{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:28:15Z","timestamp":1775712495309,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T00:00:00Z","timestamp":1649376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T00:00:00Z","timestamp":1649376000000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s00138-022-01298-7","type":"journal-article","created":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:02:32Z","timestamp":1649440952000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Paired-D++ GAN for image manipulation with text"],"prefix":"10.1007","volume":"33","author":[{"given":"Duc Minh","family":"Vo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akihiro","family":"Sugimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,8]]},"reference":[{"key":"1298_CR1","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: ICCV, (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"1298_CR2","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Manipulating images with natural language. In: NeurIPS, Text-Adaptive Generative Adversarial Networks (2018)"},{"key":"1298_CR3","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Philip H.S.T.: Text-guided image manipulation. In: CVPR, Manigan (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"1298_CR4","unstructured":"Reed, S., Akata, Z., Xinchen Y., Logeswaran L., Bernt S., Honglak L.: Generative adversarial text-to-image synthesis. In: ICML (2016)"},{"key":"1298_CR5","doi-asserted-by":"crossref","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2image: Conditional image generation from visual attributes. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"1298_CR6","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Freeman, W.T.; Image quilting for texture synthesis and transfer, In: SIGGRAPH (2001)","DOI":"10.1145\/383259.383296"},{"key":"1298_CR7","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"1298_CR8","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: NIPS (2014)"},{"key":"1298_CR9","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"1298_CR10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"1298_CR11","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Generative image modeling using style and structure adversarial networks. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"1298_CR12","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A.P., Tejani, A., Totz, J., Wang, Z., Shi, W.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"1298_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.: Stackgan++: Realistic image synthesis with stacked generative adversarial networks. In: TPAMI (2019)","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"1298_CR14","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"1298_CR15","unstructured":"Nguyen, T., Le, T., Vu, H., Phung, D.: Dual discriminator generative adversarial nets. In: NIPS (2017)"},{"key":"1298_CR16","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical Report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"1298_CR17","doi-asserted-by":"crossref","unstructured":"Nilsback, M-E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"1298_CR18","unstructured":"Yang, J., Kannan, A., Batra, D., Parikh, D.: Lr-gan: Layered recursive generative adversarial networks for image generation. In: ICLR (2017)"},{"key":"1298_CR19","doi-asserted-by":"crossref","unstructured":"Vo, D.M., Sugimoto, A.: Paired-d gan for semantic image synthesis. In: ACCV (2018)","DOI":"10.1007\/978-3-030-20870-7_29"},{"key":"1298_CR20","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes, In: ICLR (2014)"},{"key":"1298_CR21","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models, In: ICML (2014)"},{"key":"1298_CR22","unstructured":"Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: ICML (2016)"},{"key":"1298_CR23","unstructured":"Van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A.: Conditional image generation with pixelcnn decoders. In: NIPS (2016)"},{"key":"1298_CR24","unstructured":"Jiang, Y., Chang, S., Wang, Z.: Two transformers can make one strong gan. In: NeurIPS, Transgan (2021)"},{"key":"1298_CR25","unstructured":"Hudson, D.A., Zitnick, C.L.: Generative adversarial transformers. In: ICML (2021)"},{"key":"1298_CR26","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Interpretable representation learning by information maximizing generative adversarial nets. In: NIPS (2016)"},{"key":"1298_CR27","unstructured":"Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: ICLR (2017)"},{"key":"1298_CR28","unstructured":"Zhu, J.Y., Zhang, R., Pathak, D., Darrell, T., Efros, A.A., Wang, O., Shechtman, E.: Toward multimodal image-to-image translation, In: NIPS (2017)"},{"key":"1298_CR29","unstructured":"Perarnau, G., Van De Weijer, J., Raducanu, B., \u00c1lvarez, J.M.: Invertible conditional GANs for image editing. In: NIPS Workshop on Adversarial Training (2016)"},{"key":"1298_CR30","doi-asserted-by":"crossref","unstructured":"Li, C., Wand, M.: Precomputed real-time texture synthesis with markovian generative adversarial networks. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"1298_CR31","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.13"},{"key":"1298_CR32","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: NIPS (2016)"},{"key":"1298_CR33","doi-asserted-by":"crossref","unstructured":"Liu, X., Lin, Z., Zhang, J., Zhao, H., Tran, Q., Wang, X., Hongsheng L.: Open-domain image manipulation with open-vocabulary instructions. In: ECCV, Open-edit (2020)","DOI":"10.1007\/978-3-030-58621-8_6"},{"key":"1298_CR34","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"1298_CR35","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.-F.: Imagenet large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"1298_CR36","doi-asserted-by":"crossref","unstructured":"Schuster, M., Paliwal, K.\u00a0K.: Bidirectional recurrent neural networks. In: IEEE Transactions on Signal Processing (1997)","DOI":"10.1109\/78.650093"},{"key":"1298_CR37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1298_CR38","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"1298_CR39","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: CVPR (2005)"},{"key":"1298_CR40","unstructured":"Diederik, P.K., Jimmy B.A: A method for stochastic optimization. In: ICLR (2015)"},{"key":"1298_CR41","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X., Chen, X.: Improved techniques for training gans. In: NIPS (2016)"},{"key":"1298_CR42","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS (2017)"},{"key":"1298_CR43","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"issue":"3","key":"1298_CR44","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/0047-259X(82)90077-X","volume":"12","author":"DC Dowson","year":"1982","unstructured":"Dowson, D.C., Landau, B.V.: The fr\u00e9chet distance between multivariate normal distributions. J. Multiv. Anal. 12(3), 450\u2013455 (1982)","journal-title":"J. Multiv. Anal."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01298-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-022-01298-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01298-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T21:17:26Z","timestamp":1726953446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-022-01298-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,8]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["1298"],"URL":"https:\/\/doi.org\/10.1007\/s00138-022-01298-7","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,8]]},"assertion":[{"value":"16 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"45"}}