{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:02Z","timestamp":1777865342419,"version":"3.51.4"},"reference-count":49,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225601,62476029,U23B2052"],"award-info":[{"award-number":["62225601,62476029,U23B2052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01583","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17046-17055","source":"Crossref","is-referenced-by-count":0,"title":["FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Cao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huayu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, China Telecom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, China Telecom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Ban","year":"2024","journal-title":"Fair resource allocation in multi-task learning"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","author":"Adetailer","year":"2024","journal-title":"https:\/\/github.com\/Bing-su\/adetailer.git"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref5","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"ref7","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3665869"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref16","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00664"},{"key":"ref20","author":"Lin","year":"2021","journal-title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref22","author":"Liu","year":"2023","journal-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref24","author":"Lugaresi","year":"2019","journal-title":"Mediapipe: A framework for building perception pipelines"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1999.752159"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/90.879343"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00484"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00239"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISAP.2005.1599245"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref31","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref32","author":"Puigcerver","year":"2023","journal-title":"From sparse to soft mixtures of experts"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref34","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"30105","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"International conference on machine learning","author":"Sauer","year":"2023"},{"key":"ref38","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref39","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8620-6_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref44","first-page":"5824","article-title":"Gradient surgery for multi-task learning","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref49","author":"Zhu","year":"2024","journal-title":"Mole: Enhancing human-centric text-to-image diffusion via mixture of low-rank experts"}],"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\/11444334.pdf?arnumber=11444334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:09Z","timestamp":1777529829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01583","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}