{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T21:29:31Z","timestamp":1780090171629,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ERC","award":["801708"],"award-info":[{"award-number":["801708"]}]},{"name":"BMBF","award":["01IS20075"],"award-info":[{"award-number":["01IS20075"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3479219","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T11:31:01Z","timestamp":1634556661000},"page":"4878-4882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["MultiMediate"],"prefix":"10.1145","author":[{"given":"Philipp","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"DFKI GmbH, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Dietz","sequence":"additional","affiliation":[{"name":"Augsburg University, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Schiller","sequence":"additional","affiliation":[{"name":"Augsburg University, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominike","family":"Thomas","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanhua","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Gebhard","sequence":"additional","affiliation":[{"name":"DFKI GmbH, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Bulling","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.69"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979070"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_4_1","volume-title":"Frontiers in Psychology","volume":"8","author":"Barthel M.","year":"2017","unstructured":"M. Barthel , A. S. Meyer , and S. C. Levinson . 2017. Next Speakers Plan Their Turn Early and Speak after Turn-Final ?Go-Signals \". Frontiers in Psychology , Vol. 8 ( 2017 ). https:\/\/doi.org\/10.3389\/fpsyg.2017.00393 10.3389\/fpsyg.2017.00393 M. Barthel, A. S. Meyer, and S. C. Levinson. 2017. Next Speakers Plan Their Turn Early and Speak after Turn-Final ?Go-Signals\". Frontiers in Psychology, Vol. 8 (2017). https:\/\/doi.org\/10.3389\/fpsyg.2017.00393"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2740062"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"C. Birmingham Z. Hu K. Mahajan E. Reber and M. J. Mataric. 2020. Can I Trust You? A User Study of Robot Mediation of a Support Group. arXiv preprint arXiv:2002.04671 (2020).  C. Birmingham Z. Hu K. Mahajan E. Reber and M. J. Mataric. 2020. Can I Trust You? A User Study of Robot Mediation of a Support Group. arXiv preprint arXiv:2002.04671 (2020).","DOI":"10.1109\/ICRA40945.2020.9196875"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1891903.1891910"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2019.05.035"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/0163853X.2017.1330031"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/01690965.2011.615220"},{"key":"e_1_3_2_1_12_1","first-page":"268","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Ekstedt E.","year":"1865","unstructured":"E. Ekstedt and G. Skantze . 2020. TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog . In Findings of the Association for Computational Linguistics: EMNLP 2020 . Association for Computational Linguistics, Online, 2981--2990. https:\/\/doi.org\/10. 1865 3\/v1\/2020.findings-emnlp. 268 10.18653\/v1 E. Ekstedt and G. Skantze. 2020. TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, Online, 2981--2990. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.268"},{"key":"#cr-split#-e_1_3_2_1_13_1.1","doi-asserted-by":"crossref","unstructured":"O. Engwall and J. Lopes. 2020. Interaction and collaboration in robot-assisted language learning for adults. Computer Assisted Language Learning (2020) 1--37. https:\/\/doi.org\/10.1080\/09588221.2020.1799821 10.1080\/09588221.2020.1799821","DOI":"10.1080\/09588221.2020.1799821"},{"key":"#cr-split#-e_1_3_2_1_13_1.2","doi-asserted-by":"crossref","unstructured":"O. Engwall and J. Lopes. 2020. Interaction and collaboration in robot-assisted language learning for adults. Computer Assisted Language Learning (2020) 1--37. https:\/\/doi.org\/10.1080\/09588221.2020.1799821","DOI":"10.1080\/09588221.2020.1799821"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415157"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/1088868312472607"},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing. 2319--2323","author":"Ishii R.","year":"2015","unstructured":"R. Ishii , S. Kumano , and K. Otsuka . 2015. Predicting next speaker based on head movement in multi-party meetings . In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing. 2319--2323 . https:\/\/doi.org\/10.1109\/ICASSP. 2015 .7178385 10.1109\/ICASSP.2015.7178385 R. Ishii, S. Kumano, and K. Otsuka. 2015. Predicting next speaker based on head movement in multi-party meetings. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing. 2319--2323. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178385"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/mti3040070"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2522856"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2757284"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499474.2499481"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. Annual Conference of the International Speech Communication Association","volume":"1","author":"Kawahara T.","year":"2012","unstructured":"T. Kawahara , T. Iwatate , and K. Takanashi . 