_1","unstructured":"Sandoval-Castaneda M Li Y Brentari D et\u00a0al. Self-supervised video transformers for isolated sign language recognition; 2023. Available from: arXiv preprint arXiv:230902450."},{"key":"e_1_3_4_8_1","unstructured":"Tan S Miyazaki T Itoyama K et\u00a0al. 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; 2024. p. 370\u2013375."},{"key":"e_1_3_4_9_1","doi-asserted-by":"crossref","unstructured":"Rastgoo R Kiani K Escalera S et\u00a0al. Sign language production: a review. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2021. p. 3451\u20133461.","DOI":"10.1109\/CVPRW53098.2021.00384"},{"key":"e_1_3_4_10_1","unstructured":"Koller O. Quantitative survey of the state of the art in sign language recognition; 2020. Available from: arXiv preprint arXiv:200809918v2."},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118993"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12122678"},{"key":"e_1_3_4_13_1","unstructured":"Devlin J Chang M Lee K et\u00a0al. BERT: pre-training of deep bidirectional transformers for language understanding; 2018. Available from: http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_4_14_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T","year":"2020","unstructured":"Brown T, Mann B, Ryder N, et\u00a0al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020;33:1877\u20131901.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_15_1","unstructured":"Radford A Kim JW Hallacy C et\u00a0al. Learning transferable visual models from natural language supervision. In: Meila M Zhang T editors. Proceedings of the 38th International Conference on Machine Learning (Vol. 139); 18\u201324 Jul. PMLR; 2021. p. 8748\u20138763."},{"key":"e_1_3_4_16_1","unstructured":"Oquab M Darcet T Moutakanni T et\u00a0al. DINOv2: learning robust visual features without supervision. Transactions on Machine Learning Research; 2024. Available from: https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"e_1_3_4_17_1","unstructured":"Yu L Lezama J Gundavarapu NB et\u00a0al. Language model beats diffusion \u2013 tokenizer is key to visual generation. In: The Twelfth International Conference on Learning Representations; 2024. p. 1\u201319."},{"key":"e_1_3_4_18_1","doi-asserted-by":"crossref","unstructured":"Yin K Read J. Better sign language translation with STMC-transformer. In: Proceedings of the 28th International Conference on Computational Linguistics; Dec.; Barcelona Spain (Online). International Committee on Computational Linguistics; 2020. p. 5975\u20135989.","DOI":"10.18653\/v1\/2020.coling-main.525"},{"key":"e_1_3_4_19_1","unstructured":"Wong R Camgoz NC Bowden R. Sign2GPT: leveraging large language models for gloss-free sign language translation; 2024. Available from: arXiv preprint arXiv:240504164."},{"key":"e_1_3_4_20_1","doi-asserted-by":"crossref","unstructured":"Camgoz NC Hadfield S Koller O et\u00a0al. Using convolutional 3D neural networks for user-independent continuous gesture recognition. In: 2016 23rd International Conference on Pattern Recognition (ICPR); 2016. p. 49\u201354.","DOI":"10.1109\/ICPR.2016.7899606"},{"key":"e_1_3_4_21_1","doi-asserted-by":"crossref","unstructured":"Sarhan N Frintrop S. Unraveling a decade: a comprehensive survey on isolated sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2023. p. 3210\u20133219.","DOI":"10.1109\/ICCVW60793.2023.00345"},{"key":"e_1_3_4_22_1","doi-asserted-by":"crossref","unstructured":"Li D Rodriguez C Yu X et\u00a0al. Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision; 2020. p. 1459\u20131469.","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"e_1_3_4_23_1","doi-asserted-by":"crossref","unstructured":"Cho K van Merri\u00ebnboer B Gulcehre C et\u00a0al. Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Moschitti A Pang B Daelemans W editors. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha Qatar: Association for Computational Linguistics; 2014. p. 1724\u20131734. Available from: https:\/\/aclanthology.org\/D14-1179","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_4_24_1","unstructured":"Huang J Zhou W Li H et\u00a0al. Sign language recognition using 3d convolutional neural networks. In: 2015 IEEE International Conference on Multimedia and Expo (ICME); 2015. p. 1\u20136."},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3070438"},{"key":"e_1_3_4_26_1","doi-asserted-by":"crossref","unstructured":"Chen Y Wei F Sun X et\u00a0al. 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); 2022. p. 5120\u20135130.","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"e_1_3_4_27_1","unstructured":"Miyazaki T Morita Y Sano M. Machine translation from spoken language to sign language using pre-trained language model as encoder. In: Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community Technological Challenges and Application Perspectives. ELRA; 2020. p. 139\u2013144."