{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:31Z","timestamp":1776931171395,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"name":"JST, Moonshot Research and Development","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750765","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"173-180","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SignFlow: End-to-End Sign Language Generation for One-to-Many Modeling using Conditional Flow Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7105-9076","authenticated-orcid":false,"given":"Nabeela","family":"Khan","sequence":"first","affiliation":[{"name":"Systems and Control Engineering\/Engineering\/Nakadai Lab, Institute of Science Tokyo, Meguro, Tokyo, Japan and Guardian Robot Project, RIKEN, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8518-2939","authenticated-orcid":false,"given":"Bowen","family":"Wu","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, RIKEN, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9645-1131","authenticated-orcid":false,"given":"Sihan","family":"Tan","sequence":"additional","affiliation":[{"name":"Systems and Control Engineering\/Engineering\/Nakadai Lab, Institute of Science Tokyo, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8130-1048","authenticated-orcid":false,"given":"Carlos Toshinori","family":"Ishi","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, RIKEN, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6134-4558","authenticated-orcid":false,"given":"Kazuhiro","family":"Nakadai","sequence":"additional","affiliation":[{"name":"Systems and Control Engineering\/Engineering\/Nakadai Lab, Institute of Science Tokyo, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Triantafyllos Afouras Joon\u00a0Son Chung Andrew Senior Oriol Vinyals and Andrew Zisserman. 2018. Deep audio-visual speech recognition. IEEE transactions on pattern analysis and machine intelligence 44 12 (2018) 8717\u20138727.","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00194"},{"key":"e_1_3_3_2_4_2","volume-title":"The Hands Are The Head of The Mouth. The Mouth as Articulator in Sign Languages","author":"Braem P Boyes","year":"2001","unstructured":"P Boyes Braem and RL Sutton-Spence. 2001. The Hands Are The Head of The Mouth. The Mouth as Articulator in Sign Languages. Hamburg: Signum Press."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"e_1_3_3_2_6_2","unstructured":"Ricky\u00a0TQ Chen Yulia Rubanova Jesse Bettencourt and David\u00a0K Duvenaud. 2018. Neural ordinary differential equations. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Sheng Chen Qingshan Wang and Qi Wang. 2024. Semantic-driven diffusion for sign language production with gloss-pose latent spaces alignment. Computer Vision and Image Understanding 246 (2024) 104050.","DOI":"10.1016\/j.cviu.2024.104050"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.584"},{"key":"e_1_3_3_2_9_2","unstructured":"Sen Fang Chunyu Sui Yanghao Zhou Xuedong Zhang Hongbin Zhong Minyu Zhao Yapeng Tian and Chen Chen. 2023. SignDiff: Diffusion Models for American Sign Language Production. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.16082 (2023)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890373"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315166728"},{"key":"e_1_3_3_2_12_2","unstructured":"Jiayi He Xu Wang Ruobei Zhang Shengeng Tang Yaxiong Wang and Lechao Cheng. 2025. Text-Driven Diffusion Model for Sign Language Production. arXiv e-prints (2025) arXiv\u20132503."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/852"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475463"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.310"},{"key":"e_1_3_3_2_16_2","unstructured":"Biao Jiang Xin Chen Wen Liu Jingyi Yu Gang Yu and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2023) 20067\u201320079."},{"key":"e_1_3_3_2_17_2","first-page":"149","volume-title":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","author":"Khan Nabeela","year":"2025","unstructured":"Nabeela Khan, Bowen Wu, Carlos\u00a0Toshinori Ishi, and Kazuhiro Nakadai. 2025. MultiGAU: Real Time Sign Language Generation Using Multimodal Gated Attention. In International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. Springer, 149\u2013160."},{"key":"e_1_3_3_2_18_2","unstructured":"Yaron Lipman Ricky\u00a0TQ Chen Heli Ben-Hamu Maximilian Nickel and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02747 (2022)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Yinhan Liu Jiatao Gu Naman Goyal Xian Li Sergey Edunov Marjan Ghazvininejad Mike Lewis and Luke Zettlemoyer. 2020. Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics 8 (2020) 726\u2013742.","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.432"},{"key":"e_1_3_3_2_21_2","first-page":"22","volume-title":"Proceedings of the Second International Workshop on Automatic Translation for Signed and Spoken Languages","author":"Moryossef Amit","year":"2023","unstructured":"Amit Moryossef, Mathias M\u00fcller, Anne G\u00f6hring, Zifan Jiang, Yoav Goldberg, and Sarah Ebling. 