2012. Prediction of turn-taking by combining prosodic and eye-gaze information in poster conversations . Proc. Annual Conference of the International Speech Communication Association , Vol. 1 ( 2012 ), 726--729. T. Kawahara, T. Iwatate, and K. Takanashi. 2012. Prediction of turn-taking by combining prosodic and eye-gaze information in poster conversations. Proc. Annual Conference of the International Speech Communication Association, Vol. 1 (2012), 726--729."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0001-6918(67)90005-4"},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. ISCA workshop on Speech and Language Technology in Education. https:\/\/doi.org\/10","author":"Lopes J.","unstructured":"J. Lopes , O. Engwall , and G. Skantze . 2017. A first visit to the robot language caf\u00e9 . In Proc. ISCA workshop on Speech and Language Technology in Education. https:\/\/doi.org\/10 .1007\/s12369-020-00635-y 10.1007\/s12369-020-00635-y J. Lopes, O. Engwall, and G. Skantze. 2017. A first visit to the robot language caf\u00e9. In Proc. ISCA workshop on Speech and Language Technology in Education. https:\/\/doi.org\/10.1007\/s12369-020-00635-y"},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. IEEE International Conference on Tools with Artificial Intelligence. 349--354","author":"Malik U.","year":"2020","unstructured":"U. Malik , J. Saunier , K. Funakoshi , and A. Pauchet . 2020. Who Speaks Next? Turn Change and Next Speaker Prediction in Multimodal Multiparty Interaction . In Proc. IEEE International Conference on Tools with Artificial Intelligence. 349--354 . https:\/\/doi.org\/10.1109\/ICTAI50040. 2020 .00062 10.1109\/ICTAI50040.2020.00062 U. Malik, J. Saunier, K. Funakoshi, and A. Pauchet. 2020. Who Speaks Next? Turn Change and Next Speaker Prediction in Multimodal Multiparty Interaction. In Proc. IEEE International Conference on Tools with Artificial Intelligence. 349--354. https:\/\/doi.org\/10.1109\/ICTAI50040.2020.00062"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/1461445607075346"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353721"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204549"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172969"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242973"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088463.1088497"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376450"},{"key":"e_1_3_2_1_32_1","unstructured":"V. Petukhova and H. Bunt. 2009. 'Who's next? Speaker-selection mechanisms in multiparty dialogue'. In DiaHolmia. Stockholm Sweden 19--26.  V. Petukhova and H. Bunt. 2009. 'Who's next? Speaker-selection mechanisms in multiparty dialogue'. In DiaHolmia. Stockholm Sweden 19--26."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242997"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2557500.2557507"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415247"},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. IEEE International Symposium on Robot and Human Interactive Communication. 385--390","author":"Short E.","year":"2017","unstructured":"E. Short and M. J. Mataric . 2017. Robot moderation of a collaborative game: Towards socially assistive robotics in group interactions . In Proc. IEEE International Symposium on Robot and Human Interactive Communication. 385--390 . https:\/\/doi.org\/10.1109\/ROMAN. 2017 .8172331 10.1109\/ROMAN.2017.8172331 E. Short and M. J. Mataric. 2017. Robot moderation of a collaborative game: Towards socially assistive robotics in group interactions. In Proc. IEEE International Symposium on Robot and Human Interactive Communication. 385--390. https:\/\/doi.org\/10.1109\/ROMAN.2017.8172331"},{"key":"e_1_3_2_1_37_1","first-page":"17","volume-title":"Proc. Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics","author":"Skantze G.","year":"2017","unstructured":"G. Skantze . 2017 . Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LS\u2122 Recurrent Neural Networks . In Proc. Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics , Saarbr\u00fccken, Germany, 220--230. https:\/\/doi.org\/10. 18653\/v1\/W 17 - 5527 10.18653\/v1 G. Skantze. 2017. Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LS\u2122 Recurrent Neural Networks. In Proc. Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, Saarbr\u00fccken, Germany, 220--230. https:\/\/doi.org\/10.18653\/v1\/W17-5527"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0903616106"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351529.3360660"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353761"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126614"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2778103"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479219","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3479219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:48Z","timestamp":1750193328000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479219"}},"subtitle":["Multi-modal Group Behaviour Analysis for Artificial Mediation"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":44,"alternative-id":["10.1145\/3474085.3479219","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3479219","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}