{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:56Z","timestamp":1765343156948,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","funder":[{"name":"The National Natural Science Foundation of China under Grants","award":["62206137"],"award-info":[{"award-number":["62206137"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755662","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"8740-8749","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sequence-Event Semantic Consistent Learning for Text-to-Motion Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7845-781X","authenticated-orcid":false,"given":"Haoyu","family":"Shi","sequence":"first","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, 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\/CVPR.2016.572"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. JMLR, 16 pages.","author":"Bar-Tal Omer","year":"2023","unstructured":"Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel. 2023. MultiDiffusion: fusing diffusion paths for controlled image generation. In Proceedings of the 40th International Conference on Machine Learning. JMLR, 16 pages."},{"key":"e_1_3_2_1_3_1","unstructured":"Dmitry Baranchuk Ivan Rubachev Andrey Voynov Valentin Khrulkov and Artem Babenko. 2021. Label-Efficient Semantic Segmentation with Diffusion Models. arXiv:2112.03126"},{"key":"e_1_3_2_1_4_1","first-page":"899","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems -","volume":"1","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Li Yao, Guillaume Alain, and Pascal Vincent. 2013. Generalized denoising auto-encoders as generative models. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 1. 899-907."},{"key":"e_1_3_2_1_5_1","volume-title":"IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12652-12660","author":"Chen Hui","year":"2020","unstructured":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. 2020. IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12652-12660."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4171-4186."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_9_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv","author":"Dosovitskiy Alexey","year":"1929","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv, Vol. abs\/2010.11929 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"e_1_3_2_1_11_1","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume":"36","author":"Epstein Dave","year":"2023","unstructured":"Dave Epstein, Allan Jabri, Ben Poole, Alexei Efros, and Aleksander Holynski. 2023. Diffusion self-guidance for controllable image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 16222-16239.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference 2018, BMVC 2018","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3-6, 2018. BMVA Press, 12."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207910"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16226"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings, Part LVIII. 323-339","author":"Fujiwara Kent","year":"2024","unstructured":"Kent Fujiwara, Mikihiro Tanaka, and Qing Yu. 2024. Chronologically Accurate Retrieval for Motion-Language Models. In Computer Vision - ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LVIII. 323-339."},{"key":"e_1_3_2_1_16_1","first-page":"54090","volume-title":"International Conference on Representation Learning","volume":"2024","author":"Gan Yulu","year":"2024","unstructured":"Yulu Gan, Sung Woo Park, Alexander Schubert, Anthony Philippakis, and Ahmed Alaa. 2024. InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists. In International Conference on Representation Learning, Vol. 2024. 54090-54106."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02840"},{"key":"e_1_3_2_1_20_1","volume-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. The journal of machine learning research","author":"Gutmann Michael U","year":"2012","unstructured":"Michael U Gutmann and Aapo Hyv\u00e4rinen. 2012. Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. The journal of machine learning research, Vol. 13, 1 (2012), 307-361."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_3"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3509874"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1965-1974","author":"Kapon Roy","key":"e_1_3_2_1_25_1","unstructured":"Roy Kapon, Guy Tevet, Daniel Cohen-Or, and Amit H. Bermano. 2024. MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1965-1974."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_1_28_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR, Vol. abs\/1412.6980 (2014)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"e_1_3_2_1_31_1","volume-title":"Fine-grained semantically aligned vision-language pre-training. Advances in neural information processing systems","author":"Li Juncheng","year":"2022","unstructured":"Juncheng Li, Xin He, Longhui Wei, Long Qian, Linchao Zhu, Lingxi Xie, Yueting Zhuang, Qi Tian, and Siliang Tang. 2022b. Fine-grained semantically aligned vision-language pre-training. Advances in neural information processing systems, Vol. 35 (2022), 7290-7303."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022c. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_33_1","volume-title":"Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 4077-4087","author":"Li Pandeng","year":"2023","unstructured":"Pandeng Li, Chen-Wei Xie, Liming Zhao, Hongtao Xie, Jiannan Ge, Yun Zheng, Deli Zhao, and Yongdong Zhang. 2023b. Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 4077-4087."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128851"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3261443"},{"key":"e_1_3_2_1_36_1","unstructured":"Zheng Li Caili Guo Zerun Feng Jenq-Neng Hwang Ying Jin and Yufeng Zhang. 2022a. Image-Text Retrieval with Binary and Continuous Label Supervision. arXiv:2210.11319"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111431"},{"key":"e_1_3_2_1_38_1","unstructured":"Zhe Li Weihao Yuan Yisheng He Lingteng Qiu Shenhao Zhu Xiaodong Gu Weichao Shen Yuan Dong Zilong Dong and Laurence T Yang. 2024c. LaMP: Language-Motion Pretraining for Motion Generation Retrieval and Captioning. arXiv preprint arXiv:2410.07093 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"e_1_3_2_1_40_1","volume-title":"Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision","author":"Liang Han","year":"2024","unstructured":"Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu, and Lan Xu. 2024. Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision (2024), 1-21."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems. Curran Associates Inc., Article 1645","author":"Lim Sungbin","year":"2023","unstructured":"Sungbin Lim, Eunbi Yoon, Taehyun Byun, Taewon Kang, Seungwoo Kim, Kyungjae Lee, and Sungjoon Choi. 2023. Score-based generative modeling through stochastic evolution equations in hilbert spaces. In Proceedings of the 37th International Conference on Neural Information Processing Systems. Curran Associates Inc., Article 1645, 14 pages."