{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:08:47Z","timestamp":1783094927688,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671850","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"1418-1427","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["LeMon: Automating Portrait Generation for Zero-Shot Story Visualization with Multi-Character Interactions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9916-1589","authenticated-orcid":false,"given":"Ziyi","family":"Kou","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-1506","authenticated-orcid":false,"given":"Shichao","family":"Pei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Massachusetts Boston, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-5665","authenticated-orcid":false,"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"A Neural Space-Time Representation for Text-to-Image Personalization. arXiv preprint arXiv:2305.15391","author":"Alaluf Yuval","year":"2023","unstructured":"Yuval Alaluf, Elad Richardson, Gal Metzer, and Daniel Cohen-Or. 2023. A Neural Space-Time Representation for Text-to-Image Personalization. arXiv preprint arXiv:2305.15391 (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"8: Co-Creating Visual Stories with Generative AI. arXiv preprint arXiv:2309.14228","author":"Antony Victor Nikhil","year":"2023","unstructured":"Victor Nikhil Antony and Chien-Ming Huang. 2023. ID. 8: Co-Creating Visual Stories with Generative AI. arXiv preprint arXiv:2309.14228 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"key":"e_1_3_2_2_4_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_2_5_1","volume-title":"TaleCrafter: Interactive Story Visualization with Multiple Characters. arXiv preprint arXiv:2305.18247","author":"Gong Yuan","year":"2023","unstructured":"Yuan Gong, Youxin Pang, Xiaodong Cun, Menghan Xia, Haoxin Chen, Longyue Wang, Yong Zhang, Xintao Wang, Ying Shan, and Yujiu Yang. 2023. TaleCrafter: Interactive Story Visualization with Multiple Characters. arXiv preprint arXiv:2305.18247 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Junyi Jessy Li, and Greg Durrett","author":"Goyal Tanya","year":"2022","unstructured":"Tanya Goyal, Junyi Jessy Li, and Greg Durrett. 2022. News summarization and evaluation in the era of gpt-3. arXiv preprint arXiv:2209.12356 (2022)."},{"key":"e_1_3_2_2_7_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0063998"},{"key":"e_1_3_2_2_9_1","volume-title":"Zero-shot generation of coherent storybook from plain text story using diffusion models. arXiv preprint arXiv:2302.03900","author":"Jeong Hyeonho","year":"2023","unstructured":"Hyeonho Jeong, Gihyun Kwon, and Jong Chul Ye. 2023. Zero-shot generation of coherent storybook from plain text story using diffusion models. arXiv preprint arXiv:2302.03900 (2023)."},{"key":"e_1_3_2_2_10_1","unstructured":"Ziyi Kou Shichao Pei Yijun Tian and Xiangliang Zhang. [n. d.]. Character as pixels: A controllable prompt adversarial attacking framework for black-box text guided image generation models."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_20"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548034"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"e_1_3_2_2_14_1","volume-title":"Intelligent Grimm--Open-ended Visual Storytelling via Latent Diffusion Models. arXiv preprint arXiv:2306.00973","author":"Liu Chang","year":"2023","unstructured":"Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, and Weidi Xie. 2023. Intelligent Grimm--Open-ended Visual Storytelling via Latent Diffusion Models. arXiv preprint arXiv:2306.00973 (2023)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"e_1_3_2_2_16_1","volume-title":"ELODIN: Naming Concepts in Embedding Spaces. arXiv preprint arXiv:2303.04001","author":"Mello Rodrigo","year":"2023","unstructured":"Rodrigo Mello, Filipe Calegario, and Geber Ramalho. 2023. ELODIN: Naming Concepts in Embedding Spaces. arXiv preprint arXiv:2303.04001 (2023)."},{"key":"e_1_3_2_2_17_1","volume-title":"Synthesizing coherent story with auto-regressive latent diffusion models. arXiv preprint arXiv:2211.10950","author":"Pan Xichen","year":"2022","unstructured":"Xichen Pan, Pengda Qin, Yuhong Li, Hui Xue, and Wenhu Chen. 2022. Synthesizing coherent story with auto-regressive latent diffusion models. arXiv preprint arXiv:2211.10950 (2022)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00290"},{"key":"e_1_3_2_2_19_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_20_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv: 2112.10752 [cs.CV]"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_22_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_2"},{"key":"e_1_3_2_2_24_1","volume-title":"Heng Tao Shen, and Jingkuan Song","author":"Su Sitong","year":"2023","unstructured":"Sitong Su, Litao Guo, Lianli Gao, Heng Tao Shen, and Jingkuan Song. 2023. Make-A-Storyboard: A General Framework for Storyboard with Disentangled and Merged Control. arXiv preprint arXiv:2312.07549 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"TinyLLM: Learning a Small Student from Multiple Large Language Models. arXiv preprint arXiv:2402.04616","author":"Tian Yijun","year":"2024","unstructured":"Yijun Tian, Yikun Han, Xiusi Chen, Wei Wang, and Nitesh V Chawla. 2024. TinyLLM: Learning a Small Student from Multiple Large Language Models. arXiv preprint arXiv:2402.04616 (2024)."},{"key":"e_1_3_2_2_26_1","unstructured":"Yijun Tian Chuxu Zhang Zhichun Guo Xiangliang Zhang and Nitesh V Chawla. 2023. Learning MLPs on Graphs: A Unified View of Effectiveness Robustness and Efficiency. In ICLR."},{"key":"e_1_3_2_2_27_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_28_1","unstructured":"Marilyn A Walker Grace I Lin Jennifer Sawyer et al. 2012. An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style.. In LREC. 1373--1378."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_2_30_1","volume-title":"Expel: Llm agents are experiential learners. arXiv preprint arXiv:2308.10144","author":"Zhao Andrew","year":"2023","unstructured":"Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2023. Expel: Llm agents are experiential learners. arXiv preprint arXiv:2308.10144 (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_2_32_1","volume-title":"Understanding adamw through proximal methods and scale-freeness. arXiv preprint arXiv:2202.00089","author":"Zhuang Zhenxun","year":"2022","unstructured":"Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, and Francesco Orabona. 2022. Understanding adamw through proximal methods and scale-freeness. arXiv preprint arXiv:2202.00089 (2022)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671850","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:14Z","timestamp":1750291454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":32,"alternative-id":["10.1145\/3637528.3671850","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671850","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}