{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:58:37Z","timestamp":1776445117704,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["20023495"],"award-info":[{"award-number":["20023495"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","award":["WASP, WARA Media and Language"],"award-info":[{"award-number":["WASP, WARA Media and Language"]}],"id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Electronic Arts","award":["SEED"],"award-info":[{"award-number":["SEED"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,9]]},"DOI":"10.1145\/3577190.3616120","type":"proceedings-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T22:30:48Z","timestamp":1696717848000},"page":"792-801","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":56,"title":["The GENEA Challenge 2023: A large-scale evaluation of gesture generation models in monadic and dyadic settings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9838-8848","authenticated-orcid":false,"given":"Taras","family":"Kucherenko","sequence":"first","affiliation":[{"name":"SEED, Electronic Arts (EA), Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-6699","authenticated-orcid":false,"given":"Rajmund","family":"Nagy","sequence":"additional","affiliation":[{"name":"Division of Speech, Music and Hearing (TMH), KTH Royal Institute of Technology, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-3421","authenticated-orcid":false,"given":"Youngwoo","family":"Yoon","sequence":"additional","affiliation":[{"name":", ETRI, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4761-7038","authenticated-orcid":false,"given":"Jieyeon","family":"Woo","sequence":"additional","affiliation":[{"name":"ISIR, Sorbonne University, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4573-1400","authenticated-orcid":false,"given":"Teodor","family":"Nikolov","sequence":"additional","affiliation":[{"name":"Department of Computing Science, Ume\u00e5 University, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1817-440X","authenticated-orcid":false,"given":"Mihail","family":"Tsakov","sequence":"additional","affiliation":[{"name":"Department of Computing Science, Ume\u00e5 University, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1643-1054","authenticated-orcid":false,"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[{"name":"Division of Speech, Music and Hearing (TMH), KTH Royal Institute of Technology, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/mti6070051"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04380-2_12"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475223"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558060"},{"key":"e_1_3_2_2_9_1","volume-title":"Discrete Diffusion for Co-Speech Gesture Synthesis. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery.","author":"Chemburkar Ankur","year":"2023","unstructured":"Ankur Chemburkar , Shuhong Lu , and Andrew Andrew . 2023 . Discrete Diffusion for Co-Speech Gesture Synthesis. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery. Ankur Chemburkar, Shuhong Lu, and Andrew Andrew. 2023. Discrete Diffusion for Co-Speech Gesture Synthesis. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21996-7_17"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616117"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2016"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316771"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616115"},{"key":"e_1_3_2_2_15_1","volume-title":"Int. J. Comput. Games. Tech. 2022","author":"Zhiyuan He.","year":"2022","unstructured":"Zhiyuan He. 2022. Automatic quality assessment of speech-driven synthesized gestures . Int. J. Comput. Games. Tech. 2022 ( 2022 ). https:\/\/doi.org\/10.1155\/2022\/1828293 10.1155\/2022 Zhiyuan He. 2022. Automatic quality assessment of speech-driven synthesized gestures. Int. J. Comput. Games. Tech. 2022 (2022). https:\/\/doi.org\/10.1155\/2022\/1828293"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-017-1363-z"},{"key":"e_1_3_2_2_17_1","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm Sture","year":"1979","unstructured":"Sture Holm . 1979 . A simple sequentially rejective multiple test procedure . Scandinavian Journal of Statistics 6 , 2 (1979), 65 \u2013 70 . Sture Holm. 1979. A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics 6, 2 (1979), 65\u201370.","journal-title":"Scandinavian Journal of Statistics"},{"key":"e_1_3_2_2_18_1","volume-title":"Telecommunication Standardisation Sector","author":"Union International Telecommunication","year":"1996","unstructured":"International Telecommunication Union , Telecommunication Standardisation Sector . 1996 . Methods for subjective determination of transmission quality. Recommendation ITU-T P. 800. https:\/\/www.itu.int\/rec\/T-REC-P.800-199608-I International Telecommunication Union, Telecommunication Standardisation Sector. 1996. Methods for subjective determination of transmission quality. Recommendation ITU-T P.800. https:\/\/www.itu.int\/rec\/T-REC-P.800-199608-I"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423911"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479957"},{"key":"e_1_3_2_2_21_1","volume-title":"Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery.","author":"Kim Gwantae","year":"2023","unstructured":"Gwantae Kim , Yuanming Li , and Hanseok Ko . 2023 . The KU-ISPL entry to the GENEA Challenge 2023-A Diffusion Model for Co-speech Gesture generation . In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery. Gwantae Kim, Yuanming Li, and Hanseok Ko. 2023. The KU-ISPL entry to the GENEA Challenge 2023-A Diffusion Model for Co-speech Gesture generation. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095344"},{"key":"e_1_3_2_2_23_1","volume-title":"Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery.","author":"Kim Geunmo","year":"2023","unstructured":"Geunmo Kim , Jaewoong Yoo , and Hyedong Jung . 2023 . Co-Speech Gesture Generation via Audio and Text Feature Engineering . In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery. Geunmo Kim, Jaewoong Yoo, and Hyedong Jung. 2023. Co-Speech Gesture Generation via Audio and Text Feature Engineering. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616119"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450692"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616120"},{"key":"e_1_3_2_2_28_1","volume-title":"Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge","author":"Kucherenko Taras","year":"2022","unstructured":"Taras Kucherenko , Pieter Wolfert , Youngwoo Yoon , Carla Viegas , Teodor Nikolov , Mihail Tsakov , and Gustav\u00a0Eje Henter . 