{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T01:10:13Z","timestamp":1790989813496,"version":"4.1.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB1001004"],"award-info":[{"award-number":["2016YFB1001004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61672306"],"award-info":[{"award-number":["61672306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61572271"],"award-info":[{"award-number":["61572271"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61527808"],"award-info":[{"award-number":["61527808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61373074"],"award-info":[{"award-number":["61373074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61373090"],"award-info":[{"award-number":["61373090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National 1000 Young Talents Plan Program"},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"crossref","award":["2014CB349304"],"award-info":[{"award-number":["2014CB349304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Fundamental Research Fund","award":["JCYJ20170412170602564"],"award-info":[{"award-number":["JCYJ20170412170602564"]}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of China","doi-asserted-by":"crossref","award":["20120002110033"],"award-info":[{"award-number":["20120002110033"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Tsinghua University Initiative Scientific Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,11,1]]},"DOI":"10.1109\/tpami.2017.2734779","type":"journal-article","created":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T18:34:17Z","timestamp":1501612457000},"page":"2546-2554","source":"Crossref","is-referenced-by-count":76,"title":["Two-Stream Transformer Networks for Video-Based Face Alignment"],"prefix":"10.1109","volume":"40","author":[{"given":"Hao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-6707","authenticated-orcid":false,"given":"Jianjiang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref33","first-page":"521","article-title":"3D face alignment without correspondences","author":"s\u00e1nta","year":"2016","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_39"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.59"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"ref37","first-page":"3476","article-title":"Deep convolutional network\n cascade for facial point detection","author":"sun","year":"2013","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","article-title":"Globally tuned cascade pose\n regression via back propagation with application in 2D face pose estimation and heart segmentation in 3D CT images","volume":"abs 1503 8843","author":"sun","year":"2015"},{"key":"ref35","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","first-page":"1003","article-title":"The first facial landmark tracking in-the-wild challenge: Benchmark and results","author":"shen","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis Workshop"},{"key":"ref28","first-page":"1","article-title":"Beyond temporal pooling: Recurrence and temporal convolutions for\n gesture recognition in video","author":"pigou","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.247"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.218"},{"key":"ref2","article-title":"TensorFlow: Large-scale machine learning on\n heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref1","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref21","first-page":"1894","article-title":"Going deeper into\n first-person activity recognition","author":"ma","year":"2016"},{"key":"ref24","first-page":"41.1","article-title":"Deep\n face recognition","author":"parkhi","year":"2015","journal-title":"Proc British Mach Vis Conf"},{"key":"ref23","first-page":"1520","article-title":"Learning deconvolution\n network for semantic segmentation","author":"noh","year":"2015","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref26","first-page":"3880","article-title":"PIEFA: Personalized incremental and\n ensemble face alignment","author":"peng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref25","first-page":"38","article-title":"A recurrent encoder-decoder network for\n sequential face alignment","author":"peng","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","first-page":"4998","article-title":"Face alignment by coarse-to-fine shape searching","author":"zhu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008122917811"},{"key":"ref11","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.453"},{"key":"ref12","author":"gonzalez","year":"2003","journal-title":"Digital Image Processing Using Matlab"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_42"},{"key":"ref14","first-page":"552","article-title":"Fully automated and highly accurate dense correspondence for facial surfaces","author":"grewe","year":"2016","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.242"},{"key":"ref16","first-page":"3296","article-title":"Coupling alignments with recognition for still-to-video face\n recognition","author":"huang","year":"2013","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref18","first-page":"1106","article-title":"Imagenet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"340","article-title":"FaceTracer: A search engine for large collections of images with faces","author":"kumar","year":"2008","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","first-page":"2830","article-title":"Robust optimization for deep regression","author":"belagiannis","year":"2015","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref3","first-page":"1859","article-title":"Incremental face alignment in the wild","author":"asthana","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref6","first-page":"616","article-title":"Two-stage convolutional part heatmap regression for the 1st 3D face alignment in\n the wild (3DFAW) challenge","author":"bulat","year":"2016","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1995.466915"},{"key":"ref8","first-page":"954","article-title":"Offline deformable face tracking in\n arbitrary videos","author":"chrysos","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis Workshop"},{"key":"ref7","first-page":"2887","article-title":"Face alignment by explicit shape regression","author":"cao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2469286"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"ref45","first-page":"57","article-title":"Robust facial landmark detection via recurrent attentive-refinement networks","author":"xiao","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","first-page":"1","article-title":"Coarse-to-fine auto-encoder networks (CFAN)\n for real-time face alignment","author":"zhang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2509999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389830"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"ref44","first-page":"1781","article-title":"A hierarchical probabilistic\n model for facial feature detection","author":"wu","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0775-8"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8478843\/07999169.pdf?arnumber=7999169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:29:20Z","timestamp":1642004960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7999169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,1]]},"references-count":50,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2734779","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,1]]}}}