{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:16:59Z","timestamp":1772111819784,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["(NO.61425017"],"award-info":[{"award-number":["(NO.61425017"]}]},{"name":"National Natural Science Foundation of China","award":["No.61332017"],"award-info":[{"award-number":["No.61332017"]}]},{"name":"National Natural Science Foundation of China","award":["No.61773379"],"award-info":[{"award-number":["No.61773379"]}]},{"name":"National Natural Science Foundation of China","award":["No.61603390"],"award-info":[{"award-number":["No.61603390"]}]},{"name":"National Natural Science Foundation of China","award":["No.61771472"],"award-info":[{"award-number":["No.61771472"]}]},{"name":"National Key Research & Development Plan of China","award":["No. 2016YFB1001404"],"award-info":[{"award-number":["No. 2016YFB1001404"]}]},{"name":"Major Program for the National Social Science Fund of China","award":["13&ZD189"],"award-info":[{"award-number":["13&ZD189"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3266302.3266305","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T14:19:29Z","timestamp":1539872369000},"page":"91-98","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Deep Learning for Continuous Multiple Time Series Annotations"],"prefix":"10.1145","author":[{"given":"Jian","family":"Huang","sequence":"first","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyue","family":"Niu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"R. Cowie C. E. Douglas N. Tsapatsoulis etal 2001. Emotion recognition in human-computer interaction. IEEE Signal processing magazine 18(1): 32--80.  R. Cowie C. E. Douglas N. Tsapatsoulis et al. 2001. Emotion recognition in human-computer interaction. IEEE Signal processing magazine 18(1): 32--80.","DOI":"10.1109\/79.911197"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661811"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133946"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2015.2457417"},{"key":"e_1_3_2_1_6_1","volume-title":"Investigation of Bottle-Neck Features for Emotion Recognition. International Conference on Text, Speech, and Dialogue. Springer International Publishing, 426--434","author":"Popkov\u00e1 A.","year":"2016","unstructured":"A. Popkov\u00e1 , F. Povoln\u00fd , P. Matejka , 2016 . Investigation of Bottle-Neck Features for Emotion Recognition. International Conference on Text, Speech, and Dialogue. Springer International Publishing, 426--434 . A. Popkov\u00e1, F. Povoln\u00fd, P. Matejka, et al. 2016. Investigation of Bottle-Neck Features for Emotion Recognition. International Conference on Text, Speech, and Dialogue. Springer International Publishing, 426--434."},{"key":"e_1_3_2_1_7_1","volume-title":"Soundnet: Learning sound representations from unlabeled video. Advances in Neural Information Processing Systems, 892--900.","author":"Aytar Y.","year":"2016","unstructured":"Y. Aytar , C. Vondrick , A. Torralba . 2016 . Soundnet: Learning sound representations from unlabeled video. Advances in Neural Information Processing Systems, 892--900. Y. Aytar, C. Vondrick, A. Torralba. 2016. Soundnet: Learning sound representations from unlabeled video. Advances in Neural Information Processing Systems, 892--900."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.65"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988270"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806408"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019533"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.4018\/jse.2010101605"},{"key":"e_1_3_2_1_15_1","volume-title":"Thirteenth Annual Conference of the International Speech Communication Association.","author":"Viktor R.","year":"2012","unstructured":"R. Viktor , A. Sankaranarayanan , S. Shirin , K. Rohit , 2012 . Emotion recognition using acoustic and lexical features . In Thirteenth Annual Conference of the International Speech Communication Association. R. Viktor, A. Sankaranarayanan, S. Shirin, K. Rohit, et al. 2012. Emotion recognition using acoustic and lexical features. In Thirteenth Annual Conference of the International Speech Communication Association."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349500"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2656408"},{"key":"e_1_3_2_1_19_1","volume-title":"MEC 2016: The multimodal emotion recognition challenge of CCPR 2016. In Proc. Chinese Conference on Pattern Recognition","author":"Ya L.","year":"2016","unstructured":"L. Ya , T. Jianhua , S. Bj\u00f6rn , 2016 . MEC 2016: The multimodal emotion recognition challenge of CCPR 2016. In Proc. Chinese Conference on Pattern Recognition . Chengdu, China, 667--678 L. Ya, T. Jianhua, S. Bj\u00f6rn, et al. 2016. MEC 2016: The multimodal emotion recognition challenge of CCPR 2016. In Proc. Chinese Conference on Pattern Recognition. Chengdu, China, 667--678"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24033-6_1"},{"key":"e_1_3_2_1_21_1","volume-title":"Crowdsourcing: Why the Power of the Crowd is Driving the Future of Business.","author":"Sindlinger T. S.","year":"2010","unstructured":"T. S. Sindlinger . 