{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:25:28Z","timestamp":1780676728309,"version":"3.54.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T00:00:00Z","timestamp":1490140800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61272211"],"award-info":[{"award-number":["61272211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61672267"],"award-info":[{"award-number":["61672267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"the China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2015M570413"],"award-info":[{"award-number":["2015M570413"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s00530-017-0547-8","type":"journal-article","created":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T00:46:43Z","timestamp":1490230003000},"page":"451-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Multimodal shared features learning for emotion recognition by enhanced sparse local discriminative canonical correlation analysis"],"prefix":"10.1007","volume":"25","author":[{"given":"Jiamin","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juanjuan","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhao","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,3,22]]},"reference":[{"issue":"8","key":"547_CR1","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1109\/LSP.2015.2390222","volume":"22","author":"L An","year":"2015","unstructured":"An, L., Yang, S., Bhanu, B.: Person re-identification by robust canonical correlation analysis. IEEE Signal Process. Lett. 22(8), 1103\u20131107 (2015). doi:\n                    10.1109\/LSP.2015.2390222","journal-title":"IEEE Signal Process. Lett."},{"key":"547_CR2","doi-asserted-by":"publisher","unstructured":"Busso, C., Deng, Z., Yildirim, S., Bulut, M., Lee, C.M., Kazemzadeh, A., Lee, S., Neumann, U., Narayanan, S.: Analysis of emotion recognition using facial expressions, speech and multimodal information. In: International Conference on Multimodal Interfaces, vol. 38, No. 4, pp. 205\u2013211 (2004). doi:\n                    10.1145\/1027933.1027968","DOI":"10.1145\/1027933.1027968"},{"key":"547_CR3","doi-asserted-by":"publisher","unstructured":"Chen, L.S., Huang, T.S., Miyasato, T., Nakatsu, R.: Multimodal human emotion\/expression recognition. IEEE International Conference on Automatic Face and Gesture Recognition, pp. 366\u2013371 (1998). doi:\n                    10.1109\/AFGR.1998.670976","DOI":"10.1109\/AFGR.1998.670976"},{"issue":"10","key":"547_CR4","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1109\/TSP.2010.2053029","volume":"58","author":"Y Chen","year":"2010","unstructured":"Chen, Y., Wiesel, A., Eldar, Y.C., Hero, A.O.: Shrinkage algorithms for mmse covariance estimation. IEEE Trans. Signal Process. 58(10), 5016\u20135029 (2010). doi:\n                    10.1109\/TSP.2010.2053029","journal-title":"IEEE Trans. Signal Process."},{"key":"547_CR5","unstructured":"Datcu, D., Rothkrantz, L.J.M.: Multimodal recognition of emotions in car environments. In: DI & I Prague (2009)"},{"key":"547_CR6","doi-asserted-by":"publisher","unstructured":"Deng, J., Zhang, Z., Marchi, E., Schuller, B.: Sparse autoencoder-based feature transfer learning for speech emotion recognition. In: Humaine Association Conference on AVTective Computing and Intelligent Interaction, vol. 7971, pp. 511\u2013516 (2013). doi:\n                    10.1109\/ACII.2013.90","DOI":"10.1109\/ACII.2013.90"},{"issue":"53","key":"547_CR7","doi-asserted-by":"publisher","first-page":"53","DOI":"10.5772\/54002","volume":"10","author":"S Dobrisek","year":"2013","unstructured":"Dobrisek, S., Gajsek, R., Mihelic, F., Pavesic, N., Struc, V.: Towards efficient multi-modal emotion recognition. Int. J. Adv. Robot. Syst. 10(53), 53\u201353 (2013). doi:\n                    10.5772\/54002","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"547_CR8","doi-asserted-by":"publisher","unstructured":"Gajsek, R., STruc V, Mihelic F, : Multi-modal emotion recognition using canonical correlations and acoustic features. In: International Conference on Pattern Recognition, vol. 82, No. 6, pp. 4133\u20134136 (2010). doi:\n                    10.1109\/ICPR.2010.1005","DOI":"10.1109\/ICPR.2010.1005"},{"key":"547_CR9","volume-title":"From the lab to the real world: affect recognition using multiple cues and modalities","author":"H Gunes","year":"2008","unstructured":"Gunes, H., Piccardi, M., Pantic, M.: From the lab to the real world: affect recognition using multiple cues and modalities. InTech Education and Publishing, Croatia (2008)"},{"key":"547_CR10","doi-asserted-by":"publisher","unstructured":"Han, M.J., Hsu, I.H., Song, K.T., Chang, F.Y.: A new information fusion method for svm-based robotic audio-visual emotion recognition. