{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:30Z","timestamp":1765309530675,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813114208012"],"award-info":[{"award-number":["JCYJ20240813114208012"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425208,82441006,U22A2097,U23A20315,62122018,62020106008,62402094"],"award-info":[{"award-number":["62425208,82441006,U22A2097,U23A20315,62122018,62020106008,62402094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754864","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"9414-9423","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AICL: Action In-Context Learning for Text-to-Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0646-9523","authenticated-orcid":false,"given":"Jianzhi","family":"Liu","sequence":"first","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3872-6689","authenticated-orcid":false,"given":"Junchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Skywork AI, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. NeurIPS (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021","author":"Bain Max","year":"2021","unstructured":"Max Bain, Arsha Nagrani, G\u00fcl Varol, and Andrew Zisserman. 2021. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021."},{"key":"e_1_3_2_1_3_1","volume-title":"Visual prompting via image inpainting. NeurIPS","author":"Bar Amir","year":"2022","unstructured":"Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson, and Alexei Efros. 2022. Visual prompting via image inpainting. NeurIPS (2022)."},{"key":"e_1_3_2_1_4_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang Chao Weng and Ying Shan. 2023. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. arXiv:2310.19512 [cs.CV]"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Haoxin Chen Yong Zhang Xiaodong Cun Menghan Xia Xintao Wang Chao Weng and Ying Shan. 2024. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models. arXiv:2401.09047 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"e_1_3_2_1_6_1","volume-title":"Improving In-Context Few-Shot Learning via Self-Supervised Training. arXiv preprint arXiv:2205.01703","author":"Chen Mingda","year":"2022","unstructured":"Mingda Chen, Jingfei Du, Ramakanth Pasunuru, Todor Mihaylov, Srini Iyer, Veselin Stoyanov, and Zornitsa Kozareva. 2022. Improving In-Context Few-Shot Learning via Self-Supervised Training. arXiv preprint arXiv:2205.01703 (2022)."},{"key":"e_1_3_2_1_7_1","volume-title":"Shafiq Joty, Boyang Li, and Lidong Bing.","author":"Ding Bosheng","year":"2022","unstructured":"Bosheng Ding, Chengwei Qin, Linlin Liu, Yew Ken Chia, Shafiq Joty, Boyang Li, and Lidong Bing. 2022a. Is gpt-3 a good data annotator? arXiv preprint arXiv:2212.10450 (2022)."},{"key":"e_1_3_2_1_8_1","unstructured":"Ming Ding Wendi Zheng Wenyi Hong and Jie Tang. 2022b. CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers. In NeurIPS."},{"key":"e_1_3_2_1_9_1","volume-title":"Pre-Training to Learn in Context. arXiv preprint arXiv:2305.09137","author":"Gu Yuxian","year":"2023","unstructured":"Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. 2023. Pre-Training to Learn in Context. arXiv preprint arXiv:2305.09137 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths. CoRR","author":"He Yingqing","year":"2022","unstructured":"Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, and Qifeng Chen. 2022. Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths. CoRR (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"Imagen Video: High Definition Video Generation with Diffusion Models. arXiv preprint arXiv:2210.02303","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, William Chan, Chitwan Saharia, Jay Whang, Ruiqi Gao, Alexey A. Gritsenko, Diederik P. Kingma, Ben Poole, Mohammad Norouzi, David J. Fleet, and Tim Salimans. 2022a. Imagen Video: High Definition Video Generation with Diffusion Models. arXiv preprint arXiv:2210.02303 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_14_1","unstructured":"Jonathan Ho Chitwan Saharia William Chan David J. Fleet Mohammad Norouzi and Tim Salimans. 2022b. Cascaded Diffusion Models for High Fidelity Image Generation. J. Mach. Learn. Res. (2022)."},{"volume-title":"NeurIPS","author":"Ho Jonathan","key":"e_1_3_2_1_15_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. In NeurIPS, Vol. abs\/2207.12598."},{"key":"e_1_3_2_1_16_1","unstructured":"Wenyi Hong Ming Ding Wendi Zheng Xinghan Liu and Jie Tang. 2023. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. In ICLR."},{"key":"e_1_3_2_1_17_1","volume-title":"Qiang Liu, et al.","author":"Huang Shaohan","year":"2023","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Qiang Liu, et al., 2023. Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics.","author":"Isabelle Pierre","year":"2002","unstructured":"Pierre Isabelle, Eugene Charniak, and Dekang Lin. 2002. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_19_1","volume-title":"Improving image generation with better captions. https:\/\/cdn. openai. com\/papers\/dall-e-3","author":"James Betker","year":"2023","unstructured":"Betker James, Goh Gabriel, Jing Li, Brooks Tim, Wang Jianfeng, Li Linjie, Ouyang Long, Zhuang Juntang, Lee\u2020 Joyce, Guo Yufei, Manassra Wesam, Dhariwal Prafulla, Chu Casey, Jiao Yunxin, and Ramesh Aditya. 2023. Improving image generation with better captions. https:\/\/cdn. openai. com\/papers\/dall-e-3 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Finding supporting examples for in-context learning. arXiv preprint arXiv:2302.13539","author":"Li Xiaonan","year":"2023","unstructured":"Xiaonan Li and Xipeng Qiu. 2023. Finding supporting examples for in-context learning. arXiv preprint arXiv:2302.13539 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Teaching small language models to reason. arXiv preprint arXiv:2212.08410","author":"Magister Lucie Charlotte","year":"2022","unstructured":"Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn. 2022. Teaching small language models to reason. arXiv preprint arXiv:2212.08410 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943","author":"Min Sewon","year":"2021","unstructured":"Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2021. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Findings of the association for computational linguistics: Emnlp","author":"Moens Marie Francine","year":"2021","unstructured":"Marie Francine Moens, Xuan-Jing Huang, Lucia Specia, and Wen-tau Yih. 2021. Findings of the association for computational linguistics: Emnlp 2021. In EMNLP."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CultureComputing.2013.44"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2023. GPT-4: Generative Pre-trained Transformer 4. https:\/\/openai.com\/gpt-4\/."},{"key":"e_1_3_2_1_26_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633","author":"Rubin Ohad","year":"2021","unstructured":"Ohad Rubin, Jonathan Herzig, and Jonathan Berant. 2021. Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","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. NeurIPS (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASIANCON58793.2023.10270304"},{"key":"e_1_3_2_1_31_1","unstructured":"Jascha Sohl-Dickstein Eric A. Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In ICML Francis R. Bach and David M. Blei (Eds.)."},{"key":"e_1_3_2_1_32_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_33_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR (2012)."},{"key":"e_1_3_2_1_34_1","volume-title":"Exploring Effective Factors for Improving Visual In-Context Learning. arXiv preprint arXiv:2304.04748","author":"Sun Yanpeng","year":"2023","unstructured":"Yanpeng Sun, Qiang Chen, Jian Wang, Jingdong Wang, and Zechao Li. 2023. Exploring Effective Factors for Improving Visual In-Context Learning. arXiv preprint arXiv:2304.04748 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Multimodal few-shot learning with frozen language models. NeurIPS","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. NeurIPS (2021)."},{"key":"e_1_3_2_1_36_1","volume-title":"Towards Accurate Generative Models of Video: A New Metric & Challenges. CoRR","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Rapha\u00ebl Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards Accurate Generative Models of Video: A New Metric & Challenges. CoRR (2018)."},{"key":"e_1_3_2_1_37_1","first-page":"5998","article-title":"Attention is All you Need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998-6008.","journal-title":"NeurIPS."},{"key":"e_1_3_2_1_38_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023c. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation. arXiv preprint arXiv:2305.10874","author":"Wang Wenjing","year":"2023","unstructured":"Wenjing Wang, Huan Yang, Zixi Tuo, Huiguo He, Junchen Zhu, Jianlong Fu, and Jiaying Liu. 2023b. VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation. arXiv preprint arXiv:2305.10874 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Xinlong Wang Wen Wang Yue Cao Chunhua Shen and Tiejun Huang. 