{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T21:31:55Z","timestamp":1780090315295,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["801708"],"award-info":[{"award-number":["801708"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"German Research Foundation","award":["EXC 2075 ? 39074001"],"award-info":[{"award-number":["EXC 2075 ? 39074001"]}]},{"name":"European Union Horizon Europe","award":["101078950"],"award-info":[{"award-number":["101078950"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["AN 559\/10-1"],"award-info":[{"award-number":["AN 559\/10-1"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"French National Research Agency","award":["ANR-15-IDEX-01"],"award-info":[{"award-number":["ANR-15-IDEX-01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3689004","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"11377-11382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["<scp>MultiMediate'24:<\/scp>\n            Multi-Domain Engagement Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7037-7100","authenticated-orcid":false,"given":"Philipp","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"DFKI, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7153-9984","authenticated-orcid":false,"given":"Michal","family":"Balazia","sequence":"additional","affiliation":[{"name":"INRIA Sophia Antipolis, Sophia Antipolis, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2797-605X","authenticated-orcid":false,"given":"Tobias","family":"Baur","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7986-6744","authenticated-orcid":false,"given":"Michael","family":"Dietz","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2074-4280","authenticated-orcid":false,"given":"Alexander","family":"Heimerl","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8570-0007","authenticated-orcid":false,"given":"Anna","family":"Penzkofer","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7364-5772","authenticated-orcid":false,"given":"Dominik","family":"Schiller","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2988-2142","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Br\u00e9mond","sequence":"additional","affiliation":[{"name":"INRIA Sophia Antipolis, Sophia Antipolis, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6676-3145","authenticated-orcid":false,"given":"Jan","family":"Alexandersson","sequence":"additional","affiliation":[{"name":"DFKI, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2367-162X","authenticated-orcid":false,"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[{"name":"University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6317-7303","authenticated-orcid":false,"given":"Andreas","family":"Bulling","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Backchannel Detection and Agreement Estimation from Video with Transformer Networks. arXiv preprint arXiv:2306.01656","author":"Amer Ahmed","year":"2023","unstructured":"Ahmed Amer, Chirag Bhuvaneshwara, Gowtham K Addluri, Mohammed M Shaik, Vedant Bonde, and Philipp M\u00fcller. 2023. Backchannel Detection and Agreement Estimation from Video with Transformer Networks. arXiv preprint arXiv:2306.01656 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio. INTERSPEECH 2023","author":"Bain Max","year":"2023","unstructured":"Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. 2023. WhisperX: Time-Accurate Speech Transcription of Long-Form Audio. INTERSPEECH 2023 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548363"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_5_1","volume-title":"David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, et al.","author":"Barrault Lo\u00efc","year":"2023","unstructured":"Lo\u00efc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, et al. 2023. Seamless: Multilingual Expressive and Streaming Speech Translation. arXiv preprint arXiv:2312.05187 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2401836.2401846"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136780"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_9_1","volume-title":"Unsupervised Cross-lingual Representation Learning at Scale. CoRR","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised Cross-lingual Representation Learning at Scale. CoRR, Vol. abs\/1911.02116 (2019). showeprint[arXiv]1911.02116 http:\/\/arxiv.org\/abs\/1911.02116"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10648-019-09514-z"},{"key":"e_1_3_2_1_12_1","unstructured":"Pooja Guhan Naman Awasthi Kristin Bussell Dinesh Manocha Gloria Reeves Aniket Bera et al. 2020. Developing an Effective and Automated Patient Engagement Estimator for Telehealth: A Machine Learning Approach. arXiv preprint arXiv:2011.08690 (2020)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647692"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaz3791"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78114-9_19"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688986"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688988"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612856"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688987"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613851"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551589"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479219"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204549"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172969"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00092"},{"key":"e_1_3_2_1_27_1","unstructured":"Tom O'Malley Elie Bursztein James Long Franccois Chollet Haifeng Jin Luca Invernizzi et al. 2019. KerasTuner. https:\/\/github.com\/keras-team\/keras-tuner."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301687"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163129"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453163"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957781"},{"key":"e_1_3_2_1_34_1","volume-title":"Elisabeth Andr\u00e9, and Tobias Baur.","author":"Schiller Dominik","year":"2024","unstructured":"Dominik Schiller, Tobias Hallmen, Daksitha Withanage Don, Elisabeth Andr\u00e9, and Tobias Baur. 2024. DISCOVER: A Data-driven Interactive System for Comprehensive Observation, Visualization, and ExploRation of Human Behaviour. arXiv preprint arXiv:2407.13408 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612857"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612873"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612852"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3689004","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3689004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3689004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":38,"alternative-id":["10.1145\/3664647.3689004","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3689004","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}