{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:37:29Z","timestamp":1778081849691,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":64,"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\/3664647.3681050","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"10572-10581","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["QVD: Post-training Quantization for Video Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9482-2577","authenticated-orcid":false,"given":"Shilong","family":"Tian","sequence":"first","affiliation":[{"name":"Beihang University & Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9658-0593","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9599-6557","authenticated-orcid":false,"given":"Chengtao","family":"Lv","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7599-612X","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1956-3367","authenticated-orcid":false,"given":"Jinyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-4195","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0994-5631","authenticated-orcid":false,"given":"Shengxi","family":"Li","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0871-7263","authenticated-orcid":false,"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1524-9505","authenticated-orcid":false,"given":"Tao","family":"Xie","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"2","article-title":"Conditional GAN with Discriminative Filter Generation for Text-to-Video Synthesis","volume":"1","author":"Balaji Yogesh","year":"2019","unstructured":"Yogesh Balaji, Martin Renqiang Min, Bing Bai, Rama Chellappa, and Hans Peter Graf. 2019. Conditional GAN with Discriminative Filter Generation for Text-to-Video Synthesis.. In IJCAI, Vol. 1. 2.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_2_1","volume-title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. arXiv preprint arXiv:2201.06503","author":"Bao Fan","year":"2022","unstructured":"Fan Bao, Chongxuan Li, Jun Zhu, and Bo Zhang. 2022. Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. arXiv preprint arXiv:2201.06503 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444943"},{"key":"e_1_3_2_1_4_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Hong Chen Chengtao Lv Liang Ding Haotong Qin Xiabin Zhou Yifu Ding Xuebo Liu Min Zhang Jinyang Guo Xianglong Liu et al. 2024. DB-LLM: Accurate Dual-Binarization for Efficient LLMs. arXiv preprint arXiv:2402.11960 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.516"},{"key":"e_1_3_2_1_7_1","volume-title":"Hung-Yu Tseng, Tsung-Yi Lin, and Ming-Hsuan Yang.","author":"Chen Tsai-Shien","year":"2023","unstructured":"Tsai-Shien Chen, Chieh Hubert Lin, Hung-Yu Tseng, Tsung-Yi Lin, and Ming-Hsuan Yang. 2023. Motion-conditioned diffusion model for controllable video synthesis. arXiv preprint arXiv:2304.14404 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Piotr Dollar, and C. Lawrence Zitnick","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, and C. Lawrence Zitnick. 2015. Microsoft COCO Captions: Data Collection and Evaluation Server. arxiv: 1504.00325 [cs.CV]"},{"key":"e_1_3_2_1_9_1","volume-title":"Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan.","author":"Choi Jungwook","year":"2018","unstructured":"Jungwook Choi, Zhuo Wang, Swagath Venkataramani, Pierce I-Jen Chuang, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_15"},{"key":"e_1_3_2_1_12_1","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016: 19th International Conference","author":"Ciccek \u00d6zg\u00fcn","year":"2016","unstructured":"\u00d6zg\u00fcn cCiccek, Ahmed Abdulkadir, Soeren S Lienkamp, Thomas Brox, and Olaf Ronneberger. 2016. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer, 424--432."},{"key":"e_1_3_2_1_13_1","volume-title":"Generative adversarial networks: An overview","author":"Creswell Antonia","year":"2018","unstructured":"Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A Bharath. 2018. Generative adversarial networks: An overview. IEEE signal processing magazine, Vol. 35, 1 (2018), 53--65."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_15_1","volume-title":"Learned step size quantization. arXiv preprint arXiv:1902.08153","author":"Esser Steven K","year":"2019","unstructured":"Steven K Esser, Jeffrey L McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S Modha. 2019. Learned step size quantization. arXiv preprint arXiv:1902.08153 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Structural pruning for diffusion models. Advances in neural information processing systems","author":"Fang Gongfan","year":"2024","unstructured":"Gongfan Fang, Xinyin Ma, and Xinchao Wang. 2024. Structural pruning for diffusion models. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Sparsectrl: Adding sparse controls to text-to-video diffusion models. arXiv preprint arXiv:2311.16933","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. Sparsectrl: Adding sparse controls to text-to-video diffusion models. arXiv preprint arXiv:2311.16933 (2023)."