{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:59:40Z","timestamp":1765342780028,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62231022"],"award-info":[{"award-number":["62231022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Research Team for Communication and Sensing Integrated with Intelligent Computing","award":["2024KCXTD047"],"award-info":[{"award-number":["2024KCXTD047"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2108085UD12"],"award-info":[{"award-number":["2108085UD12"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755650","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"10408-10417","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8880-279X","authenticated-orcid":false,"given":"Zichao","family":"Yu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7244-1565","authenticated-orcid":false,"given":"Zhen","family":"Zou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, HeFei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3053-773X","authenticated-orcid":false,"given":"Guojiang","family":"Shao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4393-8787","authenticated-orcid":false,"given":"Chenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3274-519X","authenticated-orcid":false,"given":"Shengze","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3518-3404","authenticated-orcid":false,"given":"Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-8105","authenticated-orcid":false,"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3607-2236","authenticated-orcid":false,"given":"Xiaodong","family":"Cun","sequence":"additional","affiliation":[{"name":"Great Bay University, Dongguan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4227-0749","authenticated-orcid":false,"given":"Wenyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"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\/CVPRW50498.2020.00356"},{"volume-title":"Numerical methods for ordinary differential equations","author":"Butcher John Charles","key":"e_1_3_2_1_2_1","unstructured":"John Charles Butcher. 2016. Numerical methods for ordinary differential equations. John Wiley & Sons."},{"key":"e_1_3_2_1_3_1","volume-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426","author":"Chen Junsong","year":"2023","unstructured":"Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al., 2023. Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"\u0394 -DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125","author":"Chen Pengtao","year":"2024","unstructured":"Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, and Tao Chen. 2024. \u0394 -DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Dong Xin","year":"2017","unstructured":"Xin Dong, Shangyu Chen, and Sinno Pan. 2017. Learning to prune deep neural networks via layer-wise optimal brain surgeon. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_6_1","first-page":"41914","article-title":"One-step diffusion distillation via deep equilibrium models","volume":"36","author":"Geng Zhengyang","year":"2023","unstructured":"Zhengyang Geng, Ashwini Pokle, and J Zico Kolter. 2023. One-step diffusion distillation via deep equilibrium models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 41914-41931.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_2_1_8_1","volume-title":"Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103","author":"HaCohen Yoav","year":"2024","unstructured":"Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, et al., 2024. Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"Ernst Hairer. 1993. SP N rsett and G. Wanner. Solving ordinary differential equations I Nonsti problems."},{"key":"e_1_3_2_1_10_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_11_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26565-26577.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","unstructured":"Bo-Kyeong Kim Hyoung-Kyu Song Thibault Castells and Shinkook Choi. 2023. On architectural compression of text-to-image diffusion models. (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603","author":"Kong Weijie","year":"2024","unstructured":"Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, et al., 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"A signal propagation perspective for pruning neural networks at initialization. arXiv preprint arXiv:1906.06307","author":"Lee Namhoon","year":"2019","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, and Philip HS Torr. 2019. A signal propagation perspective for pruning neural networks at initialization. arXiv preprint arXiv:1906.06307 (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00654"},{"key":"e_1_3_2_1_17_1","volume-title":"Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, and Jian Yang.","author":"Li Senmao","year":"2023","unstructured":"Senmao Li, Taihang Hu, Fahad Shahbaz Khan, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, and Jian Yang. 2023a. Faster diffusion: Rethinking the role of unet encoder in diffusion models. CoRR (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 21915-21936","author":"Liu Enshu","year":"2023","unstructured":"Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, and Yu Wang. 2023a. Oms-dpm: Optimizing the model schedule for diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 21915-21936."},{"key":"e_1_3_2_1_20_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. 2024b. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model. arXiv preprint arXiv:2411.19108 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Audioldm 2: Learning holistic audio generation with self-supervised pretraining","author":"Liu Haohe","year":"2024","unstructured":"Haohe Liu, Yi Yuan, Xubo Liu, Xinhao Mei, Qiuqiang Kong, Qiao Tian, Yuping Wang, Wenwu Wang, Yuxuan Wang, and Mark D Plumbley. 