{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:17:06Z","timestamp":1773868626978,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Young Scientists Fund in National Natural Science Foundation of China","award":["61203374"],"award-info":[{"award-number":["61203374"]}]},{"name":"International cooperation project of Shaanxi Natural Science Foundation","award":["2014KW01-05"],"award-info":[{"award-number":["2014KW01-05"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s00371-019-01636-3","type":"journal-article","created":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T16:57:47Z","timestamp":1549040267000},"page":"499-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["Deep convolutional BiLSTM fusion network for facial expression recognition"],"prefix":"10.1007","volume":"36","author":[{"given":"Dandan","family":"Liang","sequence":"first","affiliation":[]},{"given":"Huagang","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Zhenbo","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yipu","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,1]]},"reference":[{"key":"1636_CR1","doi-asserted-by":"crossref","unstructured":"Afshar, S., Salah, A.A.: Facial expression recognition in the wild using improved dense trajectories and fisher vector encoding. In: Computer Vision and Pattern Recognition Workshops, pp. 1517\u20131525 (2016)","DOI":"10.1109\/CVPRW.2016.189"},{"key":"1636_CR2","first-page":"1","volume":"34","author":"S Agarwal","year":"2016","unstructured":"Agarwal, S., Santra, B., Mukherjee, D.P.: Anubhav: recognizing emotions through facial expression. Vis. Comput. 34, 1\u201315 (2016)","journal-title":"Vis. Comput."},{"key":"1636_CR3","doi-asserted-by":"crossref","unstructured":"Bargal, S.A., Barsoum, E., Ferrer, C.C., Zhang, C.: Emotion recognition in the wild from videos using images. In: ACM International Conference on Multimodal Interaction, pp. 433\u2013436 (2016)","DOI":"10.1145\/2993148.2997627"},{"issue":"6\u20138","key":"1636_CR4","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s00371-014-0960-3","volume":"30","author":"J Chi","year":"2014","unstructured":"Chi, J., Tu, C., Zhang, C.: Dynamic 3D facial expression modeling using Laplacian smooth and multi-scale mesh matching. Vis. Comput. 30(6\u20138), 649\u2013659 (2014)","journal-title":"Vis. Comput."},{"issue":"6\u20138","key":"1636_CR5","first-page":"1","volume":"32","author":"A Danelakis","year":"2016","unstructured":"Danelakis, A., Theoharis, T., Pratikakis, I.: A spatio-temporal wavelet-based descriptor for dynamic 3D facial expression retrieval and recognition. Vis. Comput. 32(6\u20138), 1\u201311 (2016)","journal-title":"Vis. Comput."},{"key":"1636_CR6","doi-asserted-by":"crossref","unstructured":"Ebrahimi Kahou, S., 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":"2","key":"1636_CR7","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1037\/h0030377","volume":"17","author":"P Ekman","year":"1971","unstructured":"Ekman, P., Friesen, W.V.: Constants across cultures in the face and emotion. J. Personal. Soc. Psychol. 17(2), 124 (1971)","journal-title":"J. Personal. Soc. Psychol."},{"key":"1636_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lu, X., Li, D., Liu, Y.: Video-based emotion recognition using CNN\u2013RNN and C3D hybrid networks. In: ACM International Conference on Multimodal Interaction, pp. 445\u2013450 (2016)","DOI":"10.1145\/2993148.2997632"},{"key":"1636_CR9","doi-asserted-by":"crossref","unstructured":"Goodfellow, I.J., Erhan, D., Carrier, P.L., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.H.: 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"},{"issue":"5\u20136","key":"1636_CR10","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5\u20136), 602\u2013610 (2005)","journal-title":"Neural Netw."