},{"key":"e_1_3_4_28_1","unstructured":"Moryossef A Yin K Neubig G. Data augmentation for sign language gloss translation; 2021. Available from: arXiv preprint arXiv:210507476."},{"key":"e_1_3_4_29_1","doi-asserted-by":"crossref","unstructured":"Camgoz NC Hadfield S Koller O et\u00a0al. Neural sign language translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018. p. 7784\u20137793.","DOI":"10.1109\/CVPR.2018.00812"},{"key":"e_1_3_4_30_1","unstructured":"Camgoz NC Koller O Hadfield S et\u00a0al. 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; 2020. p. 10023\u201310033."},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.013"},{"key":"e_1_3_4_32_1","doi-asserted-by":"crossref","unstructured":"Zhou H Zhou W Qi W et\u00a0al. Improving sign language translation with monolingual data by sign back-translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2021. p. 1316\u20131325.","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"e_1_3_4_33_1","doi-asserted-by":"crossref","unstructured":"Cui R Liu H Zhang C. Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 7361\u20137369.","DOI":"10.1109\/CVPR.2017.175"},{"key":"e_1_3_4_34_1","doi-asserted-by":"crossref","unstructured":"Molchanov P Yang X Gupta S et\u00a0al. Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 4207\u20134215.","DOI":"10.1109\/CVPR.2016.456"},{"key":"e_1_3_4_35_1","doi-asserted-by":"crossref","unstructured":"Graves A Fern\u00e1ndez S Gomez F et\u00a0al. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning; 2006. p. 369\u2013376.","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_4_36_1","first-page":"839","article-title":"Connectionist temporal classification with maximum entropy regularization","volume":"31","author":"Liu H","year":"2018","unstructured":"Liu H, Jin S, Zhang C. Connectionist temporal classification with maximum entropy regularization. Adv Neural Inf Process Syst. 2018;31:839\u2013849.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_37_1","doi-asserted-by":"crossref","unstructured":"Sihan T Khanum KN Katsutoshi I et\u00a0al. Improving sign language understanding introducing label smoothing. In: 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN); 2023. p. 113\u2013118.","DOI":"10.1109\/RO-MAN57019.2023.10309531"},{"key":"e_1_3_4_38_1","doi-asserted-by":"crossref","unstructured":"Zhou H Zhou W Li H. Dynamic pseudo label decoding for continuous sign language recognition. In: 2019 IEEE International Conference on Multimedia and Expo (ICME); 2019. p. 1282\u20131287.","DOI":"10.1109\/ICME.2019.00223"},{"key":"e_1_3_4_39_1","doi-asserted-by":"crossref","unstructured":"Zhou H Zhou W Zhou Y et\u00a0al. Spatial-temporal multi-cue network for continuous sign language recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2020. p. 13009\u201313016.","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"e_1_3_4_40_1","doi-asserted-by":"crossref","unstructured":"Jiao P Min Y Li Y et\u00a0al. Cosign: exploring co-occurrence signals in skeleton-based continuous sign language recognition. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV); 2023. p. 20619\u201320629.","DOI":"10.1109\/ICCV51070.2023.01890"},{"key":"e_1_3_4_41_1","first-page":"17043","article-title":"Two-stream network for sign language recognition and translation","volume":"35","author":"Chen Y","year":"2022","unstructured":"Chen Y, Zuo R, Wei F, et\u00a0al. Two-stream network for sign language recognition and translation. Adv Neural Inf Process Syst. 2022;35:17043\u201317056.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_42_1","doi-asserted-by":"crossref","unstructured":"Zuo R Mak B. C2slr: consistency-enhanced continuous sign language recognition. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022. p. 5121\u20135130.","DOI":"10.1109\/CVPR52688.2022.00507"},{"key":"e_1_3_4_43_1","doi-asserted-by":"crossref","unstructured":"Camgoz NC Hadfield S Koller O et\u00a0al. Subunets: end-to-end hand shape and continuous sign language recognition. In: 2017 IEEE International Conference on Computer Vision (ICCV); 2017. p. 3075\u20133084.","DOI":"10.1109\/ICCV.2017.332"},{"key":"e_1_3_4_44_1","doi-asserted-by":"crossref","unstructured":"Koller O Zargaran S Ney H. Re-sign: re-aligned end-to-end sequence modelling with deep recurrent cnn-hmms. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. p. 3416\u20133424.","DOI":"10.1109\/CVPR.2017.364"},{"key":"e_1_3_4_45_1","doi-asserted-by":"crossref","unstructured":"Pu J Zhou W Li H. Iterative alignment network for continuous sign language recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2019. p. 4160\u20134169.","DOI":"10.1109\/CVPR.2019.00429"},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.34"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.6046"},{"key":"e_1_3_4_48_1","doi-asserted-by":"crossref","unstructured":"Niu Z Mak B. Stochastic fine-grained labeling of multi-state sign glosses for continuous sign language recognition. In: Computer Vision\u2013ECCV 2020: 16th European Conference Glasgow UK August 23\u201328 2020; Proceedings Part XVI 16. Springer; 2020. p. 172\u2013186.","DOI":"10.1007\/978-3-030-58517-4_11"},{"key":"e_1_3_4_49_1","doi-asserted-by":"crossref","unstructured":"Hao A Min Y Chen X. Self-mutual distillation learning for continuous sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2021. p. 11303\u201311312.","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"e_1_3_4_50_1","doi-asserted-by":"crossref","unstructured":"Min Y Jiao P Li Y et\u00a0al. Deep radial embedding for visual sequence learning. In: European Conference on Computer Vision. Springer; 2022. p. 240\u2013256.","DOI":"10.1007\/978-3-031-20068-7_14"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"e_1_3_4_52_1","doi-asserted-by":"crossref","unstructured":"Hu L Gao L Liu Z et\u00a0al. Continuous sign language recognition with correlation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 2529\u20132539.","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"e_1_3_4_53_1","doi-asserted-by":"crossref","unstructured":"Ahn J Jang Y Chung JS. Slowfast network for continuous sign language recognition. In: ICASSP 2024 \u2013 2024 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP); 2024. p. 3920\u20133924.","DOI":"10.1109\/ICASSP48485.2024.10445841"},{"key":"e_1_3_4_54_1","doi-asserted-by":"crossref","unstructured":"Huang J Zhou W Zhang Q et\u00a0al. Video-based sign language recognition without temporal segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2018. p. 2257\u20132264.","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"e_1_3_4_55_1","unstructured":"Othman A Jemni M. English-asl gloss parallel corpus 2012: Aslg-pc12. In: Sign-lang@ LREC 2012. European Language Resources Association (ELRA); 2012. p. 151\u2013154."},{"key":"e_1_3_4_56_1","doi-asserted-by":"crossref","unstructured":"Yin A Zhao Z Jin W et\u00a0al. Mlslt: towards multilingual sign language translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2022. p. 5109\u20135119.","DOI":"10.1109\/CVPR52688.2022.00505"},{"key":"e_1_3_4_57_1","unstructured":"Hanke T Schulder M Konrad R et\u00a0al. Extending the public DGS corpus in size and depth. In: Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community Technological Challenges and Application Perspectives. Marseille France: European Language Resources Association (ELRA); 2020. p. 75\u201382."},{"key":"e_1_3_4_58_1","doi-asserted-by":"crossref","unstructured":"Papineni K Roukos S Ward T et\u00a0al. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics; 2002. p. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_4_59_1","doi-asserted-by":"crossref","unstructured":"Lin CY Och FJ. Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04); 2004. p. 605\u2013612.","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_4_60_1","doi-asserted-by":"crossref","unstructured":"Popovi\u0107 M. chrF: character n-gram F-score for automatic MT evaluation. In: Bojar O Chatterjee R Federmann C et\u00a0al. editors. Proceedings of the Tenth Workshop on Statistical Machine Translation. Lisbon Portugal: Association for Computational Linguistics; 2015. p. 392\u2013395. Available from: https:\/\/aclanthology.org\/W15-3049","DOI":"10.18653\/v1\/W15-3049"},{"key":"e_1_3_4_61_1","unstructured":"Banerjee S Lavie A. Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization; 2005. p. 65\u201372."},{"key":"e_1_3_4_62_1","doi-asserted-by":"crossref","unstructured":"Vedantam R Lawrence Zitnick C Parikh D. Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015. p. 4566\u20134575.","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_4_63_1","doi-asserted-by":"crossref","unstructured":"Chen Y Wei F Sun X et\u00a0al. A simple multi-modality transfer learning baseline for sign language translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2022. p. 5120\u20135130.","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"e_1_3_4_64_1","doi-asserted-by":"crossref","unstructured":"Fu B Ye P Zhang L et\u00a0al. A token-level contrastive framework for sign language translation. In: ICASSP 2023-2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). IEEE; 2023. p. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095466"},{"key":"e_1_3_4_65_1","unstructured":"Zhang B M\u00fcller M Sennrich R. SLTUNET: a simple unified model for sign language translation. In: The Eleventh International Conference on Learning Representations ICLR 2023; Kigali Rwanda 2023 May 1\u20135. OpenReview.net; 2023. p. 1\u201318. Available from: https:\/\/openreview.net\/pdf?id=EBS4C77p_5S"},{"key":"e_1_3_4_66_1","doi-asserted-by":"crossref","unstructured":"Camgoz NC Koller O Hadfield S et\u00a0al. Multi-channel transformers for multi-articulatory sign language translation. In: Computer Vision\u2013ECCV 2020 Workshops: Glasgow (UK) 2020 August 23\u201328; Proceedings Part IV 16. Springer; 2020. p. 301\u2013319.","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"e_1_3_4_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059098"},{"key":"e_1_3_4_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087006"},{"key":"e_1_3_4_69_1","doi-asserted-by":"crossref","unstructured":"Orbay A Akarun L. Neural sign language translation by learning tokenization. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). IEEE; 2020. p. 222\u2013228.","DOI":"10.1109\/FG47880.2020.00002"},{"key":"e_1_3_4_70_1","first-page":"12034","article-title":"Tspnet: hierarchical feature learning via temporal semantic pyramid for sign language translation","volume":"33","author":"Li D","year":"2020","unstructured":"Li D, Xu C, Yu X, et\u00a0al. Tspnet: hierarchical feature learning via temporal semantic pyramid for sign language translation. Adv Neural Inf Process Syst. 2020;33:12034\u201312045.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_71_1","doi-asserted-by":"crossref","unstructured":"Yin A Zhong T Tang L et\u00a0al. Gloss attention for gloss-free sign language translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 2551\u20132562.","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"e_1_3_4_72_1","doi-asserted-by":"crossref","unstructured":"Zhou B Chen Z Clap\u00e9s A et\u00a0al. Gloss-free sign language translation: improving from visual-language pretraining. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2023. p. 20871\u201320881.","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"e_1_3_4_73_1","unstructured":"Chen Z Zhou B Li J et\u00a0al. Factorized learning assisted with large language model for gloss-free sign language translation; 2024. Available from: arXiv preprint arXiv:240312556."},{"key":"e_1_3_4_74_1","doi-asserted-by":"crossref","unstructured":"Gong J Foo LG He Y et\u00a0al. Llms are good sign language translators; 2024. Available from: arXiv preprint arXiv:240400925.","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"e_1_3_4_75_1","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Adv Neural Inf Process Syst. 2017;30:6000\u20136010.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_76_1","doi-asserted-by":"crossref","unstructured":"Yin K Moryossef A Hochgesang J et\u00a0al. Including signed languages in natural language processing. In: Zong C Xia F Li W et\u00a0al. editors. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Vol.\u00a01: Long Papers); Online. Association for Computational Linguistics; 2021. p. 7347\u20137360. Available from: https:\/\/aclanthology.org\/2021.acl-long.570","DOI":"10.18653\/v1\/2021.acl-long.570"},{"issue":"3","key":"e_1_3_4_77_1","first-page":"1","article-title":"Reading and deafness: state of the evidence and implications for research and practice","volume":"9","author":"Trezek B","year":"2019","unstructured":"Trezek B, Mayer C. Reading and deafness: state of the evidence and implications for research and practice. Edu Sci. 2019;9(3):1\u201314.","journal-title":"Edu Sci"},{"key":"e_1_3_4_78_1","doi-asserted-by":"crossref","unstructured":"Duarte A Palaskar S Ventura L et\u00a0al. How2sign: a large-scale multimodal dataset for continuous American sign language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2021. p. 2735\u20132744.","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"e_1_3_4_79_1","unstructured":"Stoll S Camg\u00f6z NC Hadfield S et\u00a0al. Sign language production using neural machine translation and generative adversarial networks. In: Proceedings of the 29th British Machine Vision Conference (BMVC 2018). British Machine Vision Association; 2018. p. 1\u201312."},{"key":"e_1_3_4_80_1","doi-asserted-by":"crossref","unstructured":"Saunders B Camgoz NC Bowden R. Progressive transformers for end-to-end sign language production. In: Computer Vision\u2013ECCV 2020: 16th European Conference Glasgow UK 2020 August 23\u201328; Proceedings Part XI 16. Springer; 2020. p. 687\u2013705.","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"e_1_3_4_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01457-9"},{"key":"e_1_3_4_82_1","doi-asserted-by":"crossref","unstructured":"Saunders B Camgoz NC Bowden R. Mixed signals: sign language production via a mixture of motion primitives. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2021. p. 1919\u20131929.","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"e_1_3_4_83_1","unstructured":"Hwang EJ Kim JH Park JC. Non-autoregressive sign language production with Gaussian space. In: BMVC. Vol. 1; 2021. p. 3."