{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:28Z","timestamp":1765008868311,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770948","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3731-3180","authenticated-orcid":false,"given":"Qi","family":"Xie","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0070-4134","authenticated-orcid":false,"given":"Yongjia","family":"Ma","sequence":"additional","affiliation":[{"name":"Li Auto, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2270-3378","authenticated-orcid":false,"given":"Donglin","family":"Di","sequence":"additional","affiliation":[{"name":"Li Auto, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-5770","authenticated-orcid":false,"given":"Xuehao","family":"Gao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et\u00a0al. 2023. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19512 (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"e_1_3_3_2_4_2","unstructured":"Junsong Chen Jincheng Yu Chongjian Ge Lewei Yao Enze Xie Yue Wu Zhongdao Wang James Kwok Ping Luo Huchuan Lu et\u00a0al. 2023. Pixart-\u03b1 : Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.00426 (2023)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_3_2_6_2","unstructured":"Donglin Di He Feng Wenzhang Sun Yongjia Ma Hao Li Wei Chen Xiaofei Gou Tonghua Su and Xun Yang. 2024. FaceVid-1K: A Large-Scale High-Quality Multiracial Human Face Video Dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.07151 (2024)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_3_2_8_2","unstructured":"Zhengcong Fei Debang Li Di Qiu Changqian Yu and Mingyuan Fan. 2025. Ingredients: Blending Custom Photos with Video Diffusion Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.01790 (2025)."},{"key":"e_1_3_3_2_9_2","unstructured":"He Feng Yongjia Ma Donglin Di Lei Fan Tonghua Su and Xiangqian Wu. 2025. DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.06511 (2025)."},{"key":"e_1_3_3_2_10_2","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Yaohui Wang Yu Qiao Dahua Lin and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.04725 (2023)."},{"key":"e_1_3_3_2_11_2","unstructured":"Zinan Guo Yanze Wu Zhuowei Chen Lang Chen and Qian He. 2024. PuLID: Pure and Lightning ID Customization via Contrastive Alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.16022 (2024)."},{"key":"e_1_3_3_2_12_2","unstructured":"Xuanhua He Quande Liu Shengju Qian Xin Wang Tao Hu Ke Cao Keyu Yan Man Zhou and Jie Zhang. 2024. ID-Animator: Zero-Shot Identity-Preserving Human Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.15275 (2024)."},{"key":"e_1_3_3_2_13_2","unstructured":"Yingqing He Tianyu Yang Yong Zhang Ying Shan and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.13221 (2022)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Jack Hessel Ari Holtzman Maxwell Forbes Ronan\u00a0Le Bras and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.08718 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_3_2_15_2","unstructured":"Jonathan Ho William Chan Chitwan Saharia Jay Whang Ruiqi Gao Alexey Gritsenko Diederik\u00a0P Kingma Ben Poole Mohammad Norouzi David\u00a0J Fleet et\u00a0al. 2022. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02303 (2022)."},{"key":"e_1_3_3_2_16_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_17_2","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022. Video diffusion models."},{"key":"e_1_3_3_2_18_2","unstructured":"Wenyi Hong Ming Ding Wendi Zheng Xinghan Liu and Jie Tang. 2022. Cogvideo: Large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.15868 (2022)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_20_2","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_2_21_2","unstructured":"Hengjia Li Lifan Jiang Xi Xiao Tianyang Wang Hongwei Yi Boxi Wu and Deng Cai. 2025. MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.12689 (2025)."},{"key":"e_1_3_3_2_22_2","unstructured":"Hengjia Li Haonan Qiu Shiwei Zhang Xiang Wang Yujie Wei Zekun Li Yingya Zhang Boxi Wu and Deng Cai. 2024. PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17048 (2024)."},{"key":"e_1_3_3_2_23_2","unstructured":"Zhimin Li Jianwei Zhang Qin Lin Jiangfeng Xiong Yanxin Long Xinchi Deng Yingfang Zhang Xingchao Liu Minbin Huang Zedong Xiao et\u00a0al. 2024. Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.08748 (2024)."},{"key":"e_1_3_3_2_24_2","unstructured":"Bin Lin Yunyang Ge Xinhua Cheng Zongjian Li Bin Zhu Shaodong Wang Xianyi He Yang Ye Shenghai Yuan Liuhan Chen et\u00a0al. 2024. Open-sora plan: Open-source large video generation model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.00131 (2024)."},{"key":"e_1_3_3_2_25_2","unstructured":"Yixin Liu Kai Zhang Yuan Li Zhiling Yan Chujie Gao Ruoxi Chen Zhengqing Yuan Yue Huang Hanchi Sun Jianfeng Gao et\u00a0al. 2024. Sora: A review on background technology limitations and opportunities of large vision models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17177 (2024)."},{"key":"e_1_3_3_2_26_2","unstructured":"Yongjia Ma Junlin Chen Donglin Di Qi Xie Lei Fan Wei Chen Xiaofei Gou Na Zhao and Xun Yang. 2025. Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.05484 (2025)."},{"key":"e_1_3_3_2_27_2","unstructured":"Yongjia Ma Donglin Di Xuan Liu Xiaokai Chen Lei Fan Wei Chen and Tonghua Su. 2025. Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.16522 (2025)."},{"key":"e_1_3_3_2_28_2","unstructured":"Ze Ma Daquan Zhou Chun-Hsiao Yeh Xue-She Wang Xiuyu Li Huanrui Yang Zhen Dong Kurt Keutzer and Jiashi Feng. 2024. Magic-me: Identity-specific video customized diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.09368 (2024)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Arsha Nagrani Joon\u00a0Son Chung and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.08612 (2017).","DOI":"10.21437\/Interspeech.2017-950"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15063"},{"key":"e_1_3_3_2_32_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_2_33_2","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.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_3_2_36_2","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et\u00a0al. 2024. Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12191 (2024)."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Zhen Xing Qijun Feng Haoran Chen Qi Dai Han Hu Hang Xu Zuxuan Wu and Yu-Gang Jiang. 2024. A survey on video diffusion models. Comput. Surveys 57 2 (2024) 1\u201342.","DOI":"10.1145\/3696415"},{"key":"e_1_3_3_2_39_2","unstructured":"Jiahui Yang Yongjia Ma Donglin Di Hao Li Wei Chen Yan Xie Jianxun Cui Xun Yang and Wangmeng Zuo. 2025. QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.04599 (2025)."},{"key":"e_1_3_3_2_40_2","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_2_41_2","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06721 (2023)."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Shenghai Yuan Jinfa Huang Xianyi He Yunyuan Ge Yujun Shi Liuhan Chen Jiebo Luo and Li Yuan. 2024. Identity-Preserving Text-to-Video Generation by Frequency Decomposition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17440 (2024).","DOI":"10.32388\/TZIID6"},{"key":"e_1_3_3_2_43_2","unstructured":"Yuechen Zhang Yaoyang Liu Bin Xia Bohao Peng Zexin Yan Eric Lo and Jiaya Jia. 2025. Magic Mirror: ID-Preserved Video Generation in Video Diffusion Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03931 (2025)."},{"key":"e_1_3_3_2_44_2","unstructured":"Yunpeng Zhang Qiang Wang Fan Jiang Yaqi Fan Mu Xu and Yonggang Qi. 2025. FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13995 (2025)."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"e_1_3_3_2_46_2","unstructured":"Zangwei Zheng Xiangyu Peng Tianji Yang Chenhui Shen Shenggui Li Hongxin Liu Yukun Zhou Tianyi Li and Yang You. 2024. Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.20404 (2024)."},{"key":"e_1_3_3_2_47_2","unstructured":"Yong Zhong Zhuoyi Yang Jiayan Teng Xiaotao Gu and Chongxuan Li. 2025. Concat-ID: Towards Universal Identity-Preserving Video Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.14151 (2025)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:45Z","timestamp":1765008645000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":47,"alternative-id":["10.1145\/3743093.3770948","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770948","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}