{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:09:11Z","timestamp":1779898151524,"version":"3.53.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:00:00Z","timestamp":1652486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:00:00Z","timestamp":1652486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61966004"],"award-info":[{"award-number":["61966004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2019GXNSFDA245018"],"award-info":[{"award-number":["2019GXNSFDA245018"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s11063-022-10866-x","type":"journal-article","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T13:03:06Z","timestamp":1652533386000},"page":"5371-5391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["PBGN: Phased Bidirectional Generation Network in Text-to-Image Synthesis"],"prefix":"10.1007","volume":"54","author":[{"given":"Jianwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huifang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,14]]},"reference":[{"key":"10866_CR1","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp 2672\u20132680"},{"key":"10866_CR2","unstructured":"Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942"},{"key":"10866_CR3","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"10866_CR4","unstructured":"Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks. In: Proceedings of the International Conference on Machine Learning, pp 7354\u20137363"},{"key":"10866_CR5","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10866_CR6","unstructured":"Farnia F, Zhang JM, Tse D (2018) Generalizable adversarial training via spectral normalization. arXiv preprint arXiv:1811.07457"},{"issue":"2","key":"10866_CR7","doi-asserted-by":"publisher","first-page":"68","DOI":"10.3390\/info11020068","volume":"11","author":"L Zhao","year":"2020","unstructured":"Zhao L, Liu Y (2020) Spectral normalization for domain adaptation. Information 11(2):68","journal-title":"Information"},{"key":"10866_CR8","doi-asserted-by":"publisher","first-page":"103170","DOI":"10.1016\/j.jvcir.2021.103170","volume":"78","author":"J Zhang","year":"2021","unstructured":"Zhang J, Li Z, Zhang C, Ma H (2021) Stable self-attention adversarial learning for semi-supervised semantic image segmentation. J Vis Commun Image Represent 78:103170","journal-title":"J Vis Commun Image Represent"},{"key":"10866_CR9","doi-asserted-by":"crossref","unstructured":"Reed S, Akata Z, Lee H, Schiele B (2016) Learning deep representations of fine-grained visual descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 49\u201358","DOI":"10.1109\/CVPR.2016.13"},{"key":"10866_CR10","doi-asserted-by":"crossref","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas DN (2017) 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","DOI":"10.1109\/ICCV.2017.629"},{"key":"10866_CR11","doi-asserted-by":"crossref","unstructured":"Xu T, Zhang P, Huang Q, Zhang H, Gan Z, Huang X, He X (2018) 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","DOI":"10.1109\/CVPR.2018.00143"},{"issue":"11","key":"10866_CR12","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673\u20132681","journal-title":"IEEE Trans Signal Process"},{"key":"10866_CR13","doi-asserted-by":"crossref","unstructured":"Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. arXiv preprint arXiv:1802.05365","DOI":"10.18653\/v1\/N18-1202"},{"key":"10866_CR14","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"10866_CR15","doi-asserted-by":"crossref","unstructured":"Pavllo D, Lucchi A, Hofmann T (2020) Controlling style and semantics in weakly-supervised image generation. In: Proceedings of the European conference on computer vision, pp 482\u2013499","DOI":"10.1007\/978-3-030-58539-6_29"},{"key":"10866_CR16","doi-asserted-by":"crossref","unstructured":"Wang T, Zhang T, Lovell B (2021) Faces \u00e0 la carte: Text-to-face generation via attribute disentanglement. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3380\u20133388","DOI":"10.1109\/WACV48630.2021.00342"},{"key":"10866_CR17","doi-asserted-by":"crossref","unstructured":"Souza DM, Wehrmann J, Ruiz DD (2020) Efficient neural architecture for text-to-image synthesis. In: Proceedings of the international joint conference on neural networks (IJCNN), pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9207584"},{"key":"10866_CR18","doi-asserted-by":"crossref","unstructured":"Liang J, Pei W, Lu F (2020) Cpgan: Content-parsing generative adversarial networks for text-to-image synthesis. In: Proceedings of the European conference on computer vision, pp 491\u2013508","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"10866_CR19","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784"},{"key":"10866_CR20","unstructured":"Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H (2016) Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396"},{"key":"10866_CR21","unstructured":"Dash A, Gamboa JCB, Ahmed S, Liwicki M, Afzal MZ (2017) Tac-gan-text conditioned auxiliary classifier generative adversarial network. arXiv preprint arXiv:1703.06412"},{"key":"10866_CR22","unstructured":"Odena A, Olah C, Shlens J (2017) Conditional image synthesis with auxiliary classifier gans. In: Proceedings of the international conference on machine learning, pp 2642\u20132651"},{"key":"10866_CR23","unstructured":"Reed SE, Akata Z, Mohan S, Tenka S, Schiele B, Lee H (2016) Learning what and where to draw. In: Advances in neural information processing systems, pp 217\u2013225"},{"key":"10866_CR24","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset. Technical report, California Institute of Technology"},{"issue":"8","key":"10866_CR25","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 DN (2018) Stackgan++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans Pattern Anal Mach Intell 41(8):1947\u20131962","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10866_CR26","doi-asserted-by":"crossref","unstructured":"Yuan M, Peng Y (2018) Text-to-image synthesis via symmetrical distillation networks. In: Proceedings of the 26th ACM international conference on multimedia, pp 1407\u20131415","DOI":"10.1145\/3240508.3240559"},{"key":"10866_CR27","doi-asserted-by":"crossref","unstructured":"Ma S, Fu J, Chen CW, Mei T (2018) Da-gan: Instance-level image translation by deep attention generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5657\u20135666","DOI":"10.1109\/CVPR.2018.00593"},{"key":"10866_CR28","doi-asserted-by":"crossref","unstructured":"Zhu M, Pan P, Chen W, Yang Y (2019) 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","DOI":"10.1109\/CVPR.2019.00595"},{"key":"10866_CR29","unstructured":"Weston J, Chopra S, Bordes A (2014) Memory networks. arXiv preprint arXiv:1410.3916"},{"issue":"4","key":"10866_CR30","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1162\/neco_a_01060","volume":"30","author":"C Gulcehre","year":"2018","unstructured":"Gulcehre C, Chandar S, Cho K, Bengio Y (2018) Dynamic neural turing machine with continuous and discrete addressing schemes. Neural Comput 30(4):857\u2013884","journal-title":"Neural Comput"},{"key":"10866_CR31","doi-asserted-by":"crossref","unstructured":"Cheng J, Wu F, Tian Y, Wang L, Tao D (2020) 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","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"10866_CR32","doi-asserted-by":"crossref","unstructured":"Qiao T, Zhang J, Xu D, Tao D (2019) Mirrorgan: Learning text-to-image generation by redescription. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1505\u20131514","DOI":"10.1109\/CVPR.2019.00160"},{"key":"10866_CR33","doi-asserted-by":"crossref","unstructured":"Lee K-H, Chen X, Hua G, Hu H, He X (2018) Stacked cross attention for image-text matching. In: Proceedings of the European conference on computer vision, pp 201\u2013216","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"10866_CR34","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1109\/TIP.2019.2940693","volume":"29","author":"H Cui","year":"2020","unstructured":"Cui H, Zhu L, Li J, Yang Y, Nie L (2020) Scalable deep hashing for large-scale social image retrieval. IEEE Trans Image Process 29:1271\u20131284","journal-title":"IEEE Trans Image Process"},{"key":"10866_CR35","doi-asserted-by":"publisher","first-page":"4643","DOI":"10.1109\/TIP.2020.2974065","volume":"29","author":"L Zhu","year":"2020","unstructured":"Zhu L, Lu X, Cheng Z, Li J, Zhang H (2020) Deep collaborative multi-view hashing for large-scale image search. IEEE Trans Image Process 29:4643\u20134655","journal-title":"IEEE Trans Image Process"},{"key":"10866_CR36","doi-asserted-by":"publisher","first-page":"104475","DOI":"10.1016\/j.engappai.2021.104475","volume":"106","author":"Z Li","year":"2021","unstructured":"Li Z, Xie X, Ling F, Ma H, Shi Z (2021) Matching images and texts with multi-head attention network for cross-media hashing retrieval. Eng Appl Artif Intell 106:104475","journal-title":"Eng Appl Artif Intell"},{"key":"10866_CR37","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"10866_CR38","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"10866_CR39","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MSP.2008.926652","volume":"25","author":"X He","year":"2008","unstructured":"He X, Deng L, Chou W (2008) Discriminative learning in sequential pattern recognition. IEEE Signal Process Mag 25(5):14\u201336","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"10866_CR40","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/89.568732","volume":"5","author":"B-H Juang","year":"1997","unstructured":"Juang B-H, Hou W, Lee C-H (1997) Minimum classification error rate methods for speech recognition. IEEE Trans Speech Audio Process 5(3):257\u2013265","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10866_CR41","doi-asserted-by":"crossref","unstructured":"Fang H, Gupta S, Iandola F, Srivastava RK, Deng L, Doll\u00e1r P, Gao J, He X, Mitchell M, Platt JC, Zitnick CL, Zweig G (2015) From captions to visual concepts and back. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR), pp 1473\u20131482","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"10866_CR42","doi-asserted-by":"crossref","unstructured":"Huang P-S, He X, Gao J, Deng L, Acero A, Heck L (2013) Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM international conference on information & knowledge management, pp 2333\u20132338","DOI":"10.1145\/2505515.2505665"},{"key":"10866_CR43","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"2","key":"10866_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439734","volume":"17","author":"H Wei","year":"2021","unstructured":"Wei H, Li Z, Huang F, Zhang C, Ma H, Shi Z (2021) Integrating scene semantic knowledge into image captioning. ACM Trans Multimed Comput Commun Appl 17(2):1\u201322","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"10866_CR45","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10866_CR46","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Rohrbach M, Donahue J, Mooney R, Darrell T, Saenko K (2015) Sequence to sequence-video to text. In: Proceedings of the IEEE international conference on computer vision, pp 4534\u20134542","DOI":"10.1109\/ICCV.2015.515"},{"key":"10866_CR47","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Proceedings of the European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10866_CR48","doi-asserted-by":"crossref","unstructured":"Nilsback M-E, Zisserman A (2008) Automated flower classification over a large number of classes. In: Proceedings of the Sixth Indian conference on computer vision, graphics & image processing, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"10866_CR49","unstructured":"Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training gans. In: Advances in neural information processing systems, pp 2234\u20132242"},{"key":"10866_CR50","unstructured":"Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10866-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10866-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10866-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T19:09:50Z","timestamp":1667156990000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10866-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,14]]},"references-count":50,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10866"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10866-x","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,14]]},"assertion":[{"value":"22 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}