{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:32:01Z","timestamp":1781584321158,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"name":"National Innovation and Entrepreneurship Training Program for College Students","award":["202410307104Z"],"award-info":[{"award-number":["202410307104Z"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733366","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"497-505","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Inter - Diffusion Generation Model of Speakers and Listeners for Effective Communication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9349-3948","authenticated-orcid":false,"given":"Jinhe","family":"Huang","sequence":"first","affiliation":[{"name":"Nanjing Agriculture University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3392-2012","authenticated-orcid":false,"given":"Yongkang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nanjing Agriculture University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3756-1528","authenticated-orcid":false,"given":"Minghang","family":"Yu","sequence":"additional","affiliation":[{"name":"Northwest A&F University, Yangling, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6731-8203","authenticated-orcid":false,"given":"Gaoge","family":"Han","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong SAR, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6606-3359","authenticated-orcid":false,"given":"Jinwei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0953-3669","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0507-7256","authenticated-orcid":false,"given":"Shilei","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9027-4987","authenticated-orcid":false,"given":"Xingjian","family":"Gu","sequence":"additional","affiliation":[{"name":"Nanjing Agriculture University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings, Part XVIII 16","author":"Ahuja Chaitanya","year":"2020","unstructured":"Chaitanya Ahuja, Dong Won Lee, Yukiko I Nakano, and Louis-Philippe Morency. 2020. Style transfer for co-speech gesture animation: A multi-speaker conditional-mixture approach. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XVIII 16. Springer, 248--265."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"e_1_3_2_1_3_1","volume-title":"HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures. arXiv preprint arXiv:2503.13229","author":"Cheng Yongkang","year":"2025","unstructured":"Yongkang Cheng and Shaoli Huang. 2025. HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures. arXiv preprint arXiv:2503.13229 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32248"},{"key":"e_1_3_2_1_5_1","volume-title":"Bopr: Body-aware part regressor for human shape and pose estimation. arXiv preprint arXiv:2303.11675","author":"Cheng Yongkang","year":"2023","unstructured":"Yongkang Cheng, Shaoli Huang, Jifeng Ning, and Ying Shan. 2023. Bopr: Body-aware part regressor for human shape and pose estimation. arXiv preprint arXiv:2303.11675 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00217"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687922"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00222"},{"key":"e_1_3_2_1_11_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33, 6840--6851."},{"key":"e_1_3_2_1_12_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00294"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"e_1_3_2_1_16_1","first-page":"21386","article-title":"Audio-Driven Co-Speech Gesture Video Generation","volume":"35","author":"Liu Xian","year":"2022","unstructured":"Xian Liu, Qianyi Wu, Hang Zhou, Yuanqi Du, Wayne Wu, Dahua Lin, and Ziwei Liu. 2022a. Audio-Driven Co-Speech Gesture Video Generation. Advances in Neural Information Processing Systems, Vol. 35, 21386--21399.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_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_18_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_19_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_20_1","unstructured":"Guy Tevet Sigal Raab Brian Gordon Yonatan Shafir Daniel Cohen-Or and Amit H Bermano. 2022. Human motion diffusion model. arXiv preprint arXiv:2209.14916."},{"key":"e_1_3_2_1_21_1","volume-title":"Diffusion-gan: Training gans with diffusion. arXiv preprint arXiv:2206.02262","author":"Wang Zhendong","year":"2022","unstructured":"Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, and Mingyuan Zhou. 2022. Diffusion-gan: Training gans with diffusion. arXiv preprint arXiv:2206.02262 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Vector quantized diffusion model with codeunet for text-to-sign pose sequences generation. arXiv preprint arXiv:2208.09141","author":"Xie Pan","year":"2022","unstructured":"Pan Xie, Qipeng Zhang, Zexian Li, Hao Tang, Yao Du, and Xiaohui Hu. 2022. Vector quantized diffusion model with codeunet for text-to-sign pose sequences generation. arXiv preprint arXiv:2208.09141 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Sicheng Yang Zilin Wang Zhiyong Wu Minglei Li Zhensong Zhang Qiaochu Huang Lei Hao Songcen Xu Xiaofei Wu Zonghong Dai et al. 2023a. UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons. arXiv preprint arXiv:2309.07051.","DOI":"10.1145\/3581783.3612503"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Sicheng Yang Zhiyong Wu Minglei Li Zhensong Zhang Lei Hao Weihong Bao Ming Cheng and Long Xiao. 2023b. DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models. arXiv preprint arXiv:2305.04919.","DOI":"10.24963\/ijcai.2023\/650"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447978"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558058"},{"key":"e_1_3_2_1_29_1","volume-title":"Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001.","author":"Zhang Mingyuan","year":"2022","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2022. Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001."},{"key":"e_1_3_2_1_30_1","volume-title":"Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models. arXiv preprint arXiv:2301.03949","author":"Zhao Mengyi","year":"2023","unstructured":"Mengyi Zhao, Mengyuan Liu, Bin Ren, Shuling Dai, and Nicu Sebe. 2023. Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models. arXiv preprint arXiv:2301.03949 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558063"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:05:48Z","timestamp":1755749148000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"alternative-id":["10.1145\/3731715.3733366","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733366","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}