{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:43:00Z","timestamp":1771915380460,"version":"3.50.1"},"reference-count":26,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJICC"],"published-print":{"date-parts":[[2020,11,5]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>recent years, facial expression recognition has been widely used in human machine interaction, clinical medicine and safe driving. However, there is a limitation that conventional recurrent neural networks can only learn the time-series characteristics of expressions based on one-way propagation information.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>To solve such limitation, this paper proposes a novel model based on bidirectional gated recurrent unit networks (Bi-GRUs) with two-way propagations, and the theory of identity mapping residuals is adopted to effectively prevent the problem of gradient disappearance caused by the depth of the introduced network. Since the Inception-V3 network model for spatial feature extraction has too many parameters, it is prone to overfitting during training. This paper proposes a novel facial expression recognition model to add two reduction modules to reduce parameters, so as to obtain an Inception-W network with better generalization.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>Finally, the proposed model is pretrained to determine the best settings and selections. Then, the pretrained model is experimented on two facial expression data sets of CK+ and Oulu- CASIA, and the recognition performance and efficiency are compared with the existing methods. The highest recognition rate is 99.6%, which shows that the method has good recognition accuracy in a certain range.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>By using the proposed model for the applications of facial expression, the high recognition accuracy and robust recognition results with lower time consumption will help to build more sophisticated applications in real world.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ijicc-07-2020-0088","type":"journal-article","created":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T04:49:13Z","timestamp":1604551753000},"page":"527-543","source":"Crossref","is-referenced-by-count":8,"title":["Facial expression recognition based on bidirectional gated recurrent units within deep residual network"],"prefix":"10.1108","volume":"13","author":[{"given":"Wenjuan","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","reference":[{"key":"key2020111310170486400_ref001","first-page":"433","article-title":"Emotion recognition in the wild from videos using images","year":"2016"},{"key":"key2020111310170486400_ref002","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","year":"2017"},{"key":"key2020111310170486400_ref003","first-page":"139","article-title":"Facial expression recognition using a hybrid CNN\u2013SIFT aggregator","volume-title":"International Workshop on Multi-Disciplinary Trends in Artificial Intelligence","year":"2017"},{"issue":"8","key":"key2020111310170486400_ref004","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1109\/TPAMI.2016.2515606","article-title":"Survey on rgb, 3d, thermal, and multimodal approaches for facial expression recognition: history, trends, and affect-related applications","volume":"38","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"key2020111310170486400_ref005","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1049\/iet-bmt.2014.0104","article-title":"Survey on real-time facial expression recognition techniques","volume":"5","year":"2016","journal-title":"Iet Biometrics"},{"key":"key2020111310170486400_ref006","first-page":"1597","article-title":"Gate-variants of gated recurrent unit (GRU) neural networks","year":"2017"},{"key":"key2020111310170486400_ref007","first-page":"467","article-title":"Recurrent neural networks for emotion recognition in video","year":"2015"},{"issue":"10","key":"key2020111310170486400_ref008","first-page":"2222","article-title":"LSTM: a search space odyssey","volume":"28","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"key2020111310170486400_ref009","first-page":"87","article-title":"Ms-celeb-1m: a dataset and benchmark for large-scale face recognition","year":"2016"},{"key":"key2020111310170486400_ref010","first-page":"770","article-title":"Deep residual learning for image recognition","year":"2016"},{"key":"key2020111310170486400_ref011","first-page":"2983","article-title":"Joint fine-tuning in deep neural networks for facial expression recognition","year":"2015"},{"key":"key2020111310170486400_ref012","first-page":"619","article-title":"How deep neural networks can improve emotion recognition on video data","year":"2016"},{"key":"key2020111310170486400_ref013","first-page":"143","article-title":"Deeply learning deformable facial action parts model for dynamic expression analysis","year":"2014"},{"key":"key2020111310170486400_ref014","first-page":"1749","article-title":"Learning expressionlets on spatio-temporal manifold for dynamic facial expression recognition","year":"2014"},{"key":"key2020111310170486400_ref015","first-page":"94","article-title":"The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression","year":"2010"},{"key":"key2020111310170486400_ref016","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/j.procs.2016.07.233","article-title":"Automatic facial expression recognition using DCNN","volume":"93","year":"2016","journal-title":"Procedia Computer Science"},{"key":"key2020111310170486400_ref017","first-page":"811","article-title":"Towards a mathematical understanding of the difficulty in learning with feedforward neural networks","year":"2018"},{"key":"key2020111310170486400_ref018","first-page":"209","article-title":"Facial expression recognition by fusing Gabor and local binary pattern features","year":"2017"},{"key":"key2020111310170486400_ref019","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","year":"2017"},{"key":"key2020111310170486400_ref020","first-page":"569","article-title":"Temporal multimodal fusion for video emotion classification in the wild","year":"2017"},{"key":"key2020111310170486400_ref021","first-page":"5498","article-title":"Learning dynamic generator model by alternating back-propagation through time","year":"2019"},{"key":"key2020111310170486400_ref022","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.patrec.2020.01.019","article-title":"End-to-end video subtitle recognition via a deep Residual Neural Network","volume":"131","year":"2020","journal-title":"Pattern Recognition Letters"},{"issue":"12","key":"key2020111310170486400_ref023","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1007\/s00371-017-1443-0","article-title":"Deeper cascaded peak-piloted network for weak expression recognition","volume":"34","year":"2018","journal-title":"The Visual Computer"},{"issue":"10","key":"key2020111310170486400_ref024","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","year":"2016","journal-title":"IEEE Signal Processing Letters"},{"issue":"9","key":"key2020111310170486400_ref025","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1016\/j.imavis.2011.07.002","article-title":"Facial expression recognition from near-infrared videos","volume":"29","year":"2011","journal-title":"Image and Vision Computing"},{"key":"key2020111310170486400_ref026","first-page":"425","article-title":"Peak-piloted deep network for facial expression recognition","year":"2016"}],"container-title":["International Journal of Intelligent Computing and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-07-2020-0088\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-07-2020-0088\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:54:34Z","timestamp":1753397674000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijicc\/article\/13\/4\/527-543\/510664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,11,5]]}},"alternative-id":["10.1108\/IJICC-07-2020-0088"],"URL":"https:\/\/doi.org\/10.1108\/ijicc-07-2020-0088","relation":{},"ISSN":["1756-378X"],"issn-type":[{"value":"1756-378X","type":"print"}],"subject":[],"published":{"date-parts":[[2020,10,12]]}}}