{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:12:53Z","timestamp":1755925973141},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T00:00:00Z","timestamp":1455235200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Multimodal User Interfaces"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s12193-015-0202-7","type":"journal-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T05:27:27Z","timestamp":1455254847000},"page":"151-162","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Revisiting the EmotiW challenge: how wild is it really?"],"prefix":"10.1007","volume":"10","author":[{"given":"Markus","family":"K\u00e4chele","sequence":"first","affiliation":[]},{"given":"Martin","family":"Schels","sequence":"additional","affiliation":[]},{"given":"Sascha","family":"Meudt","sequence":"additional","affiliation":[]},{"given":"G\u00fcnther","family":"Palm","sequence":"additional","affiliation":[]},{"given":"Friedhelm","family":"Schwenker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,2,12]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Almaev TR, Y\u00fcce A, Ghitulescu A, Valstar MF (2013) Distribution-based iterative pairwise classification of emotions in the wild using LGBP-TOP. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 535\u2013542","key":"202_CR1","DOI":"10.1145\/2522848.2531742"},{"issue":"2","key":"202_CR2","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1121\/1.1912679","volume":"50","author":"BS Atal","year":"1971","unstructured":"Atal BS, Hanauer SL (1971) Speech analysis and synthesis by linear prediction of the speech wave. J Acoust Soc Am 50(2):637\u2013655","journal-title":"J Acoust Soc Am"},{"key":"202_CR3","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1037\/a0025827","volume":"12","author":"T B\u00e4nziger","year":"2012","unstructured":"B\u00e4nziger T, Mortillaro M, Scherer KR (2012) Introducing the Geneva multimodal expression corpus for experimental research on emotion perception. Emotion 12:1161\u20131179","journal-title":"Emotion"},{"doi-asserted-by":"crossref","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on Image and video retrieval, CIVR \u201907. ACM, pp 401\u2013408","key":"202_CR4","DOI":"10.1145\/1282280.1282340"},{"key":"202_CR5","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1049\/ip-f-2.1993.0054","volume":"140","author":"JF Cardoso","year":"1993","unstructured":"Cardoso JF, Souloumiac A (1993) Blind beamforming for non-gaussian signals. IEE Proc F (Radar Signal Process) 140:362\u2013370","journal-title":"IEE Proc F (Radar Signal Process)"},{"doi-asserted-by":"crossref","unstructured":"Chen J, Chen Z, Chi Z, Fu H (2014) Emotion recognition in the wild with feature fusion and multiple kernel learning. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 508\u2013513","key":"202_CR6","DOI":"10.1145\/2663204.2666277"},{"issue":"6","key":"202_CR7","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.specom.2008.03.012","volume":"50","author":"C Clavel","year":"2008","unstructured":"Clavel C, Vasilescu I, Devillers L, Richard G, Ehrette T (2008) Fear-type emotion recognition for future audio-based surveillance systems. Speech Commun 50(6):487\u2013503","journal-title":"Speech Commun"},{"doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Computer Society conference on computer vision and pattern recognition, 2005. CVPR 2005, vol 1, pp 886\u2013893","key":"202_CR8","DOI":"10.1109\/CVPR.2005.177"},{"issue":"4","key":"202_CR9","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. Acoust Speech Signal Process IEEE Trans 28(4):357\u2013366","journal-title":"Acoust Speech Signal Process IEEE Trans"},{"doi-asserted-by":"crossref","unstructured":"Day M (2013) Emotion recognition with boosted tree classifiers. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 531\u2013534","key":"202_CR10","DOI":"10.1145\/2522848.2531740"},{"doi-asserted-by":"crossref","unstructured":"Dhall A, Goecke R, Joshi J, Sikka K, Gedeon T (2014) Emotion recognition in the wild challenge 2014: Baseline, data and protocol. In: Proceedings of the 16th international conference on multimodal interaction. ACM, pp 461\u2013466","key":"202_CR11","DOI":"10.1145\/2663204.2666275"},{"doi-asserted-by":"crossref","unstructured":"Dhall A, Goecke R, Joshi J, Wagner M, Gedeon T (2013) Emotion recognition in the wild challenge 2013. In: Proceedings of the 15th ACM on international conference on multimodal