{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:30:02Z","timestamp":1780356602071,"version":"3.54.1"},"reference-count":116,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/tmm.2018.2844101","type":"journal-article","created":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T19:09:00Z","timestamp":1528830540000},"page":"157-172","source":"Crossref","is-referenced-by-count":18,"title":["Hierarchical Concept Score Postprocessing and Concept-Wise Normalization in CNN-Based Video Event Recognition"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5674-5931","authenticated-orcid":false,"given":"Mohammad","family":"Soltanian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9556-8090","authenticated-orcid":false,"given":"Shahrokh","family":"Ghaemmaghami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","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 Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IranianCEE.2017.7985290"},{"key":"ref33","article-title":"The LEAR submission at Thumos 2014","author":"oneata","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.05.021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref37","first-page":"227","article-title":"Strategies for searching video content with text queries or video examples","volume":"4","author":"yu","year":"2016","journal-title":"ITE Trans on Media Tech and App"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.508"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref34","first-page":"60.1","article-title":"Exploiting image-trained CNN architectures for unconstrained video classification","author":"zha","year":"2015","journal-title":"Proc British Mach Vis Conf"},{"key":"ref28","first-page":"1547","article-title":"Bag of sub-graphs for video event recognition","author":"aoun","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.339"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2058795"},{"key":"ref22","article-title":"Encoding feature maps of CNNS for action recognition","author":"peng","year":"0","journal-title":"Proc"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052025"},{"key":"ref24","article-title":"The AXES submissions at TrecVid 2013","author":"aly","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.427"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref100","article-title":"Contribute to word2vec_MATLAN development by creating an account on GitHub","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref50","article-title":"Non-local neural networks","author":"wang","year":"2018","journal-title":"IEEE Conf Comput Vis Pattern Recog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2559947"},{"key":"ref57","first-page":"2234","article-title":"Semantic concept discovery for large-scale zero-shot event detection","author":"chang","year":"0","journal-title":"Proc 24th Int Conf Artif Intell"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2264928"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2449660"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2359771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.154"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref8","article-title":"MoSIFT: Recognizing human actions in surveillance videos","author":"chen","year":"2009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref46","article-title":"Attention clusters: Purely attention based local feature integration for video classification","author":"long","year":"2018","journal-title":"IEEE Conf Comput Vis Pattern Recog"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539963"},{"key":"ref72","article-title":"Improving human activity recognition through ranking and re-ranking","author":"lan","year":"2015","journal-title":"arXiv 1512 03740"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2608901"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2691549"},{"key":"ref76","article-title":"About WordNet","year":"2010"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025204"},{"key":"ref75","volume":"1","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911826"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191943"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2616308"},{"key":"ref62","article-title":"Cmu-informedia at trecvid 2013 multimedia event detection","volume":"1","author":"lan","year":"0","journal-title":"Proc of the TRECVID 2013 Workshop"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2574712"},{"key":"ref63","first-page":"111","article-title":"A theoretical analysis of feature pooling in visual recognition","author":"boureau","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref64","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume":"1","author":"csurka","year":"0","journal-title":"Proc Workshop Statistical Learning in Computer Vision"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2545667"},{"key":"ref66","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191395"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.05.005"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2585023"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref109","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TPAMI.2013.128","article-title":"Learning multimodal latent attributes","volume":"36","author":"fu","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref95","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"ICLR Workshop"},{"key":"ref108","first-page":"2580","article-title":"Relevance topic model for unstructured social group activity recognition","author":"zhao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref94","article-title":"WordNet | A lexical database for English","year":"0"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.002"},{"key":"ref92","article-title":"Matlab VideoUtils","year":"2015"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref103","first-page":"3021","article-title":"Robust late fusion with rank minimization","author":"ye","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0723-7"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref110","first-page":"744","article-title":"Multi-region two-stream R-CNN for action detection","author":"peng","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref99","article-title":"An empirical study of semantic similarity in WordNet and Word2vec","author":"handler","year":"2014"},{"key":"ref96","article-title":"word2vec explained: Deriving mikolov, et al.'s negative-sampling word-embedding method","author":"goldberg","year":"2014","journal-title":"arXiv 1402 3722"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911832"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1109\/TMM.2008.917346","article-title":"A novel framework for semantic annotation and personalized retrieval of sports video","volume":"10","author":"xu","year":"2008","journal-title":"IEEE Trans Multimedia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2510329"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2004912"},{"key":"ref82","article-title":"ImageNet API documentation","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2009703"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2321530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025610"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2398195"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502171"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"ref113","first-page":"58.1","article-title":"Deep learning for detecting multiple space-time action tubes in videos","author":"saha","year":"2016","journal-title":"Proc British Mach Vis Conf"},{"key":"ref116","article-title":"UC merced submission to the ActivityNet challenge 2016","author":"zhu","year":"2017","journal-title":"arXiv 1704 03503"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2009693"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912036"},{"key":"ref89","article-title":"Pretrained CNNs–MatConvNet","year":"0"},{"key":"ref85","first-page":"530","article-title":"Attribute learning for understanding unstructured social activity","author":"fu","year":"0","journal-title":"Proc Computer Vision–ECCV"},{"key":"ref86","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"CRCV-TR-12-01"},{"key":"ref87","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8584144\/08382309.pdf?arnumber=8382309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:59:30Z","timestamp":1657745970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8382309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":116,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2844101","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}