{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:30:12Z","timestamp":1772649012179,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"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":[{"name":"German Federal Ministry for Education and Research (BMBF)","award":["13GW0568D,01IS20075"],"award-info":[{"award-number":["13GW0568D,01IS20075"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,9]]},"DOI":"10.1145\/3577190.3614133","type":"proceedings-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T22:30:48Z","timestamp":1696717848000},"page":"507-516","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ReNeLiB: Real-time Neural Listening Behavior Generation for Socially Interactive Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8831-9795","authenticated-orcid":false,"given":"Daksitha Senel","family":"Withanage Don","sequence":"first","affiliation":[{"name":"Human Centered Artificial Intelligence Lab, Augsburg University, Germany and Cognitive Assistants, German Research Center for Artificial Intelligence, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7037-7100","authenticated-orcid":false,"given":"Philipp","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Cognitive Assistants, German Research Center for Artificial Intelligence, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4043","authenticated-orcid":false,"given":"Fabrizio","family":"Nunnari","sequence":"additional","affiliation":[{"name":"Cognitive Assistants, German Research Center for Artificial Intelligence, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2367-162X","authenticated-orcid":false,"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[{"name":"Human Centered Artificial Intelligence Lab, Augsburg University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5566-4520","authenticated-orcid":false,"given":"Patrick","family":"Gebhard","sequence":"additional","affiliation":[{"name":"Cognitive Assistants, German Research Center for Artificial Intelligence, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jan Alexandersson Jochen Britz Valentin Seimetz and Daniel Tabellion. [n. d.]. White paper \u2013 SEMLA. https:\/\/semla.dfki.de\/white-paper\/. (Accessed on 04\/29\/2023).  Jan Alexandersson Jochen Britz Valentin Seimetz and Daniel Tabellion. [n. d.]. White paper \u2013 SEMLA. https:\/\/semla.dfki.de\/white-paper\/. (Accessed on 04\/29\/2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_3_1","unstructured":"Timothy Bickmore and Justine Cassell. 1999. Small talk and conversational storytelling in embodied conversational interface agents. In AAAI fall symposium on narrative intelligence. 87\u201392.  Timothy Bickmore and Justine Cassell. 1999. Small talk and conversational storytelling in embodied conversational interface agents. In AAAI fall symposium on narrative intelligence. 87\u201392."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1891903.1891910"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"e_1_3_2_1_7_1","volume-title":"EMOCA: Emotion Driven Monocular Face Capture and Animation. In Conference on Computer Vision and Pattern Recognition (CVPR). 20311\u201320322","author":"Danecek Radek","year":"2022","unstructured":"Radek Danecek , Michael\u00a0 J. Black , and Timo Bolkart . 2022 . EMOCA: Emotion Driven Monocular Face Capture and Animation. In Conference on Computer Vision and Pattern Recognition (CVPR). 20311\u201320322 . Radek Danecek, Michael\u00a0J. Black, and Timo Bolkart. 2022. EMOCA: Emotion Driven Monocular Face Capture and Animation. In Conference on Computer Vision and Pattern Recognition (CVPR). 20311\u201320322."},{"key":"e_1_3_2_1_8_1","volume-title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images. CoRR abs\/2012.04012","author":"Feng Yao","year":"2020","unstructured":"Yao Feng , Haiwen Feng , Michael\u00a0 J. Black , and Timo Bolkart . 2020. Learning an Animatable Detailed 3D Face Model from In-The-Wild Images. CoRR abs\/2012.04012 ( 2020 ). arXiv:2012.04012https:\/\/arxiv.org\/abs\/2012.04012 Yao Feng, Haiwen Feng, Michael\u00a0J. Black, and Timo Bolkart. 