{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T14:55:39Z","timestamp":1763564139164},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11432-020-2900-x","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T15:16:36Z","timestamp":1605885396000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Learning efficient text-to-image synthesis via interstage cross-sample similarity distillation"],"prefix":"10.1007","volume":"64","author":[{"given":"Fengling","family":"Mao","sequence":"first","affiliation":[]},{"given":"Bingpeng","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"2900_CR1","unstructured":"Chen X, Duan Y, Houthooft R, et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Proceedings of Advances in Neural Information Processing Systems, 2016. 2172\u20132180"},{"key":"2900_CR2","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: Proceedings of Advances in Neural Information Processing Systems, 2014. 2672\u20132680"},{"key":"2900_CR3","unstructured":"Kingma D P, Welling M. Auto-encoding variational Bayes. 2013. ArXiv: 1312.6114"},{"key":"2900_CR4","unstructured":"Brock A, Donahue J, Simonyan K. Large scale GAN training for high fidelity natural image synthesis. In: Proceedings of International Conference on Learning Representations, 2019"},{"key":"2900_CR5","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. 2018. ArXiv: 1812.04948","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2900_CR6","doi-asserted-by":"crossref","unstructured":"Xiong W, Luo W H, Ma L, et al. Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 2364\u20132373","DOI":"10.1109\/CVPR.2018.00251"},{"key":"2900_CR7","doi-asserted-by":"crossref","unstructured":"Xiong W, Lin Z, Yang J M, et al. Foreground-aware image inpainting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019. 5840\u20135848","DOI":"10.1109\/CVPR.2019.00599"},{"key":"2900_CR8","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T H, et al. Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"2900_CR9","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of IEEE International Conference on Computer Vision, 2017. 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"2900_CR10","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1360\/SSI-2019-0096","volume":"50","author":"Y W Miao","year":"2020","unstructured":"Miao Y W, Liu J Z, Chen J H, et al. Structure-preserving shape completion of 3D point clouds with generative adversarial network (in Chinese). Sci Sin Inform, 2020, 50: 675\u2013691","journal-title":"Sci Sin Inform"},{"key":"2900_CR11","doi-asserted-by":"publisher","first-page":"209302","DOI":"10.1007\/s11432-018-9668-6","volume":"62","author":"Y H Li","year":"2019","unstructured":"Li Y H, Ao D Y, Dumitru C O, et al. Super-resolution of geosynchronous synthetic aperture radar images using dialectical GANs. Sci China Inf Sci, 2019, 62: 209302","journal-title":"Sci China Inf Sci"},{"key":"2900_CR12","unstructured":"Reed S, Akata Z, Yan X C, et al. Generative adversarial text to image synthesis. In: Proceedings of International Conference on Machine Learning, 2016"},{"key":"2900_CR13","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 IEEE International Conference on Computer Vision, 2017. 5907\u20135915","DOI":"10.1109\/ICCV.2017.629"},{"key":"2900_CR14","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 S, et al. StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans Pattern Anal Mach Intell, 2018, 41: 1947\u20131962","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2900_CR15","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 IEEE Conference on Computer Vision and Pattern Recognition, 2018. 1316\u20131324","DOI":"10.1109\/CVPR.2018.00143"},{"key":"2900_CR16","doi-asserted-by":"crossref","unstructured":"Zhang Z Z, Xie Y P, Yang L. Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 6199\u20136208","DOI":"10.1109\/CVPR.2018.00649"},{"key":"2900_CR17","unstructured":"Mao F L, Ma B P, Chang H, et al. MS-GAN: text to image synthesis with attention-modulated generators and similarity-aware discriminators. In: Proceedings of British Machine Vision Conference, 2019"},{"key":"2900_CR18","unstructured":"Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. 2015. ArXiv: 1511.06434"},{"key":"2900_CR19","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. 2015. ArXiv: 1503.02531"},{"key":"2900_CR20","doi-asserted-by":"crossref","unstructured":"Nilsback M, Zisserman A. Automated flower classification over a large number of classes. In: Proceedings of Indian Conference on Computer Vision, Graphics & Image Processing, 2008. 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2900_CR21","unstructured":"Wah C, Branson S, Welinder P, et al. The Caltech-UCSD Birds-200\u20132011 Dataset. Technical Report CNS-TR-2011-001. California Institute of Technology. 2011"},{"key":"2900_CR22","unstructured":"Salimans T, Goodfellow I, Zaremba W, et al. Improved techniques for training GANs. In: Proceedings of Advances in Neural Information Processing Systems, 2016. 2234\u20132242"},{"key":"2900_CR23","unstructured":"Heusel M, Ramsauer H, Unterthiner T, et al. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 6626\u20136637"},{"key":"2900_CR24","unstructured":"Mirza M, Osindero S. Conditional generative adversarial nets. 2014. ArXiv: 1411.1784"},{"key":"2900_CR25","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1109\/TCSVT.2018.2880223","volume":"29","author":"Y W Pang","year":"2019","unstructured":"Pang Y W, Xie J, Li X L. Visual haze removal by a unified generative adversarial network. IEEE Trans Circ Syst Video Tech, 2019, 29: 3211\u20133221","journal-title":"IEEE Trans Circ Syst Video Tech"},{"key":"2900_CR26","unstructured":"Mo S, Cho M, Shin J. InstaGAN: instance-aware image-to-image translation. In: Proceedings of International Conference on Learning Representations, 2019"},{"key":"2900_CR27","doi-asserted-by":"crossref","unstructured":"Zhu Z, Huang T T, Shi B G, et al. Progressive pose attention transfer for person image generation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019","DOI":"10.1109\/CVPR.2019.00245"},{"key":"2900_CR28","doi-asserted-by":"publisher","first-page":"120104","DOI":"10.1007\/s11432-019-2718-7","volume":"63","author":"Z J Zhang","year":"2020","unstructured":"Zhang Z J, Pang Y W. CGNet: cross-guidance network for semantic segmentation. Sci China Inf Sci, 2020, 63: 120104","journal-title":"Sci China Inf Sci"},{"key":"2900_CR29","doi-asserted-by":"publisher","first-page":"120105","DOI":"10.1007\/s11432-019-2737-0","volume":"63","author":"M H Liao","year":"2020","unstructured":"Liao M H, Song B Y, Long S B, et al. SynthText3D: synthesizing scene text images from 3D virtual worlds. Sci China Inf Sci, 2020, 63: 120105","journal-title":"Sci China Inf Sci"},{"key":"2900_CR30","doi-asserted-by":"crossref","unstructured":"Reed S, Akata Z, Lee H, et al. Learning deep representations of fine-grained visual descriptions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016. 49\u201358","DOI":"10.1109\/CVPR.2016.13"},{"key":"2900_CR31","doi-asserted-by":"crossref","unstructured":"Ji Z, Wang H R, Han J G, et al. Saliency-guided attention network for image-sentence matching. In: Proceedings of IEEE International Conference on Computer Vision, 2019","DOI":"10.1109\/ICCV.2019.00585"},{"key":"2900_CR32","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 IEEE Conference on Computer Vision and Pattern Recognition, 2019. 1505\u20131514","DOI":"10.1109\/CVPR.2019.00160"},{"key":"2900_CR33","unstructured":"Qiao T T, Zhang J, Xu D Q, et al. Learn, imagine and create: text-to-image generation from prior knowledge. In: Proceedings of Advances in Neural Information Processing Systems, 2019. 885\u2013895"},{"key":"2900_CR34","doi-asserted-by":"crossref","unstructured":"Li W B, Zhang P C, Zhang L, et al. Object-driven text-to-image synthesis via adversarial training. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019","DOI":"10.1109\/CVPR.2019.01245"},{"key":"2900_CR35","unstructured":"Huang Z H, Wang N Y. Like what you like: knowledge distill via neuron selectivity transfer. 2017. ArXiv: 1707.01219"},{"key":"2900_CR36","doi-asserted-by":"crossref","unstructured":"Yim J, Joo D, Bae J, et al. A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2017. 4133\u20134141","DOI":"10.1109\/CVPR.2017.754"},{"key":"2900_CR37","unstructured":"Romero A, Ballas N, Kahou S E, et al. Fitnets: hints for thin deep nets. 2014. ArXiv: 1412.6550"},{"key":"2900_CR38","unstructured":"Zagoruyko S, Komodakis N. Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. 2016. ArXiv: 1612.03928"},{"key":"2900_CR39","doi-asserted-by":"crossref","unstructured":"Gu X Q, Ma B P, Chang H, et al. Temporal knowledge propagation for image-to-video person re-identification. In: Proceedings of IEEE International Conference on Computer Vision, 2019. 9647\u20139656","DOI":"10.1109\/ICCV.2019.00974"},{"key":"2900_CR40","doi-asserted-by":"crossref","unstructured":"Yuan M K, Peng Y X. Text-to-image synthesis via symmetrical distillation networks. In: Proceedings of ACM International Conference on Multimedia, 2018","DOI":"10.1145\/3240508.3240559"},{"key":"2900_CR41","unstructured":"Chen Y T, Wang N Y, Zhang Z X. Darkrank: accelerating deep metric learning via cross sample similarities transfer. In: Proceedings of AAAI Conference on Artificial Intelligence, 2018"},{"key":"2900_CR42","unstructured":"Dauphin Y N, Fan A, Auli M, et al. Language modeling with gated convolutional networks. In: Proceedings of International Conference on Machine Learning, 2017. 933\u2013941"},{"key":"2900_CR43","unstructured":"Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations, 2015"},{"key":"2900_CR44","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016. 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"2900_CR45","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, et al. Imagenet: a large-scale hierarchical image database. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2009. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2900_CR46","unstructured":"Abadi M, Barham P, Chen J M, et al. Tensorflow: a system for large-scale machine learning. In: Proceedings of Symposium on Operating Systems Design and Implementation, 2016. 265\u2013283"},{"key":"2900_CR47","unstructured":"Reed S E, Akata Z, Mohan S, et al. Learning what and where to draw. In: Proceedings of Advances in Neural Information Processing Systems, 2016. 217\u2013225"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-2900-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-020-2900-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-2900-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T21:26:15Z","timestamp":1647984375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-020-2900-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,17]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["2900"],"URL":"https:\/\/doi.org\/10.1007\/s11432-020-2900-x","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,17]]},"assertion":[{"value":"21 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"120102"}}