{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:15:50Z","timestamp":1773191750323,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"shaanxi provincial international science and technology collaboration project","award":["2017KW-ZD-14"],"award-info":[{"award-number":["2017KW-ZD-14"]}]},{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["61872256"],"award-info":[{"award-number":["61872256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"emo-app project"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00530-021-00849-8","type":"journal-article","created":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T17:30:48Z","timestamp":1633455048000},"page":"479-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A multi-scale multi-attention network for dynamic facial expression recognition"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5192-3863","authenticated-orcid":false,"given":"Xiaohan","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Sahli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,5]]},"reference":[{"issue":"2013","key":"849_CR1","first-page":"332","volume":"1","author":"SM Abd Elrahman","year":"2013","unstructured":"Abd Elrahman, S.M., Abraham, A.: A review of class imbalance problem. J. Netw. Innov. Comput. 1(2013), 332\u2013340 (2013)","journal-title":"J. Netw. Innov. Comput."},{"issue":"1","key":"849_CR2","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/BF01420984","volume":"12","author":"JL Barron","year":"1994","unstructured":"Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12(1), 43\u201377 (1994)","journal-title":"Int. J. Comput. Vis."},{"key":"849_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: A dataset for recognising faces across pose and age. In: 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018), IEEE, pp. 67\u201374 (2018)","DOI":"10.1109\/FG.2018.00020"},{"key":"849_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"849_CR5","doi-asserted-by":"crossref","unstructured":"Deng, D., Chen, Z., Shi, B.E.: Multitask emotion recognition with incomplete labels. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), IEEE, pp. 828\u2013835 (2020)","DOI":"10.1109\/FG47880.2020.00131"},{"key":"849_CR6","doi-asserted-by":"crossref","unstructured":"Dhall, A.: Emotiw 2019: Automatic emotion, engagement and cohesion prediction tasks. In: 2019 International Conference on Multimodal Interaction, pp. 546\u2013550 (2019)","DOI":"10.1145\/3340555.3355710"},{"issue":"03","key":"849_CR7","first-page":"34","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 Ann. Hist. Comput. 19(03), 34\u201341 (2012)","journal-title":"IEEE Ann. Hist. Comput."},{"key":"849_CR8","first-page":"84","volume-title":"International Conference on Artificial Neural Networks","author":"Y Fan","year":"2018","unstructured":"Fan, Y., Lam, J.C., Li, V.O.: Multi-region ensemble convolutional neural network for facial expression recognition. In: International Conference on Artificial Neural Networks, pp. 84\u201394. Springer, Berlin (2018)"},{"key":"849_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lam, J.C., Li, V.O.: Video-based emotion recognition using deeply-supervised neural networks. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 584\u2013588 (2018)","DOI":"10.1145\/3242969.3264978"},{"key":"849_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lu, X., Li, D., Liu, Y.: Video-based emotion recognition using cnn-rnn and c3d hybrid networks. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction, pp. 445\u2013450 (2016)","DOI":"10.1145\/2993148.2997632"},{"issue":"2","key":"849_CR11","first-page":"5","volume":"3","author":"E Friesen","year":"1978","unstructured":"Friesen, E., Ekman, P.: Facial action coding system: a technique for the measurement of facial movement. Palo Alto 3(2), 5 (1978)","journal-title":"Palo Alto"},{"key":"849_CR12","unstructured":"Gera, D., Balasubramanian, S.: Affect expression behaviour analysis in the wild using spatio-channel attention and complementary context information. \narXiv preprint arXiv:2009.14440 (2020)"},{"key":"849_CR13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neunet.2014.09.005","volume":"64","author":"IJ Goodfellow","year":"2015","unstructured":"...Goodfellow, I.J., Erhan, D., Luc Carrier, P., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.H., Zhou, Y., Ramaiah, C., Feng, F., Li, R., Wang, X., Athanasakis, D., Shawe-Taylor, J., Milakov, M., Park, J., Ionescu, R., Popescu, M., Grozea, C., Bergstra, J., Xie, J., Romaszko, L., Xu, B., Chuang, Z., Bengio, Y.: Challenges in representation learning: A report on three machine learning contests. Neural Netw. 64, 59\u201363 (2015). (Special Issue on Deep Learning of Representations)","journal-title":"Neural Netw."},{"key":"849_CR14","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.imavis.2016.05.009","volume":"58","author":"LA Jeni","year":"2017","unstructured":"Jeni, L.A., Cohn, J.F., Kanade, T.: Dense 3d face alignment from 2d video for real-time use. Image Vis. Comput. 58, 13\u201324 (2017)","journal-title":"Image Vis. Comput."