{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:47Z","timestamp":1784268647460,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 62122018, No. 62020106008, No. U22A2097, No. U23A20315"],"award-info":[{"award-number":["Grant No. 62122018, No. 62020106008, No. U22A2097, No. U23A20315"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681516","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"8238-8246","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["MagicVFX: Visual Effects Synthesis in Just Minutes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3102-8406","authenticated-orcid":false,"given":"Jiaqi","family":"Guo","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3872-6689","authenticated-orcid":false,"given":"Junchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1973-4527","authenticated-orcid":false,"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5477-4741","authenticated-orcid":false,"given":"Siyang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681656"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548184"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.19512"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.09047"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2251642"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.10648"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612583"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser and et al. 2023. Structure and Content-Guided Video Synthesis with Diffusion Models. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.02087"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.09195"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2211.13221"},{"key":"e_1_3_2_1_14_1","volume-title":"Video Diffusion Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan, Mohammad Norouzi, and David J. Fleet. 2022. Video Diffusion Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/39235c56aef13fb05a6adc95eb9d8d66-Abstract-Conference.html"},{"key":"e_1_3_2_1_15_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Hong Wenyi","year":"2023","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 The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=rB6TpjAuSRy"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2925550"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.01107"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.05735"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.09711"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.04761"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/172"},{"key":"e_1_3_2_1_22_1","volume-title":"Deep-VFX: Deep Action Recognition Driven VFX for Short Video. CoRR","author":"Luo Ao","year":"2020","unstructured":"Ao Luo, Ning Xie, Zhijia Tao, and Feng Jiang. 2020. Deep-VFX: Deep Action Recognition Driven VFX for Short Video. CoRR, Vol. abs\/2007.11257 (2020). [arXiv]2007.11257 https:\/\/arxiv.org\/abs\/2007.11257"},{"key":"e_1_3_2_1_23_1","unstructured":"Chenlin Meng and et al. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_2_1_24_1","volume-title":"The 2017 DAVIS Challenge on Video Object Segmentation. CoRR","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbelaez, Alexander Sorkine-Hornung, and Luc Van Gool. 2017. The 2017 DAVIS Challenge on Video Object Segmentation. CoRR, Vol. abs\/1704.00675 (2017). [arXiv]1704.00675 http:\/\/arxiv.org\/abs\/1704.00675"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.12328"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.02936"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.08633"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916769"},{"key":"e_1_3_2_1_30_1","unstructured":"Xiang Wang and et al. 2023. VideoComposer: Compositional Video Synthesis with Motion Controllability. In NeurIPS."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.09091"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.15818"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.04145"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2211.11018"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681516","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":34,"alternative-id":["10.1145\/3664647.3681516","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681516","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}