{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:20:22Z","timestamp":1791912022481,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":9,"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:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681464","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T02:59:33Z","timestamp":1729911573000},"page":"3907-3916","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2079-4931","authenticated-orcid":false,"given":"Zhanyu","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9062-6183","authenticated-orcid":false,"given":"Longyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0796-4078","authenticated-orcid":false,"given":"Zhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5717-9318","authenticated-orcid":false,"given":"Minghao","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6733-5879","authenticated-orcid":false,"given":"Chenyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-8648","authenticated-orcid":false,"given":"Huayang","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7717-6990","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-2424","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1712-5619","authenticated-orcid":false,"given":"Shuming","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7900-6055","authenticated-orcid":false,"given":"Zhaopeng","family":"Tu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"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. In NeurIPS."},{"key":"e_1_3_2_1_2_1","volume-title":"Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation. CoRR","author":"An Jie","year":"2023","unstructured":"Jie An, Songyang Zhang, Harry Yang, Sonal Gupta, Jia-Bin Huang, Jiebo Luo, and Xi Yin. 2023. Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation. CoRR (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","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 ICCV. 1708--1718.","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_5_1","volume-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In ACL. 65--72.","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In ACL. 65--72."},{"key":"e_1_3_2_1_6_1","volume":"202","author":"Ceylan Duygu","unstructured":"Duygu Ceylan, Chun-Hao P Huang, and Niloy J Mitra. 2023. Pix2video: Video editing using image diffusion. In ICCV. 23206--23217.","journal-title":"Niloy J Mitra."},{"key":"e_1_3_2_1_7_1","unstructured":"David Chen and William B Dolan. 2011. Collecting highly parallel data for paraphrase evaluation. In ACL. 190--200."},{"key":"e_1_3_2_1_8_1","volume-title":"ALLaVA: Harnessing GPT4V-synthesized Data for A Lite Vision-Language Model. arXiv preprint arXiv:2402.11684","author":"Chen Guiming Hardy","year":"2024","unstructured":"Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, and Benyou Wang. 2024. ALLaVA: Harnessing GPT4V-synthesized Data for A Lite Vision-Language Model. arXiv preprint arXiv:2402.11684 (2024)."},{"key":"e_1_3_2_1_9_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."}],"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\/3664647.3681464","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:57:47Z","timestamp":1750280267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":9,"alternative-id":["10.1145\/3664647.3681464","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681464","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"}}]}}