{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:26:35Z","timestamp":1781144795669,"version":"3.54.1"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1109\/taffc.2021.3097002","type":"journal-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T19:12:41Z","timestamp":1629832361000},"page":"1334-1350","source":"Crossref","is-referenced-by-count":65,"title":["The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3761-2225","authenticated-orcid":false,"given":"Lukas","family":"Stappen","sequence":"first","affiliation":[{"name":"EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alice","family":"Baird","sequence":"additional","affiliation":[{"name":"EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-569X","authenticated-orcid":false,"given":"Lea","family":"Schumann","sequence":"additional","affiliation":[{"name":"EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[{"name":"EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-017-0915-5"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/0963721411422522"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10619-010-7077-0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1177\/2056305118786720"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2020.00025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3414\/ME0617"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS.1997.647126"},{"key":"ref54","first-page":"1556","article-title":"Elan: A professional framework for multimodality research","author":"wittenburg","year":"2006","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref51","first-page":"353","article-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21416"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-0404"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-100508-8.00009-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663260"},{"key":"ref43","article-title":"A multimodal movie review corpus for fine-grained opinion mining","author":"garcia","year":"2019"},{"key":"ref49","first-page":"1","article-title":"Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface","author":"kollias","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296543"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref4","article-title":"Most famous social network sites worldwide as of july 2019, ranked by number of active users (in millions)","author":"clement","year":"2019"},{"key":"ref3","article-title":"Facebook tests video feed to sidestep youtube with friendly discovery","author":"constine","year":"2019"},{"key":"ref6","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2016908452"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1453\/1\/012092"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2012.07.006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2017.10.002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5213"},{"key":"ref36","first-page":"79","article-title":"Towards multimodal emotion recognition in german speech events in cars using transfer learning","author":"cevher","year":"2019","journal-title":"in Proc Conf Nat Lang Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.26"},{"key":"ref33","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref32","first-page":"1801","article-title":"Moseas: A multimodal language dataset for spanish, portuguese, german and french","author":"zadeh","year":"2020","journal-title":"Proc Conf Empirical Methods Nat Lang Process"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4_13"},{"key":"ref38","first-page":"973","article-title":"Utterance-level multimodal sentiment analysis","author":"p\u00e9rez-rosas","year":"2013","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74889-2_43"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.02.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref20","article-title":"Deep learning for sentiment analysis: An overview and perspectives","author":"karas","year":"2020","journal-title":"Natural Language Processing for Global and Local Business"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607572"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref13","article-title":"Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"zadeh","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-51"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00126"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901779"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04559-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0007313503680376"},{"key":"ref17","first-page":"35","article-title":"Muse 2020 challenge and workshop: Multimodal sentiment analysis, emotion-target engagement and trustworthiness detection in real-life media","author":"stappen","year":"2020","journal-title":"Proc Int Multimodal Sentiment Anal Real-life Media Challenge Workshop Co-located ACM Int Conf Multimedia"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925452"},{"key":"ref92","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref95","article-title":"Proceedings of grand challenge and workshop on human multimodal language (challenge-hml)","author":"zadeh","year":"2018","journal-title":"Proc Grand Challenge Workshop Hum Multimodal Lang"},{"key":"ref94","article-title":"Multimodal fusion with attention mechanism for trustworthiness prediction in car advertisements","author":"yang","year":"2020","journal-title":"Proc 9th Int Conf Smart Media Appl"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref90","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref88","first-page":"1","article-title":"OpenFace: An open source facial behavior analysis toolkit","author":"baltru\u0161aitis","year":"2016","journal-title":"Proc IEEE Winter Conf Appl Comput Vis"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref82","article-title":"On many-to-many mapping between concordance correlation coefficient and mean square error","author":"pandit","year":"2019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3421901"},{"key":"ref83","doi-asserted-by":"crossref","first-page":"255","DOI":"10.2307\/2532051","article-title":"A concordance correlation coefficient to evaluate reproducibility","volume":"45","author":"lawrence","year":"1989","journal-title":"Biometrics"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref75","article-title":"Go-card–generic, optical car part recognition and detection: Collection, insights, and applications","author":"stappen","year":"2020"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2836924"},{"key":"ref74","first-page":"9175","article-title":"Learning intelligent dialogs for bounding box annotation","author":"konyushkova","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-017-0935-z"},{"key":"ref77","article-title":"Deep audio-visual speech recognition","volume":"abs 1809 2108","author":"afouras","year":"2018","journal-title":"CoRR"},{"key":"ref102","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.552"},{"key":"ref2","article-title":"Internet video to account for 80% of global traffic by 2019","author":"roesler","year":"2019"},{"key":"ref1","article-title":"Cisco visual networking index: Forecast and trends, 2017–2022 white paper","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"key":"ref70","first-page":"287","article-title":"Extracting textual overlays from social media videos using neural networks","author":"s?ucki","year":"2018","journal-title":"Proc Int Conf Comput Vis Graph"},{"key":"ref73","first-page":"40","article-title":"Crowdsourcing annotations for visual object detection","author":"su","year":"2012","journal-title":"Proc Workshops AAAI Conf Artif Intell"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973811"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-381"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.007"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36806-6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2497700"},{"key":"ref66","first-page":"2156","article-title":"Introducing the weighted trustability evaluator for crowdsourcing exemplified by speaker likability classification","author":"hantke","year":"2016","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566530"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1086\/291373"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.92.4.909"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2016.05.008"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10138707\/09484711.pdf?arnumber=9484711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:10:37Z","timestamp":1687198237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9484711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":105,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2021.3097002","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]}}}