{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T21:16:35Z","timestamp":1781990195124,"version":"3.54.5"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00784","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8372-8383","source":"Crossref","is-referenced-by-count":1,"title":["MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild"],"prefix":"10.1109","author":[{"given":"Muhammad Usama","family":"Saleem","sequence":"first","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ekkasit","family":"Pinyoanuntapong","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayur Jagdishbhai","family":"Patel","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Xue","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Helmy","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srijan","family":"Das","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte,Charlotte,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Kaggle asl alphabet","year":"2021"},{"key":"ref2","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Alexey","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00869"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01103"},{"key":"ref9","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00839"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1327"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"ref17","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00623"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.12.001"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2159616.2159630"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6498-7_16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00080"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01238"},{"key":"ref35","article-title":"Single image 3d hand reconstruction with mesh convolutions","author":"Kulon","year":"2019","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00504"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00068"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355652"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2556964"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.145"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_13"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.305"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702136"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298941"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130853"},{"key":"ref60","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref61","first-page":"5785","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kumar","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417852"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00425"},{"key":"ref64","first-page":"4524","article-title":"Hierarchical quantized autoencoders","volume":"33","author":"Williams","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01122"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01635"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00277"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"ref69","article-title":"Uv-based 3d hand-object reconstruction with grasp optimization","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"ref71","article-title":"Light-weight multi-person total capture using sparse multi-view cameras","author":"Zhang","year":"2021","journal-title":"ICCV"},{"key":"ref72","first-page":"27196","article-title":"Ufcbert: Unifying multi-modal controls for conditional image synthesis","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","article-title":"Combining marker-based mocap and rgb-d camera for acquiring high-fidelity hand motion data","author":"Zhao","year":"2012","journal-title":"SIGGRAPH"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00136"},{"key":"ref75","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"ArXiv. abs\/2010.04159"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443471.pdf?arnumber=11443471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:12Z","timestamp":1777612452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00784","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}