{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T07:09:09Z","timestamp":1769929749584,"version":"3.49.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1629898"],"award-info":[{"award-number":["CNS-1629898"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/fg52635.2021.9666970","type":"proceedings-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T05:34:23Z","timestamp":1643175263000},"page":"01-08","source":"Crossref","is-referenced-by-count":11,"title":["Your \u201cAttention\u201d Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis"],"prefix":"10.1109","author":[{"given":"Xiaotian","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhihua","family":"Li","sequence":"additional","affiliation":[]},{"given":"Huiyuan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Geran","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Lijun","family":"Yin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Joint action unit localisation and intensity estimation through heatmap regression","author":"sanchez-lozano","year":"2018","journal-title":"BMVA"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"AAAI"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref32","article-title":"Imagenet large scale visual recognition challenge","author":"russakovsky","year":"2014","journal-title":"International Journal of Computer Vision"},{"key":"ref31","first-page":"5","author":"pantic","year":"0","journal-title":"2005 IEEE International Conference on Multimedia and Expo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01219"},{"key":"ref37","author":"shao","year":"2020","journal-title":"Spatio-temporal relation and attention learning for facial action unit detection"},{"key":"ref36","article-title":"JAa-net: Joint facial action unit detection and face alignment via adaptive attention","author":"shao","year":"2020","journal-title":"International Journal of Computer Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2948635"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477450"},{"key":"ref2","article-title":"High-performance large-scale image recognition without normalization","author":"brock","year":"2021","journal-title":"ar Xiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s21030833"},{"key":"ref22","article-title":"Deeply learning deformable facial action parts model for dynamic expression analysis","author":"liu","year":"2015","journal-title":"ACCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.026"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00112"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref50","article-title":"A 3d facial expression database for facial behavior research","author":"yin","year":"0","journal-title":"International Conference on FGR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413674"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.374"},{"key":"ref52","article-title":"Image super-resolution using very deep residual channel attention networks","author":"zhang","year":"2018","journal-title":"ECCV"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref40","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref12","author":"huang","year":"2019","journal-title":"GPipe Efficient training of giant neural networks using pipeline parallelism"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.341"},{"key":"ref14","article-title":"A spatio-temporal descriptor based on 3d-gradients","author":"hiser","year":"0","journal-title":"Proceedings of BMVC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.07.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.136"},{"key":"ref4","article-title":"Multi-head attention: Collaborate instead of concatenate","author":"cordonnier","year":"2021","journal-title":"ar Xiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP47243.2019.8965826"},{"key":"ref6","author":"dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words Transformers for image recognition at scale"},{"key":"ref5","article-title":"Deep structure inference network for facial action unit recognition","author":"corneanu","year":"0","journal-title":"Proceedings of ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2019.00011"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/s20185391"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2386334"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00231"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref48","first-page":"1","article-title":"Automatic 3d facial expression recognition using geometric scattering representation","author":"yang","year":"0","journal-title":"2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00746"},{"key":"ref41","article-title":"Survey on the attention based RNN model and its applications in computer vision","author":"wang","year":"2016","journal-title":"arXiv preprint 1601 06823"},{"key":"ref44","author":"wu","year":"0"},{"key":"ref43","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proceedings of the ECCV"}],"event":{"name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","location":"Jodhpur, India","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9666787\/9666788\/09666970.pdf?arnumber=9666970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T19:59:57Z","timestamp":1674590397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9666970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/fg52635.2021.9666970","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}