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 2656\u20132661 (2007). doi:\n                    10.1109\/ICSMC.2007.4413990","DOI":"10.1109\/ICSMC.2007.4413990"},{"issue":"3","key":"547_CR11","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10994-010-5222-7","volume":"83","author":"DR Hardoon","year":"2011","unstructured":"Hardoon, D.R., Shawe-Taylor, J.: Sparse canonical correlation analysis. Mach. Learn. 83(3), 331\u2013353 (2011). doi:\n                    10.1007\/s10994-010-5222-7","journal-title":"Mach. Learn."},{"issue":"12","key":"547_CR12","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639\u20132664 (2004). doi:\n                    10.1162\/0899766042321814","journal-title":"Neural Comput."},{"key":"547_CR13","doi-asserted-by":"publisher","unstructured":"Huang, L., Xin, L., Zhao, L., Tao, J.: Combining audio and video by dominance in bimodal emotion recognition. In: Second International Conference on Affective Computing and Intelligent Interaction, vo.l 4738, pp. 729\u2013730 (2007). doi:\n                    10.1007\/978-3-540-74889-2_71","DOI":"10.1007\/978-3-540-74889-2_71"},{"issue":"8","key":"547_CR14","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1016\/j.ijhcs.2007.02.003","volume":"65","author":"A Kapoor","year":"2007","unstructured":"Kapoor, A., Burleson, W., Picard, R.W.: Automatic prediction of frustration. Int. J. Hum. Comput. Stud. 65(8), 724\u2013736 (2007). doi:\n                    10.1016\/j.ijhcs.2007.02.003","journal-title":"Int. J. Hum. Comput. Stud."},{"key":"547_CR15","doi-asserted-by":"publisher","unstructured":"Kim, Y., Lee, H., Provost, E.M.: Deep learning for robust feature generation in audiovisual emotion recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 32, No. 3, pp. 3687\u20133691 (2013). doi:\n                    10.1109\/ICASSP.2013.6638346","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"547_CR16","doi-asserted-by":"publisher","unstructured":"Le, D., Provost, E.M.: Emotion recognition from spontaneous speech using hidden markov models with deep belief networks. In: Automatic Speech Recognition and Understanding, pp. 216\u2013221 (2013). doi:\n                    10.1109\/ASRU.2013.6707732","DOI":"10.1109\/ASRU.2013.6707732"},{"issue":"2","key":"547_CR17","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1214\/12-AOS989","volume":"40","author":"O Ledoit","year":"2012","unstructured":"Ledoit, O., Wolf, M.: Nonlinear shrinkage estimation of large-dimensional covariance matrices. Ann. Stat. 40(2), 1024\u20131060 (2012). doi:\n                    10.1214\/12-AOS989","journal-title":"Ann. Stat."},{"issue":"12","key":"547_CR18","doi-asserted-by":"publisher","first-page":"5343","DOI":"10.1109\/TIP.2015.2479560","volume":"24","author":"Z Li","year":"2015","unstructured":"Li, Z., Tang, J.: Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans. Image Process. 24(12), 5343\u20135355 (2015). doi:\n                    10.1109\/TIP.2015.2479560","journal-title":"IEEE Trans. Image Process."},{"issue":"99","key":"547_CR19","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1109\/TIP.2016.2624140","volume":"26","author":"Z Li","year":"2017","unstructured":"Li, Z., Tang, J.: Weakly-supervised deep matrix factorization for social image understanding. IEEE Trans. Image Process. 26(99), 276\u2013288 (2017). doi:\n                    10.1109\/TIP.2016.2624140","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"547_CR20","doi-asserted-by":"publisher","first-page":"2138","DOI":"10.1109\/TKDE.2013.65","volume":"26","author":"Z Li","year":"2014","unstructured":"Li, Z., Liu, J., Yang, Y., Zhou, X., Lu, H.: Clustering-guided sparse structural learning for unsupervised feature selection. IEEE Trans. Knowl. Data Eng. 26(9), 2138\u20132150 (2014). doi:\n                    10.1109\/TKDE.2013.65","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"10","key":"547_CR21","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.1109\/TPAMI.2015.2400461","volume":"37","author":"Z Li","year":"2015","unstructured":"Li, Z., Liu, J., Tang, J., Lu, H.: Robust structured subspace learning for data representation. IEEE Trans. Pattern Anal. Mach. Intell. 