},{"key":"1636_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Y., Zhao, G., Pietikainen, M.: Dynamic facial expression recognition using longitudinal facial expression atlases. In: European Conference on Computer Vision, pp. 631\u2013644 (2012)","DOI":"10.1007\/978-3-642-33709-3_45"},{"key":"1636_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1636_CR13","doi-asserted-by":"crossref","unstructured":"Jaiswal, S., Valstar, M.: Deep learning the dynamic appearance and shape of facial action units. In: Applications of Computer Vision (WACV), pp. 1\u20138 (2016)","DOI":"10.1109\/WACV.2016.7477625"},{"key":"1636_CR14","doi-asserted-by":"crossref","unstructured":"Jung, H., Lee, S., Yim, J., Park, S., Kim, J.: Joint fine-tuning in deep neural networks for facial expression recognition. In: IEEE International Conference on Computer Vision, pp. 2983\u20132991 (2015)","DOI":"10.1109\/ICCV.2015.341"},{"key":"1636_CR15","doi-asserted-by":"crossref","unstructured":"Kacem, A., Daoudi, M., Amor, B.B., Alvarezpaiva, J.C.: A novel space-time representation on the positive semidefinite cone for facial expression recognition. In: IEEE International Conference on Computer Vision, pp. 3199\u20133208 (2017)","DOI":"10.1109\/ICCV.2017.345"},{"key":"1636_CR16","doi-asserted-by":"crossref","unstructured":"Khorrami, P., Paine, T.L., Brady, K., Dagli, C., Huang, T.S.: How deep neural networks can improve emotion recognition on video data, pp. 619\u2013623 (2016)","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"1636_CR17","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: Proceedings of the British Machine Vision Conference, pp. 1\u201310 (2008)","DOI":"10.5244\/C.22.99"},{"key":"1636_CR18","unstructured":"LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, pp. 396\u2013404 (1990)"},{"key":"1636_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., Jie, Z., Jayashree, K., Qi, M., Jiang, J., Yan, S., Feng, J.: Video-based person re-identification with accumulative motion context. In: CoRR (2017)","DOI":"10.1109\/TCSVT.2017.2715499"},{"key":"1636_CR20","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, S., Shan, S., Wang, R., Chen, X.: Deeply learning deformable facial action parts model for dynamic expression analysis. In: Asian Conference on Computer Vision, pp. 143\u2013157 (2014)","DOI":"10.1007\/978-3-319-16817-3_10"},{"key":"1636_CR21","doi-asserted-by":"crossref","unstructured":"Liu, M., Shan, S., Wang, R., Chen, X.: Learning expression lets on spatio-temporal manifold for dynamic facial expression recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1749\u20131756 (2014)","DOI":"10.1109\/CVPR.2014.226"},{"key":"1636_CR22","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn, J.F., Kanade, T., Saragih, J.: The extended Cohn\u2013Kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: Computer Vision and Pattern Recognition Workshops, pp. 94\u2013101 (2010)","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"1636_CR23","unstructured":"Metaxas, D.N., Huang, J., Liu, B., Yang, P., Liu, Q., Zhong, L.: Learning active facial patches for expression analysis. In: Computer Vision and Pattern Recognition, pp. 2562\u20132569 (2012)"},{"key":"1636_CR24","doi-asserted-by":"crossref","unstructured":"Mollahosseini, A., Chan, D., Mahoor, M.H.: Going deeper in facial expression recognition using deep neural networks. In: Applications of Computer Vision (WACV), pp. 1\u201310 (2016)","DOI":"10.1109\/WACV.2016.7477450"},{"key":"1636_CR25","unstructured":"Ofodile, I., Kulkarni, K., Corneanu, C.A., Escalera, S., Baro, X., Hyniewska, S., Allik, J., Anbarjafari, G.: Automatic recognition of deceptive facial expressions of emotion. In: CoRR (2017)"},{"key":"1636_CR26","doi-asserted-by":"crossref","unstructured":"Sanin, A., Sanderson, C., Harandi, M.T., Lovell, B.C.: Spatio-temporal covariance descriptors for action and gesture recognition. In: IEEE Workshop on Applications of Computer Vision, pp. 103\u2013110 (2013)","DOI":"10.1109\/WACV.2013.6475006"},{"issue":"1","key":"1636_CR27","first-page":"224","volume":"2","author":"PV Saudagare","year":"2012","unstructured":"Saudagare, P.V., Chaudhari, D.: Facial expression recognition using neural network-an overview. Int. J. Soft Comput. Eng. (IJSCE) 2(1), 224\u2013227 (2012)","journal-title":"Int. J. Soft Comput. Eng. (IJSCE)"},{"key":"1636_CR28","doi-asserted-by":"crossref","unstructured":"Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. In: Image and Vision Computing, pp. 803\u2013816 (2009)","DOI":"10.1016\/j.imavis.2008.08.005"},{"key":"1636_CR29","doi-asserted-by":"crossref","unstructured":"Sikka, K., Sharma, G., Bartlett, M.: Lomo: latent ordinal