{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T01:04:28Z","timestamp":1770426268991,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,16]]},"DOI":"10.1145\/3742886.3756732","type":"proceedings-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:55:41Z","timestamp":1759244141000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Text-to-Sign Language Production via Intermediate Skeletal Representations using Transformers and Neural Rendering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9904-8463","authenticated-orcid":false,"given":"Chrysa","family":"Pratikaki","sequence":"first","affiliation":[{"name":"School of ECE, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2301-0602","authenticated-orcid":false,"given":"Stavroula-Evita","family":"Fotinea","sequence":"additional","affiliation":[{"name":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4253-5612","authenticated-orcid":false,"given":"Eleni","family":"Efthimiou","sequence":"additional","affiliation":[{"name":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2042-245X","authenticated-orcid":false,"given":"Panagiotis Paraskevas","family":"Filntisis","sequence":"additional","affiliation":[{"name":"Athena Research Center, Robotics Institute, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6015-3357","authenticated-orcid":false,"given":"Anastasios","family":"Roussos","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Foundation for Research & Technology - Hellas (FORTH), Heraklion, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0534-2707","authenticated-orcid":false,"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[{"name":"Athena RC, Robotics Institute, Athens, Greece; School of ECE, NTUA, Athens, Greece and HERON - Center of Excellence in Robotics, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"1985","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Baltatzis Vasileios","year":"2024","unstructured":"Vasileios Baltatzis, Rolandos\u00a0Alexandros Potamias, Evangelos Ververas, Guanxiong Sun, Jiankang Deng, and Stefanos Zafeiriou. 2024. Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1985\u20131995."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622141"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Necati\u00a0Cihan Camg\u00f6z Oscar Koller Simon Hadfield and Richard Bowden. 2020. Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation.","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Michail\u00a0Christos Doukas Mohammad\u00a0Rami Koujan Viktoriia Sharmanska Anastasios Roussos and Stefanos Zafeiriou. 2021. Head2Head++: Deep Facial Attributes Re-Targeting. IEEE Transactions on Biometrics Behavior and Identity Science 3 1 (Jan. 2021) 31\u201343. 10.1109\/tbiom.2021.3049576","DOI":"10.1109\/tbiom.2021.3049576"},{"key":"e_1_3_3_2_9_2","unstructured":"Yao Feng Haiwen Feng Michael\u00a0J. Black and Timo Bolkart. 2020. Learning an Animatable Detailed 3D Face Model from In-The-Wild Images. CoRR abs\/2012.04012 (2020). arxiv:https:\/\/arXiv.org\/abs\/2012.04012\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2012.04012"},{"key":"e_1_3_3_2_10_2","unstructured":"Google. [n. d.]. MediaPipe Holistic Solution Documentation. https:\/\/github.com\/google\/mediapipe\/blob\/master\/docs\/solutions\/holistic.md."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00048"},{"key":"e_1_3_3_2_12_2","unstructured":"Xudong Mao Qing Li Haoran Xie Raymond Y.\u00a0K. Lau Zhen Wang and Stephen\u00a0Paul Smolley. 2017. Least Squares Generative Adversarial Networks. arxiv:https:\/\/arXiv.org\/abs\/1611.04076\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1611.04076"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Georgios Pavlakos Vasileios Choutas Nima Ghorbani Timo Bolkart Ahmed A.\u00a0A. Osman Dimitrios Tzionas and Michael\u00a0J. Black. 2019. Expressive Body Capture: 3D Hands Face and Body from a Single Image. arxiv:https:\/\/arXiv.org\/abs\/1904.05866\u00a0[cs.CV]","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_14_2","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Retsinas George","year":"2024","unstructured":"George Retsinas, Panagiotis\u00a0P. Filntisis, Radek Danecek, Victoria\u00a0F. Abrevaya, Anastasios Roussos, Timo Bolkart, and Petros Maragos. 2024. 3D Facial Expressions through Analysis-by-Neural-Synthesis. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_15_2","unstructured":"Anastasios Roussos Stavros Theodorakis Vassilis Pitsikalis and Petros Maragos. 2013. Dynamic Affine-Invariant Shape-Appearance Handshape Features and Classification in Sign Language Videos. Journal of Machine Learning Research 14 51 (2013) 1627\u20131663. http:\/\/jmlr.org\/papers\/v14\/roussos13a.html"},{"key":"e_1_3_3_2_16_2","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2020. Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video. arxiv:https:\/\/arXiv.org\/abs\/2011.09846\u00a0[cs.CV]"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2020. Progressive Transformers for End-to-End Sign Language Production. (2020). http:\/\/arxiv.org\/abs\/2004.14874","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666984"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Ben Saunders Necati\u00a0Cihan Camgoz and Richard Bowden. 2022. Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production.","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Stephanie Stoll Necati\u00a0Cihan Camgoz Simon Hadfield and Richard Bowden. 2020. Text2Sign: Towards Sign Language Production Using Neural Machine Translation and Generative Adversarial Networks. International Journal of Computer Vision 128 4 (01 Apr 2020) 891\u2013908. 10.1007\/s11263-019-01281-2","DOI":"10.1007\/s11263-019-01281-2"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Stephanie Stoll Armin Mustafa and Jean\u00a0Yves Guillemaut. 2022. There and Back Again: 3D Sign Language Generation from Text Using Back-Translation. Proceedings - 2022 International Conference on 3D Vision 3DV 2022 187\u2013196. 10.1109\/3DV57658.2022.00031","DOI":"10.1109\/3DV57658.2022.00031"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Stavros Theodorakis Vassilis Pitsikalis and Petros Maragos. 2014. Dynamic\u2013static unsupervised sequentiality statistical subunits and lexicon for sign language recognition. Image and Vision Computing 32 8 (2014) 533\u2013549. 10.1016\/j.imavis.2014.04.012","DOI":"10.1016\/j.imavis.2014.04.012"},{"key":"e_1_3_3_2_23_2","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Tze Christina\u00a0O.","year":"2023","unstructured":"Christina\u00a0O. Tze, Panagiotis\u00a0P. Filntisis, Athanasia-Lida Dimou, Anastasios Roussos, and Petros Maragos. 2023. Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)."},{"key":"e_1_3_3_2_24_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Andreas Voskou Konstantinos\u00a0P. Panousis Harris Partaourides Kyriakos Tolias and Sotirios Chatzis. 2023. A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset. arxiv:https:\/\/arXiv.org\/abs\/2310.04753\u00a0[cs.CL]","DOI":"10.1109\/ICCVW60793.2023.00211"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"}],"event":{"name":"IVA Adjunct '25: ACM International Conference on Intelligent Virtual Agents","location":"Berlin Germany","acronym":"IVA Adjunct '25","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Adjunct Proceedings of the 25th ACM International Conference on Intelligent Virtual Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3742886.3756732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:57:14Z","timestamp":1759244234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742886.3756732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":25,"alternative-id":["10.1145\/3742886.3756732","10.1145\/3742886"],"URL":"https:\/\/doi.org\/10.1145\/3742886.3756732","relation":{},"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"2025-09-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}