{"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":1780923298045,"version":"3.54.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72992-8_27","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"479-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["StoryImager: A Unified and\u00a0Efficient Framework for\u00a0Coherent Story Visualization and\u00a0Completion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7170","authenticated-orcid":false,"given":"Ming","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2077-1246","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"27_CR1","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Han, R., Wu, T.L., Nakayama, H., Peng, N.: Character-centric story visualization via visual planning and token alignment. arXiv preprint arXiv:2210.08465 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.565"},{"key":"27_CR3","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. NeurIPS (2021)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723 (2020)","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"27_CR6","unstructured":"Gong, Y., et al.: Talecrafter: interactive story visualization with multiple characters. arXiv preprint arXiv:2305.18247 (2023)"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"27_CR8","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":"27_CR9","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: NeurIPS (2017)"},{"key":"27_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"27_CR11","first-page":"47","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. JMLR 23, 47\u20131 (2022)","journal-title":"JMLR"},{"key":"27_CR12","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"27_CR13","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":"27_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-031-20059-5_20","volume-title":"ECCV 2022","author":"B Li","year":"2022","unstructured":"Li, B.: Word-level fine-grained story visualization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 347\u2013362. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_20"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Li, B., Torr, P.H., Lukasiewicz, T.: Clustering generative adversarial networks for story visualization. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 769\u2013778 (2022)","DOI":"10.1145\/3503161.3548034"},{"key":"27_CR16","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: 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":"27_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Wu, H., Zhong, Y., Zhang, X., Xie, W.: Intelligent grimm\u2013open-ended visual storytelling via latent diffusion models. arXiv preprint arXiv:2306.00973 (2023)","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning: prompt tuning can be comparable to fine-tuning across scales and tasks. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 61\u201368 (2022)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"27_CR20","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":"27_CR21","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":"27_CR22","doi-asserted-by":"crossref","unstructured":"Maharana, A., Hannan, D., Bansal, M.: Storydall-e: adapting pretrained text-to-image transformers for story continuation. arXiv preprint arXiv:2209.06192 (2022)","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"27_CR23","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S., Bossan, B.: PEFT: state-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"27_CR24","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)"},{"key":"27_CR25","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"27_CR26","unstructured":"Pan, X., Qin, P., Li, Y., Xue, H., Chen, W.: Synthesizing coherent story with auto-regressive latent diffusion models. arXiv preprint arXiv:2211.10950 (2022)"},{"issue":"8","key":"27_CR27","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"issue":"140","key":"27_CR28","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21(140), 1\u201367 (2020)","journal-title":"JMLR"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Rahman, T., Lee, H.Y., Ren, J., Tulyakov, S., Mahajan, S., Sigal, L.: Make-a-story: visual memory conditioned consistent story generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2493\u20132502 (2023)","DOI":"10.1109\/CVPR52729.2023.00246"},{"key":"27_CR30","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"27_CR31","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR33","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"27_CR34","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"27_CR35","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Song, T., Cao, J., Wang, K., Liu, B., Zhang, X.: Causal-story: local causal attention utilizing parameter-efficient tuning for visual story synthesis. arXiv preprint arXiv:2309.09553 (2023)","DOI":"10.1109\/ICASSP48485.2024.10446420"},{"key":"27_CR37","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":"27_CR38","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: Galip: generative adversarial clips for text-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Changsheng, X.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"27_CR41","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"27_CR43","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00595"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, J.: Cogcartoon: towards practical story visualization. arXiv preprint arXiv:2312.10718 (2023)","DOI":"10.1007\/s11263-024-02267-5"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72992-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:50:25Z","timestamp":1730191825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}