{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T10:37:21Z","timestamp":1771670241662,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ETH Zurich Research Grant","award":["ETH-10 22-1"],"award-info":[{"award-number":["ETH-10 22-1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,4]]},"DOI":"10.1145\/3678957.3685759","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:35:53Z","timestamp":1730262953000},"page":"12-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["On Multimodal Emotion Recognition for Human-Chatbot Interaction in the Wild"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1337-7670","authenticated-orcid":false,"given":"Nikola","family":"Kovacevic","sequence":"first","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9655-9519","authenticated-orcid":false,"given":"Christian","family":"Holz","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9324-779X","authenticated-orcid":false,"given":"Markus","family":"Gross","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-1305","authenticated-orcid":false,"given":"Rafael","family":"Wampfler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-023-00340-7"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3143803"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534573"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/eng2.12189"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6695-0_9"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2022.200171"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74628-7_27"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/10494820.2014.908927"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4337484"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161175"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7916(94)90063-9"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2092"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-2005"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300705"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2019.8791893"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1810.04805"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.99.3.550"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","unstructured":"Paul Ekman and Wallace\u00a0V. Friesen. 1978. Facial Action Coding System. https:\/\/doi.org\/10.1037\/t27734-000","DOI":"10.1037\/t27734-000"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267896"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_25_1","unstructured":"Ulrich Gnewuch Stefan Morana and Alexander Maedche. 2017. Towards Designing Cooperative and Social Conversational Agents for Customer Service.. In ICIS. 1\u201313."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21155015"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.005"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.102423"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/jintelligence11010006"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.60.110707.163539"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00307-3"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77712-2_23"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18020401"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sigdial-1.9"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00464-x"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3659626"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.370"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Greg Kondrak and Taro Watanabe (Eds.). Asian Federation of Natural Language Processing","author":"Li Yanran","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Greg Kondrak and Taro Watanabe (Eds.). Asian Federation of Natural Language Processing, Taipei, Taiwan, 986\u2013995. https:\/\/aclanthology.org\/I17-1099"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. https:\/\/doi.org\/10.48550\/ARXIV.1907.11692","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536220.3563687"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490399"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569483"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2017.2740923"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2017.64"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2929050"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596269"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2021.102630"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-x"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448117"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00263"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","unstructured":"Steffen Schneider Alexei Baevski Ronan Collobert and Michael Auli. 2019. wav2vec: Unsupervised Pre-training for Speech Recognition. https:\/\/doi.org\/10.48550\/ARXIV.1904.05862","DOI":"10.48550\/ARXIV.1904.05862"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51645-5_1"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3026823"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40359-018-0257-9"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14000-6_2"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501835"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110285"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","unstructured":"Olivia Wiles A.\u00a0Sophia Koepke and Andrew Zisserman. 2018. Self-supervised learning of a facial attribute embedding from video. https:\/\/doi.org\/10.48550\/ARXIV.1808.06882","DOI":"10.48550\/ARXIV.1808.06882"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2020.3005660"},{"key":"e_1_3_2_2_65_1","unstructured":"U. Zarins. 2019. Anatomy of Facial Expression. Anatomy Next Incorporated. 136\u2013196 pages. https:\/\/books.google.ch\/books?id=8UV5zQEACAAJ"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388790"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03705-0"}],"event":{"name":"ICMI '24: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"San Jose Costa Rica","acronym":"ICMI '24"},"container-title":["International Conference on Multimodel Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685759","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678957.3685759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:12Z","timestamp":1750295412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":67,"alternative-id":["10.1145\/3678957.3685759","10.1145\/3678957"],"URL":"https:\/\/doi.org\/10.1145\/3678957.3685759","relation":{},"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2024-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}