{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:30:18Z","timestamp":1764588618836,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["No. 62172241"],"award-info":[{"award-number":["No. 62172241"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["No.CUC23ZDTJ003, CUC24CGJ08"],"award-info":[{"award-number":["No.CUC23ZDTJ003, CUC24CGJ08"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.1145\/3712678.3721882","type":"proceedings-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T06:20:32Z","timestamp":1743661232000},"page":"57-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bimodal Semantic-Driven 3D Immersive Telepresence System"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2943-2842","authenticated-orcid":false,"given":"Jiakun","family":"Li","sequence":"first","affiliation":[{"name":"Communication University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1335-2780","authenticated-orcid":false,"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-8887","authenticated-orcid":false,"given":"Lingjun","family":"Pu","sequence":"additional","affiliation":[{"name":"Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1170-636X","authenticated-orcid":false,"given":"Tao","family":"Lin","sequence":"additional","affiliation":[{"name":"Communication University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4153-313X","authenticated-orcid":false,"given":"Jinyao","family":"Yan","sequence":"additional","affiliation":[{"name":"Communication University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"e_1_3_2_1_2_1","unstructured":"Gary Bradski Adrian Kaehler et al. 2000. Opencv. Dr. Dobb's journal of software tools 3 2."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661879"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628184"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699344"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Kyusun Cho Joungbin Lee Heeji Yoon Yeobin Hong Jaehoon Ko Sangjun Ahn and Seungryong Kim. 2024. Gaussiantalker: real-time high-fidelity talking head synthesis with audio-driven 3d gaussian splatting. arXiv preprint arXiv:2404.16012.","DOI":"10.1145\/3664647.3681627"},{"key":"e_1_3_2_1_7_1","unstructured":"Draco. 2021. Draco 3d graphics compression. https:\/\/google.github.io\/draco\/. (2021)."},{"key":"e_1_3_2_1_8_1","unstructured":"Jianglong Li et al. 2024. Nerf based 3d generative video conferencing system. https:\/\/www.ibc.org\/accelerating-innovation\/reports\/ibc2024-tech-papers-nerf-based-3d-generative-video-conferencing-system\/21395. (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"Lex Fridman. 2024. Mark zuckerberg: first interview in the metaverse | lex fridman podcast https:\/\/www.youtube.com\/watch?v=MVYrJJNdrEg. (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592530"},{"key":"e_1_3_2_1_11_1","unstructured":"Jia Guo Jiankang Deng Alexandros Lattas and Stefanos Zafeiriou. 2021. Sample and computation redistribution for efficient face detection. arXiv preprint arXiv:2105.04714."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Sangtae Ha Injong Rhee and Lisong Xu. 2008. Cubic: a new tcp-friendly high-speed tcp variant. ACM SIGOPS operating systems review 42 5 64--74.","DOI":"10.1145\/1400097.1400105"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"e_1_3_2_1_16_1","unstructured":"The Cambridge-MIT Institute and T-Party. 2006. Pyaudio. https:\/\/people.csail.mit.edu\/hubert\/pyaudio. (2006)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2900721"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3393578"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00092"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2015.43"},{"key":"e_1_3_2_1_21_1","unstructured":"Jeremy Lain\u00e9. 2024. Aioquic. https:\/\/github.com\/aiortc\/aioquic. (2024)."},{"volume-title":"Proceedings of the conference of the ACM special interest group on data communication, 183--196","author":"Adam","key":"e_1_3_2_1_22_1","unstructured":"Adam Langley et al. 2017. The quic transport protocol: design and internetscale deployment. In Proceedings of the conference of the ACM special interest group on data communication, 183--196."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641517.3664381"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592525"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419214"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649364"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_29_1","unstructured":"Microsoft. 2022. Virtualcube. https:\/\/www.microsoft.com\/en-us\/research\/articles\/virtualcube\/. (2022)."},{"key":"e_1_3_2_1_30_1","unstructured":"Netflix. 2020. Vmaf - video multi-method assessment fusion. https:\/\/github.com\/Netflix\/vmaf?tab=readme-ov-file. (2020)."},{"key":"e_1_3_2_1_31_1","unstructured":"OpenCV. 2024. Perspective-n-point (pnp) pose computation. https:\/\/docs.opencv.org\/3.4\/d5\/d1f\/calib3d_solvePnP.html. (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"e_1_3_2_1_33_1","article-title":"Parametrization of an orthogonal matrix in terms of generalized eulerian angles","volume":"4","author":"Raffenetti Richard C","year":"1969","unstructured":"Richard C Raffenetti and Klaus Ruedenberg. 1969. Parametrization of an orthogonal matrix in terms of generalized eulerian angles. International Journal of Quantum Chemistry, 4, S3B, 625--634.","journal-title":"International Journal of Quantum Chemistry"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980567"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"e_1_3_2_1_36_1","unstructured":"Jiaxiang Tang Kaisiyuan Wang Hang Zhou Xiaokang Chen Dongliang He Tianshu Hu Jingtuo Liu Gang Zeng and Jingdong Wang. 2022. Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. arXiv preprint arXiv:2211.12368."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661858"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Yifan Xie Tao Feng Xin Zhang Xiangyang Luo Zixuan Guo Weijiang Yu Heng Chang Fei Ma and Fei Richard Yu. 2024. Pointtalk: audio-driven dynamic lip point cloud for 3d gaussian-based talking head synthesis. arXiv preprint arXiv:2412.08504.","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"e_1_3_2_1_40_1","unstructured":"Shunyu Yao RuiZhe Zhong Yichao Yan Guangtao Zhai and Xiaokang Yang. 2022. Dfa-nerf: personalized talking head generation via disentangled face attributes neural rendering. arXiv preprint arXiv:2201.00791."},{"key":"e_1_3_2_1_41_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Yeo Hyunho","year":"2018","unstructured":"Hyunho Yeo, Youngmok Jung, Jaehong Kim, Jinwoo Shin, and Dongsu Han. 2018. Neural adaptive content-aware internet video delivery. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), 645--661."},{"key":"e_1_3_2_1_42_1","unstructured":"yinguobing. 2019. Cnn-facial-landmark. https:\/\/github.com\/yinguobing\/cnn-facial-landmark. (2019)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"ChangAn Zhu and Chris Joslin. 2024. A review of motion retargeting techniques for 3d character facial animation. Computers & Graphics 104037.","DOI":"10.1016\/j.cag.2024.104037"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217928"},{"volume-title":"Impact of frame rate and resolution on objective qoe metrics. In 2010 second international workshop on quality of multimedia experience (QoMEX)","author":"Zinner Thomas","key":"e_1_3_2_1_46_1","unstructured":"Thomas Zinner, Oliver Hohlfeld, Osama Abboud, and Tobias Ho\u00dffeld. 2010. Impact of frame rate and resolution on objective qoe metrics. In 2010 second international workshop on quality of multimedia experience (QoMEX). IEEE, 29--34."}],"event":{"name":"MMSys '25: ACM Multimedia Systems Conference 2025","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"],"location":"Stellenbosch South Africa","acronym":"MMSys '25"},"container-title":["Proceedings of the 35th edition of the Workshop on Network and Operating System Support for Digital Audio and Video"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712678.3721882","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712678.3721882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:16:39Z","timestamp":1756235799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712678.3721882"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":46,"alternative-id":["10.1145\/3712678.3721882","10.1145\/3712678"],"URL":"https:\/\/doi.org\/10.1145\/3712678.3721882","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]},"assertion":[{"value":"2025-04-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}