2020. Learning an Animatable Detailed 3D Face Model from In-The-Wild Images. CoRR abs\/2012.04012 (2020). arXiv:2012.04012https:\/\/arxiv.org\/abs\/2012.04012"},{"key":"e_1_3_2_1_9_1","unstructured":"Epic Gaming. [n. d.]. MetaHuman - Unreal Engine. https:\/\/www.unrealengine.com\/en-US\/metahuman. (Accessed on 04\/29\/2023).  Epic Gaming. [n. d.]. MetaHuman - Unreal Engine. https:\/\/www.unrealengine.com\/en-US\/metahuman. (Accessed on 04\/29\/2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Visual SceneMaker-a tool for authoring interactive virtual characters. Journal on Multimodal User Interfaces 6 (7","author":"Gebhard Patrick","year":"2012","unstructured":"Patrick Gebhard , Gregor Mehlmann , and Michael Kipp . 2012. Visual SceneMaker-a tool for authoring interactive virtual characters. Journal on Multimodal User Interfaces 6 (7 2012 ), 3\u201311. Issue 1-2. https:\/\/doi.org\/10.1007\/s12193-011-0077-1 10.1007\/s12193-011-0077-1 Patrick Gebhard, Gregor Mehlmann, and Michael Kipp. 2012. Visual SceneMaker-a tool for authoring interactive virtual characters. Journal on Multimodal User Interfaces 6 (7 2012), 3\u201311. Issue 1-2. https:\/\/doi.org\/10.1007\/s12193-011-0077-1"},{"key":"e_1_3_2_1_11_1","unstructured":"Charamel GmbH. [n. d.]. VuppetMaster\u00ae - interaktive 3D Avatare f\u00fcr Websites und Applikationen. https:\/\/vuppetmaster.de\/. (Accessed on 01\/06\/2023).  Charamel GmbH. [n. d.]. VuppetMaster\u00ae - interaktive 3D Avatare f\u00fcr Websites und Applikationen. https:\/\/vuppetmaster.de\/. (Accessed on 01\/06\/2023)."},{"key":"#cr-split#-e_1_3_2_1_12_1.1","doi-asserted-by":"crossref","unstructured":"Jonathan Gratch Anya Okhmatovskaia Francois Lamothe Stacy Marsella Mathieu Morales Rick Werf and Louis-Philippe Morency. 2006. Virtual Rapport. 14-27. https:\/\/doi.org\/10.1007\/11821830_2 10.1007\/11821830_2","DOI":"10.1007\/11821830_2"},{"key":"#cr-split#-e_1_3_2_1_12_1.2","doi-asserted-by":"crossref","unstructured":"Jonathan Gratch Anya Okhmatovskaia Francois Lamothe Stacy Marsella Mathieu Morales Rick Werf and Louis-Philippe Morency. 2006. Virtual Rapport. 14-27. https:\/\/doi.org\/10.1007\/11821830_2","DOI":"10.1007\/11821830_2"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"#cr-split#-e_1_3_2_1_14_1.1","doi-asserted-by":"crossref","unstructured":"Lixing Huang Louis-Philippe Morency and Jonathan Gratch. 2011. Virtual Rapport 2.0. 68-79. https:\/\/doi.org\/10.1007\/978-3-642-23974-8_8 10.1007\/978-3-642-23974-8_8","DOI":"10.1007\/978-3-642-23974-8_8"},{"key":"#cr-split#-e_1_3_2_1_14_1.2","doi-asserted-by":"crossref","unstructured":"Lixing Huang Louis-Philippe Morency and Jonathan Gratch. 2011. Virtual Rapport 2.0. 68-79. https:\/\/doi.org\/10.1007\/978-3-642-23974-8_8","DOI":"10.1007\/978-3-642-23974-8_8"},{"key":"e_1_3_2_1_15_1","unstructured":"Alphabet Inc.[n. d.]. google\/mediapipe: Cross-platform customizable ML solutions for live and streaming media.https:\/\/github.com\/google\/mediapipe. (Accessed on 04\/26\/2023).  Alphabet Inc.[n. d.]. google\/mediapipe: Cross-platform customizable ML solutions for live and streaming media.https:\/\/github.com\/google\/mediapipe. (Accessed on 04\/26\/2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Apple AR blendShapes. https:\/\/developer.apple.com\/documentation\/arkit\/arfaceanchor\/2928251-blendshapes. Accessed","author":"Apple Inc. 2022.","year":"2022","unstructured":"Apple Inc. 2022. Apple AR blendShapes. https:\/\/developer.apple.com\/documentation\/arkit\/arfaceanchor\/2928251-blendshapes. Accessed : 2022 . Apple Inc. 2022. Apple AR blendShapes. https:\/\/developer.apple.com\/documentation\/arkit\/arfaceanchor\/2928251-blendshapes. Accessed: 2022."},{"key":"#cr-split#-e_1_3_2_1_17_1.1","doi-asserted-by":"crossref","unstructured":"Kristiina Jokinen and Graham Wilcock. 2014. Multimodal Open-Domain Conversations with the Nao Robot. 