},{"key":"e_1_3_2_1_18_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Zhengyang Liang Yaohui Wang Yu Qiao Maneesh Agrawala Dahua Lin and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. arxiv: 2307.04725 [cs.CV]"},{"key":"e_1_3_2_1_19_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"He Yefei","year":"2024","unstructured":"Yefei He, Luping Liu, Jing Liu, Weijia Wu, Hong Zhou, and Bohan Zhuang. 2024. Ptqd: Accurate post-training quantization for diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Animate-a-story: Storytelling with retrieval-augmented video generation. arXiv preprint arXiv:2307.06940","author":"He Yingqing","year":"2023","unstructured":"Yingqing He, Menghan Xia, Haoxin Chen, Xiaodong Cun, Yuan Gong, Jinbo Xing, Yong Zhang, Xintao Wang, Chao Weng, Ying Shan, et al. 2023. Animate-a-story: Storytelling with retrieval-augmented video generation. arXiv preprint arXiv:2307.06940 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221","author":"He Yingqing","year":"2022","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:2211.13221 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_23_1","first-page":"8633","article-title":"Video diffusion models","volume":"35","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, and David J Fleet. 2022. Video diffusion models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 8633--8646.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117","author":"Hu Li","year":"2023","unstructured":"Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, and Liefeng Bo. 2023. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"Wei Huang Xingyu Zheng Xudong Ma Haotong Qin Chengtao Lv Hong Chen Jie Luo Xiaojuan Qi Xianglong Liu and Michele Magno. 2024. An Empirical Study of LLaMA3 Quantization: From LLMs to MLLMs. arxiv: 2404.14047 [cs.LG] https:\/\/arxiv.org\/abs\/2404.14047"},{"key":"e_1_3_2_1_27_1","volume-title":"Tfmq-dm: Temporal feature maintenance quantization for diffusion models. arXiv preprint arXiv:2311.16503","author":"Huang Yushi","year":"2023","unstructured":"Yushi Huang, Ruihao Gong, Jing Liu, Tianlong Chen, and Xianglong Liu. 2023. Tfmq-dm: Temporal feature maintenance quantization for diffusion models. arXiv preprint arXiv:2311.16503 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"e_1_3_2_1_30_1","volume-title":"Towards safe self-distillation of internet-scale text-to-image diffusion models. arXiv preprint arXiv:2307.05977","author":"Kim Sanghyun","year":"2023","unstructured":"Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, and Juho Lee. 2023. Towards safe self-distillation of internet-scale text-to-image diffusion models. arXiv preprint arXiv:2307.05977 (2023)."},{"key":"e_1_3_2_1_31_1","first-page":"28858","article-title":"Efficient spatially sparse inference for conditional gans and diffusion models","volume":"35","author":"Li Muyang","year":"2022","unstructured":"Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, and Jun-Yan Zhu. 2022. Efficient spatially sparse inference for conditional gans and diffusion models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 28858--28873.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"e_1_3_2_1_33_1","volume-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. 2021. Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021)."},{"key":"e_1_3_2_1_34_1","volume-title":"Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778","author":"Liu Luping","year":"2022","unstructured":"Luping Liu, Yi Ren, Zhijie Lin, and Zhou Zhao. 2022. Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778 (2022)."},{"key":"e_1_3_2_1_35_1","first-page":"5775","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Advances in Neural Information Processing Systems, Vol. 35 (2022), 5775--5787.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01509"},{"key":"e_1_3_2_1_37_1","volume-title":"Follow your pose: Pose-guided text-to-video generation using pose-free videos. arXiv preprint arXiv:2304.01186","author":"Ma Yue","year":"2023","unstructured":"Yue Ma, Yingqing He, Xiaodong Cun, Xintao Wang, Ying Shan, Xiu Li, and Qifeng Chen. 2023. Follow your pose: Pose-guided text-to-video generation using pose-free videos. arXiv preprint arXiv:2304.01186 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_2_1_39_1","volume-title":"Convolutional neural networks using logarithmic data representation. arXiv preprint arXiv:1603.01025","author":"Miyashita Daisuke","year":"2016","unstructured":"Daisuke Miyashita, Edward H Lee, and Boris Murmann. 2016. Convolutional neural networks using logarithmic data representation. arXiv preprint arXiv:1603.01025 (2016)."},{"key":"e_1_3_2_1_40_1","volume-title":"Yossi Matias, Yael Pritch, Yaniv Leviathan, and Yedid Hoshen.","author":"Molad Eyal","year":"2023","unstructured":"Eyal Molad, Eliahu Horwitz, Dani Valevski, Alex Rav Acha, Yossi Matias, Yael Pritch, Yaniv Leviathan, and Yedid Hoshen. 