},{"key":"e_1_3_4_84_1","doi-asserted-by":"crossref","unstructured":"Arkushin RS Moryossef A Fried O. Ham2pose: animating sign language notation into pose sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 21046\u201321056.","DOI":"10.1109\/CVPR52729.2023.02016"},{"key":"e_1_3_4_85_1","unstructured":"Walsh H Saunders B Bowden R. Changing the representation: examining language representation for neural sign language production; 2022. arXiv preprint arXiv:221006312."},{"key":"e_1_3_4_86_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.030"},{"key":"e_1_3_4_87_1","unstructured":"Fang S Sui C Zhang X et\u00a0al. Signdiff: learning diffusion models for American sign language production; 2023. Available from: arXiv preprint arXiv:230816082."},{"key":"e_1_3_4_88_1","doi-asserted-by":"crossref","unstructured":"Baltatzis V Potamias RA Ververas E et\u00a0al. Neural sign actors: a diffusion model for 3d sign language production from text. In: CVPR; 2024. p. 1985\u20131995.","DOI":"10.1109\/CVPR52733.2024.00194"},{"key":"e_1_3_4_89_1","unstructured":"Ventura L Duarte A Gir\u00f3-i Nieto X. Can everybody sign now? Exploring sign language video generation from 2d poses; 2020. Available from: arXiv preprint arXiv:201210941"},{"key":"e_1_3_4_90_1","unstructured":"Saunders B Camgoz NC Bowden R. Everybody sign now: translating spoken language to photo realistic sign language video; 2020. Available from: arXiv preprint arXiv:201109846."},{"key":"e_1_3_4_91_1","doi-asserted-by":"crossref","unstructured":"Saunders B Camgoz NC Bowden R. Signing at scale: learning to co-articulate signs for large-scale photo-realistic sign language production. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2022. p. 5141\u20135151.","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"e_1_3_4_92_1","doi-asserted-by":"crossref","unstructured":"Zhang L Rao A Agrawala M. Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2023. p. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_4_93_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01281-2"},{"key":"e_1_3_4_94_1","unstructured":"Saunders B Camgoz NC Bowden R. Adversarial training for multi-channel sign language production; 2020. Available from: arXiv preprint arXiv:200812405."},{"key":"e_1_3_4_95_1","unstructured":"Saunders B Camgoz NC Bowden R. Skeletal graph self-attention: embedding a skeleton inductive bias into sign language production; 2021. Available from: arXiv preprint arXiv:211205277."},{"key":"e_1_3_4_96_1","doi-asserted-by":"crossref","unstructured":"Zhu D Czehmann V Avramidis E. Neural machine translation methods for translating text to sign language glosses. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers); 2023. p. 12523\u201312541.","DOI":"10.18653\/v1\/2023.acl-long.700"},{"key":"e_1_3_4_97_1","doi-asserted-by":"crossref","unstructured":"Kanakanti M Singh S Shrivastava M. Multifacet: a multi-tasking framework for speech-to-sign language generation. In: Companion Publication of the 25th International Conference on Multimodal Interaction; 2023. p. 205\u2013213.","DOI":"10.1145\/3610661.3616550"},{"key":"e_1_3_4_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"e_1_3_4_99_1","unstructured":"Zhao WX Zhou K Li J et\u00a0al. A survey of large language models; 2023. arXiv preprint arXiv:230318223."},{"key":"e_1_3_4_100_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_4_101_1","unstructured":"Lin XV Mihaylov T Artetxe M et\u00a0al. Few-shot learning with multilingual language models; 2021. Available from: https:\/\/arxiv.org\/abs\/2112.10668"},{"key":"e_1_3_4_102_1","unstructured":"Touvron H Lavril T Izacard G et\u00a0al. Llama: open and efficient foundation language models; 2023. arXiv preprint arXiv:230213971."},{"key":"e_1_3_4_103_1","unstructured":"Sutskever I Vinyals O Le QV. Sequence to sequence learning with neural networks; 2014. Available from: http:\/\/arxiv.org\/abs\/1409.3215"},{"key":"e_1_3_4_104_1","unstructured":"Kalchbrenner N Espeholt L Simonyan K et\u00a0al. Neural machine translation in linear time; 2016. Available from: arXiv preprint arXiv:161010099."},{"key":"e_1_3_4_105_1","doi-asserted-by":"crossref","unstructured":"Lewis M Liu Y Goyal N et\u00a0al. BART: denoising sequence-to-sequence pre-training for natural language generation translation and comprehension; 2019. Available from: http:\/\/arxiv.org\/abs\/1910.13461","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"70","key":"e_1_3_4_106_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung HW","year":"2024","unstructured":"Chung HW, Hou L, Longpre S, et\u00a0al. Scaling instruction-finetuned language models. J Mach Learn Res. 2024;25(70):1\u201353. Available from: http:\/\/jmlr.org\/papers\/v25\/23-0870.html","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_107_1","unstructured":"Tay Y Dehghani M Tran VQ et\u00a0al. Ul2: unifying language learning paradigms. In: The Eleventh International Conference on Learning Representations; 2023. p. 1\u201333."