{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T01:56:48Z","timestamp":1769738208699,"version":"3.49.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFC3310400"],"award-info":[{"award-number":["2022YFC3310400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2054"],"award-info":[{"award-number":["U23B2054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076240"],"award-info":[{"award-number":["62076240"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276263"],"award-info":[{"award-number":["62276263"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306309"],"award-info":[{"award-number":["62306309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["4222054"],"award-info":[{"award-number":["4222054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2023.3345866","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T14:35:03Z","timestamp":1704292503000},"page":"9438-9453","source":"Crossref","is-referenced-by-count":17,"title":["AnyFace++: A Unified Framework for Free-Style Text-to-Face Synthesis and Manipulation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1149-7185","authenticated-orcid":false,"given":"Jianxin","family":"Sun","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Qiyao","family":"Deng","sequence":"additional","affiliation":[{"name":"People’s Public Security University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7905-2860","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9506-7643","authenticated-orcid":false,"given":"Muyi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8929-4866","authenticated-orcid":false,"given":"Yunfan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical, and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-9935","authenticated-orcid":false,"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref4","article-title":"Conditional image generation and manipulation for user-specified content","author":"Stap","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108581"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/70"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00480"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref11","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093463"},{"key":"ref17","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref21","article-title":"DF-GAN: Deep fusion generative adversarial networks for text-to-image synthesis","author":"Tao","year":"2020"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01813"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086590"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2957930"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref31","article-title":"CausalVLR: A toolbox and benchmark for visual-linguistic causal reasoning","author":"Liu","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00666"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159811"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref36","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref37","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref39","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref40","first-page":"10336","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Huang"},{"key":"ref41","first-page":"204","article-title":"Meter: Unsupervised text embeddings evaluation metrics","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Chen"},{"key":"ref42","first-page":"216","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Luo"},{"key":"ref43","first-page":"228","article-title":"BLIP: Better language models by pretraining intermediate representations with distribution smoothing","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Liu"},{"key":"ref44","first-page":"19730","article-title":"BLIP-2: Better language models by pretraining intermediate representations with bi-directional transformers","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Liu"},{"key":"ref45","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3164187"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref52","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref53","article-title":"FTGAN: A fully-trained generative adversarial networks for text to face generation","author":"Chen","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"ref55","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref56","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref57","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref58","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref59","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref60","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref65","article-title":"KNN-Diffusion: Image generation via large-scale retrieval","author":"Sheynin","year":"2022"},{"key":"ref66","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","author":"Rombach","year":"2022"},{"key":"ref67","article-title":"Retrieval-augmented diffusion models","author":"Blattmann","year":"2022"},{"key":"ref68","article-title":"Memory networks","author":"Weston","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01154"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00764"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3122930"},{"key":"ref75","first-page":"1","article-title":"Showface: Coordinated face inpainting with memory-disentangled refinement networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Wu"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475236"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17280"},{"key":"ref79","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref84","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2631888"},{"key":"ref88","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/11192800\/10380501.pdf?arnumber=10380501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:39Z","timestamp":1759772199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10380501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":88,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3345866","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}