{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:26:36Z","timestamp":1783182396084,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"KFUPM","award":["INSS2305"],"award-info":[{"award-number":["INSS2305"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-1703883, IIS-1955404, IIS-1955365, RETTL-2119265, and EAGER- 2122119"],"award-info":[{"award-number":["IIS-1703883, IIS-1955404, IIS-1955365, RETTL-2119265, and EAGER- 2122119"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,27]]},"DOI":"10.1145\/3581641.3584045","type":"proceedings-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T16:16:52Z","timestamp":1679933812000},"page":"790-801","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7935-8723","authenticated-orcid":false,"given":"Che-Jui","family":"Chang","sequence":"first","affiliation":[{"name":"Rutgers University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4700-954X","authenticated-orcid":false,"given":"Samuel S","family":"Sohn","sequence":"additional","affiliation":[{"name":"Rutgers University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8445-4848","authenticated-orcid":false,"given":"Sen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rutgers University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1846-8061","authenticated-orcid":false,"given":"Rajath","family":"Jayashankar","sequence":"additional","affiliation":[{"name":"Rutgers University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2059-7206","authenticated-orcid":false,"given":"Muhammad","family":"Usman","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, King Fahd University of Petroleum & Minerals, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3501-0028","authenticated-orcid":false,"given":"Mubbasir","family":"Kapadia","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rutgers University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Tukey\u2019s honestly significant difference (HSD) test. Encyclopedia of research design 3, 1","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi and Lynne\u00a0J Williams. 2010. Tukey\u2019s honestly significant difference (HSD) test. Encyclopedia of research design 3, 1 (2010), 1\u20135."},{"key":"e_1_3_2_2_2_1","volume-title":"Computer Graphics Forum, Vol.\u00a039","author":"Alexanderson Simon","unstructured":"Simon Alexanderson, Gustav\u00a0Eje Henter, Taras Kucherenko, and Jonas Beskow. 2020. Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows. In Computer Graphics Forum, Vol.\u00a039. Wiley Online Library, 487\u2013496."},{"key":"e_1_3_2_2_3_1","volume-title":"Body cues, not facial expressions, discriminate between intense positive and negative emotions. Science 338, 6111","author":"Aviezer Hillel","year":"2012","unstructured":"Hillel Aviezer, Yaacov Trope, and Alexander Todorov. 2012. Body cues, not facial expressions, discriminate between intense positive and negative emotions. Science 338, 6111 (2012), 1225\u20131229."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/2158244015592454"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 1. 361\u2013368","author":"Bergmann Kirsten","year":"2009","unstructured":"Kirsten Bergmann and Stefan Kopp. 2009. Increasing the expressiveness of virtual agents: autonomous generation of speech and gesture for spatial description tasks. In Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 1. 361\u2013368."},{"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":"crossref","unstructured":"Uttaran Bhattacharya Nicholas Rewkowski Abhishek Banerjee Pooja Guhan Aniket Bera and Dinesh Manocha. 2021. Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents** This work has been supported in part by ARO Grants W911NF1910069 and W911NF1910315 and Intel. Code and additional materials available at: https:\/\/gamma. umd. edu\/t2g. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR). IEEE 1\u201310.","DOI":"10.1109\/VR50410.2021.00037"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423872"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478344"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267853"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Che-Jui Chang. 2020. Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion. https:\/\/doi.org\/10.48550\/ARXIV.2009.14668","DOI":"10.48550\/ARXIV.2009.14668"},{"key":"e_1_3_2_2_12_1","volume-title":"The TeamName entry to the GENEA Challenge 2022 \u2013 A Tacotron2 Based Method for Co-Speech Gesture Generation With Locality-Constraint Attention Mechanism. in press","author":"Chang Che-Jui","year":"2022","unstructured":"Che-Jui Chang, Sen Zhang, and Mubbasir Kapadia. 2022. The TeamName entry to the GENEA Challenge 2022 \u2013 A Tacotron2 Based Method for Co-Speech Gesture Generation With Locality-Constraint Attention Mechanism. in press (2022)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2076"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423912"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04380-2_31"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1374"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329419"},{"key":"e_1_3_2_2_18_1","volume-title":"2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW). IEEE, 91\u201392","author":"Steve","unstructured":"Steve DiPaola and \u00d6zge\u00a0Nilay Yal\u00e7in. 2019. A multi-layer artificial intelligence and sensing based affective conversational embodied agent. In 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW). IEEE, 91\u201392."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983620"},{"key":"e_1_3_2_2_20_1","volume-title":"Basic emotions. Handbook of cognition and emotion 98, 45-60","author":"Ekman Paul","year":"1999","unstructured":"Paul Ekman. 