interaction. ACM, pp 509\u2013516","key":"202_CR12","DOI":"10.1145\/2522848.2531739"},{"key":"202_CR13","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MMUL.2012.26","volume":"3","author":"A Dhall","year":"2012","unstructured":"Dhall A, Goecke R, Lucey S, Gedeon T (2012) Collecting large, richly annotated facial-expression databases from movies. IEEE Multimed 3:34\u201341","journal-title":"IEEE Multimed"},{"issue":"1","key":"202_CR14","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1177\/0305735610362821","volume":"39","author":"T Eerola","year":"2011","unstructured":"Eerola T, Vuoskoski JK (2011) A comparison of the discrete and dimensional models of emotion in music. Psychol Music 39(1):18\u201349","journal-title":"Psychol Music"},{"doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2009) OpenEAR - introducing the Munich open-source emotion and affect recognition toolkit. In: Affective computing and intelligent interaction and workshops, 2009. ACII 2009, pp 1\u20136","key":"202_CR15","DOI":"10.1109\/ACII.2009.5349350"},{"doi-asserted-by":"crossref","unstructured":"Gehrig T, Ekenel HK (2013) Why is facial expression analysis in the wild challenging? In: Proceedings of the 2013 on emotion recognition in the wild challenge and workshop, EmotiW \u201913. ACM, pp 9\u201316","key":"202_CR16","DOI":"10.1145\/2531923.2531924"},{"doi-asserted-by":"crossref","unstructured":"G\u00f3mez J\u00e1uregui DA, Martin JC (2013) Evaluation of vision-based real-time measures for emotions discrimination under uncontrolled conditions. In: Proceedings of the 2013 on emotion recognition in the wild challenge and workshop, EmotiW \u201913. ACM, pp 17\u201322","key":"202_CR17","DOI":"10.1145\/2531923.2531925"},{"doi-asserted-by":"crossref","unstructured":"Grimm M, Kroschel K, Narayanan S (2008) The Vera am Mittag German audio-visual emotional speech database. In: IEEE international conference on multimedia and expo, pp 865\u2013868","key":"202_CR18","DOI":"10.1109\/ICME.2008.4607572"},{"doi-asserted-by":"crossref","unstructured":"Grosicki M (2014) Neural networks for emotion recognition in the wild. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 467\u2013472","key":"202_CR19","DOI":"10.1145\/2663204.2666270"},{"issue":"6","key":"202_CR20","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1109\/TPAMI.2007.1110","volume":"29","author":"Z Guoying","year":"2007","unstructured":"Guoying Z, Pietik\u00e4inen M (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach Intell 29(6):915\u2013928","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"202_CR21","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky H (1990) Perceptual linear predictive (PLP) analysis of speech. J Acoust Soc Am 87(4):1738\u20131752","journal-title":"J Acoust Soc Am"},{"doi-asserted-by":"crossref","unstructured":"Hermansky H (1997) The modulation spectrum in automatic recognition of speech. In: Proceedings of IEEE workshop on automatic speech recognition and understanding","key":"202_CR22","DOI":"10.1109\/ASRU.1997.658998"},{"doi-asserted-by":"crossref","unstructured":"Hermansky H, Morgan N, Bayya A, Kohn P (1992) RASTA-PLP speech analysis technique. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP-92), vol 1, pp 121\u2013124","key":"202_CR23","DOI":"10.1109\/ICASSP.1992.225957"},{"doi-asserted-by":"crossref","unstructured":"Huang X, He Q, Hong X, Zhao G, Pietik\u00e4inen M (2014) Improved spatiotemporal local monogenic binary pattern for emotion recognition in the wild. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 514\u2013520","key":"202_CR24","DOI":"10.1145\/2663204.2666278"},{"doi-asserted-by":"crossref","unstructured":"K\u00e4chele M, Schels M, Schwenker F (2014) Inferring depression and affect from application dependent meta knowledge. In: Proceedings of the 4th international workshop on audio\/visual emotion challenge, AVEC \u201914. ACM, pp 41\u201348","key":"202_CR25","DOI":"10.1145\/2661806.2661813"},{"doi-asserted-by":"crossref","unstructured":"K\u00e4chele M., Thiam P., Palm G., Schwenker F., Schels M (2015) Ensemble methods for continuous affect recognition: multi-modality, temporality, and challenges. In: Proceedings of the 5th international workshop on audio\/visual emotion challenge, AVEC \u201915. ACM, pp 9\u201316","key":"202_CR26","DOI":"10.1145\/2808196.2811637"},{"doi-asserted-by":"crossref","unstructured":"K\u00e4chele M, Zharkov D, Meudt S, Schwenker F (2014) Prosodic, spectral and voice quality feature selection using a long-term stopping criterion for audio-based emotion recognition. In: Proceedings of the international conference on pattern recognition (ICPR), pp 803\u2013808","key":"202_CR27","DOI":"10.1109\/ICPR.2014.148"},{"doi-asserted-by":"crossref","unstructured":"Kahou SE, Pal C, Bouthillier X, Froumenty P, G\u00fcl\u00e7ere \u00c7, et al. (2013) Combining modality specific deep neural networks for emotion recognition in video. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 543\u2013550","key":"202_CR28","DOI":"10.1145\/2522848.2531745"},{"key":"202_CR29","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/AFGR.2000.840611","volume":"2000","author":"T Kanade","year":"2000","unstructured":"Kanade T, Cohn J, Tian Y (2000) Comprehensive database for facial expression analysis. Autom Face Gesture Recognit 2000:46\u201353","journal-title":"Autom Face Gesture Recognit"},{"doi-asserted-by":"crossref","unstructured":"Kaya H, Salah AA (2014) Combining modality-specific extreme learning machines for emotion recognition in the wild. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 487\u2013493","key":"202_CR30","DOI":"10.1145\/2663204.2666273"},{"doi-asserted-by":"crossref","unstructured":"Krishna T, Rai A, Bansal S, Khandelwal S, Gupta S, Goyal D (2013) Emotion recognition using facial and audio features. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 557\u2013564","key":"202_CR31","DOI":"10.1145\/2522848.2531746"},{"doi-asserted-by":"crossref","unstructured":"Levi K, Weiss Y (2004) Learning object detection from a small number of examples: the importance of good features. In: Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition (CVPR), vol 2, pp II-53\u2013II-60","key":"202_CR32","DOI":"10.1109\/CVPR.2004.1315144"},{"doi-asserted-by":"crossref","unstructured":"Liu M, Wang R, Huang Z, Shan S, Chen X (2013) Partial least squares regression on grassmannian manifold for emotion recognition. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 525\u2013530","key":"202_CR33","DOI":"10.1145\/2522848.2531738"},{"doi-asserted-by":"crossref","unstructured":"Liu M, Wang R, Li S, Shan S, Huang Z, Chen X (2014) Combining multiple kernel methods on riemannian manifold for emotion recognition in the wild. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 494\u2013501","key":"202_CR34","DOI":"10.1145\/2663204.2666274"},{"doi-asserted-by":"crossref","unstructured":"McKeown G, Valstar MF, Cowie R, Pantic M (2010) The SEMAINE corpus of emotionally coloured character interactions. In: IEEE international conference on multimedia and expo (ICME). IEEE, pp 1079\u20131084","key":"202_CR35","DOI":"10.1109\/ICME.2010.5583006"},{"issue":"12","key":"202_CR36","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1016\/j.patrec.2009.03.003","volume":"30","author":"H Meng","year":"2009","unstructured":"Meng H, Pears N (2009) Descriptive temporal template features for visual motion recognition. Pattern Recognit Lett 30(12):1049\u20131058","journal-title":"Pattern Recognit Lett"},{"doi-asserted-by":"crossref","unstructured":"Meng H, Romera-Paredes B, Bianchi-Berthouze N (2011) Emotion recognition by two view SVM-2K classifier on dynamic facial expression features. In: 2011 IEEE international conference on automatic face gesture recognition and workshops (FG 2011), pp 854\u2013859","key":"202_CR37","DOI":"10.1109\/FG.2011.5771362"},{"doi-asserted-by":"crossref","unstructured":"Meudt S, Schwenker F (2014) Enhanced autocorrelation in real world emotion recognition. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 502\u2013507","key":"202_CR38","DOI":"10.1145\/2663204.2666276"},{"doi-asserted-by":"crossref","unstructured":"Meudt S, Zharkov D, K\u00e4chele M, Schwenker F (2013) Multi classifier systems and forward backward feature selection algorithms to classify emotional coloured speech. In: Proceedings of the international conference on multimodal interaction, ICMI 2013. ACM, pp 551\u2013556","key":"202_CR39","DOI":"10.1145\/2522848.2531743"},{"issue":"7","key":"202_CR40","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietik\u00e4inen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Pattern Anal Mach Intell IEEE Trans 24(7):971\u2013987","journal-title":"Pattern Anal Mach Intell IEEE Trans"},{"issue":"3","key":"202_CR41","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145\u2013175","journal-title":"Int J Comput Vis"},{"issue":"11","key":"202_CR42","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/0167-8655(94)90127-9","volume":"15","author":"P Pudil","year":"1994","unstructured":"Pudil P, Novovi\u010dov\u00e1 J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15(11):1119\u20131125","journal-title":"Pattern Recognit Lett"},{"doi-asserted-by":"crossref","unstructured":"Ringeval F, Amiriparian S, Eyben F, Scherer K, Schuller B (2014) Emotion recognition in the wild: Incorporating voice and lip activity in multimodal decision-level fusion. