{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T08:00:52Z","timestamp":1725868852090},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811030048"},{"type":"electronic","value":"9789811030055"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-981-10-3005-5_58","type":"book-chapter","created":{"date-parts":[[2016,10,21]],"date-time":"2016-10-21T11:48:07Z","timestamp":1477050487000},"page":"707-720","source":"Crossref","is-referenced-by-count":2,"title":["The SYSU System for CCPR 2016 Multimodal Emotion Recognition Challenge"],"prefix":"10.1007","author":[{"given":"Gaoyuan","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinkun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuebo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,22]]},"reference":[{"issue":"4","key":"58_CR1","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1177\/0539018405058216","volume":"44","author":"KR Scherer","year":"2005","unstructured":"Scherer, K.R.: What are emotions? And how can they be measured? Soc. Sci. Inf. 44(4), 695\u2013729 (2005)","journal-title":"Soc. Sci. Inf."},{"key":"58_CR2","doi-asserted-by":"crossref","unstructured":"Lyons, M., Akamatsu, S., Kamachi, M., Gyoba, J.: Coding facial expressions with gabor wavelets. In: Third IEEE International Conference on Automatic Face and Gesture Recognition, Proceedings, pp. 200\u2013205 (1998)","DOI":"10.1109\/AFGR.1998.670949"},{"issue":"5","key":"58_CR3","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/j.imavis.2009.08.002","volume":"28","author":"R Gross","year":"2010","unstructured":"Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image Vision Comput. 28(5), 807\u2013813 (2010)","journal-title":"Image Vision Comput."},{"key":"58_CR4","doi-asserted-by":"crossref","unstructured":"Dhall, A., Goecke, R., Joshi, J., Sikka, K., Gedeon, T.: Emotion recognition in the wild challenge 2014: baseline, data and protocol. In: Proceedings of the 16th International Conference on Multimodal Interaction, pp. 461\u2013466 (2014)","DOI":"10.1145\/2663204.2666275"},{"issue":"6","key":"58_CR5","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1016\/j.imavis.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. Image Vision Comput. 27(6), 803\u2013816 (2009)","journal-title":"Image Vision Comput."},{"issue":"6","key":"58_CR6","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1109\/TPAMI.2007.1110","volume":"29","author":"G Zhao","year":"2007","unstructured":"Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 915\u2013928 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"58_CR7","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MMUL.2012.26","volume":"19","author":"A Dhall","year":"2012","unstructured":"Dhall, A., Goecke, R., Lucey, S., Gedeon, T.: Collecting large, richly annotated facial-expression databases from movies. IEEE Multimedia 19(3), 34\u201341 (2012)","journal-title":"IEEE Multimedia"},{"key":"58_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1106\u20131114 (2012)"},{"key":"58_CR9","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3476\u20133483 (2013)","DOI":"10.1109\/CVPR.2013.446"},{"key":"58_CR10","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zhang, C.: Image based static facial expression recognition with multiple deep network learning. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 435\u2013442 (2015)","DOI":"10.1145\/2818346.2830595"},{"key":"58_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"58_CR12","doi-asserted-by":"crossref","unstructured":"Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing, vol. 10, pp. 79\u201386 (2002)","DOI":"10.3115\/1118693.1118704"},{"key":"58_CR13","doi-asserted-by":"crossref","unstructured":"Goodfellow, I.J., Erhan, D., Carrier, P.L., Courville, A., Mirza, M., et al.: Challenges in representation learning: a report on three machine learning contests. In: International Conference on Neural Information Processing, pp. 117\u2013124 (2013)","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"58_CR14","doi-asserted-by":"crossref","unstructured":"Dhall, A., Goecke, R., Lucey, S., Gedeon, T.: Static facial expression analysis in tough conditions: data, evaluation protocol and benchmark. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 2106\u20132112 (2011)","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"58_CR15","doi-asserted-by":"crossref","unstructured":"Kahou, S.E., Michalski, V., Konda, K., Memisevic, R., Pal, C.: Recurrent neural networks for emotion recognition in video. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 467\u2013474 (2015)","DOI":"10.1145\/2818346.2830596"},{"issue":"1\u20134","key":"58_CR16","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s13042-010-0001-0","volume":"1","author":"Y Zhang","year":"2010","unstructured":"Zhang, Y., Jin, R., Zhou, Z.H.: Understanding bag-of-words model: a statistical framework. Int. J. Mach. Learn. Cybern. 