{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:46:09Z","timestamp":1759538769484,"version":"build-2065373602"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SNSF Project \u201cSMILE II\u201d","award":["CRSII5 193686"],"award-info":[{"award-number":["CRSII5 193686"]}]},{"name":"European Union\u2019s Horizon2020 Programme","award":["101016982"],"award-info":[{"award-number":["101016982"]}]},{"name":"Innosuisse IICT Flagship","award":["PFFS-21-47"],"award-info":[{"award-number":["PFFS-21-47"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tbiom.2025.3577085","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T13:39:16Z","timestamp":1749130756000},"page":"890-901","source":"Crossref","is-referenced-by-count":0,"title":["Handling the Details: A Two-Stage Diffusion Approach to Improving Hands in Human Image Generation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9075-5718","authenticated-orcid":false,"given":"Anton","family":"Pelykh","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-0634","authenticated-orcid":false,"given":"Ozge","family":"Mercanoglu Sincan","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3285-8020","authenticated-orcid":false,"given":"Richard","family":"Bowden","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Stable-pose: Leveraging transformers for pose-guided text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2406.02485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"ref8","first-page":"1","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Shen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref11","first-page":"1","article-title":"A dataset of relighted 3D interacting hands","volume-title":"Proc. 37th NeurIPS","author":"Moon"},{"key":"ref12","first-page":"813","article-title":"FreiHAND: A dataset for markerless capture of hand pose and shape from single RGB images","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Zimmermann"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00239"},{"key":"ref14","article-title":"Concept sliders: LoRA adaptors for precise control in diffusion models","author":"Gandikota","year":"2023","journal-title":"arXiv:2311.12092"},{"key":"ref15","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582008"},{"key":"ref17","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref18","first-page":"1","article-title":"YouTube-ASL: A large-scale, open-domain American sign language-English parallel corpus","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Uthus"},{"key":"ref19","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref21","article-title":"Denoising diffusion implicit models","author":"Song","year":"2022","journal-title":"arXiv:2010.02502"},{"key":"ref22","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref23","first-page":"1","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref24","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref25","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"140","key":"ref27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref29","first-page":"405","article-title":"Pose guided person image generation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"ref34","article-title":"Everybody sign now: Translating spoken language to photo realistic sign language video","author":"Saunders","year":"2020","journal-title":"arXiv:2011.09846"},{"key":"ref35","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref38","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2023","journal-title":"arXiv:1606.08415"},{"key":"ref39","first-page":"2980","article-title":"Mask R-CNN","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"He"},{"key":"ref40","first-page":"1","article-title":"Learning multiple tasks with multilinear relationship networks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref41","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Kendall"},{"key":"ref42","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref43","article-title":"Block-wise LoRA: Revisiting fine-grained LoRA for effective Personalization and Stylization in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv:2403.07500"},{"key":"ref44","first-page":"6430","article-title":"MACE: Mass concept erasure in diffusion models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Lu"},{"key":"ref45","first-page":"1931","article-title":"Multi-concept Customization of text-to-image diffusion","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Kumari"},{"key":"ref46","first-page":"1","article-title":"CtrLoRA: An extensible and efficient framework for controllable image generation","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref47","first-page":"18187","article-title":"Blended diffusion for text-driven editing of natural images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Avrahami"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref49","article-title":"HaGRID\u2014HAnd gesture recognition image datset","author":"Kapitanov","year":"2022","journal-title":"arXiv:2206.08219"},{"key":"ref50","article-title":"MediaPipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv:1906.08172"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref52","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref55","first-page":"1","article-title":"Demystifying MMD GANs","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Binkowski"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref57","article-title":"Compound Frechet inception distance for quality assessment of GAN created images","author":"Nunn","year":"2021","journal-title":"arXiv:2106.08575"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_9"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/11180155\/11025996.pdf?arnumber=11025996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:27:21Z","timestamp":1759512441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11025996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2025.3577085","relation":{},"ISSN":["2637-6407"],"issn-type":[{"type":"electronic","value":"2637-6407"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}