{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T23:35:07Z","timestamp":1773099307592,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585198","type":"print"},{"value":"9783030585204","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\/978-3-030-58520-4_2","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"18-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Character-Preserving Coherent Story Visualization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4542-8505","authenticated-orcid":false,"given":"Yun-Zhu","family":"Song","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9968-2416","authenticated-orcid":false,"given":"Zhi","family":"Rui Tam","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3129-1595","authenticated-orcid":false,"given":"Hung-Jen","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4630-2915","authenticated-orcid":false,"given":"Huiao-Han","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-077X","authenticated-orcid":false,"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"3272","DOI":"10.1609\/aaai.v33i01.33013272","volume":"33","author":"M Cha","year":"2019","unstructured":"Cha, M., Gwon, Y.L., Kung, H.: Adversarial learning of semantic relevance in text to image synthesis. Proceedings of the AAAI Conference on Artificial Intelligence. 33, 3272\u20133279 (2019)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Neural storyboard artist: Visualizing stories with coherent image sequences. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2236\u20132244 (2019)","DOI":"10.1145\/3343031.3350571"},{"key":"2_CR4","unstructured":"Cheng, Y., Gan, Z., Li, Y., Liu, J., Gao, J.: Sequential attention gan for interactive image editing via dialogue. arXiv preprint arXiv:1812.08352 (2018)"},{"key":"2_CR5","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. (2019)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Dandi, Y., Das, A., Singhal, S., Namboodiri, V., Rai, P.: Jointly trained image and video generation using residual vectors. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 3028\u20133042 (2020)","DOI":"10.1109\/WACV45572.2020.9093308"},{"key":"2_CR7","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":"2_CR8","doi-asserted-by":"crossref","unstructured":"El-Nouby, A., et al.: Tell, draw, and repeat: generating and modifying images based on continual linguistic instruction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10304\u201310312 (2019)","DOI":"10.1109\/ICCV.2019.01040"},{"key":"2_CR9","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/978-3-030-01228-1_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J He","year":"2018","unstructured":"He, J., Lehrmann, A., Marino, J., Mori, G., Sigal, L.: Probabilistic video generation using holistic attribute control. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 466\u2013483. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_28"},{"key":"2_CR11","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: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"2_CR12","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":"2_CR13","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321 (2019)"},{"key":"2_CR14","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, pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"2_CR15","unstructured":"Huang, T.H., et al.: Visual storytelling. In: HLT-NAACL (2016)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Kim, K.M., Heo, M.O., Choi, S.H., Zhang, B.T.: Deepstory: Video story qa by deep embedded memory networks. arXiv preprint arXiv:1707.00836 (2017)","DOI":"10.24963\/ijcai.2017\/280"},{"key":"2_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, pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Storygan: a sequential conditional GAN for story visualization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00649"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M.R., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"2_CR20","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. ArXiv abs\/1802.05957 (2018)"},{"key":"2_CR21","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 2642\u20132651. JMLR. org (2017)"},{"key":"2_CR22","unstructured":"Park, H., Yoo, Y., Kwak, N.: MC-GAN: multi-conditional generative adversarial network for image synthesis. In: The British MachineVision Conference (BMVC) (2018)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: Mirrorgan: learning text-to-image generation by redescription. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"2_CR24","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, pp. 2234\u20132242 (2016)"},{"key":"2_CR25","unstructured":"Sharma, S., Suhubdy, D., Michalski, V., Kahou, S.E., Bengio, Y.: Chatpainter: Improving text to image generation using dialogue. arXiv preprint arXiv:1802.08216 (2018)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2_CR27","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 International Conference on Computer Vision, pp. 10501\u201310510 (2019)","DOI":"10.1109\/ICCV.2019.01060"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2_CR30","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"2_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. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2322\u20132331 (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"2_CR32","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan++: Realistic image synthesis with stacked generative adversarial networks. arXiv: 1710.10916 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: ext to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"2_CR35","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 Conference on Computer Vision and Pattern Recognition, 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\/978-3-030-58520-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:15:10Z","timestamp":1731888910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58520-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585198","9783030585204"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58520-4_2","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":"19 November 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}