{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:05:35Z","timestamp":1771697135116,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01GM087694"],"award-info":[{"award-number":["R01GM087694"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["P30DA035778"],"award-info":[{"award-number":["P30DA035778"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Data to Decisions Cooperative Research Centre"},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1509206"],"award-info":[{"award-number":["U1509206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,8,1]]},"DOI":"10.1109\/tpami.2016.2608901","type":"journal-article","created":{"date-parts":[[2016,9,13]],"date-time":"2016-09-13T14:17:02Z","timestamp":1473776222000},"page":"1617-1632","source":"Crossref","is-referenced-by-count":293,"title":["Semantic Pooling for Complex Event Analysis in Untrimmed Videos"],"prefix":"10.1109","volume":"39","author":[{"given":"Xiaojun","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao-Liang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric P.","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","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":"ref72","first-page":"521","article-title":"Parallel support vector machines: The cascade SVM","author":"graf","year":"2004","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref71","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150429"},{"key":"ref39","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2362935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.335"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1145\/2671188.2749404","article-title":"Bag-of-fragments: Selecting and encoding video fragments for event detection and recounting","author":"mettes","year":"2015","journal-title":"Proc 5th ACM Int Conf Multimedia Retrieval"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.329"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_44"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"ref34","first-page":"397","article-title":"Local expert forest of score fusion for video event classification","author":"liu","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1198\/TECH.2010.10111"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339675"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.178"},{"key":"ref64","first-page":"570","article-title":"Characterizing the representer theorem","author":"yu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref65","first-page":"1313","article-title":"Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning","author":"rahimi","year":"2006","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1080\/00207728108963798"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref67","first-page":"91","article-title":"On decomposing the proximal map","author":"yu","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/996986501"},{"key":"ref69","first-page":"265","article-title":"On the algorithmic implementation of multiclass kernel-based vector machines","volume":"2","author":"crammer","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248114"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2264928"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.11.023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref23","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref26","first-page":"60.1","article-title":"Exploiting image-trained CNN architectures for unconstrained video classification","author":"zha","year":"2015","journal-title":"Proc 26th British Mach Vis Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806218"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.888023"},{"key":"ref59","author":"barlow","year":"1972","journal-title":"Statistical Inference Under Order Restrictions The Theory and Application of Isotonic Regression"},{"key":"ref58","article-title":"Videostory embeddings recognize events when examples are scarce","author":"habibian","year":"2015"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2499178.2499180"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref52","first-page":"1245","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","first-page":"366","article-title":"Segmenting salient objects from images and videos","author":"rahtu","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref11","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref40","article-title":"Action recognition using visual attention","author":"sharma","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref13","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref15","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0701-9"},{"key":"ref17","first-page":"1348","article-title":"Complex event detection using semantic saliency and nearly-isotonic SVM","author":"chang","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.265"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2021724"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.170"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2306419"},{"key":"ref6","article-title":"Informedia@TRECVID 2014 MED and MER","author":"yu","year":"2014","journal-title":"Trecvid"},{"key":"ref5","article-title":"The AXES submissions at TrecVid 2013","author":"aly","year":"2013","journal-title":"Trecvid"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.339"},{"key":"ref7","first-page":"688","article-title":"Scene aligned pooling for complex video recognition","author":"cao","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"ref9","first-page":"219","article-title":"Shifts in selective visual attention: Towards the underlying neural circuitry","volume":"4","author":"koch","year":"1985","journal-title":"Human Neurobiology"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6475038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2449660"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072411"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578757"},{"key":"ref42","first-page":"828","article-title":"Image labeling on a network: Using social-network metadata for image classification","author":"mcauley","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_31"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.151"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7963909\/07565615.pdf?arnumber=7565615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:35Z","timestamp":1641987635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7565615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,1]]},"references-count":75,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2608901","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":[[2017,8,1]]}}}