{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:26:52Z","timestamp":1771064812319,"version":"3.50.1"},"reference-count":85,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002347","name":"German Ministry of Education and Research","doi-asserted-by":"publisher","award":["01IW20002"],"award-info":[{"award-number":["01IW20002"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10582038","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["SynthSL: Expressive Humans for Sign Language Image Synthesis"],"prefix":"10.1109","author":[{"given":"Jilliam M. D\u00edaz","family":"Barros","sequence":"first","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"RPTU Kaiserslautern"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jameel","family":"Malik","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdalla","family":"Arafa","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"A comprehensive study on sign language recognition methods","volume":"1","author":"Adaloglou","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"27","article-title":"Facial expression phoenix (feph): An annotated sequenced dataset for facial and emotion-specified expressions in sign language","volume":"20","author":"Alaghband","year":"2020","journal-title":"Image"},{"key":"ref3","article-title":"BOBSL: BBC-Oxford British Sign Language Dataset","author":"Albanie","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073207"},{"key":"ref5","volume-title":"Autodesk, INC. Maya"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref8","article-title":"Smpler-x: Scaling up expressive human pose and shape estimation","author":"Cai","year":"2023","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.143"},{"key":"ref12","volume-title":"The devisign large vocabulary of chinese sign language database and baseline evaluations. Technical Report VIPL-TR-14-SLR-001","author":"Chai","year":"2014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00194"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00625"},{"key":"ref16","article-title":"Blender - a 3D modelling and rendering package","volume-title":"Blender Foundation, Stichting Blender Foundation, Amsterdam","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/638249.638287"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref20","first-page":"7","article-title":"Modeling image variability in appearance-based gesture recognition","volume-title":"ECCV Workshop on Statistical Methods in Multi-image and Video Processing","author":"Dreuw","year":"2006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00276"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3352587"},{"key":"ref23","first-page":"1","article-title":"Domain stylization: A strong, simple baseline for synthetic to real image domain adaptation","volume":"1","author":"Dundar","year":"2018","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"4221","article-title":"Smile swiss german sign language dataset","volume-title":"Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC18)","author":"Ebling","year":"2018"},{"key":"ref25","article-title":"Signdiff: Learning diffusion models for american sign language production","author":"Fang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"3785","article-title":"RWTH-PHOENIX-Weather: A large vocabulary sign language recognition and translation corpus","volume-title":"Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC12)","author":"Forster","year":"2012"},{"key":"ref27","first-page":"1911","article-title":"Extensions of the sign language recognition and translation corpus RWTH-PHOENIX-Weather","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC14)","author":"Forster","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.75"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2030365.2030371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-015-0411-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3233\/TAD-2006-18408"},{"key":"ref32","first-page":"27","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref33","first-page":"30","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani","year":"2017","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_43"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2005.06.004"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref42","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/app9132683"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.412"},{"key":"ref45","volume-title":"Sign language: The study of deaf people and their language","author":"Kyle","year":"1988"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref48","article-title":"Geometric GAN","author":"Lim","year":"2017","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01192-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref51","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","volume-title":"CVPR","author":"Liu","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref53","article-title":"Mediapipe: A framework for perceiving and processing reality","author":"Lugaresi","year":"2019","journal-title":"CVPR-W"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3122874"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-015-0407-2"},{"key":"ref57","first-page":"1","article-title":"Bosphorussign22k sign language recognition dataset","volume":"1","author":"Ozdemir","year":"2020","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref60","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01279-w"},{"key":"ref62","first-page":"1","article-title":"Learning human optical flow","volume-title":"BMVC","author":"Ranjan","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_40"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref66","first-page":"1","article-title":"Adversarial training for multi-channel sign language production","volume-title":"The 31st British Machine Vision Virtual Conference","author":"Saunders","year":"2020"},{"key":"ref67","first-page":"1","article-title":"Everybody sign now: Translating spoken language to photo realistic sign language video","volume":"1","author":"Saunders","year":"2020","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"ref70","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref71","first-page":"1","article-title":"Sign language production using neural machine translation and generative adversarial networks","volume-title":"BMVC","author":"Stoll","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01281-2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_21"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref75","first-page":"1","article-title":"MS-ASL: A large-scale data set and benchmark for understanding american sign language","volume-title":"BMVC","author":"Vaezi Joze","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01467-7"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref78","first-page":"1","article-title":"Can everybody sign now? exploring sign language video generation from 2d poses","volume-title":"Sign Language Recognition, Translation and Production (SLRTP) Workshop - Extended Abstracts","author":"Ventura","year":"2020"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref80","volume-title":"Teaching and talking with deaf children","volume":"10","author":"Wood","year":"1986"},{"key":"ref81","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref82","article-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093516"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Istanbul, Turkiye","start":{"date-parts":[[2024,5,27]]},"end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10582038.pdf?arnumber=10582038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:05:28Z","timestamp":1721279128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10582038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10582038","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}