{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:41:15Z","timestamp":1783183275269,"version":"3.54.6"},"reference-count":279,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2011,11,1]],"date-time":"2011-11-01T00:00:00Z","timestamp":1320105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst., Man, Cybern. C"],"published-print":{"date-parts":[[2011,11]]},"DOI":"10.1109\/tsmcc.2011.2109710","type":"journal-article","created":{"date-parts":[[2011,3,15]],"date-time":"2011-03-15T15:04:05Z","timestamp":1300201445000},"page":"797-819","source":"Crossref","is-referenced-by-count":406,"title":["A Survey on Visual Content-Based Video Indexing and Retrieval"],"prefix":"10.1109","volume":"41","author":[{"family":"Weiming Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Nianhua Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Li Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Xianglin Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Maybank","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463576"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463565"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463569"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463568"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70801"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906586"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463578"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2007.4412909"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463564"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.854477"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2006.1649689"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2008.4560124"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2005.1405707"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/1290031.1290035"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.897466"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/1290031.1290047"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2008.7"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/SUTC.2008.88"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ISECS.2008.118"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/957052.957087"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1109\/TMM.2007.900143","article-title":"Incorporating concept ontology to boost hierarchical classifier training for automatic multi-level annotation","volume":"9","author":"fan","year":"2007","journal-title":"IEEE Trans Multimedia"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/11788034_3","article-title":"Mining novice user activity with TRECVID interactive retrieval tasks","author":"christel","year":"2006","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367294"},{"key":"ref267","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/11957959_7","author":"sivic","year":"2006","journal-title":"Toward Category-Level Object Recognition"},{"key":"ref37","first-page":"237","article-title":"Content-based video retrieval based on object motion trajectory","author":"lie","year":"2002","journal-title":"Proc IEEE Workshop Multimedia Signal Process"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101342"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.891352"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291295"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IVL.2000.853838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2005.1530615"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621451"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.856896"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.819783"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.876282"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621445"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-005-0129-9"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-006-0001-1"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262715"},{"key":"ref187","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/11815921_24","author":"geng","year":"2006","journal-title":"Lecture Notes in Computer Science vol 4109"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035560"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1007\/11788034_37","article-title":"Video mining with frequent item set configurations","author":"quack","year":"2006","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.869965"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/1290031.1290032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916338"},{"key":"ref20","first-page":"245","article-title":"Video indexing and retrieval based on recognized text","author":"li","year":"2002","journal-title":"Proc IEEE Workshop Multimedia Signal Process"},{"key":"ref22","first-page":"454","article-title":"Video retrieval using video object-trajectory and edge potential function","author":"dao","year":"2004","journal-title":"Proc Int Symp Intell Multimedia Video Speech Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262911"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-35592-4_25"},{"key":"ref23","year":"0"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.08.033"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.902875"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2012919"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/6979.954548"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1199092"},{"key":"ref51","first-page":"49","article-title":"An integrated approach to video retrieval","volume":"75","author":"chen","year":"2007","journal-title":"Proc Australasian Database Conf"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027601"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394400"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2005.1405707"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180729"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/973264.973297"},{"key":"ref152","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/11526346_13","article-title":"Story segmentation in news using visual and text cues","author":"zhai","year":"2005","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.01.005"},{"key":"ref146","first-page":"657","article-title":"Semi-supervised cross feature learning for semantic concept detection in videos","volume":"1","author":"yan","year":"2005","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref147","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/ICME.2000.871563","article-title":"Video scene segmentation using video and audio features","author":"sundaram","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284704"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284701"},{"key":"ref59","first-page":"465","article-title":"Content-based video similarity model","author":"wu","year":"2000","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MUE.2008.102"},{"key":"ref57","first-page":"1779","article-title":"Shot boundary detection using spectral clustering","author":"damnjanovic","year":"2007","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/11558484_33"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/EURCON.2005.1629878"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1117\/12.629654"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1290067.1290075"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/967900.968120"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2008.04.012"},{"key":"ref167","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1145\/1282280.1282308","article-title":"Semi-supervised learning for semantic video retrieval","author":"ewerth","year":"2007","journal-title":"Proceedings of International Conference on Image Video Retrieval"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2004.04.005"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.812758"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.854230"},{"key":"ref163","year":"0"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.890857"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/60245"},{"key":"ref160","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/TCSVT.2004.841694","article-title":"Video summarization and scene detection by graph