{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:12:31Z","timestamp":1780600351799,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010942"],"award-info":[{"award-number":["2022A1515010942"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3313248","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:35:37Z","timestamp":1694194537000},"page":"99030-99045","source":"Crossref","is-referenced-by-count":5,"title":["GrainedCLIP and DiffusionGrainedCLIP: Text-Guided Advanced Models for Fine-Grained Attribute Face Image Processing"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2383-8397","authenticated-orcid":false,"given":"Jincheng","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, South China Normal University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5470-1799","authenticated-orcid":false,"given":"Liwei","family":"Mu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, South China Normal University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2019","journal-title":"Proc Int Conf Learn Reps (ICLR)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref12","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref56","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref53","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"saharia","year":"2022","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref52","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","author":"dhariwal","year":"2021","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref11","article-title":"Generating high fidelity images with subscale pixel networks and multidimensional upscaling","author":"menick","year":"2019","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref55","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"ramesh","year":"2022","journal-title":"arXiv 2204 06125"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref51","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"2022","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref50","first-page":"1942","article-title":"TeCM-CLIP: Text-based controllable multi-attribute face image manipulation","author":"lou","year":"2022","journal-title":"Proc Asian Conf Comput Vis (ACCV)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref45","first-page":"42","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","author":"nam","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"One model to edit them all: Free-form text-driven image manipulation with semantic modulations","author":"zhu","year":"2022","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref41","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref44","first-page":"2063","article-title":"Controllable text-to-image generation","author":"li","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","author":"dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref4","article-title":"Democratizing contrastive language-image pre-training: A CLIP benchmark of data, model, and supervision","author":"cui","year":"2022","journal-title":"arXiv 2203 05796"},{"key":"ref3","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"yao","year":"2022","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref6","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"ref35","article-title":"CLIP-adapter: Better vision-language models with feature adapters","author":"gao","year":"2021","journal-title":"arXiv 2110 04544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref32","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref2","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"li","year":"2022","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref22","article-title":"Neural photo editing with introspective adversarial networks","author":"brock","year":"2017","journal-title":"Proc Int Conf Learn Reps (ICLR)"},{"key":"ref66","first-page":"853","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"hodosh","year":"2015","journal-title":"Proc Int Conf Artif Intell (ICAI)"},{"key":"ref21","article-title":"Semantic photo manipulation with a generative image prior","author":"bau","year":"2020","journal-title":"arXiv 2005 07727"},{"key":"ref65","article-title":"Mixed precision training","author":"micikevicius","year":"2017","journal-title":"arXiv 1710 03740"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref27","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref29","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","article-title":"Convolutional networks for images, speech, and time-series","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref62","article-title":"Denoising diffusion implicit models","author":"song","year":"2021","journal-title":"Proc Int Conf Learn Repsent (ICLR)"},{"key":"ref61","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10244046.pdf?arnumber=10244046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:22:24Z","timestamp":1696879344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10244046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3313248","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}