37(10), 2085\u20132098 (2015). doi:\n                    10.1109\/TPAMI.2015.2400461","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"547_CR22","doi-asserted-by":"publisher","unstructured":"Liu, M., Shan, S., Wang, R., Chen, X.: Learning expressionlets on spatio-temporal manifold for dynamic facial expression recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1749\u20131756 (2014). doi:\n                    10.1109\/CVPR.2014.226","DOI":"10.1109\/CVPR.2014.226"},{"key":"547_CR23","doi-asserted-by":"publisher","unstructured":"Lu J, Hu J, Zhou X, Shang Y: Activity-based person identification using sparse coding and discriminative metric learning. In: ACM International Conference on Multimedia, pp. 1061\u20131064, (2012). doi:\n                    10.1145\/2393347.2396383","DOI":"10.1145\/2393347.2396383"},{"issue":"2","key":"547_CR24","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh, M., Moghaddam Charkari, N.: Multimodal information fusion application to human emotion recognition from face and speech. Multimed. Tools Appl. 49(2), 277\u2013297 (2010). doi:\n                    10.1007\/s11042-009-0344-2","journal-title":"Multimed. Tools Appl."},{"key":"547_CR25","doi-asserted-by":"publisher","unstructured":"Martin O, Kotsia I, Macq B, Pitas I (2006) The enterface\u201905 audio-visual emotion database. In: International Conference on Data Engineering Workshops, pp. 8\u20138. doi:\n                    10.1109\/ICDEW.2006.145","DOI":"10.1109\/ICDEW.2006.145"},{"issue":"8","key":"547_CR26","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1109\/LSP.2015.2390222","volume":"22","author":"Le An","year":"2015","unstructured":"Mroueh, Y., Marcheret, E., Goel, V.: Deep multimodal learning for audio-visual speech recognition. In: IEEE International Conference on Acoustics Speech and Signal Processing, vol. 22, pp. 1103\u20131107 (2015). doi:\n                    10.1109\/LSP.2015.2390222","journal-title":"IEEE Signal Processing Letters"},{"key":"547_CR27","doi-asserted-by":"publisher","unstructured":"Nie, L., Zhang, L., Yang, Y., Wang, M., Hong, R., Chua, T.S.: Beyond doctors: future health prediction from multimedia and multimodal observations. In: The 23rd ACM International Conference on Multimedia, pp. 591\u2013600. (2015). doi:\n                    10.1145\/2733373.2806217","DOI":"10.1145\/2733373.2806217"},{"issue":"2","key":"547_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00714ED1V01Y201603ICR048","volume":"8","author":"Liqiang Nie","year":"2016","unstructured":"Nie, L., Song, X., Chua, T.S.: Learning from Multiple Social Networks, pp. 118\u2013118. Morgan & Claypool, San Rafael (2016). doi:\n                    10.2200\/S00714ED1V01Y201603ICR048","journal-title":"Synthesis Lectures on Information Concepts, Retrieval, and Services"},{"key":"547_CR29","doi-asserted-by":"publisher","unstructured":"Paleari, M., Huet, B.: Toward emotion indexing of multimedia excerpts. In: International Workshop on Content-Based Multimedia Indexing, pp. 425\u2013432, (2008). doi:\n                    10.1109\/CBMI.2008.4564978","DOI":"10.1109\/CBMI.2008.4564978"},{"key":"547_CR30","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-540-92892-8_44","volume-title":"Lecture Notes in Computer Science","author":"Marco Paleari","year":"2009","unstructured":"Paleari, M., Benmokhtar, R., Huet, B.: Evidence theory-based multimodal emotion recognition. In: International Multimedia Modeling Conference on Advances in Multimedia Modeling, vol. 5371, pp. 435\u2013446 (2009). doi:\n                    10.1007\/978-3-540-92892-8_44"},{"key":"547_CR31","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-642-17248-9_32","volume-title":"Social Robotics","author":"Marco Paleari","year":"2010","unstructured":"Paleari, M., Chellali, R., Huet, B.: Bimodal emotion recognition. In: International Conference on Social Robotics, vol. 6414, pp. 305\u2013314 (2010). doi:\n                    10.1007\/978-3-642-17248-9_32"},{"issue":"1","key":"547_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11063-009-9123-3","volume":"31","author":"Y Peng","year":"2010","unstructured":"Peng, Y., Zhang, D., Zhang, J.: A new canonical correlation analysis algorithm with local discrimination. Neural Process. Lett. 31(1), 1\u201315 (2010). doi:\n                    10.1007\/s11063-009-9123-3","journal-title":"Neural Process. Lett."