{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:01:49Z","timestamp":1774051309709,"version":"3.50.1"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,28]],"date-time":"2021-09-28T00:00:00Z","timestamp":1632787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,28]],"date-time":"2021-09-28T00:00:00Z","timestamp":1632787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,28]],"date-time":"2021-09-28T00:00:00Z","timestamp":1632787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,28]]},"DOI":"10.1109\/acii52823.2021.9597460","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:55:44Z","timestamp":1637016944000},"page":"1-8","source":"Crossref","is-referenced-by-count":15,"title":["Spatiotemporal Contrastive Learning of Facial Expressions in Videos"],"prefix":"10.1109","author":[{"given":"Shuvendu","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref31","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref30","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref36","article-title":"Spatiotemporal contrastive video representation learning","author":"qian","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref28","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","author":"dosovitskiy","year":"2014","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"ref27","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"2","author":"hadsell","year":"2006","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00231"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143006"},{"key":"ref20","article-title":"Detection of maternal and fetal stress from ecg with self-supervised representation learning","author":"sarkar","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref21","article-title":"Self-supervised ecg representation learning for emotion recognition","author":"sarkar","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref24","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref26","first-page":"2536","article-title":"Context encoders: Feature learning by inpainting","author":"pathak","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref25","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2956998"},{"key":"ref51","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689999"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-017-1443-0"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_45"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.226"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539"},{"key":"ref11","first-page":"6707","article-title":"Self-supervised learning of pretextinvariant representations","author":"misra","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref40","first-page":"3367","article-title":"Facial emotion recognition using light field images with deep attention-based bidirectional lstm","author":"sepas-moghaddam","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref12","article-title":"Self-supervised wearable-based activity recognition by learning to forecast motion","author":"taghanaki","year":"2020"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref17","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3328932"},{"key":"ref19","first-page":"3217","article-title":"Self-supervised learning for ecg-based emotion recognition","author":"sarkar","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24600-5_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/10140"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.12.013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2541831.2541864"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_27"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s21030833"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00286"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.341"},{"key":"ref48","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264992"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3054476"},{"key":"ref44","first-page":"143","article-title":"Deeply learning deformable facial action parts model for dynamic expression analysis","author":"liu","year":"2014","journal-title":"Asian Conference on Computer Vision"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997640"}],"event":{"name":"2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)","location":"Nara, Japan","start":{"date-parts":[[2021,9,28]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9597394\/9597388\/09597460.pdf?arnumber=9597460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:50:51Z","timestamp":1652201451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9597460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,28]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/acii52823.2021.9597460","relation":{},"subject":[],"published":{"date-parts":[[2021,9,28]]}}}