213-224. https:\/\/doi.org\/10.1007\/978-1-4614-8280-2_19 10.1007\/978-1-4614-8280-2_19","DOI":"10.1007\/978-1-4614-8280-2_19"},{"key":"#cr-split#-e_1_3_2_1_17_1.2","doi-asserted-by":"crossref","unstructured":"Kristiina Jokinen and Graham Wilcock. 2014. Multimodal Open-Domain Conversations with the Nao Robot. 213-224. https:\/\/doi.org\/10.1007\/978-1-4614-8280-2_19","DOI":"10.1007\/978-1-4614-8280-2_19"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423911"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3054677"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/11821830_17"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"e_1_3_2_1_22_1","volume-title":"Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6","author":"Li Tianye","year":"2017","unstructured":"Tianye Li , Timo Bolkart , Michael.\u00a0 J. Black , Hao Li , and Javier Romero . 2017. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6 ( 2017 ), 194:1\u2013194:17. https:\/\/doi.org\/10.1145\/3130800.3130813 10.1145\/3130800.3130813 Tianye Li, Timo Bolkart, Michael.\u00a0J. Black, Hao Li, and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6 (2017), 194:1\u2013194:17. https:\/\/doi.org\/10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_23_1","volume-title":"3D multiscale physiological human","author":"Magnenat-Thalmann Nadia","unstructured":"Nadia Magnenat-Thalmann , Osman Ratib , and Hon\u00a0Fai Choi . 2013. 3D multiscale physiological human . Springer . Nadia Magnenat-Thalmann, Osman Ratib, and Hon\u00a0Fai Choi. 2013. 3D multiscale physiological human. Springer."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3628"},{"key":"#cr-split#-e_1_3_2_1_25_1.1","doi-asserted-by":"crossref","unstructured":"Yoichi Matsuyama Arjun Bhardwaj Ran Zhao Oscar Romero Sushma\u00a0Anand Akoju and Justine Cassell. 2016. Socially-Aware Animated Intelligent Personal Assistant Agent. 224-227. https:\/\/doi.org\/10.18653\/v1\/W16-3628 10.18653\/v1","DOI":"10.18653\/v1\/W16-3628"},{"key":"#cr-split#-e_1_3_2_1_25_1.2","doi-asserted-by":"crossref","unstructured":"Yoichi Matsuyama Arjun Bhardwaj Ran Zhao Oscar Romero Sushma\u00a0Anand Akoju and Justine Cassell. 2016. Socially-Aware Animated Intelligent Personal Assistant Agent. 224-227. https:\/\/doi.org\/10.18653\/v1\/W16-3628","DOI":"10.18653\/v1\/W16-3628"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/10720296"},{"key":"e_1_3_2_1_28_1","volume-title":"Facial Affective Behavior in Mental Disorder. Journal of Nonverbal Behavior 39 (12","author":"Peham Doris","year":"2015","unstructured":"Doris Peham , Astrid Bock , Cathrin Schiestl , Eva Huber , Johannes Zimmermann , Dietmar Kratzer , Reiner Dahlbender , Wilfried Biebl , and Cord Benecke . 2015. Facial Affective Behavior in Mental Disorder. Journal of Nonverbal Behavior 39 (12 2015 ), 371\u2013396. Issue 4. https:\/\/doi.org\/10.1007\/s10919-015-0216-6 10.1007\/s10919-015-0216-6 Doris Peham, Astrid Bock, Cathrin Schiestl, Eva Huber, Johannes Zimmermann, Dietmar Kratzer, Reiner Dahlbender, Wilfried Biebl, and Cord Benecke. 2015. Facial Affective Behavior in Mental Disorder. Journal of Nonverbal Behavior 39 (12 2015), 371\u2013396. Issue 4. https:\/\/doi.org\/10.1007\/s10919-015-0216-6"},{"key":"e_1_3_2_1_29_1","volume-title":"Biological sciences 364 (12","author":"Pelachaud Catherine","year":"2009","unstructured":"Catherine Pelachaud . 2009. Modelling Multimodal Expression of Emotion in a Virtual Agent. Philosophical transactions of the Royal Society of London. Series B , Biological sciences 364 (12 2009 ), 3539\u201348. https:\/\/doi.org\/10.1098\/rstb.2009.0186 10.1098\/rstb.2009.0186 Catherine Pelachaud. 2009. Modelling Multimodal Expression of Emotion in a Virtual Agent. Philosophical transactions of the Royal Society of London. Series B, Biological sciences 364 (12 2009), 3539\u201348. https:\/\/doi.org\/10.1098\/rstb.2009.0186"},{"key":"e_1_3_2_1_30_1","volume-title":"Multimodal Behavior Modeling for Socially Interactive Agents (1 ed.)","author":"Pelachaud Catherine","unstructured":"Catherine Pelachaud , Carlos Busso , and Dirk Heylen . 