modeling","volume":"15","author":"ngo","year":"2005","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2006045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2009.2023380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1101826.1101844"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.2007257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315274"},{"key":"ref159","first-page":"160","article-title":"Summarizing audio–visual contents of a video program","volume":"2003","author":"gong","year":"2003","journal-title":"EURASIP J Appl Signal Process Special Issue Unstructured Inform Manag Multimedia Data Sources"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1178677.1178716"},{"key":"ref49","first-page":"278","article-title":"An interface for image retrieval and its extension to video retrieval","author":"thi","year":"2006","journal-title":"Proc Nat Symp Res Develop Appl Inform Commun Technol"},{"key":"ref157","first-page":"638","article-title":"Automatic mobile sports highlights","author":"wan","year":"2005","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262673"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2008.601"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854410"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886357"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.864272"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11949619_35"},{"key":"ref42","first-page":"598","article-title":"SPSA-based feature relevance estimation for video retrieval","author":"sudha","year":"2008","journal-title":"Proc IEEE Workshop Multimedia Signal Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957072"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775067"},{"key":"ref73","first-page":"188","article-title":"Multi-label machine learning and its application to semantic scene classification","author":"shen","year":"2004","journal-title":"Proc Int Symp Electron Imag"},{"key":"ref72","article-title":"JDL at TRECVID 2006 shot boundary detection","author":"liu","year":"2006","journal-title":"Proc TREC Video Retrieval Eval Workshop"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101256"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326724"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2006.63"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2008.122"},{"key":"ref74","first-page":"1205","article-title":"Co-training non-robust classifiers for video semantic concept detection","author":"yan","year":"2005","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840618"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-006-0048-9"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.900143"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1117\/1.2199878"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2007.385430"},{"key":"ref61","article-title":"BUPT at TRECVID 2007: Shot boundary detection","author":"zhao","year":"2007","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref63","year":"0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/S0920-5489(01)00085-X"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/76.988656"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2006.09.001"},{"key":"ref67","first-page":"259","article-title":"Content-based video retrieval system using wavelet transform","volume":"6","author":"chung","year":"2007","journal-title":"World Sci Eng Acad Soc Trans Circuits Syst"},{"key":"ref68","first-page":"3047","article-title":"Video shot boundary detection using petri-net","author":"bai","year":"2008","journal-title":"Proc Int Conf Mach Learning Cybern"},{"key":"ref69","first-page":"660","article-title":"On the detection of semantic concepts at TRECVID","author":"naphade","year":"2004","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref197","first-page":"657","article-title":"Object-based video abstraction using cluster analysis","volume":"2","author":"kim","year":"2001","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148228"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009630817712"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.895353"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.848347"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.877419"},{"key":"ref196","article-title":"Spatial analysis in key-frame extraction using video segmentation","author":"calic","year":"2004","journal-title":"Proc Workshop Image Anal Multimedia Interactive Services"},{"key":"ref95","first-page":"255","article-title":"Improving web-based learning: Automatic annotation of multimedia semantics and cross-media indexing","author":"zhuang","year":"2004","journal-title":"Proc Adv Web-Based Learning ICWL (Lect Notes Comput Sci ) 3143"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.856903"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906602"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.212"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888015"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1108\/03684920510595490"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101242"},{"key":"ref91","first-page":"1373","article-title":"Video classification based on HMM using text and faces","author":"dimitrova","year":"2000","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref90","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/ICPR.2000.902901","article-title":"Automatic genre identification for content-based video categorization","volume":"4","author":"truong","year":"2000","journal-title":"Proc IEEE Int Conf Pattern Recog"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.819583"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886275"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/11526346_29"},{"key":"ref97","first-page":"114","article-title":"Video annotation by active learning and cluster tuning","author":"qi","year":"2006","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog Workshop"},{"key":"ref82","first-page":"651","article-title":"A video shot boundary detection algorithm based on feature tracking","author":"gao","year":"2006","journal-title":"Proc Int Conf Rough Sets Knowl Technol (Lect Notes Comput Sci ) 4062"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005801"},{"key":"ref84","article-title":"Shot boundary detection at TRECVID 2006","author":"chavez","year":"2006","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/860743"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/TCSVT.2007.890633","article-title":"Personalized content retrieval in context using ontological knowledge","volume":"17","author":"vallet","year":"2007","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/217279.215295"},{"key":"ref85","first-page":"617","article-title":"Shot boundary detection algorithm in compressed domain based on adaboost and fuzzy theory","author":"zhao","year":"2006","journal-title":"Proc Int Conf Nat Comput"},{"key":"ref86","first-page":"-488i","article-title":"Video data mining using configurations of viewpoint invariant regions","volume":"1","author":"sivic","year":"2004","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref87","article-title":"Chinese university of Hong Kong at TRECVID 2006: Shot boundary detection and video search","author":"hoi","year":"2006","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.873781"},{"key":"ref200","first-page":"117","article-title":"Multilevel video representation with application to keyframe extraction","author":"yu","year":"2004","journal-title":"Proc Int Multimedia Modelling Conf"},{"key":"ref101","first-page":"1","article-title":"The perseus project: Creating personalized multimedia news portal","author":"kules","year":"2001","journal-title":"Proc 2nd Int Workshop Multimedia Data Mining"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.83"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00109-4"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.816521"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.811617"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1048427"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/MUE.2007.65"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/ICIG.2007.11"},{"key":"ref208","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/978-3-540-27814-6_50","article-title":"A geometrical key-frame selection