},{"issue":"240","key":"e_1_3_4_108_1","first-page":"1","article-title":"Palm: scaling language modeling with pathways","volume":"24","author":"Chowdhery A","year":"2023","unstructured":"Chowdhery A, Narang S, Devlin J, et\u00a0al. Palm: scaling language modeling with pathways. J Mach Learn Res. 2023;24(240):1\u2013113. Available from: http:\/\/jmlr.org\/papers\/v24\/22-1144.html","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_109_1","first-page":"1","article-title":"DINOv2: learning robust visual features without supervision","author":"Oquab M","year":"2024","unstructured":"Oquab M, Darcet T, Moutakanni T, et al. DINOv2: learning robust visual features without supervision. Transact Machine Learn Res. 2024;1\u201332.","journal-title":"Transact Machine Learn Res"},{"key":"e_1_3_4_110_1","unstructured":"Hu EJ Shen Y Wallis P et\u00a0al. LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations; 2022. p. 1\u201313."},{"key":"e_1_3_4_111_1","unstructured":"Kingma DP Welling M. Auto-encoding variational bayes. In: The Second International Conference on Learning Representations; 2014. p. 1\u201314."},{"key":"e_1_3_4_112_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho J","year":"2020","unstructured":"Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models. Adv Neural Inf Process Syst. 2020;33:6840\u20136851.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_113_1","doi-asserted-by":"crossref","unstructured":"Athanasiou N Petrovich M Black MJ et\u00a0al. Sinc: spatial composition of 3d human motions for simultaneous action generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2023. p. 9984\u20139995.","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"e_1_3_4_114_1","doi-asserted-by":"crossref","unstructured":"Kalakonda SS Maheshwari S Sarvadevabhatla RK. Action-GPT: leveraging large-scale language models for improved and generalized action generation. In: 2023 IEEE International Conference on Multimedia and Expo (ICME). IEEE; 2023. p. 31\u201336.","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"e_1_3_4_115_1","doi-asserted-by":"crossref","unstructured":"Huang Y Wan W Yang Y et\u00a0al. Como: controllable motion generation through language guided pose code editing; 2024. Available from: arXiv preprint arXiv:240313900","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"e_1_3_4_116_1","unstructured":"Achiam J Adler S Agarwal S et\u00a0al. Gpt-4 technical report; 2023. Available from: arXiv preprint arXiv:230308774."},{"key":"e_1_3_4_117_1","doi-asserted-by":"crossref","unstructured":"Zhang Y Huang D Liu B et\u00a0al. MotionGPT: finetuned LLMs are general-purpose motion generators. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2024. p. 7368\u20137376.","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"e_1_3_4_118_1","first-page":"1","article-title":"Free-bloom: zero-shot text-to-video generator with LLM director and LDM animator","volume":"36","author":"Huang H","year":"2024","unstructured":"Huang H, Feng Y, Shi C, et\u00a0al. Free-bloom: zero-shot text-to-video generator with LLM director and LDM animator. Adv Neural Inf Process Syst. 2024;36:1\u201324.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_119_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang L","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, et\u00a0al. Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst. 2022;35:27730\u201327744.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_120_1","unstructured":"Long F Qiu Z Yao T et\u00a0al. Videodrafter: content-consistent multi-scene video generation with llm; 2024. Available from: arXiv preprint arXiv:240101256."},{"key":"e_1_3_4_121_1","unstructured":"GLM T Zeng A Xu B et\u00a0al. Chatglm: a family of large language models from glm-130b to glm-4 all tools; 2024. Available from: arXiv preprint arXiv:240612793."},{"key":"e_1_3_4_122_1","unstructured":"Wu S Fei H Qu L et\u00a0al. NExT-GPT: any-to-any multimodal LLM; 2023. Available from: arXiv preprint arXiv:230905519."},{"key":"e_1_3_4_123_1","unstructured":"Chiang WL Li Z Lin Z et\u00a0al. Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality. See https:\/\/vicuna lmsys org [accessed 2023 April 14]. 2023;2(3):6."},{"key":"e_1_3_4_124_1","unstructured":"Lian L Shi B Yala A et\u00a0al. LLM-grounded video diffusion models. In: The Twelfth International Conference on Learning Representations; 2024. p. 1\u201321."},{"key":"e_1_3_4_125_1","unstructured":"Kondratyuk D Yu L Gu X et\u00a0al. Videopoet: a large language model for zero-shot video generation. In: The International Conference on Machine Learning (ICML); 2024. p. 1\u201320."},{"key":"e_1_3_4_126_1","unstructured":"Anil R Dai AM Firat O et\u00a0al. Palm 2 technical report; 2023. Available from: arXiv preprint arXiv:230510403."},{"key":"e_1_3_4_127_1","unstructured":"Chen H Xia M He Y et\u00a0al. Videocrafter1: open diffusion models for high-quality video generation; 2023. Available from: arXiv preprint arXiv:231019512."