{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:05:38Z","timestamp":1772553938489,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"R&D program for Advanced Integrated-Intelligence for Identification (AIID) through the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2018M3E3A1057289"],"award-info":[{"award-number":["NRF-2018M3E3A1057289"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2996086","type":"journal-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T20:38:33Z","timestamp":1590611913000},"page":"6977-6991","source":"Crossref","is-referenced-by-count":84,"title":["Multi-Modal Recurrent Attention Networks for Facial Expression Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0840-3317","authenticated-orcid":false,"given":"Jiyoung","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9665-4214","authenticated-orcid":false,"given":"Sunok","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3715-0331","authenticated-orcid":false,"given":"Kwanghoon","family":"Sohn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref72","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref71","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref70","author":"wiedemeyer","year":"2015","journal-title":"IAI Kinect2"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref74","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 14th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670949"},{"key":"ref75","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref78","first-page":"1","article-title":"Deep face recognition","author":"parkhi","year":"2015","journal-title":"Proc BMVC"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-013-0159-8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388781"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"ref60","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.53.4.712"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.657"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666275"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461920"},{"key":"ref66","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811638"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296377"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref69","author":"ekman","year":"1977","journal-title":"Facial Action Coding System"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2007.79"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(03)00051-X"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2060716"},{"key":"ref21","first-page":"1","article-title":"Spontaneous facial expression analysis based on temperature changes and head motions","author":"liu","year":"2015","journal-title":"Proc 11th IEEE Int Conf Workshops Autom Face Gesture Recognit (FG)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.374"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0901-x"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351062"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00791"},{"key":"ref57","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref55","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","author":"larochelle","year":"2010","journal-title":"Proc NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref53","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2774007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868382"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.02.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-X"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2436926"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.212"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.11.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806408"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388776"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264978"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FGR.2006.55"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.12"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.38"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref9","first-page":"543","article-title":"Combining modality specific deep neural networks for emotion recognition in video","author":"kahou","year":"2013","journal-title":"Proc ACM Int Conf Multimodal Interact (ICMI)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738487"},{"key":"ref47","first-page":"211","article-title":"A 3D facial expression database for facial behavior research","author":"yin","year":"2006","journal-title":"Proc 7th Int Conf Autom Face Gesture Recognit"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.130"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7916(94)90063-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.26"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09102419.pdf?arnumber=9102419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:10Z","timestamp":1651070350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9102419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2996086","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}