{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T12:55:54Z","timestamp":1783688154185,"version":"3.55.0"},"reference-count":213,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Pandemic Sciences Institute at the University of Oxford"},{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Oxford Biomedical Research Centre"},{"name":"NIHR Research Professorship"},{"name":"Royal Academy of Engineering Research Chair"},{"name":"Wellcome Trust funded VITAL project","award":["204904\/Z\/16\/Z"],"award-info":[{"award-number":["204904\/Z\/16\/Z"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/W031744\/1"],"award-info":[{"award-number":["EP\/W031744\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Hong Kong Centre for Cerebro-cardiovascular Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3522305","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:17:15Z","timestamp":1735327035000},"page":"2212-2231","source":"Crossref","is-referenced-by-count":43,"title":["RenAIssance: A Survey Into AI Text-to-Image Generation in the Era of Large Model"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6483-6101","authenticated-orcid":false,"given":"Fengxiang","family":"Bie","sequence":"first","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-7231","authenticated-orcid":false,"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongzhu","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8495-1876","authenticated-orcid":false,"given":"Adam","family":"Ghanem","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhewei","family":"Yao","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxia","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connor","family":"Holmes","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pareesa","family":"Golnari","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-8555","authenticated-orcid":false,"given":"David A.","family":"Clifton","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiong","family":"He","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaiwen Leon","family":"Song","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2024.100541"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00774"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref15","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref18","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref21","first-page":"5485","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":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"issue":"8","key":"ref23","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref24","article-title":"Stable diffusion online"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref26","article-title":"NovelAI"},{"key":"ref27","article-title":"Midjourney"},{"key":"ref28","article-title":"Generating images from captions with attention","author":"Mansimov","year":"2015"},{"key":"ref29","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref30","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref31","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"issue":"7553","key":"ref32","first-page":"436","article-title":"Deep learning","volume":"521","year":"2015","journal-title":"Nature Cell Biol."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref36","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref39","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref40","first-page":"16 784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Nichol"},{"key":"ref41","article-title":"The multivariate Gaussian distribution","volume":"229","author":"Do","year":"2008","journal-title":"Sect. Notes Lecture Mach. Learn."},{"key":"ref42","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref43","first-page":"16 890","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref44","article-title":"LAFITE: Towards language-free training for text-to-image generation","author":"Zhou","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.07.019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-3590-9_52"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108098"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.069"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/9781118818565.ch2"},{"key":"ref53","article-title":"An introduction to convolutional neural networks","author":"O\u2019Shea","year":"2015"},{"issue":"23","key":"ref54","article-title":"Introduction to convolutional neural networks","volume":"5","author":"Wu","year":"2017"},{"key":"ref55","article-title":"Segdiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013272"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3361862"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6955"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref60","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00061"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3434373"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"ref66","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref68","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref70","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref72","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref73","first-page":"469","article-title":"Coupled generative adversarial networks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3124155"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00617"},{"key":"ref76","article-title":"Non-autoregressive neural machine translation","author":"Gu","year":"2017"},{"key":"ref77","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref78","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref79","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref80","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref81","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref82","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref83","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref84","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref85","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref86","article-title":"Using deepSpeed and megatron to train megatron-turing NLG 530b, a large-scale generative language model","author":"Smith","year":"2022"},{"key":"ref87","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref88","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baranchuk"},{"key":"ref89","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","volume-title":"Proc. Int. Conf. Med. Imag. Deep Learn.","author":"Wolleb"},{"key":"ref90","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref92","first-page":"3609","article-title":"EGSDE: Unpaired image-to-image translation via energy-guided stochastic differential equations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref93","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref94","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref95","article-title":"Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref96","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref98","first-page":"574","article-title":"Sliced score matching: A scalable approach to density and score estimation","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Song","year":"2020"},{"key":"ref99","first-page":"19175","article-title":"Efficient learning of generative models via finite-difference score