{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T11:13:55Z","timestamp":1772795635445,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100004963","name":"FP7","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"ERC","doi-asserted-by":"publisher","award":["240530"],"award-info":[{"award-number":["240530"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"COGNIMUND"},{"DOI":"10.13039\/501100004040","name":"KU Leuven","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004040","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DBOF"},{"DOI":"10.13039\/501100003130","name":"FWO","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004003","name":"iMinds","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004003","id-type":"DOI","asserted-by":"crossref"}]},{"name":"High-Tech Visualization project"},{"name":"Australian Research Council Centre of Excellence for Robotic Vision","award":["CE140100016"],"award-info":[{"award-number":["CE140100016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,4,1]]},"DOI":"10.1109\/tpami.2016.2558148","type":"journal-article","created":{"date-parts":[[2016,4,25]],"date-time":"2016-04-25T18:07:07Z","timestamp":1461607627000},"page":"773-787","source":"Crossref","is-referenced-by-count":231,"title":["Rank Pooling for Action Recognition"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-9916","authenticated-orcid":false,"given":"Basura","family":"Fernando","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Oramas M.","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Ghodrati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.247"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1992.223161"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2532589"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298924"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351243"},{"key":"ref75","first-page":"481","article-title":"Pipelining localized semantic features for fine-grained action recognition","author":"zhou","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref38","first-page":"2929","article-title":"Actions in\n context","author":"marsza?ek","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/1500000016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995672"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref60","first-page":"3104","article-title":"Sequence to\n sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","first-page":"140","article-title":"Convolutional learning of\n spatio-temporal features","author":"taylor","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.153"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref29","article-title":"The best of both worlds: Combining data-independent and data-driven approaches for action\n recognition","author":"lan","year":"2015","journal-title":"CoRR arXiv 1505 04427"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.214"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.98"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.330"},{"key":"ref2","first-page":"2911","article-title":"Three things everyone should know to improve object retrieval","author":"arandjelovi?","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150429"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.242"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.453"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2015.55"},{"key":"ref57","article-title":"Unsupervised learning of video representations using LSTMs","volume":"abs 1502 4681","author":"srivastava","year":"2015","journal-title":"CoRR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.457"},{"key":"ref55","first-page":"155","article-title":"Support vector regression machines","volume":"9","author":"smola","year":"1997","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.014"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"ICLRE"},{"key":"ref52","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"abs 1406 2199","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.212"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.319"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2359771"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995646"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0741-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref19","first-page":"3","article-title":"Improving human action recognition using score distribution and ranking","author":"hoai","year":"0","journal-title":"Proc 12th Asian Conf Comput Vis"},{"key":"ref4","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"bousquet","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7026167"},{"key":"ref5","first-page":"3218","article-title":"P-CNN:\n Pose-based CNN features for action recognition","author":"ch\u00e9ron","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref8","first-page":"1110","article-title":"Hierarchical recurrent\n neural network for skeleton based action recognition","author":"du","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021669406132"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2532595"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.129"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.318"},{"key":"ref42","first-page":"581","article-title":"Action recognition with stacked Fisher\n vectors","author":"peng","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050034"},{"key":"ref44","first-page":"814","article-title":"Domain-adaptive discriminative one-shot learning of gestures","author":"pfister","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7870775\/07458903.pdf?arnumber=7458903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:08:21Z","timestamp":1642003701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7458903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":75,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2558148","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":[[2017,4,1]]}}}