},{"key":"e_1_3_4_128_1","unstructured":"OpenAI. Video generation models as world simulators; 2024. Available from: https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"e_1_3_4_129_1","doi-asserted-by":"crossref","unstructured":"Peebles W Xie S. Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2023. p. 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_4_130_1","unstructured":"Liu H Li C Wu Q et\u00a0al. Visual instruction tuning. In: Advances in Neural Information Processing Systems; 2023. p. 34892\u201334916."},{"key":"e_1_3_4_131_1","doi-asserted-by":"crossref","unstructured":"Von Agris U Knorr M Kraiss KF. The significance of facial features for automatic sign language recognition. In: 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition; 2008. p. 1\u20136.","DOI":"10.1109\/AFGR.2008.4813472"},{"key":"e_1_3_4_132_1","doi-asserted-by":"crossref","unstructured":"Pu J Zhou W Li H. Sign language recognition with multi-modal features. In: Advances in Multimedia Information Processing-PCM 2016: 17th Pacific-Rim Conference on Multimedia. Xi'an China 2016 September 15\u201316; Proceedings Part II; 2016. p. 252\u2013261.","DOI":"10.1007\/978-3-319-48896-7_25"},{"key":"e_1_3_4_133_1","unstructured":"Adaloglou N Chatzis T Papastratis I et\u00a0al. A comprehensive study on sign language recognition methods. Vol. 2. No. 2; 2020. Available from: arXiv preprint arXiv:200712530."},{"key":"e_1_3_4_134_1","unstructured":"Joze HRV Koller O. MS-ASL: a large-scale data set and benchmark for understanding American sign language; 2018. Available from: arXiv preprint arXiv:181201053."},{"key":"e_1_3_4_135_1","unstructured":"Forster J Schmidt C Koller O et\u00a0al. Extensions of the sign language recognition and translation corpus rwth-phoenix-weather. In: LREC; 2014. p. 1911\u20131916."},{"key":"e_1_3_4_136_1","unstructured":"Hochgesang JA Crasborn O Lillo-Martin DC. Building the asl signbank. lemmatization principles for asl. In: International Conference on Language Resources and Evaluation; 2018. p. 69\u201374."},{"key":"e_1_3_4_137_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-016-0742-0"},{"key":"e_1_3_4_138_1","unstructured":"Neidle C Vogler C. A new web interface to facilitate access to corpora: development of the asllrp data access interface (dai). In: Proc. 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon; LREC. Vol. 3. Citeseer; 2012. p. 1\u20136."},{"key":"e_1_3_4_139_1","unstructured":"Albanie S Varol G Momeni L et\u00a0al. Bbc-oxford British sign language dataset; 2021. Available from: https:\/\/arxiv.org\/abs\/2111.03635"},{"key":"e_1_3_4_140_1","first-page":"136","article-title":"Building the British sign language corpus","volume":"7","author":"Schembri A","year":"2013","unstructured":"Schembri A, Fenlon J, Rentelis R, et\u00a0al. Building the British sign language corpus. Lang Document Conser. 2013;7:136\u2013154.","journal-title":"Lang Document Conser"},{"key":"e_1_3_4_141_1","doi-asserted-by":"crossref","unstructured":"Shi B Brentari D Shakhnarovich G et\u00a0al. Open-domain sign language translation learned from online video. In: EMNLP; 2022. p. 6365\u20136379.","DOI":"10.18653\/v1\/2022.emnlp-main.427"},{"key":"e_1_3_4_142_1","unstructured":"Fang S Wang L Zheng C et\u00a0al. SignLLM: sign languages production large language models; 2024."},{"key":"e_1_3_4_143_1","unstructured":"Hanke T Schulder M Konrad R et\u00a0al. Extending the public dgs corpus in size and depth. In: Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community Technological Challenges and Application Perspectives; 2020. p. 75\u201382."},{"key":"e_1_3_4_144_1","unstructured":"von Agris U Kraiss KF. Signum database: video corpus for signer-independent continuous sign language recognition. In: sign-lang@ LREC 2010; European Language Resources Association (ELRA); 2010. p. 243\u2013246."},{"key":"e_1_3_4_145_1","doi-asserted-by":"crossref","unstructured":"M\u00fcller M Jiang Z Moryossef A et\u00a0al. Considerations for meaningful sign language machine translation based on glosses. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers); Jul.; Toronto Canada. Association for Computational Linguistics; 2023. p. 682\u2013693. Available from: https:\/\/aclanthology.org\/2023.acl-short.60","DOI":"10.18653\/v1\/2023.acl-short.60"},{"key":"e_1_3_4_146_1","first-page":"1","article-title":"Youtube-asl: a large-scale, open-domain American sign language-English parallel corpus","volume":"36","author":"Uthus D","year":"2024","unstructured":"Uthus D, Tanzer G, Georg M. Youtube-asl: a large-scale, open-domain American sign language-English parallel corpus. Adv Neural Inf Process Syst. 2024;36:1\u201319.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_147_1","doi-asserted-by":"crossref","unstructured":"Denkowski M Lavie A. Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation; 2014. p. 376\u2013380.","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_4_148_1","doi-asserted-by":"crossref","unstructured":"Post M. A call for clarity in reporting BLEU scores. In: Bojar O Chatterjee R Federmann C et\u00a0al. editors. Proceedings of the Third Conference on Machine Translation: Research Papers; Oct.; Brussels Belgium. Association for Computational Linguistics; 2018. p. 186\u2013191. Available from: https:\/\/aclanthology.org\/W18-6319","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_4_149_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"},{"key":"e_1_3_4_150_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"e_1_3_4_151_1","doi-asserted-by":"crossref","unstructured":"Takahashi K Mikami D Isogawa M et\u00a0al. Human pose as calibration pattern; 3d human pose estimation with multiple unsynchronized and uncalibrated cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops; 2018. p. 1775\u20131782.","DOI":"10.1109\/CVPRW.2018.00230"},{"key":"e_1_3_4_152_1","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel M","year":"2017","unstructured":"Heusel M, Ramsauer H, Unterthiner T, et al. Gans trained by a two time-scale update rule converge to a local Nash equilibrium. Adv Neural Inf Process Syst. 2017;30:6626\u20136637.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_4_154_1","doi-asserted-by":"crossref","unstructured":"Jayasumana S Ramalingam S Veit A et\u00a0al. Rethinking fid: towards a better evaluation metric for image generation; 2023. Available from: arXiv preprint arXiv:240109603.","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"e_1_3_4_155_1","doi-asserted-by":"crossref","unstructured":"Pambrun JF Noumeir R. Limitations of the SSIM quality metric in the context of diagnostic imaging. In: 2015 IEEE International Conference on Image Processing (ICIP). IEEE; 2015. p. 2960\u20132963.","DOI":"10.1109\/ICIP.2015.7351345"},{"key":"e_1_3_4_156_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"e_1_3_4_157_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"e_1_3_4_158_1","doi-asserted-by":"crossref","unstructured":"Hu W Xu Y Li Y et\u00a0al. BLIVA: a simple multimodal LLM for better handling of text-rich visual questions. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2024. p. 2256\u20132264.","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"e_1_3_4_159_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00523-0"},{"key":"e_1_3_4_160_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3086003"},{"key":"e_1_3_4_161_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.11.101"},{"key":"e_1_3_4_162_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00627-3"},{"key":"e_1_3_4_163_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-017-0412-0"},{"key":"e_1_3_4_164_1","first-page":"90","article-title":"Asimo and humanoid robot research at Honda","volume":"55","author":"Shigemi S","year":"2018","unstructured":"Shigemi S, Goswami A, Vadakkepat P. Asimo and humanoid robot research at Honda. Human Robot: Ref. 2018;55:90.","journal-title":"Human Robot: Ref"},{"key":"e_1_3_4_165_1","doi-asserted-by":"crossref","unstructured":"Hei X Yu C Zhang H et\u00a0al. A bilingual social robot with sign language and natural language. In: Companion of the 2024 ACM\/IEEE International Conference on Human\u2013Robot Interaction; New York NY USA. Association for Computing Machinery; 2024. p. 526\u2013529; HRI '24.","DOI":"10.1145\/3610978.3640549"},{"key":"e_1_3_4_166_1","unstructured":"Moryossef A Goldberg Y. Sign language processing; 2021. Available from: https:\/\/sign-language-processing.github.io\/"},{"key":"e_1_3_4_167_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3061608"},{"key":"e_1_3_4_168_1","unstructured":"Sabyrov A Mukushev M Imashev A et\u00a0al. Towards real-time sign language interpreting robot: evaluation of non-manual components on recognition accuracy. In: CVPR Workshops; 2019."},{"key":"e_1_3_4_169_1","volume-title":"Deaf in America: voices from a culture","author":"Padden CA","year":"1988","unstructured":"Padden CA, Humphries TL. Deaf in America: voices from a culture. Cambridge (MA):\u00a0Harvard University Press; 1988."}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2024.2442721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T09:56:07Z","timestamp":1735811767000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2024.2442721"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":168,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["10.1080\/01691864.2024.2442721"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2024.2442721","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-06-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-14","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}