2010 . Crowdsourcing: Why the Power of the Crowd is Driving the Future of Business. T. S. Sindlinger. 2010. Crowdsourcing: Why the Power of the Crowd is Driving the Future of Business."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"A. P. Dawid A. M. Skene. 1979. Maximum likelihood estimation of observer error-rates using the EM algorithm. Applied statistics 20--28.  A. P. Dawid A. M. Skene. 1979. Maximum likelihood estimation of observer error-rates using the EM algorithm. Applied statistics 20--28.","DOI":"10.2307\/2346806"},{"key":"e_1_3_2_1_24_1","article-title":"Maximum likelihood from incomplete data via the em algorithm","author":"Arthur P. D.","year":"1977","unstructured":"P. D. Arthur , M. L. Nan , B. R. Donald . 1977 . Maximum likelihood from incomplete data via the em algorithm . Journal of the Royal Statistical Society. Series B (Methodological). P. D. Arthur, M. L. Nan, B. R. Donald. 1977. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological).","journal-title":"Journal of the Royal Statistical Society. Series B (Methodological)."},{"key":"e_1_3_2_1_25_1","unstructured":"J. Whitehill T. Wu J. Bergsma etal 2009. Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. Advances in neural information processing systems 2035--2043.   J. Whitehill T. Wu J. Bergsma et al. 2009. Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. Advances in neural information processing systems 2035--2043."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1837885.1837906"},{"key":"e_1_3_2_1_27_1","unstructured":"P. Smyth U. Fayyad M. Burl etal 1995. Learning with probabilistic supervision. Computational learning theory and natural learning systems 3: 163--182.  P. Smyth U. Fayyad M. Burl et al. 1995. Learning with probabilistic supervision. Computational learning theory and natural learning systems 3: 163--182."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859894"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5412-1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.05.012"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2029604.2029625"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566530"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2334294"},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Feng Z.","unstructured":"Z. Feng and D. Fernando . 2009. Canonical time warping for alignment of human behavior . In Proc. Advances in Neural Information Processing Systems . Vancouver, Canada, 2286--2294. Z. Feng and D. Fernando. 2009. Canonical time warping for alignment of human behavior. In Proc. Advances in Neural Information Processing Systems. Vancouver, Canada, 2286--2294."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_8"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2414429"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2592918"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123383"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-512"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461321"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"M. Y. Guan V. Gulshan A. M. Dai etal 2017. Who said what: Modeling individual labelers improves classification. arXiv preprint arXiv:1703.08774.  M. Y. Guan V. Gulshan A. M. Dai et al. 2017. Who said what: Modeling individual labelers improves classification. arXiv preprint arXiv:1703.08774.","DOI":"10.1609\/aaai.v32i1.11756"},{"key":"e_1_3_2_1_42_1","unstructured":"F. Rodrigues F. Pereira. 2017. Deep learning from crowds. arXiv preprint arXiv:1709.01779.  F. Rodrigues F. Pereira. 2017. Deep learning from crowds. arXiv preprint arXiv:1709.01779."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"e_1_3_2_1_46_1","unstructured":"S. Maximilian B. Schuller. 2016. openXBOW -- Introducing the Passau open-source crossmodal Bag-of-Words toolkit. preprint arXiv:1605.06778.  S. Maximilian B. Schuller. 2016. openXBOW -- Introducing the Passau open-source crossmodal Bag-of-Words toolkit. preprint arXiv:1605.06778."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"e_1_3_2_1_48_1","unstructured":"M. D. Zeiler. 2012. ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701.  M. D. Zeiler. 2012. ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701."}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2018 on Audio\/Visual Emotion Challenge and Workshop"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3266302.3266305","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3266302.3266305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:26:51Z","timestamp":1750278411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3266302.3266305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":48,"alternative-id":["10.1145\/3266302.3266305","10.1145\/3266302"],"URL":"https:\/\/doi.org\/10.1145\/3266302.3266305","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}