{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:54:58Z","timestamp":1780923298226,"version":"3.54.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_20","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"347-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Word-Level Fine-Grained Story Visualization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2059-2544","authenticated-orcid":false,"given":"Bowen","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Balaji, Y., Min, M.R., Bai, B., Chellappa, R., Graf, H.P.: Conditional gan with discriminative filter generation for text-to-video synthesis. In: IJCAI, vol. 1, p. 2 (2019)","DOI":"10.24963\/ijcai.2019\/276"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5706\u20135714 (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"20_CR3","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwenk, D., Farhadi, A., Hoiem, D., Kembhavi, A.: Imagine this! scripts to compositions to videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 598\u2013613 (2018)","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"20_CR5","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":"20_CR6","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Semantic object accuracy for generative text-to-image synthesis. arXiv preprint. arXiv:1910.13321 (2019)"},{"key":"20_CR7","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":"20_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980 (2014)"},{"key":"20_CR9","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: Advances in Neural Information Processing Systems, pp. 2063\u20132073 (2019)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: ManiGAN: text-guided image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7880\u20137889 (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"20_CR11","unstructured":"Li, B., Qi, X., Torr, P., Lukasiewicz, T.: Image-to-image translation with text guidance. arXiv preprint. arXiv:2002.05235 (2020)"},{"key":"20_CR12","first-page":"22020","volume":"33","author":"B Li","year":"2020","unstructured":"Li, B., Qi, X., Torr, P., Lukasiewicz, T.: Lightweight generative adversarial networks for text-guided image manipulation. Adv. Neural. Inf. Process. Syst. 33, 22020\u201322031 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR13","unstructured":"Li, B., Torr, P., Lukasiewicz, T.: Memory-driven text-to-image generation (2021)"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Gan, Z., Shen, Y., Liu, J., Cheng, Y., Wu, Y., Carin, L., Carlson, D., Gao, J.: Storygan: a sequential conditional gan for story visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2019)","DOI":"10.1109\/CVPR.2019.00649"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Maharana, A., Bansal, M.: Integrating visuospatial, linguistic and commonsense structure into story visualization. arXiv preprint. arXiv:2110.10834 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Maharana, A., Hannan, D., Bansal, M.: Improving generation and evaluation of visual stories via semantic consistency. arXiv preprint. arXiv:2105.10026 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.194"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Mahon, L., Giunchiglia, E., Li, B., Lukasiewicz, T.: Knowledge graph extraction from videos. In: 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 25\u201332. IEEE (2020)","DOI":"10.1109\/ICMLA51294.2020.00014"},{"key":"20_CR19","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Text-adaptive generative adversarial networks: manipulating images with natural language. In: Advances in Neural Information Processing Systems, pp. 42\u201351 (2018)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Pan, Y., Qiu, Z., Yao, T., Li, H., Mei, T.: To create what you tell: generating videos from captions. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 1789\u20131798 (2017)","DOI":"10.1145\/3123266.3127905"},{"key":"20_CR21","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, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"20_CR22","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"20_CR23","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. arXiv preprint. arXiv:1605.05396 (2016)"},{"key":"20_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58520-4_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-Z Song","year":"2020","unstructured":"Song, Y.-Z., Rui Tam, Z., Chen, H.-J., Lu, H.-H., Shuai, H.-H.: Character-preserving coherent story visualization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 18\u201333. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_2"},{"key":"20_CR25","unstructured":"Tao, M., et al.: DF-GAN: deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint. arXiv:2008.05865 (2020)"},{"key":"20_CR26","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, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., Lee, H., Yang, Y.: Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 833\u2013842 (2021)","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"20_CR28","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, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.N.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligenc, vol. 41, no.8, pp. 1947\u20131962 (2018)","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"20_CR30","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"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Parikh, D.: Bringing semantics into focus using visual abstraction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3009\u20133016 (2013)","DOI":"10.1109\/CVPR.2013.387"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Parikh, D., Vanderwende, L.: Learning the visual interpretation of sentences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1681\u20131688 (2013)","DOI":"10.1109\/ICCV.2013.211"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:08:20Z","timestamp":1666973300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}