{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:22:13Z","timestamp":1760955733966,"version":"3.37.3"},"reference-count":116,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Early Career Research Award"},{"DOI":"10.13039\/501100001843","name":"SERB","doi-asserted-by":"crossref","award":["ECR\/2016\/001158"],"award-info":[{"award-number":["ECR\/2016\/001158"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Research-I foundation at IIT Kanpur"},{"name":"NIH","award":["R01 NR013500"],"award-info":[{"award-number":["R01 NR013500"]}]},{"name":"National Institute of Health"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,8,1]]},"DOI":"10.1109\/tpami.2017.2741482","type":"journal-article","created":{"date-parts":[[2017,8,22]],"date-time":"2017-08-22T18:20:46Z","timestamp":1503426046000},"page":"1829-1844","source":"Crossref","is-referenced-by-count":7,"title":["Discriminatively Trained Latent Ordinal Model for Video Classification"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0187-5322","authenticated-orcid":false,"given":"Karan","family":"Sikka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4508-2009","authenticated-orcid":false,"given":"Gaurav","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771414"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/TPAMI.2013.134","article-title":"Neighborhood repulsed metric learning for Kinship verification","volume":"36","author":"lu","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472007"},{"key":"ref31","article-title":"Expression-invariant age estimation","author":"alnajar","year":"2014","journal-title":"Proc British Mach Vis Conf"},{"article-title":"Labeled faces in the wild: A\n database for studying face recognition in unconstrained environments","year":"2007","author":"huang","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33868-7_25"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-997-0_19"},{"key":"ref35","first-page":"368","article-title":"Continuous\n pain intensity estimation from facial expressions","author":"kaltwang","year":"2012","journal-title":"Proc Int Symp Visual Comput"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00052-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.602"},{"key":"ref27","first-page":"50.1","article-title":"High five: Recognising human\n interactions in TV shows","author":"patron-perez","year":"2010","journal-title":"Proc British Mach Vis Conf"},{"key":"ref29","article-title":"Deep\n face recognition","author":"parkhi","year":"2015","journal-title":"Proc British Mach Vis Conf"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206709"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part based models","volume":"32","author":"girshick","year":"2010","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"article-title":"VLFeat: An open and portable library of computer vision algorithms","year":"2008","author":"vedaldi","key":"ref101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457525"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.131"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21236\/ADA507101"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248093"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.284"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126413"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670990"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0846-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2163710"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.02.008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206612"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670980"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.93"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1124"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543267"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301350"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771370"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0677-1"},{"key":"ref72","first-page":"425","article-title":"Trajectory-based modeling of human actions with motion reference points","author":"jiang","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.332"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref74","first-page":"204","article-title":"Beyond Gaussian pyramid: Multi-skip feature stacking for action recognition","author":"lan","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.339"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.17"},{"key":"ref79","first-page":"536","article-title":"Modeling the temporal extent of actions","author":"satkin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.442"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.333"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.330"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref65","first-page":"1","article-title":"Visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc Workshop Statistical Learning in Computer Vision"},{"key":"ref66","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref67","first-page":"572","article-title":"A comparative\n study of encoding, pooling and normalization methods for action recognition","author":"wang","year":"2012","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2010.5583046"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref109","first-page":"167","article-title":"Improving pain recognition through better utilisation of temporal information","author":"lucey","year":"2008","journal-title":"Proc Int Conf Audit Vis Speech Process"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref108","first-page":"631","article-title":"Dynamic facial\n expression recognition using longitudinal facial expression Atlases","author":"guo","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.226"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0677-1"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005594"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref102","first-page":"ii-506","article-title":"PCA-SIFT: A more distinctive representation for local image descriptors","author":"ke","year":"2004","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.117"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32717-9_14"},{"key":"ref96","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771462"},{"key":"ref11","first-page":"1417","article-title":"Multiple\n instance boosting for object detection","author":"viola","year":"2006","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247983"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539998"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301321"},{"key":"ref15","first-page":"577","article-title":"Support vector machines for multiple-instance learning","author":"andrews","year":"2002","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref16","article-title":"Regularized multi-concept MIL for weakly-supervised facial behavior categorization","author":"ruiz","year":"2014","journal-title":"Proc British Mach Vis Conf"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref17","first-page":"1","article-title":"Multi-instance hidden Markov\n model for facial expression recognition","author":"wu","year":"2015","journal-title":"Proc IEEE Int Workshop Autom Face Gesture Recogn"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299137"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299056"},{"key":"ref84","article-title":"ImageNet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref83","first-page":"3","article-title":"Improving human action recognition using score distribution and ranking","author":"hoai","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0897-2"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref89","article-title":"VideoLSTM convolves, attends and flows for action\n recognition","author":"li","year":"2016","journal-title":"arXiv 1607 01794"},{"key":"ref85","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref86","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref88","article-title":"Delving deeper into convolutional\n networks for learning video representations","author":"ballas","year":"2015","journal-title":"arXiv 1511 06432"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8401722\/08014499.pdf?arnumber=8014499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T11:46:58Z","timestamp":1643197618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8014499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,1]]},"references-count":116,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2741482","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2018,8,1]]}}}