{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:54Z","timestamp":1765339794943,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3761991","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"13766-13770","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ACM Multimedia 2025 Grand Challenge report for Image-to-Video Generation Model Acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2856-2239","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"first","affiliation":[{"name":"Hunan University, Changsha, Hunan, China and MGTV, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0324-243X","authenticated-orcid":false,"given":"Shien","family":"Song","sequence":"additional","affiliation":[{"name":"MGTV, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7984-8054","authenticated-orcid":false,"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"MGTV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0171-4488","authenticated-orcid":false,"given":"Haoyuan","family":"Xie","sequence":"additional","affiliation":[{"name":"MGTV, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8206-873X","authenticated-orcid":false,"given":"Han","family":"Qi","sequence":"additional","affiliation":[{"name":"MGTV, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4443-4367","authenticated-orcid":false,"given":"Yifei","family":"Xue","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6284-1724","authenticated-orcid":false,"given":"Yizhen","family":"Lao","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"e_1_3_2_1_2_1","unstructured":"Kazuki Egashira Robin Staab Mark Vero Jingxuan He and Martin Vechev. 2025. Mind the Gap: A Practical Attack on GGUF Quantization. arXiv:2505.23786 [cs.CR] https:\/\/arxiv.org\/abs\/2505.23786"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser Johnathan Chiu Parmida Atighehchian Jonathan Granskog and Anastasis Germanidis. 2023. Structure and Content-Guided Video Synthesis with Diffusion Models. arXiv:2302.03011 [cs.CV] https:\/\/arxiv.org\/abs\/2302.03011","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_4_1","unstructured":"Xuan Ju Yiming Gao Zhaoyang Zhang Ziyang Yuan Xintao Wang Ailing Zeng Yu Xiong Qiang Xu and Ying Shan. 2024. MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions. arXiv:2407.06358 [cs.CV] https:\/\/arxiv.org\/abs\/2407.06358"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_6_1","volume-title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model. arXiv preprint arXiv:2411.19108","author":"Liu Feng","year":"2024","unstructured":"Feng Liu, Shiwei Zhang, Xiaofeng Wang, Yujie Wei, Haonan Qiu, Yuzhong Zhao, Yingya Zhang, Qixiang Ye, and Fang Wan. 2024. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model. arXiv preprint arXiv:2411.19108 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Yang Liu Hong Wang Lei Zhang and Xin Li. 2023. Quantization-Aware Training for Low-Latency Image-to-Video Generation. arXiv preprint arXiv:2311.16548."},{"key":"e_1_3_2_1_8_1","unstructured":"B. Graham N. Neverova A. Vedaldi N. Karaev I. Rocco and C. Rupprecht. 2021. Emerging properties in self-supervised vision transformers. In ICCV."},{"key":"e_1_3_2_1_9_1","unstructured":"OpenAI 2025. GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_10_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In ECCV.","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In ECCV."},{"key":"e_1_3_2_1_11_1","volume-title":"Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314","author":"Wan Team","year":"2025","unstructured":"Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, and Di Chen. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314 (2025)."},{"key":"e_1_3_2_1_12_1","unstructured":"Zhi Wang Hui Li Yu Chen Sen Zhang and Wei Liu. 2024. I2V-Accel: Efficient Image-to-Video Generation via Temporal-Aware Cache and Kernel Fusion. arXiv preprint arXiv:2403.12876."},{"key":"e_1_3_2_1_13_1","volume-title":"Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models. arXiv preprint arXiv:2412.09645","author":"Zhang Fan","year":"2024","unstructured":"Fan Zhang, Shulin Tian, Ziqi Huang, Yu Qiao, and Ziwei Liu. 2024. Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models. arXiv preprint arXiv:2412.09645 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Haofeng Huang, Pengle Zhang, Jia Wei, Jun Zhu, and Jianfei Chen. 2025. Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Jia Wei, Pengle Zhang, Jun Zhu, and Jianfei Chen. 2025. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, and Jianfei Chen. 2025. Spargeattn: Accurate sparse attention accelerating any model inference. In International Conference on Machine Learning (ICML)"}],"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\/3746027.3761991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:00Z","timestamp":1765339620000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3761991"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":16,"alternative-id":["10.1145\/3746027.3761991","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3761991","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"}}]}}