{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:25:29Z","timestamp":1710289529397},"reference-count":31,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Communications and Networks"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1016\/j.dcan.2022.07.009","type":"journal-article","created":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T06:52:57Z","timestamp":1659250377000},"page":"1441-1447","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"title":["The deep spatiotemporal network with dual-flow fusion for video-oriented facial expression recognition"],"prefix":"10.1016","volume":"9","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-0453-5630","authenticated-orcid":false,"given":"Chenquan","family":"Gan","sequence":"first","affiliation":[]},{"given":"Jinhui","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Shuaiying","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Zufan","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5779-1910","authenticated-orcid":false,"given":"Lianxiang","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.dcan.2022.07.009_bib1","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/ACCESS.2019.2961606","article-title":"Monocular depth estimation based on multi-scale graph convolution networks","volume":"8","author":"Fu","year":"2019","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.dcan.2022.07.009_bib2","article-title":"Light-weight residual learning for single image dehazing","volume":"28","author":"Ding","year":"2019","journal-title":"J.\u00a0Electron. Imag."},{"issue":"11","key":"10.1016\/j.dcan.2022.07.009_bib3","doi-asserted-by":"crossref","first-page":"8533","DOI":"10.1109\/TIE.2018.2890499","article-title":"Sequential Monte Carlo filter for state-of-charge estimation of lithium-ion batteries based on auto regressive exogenous model","volume":"66","author":"Dong","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"10","key":"10.1016\/j.dcan.2022.07.009_bib4","doi-asserted-by":"crossref","first-page":"2484","DOI":"10.1109\/TCSVT.2017.2772026","article-title":"Mixture statistic metric learning for robust human action and expression recognition","volume":"28","author":"Dai","year":"2017","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"6","key":"10.1016\/j.dcan.2022.07.009_bib5","first-page":"e1264","article-title":"Deep learning for remote sensing image classification: a survey","volume":"8","author":"Li","year":"2018","journal-title":"Wiley Interdisciplinary Reviews: Data Min. Knowl. Discov."},{"key":"10.1016\/j.dcan.2022.07.009_bib6","series-title":"2018 IEEE\/ACS 15th International Conference on Computer Systems and Applications (AICCSA)","first-page":"1","article-title":"Improving human face recognition using deep learning based image registration and multi-classifier approaches","author":"Abuzneid","year":"2018"},{"key":"10.1016\/j.dcan.2022.07.009_bib7","series-title":"2017 International Joint Conference on Neural Networks (IJCNN)","first-page":"2865","article-title":"Recent advances in video-based human action recognition using deep learning: a review","author":"Wu","year":"2017"},{"key":"10.1016\/j.dcan.2022.07.009_bib8","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"2121","article-title":"A\u00a0compact deep learning model for robust facial expression recognition","author":"Kuo","year":"2018"},{"key":"10.1016\/j.dcan.2022.07.009_bib9","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.jvcir.2018.12.039","article-title":"Video facial emotion recognition based on local enhanced motion history image and cnn-ctslstm networks","volume":"59","author":"Hu","year":"2019","journal-title":"J.\u00a0Vis. Commun. Image Represent."},{"key":"10.1016\/j.dcan.2022.07.009_bib10","series-title":"European Conference on Computer Vision","first-page":"425","article-title":"Peak-piloted deep network for facial expression recognition","author":"Zhao","year":"2016"},{"key":"10.1016\/j.dcan.2022.07.009_bib11","doi-asserted-by":"crossref","first-page":"147571","DOI":"10.1109\/ACCESS.2019.2946870","article-title":"Learning spatiotemporal features of csi for indoor localization with dual-stream 3d convolutional neural networks","volume":"7","author":"Jing","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.dcan.2022.07.009_bib12","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.neucom.2018.07.028","article-title":"Spatio-temporal convolutional features with nested lstm for facial expression recognition","volume":"317","author":"Yu","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.dcan.2022.07.009_bib13","series-title":"Proceedings of the 19th ACM International Conference on Multimodal Interaction","first-page":"536","article-title":"Modeling multimodal cues in a deep learning-based framework for emotion recognition in the wild","author":"Pini","year":"2017"},{"key":"10.1016\/j.dcan.2022.07.009_bib14","series-title":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","first-page":"1","article-title":"Visual scene-aware hybrid neural network architecture for video-based facial expression recognition","author":"Lee","year":"2019"},{"issue":"12","key":"10.1016\/j.dcan.2022.07.009_bib15","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","author":"Yu","year":"2018","journal-title":"Vis. Comput."