{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T04:48:59Z","timestamp":1788324539785,"version":"build-2803163510"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61807002"],"award-info":[{"award-number":["61807002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03326-1","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T07:02:00Z","timestamp":1711609320000},"page":"303-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["PMGAN: pretrained model-based generative adversarial network for text-to-image generation"],"prefix":"10.1007","volume":"41","author":[{"given":"Yue","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingshuo","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"3326_CR1","unstructured":"Chang, H., Zhang, H., Barber, J., et\u00a0al.: Muse: Text-to-image generation via masked generative transformers (2023). arXiv:2301.00704"},{"key":"3326_CR2","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., Yang, Z., Hong, W., et al.: Cogview: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3326_CR3","first-page":"16890","volume":"35","author":"M Ding","year":"2022","unstructured":"Ding, M., Zheng, W., Hong, W., et al.: Cogview2: faster and better text-to-image generation via hierarchical transformers. Adv. Neural. Inf. Process. Syst. 35, 16890\u201316902 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3326_CR4","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3326_CR5","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., et\u00a0al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"3326_CR6","doi-asserted-by":"crossref","unstructured":"Kang, M., Zhu, J.Y,. Zhang, R., et\u00a0al.: Scaling up gans for text-to-image synthesis. arXiv:2303.05511 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"3326_CR7","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"3326_CR8","unstructured":"Li, B., Torr, P.H., Lukasiewicz, T.: Memory-driven text-to-image generation. arXiv:2208.07022 (2022)"},{"key":"3326_CR9","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.isprsjprs.2021.07.007","volume":"179","author":"X Li","year":"2021","unstructured":"Li, X., Du, Z., Huang, Y., et al.: A deep translation (gan) based change detection network for optical and sar remote sensing images. ISPRS J. Photogramm. Remote. Sens. 179, 14\u201334 (2021)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"3326_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision (ECCV), Springer, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3326_CR11","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., et\u00a0al.: Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741 (2021)"},{"key":"3326_CR12","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., et\u00a0al.: Mirrorgan: Learning text-to-image generation by redescription. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"3326_CR13","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp. 8748\u20138763 (2021)"},{"issue":"1","key":"3326_CR14","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"3326_CR15","unstructured":"Ramesh, A., Pavlov, M., Goh, G., et\u00a0al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, PMLR, pp. 8821\u20138831 (2021)"},{"key":"3326_CR16","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., et\u00a0al.: Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 1(2) (2022)"},{"key":"3326_CR17","unstructured":"Reed, S., Akata, Z., Yan, X., et\u00a0al.: Generative adversarial text to image synthesis. In: International conference on machine learning, PMLR, pp. 1060\u20131069 (2016)"},{"key":"3326_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et\u00a0al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3326_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"3326_CR20","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"11","key":"3326_CR21","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"3326_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et\u00a0al.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"3326_CR23","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., et\u00a0al.: Df-gan: A simple and effective baseline for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16515\u201316525 (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"3326_CR24","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., et\u00a0al.: Galip: Generative adversarial clips for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14214\u201314223 (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"3326_CR25","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6309\u20136318 (2017)"},{"key":"3326_CR26","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3326_CR27","unstructured":"Wah, C., Branson, S., Welinder, P., et\u00a0al.: The caltech-ucsd birds-200-2011 dataset. California Institute of Technology (2011)"},{"issue":"12","key":"3326_CR28","doi-asserted-by":"publisher","first-page":"6085","DOI":"10.1007\/s00371-022-02714-9","volume":"39","author":"S Wang","year":"2023","unstructured":"Wang, S., Gao, Z., Liu, D.: Swin-gan: generative adversarial network based on shifted windows transformer architecture for image generation. Vis. Comput. 39(12), 6085\u20136095 (2023)","journal-title":"Vis. Comput."},{"key":"3326_CR29","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., Huang, Q., et\u00a0al.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Rrecognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"3326_CR30","unstructured":"Yu, J., Xu, Y., Koh, J.Y., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv:2206.10789 2(3) (2022)"},{"key":"3326_CR31","doi-asserted-by":"publisher","first-page":"30637","DOI":"10.1109\/ACCESS.2019.2903543","volume":"7","author":"L Yuan","year":"2019","unstructured":"Yuan, L., Chen, D., Hu, H.: Unsupervised object-level image-to-image translation using positional attention bi-flow generative network. IEEE Access 7, 30637\u201330647 (2019)","journal-title":"IEEE Access"},{"key":"3326_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., et\u00a0al.: Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"3326_CR33","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., Xu, T., Li, H., et al.: Stackgan++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1947\u20131962 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3326_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., et\u00a0al.: Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 833\u2013842 (2021)","DOI":"10.1109\/CVPR46437.2021.00089"},{"issue":"4","key":"3326_CR35","first-page":"1283","volume":"39","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Han, S., Zhang, Z., et al.: Cf-gan: cross-domain feature fusion generative adversarial network for text-to-image synthesis. Vis. Comput. 39(4), 1283\u20131293 (2023)","journal-title":"Vis. Comput."},{"key":"3326_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, R., Chen, C., et\u00a0al.: Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17907\u201317917 (2022)","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"3326_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., et\u00a0al.: Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03326-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03326-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03326-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T13:02:56Z","timestamp":1737723776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03326-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,28]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3326"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03326-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,28]]},"assertion":[{"value":"20 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}