{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:27:21Z","timestamp":1773329241751,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","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":[{"DOI":"10.13039\/501100007162","name":"Guangdong S&T Programme","doi-asserted-by":"publisher","award":["2024B0101010003"],"award-info":[{"award-number":["2024B0101010003"]}],"id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["GJHZ20220913142600001"],"award-info":[{"award-number":["GJHZ20220913142600001"]}]},{"DOI":"10.13039\/100018919","name":"Major Key Project of PCL","doi-asserted-by":"publisher","award":["PCL2024A04"],"award-info":[{"award-number":["PCL2024A04"]}],"id":[{"id":"10.13039\/100018919","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3584554","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:46:14Z","timestamp":1752860774000},"page":"19010-19023","source":"Crossref","is-referenced-by-count":2,"title":["RealignDiff: Boosting Text-to-Image Diffusion Model With Coarse-to-Fine Semantic Realignment"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6787-5499","authenticated-orcid":false,"given":"Zutao","family":"Jiang","sequence":"first","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7344-2333","authenticated-orcid":false,"given":"Guian","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"given":"Guansong","family":"Lu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8941-2295","authenticated-orcid":false,"given":"Shengcai","family":"Liao","sequence":"additional","affiliation":[{"name":"College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_12"},{"key":"ref6","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xu"},{"key":"ref7","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Feng"},{"key":"ref8","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref9","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref11","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref13","article-title":"Semantic-guided image augmentation with pre-trained models","author":"Li","year":"2023","journal-title":"arXiv:2302.02070"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref19","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref22","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref25","article-title":"Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis","author":"Tao","year":"2020","journal-title":"arXiv:2008.05865"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.137"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref28","first-page":"30105","article-title":"StyleGAN-t: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Sauer"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3477467"},{"key":"ref31","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref32","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref33","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Esser"},{"key":"ref34","first-page":"16890","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref35","article-title":"M6-UFC: Unifying multi-modal controls for conditional image synthesis via non-autoregressive generative transformers","author":"Zhang","year":"2021","journal-title":"arXiv:2105.14211"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref37","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv:2301.00704"},{"key":"ref38","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref39","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref41","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"issue":"47","key":"ref42","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","first-page":"66923","article-title":"Optimizing prompts for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hao"},{"key":"ref44","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023","journal-title":"arXiv:2302.12192"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref46","article-title":"RAFT: Reward rAnked FineTuning for generative foundation model alignment","author":"Dong","year":"2023","journal-title":"arXiv:2304.06767"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref48","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref50","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref54","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref56","volume-title":"Deepfloyd If: A Powerful Text-to-Image Model That Can Smartly Integrate Text Into Images","author":"Shonenkov","year":"2023"},{"key":"ref57","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv:2305.13301"},{"key":"ref58","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref59","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref60","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref61","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref62","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref63","article-title":"What the DAAM: Interpreting stable diffusion using cross attention","author":"Tang","year":"2022","journal-title":"arXiv:2210.04885"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11084988.pdf?arnumber=11084988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:28Z","timestamp":1765219288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3584554","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}