matching","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pang"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref101","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan"},{"key":"ref102","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref103","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref104","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref106","article-title":"Ernie 3.0 titan: Exploring larger-scale knowledge enhanced pre-training for language understanding and generation","author":"Wang","year":"2021"},{"key":"ref107","article-title":"DeBERTa: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"key":"ref108","article-title":"Multitask prompted training enables zero-shot task generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sanh"},{"key":"ref109","article-title":"GLM-130B: An open bilingual pre-trained model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref110","article-title":"Alexatm 20B: Few-shot learning using a large-scale multilingual seq2seq model","author":"Soltan","year":"2022"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw55747.2022.00171"},{"key":"ref115","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref116","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref117","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Scao","year":"2022"},{"key":"ref118","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022"},{"key":"ref119","first-page":"95","article-title":"GPT-NeoX-20B: An open-source autoregressive language model","volume-title":"Proc. BigScience Episode# 5\u2013Workshop Challenges Perspectives Creating Large Lang. Models","author":"Black"},{"key":"ref120","article-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023"},{"key":"ref121","article-title":"Scaling language models: Methods, analysis & insights from training Gopher","author":"Rae","year":"2021"},{"key":"ref122","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref123","article-title":"WebGPT: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021"},{"key":"ref124","first-page":"18 332","article-title":"DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rajbhandari"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref126","article-title":"Colossal-ai: A unified deep learning system for large-scale parallel training","author":"Li","year":"2021"},{"key":"ref127","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref128","first-page":"4913","article-title":"Naturalprover: Grounded mathematical proof generation with language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Welleck"},{"key":"ref129","article-title":"Localvit: Bringing locality to vision transformers","author":"Li","year":"2021"},{"key":"ref130","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Riquelme"},{"key":"ref131","first-page":"32 897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bao"},{"key":"ref132","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref136","first-page":"26 183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref140","article-title":"BEIT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref141","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020"},{"key":"ref142","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_63"},{"key":"ref144","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref145","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref146","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref147","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref149","article-title":"InterBERT: Vision-and-language interaction for multi-modal pretraining","author":"Lin","year":"2020"},{"key":"ref150","first-page":"22 680","article-title":"Vlmixer: Unpaired vision-language pre-training via cross-modal cutmix","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref153","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Reed"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00028"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018312"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_35"},{"issue":"5","key":"ref160","article-title":"Conditional generative adversarial nets for convolutional face generation","volume":"2014","author":"Gauthier","year":"2014","journal-title":"Class Project Stanford CS231N: Convolutional Neural Netw. Vis. Recognit. Winter Semester"},{"key":"ref161","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref166","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Odena"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2394\/fig-2"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.5220\/0010503701660174"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref171","article-title":"Fusedream: Training-free text-to-image generation with improved clip+ GAN space optimization","author":"Liu","year":"2021"},{"key":"ref172","first-page":"30 105","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sauer"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref174","first-page":"25 278","article-title":"Laion-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref175","article-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref176","article-title":"Discrete variational autoencoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rolfe"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref178","article-title":"Dall\u00b7 E mini","author":"Dayma","year":"2021"},{"key":"ref179","first-page":"19 822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref180","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref181","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"issue":"1","key":"ref182","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref184","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref187","article-title":"A picture is worth a thousand words: Principled recaptioning improves image generation","author":"Segalis","year":"2023"},{"issue":"3","key":"ref188","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref189","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref190","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref192","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref194","article-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref195","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref198","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref201","article-title":"Text-to-image generation via implicit visual guidance and hypernetwork","author":"Yuan","year":"2022"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref203","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022"},{"key":"ref204","article-title":"Upainting: Unified text-to-image diffusion generation with cross-modal guidance","author":"Li","year":"2022"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00283"},{"key":"ref206","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref208","article-title":"Common crawl"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"ref213","article-title":"An improved evaluation framework for generative adversarial networks","author":"Liu","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10873290\/10817489-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10817489.pdf?arnumber=10817489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:33Z","timestamp":1738867053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":213,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3522305","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":[[2025,3]]}}}