{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T20:55:23Z","timestamp":1758056123602,"version":"3.44.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03993-8","type":"journal-article","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T01:33:50Z","timestamp":1748050430000},"page":"9691-9704","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic local affine transformation for enhanced text-to-image generation with GANs"],"prefix":"10.1007","volume":"41","author":[{"given":"Qiang","family":"Lan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"key":"3993_CR1","first-page":"2672","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. Adv. Neural. Inf. Process. Syst. 27, 2672\u20132680 (2014)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3993_CR2","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR. arXiv:1411.1784 (2014)"},{"key":"3993_CR3","unstructured":"Reed, S., Akata, Z., Yan, X.C., et al.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning. PMLR, vol. 48, pp. 1060\u20131069 (2016)"},{"key":"3993_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H.S., et al.: 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":"3993_CR5","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2019","unstructured":"Zhang, H., Xu, T., Li, H.S., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1947\u20131962 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3993_CR6","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., et al.: 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":"3993_CR7","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P.C., Huang, Q.Y., et al.: AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"3993_CR8","unstructured":"Wah, C., Branson, S., Welinder, P., et al.: The Caltech-UCSD birds-200-2011 dataset. California Institute of Technology, vol. 7, no. 1, pp. 1\u20138 (2011)"},{"key":"3993_CR9","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et al.: Microsoft COCO: common objects in context. In: Proceedings of the 13th European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3993_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, J., Wu, F.X., Tian, Y.L., et al.: RiFeGAN: Rich feature generation for text-to-image synthesis from prior knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10911\u201310920 (2020)","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"3993_CR11","doi-asserted-by":"crossref","unstructured":"Zhu, M.F., Pan, P.B., Chen, W., et al.: 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"},{"key":"3993_CR12","doi-asserted-by":"crossref","unstructured":"Yin, G.J., Liu, B., Sheng, L., et al.: Semantics disentangling for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2327\u20132336 (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"3993_CR13","doi-asserted-by":"crossref","unstructured":"Qiao, T.T., Zhang, J., Xu, D.Q., et al.: 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":"3993_CR14","doi-asserted-by":"crossref","unstructured":"Liao, W.T., Hu, K., Yang, M.Y., et al.: Text to image generation with semantic-spatial aware GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18187\u201318196 (2022)","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"3993_CR15","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TMM.2023.3266607","volume":"26","author":"SM Ye","year":"2024","unstructured":"Ye, S.M., Wang, H., Tan, M.K., et al.: Recurrent affine transformation for text-to-image synthesis. IEEE Trans. Multim. 26, 462\u2013473 (2024)","journal-title":"IEEE Trans. Multim."},{"key":"3993_CR16","doi-asserted-by":"crossref","unstructured":"Wu, X.T., Zhao, H.B., Zheng, L.L., et al.: Adma-GAN: attribute-driven memory augmented GANs for text-to-image generation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1593\u20131602 (2022)","DOI":"10.1145\/3503161.3547821"},{"key":"3993_CR17","doi-asserted-by":"publisher","first-page":"109883","DOI":"10.1016\/j.patcog.2023.109883","volume":"144","author":"ZR Tan","year":"2023","unstructured":"Tan, Z.R., Yang, X., Ye, Z.H., et al.: Semantic similarity distance: towards better text-image consistency metric in text-to-image generation. Pattern Recogn. 144, 109883 (2023)","journal-title":"Pattern Recogn."},{"key":"3993_CR18","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"3993_CR19","doi-asserted-by":"crossref","unstructured":"Ruan, S.L., Zhang, Y., Zhang, K., et al.: DAE-GAN: Dynamic aspect-aware GAN for text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13960\u201313969 (2021)","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"3993_CR20","first-page":"1","volume":"41","author":"Y Yu","year":"2024","unstructured":"Yu, Y., Yang, Y., Xing, J.S.: PMGAN: pretrained model-based generative adversarial network for text-to-image generation. Vis. Comput. 41, 1\u201312 (2024)","journal-title":"Vis. Comput."},{"key":"3993_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: Layoutdiffusion: controllable diffusion model for layout-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22490\u201322499 (2023)","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"3993_CR22","doi-asserted-by":"crossref","unstructured":"Wu, T., Li, X., Qi, Z., Hu, D., Wang, X., Shan, Y., Li, X.: Spherediffusion: spherical geometry-aware distortion resilient diffusion model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 6, pp. 6126\u20136134 (2024)","DOI":"10.1609\/aaai.v38i6.28429"},{"key":"3993_CR23","doi-asserted-by":"crossref","unstructured":"Kang, M., Zhu, J.Y., Zhang, R., et al.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"issue":"12","key":"3993_CR24","doi-asserted-by":"publisher","first-page":"7991","DOI":"10.1109\/TII.2021.3064369","volume":"17","author":"MN Cheema","year":"2021","unstructured":"Cheema, M.N., Nazir, A., Yang, P., et al.: Modified GAN-cAED to minimize risk of unintentional liver major vessels cutting by controlled segmentation using CTA\/SPET-CT. IEEE Trans. Ind. Inf. 17(12), 7991\u20138002 (2021)","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"6","key":"3993_CR25","doi-asserted-by":"publisher","first-page":"2701","DOI":"10.1109\/TCYB.2019.2924589","volume":"50","author":"MJ Zhang","year":"2019","unstructured":"Zhang, M.J., Wang, N.N., Li, Y.S., et al.: Bionic face sketch generator. IEEE Trans Cybern 50(6), 2701\u20132714 (2019)","journal-title":"IEEE Trans Cybern"},{"key":"3993_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, M.J., He, C.Y., Zhang, J., et al.: SAR-to-optical image translation via neural partial differential equations. In: IJCAI, pp. 1644\u20131650 (2022)","DOI":"10.24963\/ijcai.2022\/229"},{"issue":"5","key":"3993_CR27","doi-asserted-by":"publisher","first-page":"053056","DOI":"10.1117\/1.JEI.33.5.053056","volume":"33","author":"Z Lu","year":"2024","unstructured":"Lu Z, Guo T, Wang F.: Semisupervised Chinese poem-topainting generation via cycle-consistent adversarial networks. J. Electron. Imaging 33(5):053056\u2013053056 (2024)","journal-title":"J. Electron. Imaging"},{"key":"3993_CR28","first-page":"6626","volume":"30","author":"M Heusel","year":"2017","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., et al.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural. Inf. Process. Syst. 30, 6626\u20136637 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3993_CR29","first-page":"2234","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., et al.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29, 2234\u20132242 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3993_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: 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"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03993-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03993-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03993-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:36:39Z","timestamp":1757928999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03993-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,24]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3993"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03993-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,5,24]]},"assertion":[{"value":"8 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}