{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:12:50Z","timestamp":1742958770941,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-981-10-3005-5_57","type":"book-chapter","created":{"date-parts":[[2016,10,21]],"date-time":"2016-10-21T11:48:07Z","timestamp":1477050487000},"page":"692-706","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio Visual Recognition of Spontaneous Emotions In-the-Wild"],"prefix":"10.1007","author":[{"given":"Xiaohan","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ercheng","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Sahli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,22]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The INTERSPEECH 2009 emotion challenge. In: Proceedings of Interspeech, pp. 312\u2013315, Brighton (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"key":"57_CR2","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. In: Proceedings of Interspeech, pp. 148\u2013152, Lyon (2013)","DOI":"10.21437\/Interspeech.2013-56"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Epps, J., Eyben, F., Ringeval, F., Marchi, E., Zhang, Y.: The INTERSPEECH 2014 computational paralinguistics challenge: cognitive and physical load. In: Proceedings of Interspeech 2014, Singapore (2014)","DOI":"10.21437\/Interspeech.2014-104"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Valstar, M., Jiang, B., Mehu, M., Pantic, M., Scherer, K.: The first facial expression recognition and analysis challenge. In: Proceedings of IEEE International Conference Automatic Face and Gesture Recognition, pp. 921\u2013926, Ljubljana (2011)","DOI":"10.1109\/FG.2011.5771374"},{"key":"57_CR5","doi-asserted-by":"crossref","unstructured":"Schuller, B., Valster, M., Eyben, F., Cowie, R., Pantic, M.: AVEC 2012: the continuous audio\/visual emotion challenge. In: Proceedings of the 14th ACM International Conference on Multimodal Interaction, pp. 449\u2013456. ACM, USA (2012)","DOI":"10.1145\/2388676.2388776"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Valstar, M., Schuller, B., Smith, K., Eyben, F., Jiang, B., Bilakhia, S., Schnieder, S., Cowie, R., Pantic, M.: AVEC 2013: the continuous audio\/visual emotion and depression recognition challenge. In: Proceedings of the 3rd ACM International Workshop on Audio\/Visual Emotion Challenge, pp. 3\u201310. ACM, Spain (2013)","DOI":"10.1145\/2512530.2512533"},{"key":"57_CR7","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 2014 ACM on International Conference on Multimodal Interaction, pp. 461\u2013466, Istanbul, Turkey (2014)","DOI":"10.1145\/2663204.2666275"},{"key":"57_CR8","doi-asserted-by":"crossref","unstructured":"Dhall, A., Ramana Murthy, O., Goecke, R., Joshi, J., Gedeon, T.: Video and image based emotion recognition challenges in the wild: Emotiw 2015. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 423\u2013426, Seattle (2015)","DOI":"10.1145\/2818346.2829994"},{"key":"57_CR9","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, R., Li, S., Shan, S., Huang, Z., Chen, X.: Combining multiple kernel methods on Riemannian manifold for emotion recognition in the wild. In: Proceedings of the 16th International Conference on Multimodal Interaction, pp. 494\u2013501, Istanbul (2014)","DOI":"10.1145\/2663204.2666274"},{"key":"57_CR10","doi-asserted-by":"crossref","unstructured":"Kaya, H., G\u00fcrpinar, F., Afshar, S., Salah, A.A.: Contrasting and combining least squares based learners for emotion recognition in the wild. In: Proceedings of the 17th International Conference on Multimodal Interaction, pp. 459\u2013466, Seattle (2015)","DOI":"10.1145\/2818346.2830588"},{"issue":"2","key":"57_CR11","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/TCYB.2013.2249063","volume":"44","author":"B Jiang","year":"2014","unstructured":"Jiang, B., Valstar, M., Martinez, B., Pantic, M.: A dynamic appearance descriptor approach to facial actions temporal modeling. IEEE Trans. Cybern. 44(2), 161\u2013174 (2014)","journal-title":"IEEE Trans. Cybern."},{"key":"57_CR12","doi-asserted-by":"crossref","unstructured":"Dhall, A., Asthana, A., Goecke, R., Gedeon, T.: Emotion recognition using PHOG and LPQ features. In: Ninth IEEE International Conference on Automatic Face and Gesture Recognition (FG 2011), pp. 21\u201325, Santa Barbara (2011)","DOI":"10.1109\/FG.2011.5771366"},{"key":"57_CR13","doi-asserted-by":"crossref","unstructured":"Sikka, K., Dykstra, K., Sathyanarayana, S., Littlewort, G., Bartlett, M.: Multiple Kernel learning for emotion recognition in the wild. In: Proceedings of the 15th ACM on International Conference on Multimodal Interaction, pp. 517\u2013524, Sydney (2013)","DOI":"10.1145\/2522848.2531741"},{"key":"57_CR14","doi-asserted-by":"crossref","unstructured":"Yao, A., Shao, J., Ma, N., Chen, Y.: Capturing AU-aware facial features and their latent relations for emotion recognition in the wild. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 451\u2013458, Seattle (2015)","DOI":"10.1145\/2818346.2830585"},{"key":"57_CR15","unstructured":"Zhiding, Y., 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, Seattle (2015)"},{"key":"57_CR16","doi-asserted-by":"crossref","unstructured":"Ng, H.