{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:52:13Z","timestamp":1781279533679,"version":"3.54.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"DOI":"10.1007\/s00371-022-02404-6","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:03:33Z","timestamp":1643900613000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["CF-GAN: cross-domain feature fusion generative adversarial network for text-to-image synthesis"],"prefix":"10.1007","author":[{"given":"Yubo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2442-330X","authenticated-orcid":false,"given":"Hongbo","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,3]]},"reference":[{"key":"2404_CR1","doi-asserted-by":"crossref","unstructured":"Bishop, C.M., et al.: Neural Networks for Pattern Recognition. Oxford University Press (1995)","DOI":"10.1201\/9781420050646.ptb6"},{"key":"2404_CR2","unstructured":"Chen, X., Qing, L., He, X., Luo, X., Xu, Y.: Ftgan: A fully-trained generative adversarial networks for text to face generation. arXiv preprint arXiv:1904.05729 (2019)"},{"key":"2404_CR3","unstructured":"Dash, A., Gamboa, J.C.B., Ahmed, S., Liwicki, M., Afzal, M.Z.: Tac-gan-text conditioned auxiliary classifier generative adversarial network. arXiv preprint arXiv:1703.06412 (2017)"},{"key":"2404_CR4","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5706\u20135714 (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"2404_CR5","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"2404_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2404_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2404_CR8","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: Controllable text-to-image generation. arXiv preprint arXiv:1909.07083 (2019)"},{"key":"2404_CR9","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: Manigan: text-guided image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7880\u20137889 (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"2404_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, P., Zhang, L., Huang, Q., He, X., Lyu, S., Gao, J.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"2404_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Gan, Z., Shen, Y., Liu, J., Cheng, Y., Wu, Y., Carin, L., Carlson, D., Gao, J.: Storygan: A sequential conditional gan for story visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2019)","DOI":"10.1109\/CVPR.2019.00649"},{"key":"2404_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2404_CR13","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug & play generative networks: conditional iterative generation of images in latent space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4467\u20134477 (2017)","DOI":"10.1109\/CVPR.2017.374"},{"key":"2404_CR14","doi-asserted-by":"publisher","first-page":"37697","DOI":"10.1109\/ACCESS.2020.2975841","volume":"8","author":"J Ni","year":"2020","unstructured":"Ni, J., Zhang, S., Zhou, Z., Hou, J., Gao, F.: Instance mask embedding and attribute-adaptive generative adversarial network for text-to-image synthesis. IEEE Access 8, 37697\u201337711 (2020)","journal-title":"IEEE Access"},{"key":"2404_CR15","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: 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":"2404_CR16","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"2404_CR17","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. arXiv preprint arXiv:1610.02454 (2016)"},{"key":"2404_CR18","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"2404_CR19","unstructured":"Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press (2007)"},{"issue":"3","key":"2404_CR20","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., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"2404_CR21","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. arXiv preprint arXiv:1606.03498 (2016)"},{"key":"2404_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2019.03.055","volume":"490","author":"C Shi","year":"2019","unstructured":"Shi, C., Pun, C.M.: Adaptive multi-scale deep neural networks with perceptual loss for panchromatic and multispectral images classification. Inf. Sci. 490, 1\u201317 (2019)","journal-title":"Inf. Sci."},{"key":"2404_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2404_CR24","doi-asserted-by":"crossref","unstructured":"Tan, F., Feng, S., Ordonez, V.: Text2scene: generating compositional scenes from textual descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6710\u20136719 (2019)","DOI":"10.1109\/CVPR.2019.00687"},{"key":"2404_CR25","doi-asserted-by":"crossref","unstructured":"Tan, H., Liu, X., Li, X., Zhang, Y., Yin, B.: Semantics-enhanced adversarial nets for text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10501\u201310510 (2019)","DOI":"10.1109\/ICCV.2019.01060"},{"key":"2404_CR26","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, S., Sebe, N., Wu, F., Jing, X.Y.: Df-gan: deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint arXiv:2008.05865 (2020)","DOI":"10.1109\/ICIBA50161.2020.9277299"},{"key":"2404_CR27","unstructured":"Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S-PLUS. Springer Science & Business Media (2013)"},{"key":"2404_CR28","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"2404_CR29","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., He, X.: 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":"2404_CR30","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1109\/TIP.2021.3055062","volume":"30","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Wang, L., Xie, D., Deng, C., Tao, D.: Multi-sentence auxiliary adversarial networks for fine-grained text-to-image synthesis. IEEE Trans. Image Process. 30, 2798\u20132809 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2404_CR31","doi-asserted-by":"crossref","unstructured":"Yin, G., Liu, B., Sheng, L., Yu, N., Wang, X., Shao, J.: 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":"2404_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.N.: 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":"2404_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., Zhang, S., Wang, X., Huang, X., Metaxas, D.N.: 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":"2404_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Yang, L.: Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6199\u20136208 (2018)","DOI":"10.1109\/CVPR.2018.00649"},{"key":"2404_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhou, J., Yu, W., Jiang, N.: Drawgan: text to image synthesis with drawing generative adversarial networks. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4195\u20134199. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414166"},{"key":"2404_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: 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\/s00371-022-02404-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02404-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02404-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:03:55Z","timestamp":1643900635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02404-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,3]]},"references-count":36,"alternative-id":["2404"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02404-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,3]]},"assertion":[{"value":"5 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}