{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T19:16:43Z","timestamp":1772738203708,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Fund of China","award":["62171183"],"award-info":[{"award-number":["62171183"]}]},{"name":"National Natural Science Fund of China","award":["62221002"],"award-info":[{"award-number":["62221002"]}]},{"name":"Hunan Provincial Natural Science Foundation of China","award":["2022JJ20017"],"award-info":[{"award-number":["2022JJ20017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612847","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9472-9476","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-scale Conformer Fusion Network for Multi-participant Behavior Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3115-0672","authenticated-orcid":false,"given":"Qiya","family":"Song","sequence":"first","affiliation":[{"name":"Hunan university, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9197-6292","authenticated-orcid":false,"given":"Renwei","family":"Dian","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7029-8784","authenticated-orcid":false,"given":"Bin","family":"Sun","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4710-4275","authenticated-orcid":false,"given":"Jie","family":"Xie","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0585-9848","authenticated-orcid":false,"given":"Shutao","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00339"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548363"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479213"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131902"},{"key":"e_1_3_2_1_6_1","volume-title":"Coordinating utterances during turn-taking: The role of prediction, response preparation, and articulation. Discourse processes","author":"Ruth E Corps","year":"2018","unstructured":"Ruth E Corps, Chiara Gambi, and Martin J Pickering. 2018. Coordinating utterances during turn-taking: The role of prediction, response preparation, and articulation. Discourse processes, Vol. 55, 2 (2018), 230--240."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/01690965.2011.615220"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479230"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178385"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/mti3040070"},{"key":"e_1_3_2_1_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_13_1","volume-title":"Gaze and eye contact: a research review. Psychological bulletin","author":"Kleinke Chris L","year":"1986","unstructured":"Chris L Kleinke. 1986. Gaze and eye contact: a research review. Psychological bulletin, Vol. 100, 1 (1986), 78."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967747"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.239"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613851"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551589"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479219"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172969"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204549"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379155.3391332"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376450"},{"key":"e_1_3_2_1_25_1","volume-title":"Workshop on the Semantics and Pragmatics of Dialogue.","author":"Petukhova Volha","year":"2009","unstructured":"Volha Petukhova and Harry Bunt. 2009. Who's next? Speaker-selection mechanisms in multiparty dialogue. In Workshop on the Semantics and Pragmatics of Dialogue."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00290"},{"key":"e_1_3_2_1_27_1","volume-title":"Investigating speech features for continuous turn-taking prediction using lstms. arXiv preprint arXiv:1806.11461","author":"Roddy Matthew","year":"2018","unstructured":"Matthew Roddy, Gabriel Skantze, and Naomi Harte. 2018. Investigating speech features for continuous turn-taking prediction using lstms. arXiv preprint arXiv:1806.11461 (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820749"},{"key":"e_1_3_2_1_29_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747056"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353761"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612847","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:15Z","timestamp":1755821655000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":31,"alternative-id":["10.1145\/3581783.3612847","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612847","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}