},{"issue":"2","key":"547_CR33","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1109\/TNSRE.2006.875544","volume":"14","author":"T Pun","year":"2006","unstructured":"Pun, T., Alecu, T.I., Chanel, G., Kronegg, J.: Brain-computer interaction research at the computer vision and multimedia laboratory, university of geneva. IEEE Trans. Neural Syst. Rehabil. Eng. 14(2), 210\u2013213 (2006). doi:\n                    10.1109\/TNSRE.2006.875544","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"issue":"6","key":"547_CR34","first-page":"6","volume":"5","author":"EM Schmidt","year":"2012","unstructured":"Schmidt, E.M.: Modeling and predicting emotion in music. Emotion 5, 6-6 (2012)","journal-title":"Emotion"},{"key":"547_CR35","doi-asserted-by":"publisher","unstructured":"Schuller B, Vlasenko B, Eyben F, Rigoll G, Wendemuth A (2009) Acoustic emotion recognition: a benchmark comparison of performances. In: IEEE Workshop on Automatic Speech Recognition & Understanding, pp. 552\u2013557, doi:\n                    10.1109\/ASRU.2009.5372886","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"547_CR36","doi-asserted-by":"publisher","unstructured":"Shan, C., Gong, S., Mcowan, P.W.: Beyond facial expressions: Learning human emotion from body gestures. In: Proceedings of the British Machine Vision Conference, pp. 43.1\u201343.10 (2007). doi:\n                    10.5244\/C.21.43","DOI":"10.5244\/C.21.43"},{"issue":"4","key":"547_CR37","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1109\/TNNLS.2012.2183645","volume":"23","author":"A Stuhlsatz","year":"2012","unstructured":"Stuhlsatz, A., Lippel, J., Zielke, T.: Feature extraction with deep neural networks by a generalized discriminant analysis. IEEE Trans. Neural Netw. Learn. Syst. 23(4), 596\u2013608 (2012). doi:\n                    10.1109\/TNNLS.2012.2183645","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"547_CR38","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.1109\/TPAMI.2016.2608882","volume":"39","author":"Jinhui Tang","year":"2017","unstructured":"Tang, J., Shu, X., Qi, G.J., Li, Z., Wang, M., Yan, S., Jain, R.: Tri-clustered tensor completion for social-aware image tag refinement. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1\u20131 (2016). doi:\n                    10.1109\/TPAMI.2016.2608882","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"547_CR39","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1109\/LSP.2010.2071863","volume":"17","author":"H Wang","year":"2010","unstructured":"Wang, H.: Local two-dimensional canonical correlation analysis. IEEE Signal Process. Lett. 17(11), 921\u2013924 (2010). doi:\n                    10.1109\/LSP.2010.2071863","journal-title":"IEEE Signal Process. Lett."},{"key":"547_CR40","doi-asserted-by":"publisher","unstructured":"Wang, Y., Guan, L., Venetsanopoulos, A.N.: Audiovisual emotion recognition via cross-modal association in kernel space. In: IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2011). doi:\n                    10.1109\/ICME.2011.6011949","DOI":"10.1109\/ICME.2011.6011949"},{"issue":"2","key":"547_CR41","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TMM.2006.886310","volume":"9","author":"Z Zeng","year":"2007","unstructured":"Zeng, Z., Tu, J., Liu, M., Huang, T.S., Pianfetti, B., Roth, D., Levinson, S.: Audio-visual affect recognition. IEEE Trans. Multimed. 9(2), 424\u2013428 (2007). doi:\n                    10.1109\/TMM.2006.886310","journal-title":"IEEE Trans. Multimed."},{"issue":"6","key":"547_CR42","doi-asserted-by":"publisher","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). doi:\n                    10.1109\/TPAMI.2007.1110","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0547-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-017-0547-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0547-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,3]],"date-time":"2019-11-03T21:02:51Z","timestamp":1572814971000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-017-0547-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,22]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["547"],"URL":"https:\/\/doi.org\/10.1007\/s00530-017-0547-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,22]]},"assertion":[{"value":"22 March 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}