2024a. Audioldm 2: Learning holistic audio generation with self-supervised pretraining. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 7021-7032","author":"Liu Liyang","year":"2021","unstructured":"Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou, Jing-Hao Xue, Xinjiang Wang, Yimin Chen, Wenming Yang, Qingmin Liao, and Wayne Zhang. 2021. Group fisher pruning for practical network compression. In International Conference on Machine Learning. PMLR, 7021-7032."},{"key":"e_1_3_2_1_23_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Liu Xingchao","year":"2023","unstructured":"Xingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng, et al., 2023b. Instaflow: One step is enough for high-quality diffusion-based text-to-image generation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_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. 2022a. 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_25_1","volume-title":"Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022b. Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)."},{"key":"e_1_3_2_1_26_1","volume-title":"Fastercache: Training-free video diffusion model acceleration with high quality. arXiv preprint arXiv:2410.19355","author":"Lv Zhengyao","year":"2024","unstructured":"Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, and Kwan-Yee K Wong. 2024. Fastercache: Training-free video diffusion model acceleration with high quality. arXiv preprint arXiv:2410.19355 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"e_1_3_2_1_28_1","volume-title":"Latte: Latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048","author":"Ma Xin","year":"2024","unstructured":"Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, and Yu Qiao. 2024b. Latte: Latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_31_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_33_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_34_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479-36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"European Conference on Computer Vision. Springer, 87-103","author":"Sauer Axel","year":"2024","unstructured":"Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. 2024. Adversarial diffusion distillation. In European Conference on Computer Vision. Springer, 87-103."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"e_1_3_2_1_38_1","volume-title":"Lazydit: Lazy learning for the acceleration of diffusion transformers. arXiv preprint arXiv:2412.12444","author":"Shen Xuan","year":"2024","unstructured":"Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Yanyu Li, Yifan Gong, Kai Zhang, Hao Tan, Jason Kuen, Henghui Ding, et al., 2024. Lazydit: Lazy learning for the acceleration of diffusion transformers. arXiv preprint arXiv:2412.12444 (2024)."},{"key":"e_1_3_2_1_39_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. 2020a. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_40_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. (2023)."},{"key":"e_1_3_2_1_41_1","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume":"34","author":"Song Yang","year":"2021","unstructured":"Yang Song, Conor Durkan, Iain Murray, and Stefano Ermon. 2021. Maximum likelihood training of score-based diffusion models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 1415-1428.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020b. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_44_1","volume-title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation. arXiv preprint arXiv:2503.10522","author":"Tian Zeyue","year":"2025","unstructured":"Zeyue Tian, Yizhu Jin, Zhaoyang Liu, Ruibin Yuan, Xu Tan, Qifeng Chen, Wei Xue, and Yike Guo. 2025. AudioX: Diffusion Transformer for Anything-to-Audio Generation. arXiv preprint arXiv:2503.10522 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_46_1","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 15903-15935.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse. arXiv preprint arXiv:2504.10540","author":"Yu Zichao","year":"2025","unstructured":"Zichao Yu, Zhen Zou, Guojiang Shao, Chengwei Zhang, Shengze Xu, Jie Huang, Feng Zhao, Xiaodong Cun, and Wenyi Zhang. 2025. AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse. arXiv preprint arXiv:2504.10540 (2025)."},{"key":"e_1_3_2_1_49_1","volume-title":"Mike Zheng Shou, and J\u00fcrgen Schmidhuber","author":"Zhang Wentian","year":"2024","unstructured":"Wentian Zhang, Haozhe Liu, Jinheng Xie, Francesco Faccio, Mike Zheng Shou, and J\u00fcrgen Schmidhuber. 2024. Cross-attention makes inference cumbersome in text-to-image diffusion models. arXiv e-prints (2024), arXiv-2404."},{"key":"e_1_3_2_1_50_1","volume-title":"Real-time video generation with pyramid attention broadcast. arXiv preprint arXiv:2408.12588","author":"Zhao Xuanlei","year":"2024","unstructured":"Xuanlei Zhao, Xiaolong Jin, Kai Wang, and Yang You. 2024. Real-time video generation with pyramid attention broadcast. arXiv preprint arXiv:2408.12588 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404","author":"Zheng Zangwei","year":"2024","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:2412.20404 (2024)."}],"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\/3746027.3755650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:56:46Z","timestamp":1765342606000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755650","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755650","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"}}]}}