{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:11:42Z","timestamp":1779379902941,"version":"3.53.1"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461920","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"1513-1517","source":"Crossref","is-referenced-by-count":22,"title":["Spatiotemporal Attention Based Deep Neural Networks for Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Jiyoung","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunok","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungryong","family":"Kiim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwanghoon","family":"Sohn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","author":"ringeval","year":"2017","journal-title":"Avec 2017-real-life depression and a ect recognition workshop and challenge"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.53.4.712"},{"key":"ref11","author":"ekman","year":"1994","journal-title":"Strong Evidence for Universals in Facial Expressions A Reply to Russell's Mistaken Critique"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-X"},{"key":"ref13","author":"ekman","year":"2003","journal-title":"Unmasking the Face A Guide to Recognizing Emotions From Facial Clues"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.410"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","author":"sharma","year":"2015","journal-title":"Action recognition using visual attention"},{"key":"ref19","article-title":"Automatic 2d-to-3d conversion using multi-scale deep neural network","author":"lee","year":"2017","journal-title":"CA Proc IEEE Int Image Proc"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref4","first-page":"1","article-title":"Automatically detecting pain using facial actions","author":"patrie","year":"2009","journal-title":"Proc IEEE Affect Comput Intel Inter Work"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.297"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811638"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.12.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FGR.2006.55"},{"key":"ref2","first-page":"543","article-title":"Combining modality specific deep neural networks for emotion recognition in video","author":"kahou","year":"2013","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref9","first-page":"19","article-title":"Do deep neural networks learn facial action units when doing expression recognition?","author":"khorrami","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis Work"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"ref20","article-title":"Depth prediction from a single image with conditional adversarial networks","author":"jung","year":"2017","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref22","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","first-page":"802","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc Neur Info Proc Sys"},{"key":"ref24","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref23","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","journal-title":"software available from"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806408"},{"key":"ref25","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Ar-tific Intell Statis"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461920.pdf?arnumber=8461920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:03:39Z","timestamp":1598231019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461920","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}