1999. Basic emotions. Handbook of cognition and emotion 98, 45-60 (1999), 16."},{"key":"e_1_3_2_2_21_1","unstructured":"Unreal Engine. 2021. MetaHuman Creator."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522628.2522633"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267892"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423882"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2016"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478338"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329473"},{"key":"e_1_3_2_2_30_1","unstructured":"IBM. 2015. IBM Text to Speech. https:\/\/www.ibm.com\/watson. Accessed: 2022-03-05."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423908"},{"key":"e_1_3_2_2_32_1","unstructured":"Sepehr Janghorbani Ashutosh Modi Jakob Buhmann and Mubbasir Kapadia. 2019. Domain authoring assistant for intelligent virtual agents. arXiv preprint arXiv:1904.03266(2019)."},{"key":"e_1_3_2_2_33_1","volume-title":"ANOVA, and beyond","author":"Judd M","unstructured":"Charles\u00a0M Judd, Gary\u00a0H McClelland, and Carey\u00a0S Ryan. 2017. Data analysis: A model comparison approach to regression, ANOVA, and beyond. Routledge."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Mubbasir Kapadia Fabio Z\u00fcnd Jessica Falk Marcel Marti Robert\u00a0W Sumner and Markus Gross. 2015. Evaluating the authoring complexity of interactive narratives with interactive behaviour trees. Foundations of Digital Games(2015).","DOI":"10.1145\/2699276.2699279"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/11821830_17"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/11821830_20"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423902"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472307.3484167"},{"key":"e_1_3_2_2_41_1","volume-title":"Behavior matching in multimodal communication is synchronized. Cognitive science 36, 8","author":"Louwerse M","year":"2012","unstructured":"Max\u00a0M Louwerse, Rick Dale, Ellen\u00a0G Bard, and Patrick Jeuniaux. 2012. Behavior matching in multimodal communication is synchronized. Cognitive science 36, 8 (2012), 1404\u20131426."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.1992.tb00970.x"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1394281.1394294"},{"key":"e_1_3_2_2_44_1","unstructured":"David McNeill. 1992. Hand and Mind: What Gestures Reveal About Thought.(1992)."},{"key":"e_1_3_2_2_45_1","unstructured":"Rajmund Nagy Taras Kucherenko Birger Moell Andr\u00e9 Pereira Hedvig Kjellstr\u00f6m and Ulysses Bernardet. 2021. A framework for integrating gesture generation models into interactive conversational agents. arXiv preprint arXiv:2102.12302(2021)."},{"key":"e_1_3_2_2_46_1","unstructured":"Nvidia. 2021. Omniverse Audio2Face."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267884"},{"key":"e_1_3_2_2_48_1","unstructured":"Qualtrics. 2021. Qualtrics. Qualtrics Provo Utah USA. http:\/\/www.qualtrics.com"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343036.3343129"},{"key":"e_1_3_2_2_50_1","volume-title":"Automating the production of communicative gestures in embodied characters. Frontiers in psychology 9","author":"Ravenet Brian","year":"2018","unstructured":"Brian Ravenet, Catherine Pelachaud, Chlo\u00e9 Clavel, and Stacy Marsella. 2018. Automating the production of communicative gestures in embodied characters. Frontiers in psychology 9 (2018), 1144."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"James\u00a0A Russell. 1980. A circumplex model of affect.Journal of personality and social psychology 39 6(1980) 1161.","DOI":"10.1037\/h0077714"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2019.100313"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-150"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.251"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329474"},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 2250\u20132252","author":"Sohn S","year":"2018","unstructured":"Samuel\u00a0S Sohn, Xun Zhang, Fernando Geraci, and Mubbasir Kapadia. 2018. An emotionally aware embodied conversational agent. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 2250\u20132252."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439795"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Petra Wagner Zofia Malisz and Stefan Kopp. 2014. Gesture and speech in interaction: An overview. 209\u2013232\u00a0pages.","DOI":"10.1016\/j.specom.2013.09.008"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/34.1-2.1"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3149173"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2019.09.016"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"crossref","unstructured":"Hao Zhou Minlie Huang Tianyang Zhang Xiaoyan Zhu and Bing-Qian Liu. 2018. Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory. In AAAI.","DOI":"10.1609\/aaai.v32i1.11325"}],"event":{"name":"IUI '23: 28th International Conference on Intelligent User Interfaces","location":"Sydney NSW Australia","acronym":"IUI '23","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 28th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581641.3584045","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581641.3584045","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581641.3584045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:20Z","timestamp":1750178180000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581641.3584045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":64,"alternative-id":["10.1145\/3581641.3584045","10.1145\/3581641"],"URL":"https:\/\/doi.org\/10.1145\/3581641.3584045","relation":{},"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"2023-03-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}