},{"key":"10.1016\/j.dcan.2022.07.009_bib16","doi-asserted-by":"crossref","first-page":"48807","DOI":"10.1109\/ACCESS.2019.2907271","article-title":"A\u00a0deep spatial and temporal aggregation framework for video-based facial expression recognition","volume":"7","author":"Pan","year":"2019","journal-title":"IEEE Access"},{"issue":"4","key":"10.1016\/j.dcan.2022.07.009_bib17","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1049\/iet-ipr.2018.5728","article-title":"Geometric positions and optical flow based emotion detection using mlp and reduced dimensions","volume":"13","author":"Khan","year":"2019","journal-title":"IET Image Process."},{"issue":"10","key":"10.1016\/j.dcan.2022.07.009_bib18","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1007\/s00371-018-1477-y","article-title":"Learning deep facial expression features from image and optical flow sequences using 3d cnn","volume":"34","author":"Zhao","year":"2018","journal-title":"Vis. Comput."},{"key":"10.1016\/j.dcan.2022.07.009_bib19","doi-asserted-by":"crossref","first-page":"32297","DOI":"10.1109\/ACCESS.2019.2901521","article-title":"Learning affective video features for facial expression recognition via hybrid deep learning","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.dcan.2022.07.009_bib20","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105540","article-title":"Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation","volume":"82","author":"Yi","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.dcan.2022.07.009_bib21","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2983","article-title":"Joint fine-tuning in deep neural networks for facial expression recognition","author":"Jung","year":"2015"},{"issue":"9","key":"10.1016\/j.dcan.2022.07.009_bib22","doi-asserted-by":"crossref","first-page":"4193","DOI":"10.1109\/TIP.2017.2689999","article-title":"Facial expression recognition based on deep evolutional spatial-temporal networks","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.dcan.2022.07.009_bib23","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6450","article-title":"A\u00a0closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2018"},{"key":"10.1016\/j.dcan.2022.07.009_bib24","series-title":"2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)","first-page":"790","article-title":"Spatio-temporal facial expression recognition using convolutional neural networks and conditional random fields","author":"Hasani","year":"2017"},{"key":"10.1016\/j.dcan.2022.07.009_bib25","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.jvcir.2018.12.039","article-title":"Video facial emotion recognition based on local enhanced motion history image and cnn-ctslstm networks","volume":"59","author":"Hu","year":"2019","journal-title":"J.\u00a0Vis. Commun. Image Represent."},{"issue":"1","key":"10.1016\/j.dcan.2022.07.009_bib26","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/TAFFC.2016.2593719","article-title":"Facial expression recognition in video with multiple feature fusion","volume":"9","author":"Chen","year":"2016","journal-title":"IEEE Transact. Affective Comput."},{"issue":"15","key":"10.1016\/j.dcan.2022.07.009_bib27","doi-asserted-by":"crossref","first-page":"19455","DOI":"10.1007\/s11042-017-5354-x","article-title":"Facial-expression recognition based on a low-dimensional temporal feature space","volume":"77","author":"Abdallah","year":"2018","journal-title":"Multimed. Tool. Appl."},{"issue":"3","key":"10.1016\/j.dcan.2022.07.009_bib28","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3906\/elk-1809-75","article-title":"Efficient hierarchical temporal segmentation method for facial expression sequences","volume":"27","author":"Bian","year":"2019","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"key":"10.1016\/j.dcan.2022.07.009_bib29","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2852","article-title":"Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild","author":"Li","year":"2017"},{"key":"10.1016\/j.dcan.2022.07.009_bib30","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1749","article-title":"Learning expression lets on spatio-temporal manifold for dynamic facial expression recognition","author":"Liu","year":"2014"},{"key":"10.1016\/j.dcan.2022.07.009_bib31","series-title":"Proceedings of the 22nd ACM International Conference on Multimedia","first-page":"675","article-title":"Caffe: convolutional architecture for fast feature embedding","author":"Jia","year":"2014"}],"container-title":["Digital Communications and Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352864822001572?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352864822001572?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:25:39Z","timestamp":1710257139000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352864822001572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["S2352864822001572"],"URL":"https:\/\/doi.org\/10.1016\/j.dcan.2022.07.009","relation":{},"ISSN":["2352-8648"],"issn-type":[{"value":"2352-8648","type":"print"}],"subject":[],"published":{"date-parts":[[2023,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"The deep spatiotemporal network with dual-flow fusion for video-oriented facial expression recognition","name":"articletitle","label":"Article Title"},{"value":"Digital Communications and Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dcan.2022.07.009","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Chongqing University of Posts and Telecommunications. Publishing Services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd.","name":"copyright","label":"Copyright"}]}}