{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T10:38:47Z","timestamp":1756463927647,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of the Hong Kong Special Administrative Region","award":["CityU 120213"],"award-info":[{"award-number":["CityU 120213"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/tmm.2018.2884478","type":"journal-article","created":{"date-parts":[[2018,12,3]],"date-time":"2018-12-03T23:59:12Z","timestamp":1543881552000},"page":"1450-1463","source":"Crossref","is-referenced-by-count":17,"title":["A Fine Granularity Object-Level Representation for Event Detection and Recounting"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1664-8739","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0781-x"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552981"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912015"},{"key":"ref32","article-title":"VIREO-TNO@ TRECVID 2014: Multimedia event detection and recounting (MED and MER)","author":"ngo","year":"0","journal-title":"Proc TREC Video Retrieval Eval"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2168948"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.60"},{"key":"ref37","article-title":"BUPT-MCPRL at TRECVID 2016","author":"zhao","year":"0","journal-title":"Proc TREC Video Retrieval Eval"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2359771"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578764"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref62","article-title":"TRECVID 2013: An overview of the goals, tasks, data evaluation mechanisms, and metrics","author":"over","year":"0","journal-title":"Proc TREC Video Retrieval Eval"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.125"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654913"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref29","first-page":"218","article-title":"Object pooling for multimedia event detection and evidence localization","volume":"4","author":"zhang","year":"2016","journal-title":"ITE Trans on Media Tech and App"},{"key":"ref67","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","article-title":"TRECVID 2012—An overview of the goals, tasks, data, evaluation mechanisms and metrics","author":"over","year":"0","journal-title":"Proc TREC Video Retrieval Eval"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.900150"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.1017733"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749402"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806221"},{"key":"ref24","first-page":"427","article-title":"Bag-of-fragments: Selecting and encoding video fragments for event detection and recounting","author":"mettes","year":"0","journal-title":"Proc 5th ACM Int Conf Multimedia Retrieval"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2449660"},{"key":"ref25","article-title":"Complex event detection using semantic saliency and nearly-isotonic SVM","author":"chang","year":"0","journal-title":"Proc 32th Int Conf Mach Learn"},{"key":"ref50","first-page":"4032","article-title":"Deck: Discovering event composition knowledge from web images for zero-shot event detection and recounting in videos","author":"gan","year":"0","journal-title":"Proc Conf Artif Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref57","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref54","first-page":"1164","article-title":"Deep convolutional matching","author":"revaud","year":"0","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2766959"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref10","first-page":"52","article-title":"TRECVID 2014–An overview of the goals, tasks, data, evaluation mechanisms and metrics","author":"over","year":"0","journal-title":"Proc TREC Video Retrieval Eval"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2671414"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2659221"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912036"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051360"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2315780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.227"},{"article-title":"Ucf101: A dataset of 101 human action classes from videos in the wild","year":"2012","author":"soomro","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.329"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6475038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-015-0090-3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578757"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2324796.2324799"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8720290\/08556097.pdf?arnumber=8556097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:57:18Z","timestamp":1657745838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8556097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":71,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2884478","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}