2023a. Images speak in images: A generalist painter for in-context visual learning. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"e_1_3_2_1_41_1","volume-title":"VideoComposer: Compositional Video Synthesis with Motion Controllability. arXiv preprint arXiv:2306.02018","author":"Wang Xiang","year":"2023","unstructured":"Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023d. VideoComposer: Compositional Video Synthesis with Motion Controllability. arXiv preprint arXiv:2306.02018 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Atharva Naik, David Stap, et al.","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, et al., 2022. Super-naturalinstructions: Generalization via declarative instructions on 1600 nlp tasks. arXiv preprint arXiv:2204.07705 (2022)."},{"key":"e_1_3_2_1_43_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Jerry Wei Le Hou Andrew Lampinen Xiangning Chen Da Huang Yi Tay Xinyun Chen Yifeng Lu Denny Zhou Tengyu Ma et al. 2023. Symbol tuning improves in-context learning in language models. arXiv preprint arXiv:2305.08298 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.61"},{"volume-title":"Phrases and Philosophies for the Use of the Young","author":"Wilde Oscar","key":"e_1_3_2_1_45_1","unstructured":"Oscar Wilde. 1894. Phrases and Philosophies for the Use of the Young. Publisher."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_47_1","volume-title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:2212.11565","author":"Wu Jay Zhangjie","year":"2022","unstructured":"Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Weixian Lei, Yuchao Gu, Wynne Hsu, Ying Shan, Xiaohu Qie, and Mike Zheng Shou. 2022. Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:2212.11565 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"k NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference. arXiv preprint arXiv:2303.13824","author":"Xu Benfeng","year":"2023","unstructured":"Benfeng Xu, Quan Wang, Zhendong Mao, Yajuan Lyu, Qiaoqiao She, and Yongdong Zhang. 2023a. k NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference. arXiv preprint arXiv:2303.13824 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Small models are valuable plug-ins for large language models. arXiv preprint arXiv:2305.08848","author":"Xu Canwen","year":"2023","unstructured":"Canwen Xu, Yichong Xu, Shuohang Wang, Yang Liu, Chenguang Zhu, and Julian McAuley. 2023b. Small models are valuable plug-ins for large language models. arXiv preprint arXiv:2305.08848 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Enabling the Encoder-Empowered GAN-based Video Generators for Long Video Generation. In 2023 IEEE International Conference on Image Processing (ICIP). IEEE, 1425-1429","author":"Yang Jingbo","year":"2023","unstructured":"Jingbo Yang and Adrian G Bors. 2023. Enabling the Encoder-Empowered GAN-based Video Generators for Long Video Generation. In 2023 IEEE International Conference on Image Processing (ICIP). IEEE, 1425-1429."},{"key":"e_1_3_2_1_51_1","volume-title":"What Makes Good Examples for Visual In-Context Learning? arXiv preprint arXiv:2301.13670","author":"Zhang Yuanhan","year":"2023","unstructured":"Yuanhan Zhang, Kaiyang Zhou, and Ziwei Liu. 2023. What Makes Good Examples for Visual In-Context Learning? arXiv preprint arXiv:2301.13670 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models. CoRR","author":"Zhou Daquan","year":"2022","unstructured":"Daquan Zhou, Weimin Wang, Hanshu Yan, Weiwei Lv, Yizhe Zhu, and Jiashi Feng. 2022. MagicVideo: Efficient Video Generation With Latent Diffusion Models. CoRR (2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images. arXiv preprint arXiv:2306.07257","author":"Zhu Junchen","year":"2023","unstructured":"Junchen Zhu, Huan Yang, Huiguo He, Wenjing Wang, Zixi Tuo, Wen-Huang Cheng, Lianli Gao, Jingkuan Song, and Jianlong Fu. 2023. MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images. arXiv preprint arXiv:2306.07257 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:01Z","timestamp":1765309261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3754864","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754864","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}