},{"key":"849_CR15","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: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2983\u20132991 (2015)","DOI":"10.1109\/ICCV.2015.341"},{"key":"849_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2961089","author":"I Kansizoglou","year":"2019","unstructured":"Kansizoglou, I., Bampis, L., Gasteratos, A.: An active learning paradigm for online audio-visual emotion recognition. IEEE Trans. Affect. Comput. (2019). https:\/\/doi.org\/10.1109\/TAFFC.2019.2961089","journal-title":"IEEE Trans. Affect. Comput."},{"key":"849_CR17","first-page":"3146","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.Y.: Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, 3146\u20133154 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"849_CR18","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1109\/TAFFC.2017.2695999","volume":"10","author":"DH Kim","year":"2017","unstructured":"Kim, D.H., Baddar, W.J., Jang, J., Ro, Y.M.: Multi-objective based spatio-temporal feature representation learning robust to expression intensity variations for facial expression recognition. IEEE Trans. Affect. Comput. 10(2), 223\u2013236 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"849_CR19","doi-asserted-by":"crossref","unstructured":"Knyazev, B., Shvetsov, R., Efremova, N., Kuharenko, A.: Leveraging large face recognition data for emotion classification. In: 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018), IEEE, pp. 692\u2013696 (2018)","DOI":"10.1109\/FG.2018.00109"},{"key":"849_CR20","doi-asserted-by":"crossref","unstructured":"Kollias, D., Schulc, A., Hajiyev, E., Zafeiriou, S.: Analysing affective behavior in the first abaw 2020 competition. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), IEEE, pp. 637\u2013643 (2020)","DOI":"10.1109\/FG47880.2020.00126"},{"key":"849_CR21","doi-asserted-by":"crossref","unstructured":"Kuhnke, F., Rumberg, L., Ostermann, J.: Two-stream aural-visual affect analysis in the wild. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), IEEE, pp. 600\u2013605 (2020)","DOI":"10.1109\/FG47880.2020.00056"},{"key":"849_CR22","first-page":"1243","volume-title":"Proceedings of the 23rdInternational Conference on Neural Information Processing Systems","author":"H Larochelle","year":"2010","unstructured":"Larochelle, H., Hinton, G.: Learning to combine foveal glimpses with a third-order boltzmann machine. In: Proceedings of the 23rdInternational Conference on Neural Information Processing Systems, pp. 1243\u20131251. Curran Associates Inc, Red Hook (2010)"},{"key":"849_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446","author":"S Li","year":"2020","unstructured":"Li, S., Deng, W.: Deep facial expression recognition: A survey. IEEE Trans. Affect. Comput. (2020). https:\/\/doi.org\/10.1109\/TAFFC.2020.2981446","journal-title":"IEEE Trans. Affect. Comput."},{"key":"849_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Zheng, W., Zong, Y., Lu, C., Tang, C., Jiang, X., Liu, J., Xia, W.: Bi-modality fusion for emotion recognition in the wild. In: 2019 International Conference on Multimodal Interaction, pp. 89\u2013594 (2019)","DOI":"10.1145\/3340555.3355719"},{"key":"849_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., Tang, T., Lv, K., Wang, M.: Multi-feature based emotionrecognition for video clips. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 630\u2013634 (2018)","DOI":"10.1145\/3242969.3264989"},{"key":"849_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Zeng, J., Shan, S.: Facial expression recognition for in-the-wild videos. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 615\u2013618 (2020)","DOI":"10.1109\/FG47880.2020.00102"},{"key":"849_CR27","first-page":"143","volume-title":"Asian Conference on Computer Vision","author":"M Liu","year":"2014","unstructured":"Liu, M., Li, S., Shan, S., Wang, R., Chen, S.: Deeply learning deformable facial action parts model for dynamic expression analysis. In: Asian Conference on Computer Vision, pp. 143\u2013157. Springer, Berlin (2014)"},{"key":"849_CR28","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.inffus.2018.06.003","volume":"46","author":"Y Ma","year":"2019","unstructured":"Ma, Y., Hao, Y., Chen, M., Chen, J., Lu, P., Ko\u0161ir, A.: Audio-visual emotion fusion (avef): A deep efficient weighted approach. Inf. Fus. 46, 184\u2013192 (2019)","journal-title":"Inf. Fus."},{"key":"849_CR29","doi-asserted-by":"crossref","unstructured":"Meng, D., Peng, X., Wang, K., Qiao, Y.: Frame attention networks for facial expression recognition in videos. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 3866\u20133870 (2019)","DOI":"10.1109\/ICIP.2019.8803603"},{"issue":"1","key":"849_CR30","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: A database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"849_CR31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3389\/fcomp.2019.00011","volume":"1","author":"EI Onal","year":"2019","unstructured":"Onal E.I., Yang, L., Jeni, L.A., Cohn, J.F.: D-pattnet: Dynamic patch-attentive deep network for action unit detection. Front. Comput. Sci. 1, 11 (2019)","journal-title":"Front. Comput. Sci."