{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:23:56Z","timestamp":1787315036673,"version":"build-2736575974"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134293","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:29:42Z","timestamp":1781713782000},"page":"134293","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Data density scaling for text-to-image models on small dataset"],"prefix":"10.1016","volume":"698","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1978-3805","authenticated-orcid":false,"given":"Senmao","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7593-1593","authenticated-orcid":false,"given":"Dawei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madal","family":"Artur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-0996","authenticated-orcid":false,"given":"Hua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-9215","authenticated-orcid":false,"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134293_bib0005","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"Reed","year":"2016","journal-title":"Int. Conf. Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134293_bib0010","author":"Ramesh"},{"key":"10.1016\/j.neucom.2026.134293_bib0015","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.neunet.2023.08.038","article-title":"Word self-update contrastive adversarial networks for text-to-image synthesis","volume":"167","author":"Xiao","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134293_bib0020","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.neunet.2021.01.023","article-title":"SAM-GAN: self-attention supporting multi-stage generative adversarial networks for text-to-image synthesis","volume":"138","author":"Peng","year":"2021","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134293_bib0025","article-title":"Dormant key: unlocking universal adversarial control in text-to-image models","author":"Hu","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134293_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107599","article-title":"Towards better text image machine translation with multimodal codebook and multi-stage training","author":"Lan","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134293_bib0035","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.neucom.2021.04.069","article-title":"A survey on generative adversarial network-based text-to-image synthesis","volume":"451","author":"Zhou","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134293_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.132363","article-title":"PointT2I: LLM-based text-to-image generation via keypoints","volume":"668","author":"Lee","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134293_bib0045","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neucom.2021.12.005","article-title":"Divergan: an efficient and effective single-stage framework for diverse text-to-image generation","volume":"473","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134293_bib0050","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1007\/s00170-023-10804-8","article-title":"A systematic review on digital human models in assembly process planning","volume":"125","author":"Yin","year":"2023","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"10.1016\/j.neucom.2026.134293_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8861","article-title":"Ledits++: limitless image editing using text-to-image models","author":"Brack","year":"2024"},{"key":"10.1016\/j.neucom.2026.134293_bib0060","series-title":"Proceedings of the 2023 ACM Designing Interactive Systems Conference","first-page":"1955","article-title":"3DALL-E: integrating text-to-image AI in 3D design workflows","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134293_bib0065","author":"Yu"},{"key":"10.1016\/j.neucom.2026.134293_bib0070","series-title":"European Conference on Computer Vision","first-page":"89","article-title":"Make-a-scene: scene-based text-to-image generation with human priors","author":"Gafni","year":"2022"},{"key":"10.1016\/j.neucom.2026.134293_bib0075","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134293_bib0080","author":"Sheynin"},{"key":"10.1016\/j.neucom.2026.134293_bib0085","author":"Li"},{"key":"10.1016\/j.neucom.2026.134293_bib0090","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134293_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10696","article-title":"Vector quantized diffusion model for text-to-image synthesis","author":"Gu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134293_bib0100","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/j.neucom.2026.134293_bib0105","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134293_bib0110","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"10.1016\/j.neucom.2026.134293_bib0115","doi-asserted-by":"crossref","first-page":"5514","DOI":"10.1109\/TIP.2018.2855406","article-title":"Attentive linear transformation for image captioning","volume":"27","author":"Ye","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134293_bib0120","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"Roweis","year":"2000","journal-title":"Science"},{"key":"10.1016\/j.neucom.2026.134293_bib0125","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.neucom.2026.134293_bib0130","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1109\/TMM.2021.3075997","article-title":"Modality disentangled discriminator for text-to-image synthesis","volume":"24","author":"Feng","year":"2022","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.neucom.2026.134293_bib0135","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/TMM.2021.3060291","article-title":"Cross-modal semantic matching generative adversarial networks for text-to-image synthesis","volume":"24","author":"Tan","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134293_bib0140","doi-asserted-by":"crossref","first-page":"4356","DOI":"10.1109\/TMM.2021.3116416","article-title":"Knowledge-driven generative adversarial network for text-to-image synthesis","volume":"24","author":"Peng","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134293_bib0145","doi-asserted-by":"crossref","first-page":"3409","DOI":"10.1109\/TMM.2022.3160360","article-title":"TextFace: text-to-style mapping based face generation and manipulation","volume":"25","author":"Hou","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134293_bib0150","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.neucom.2021.03.059","article-title":"PCCM-GAN: photographic text-to-image generation with pyramid contrastive consistency model","volume":"449","author":"Qi","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134293_bib0155","article-title":"ML-GAN: multi-level text-driven fine-grained image generation using generative adversarial network","author":"Zhao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134293_bib0160","article-title":"Conditional generative adversarial nets","volume":"abs\/1411.1784","author":"Mirza","year":"2014","journal-title":"CoRR"},{"key":"10.1016\/j.neucom.2026.134293_bib0165","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"16494","article-title":"DF-GAN: a simple and effective baseline for text-to-image synthesis","author":"Tao","year":"2022"},{"key":"10.1016\/j.neucom.2026.134293_bib0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14214","article-title":"Galip: generative adversarial clips for text-to-image synthesis","author":"Tao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134293_bib0175","series-title":"International Conference on Machine Learning","first-page":"30105","article-title":"Stylegan-t: unlocking the power of GANs for fast large-scale text-to-image synthesis","author":"Sauer","year":"2023"},{"key":"10.1016\/j.neucom.2026.134293_bib0180","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134293_bib0185","series-title":"Advances in Neural Information Processing Systems","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019"},{"key":"10.1016\/j.neucom.2026.134293_bib0190","series-title":"9th International Conference on Learning Representations, ICLR","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"10.1016\/j.neucom.2026.134293_bib0195","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134293_bib0200","author":"Saharia"},{"key":"10.1016\/j.neucom.2026.134293_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neucom.2026.134293_bib0210","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134293_bib0215","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.1109\/TCSVT.2025.3609840","article-title":"HOH-net: high-order hierarchical middle-feature learning network for visible-infrared person re-identification","volume":"36","author":"Qiu","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134293_bib0220","series-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6645","article-title":"Speech recognition with deep recurrent neural networks","author":"Graves","year":"2013"},{"key":"10.1016\/j.neucom.2026.134293_bib0225","series-title":"International Conference on Machine Learning","first-page":"173","article-title":"Deep speech 2: end-to-end speech recognition in english and mandarin","author":"Amodei","year":"2016"},{"key":"10.1016\/j.neucom.2026.134293_bib0230","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134293_bib0235","article-title":"VGG convolutional neural networks practical","volume":"66","author":"Vedaldi","year":"2016","journal-title":"Department of Engineering Science, University of Oxford"},{"key":"10.1016\/j.neucom.2026.134293_bib0240","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 34","first-page":"13001","article-title":"Random erasing data augmentation","author":"Zhong","year":"2020"},{"key":"10.1016\/j.neucom.2026.134293_bib0245","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134293_bib0250","series-title":"International Conference on Machine Learning","first-page":"6448","article-title":"Does label smoothing mitigate label noise?","author":"Lukasik","year":"2020"},{"key":"10.1016\/j.neucom.2026.134293_bib0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106311","article-title":"Score mismatching for generative modeling","volume":"175","author":"Ye","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134293_bib0260","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.134293_bib0265","author":"Ho"},{"key":"10.1016\/j.neucom.2026.134293_bib0270","series-title":"NIPS","article-title":"Learning what and where to draw","author":"Reed","year":"2016"},{"key":"10.1016\/j.neucom.2026.134293_bib0275","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134293_bib0280","series-title":"NIPS","first-page":"2226","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016"},{"key":"10.1016\/j.neucom.2026.134293_bib0285","series-title":"NIPS","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"Heusel","year":"2017"},{"key":"10.1016\/j.neucom.2026.134293_bib0290","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","article-title":"StackGAN++: realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134293_bib0295","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TMM.2023.3266607","article-title":"Recurrent affine transformation for text-to-image synthesis","volume":"26","author":"Ye","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134293_bib0300","series-title":"CVPR","article-title":"DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis","author":"Zhu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134293_bib0305","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021","first-page":"13940","article-title":"DAE-GAN: dynamic aspect-aware GAN for text-to-image synthesis","author":"Ruan","year":"2021"},{"key":"10.1016\/j.neucom.2026.134293_bib0310","series-title":"CVPR","article-title":"AttnGAN: fine-grained text to image generation with attentional generative adversarial networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134293_bib0315","series-title":"IJCNN","first-page":"1","article-title":"DTGAN: dual attention generative adversarial networks for text-to-image generation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134293_bib0320","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22669","article-title":"All are worth words: a VIT backbone for diffusion models","author":"Bao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134293_bib0325","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.52202\/068431-1833","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134293_bib0330","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.isprsjprs.2026.03.029","article-title":"Material proportion guided hyperspectral image super-resolution via unmixing","volume":"235","author":"Xu","year":"2026","journal-title":"ISPRS J. Photogramm. Remote Sens."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016917?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016917?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:38:05Z","timestamp":1787312285000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":66,"alternative-id":["S0925231226016917"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134293","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Data density scaling for text-to-image models on small dataset","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134293","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134293"}}