{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:14:52Z","timestamp":1768436092328,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":14,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3684992","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11261-11263","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MAF-ID: Multi-Agent Framework for Interactive Dubbing through Deep Video Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4719-8356","authenticated-orcid":false,"given":"Zhanbin","family":"Hu","sequence":"first","affiliation":[{"name":"Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2387-9853","authenticated-orcid":false,"given":"Xiaodong","family":"He","sequence":"additional","affiliation":[{"name":"Wenzhou Institute of Industry and Science, Wenzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6821-1182","authenticated-orcid":false,"given":"Renzhou","family":"Pan","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9833-5372","authenticated-orcid":false,"given":"Xianzhou","family":"Zeng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0915-7860","authenticated-orcid":false,"given":"Chenming","family":"Fan","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2405-6776","authenticated-orcid":false,"given":"Qiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman Clarence Ng Ricky Wang and Aditya Ramesh. 2024. Video generation models as world simulators. (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"e_1_3_2_2_2_1","volume-title":"Sheng Zheng, Jingyao Zheng, Lik-Hang Lee, Tae-Ho Kim, Choong Seon Hong, and Chaoning Zhang.","author":"Cho Joseph","year":"2024","unstructured":"Joseph Cho, Fachrina Dewi Puspitasari, Sheng Zheng, Jingyao Zheng, Lik-Hang Lee, Tae-Ho Kim, Choong Seon Hong, and Chaoning Zhang. 2024. Sora as an agi world model? a complete survey on text-to-video generation. arXiv preprint arXiv:2403.05131 (2024)."},{"key":"e_1_3_2_2_3_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Copet Jade","year":"2024","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre D\u00e9fossez. 2024. Simple and controllable music generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_4_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10414-6"},{"key":"e_1_3_2_2_7_1","unstructured":"Suno Team. 2024. Suno AI. https:\/\/suno.com. Accessed: 2024-06-01."},{"key":"e_1_3_2_2_8_1","unstructured":"Udio Team. 2024. Udio AI Music Generator. https:\/\/www.udio.com. Accessed: 2024-06-01."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_2_10_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824--24837."},{"key":"e_1_3_2_2_11_1","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864 (2023)."},{"key":"e_1_3_2_2_12_1","volume-title":"A survey on multimodal large language models. arXiv preprint arXiv:2306.13549","author":"Yin Shukang","year":"2023","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2023. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)."},{"key":"e_1_3_2_2_13_1","unstructured":"Zangwei Zheng Xiangyu Peng and Yang You. 2024. Open-Sora: Democratizing Efficient Video Production for All. https:\/\/github.com\/hpcaitech\/Open-Sora"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29946"}],"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\/3664647.3684992","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3684992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3684992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":14,"alternative-id":["10.1145\/3664647.3684992","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3684992","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"}}]}}