1(1\u20134), 43\u201352 (2010)","journal-title":"Int. J. Mach. Learn. Cybern.."},{"key":"58_CR17","doi-asserted-by":"crossref","unstructured":"Wallach, H.M.: Topic modeling: beyond bag-of-words. In: Proceedings of the 23rd International Conference on Machine learning, pp. 977\u2013984. ACM (2006)","DOI":"10.1145\/1143844.1143967"},{"issue":"Jan","key":"58_CR18","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"58_CR19","doi-asserted-by":"crossref","unstructured":"Ramage, D., Hall, D., Nallapati, R., et al.: Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, vol. 1, pp. 248\u2013256 (2009)","DOI":"10.3115\/1699510.1699543"},{"key":"58_CR20","doi-asserted-by":"crossref","unstructured":"Metze, F., Batliner, A., Eyben, F., Polzehl, T., Schuller, B., Steidl, S.: Emotion recognition using imperfect speech recognition. ISCA (2010)","DOI":"10.21437\/Interspeech.2010-202"},{"issue":"2","key":"58_CR21","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"CN Anagnostopoulos","year":"2015","unstructured":"Anagnostopoulos, C.N., Iliou, T., Giannoukos, I.: Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011. Artif. Intell. Rev. 43(2), 155\u2013177 (2015)","journal-title":"Artif. Intell. Rev."},{"issue":"3","key":"58_CR22","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M Ayadi El","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"58_CR23","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"58_CR24","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The INTERSPEECH 2009 emotion challenge. In: INTERSPEECH, pp. 312\u2013315 (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"issue":"1","key":"58_CR25","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.csl.2012.01.008","volume":"27","author":"M Li","year":"2013","unstructured":"Li, M., Han, K.J., Narayanan, S.: Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Comput. Speech Lang. 27(1), 151\u2013167 (2013)","journal-title":"Comput. Speech Lang."},{"key":"58_CR26","doi-asserted-by":"crossref","unstructured":"Li, M., Metallinou, A., Bone, D., Narayanan, S.: Speaker states recognition using latent factor analysis based eigenchannel factor vector modeling. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1937\u20131940 (2012)","DOI":"10.1109\/ICASSP.2012.6288284"},{"key":"58_CR27","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M.A., Zafeiriou, S.: Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5200\u20135204 (2016)","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"58_CR28","doi-asserted-by":"crossref","unstructured":"Bao, W., Li, Y., Gu, M., Yang, M., Li, H., Chao, L., Tao, J.: Building a Chinese natural emotional audio-visual database. In: 2014 12th International Conference on Signal Processing (ICSP), pp. 583\u2013587 (2014)","DOI":"10.1109\/ICOSP.2014.7015071"},{"key":"58_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Tao, J., Schuller, B., Shan, S., Jiang, D., Jia, J.: MEC 2016: the multimodal emotion recognition challenge of CCPR 2016, submitted to CCPR 2016","DOI":"10.1007\/978-981-10-3005-5_55"},{"key":"58_CR30","doi-asserted-by":"crossref","unstructured":"Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 532\u2013539 (2013)","DOI":"10.1109\/CVPR.2013.75"},{"key":"58_CR31","unstructured":"Chollet, F.: Keras. Github (2015). https:\/\/github.com\/fchollet\/keras"},{"issue":"1","key":"58_CR32","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M Mohri","year":"2002","unstructured":"Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. Comput. Speech Lang. 16(1), 69\u201388 (2002)","journal-title":"Comput. Speech Lang."},{"key":"58_CR33","unstructured":"Hsu, C.W., Chang, C.C., Lin, C.J.: A practical guide to support vector classification (2003)"},{"key":"58_CR34","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (2011)"},{"issue":"Aug","key":"58_CR35","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9(Aug), 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"58_CR36","first-page":"819","volume":"5","author":"T Jebara","year":"2004","unstructured":"Jebara, T., Kondor, R., Howard, A.: Probability product kernels. J. Mach. Learn. Res. 5, 819\u2013844 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"58_CR37","unstructured":"Br\u00fcmmer, N.: FoCal multi-class: toolkit for evaluation, fusion and calibration of multi-class recognition scores\u2013tutorial and user manual\u2013 (2007). http:\/\/sites.google.com\/site\/nikobrummer\/focalmulticlass"}],"container-title":["Communications in Computer and Information Science","Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-3005-5_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T22:57:09Z","timestamp":1657493829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-10-3005-5_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9789811030048","9789811030055"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-3005-5_58","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2016]]}}}