-W., Nguyen, V.D., Vonikakis, V., Winkler, S.: Deep learning for emotion recognition on small datasets using transfer learning. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 443\u2013449, Seattle (2015)","DOI":"10.1145\/2818346.2830593"},{"key":"57_CR17","doi-asserted-by":"crossref","unstructured":"Han, K., Dong, Y., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: Proceedings of Interspeech, Singapore (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"57_CR18","doi-asserted-by":"crossref","unstructured":"Bao, W., et al.: Building a Chinese natural emotional audio-visual database. In: 2014 International Conference on Signal Processing. IEEE Press, Hangzhou (2014)","DOI":"10.1109\/ICOSP.2014.7015071"},{"key":"57_CR19","doi-asserted-by":"crossref","unstructured":"Valstar, M.F., Schuller, B.W., Smith, K., Almaev, T.R., Eyben, F., Krajewski, J., Cowie, R., Pantic, M.: AVEC 2014: 3D dimensional affect and depression recognition challenge. In: Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge (AVEC). ACM MM, Orlando, USA (2014)","DOI":"10.1145\/2661806.2661807"},{"key":"57_CR20","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Schuller, B., Valstar, M., Jaiswal, S., Marchi, E., Lalanne, D., Cowie, R., Pantic, M.: AV+EC 2015 - the first affect recognition challenge bridging across audio, video, and physiological data. In: Proceedings of the 5th International Workshop on Audio\/Visual Emotion Challenge (AVEC). ACM MM, Brisbane, Australia (2015)","DOI":"10.1145\/2808196.2811642"},{"key":"57_CR21","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 835\u2013838, New York (2013)","DOI":"10.1145\/2502081.2502224"},{"issue":"2","key":"57_CR22","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time object detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"57_CR23","doi-asserted-by":"crossref","unstructured":"Xiong, X., Torre, F.D.L.: Supervised descent method and its applications to face alignment. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 532\u2013539, Portland, USA (2013)","DOI":"10.1109\/CVPR.2013.75"},{"key":"57_CR24","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1109\/TPAMI.2007.1110","volume":"29","author":"G Zhao","year":"2007","unstructured":"Zhao, G., Pietikinen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29, 915\u2013928 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"57_CR25","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. In: Chinese Conference on Pattern Recognition (CCPR), Chengdu, China (2016)","DOI":"10.1007\/978-981-10-3005-5_55"},{"key":"57_CR26","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Robinson, P., Morency, L.-P.: OpenFace: an open source facial behavior analysis toolkit. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision, New York, USA (2016)","DOI":"10.1109\/WACV.2016.7477553"},{"key":"57_CR27","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Morency, L.-P., Robinson, P.: Constrained local neural fields for robust facial landmark detection in the wild. In: Proceedings of 2013 IEEE International Conference on Computer Vision Workshops, pp. 354\u2013361, Sydney, Australia (2013)","DOI":"10.1109\/ICCVW.2013.54"},{"issue":"12","key":"57_CR28","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.1109\/TPAMI.2013.23","volume":"35","author":"PN Belhumeur","year":"2013","unstructured":"Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2930\u20132940 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"57_CR29","doi-asserted-by":"crossref","unstructured":"Le, V., Brandt, J., Lin, Z., Bourdev, L., Huang, T.S.: Interactive facial feature localization. In: Proceedings of 12th European Conference on Computer Vision, pp. 679\u2013692, Florence, Italy (2012)","DOI":"10.1007\/978-3-642-33712-3_49"},{"key":"57_CR30","unstructured":"http:\/\/www.cse.oulu.fi\/wsgi\/CMV\/Downloads . Accessed 28 July 2016"},{"key":"57_CR31","unstructured":"http:\/\/prdownloads.sourceforge.net\/weka\/weka-3-6-14.zip . Accessed 28 July 2016"},{"key":"57_CR32","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer, M., Metallinou, A., Eyben, F., Narayanan, S.S.: Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling. In: Proceedings of INTERSPEECH 2010, Makuhari, Chiba (2010)","DOI":"10.21437\/Interspeech.2010-646"},{"key":"57_CR33","volume-title":"The HTK Book","author":"S Young","year":"2006","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book. Entropic Cambridge Research Laboratory, Cambridge (2006)"}],"container-title":["Communications in Computer and Information Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-3005-5_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T22:57:08Z","timestamp":1657493828000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-10-3005-5_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9789811030048","9789811030055"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-3005-5_57","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"22 October 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccpr2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.uestcrobot.net\/ccpr2016\/english_index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}