2023. Dreamix: Video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 7197--7206","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? adaptive rounding for post-training quantization. In International Conference on Machine Learning. PMLR, 7197--7206."},{"key":"e_1_3_2_1_42_1","volume-title":"Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort.","author":"Nagel Markus","year":"2021","unstructured":"Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295 (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"So Junhyuk","year":"2024","unstructured":"Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, and Eunhyeok Park. 2024. Temporal dynamic quantization for diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"International conference on machine learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_50_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_51_1","volume-title":"Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly.","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)."},{"key":"e_1_3_2_1_52_1","volume-title":"Disco: Disentangled control for realistic human dance generation. arXiv preprint arXiv:2307.00040","author":"Wang Tan","year":"2023","unstructured":"Tan Wang, Linjie Li, Kevin Lin, Yuanhao Zhai, Chung-Ching Lin, Zhengyuan Yang, Hanwang Zhang, Zicheng Liu, and Lijuan Wang. 2023. Disco: Disentangled control for realistic human dance generation. arXiv preprint arXiv:2307.00040 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Xiang","year":"2024","unstructured":"Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, and Jingren Zhou. 2024. Videocomposer: Compositional video synthesis with motion controllability. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103","author":"Wang Yaohui","year":"2023","unstructured":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, et al. 2023. Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"Qdrop: Randomly dropping quantization for extremely low-bit post-training quantization. arXiv preprint arXiv:2203.05740","author":"Wei Xiuying","year":"2022","unstructured":"Xiuying Wei, Ruihao Gong, Yuhang Li, Xianglong Liu, and Fengwei Yu. 2022. Qdrop: Randomly dropping quantization for extremely low-bit post-training quantization. arXiv preprint arXiv:2203.05740 (2022)."},{"key":"e_1_3_2_1_56_1","volume-title":"Outlier suppression: Accurate quantization of large language models by equivalent and optimal shifting and scaling. arXiv preprint arXiv:2304.09145","author":"Wei Xiuying","year":"2023","unstructured":"Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang, Ruihao Gong, Jinyang Guo, and Xianglong Liu. 2023. Outlier suppression: Accurate quantization of large language models by equivalent and optimal shifting and scaling. arXiv preprint arXiv:2304.09145 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Integer quantization for deep learning inference: Principles and empirical evaluation. arXiv preprint arXiv:2004.09602","author":"Wu Hao","year":"2020","unstructured":"Hao Wu, Patrick Judd, Xiaojie Zhang, Mikhail Isaev, and Paulius Micikevicius. 2020. Integer quantization for deep learning inference: Principles and empirical evaluation. arXiv preprint arXiv:2004.09602 (2020)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_59_1","volume-title":"Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, and Mike Zheng Shou.","author":"Xu Zhongcong","year":"2023","unstructured":"Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, and Mike Zheng Shou. 2023. MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model. arxiv: 2311.16498 [cs.CV]"},{"key":"e_1_3_2_1_60_1","volume-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory. arXiv preprint arXiv:2308.08089","author":"Yin Shengming","year":"2023","unstructured":"Shengming Yin, Chenfei Wu, Jian Liang, Jie Shi, Houqiang Li, Gong Ming, and Nan Duan. 2023. Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory. arXiv preprint arXiv:2308.08089 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2023","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2023. Show-1: Marrying pixel and latent diffusion models for text-to-video generation. arXiv preprint arXiv:2309.15818 (2023)."},{"key":"e_1_3_2_1_62_1","volume-title":"gddim: Generalized denoising diffusion implicit models. arXiv preprint arXiv:2206.05564","author":"Zhang Qinsheng","year":"2022","unstructured":"Qinsheng Zhang, Molei Tao, and Yongxin Chen. 2022. gddim: Generalized denoising diffusion implicit models. arXiv preprint arXiv:2206.05564 (2022)."},{"key":"e_1_3_2_1_63_1","volume-title":"Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018","author":"Zhou Daquan","year":"2022","unstructured":"Daquan Zhou, Weimin Wang, Hanshu Yan, Weiwei Lv, Yizhe Zhu, and Jiashi Feng. 2022. Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612707"}],"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\/3664647.3681050","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":64,"alternative-id":["10.1145\/3664647.3681050","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681050","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"}}]}}