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60639-8_40"},{"key":"e_1_3_2_1_43_1","article-title":"SMPL: A Skinned Multi-Person Linear Model","volume":"34","author":"Loper Matthew","year":"2015","unstructured":"Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. ACM Trans. Graphics (Proc. SIGGRAPH Asia), Vol. 34, 6 (2015), 248:1-248:16.","journal-title":"ACM Trans. Graphics (Proc. SIGGRAPH Asia)"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_45_1","volume-title":"SDEdit: Image Synthesis and Editing with Stochastic Differential Equations. ArXiv","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. SDEdit: Image Synthesis and Editing with Stochastic Differential Equations. ArXiv, Vol. abs\/2108.01073 (2021)."},{"key":"e_1_3_2_1_46_1","first-page":"2420","volume-title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. In ACM SIGIR 2023","author":"Messina Nicola","year":"2023","unstructured":"Nicola Messina, Jan Sedmidubsk\u00fd, Fabrizio Falchi, and Tom\u00e1s Rebok. 2023. Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. In ACM SIGIR 2023, Taipei, Taiwan, July 23-27, 2023. ACM, 2420-2425."},{"key":"e_1_3_2_1_47_1","volume-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, and Jian Zhang. 2023. Dragondiffusion: Enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Masked Diffusion as Self-supervised Representation Learner. ArXiv","author":"Pan Zixuan","year":"2023","unstructured":"Zixuan Pan, Jianxu Chen, and Yi Shi. 2023. Masked Diffusion as Self-supervised Representation Learner. ArXiv, Vol. abs\/2308.05695 (2023)."},{"key":"e_1_3_2_1_49_1","first-page":"480","volume-title":"Tel Aviv","volume":"13682","author":"Petrovich Mathis","year":"2022","unstructured":"Mathis Petrovich, Michael J. Black, and G\u00fcl Varol. 2022. TEMOS: Generating Diverse Human Motions from Textual Descriptions. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXII, Vol. 13682. Springer, 480-497."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_2_1_53_1","first-page":"17567","article-title":"Diffusion-tta: Test-time adaptation of discriminative models via generative feedback","volume":"36","author":"Prabhudesai Mihir","year":"2023","unstructured":"Mihir Prabhudesai, Tsung-Wei Ke, Alex Li, Deepak Pathak, and Katerina Fragkiadaki. 2023. Diffusion-tta: Test-time adaptation of discriminative models via generative feedback. Advances in Neural Information Processing Systems, Vol. 36 (2023), 17567-17583.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Proceedings IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 722-731","author":"Punnakkal Abhinanda R.","key":"e_1_3_2_1_54_1","unstructured":"Abhinanda R. Punnakkal, Arjun Chandrasekaran, Nikos Athanasiou, Alejandra Quiros-Ramirez, and Michael J. Black. 2021. BABEL: Bodies, Action and Behavior with English Labels. In Proceedings IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 722-731."},{"key":"e_1_3_2_1_55_1","volume-title":"International conference on machine learning. 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. 8748-8763."},{"key":"e_1_3_2_1_56_1","volume-title":"Contrastive Learning with Hard Negative Samples. In 9th International Conference on Learning Representations, ICLR 2021","author":"Robinson Joshua David","year":"2021","unstructured":"Joshua David Robinson, Ching-Yao Chuang, Suvrit Sra, and Stefanie Jegelka. 2021. Contrastive Learning with Hard Negative Samples. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681625"},{"key":"e_1_3_2_1_58_1","volume-title":"Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations.","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yoni Shafir, Daniel Cohen-or, and Amit Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_59_1","first-page":"48382","article-title":"Stablerep: Synthetic images from text-to-image models make strong visual representation learners","volume":"36","author":"Tian Yonglong","year":"2023","unstructured":"Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, and Dilip Krishnan. 2023. Stablerep: Synthetic images from text-to-image models make strong visual representation learners. Advances in Neural Information Processing Systems, Vol. 36 (2023), 48382-48402.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_60_1","first-page":"14590","volume-title":"Effective Data Augmentation With Diffusion Models. In International Conference on Representation Learning","volume":"2024","author":"Trabucco Brandon","year":"2024","unstructured":"Brandon Trabucco, Kyle Doherty, Max Gurinas, and Ruslan Salakhutdinov. 2024. Effective Data Augmentation With Diffusion Models. In International Conference on Representation Learning, Vol. 2024. 14590-14612."},{"key":"e_1_3_2_1_61_1","first-page":"74327","volume-title":"Diffusion Feedback Helps CLIP See Better. In International Conference on Representation Learning","volume":"2025","author":"Wang Wenxuan","year":"2025","unstructured":"Wenxuan Wang, Quan Sun, Fan Zhang, Yepeng Tang, Jing Liu, and Xinlong Wang. 2025. Diffusion Feedback Helps CLIP See Better. In International Conference on Representation Learning, Vol. 2025. 74327-74345."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"e_1_3_2_1_64_1","volume-title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2804-2815","author":"Wang Ziyang","year":"2023","unstructured":"Ziyang Wang, Yi-Lin Sung, Feng Cheng, Gedas Bertasius, and Mohit Bansal. 2023a. Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2804-2815."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626459"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657804"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00158"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00095"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248873"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"e_1_3_2_1_75_1","volume-title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation. In European Conference on Computer Vision. 18-38","author":"Zhou Wenyang","year":"2025","unstructured":"Wenyang Zhou, Zhiyang Dou, Zeyu Cao, Zhouyingcheng Liao, Jingbo Wang, Wenjia Wang, Yuan Liu, Taku Komura, Wenping Wang, and Lingjie Liu. 2025. EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation. In European Conference on Computer Vision. 18-38."}],"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\/3746027.3755662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:02:38Z","timestamp":1765342958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":75,"alternative-id":["10.1145\/3746027.3755662","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755662","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"}}]}}