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 473\u2013480","key":"202_CR43","DOI":"10.1145\/2663204.2666271"},{"doi-asserted-by":"crossref","unstructured":"Ringeval F, Sonderegger A, Sauer J, Lalanne D (2013) Introducing the RECOLA multimodal corpus of remote collaborative and affective interactions. In: Proceedings of face and gestures 2013, 2nd IEEE international workshop on emotion representation, analysis and synthesis in continuous time and space (EmoSPACE)","key":"202_CR44","DOI":"10.1109\/FG.2013.6553805"},{"issue":"5","key":"202_CR45","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1088\/0508-3443\/7\/5\/302","volume":"7","author":"DW Robinson","year":"1956","unstructured":"Robinson DW, Dadson RS (1956) A re-determination of the equal-loudness relations for pure tones. Br J Appl Phys 7(5):166\u2013181","journal-title":"Br J Appl Phys"},{"doi-asserted-by":"crossref","unstructured":"Sidorov M, Minker W (2014) Emotion recognition in real-world conditions with acoustic and visual features. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 521\u2013524","key":"202_CR46","DOI":"10.1145\/2663204.2666279"},{"doi-asserted-by":"crossref","unstructured":"Sikka K, Dykstra K, Sathyanarayana S, Littlewort G, Bartlett M (2013) Multiple kernel learning for emotion recognition in the wild. In: Proceedings of the 15th ACM on international conference on multimodal interaction, ICMI \u201913. ACM, pp 517\u2013524","key":"202_CR47","DOI":"10.1145\/2522848.2531741"},{"doi-asserted-by":"crossref","unstructured":"Sun B, Li L, Zuo T, Chen Y, Zhou G, Wu X (2014) Combining multimodal features with hierarchical classifier fusion for emotion recognition in the wild. In: Proceedings of the 16th international conference on multimodal interaction, ICMI \u201914. ACM, pp 481\u2013486","key":"202_CR48","DOI":"10.1145\/2663204.2666272"},{"issue":"6","key":"202_CR49","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/89.876309","volume":"8","author":"T Tolonen","year":"2000","unstructured":"Tolonen T, Karjalainen M (2000) A computationally efficient multipitch analysis model. IEEE Trans Speech Audio Process 8(6):708\u2013716","journal-title":"IEEE Trans Speech Audio Process"},{"key":"202_CR50","first-page":"603","volume-title":"Human\u2013computer interaction","author":"S Walter","year":"2011","unstructured":"Walter S, Scherer S, Schels M, Glodek M, Hrabal D, Schmidt M, B\u00f6ck R, Limbrecht K, Traue H, Schwenker F (2011) Multimodal emotion classification in naturalistic user behavior, towards mobile and intelligent interaction environments, LNCS. In: Jacko J (ed) Human\u2013computer interaction, vol 6763. Springer, Berlin Heidelberg, pp 603\u2013611"},{"key":"202_CR51","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-34555-0","volume-title":"Text mining: predictive methods for analyzing unstructured information","author":"S Weiss","year":"2005","unstructured":"Weiss S, Indurkhya N, Zhang T, Damerau F (2005) Text mining: predictive methods for analyzing unstructured information, 1st edn. Springer, New York","edition":"1"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-015-0202-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-015-0202-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-015-0202-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T21:06:44Z","timestamp":1692220004000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-015-0202-7"}},"subtitle":["Classification of human emotions in movie snippets based on multiple features"],"short-title":[],"issued":{"date-parts":[[2016,2,12]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["202"],"URL":"https:\/\/doi.org\/10.1007\/s12193-015-0202-7","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"type":"print","value":"1783-7677"},{"type":"electronic","value":"1783-8738"}],"subject":[],"published":{"date-parts":[[2016,2,12]]}}}