2023. An open-source gloss-based baseline for spoken to signed language translation. In Proceedings of the Second International Workshop on Automatic Translation for Signed and Spoken Languages. 22\u201333."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Meinard M\u00fcller. 2007. Dynamic time warping. Information retrieval for music and motion (2007) 69\u201384.","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_24_2","first-page":"252","volume-title":"European Conference on Computer Vision","author":"Qi Fan","year":"2024","unstructured":"Fan Qi, Yu Duan, Huaiwen Zhang, and Changsheng Xu. 2024. SignGen: End-to-End Sign Language Video Generation with Latent Diffusion. In European Conference on Computer Vision. Springer, 252\u2013270."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2020. Adversarial training for multi-channel sign language production. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.12405 (2020).","DOI":"10.5244\/C.34.63"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2021. Continuous 3d multi-channel sign language production via progressive transformers and mixture density networks. International journal of computer vision 129 7 (2021) 2113\u20132135.","DOI":"10.1007\/s11263-021-01457-9"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"e_1_3_3_2_29_2","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2021. Skeletal graph self-attention: Embedding a skeleton inductive bias into sign language production. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.05277 (2021)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"e_1_3_3_2_31_2","volume-title":"Proceedings of the 29th British Machine Vision Conference (BMVC 2018)","author":"Stoll Stephanie","year":"2018","unstructured":"Stephanie Stoll, Necati\u00a0Cihan Camg\u00f6z, Simon Hadfield, and Richard Bowden. 2018. 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."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00031"},{"key":"e_1_3_3_2_33_2","first-page":"3255","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Tan Sihan","year":"2025","unstructured":"Sihan Tan, Taro Miyazaki, Nabeela Khan, and Kazuhiro Nakadai. 2025. Improvement in Sign Language Translation Using Text CTC Alignment. In Proceedings of the 31st International Conference on Computational Linguistics. 3255\u20133266."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32781"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Shengeng Tang Feng Xue Jingjing Wu Shuo Wang and Richang Hong. 2025. Gloss-driven conditional diffusion models for sign language production. ACM Transactions on Multimedia Computing Communications and Applications 21 4 (2025) 1\u201317.","DOI":"10.1145\/3663572"},{"key":"e_1_3_3_2_36_2","unstructured":"Sumeyye\u00a0Meryem Tasyurek Tugce Kiziltepe and Hacer\u00a0Yalim Keles. 2025. Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.06610 (2025)."},{"key":"e_1_3_3_2_37_2","unstructured":"Alexander Tong Kilian Fatras Nikolay Malkin Guillaume Huguet Yanlei Zhang Jarrid Rector-Brooks Guy Wolf and Yoshua Bengio. 2023. Improving and generalizing flow-based generative models with minibatch optimal transport. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.00482 (2023)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00300"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28441"},{"key":"e_1_3_3_2_40_2","unstructured":"Aoxiong Yin Haoyuan Li Kai Shen Siliang Tang and Yueting Zhuang. 2024. T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.07119 (2024)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.570"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"e_1_3_3_2_43_2","unstructured":"Ronglai Zuo Rolandos Alexandros\u00a0Potamias Evangelos Ververas Jiankang Deng and Stefanos Zafeiriou. 2024. Signs as Tokens: An Autoregressive Multilingual Sign Language Generator. arXiv e-prints (2024) arXiv\u20132411."},{"key":"e_1_3_3_2_44_2","first-page":"36","volume-title":"European Conference on Computer Vision","author":"Zuo Ronglai","year":"2024","unstructured":"Ronglai Zuo, Fangyun Wei, Zenggui Chen, Brian Mak, Jiaolong Yang, and Xin Tong. 2024. A simple baseline for spoken language to sign language translation with 3d avatars. In European Conference on Computer Vision. Springer, 36\u201354."}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:28:07Z","timestamp":1769466487000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750765"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":43,"alternative-id":["10.1145\/3716553.3750765","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750765","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}