2023. Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022 . arXiv preprint arXiv:2303.08737 (2023). Taras Kucherenko, Pieter Wolfert, Youngwoo Yoon, Carla Viegas, Teodor Nikolov, Mihail Tsakov, and Gustav\u00a0Eje Henter. 2023. Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022. arXiv preprint arXiv:2303.08737 (2023)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00085"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778861"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"e_1_3_2_2_32_1","volume-title":"Hand and Mind: What Gestures Reveal about Thought","author":"McNeill David","unstructured":"David McNeill . 1992. Hand and Mind: What Gestures Reveal about Thought . University of Chicago Press. https :\/\/doi.org\/10.1177\/002383099403700208 10.1177\/002383099403700208 David McNeill. 1992. Hand and Mind: What Gestures Reveal about Thought. University of Chicago Press. https:\/\/doi.org\/10.1177\/002383099403700208"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-24"},{"key":"e_1_3_2_2_34_1","volume-title":"Computer Graphics Forum, Vol.\u00a042","author":"Nyatsanga Simbarashe","unstructured":"Simbarashe Nyatsanga , Taras Kucherenko , Chaitanya Ahuja , Gustav\u00a0Eje Henter , and Michael Neff . 2023. A Comprehensive Review of Data-Driven Co-Speech Gesture Generation . In Computer Graphics Forum, Vol.\u00a042 . Wiley Online Library , 569\u2013596. Simbarashe Nyatsanga, Taras Kucherenko, Chaitanya Ahuja, Gustav\u00a0Eje Henter, and Michael Neff. 2023. A Comprehensive Review of Data-Driven Co-Speech Gesture Generation. In Computer Graphics Forum, Vol.\u00a042. Wiley Online Library, 569\u2013596."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556608"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00082"},{"key":"e_1_3_2_2_37_1","volume-title":"Article 191940","author":"Salvi Giampiero","year":"2009","unstructured":"Giampiero Salvi , Jonas Beskow , Samer Al\u00a0Moubayed , and Bj\u00f6rn Granstr\u00f6m . 2009. SynFace\u2014Speech-driven facial animation for virtual speech-reading support. EURASIP J. Audio Spee ., Article 191940 ( 2009 ), 10\u00a0pages. https:\/\/doi.org\/10.1155\/2009\/191940 10.1155\/2009 Giampiero Salvi, Jonas Beskow, Samer Al\u00a0Moubayed, and Bj\u00f6rn Granstr\u00f6m. 2009. SynFace\u2014Speech-driven facial animation for virtual speech-reading support. EURASIP J. Audio Spee., Article 191940 (2009), 10\u00a0pages. https:\/\/doi.org\/10.1155\/2009\/191940"},{"key":"e_1_3_2_2_38_1","volume-title":"Speaker. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery.","author":"Schmuck Viktor","year":"2023","unstructured":"Viktor Schmuck , Nguyen Tan\u00a0Viet Tuyen , and Oya Celiktutan . 2023 . The KCL-SAIR team\u2019s entry to the GENEA Challenge 2023 Exploring Role-based Gesture Generation in Dyadic Interactions: Listener vs . Speaker. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery. Viktor Schmuck, Nguyen Tan\u00a0Viet Tuyen, and Oya Celiktutan. 2023. The KCL-SAIR team\u2019s entry to the GENEA Challenge 2023 Exploring Role-based Gesture Generation in Dyadic Interactions: Listener vs. Speaker. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery."},{"key":"e_1_3_2_2_39_1","volume-title":"Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery.","author":"Tonoli Rodolfo\u00a0Luis","year":"2023","unstructured":"Rodolfo\u00a0Luis Tonoli , Leonardo Boulitreau\u00a0de Menezes Martins\u00a0Marques , Lucas\u00a0Hideki Ueda , and Paula Paro\u00a0Dornhofer Costa . 2023 . Gesture Generation with Diffusion Models Aided by Speech Activity Information . In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery. Rodolfo\u00a0Luis Tonoli, Leonardo Boulitreau\u00a0de Menezes Martins\u00a0Marques, Lucas\u00a0Hideki Ueda, and Paula Paro\u00a0Dornhofer Costa. 2023. Gesture Generation with Diffusion Models Aided by Speech Activity Information. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). Association for Computing Machinery."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479914"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616116"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479889"},{"key":"e_1_3_2_2_43_1","volume-title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models. arXiv preprint arXiv:2305.04919","author":"Yang Sicheng","year":"2023","unstructured":"Sicheng Yang , Zhiyong Wu , Minglei Li , Zhensong Zhang , Lei Hao , Weihong Bao , Ming Cheng , and Long Xiao . 2023. DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models. arXiv preprint arXiv:2305.04919 ( 2023 ). Sicheng Yang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Lei Hao, Weihong Bao, Ming Cheng, and Long Xiao. 2023. DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models. arXiv preprint arXiv:2305.04919 (2023)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00230"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981117"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474789"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558058"},{"key":"e_1_3_2_2_51_1","volume-title":"DiffuGesture: Generating Human Gesture From Two-person Dialogue With Diffusion Models. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). ACM.","author":"Zhao Weiyu","year":"2023","unstructured":"Weiyu Zhao , Liangxiao Hu , and Shengping Zhang . 2023 . DiffuGesture: Generating Human Gesture From Two-person Dialogue With Diffusion Models. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). ACM. Weiyu Zhao, Liangxiao Hu, and Shengping Zhang. 2023. DiffuGesture: Generating Human Gesture From Two-person Dialogue With Diffusion Models. In Companion Publication of the 2023 International Conference on Multimodal Interaction(ICMI \u201923 Companion). ACM."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616118"}],"event":{"name":"ICMI '23: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Paris France","acronym":"ICMI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616120","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577190.3616120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:02Z","timestamp":1750178222000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":52,"alternative-id":["10.1145\/3577190.3616120","10.1145\/3577190"],"URL":"https:\/\/doi.org\/10.1145\/3577190.3616120","relation":{},"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"2023-10-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}