{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:49Z","timestamp":1777655809807,"version":"3.51.4"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099440","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-11","source":"Crossref","is-referenced-by-count":7,"title":["SignDiff: Diffusion Model for American Sign Language Production"],"prefix":"10.1109","author":[{"given":"Sen","family":"Fang","sequence":"first","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Sui","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuedong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Victoria University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00194"},{"key":"ref3","article-title":"Using Dynamic Time Warping to Find Patterns in Time Series","volume-title":"AAA1-94 Workshop on Knowledge Discovery in Databases","author":"Berndt"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.00770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75773-3_10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/638249.638287"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960700"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.175"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00520"},{"key":"ref15","article-title":"Sign Language Interpreting in the Workplace","author":"Dickinson","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"ref17","volume-title":"Signx: The foundation model for sign recognition","author":"Fang","year":"2025"},{"key":"ref18","article-title":"Signllm: Sign languages production large language models","author":"Fang","year":"2024"},{"key":"ref19","article-title":"RWTH-PHOENIX-Weather: A Large Vocabulary Sign Language Recognition and Translation Corpus","volume-title":"Proceedings of the International Conference on Language Resources and Evaluation (LREC)","author":"Forster"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1997.625742"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref24","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)","author":"Heusel"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475463"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/C.18.96"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2005.06.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app9132683"},{"key":"ref30","article-title":"Quantitative Survey of the State of the Art in Sign Language Recognition","author":"Koller","year":"2020","journal-title":"arXiv preprint arXiv:2008.09918"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_18"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351020"},{"key":"ref35","article-title":"Pose Guided Person Image Generation","author":"Ma","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3490035.3490286"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-015-0407-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref41","article-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","author":"Radford","year":"2015","journal-title":"arXiv preprint arXiv:1511.06434"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref44","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.63"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666984"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01457-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"ref50","article-title":"Skeletal Graph SelfAttention: Embedding a Skeleton Inductive Bias into Sign Language Production","author":"Saunders","year":"2021","journal-title":"arXiv preprint arXiv:2112.05277"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1531930.1531935"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref54","volume-title":"Sign Language Structure. Annual Review of Anthropology","author":"Stokoe","year":"1980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01281-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01281-2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240704"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref62","article-title":"Can Everybody Sign Now? Exploring Sign Language Video Generation from 2D Poses","volume-title":"E C C V Sign Language Recognition, Translation and Production Workshop","author":"Ventura"},{"key":"ref63","article-title":"Generating Videos with Scene Dynamics","author":"Vondrick","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref64","article-title":"Few-shot Video-to-Video Synthesis","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref65","article-title":"Video-to-Video Synthesis","author":"Wang","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011290"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413555"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093516"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00355"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747380"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00153"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Tampa\/Clearwater, FL, USA","start":{"date-parts":[[2025,5,26]]},"end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099440.pdf?arnumber=11099440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:00:56Z","timestamp":1754542856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099440","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}