model for facial analysis in videos. In: Computer Vision and Pattern Recognition, pp. 5580\u20135589 (2016)","DOI":"10.1109\/CVPR.2016.602"},{"key":"1636_CR30","doi-asserted-by":"crossref","unstructured":"Sikka, K., Wu, T., Susskind, J., Bartlett, M.: Exploring bag of words architectures in the facial expression domain. In: Computer Vision\u2014ECCV 2012. Workshops and Demonstrations, pp. 250\u2013259 (2012)","DOI":"10.1007\/978-3-642-33868-7_25"},{"key":"1636_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: CoRR (2014)"},{"key":"1636_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp. 4278\u20134284 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1636_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1636_CR34","unstructured":"Taini, M., Zhao, G., Li, S.Z., Pietikainen, M.: Facial expression recognition from near-infrared video sequences. In: International Conference on Pattern Recognition, pp. 1\u20134 (2011)"},{"key":"1636_CR35","unstructured":"Valstar, M., Pantic, M.: Induced disgust, happiness and surprise: an addition to the MMI facial expression database. In: Proceedings of the 3rd International Workshop on EMOTION (satellite of LREC): Corpora for Research on Emotion and Affect, p. 65 (2010)"},{"key":"1636_CR36","doi-asserted-by":"crossref","unstructured":"Valstar, M.F., Almaev, T., Girard, J.M., Mckeown, G.: Fera 2015 second facial expression recognition and analysis challenge. In: IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, pp. 1\u20138 (2015)","DOI":"10.1109\/FG.2015.7284874"},{"key":"1636_CR37","unstructured":"Yang, P.: Learning active facial patches for expression analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2562\u20132569 (2012)"},{"key":"1636_CR38","unstructured":"Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. In: CoRR (2014)"},{"key":"1636_CR39","first-page":"1","volume":"6\u20138","author":"Z Yu","year":"2017","unstructured":"Yu, Z., Liu, Q., Liu, G.: Deeper cascaded peak-piloted network for weak expression recognition. Vis. Comput. 6\u20138, 1\u20139 (2017)","journal-title":"Vis. Comput."},{"key":"1636_CR40","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zhang, C.: Image based static facial expression recognition with multiple deep network learning. In: ACM on International Conference on Multimodal Interaction, pp. 435\u2013442 (2015)","DOI":"10.1145\/2818346.2830595"},{"key":"1636_CR41","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23, 1499\u20131503 (2016)","journal-title":"IEEE Signal Process. Lett."},{"issue":"5","key":"1636_CR42","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11263-017-1055-1","volume":"126","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Luo, P., Chen, C.L., Tang, X.: From facial expression recognition to interpersonal relation prediction. Int. J. Comput. Vis. 126(5), 550\u2013569 (2018)","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"1636_CR43","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.imavis.2011.07.002","volume":"29","author":"G Zhao","year":"2011","unstructured":"Zhao, G., Huang, X., Taini, M., Li, S.Z., Pietik\u00e4inen, M.: Facial expression recognition from near-infrared videos. Image Vis. Comput. 29(9), 607\u2013619 (2011)","journal-title":"Image Vis. Comput."},{"key":"1636_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, X., Liang, X., Liu, L., Li, T., Han, Y., Vasconcelos, N., Yan, S.: Peak-piloted deep network for facial expression recognition. In: European Conference on Computer Vision, pp. 425\u2013442 (2016)","DOI":"10.1007\/978-3-319-46475-6_27"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-019-01636-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01636-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01636-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,11]],"date-time":"2022-09-11T08:09:43Z","timestamp":1662883783000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-019-01636-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,1]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1636"],"URL":"https:\/\/doi.org\/10.1007\/s00371-019-01636-3","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,1]]},"assertion":[{"value":"1 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}