{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:52:10Z","timestamp":1778806330894,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585471","type":"print"},{"value":"9783030585488","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58548-8_29","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T23:02:42Z","timestamp":1603926162000},"page":"491-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis"],"prefix":"10.1007","author":[{"given":"Jiadong","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"29_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis (2017)"},{"issue":"11","key":"29_CR3","doi-asserted-by":"publisher","first-page":"2750","DOI":"10.1109\/TMM.2019.2911457","volume":"21","author":"C Cao","year":"2019","unstructured":"Cao, C., Lu, F., Li, C., Lin, S., Shen, X.: Makeup removal via bidirectional tunable de-makeup network. IEEE Trans. Multimedia (TMM) 21(11), 2750\u20132761 (2019)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Cha, M., Gwon, Y., Kung, H.: Adversarial nets with perceptual losses for text-to-image synthesis. In: 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/MLSP.2017.8168140"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Cha, M., Gwon, Y.L., Kung, H.: Adversarial learning of semantic relevance in text to image synthesis. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 33, pp. 3272\u20133279 (2019)","DOI":"10.1609\/aaai.v33i01.33013272"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Das, R., Zaheer, M., Reddy, S., Mccallum, A.: Question answering on knowledge bases and text using universal schema and memory networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 358\u2013365 (2017)","DOI":"10.18653\/v1\/P17-2057"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Y., Zhang, S., Zhang, A., Wang, D., Abel, A.: Memory-augmented neural machine translation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1390\u20131399 (2017)","DOI":"10.18653\/v1\/D17-1146"},{"key":"29_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), pp. 2672\u20132680 (2014)"},{"key":"29_CR9","unstructured":"Hao, D., Yu, S., Chao, W., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5706\u20135714 (2017)"},{"key":"29_CR10","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Semantic object accuracy for generative text-to-image synthesis. arXiv:1910.13321 (2019)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"29_CR12","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"29_CR14","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Lao, Q., Havaei, M., Pesaranghader, A., Dutil, F., Jorio, L.D., Fevens, T.: Dual adversarial inference for text-to-image synthesis. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7567\u20137576 (2019)","DOI":"10.1109\/ICCV.2019.00766"},{"key":"29_CR16","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 2063\u20132073 (2019)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., You, S., Lu, F.: Unsupervised learning for intrinsic image decomposition from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3248\u20133257 (2020)","DOI":"10.1109\/CVPR42600.2020.00331"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lu, F.: Separate in latent space: unsupervised single image layer separation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 11661\u201311668 (2020)","DOI":"10.1609\/aaai.v34i07.6835"},{"key":"29_CR21","unstructured":"Lv, F., Lu, F.: Attention-guided low-light image enhancement. arXiv preprint arXiv:1908.00682 (2019)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Ma, C., Shen, C., Dick, A., Den Hengel, A.V.: Visual question answering with memory-augmented networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6975\u20136984 (2018)","DOI":"10.1109\/CVPR.2018.00729"},{"key":"29_CR23","unstructured":"Mansimov, E., Parisotto, E., Ba, J., Salakhutdinov, R.: Generating images from captions with attention. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Maruf, S., Haffari, G.: Document context neural machine translation with memory networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1275\u20131284 (2018)","DOI":"10.18653\/v1\/P18-1118"},{"key":"29_CR25","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Mohtarami, M., Baly, R., Glass, J., Nakov, P., M\u00e0rquez, L., Moschitti, A.: Automatic stance detection using end-to-end memory networks. arXiv preprint arXiv:1804.07581 (2018)","DOI":"10.18653\/v1\/N18-1070"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Niu, Y., et al.: Pathological evidence exploration in deep retinal image diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 33, pp. 1093\u20131101 (2019)","DOI":"10.1609\/aaai.v33i01.33011093"},{"key":"29_CR29","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34rd International Conference on Machine Learning (ICML), pp. 2642\u20132651 (2017)"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Pei, W., Zhang, J., Wang, X., Ke, L., Shen, X., Tai, Y.W.: Memory-attended recurrent network for video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8347\u20138356 (2019)","DOI":"10.1109\/CVPR.2019.00854"},{"key":"29_CR31","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: Learn, imagine and create: text-to-image generation from prior knowledge. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 885\u2013895 (2019)"},{"key":"29_CR32","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4321\u20134330 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"29_CR33","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"29_CR34","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: Proceedings of the 33rd International Conference on Machine Learning (ICML) (2016)"},{"key":"29_CR35","unstructured":"Reed, S., et al.: Parallel multiscale autoregressive density estimation. In: Proceedings of the 34rd International Conference on Machine Learning (ICML), pp. 2912\u20132921 (2017)"},{"key":"29_CR36","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in neural information processing systems (NIPS), pp. 2234\u20132242 (2016)"},{"key":"29_CR37","unstructured":"Reed, S., Van Den Oord, A., Kalchbrenner, N., Bapst, V., Botvinick, M., De Freitas, N.: Generating interpretable images with controllable structure. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"29_CR38","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 2440\u20132448 (2015)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Tan, L., Li, Y., Zhang, Y.: Semantics-enhanced adversarial nets for text-to-image synthesis. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 10501\u201310510 (2019)","DOI":"10.1109\/ICCV.2019.01060"},{"key":"29_CR40","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Wang, S., Mazumder, S., Liu, B., Zhou, M., Chang, Y.: Target-sensitive memory networks for aspect sentiment classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 957\u2013967 (2018)","DOI":"10.18653\/v1\/P18-1088"},{"key":"29_CR42","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Xu, T., 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 (CVPR), pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"29_CR44","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2327\u20132336 (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Yu, H., Cai, M., Liu, Y., Lu, F.: What I see is what you see: joint attention learning for first and third person video co-analysis. In: Proceedings of the 27th ACM International Conference on Multimedia (ACMMM), pp. 1358\u20131366 (2019)","DOI":"10.1145\/3343031.3350896"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, M., Peng, Y.: Bridge-GAN: interpretable representation learning for text-to-image synthesis. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) (2019)","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, M., Peng, Y.: CKD: cross-task knowledge distillation for text-to-image synthesis. IEEE Trans. Multimedia (TMM) (2019)","DOI":"10.1109\/TMM.2019.2951463"},{"key":"29_CR48","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: Proceedings of the 36rd International Conference on Machine Learning (ICML) (2019)"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"29_CR50","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 41(8), 1947\u20131962 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"29_CR52","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, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58548-8_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:11:48Z","timestamp":1730160708000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58548-8_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585471","9783030585488"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58548-8_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}