{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:37:07Z","timestamp":1773988627162,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298789","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T22:42:06Z","timestamp":1444948926000},"page":"1798-1807","source":"Crossref","is-referenced-by-count":281,"title":["A discriminative CNN video representation for event detection"],"prefix":"10.1109","author":[{"given":"Zhongwen","family":"Xu","sequence":"first","affiliation":[]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref32","article-title":"AXES at TRECVid 2012: KIS, INS, and MED","author":"oneata","year":"2012","journal-title":"TRECVID Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref30","article-title":"BBN VISER TRECVID 2013 Multimedia Event Detection and Multimedia Event Recounting Systems","author":"natarajan","year":"2013","journal-title":"TRECVID 2013 Workshop"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ar Xiv preprint arXiv 1409 1556"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref35","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"ECCV"},{"key":"ref34","article-title":"Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice","author":"peng","year":"2014","journal-title":"ar Xiv preprint arXiv 1405 4506"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.229"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref13","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"ECCV"},{"key":"ref14","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref18","article-title":"Caffe: An open source convolutional architecture for fast feature embedding","author":"jia","year":"2013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.332"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890234"},{"key":"ref4","author":"arandjelovic","year":"2013","journal-title":"CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.339"},{"key":"ref3","article-title":"The AXES submissions at TrecVid 2013","author":"aly","year":"2013"},{"key":"ref6","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"BMVC"},{"key":"ref29","article-title":"The 2013 SESAME Multimedia Event Detection and Recounting system","author":"myers","year":"2013","journal-title":"TRECVID 2013 Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.369"},{"key":"ref7","article-title":"Mosift: Recognizing human actions in surveillance videos","author":"chen","year":"2009","journal-title":"CMU TR"},{"key":"ref2","year":"0","journal-title":"TRECVID MED 14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref1","year":"0","journal-title":"TRECVID MED 13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.456"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.427"},{"key":"ref22","article-title":"CMU-Informedia at TRECVID 2013 Multimedia Event Detection","author":"lan","year":"2013","journal-title":"TRECVID 2013 Workshop"},{"key":"ref21","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref24","article-title":"Network in network","author":"lin","year":"2013","journal-title":"Corr abs\/1312 4400"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1109\/TPAMI.2009.154","article-title":"Evaluating color descriptors for object and scene recognition","volume":"32","author":"van","year":"2010","journal-title":"TPAMI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2306419"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298789.pdf?arnumber=7298789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T21:24:39Z","timestamp":1498253079000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298789","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}