{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:05:33Z","timestamp":1772553933125,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"IBM","award":["4915012629"],"award-info":[{"award-number":["4915012629"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2019,4,1]]},"DOI":"10.1109\/taffc.2017.2702653","type":"journal-article","created":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T21:38:00Z","timestamp":1494625080000},"page":"196-208","source":"Crossref","is-referenced-by-count":38,"title":["ISLA: Temporal Segmentation and Labeling for Audio-Visual Emotion Recognition"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6503-4637","authenticated-orcid":false,"given":"Yelin","family":"Kim","sequence":"first","affiliation":[]},{"given":"Emily Mower","family":"Provost","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.17"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946960"},{"key":"ref33","article-title":"ANVIL: The video annotation research tool","author":"kipp","year":"2010","journal-title":"Handbook of Corpus Phonology"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref31","first-page":"1","article-title":"Deep multimodal fusion: A hybrid approach","author":"amer","year":"2017","journal-title":"Int J Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/U-MEDIA.2014.32"},{"key":"ref36","first-page":"1","article-title":"SailAlign: Robust long speech-text alignment","author":"katsamanis","year":"2011","journal-title":"Proc of Workshop on New Tools and Methods for Very-Large Scale Phonetics Research"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-56","article-title":"The interspeech 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/cd.23219925506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494890"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.11.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2011.11.013"},{"key":"ref23","first-page":"2777","article-title":"Detecting pitch accent using pitch-corrected energy-based predictors","author":"rosenberg","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.37.11.2049"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2425836.2425905"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1177\/0022022104273656"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.115.1.102"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2008.02088.x"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521463"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1037\/a0036052"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2490070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2808204"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494893"},{"key":"ref13","first-page":"247","article-title":"Involvement of head movement in speech production and its implications for language pathology","volume":"42","author":"hadar","year":"1983","journal-title":"Advances in Neurology"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.01502010.x"},{"key":"ref15","first-page":"655","article-title":"Prosodic cues in multimodal speech perception","author":"granstr\u00f6m","year":"1999","journal-title":"Proc Int Congr Phonetic Sci"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318448"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076804"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.905145"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0344-2"},{"key":"ref4","first-page":"27","article-title":"Say cheese versus smile: Reducing speech-related variability for facial emotion recognition","author":"kim","year":"2014","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","author":"picard","year":"1997","journal-title":"Affective Computing"},{"key":"ref6","first-page":"398","article-title":"Multimodal emotion recognition","author":"haq","year":"2010","journal-title":"Machine Audition Principles Algorithms and Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.869630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553752"},{"key":"ref7","first-page":"411","article-title":"Semantic audio-visual data fusion for automatic emotion recognition","author":"datcu","year":"2014","journal-title":"Emotion Recognition A Pattern Analysis Approach"},{"key":"ref49","author":"ekman","year":"1972","journal-title":"Emotion in the Human Face Guide-lines for Research and an Integration of Findings Guidelines for Research and an Integration of Findings"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467432"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.58.2.342"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511752841"},{"key":"ref48","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":"ref47","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.37.5.642"},{"key":"ref42","article-title":"Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression","volume":"1","author":"k\u00e4chele","year":"2014","journal-title":"Depression"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017197"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388781"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512534"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/8725811\/07922564.pdf?arnumber=7922564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T14:47:44Z","timestamp":1750258064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7922564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,1]]},"references-count":58,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2017.2702653","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,1]]}}}