},{"key":"849_CR32","doi-asserted-by":"publisher","first-page":"48807","DOI":"10.1109\/ACCESS.2019.2907271","volume":"7","author":"X Pan","year":"2019","unstructured":"Pan, X., Ying, G., Chen, G., Li, H., Li, W.: A deep spatial and temporal aggregation framework for video-based facial expression recognition. IEEE Access 7, 48807\u201348815 (2019)","journal-title":"IEEE Access"},{"issue":"6","key":"849_CR33","doi-asserted-by":"publisher","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 Vis. Comput. 27(6), 803\u2013816 (2009)","journal-title":"Image Vis. Comput."},{"key":"849_CR34","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision(ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"849_CR35","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"849_CR36","doi-asserted-by":"crossref","unstructured":"Vielzeuf, V., Kervadec, C., Pateux, S., Lechervy, A., Jurie, F.: An occam\u2019s razor view on learning audiovisual emotion recognition withsmall training sets. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 589\u2013593 (2018)","DOI":"10.1145\/3242969.3264980"},{"issue":"5","key":"849_CR37","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Guan, L.: Recognizing human emotional state from audiovisual signals. IEEE Trans. Multimed. 10(5), 936\u2013946 (2008)","journal-title":"IEEE Trans. Multimed."},{"key":"849_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, J., Hoashi, K.: Multi-attention fusion network forvideo-based emotion recognition. In: 2019 International Conferenceon Multimodal Interaction, Association for Computing Machinery, pp. 595\u2013601 (2019)","DOI":"10.1145\/3340555.3355720"},{"key":"849_CR39","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., So Kweon, I.: Cbam: Convolutionalblock attention module. In: Proceedings of the European conferenceon computer vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"849_CR40","doi-asserted-by":"crossref","unstructured":"Xia, X., Liu, J., Yang, T., Jiang, D., Han, W., Sahli, H.: Videoemotion recognition using hand-crafted and deep learning features. In: 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia), IEEE, pp. 1\u20136 (2018)","DOI":"10.1109\/ACIIAsia.2018.8470326"},{"key":"849_CR41","unstructured":"Youoku, S., Toyoda, Y., Yamamoto, T., Saito, J., Kawamura, R., Mi, X., Murase, K.: A multi-term and multi-task analyzing framework for affective analysis in-the-wild. arXiv preprint arXiv:2009.13885 (2020)"},{"issue":"9","key":"849_CR42","doi-asserted-by":"publisher","first-page":"4193","DOI":"10.1109\/TIP.2017.2689999","volume":"26","author":"K Zhang","year":"2017","unstructured":"Zhang, K., Huang, Y., Du, Y., Wang, L.: Facial expression recognition based on deep evolutional spatial-temporal networks. IEEE Trans. Image Process. 26(9), 4193\u20134203 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"849_CR43","doi-asserted-by":"publisher","first-page":"32297","DOI":"10.1109\/ACCESS.2019.2901521","volume":"7","author":"S Zhang","year":"2019","unstructured":"Zhang, S., Pan, X., Cui, Y., Zhao, X., Liu, L.: Learning affective video features for facial expression recognition via hybrid deep learning. IEEE Access 7, 32297\u201332304 (2019)","journal-title":"IEEE Access"},{"key":"849_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, S., Huang, T., Gao, W.: Multimodal deep convolutional neural network for audio-visual emotion recognition. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 281\u2013284 (2016)","DOI":"10.1145\/2911996.2912051"},{"issue":"10","key":"849_CR45","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","volume":"28","author":"S Zhang","year":"2017","unstructured":"Zhang, S., Zhang, S., Huang, T., Gao, W., Tian, Q.: Learning affective features with a hybrid deep model for audio-visual emotion recognition. IEEE Trans. Circuits Syst. Video Technol. 28(10), 3030\u20133043 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"849_CR46","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2020.1814168","author":"X Zhao","year":"2020","unstructured":"Zhao, X., Chen, G., Chuang, Y., Tao, X., Zhang, S.: Learning expression features via deep residual attention networks for facial expression recognition from video sequences. IETE Tech. Rev. (2020). https:\/\/doi.org\/10.1080\/02564602.2020.1814168","journal-title":"IETE Tech. Rev."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00849-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00849-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00849-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,16]],"date-time":"2022-04-16T07:33:52Z","timestamp":1650094432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00849-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,5]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["849"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00849-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,5]]},"assertion":[{"value":"28 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}