2021. Multimodal Behavior Modeling for Socially Interactive Agents (1 ed.) . Association for Computing Machinery , New York, NY, USA , Chapter\u00a01, 259\u2013310. https:\/\/doi.org\/10.1145\/3477322.3477331 10.1145\/3477322.3477331 Catherine Pelachaud, Carlos Busso, and Dirk Heylen. 2021. Multimodal Behavior Modeling for Socially Interactive Agents (1 ed.). Association for Computing Machinery, New York, NY, USA, Chapter\u00a01, 259\u2013310. https:\/\/doi.org\/10.1145\/3477322.3477331"},{"key":"e_1_3_2_1_31_1","volume-title":"Nonverbal synchrony of head-and body-movement in psychotherapy: different signals have different associations with outcome. Frontiers in psychology 5","author":"Ramseyer Fabian","year":"2014","unstructured":"Fabian Ramseyer and Wolfgang Tschacher . 2014. Nonverbal synchrony of head-and body-movement in psychotherapy: different signals have different associations with outcome. Frontiers in psychology 5 ( 2014 ), 979. Fabian Ramseyer and Wolfgang Tschacher. 2014. Nonverbal synchrony of head-and body-movement in psychotherapy: different signals have different associations with outcome. Frontiers in psychology 5 (2014), 979."},{"key":"e_1_3_2_1_32_1","volume-title":"The Media Equation: How People Treat Computers, Television, and New Media like Real People and Places","author":"Reeves Byron","unstructured":"Byron Reeves and Clifford Nass . 1996. The Media Equation: How People Treat Computers, Television, and New Media like Real People and Places . Cambridge University Press , USA. Byron Reeves and Clifford Nass. 1996. The Media Equation: How People Treat Computers, Television, and New Media like Real People and Places. Cambridge University Press, USA."},{"key":"e_1_3_2_1_33_1","unstructured":"Mark Sagar Alecia Moser and Annette Henderson. [n. d.]. Digital People - The Future of CX - Soul Machines. https:\/\/www.soulmachines.com\/. (Accessed on 04\/29\/2023).  Mark Sagar Alecia Moser and Annette Henderson. [n. d.]. Digital People - The Future of CX - Soul Machines. https:\/\/www.soulmachines.com\/. (Accessed on 04\/29\/2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00795"},{"key":"#cr-split#-e_1_3_2_1_35_1.1","doi-asserted-by":"crossref","unstructured":"Henning Schauenburg and Tilman Grande. 2000. Operationalisierte Psychodynamische Diagnostik - OPD. 55-73. https:\/\/doi.org\/10.1007\/978-3-7091-6767-0_4 10.1007\/978-3-7091-6767-0_4","DOI":"10.1007\/978-3-7091-6767-0_4"},{"key":"#cr-split#-e_1_3_2_1_35_1.2","doi-asserted-by":"crossref","unstructured":"Henning Schauenburg and Tilman Grande. 2000. Operationalisierte Psychodynamische Diagnostik - OPD. 55-73. https:\/\/doi.org\/10.1007\/978-3-7091-6767-0_4","DOI":"10.1007\/978-3-7091-6767-0_4"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322201"},{"key":"e_1_3_2_1_37_1","unstructured":"Justus Thies Michael Zollh\u00f6fer Marc Stamminger Christian Theobalt and Matthias Nie\u00dfner. 2020. Face2Face: Real-time Face Capture and Reenactment of RGB Videos. arxiv:2007.14808\u00a0[cs.CV]  Justus Thies Michael Zollh\u00f6fer Marc Stamminger Christian Theobalt and Matthias Nie\u00dfner. 2020. Face2Face: Real-time Face Capture and Reenactment of RGB Videos. arxiv:2007.14808\u00a0[cs.CV]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267918"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00109-5"}],"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\/3577190.3614133","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577190.3614133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:01Z","timestamp":1750178221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3614133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":44,"alternative-id":["10.1145\/3577190.3614133","10.1145\/3577190"],"URL":"https:\/\/doi.org\/10.1145\/3577190.3614133","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"}}]}}