method exploiting dominant motion estimation in video","author":"fauvet","year":"2004","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/IIH-MSP.2008.245"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292250"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038180"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(02)00391-4"},{"key":"ref212","first-page":"571","article-title":"Key frame extraction using inter-shot information","author":"rong","year":"2004","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521470"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/76.809161"},{"key":"ref215","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/ICIAP.2003.1234093","article-title":"A shortest path representation for video summarization","author":"porter","year":"2003","journal-title":"Proc Int Conf Image Anal Process"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1016\/S0923-5965(02)00089-9"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.05.020"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/ITCC.2002.1000355"},{"key":"ref219","article-title":"Tsinghua University at TRECVID 2005","author":"yuan","year":"2005","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref220","first-page":"1","article-title":"Scalable temporal interest points for abstraction and classification of video events","author":"han","year":"2005","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref222","article-title":"IBM research TRECVID-2003 video retrieval system","author":"amir","year":"2003","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref221","first-page":"370","article-title":"Video retrieval using high level features: Exploiting query matching and confidence-based weighting","author":"neo","year":"2006","journal-title":"Proceedings of International Conference on Image Video Retrieval"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-007-9031-y"},{"key":"ref228","article-title":"Confounded expectations: Informedia at TRECVID 2004","author":"hauptmann","year":"2004","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262951"},{"key":"ref226","article-title":"FXPAL experiments for TRECVID 2004","author":"adcock","year":"2004","journal-title":"Proc TREC Video Retrieval Eval Gaithersburg"},{"key":"ref225","article-title":"TRECVID 2004 experiments in Dublin city university","author":"cooke","year":"2004","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref224","article-title":"TRECVID 2005 experiments at Dublin city university","author":"foley","year":"2005","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref223","article-title":"Informedia at TRECVID 2003: Analyzing and searching broadcast news video","author":"hauptmann","year":"2003","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4285119"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.278"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref129","first-page":"614","article-title":"Traffic jam detection based on corner feature of background scene in video-based ITS","author":"xie","year":"2008","journal-title":"Proc IEEE Int Conf Netw Sens Control"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2004.1421719"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IATW.2006.55"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211489"},{"key":"ref134","first-page":"262","article-title":"Video shot grouping using best first model merging","author":"zhao","year":"2001","journal-title":"Proc SPIE Storage and Retrieval for Media Database"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-006-7715-8"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.876299"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911830"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2002.999674"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916362"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911826"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1145\/1290082.1290119"},{"key":"ref238","first-page":"544","article-title":"Motion trajectory matching of video objects","author":"chen","year":"2000","journal-title":"Proc SPIE 3972 Storage and Retrieval for Media Databases"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/69.404033"},{"key":"ref234","first-page":"548","article-title":"Motion texture: A new motion based video representation","volume":"2","author":"ma","year":"2002","journal-title":"Proc Int Conf Pattern Recog"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886346"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/76.718507"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858392"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291431"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.830810"},{"key":"ref137","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/ICIP.2002.1038099","article-title":"Model-based clustering and analysis of video scenes","volume":"1","author":"tan","year":"2002","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2007.07.024"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/76.767124"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180855"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/s005300050138"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180768"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408894"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020341931699"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383170"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2002.808084"},{"key":"ref241","first-page":"421-430","article-title":"The challenge problem for automated detection of 101 semantic concepts in multimedia","author":"snoek","year":"2006","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.900156"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.900150"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291245"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.313037"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394372"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/76.825867"},{"key":"ref246","first-page":"928","article-title":"Algorithms and system for segmentation and structure analysis in soccer video","author":"xu","year":"2001","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.919173"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221649"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1117\/12.410939"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941230"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/357744.357941"},{"key":"ref106","first-page":"348","article-title":"Recent trends in video analysis: A taxonomy of video classification problems","author":"roach","year":"2002","journal-title":"Proc Int Assoc Sci Technol Develop Int Conf Internet Multimedia Syst Appl"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.61"},{"key":"ref104","first-page":"18","article-title":"Multimedia data mining framework for raw video sequences","author":"oh","year":"2002","journal-title":"Proc of The 5th International Workshop on Multimedia Data Mining"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27814-6_17"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/584792.584859"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038097"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2004.1269600"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4379(02)00018-2"},{"key":"ref250","first-page":"2917","article-title":"Active concept-based concept fusion with partial user labels","author":"jiang","year":"2006","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101235"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916384"},{"key":"ref255","first-page":"1","article-title":"Utilizing semantic word similarity measures for video retrieval","author":"aytar","year":"2008","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916355"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.827232"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367292"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1023\/B:MTAP.0000046380.27575.a5"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101339"},{"key":"ref10","first-page":"84","article-title":"A Framework for sub-window shot detection","author":"yeo","year":"2005","journal-title":"Proc Int Multimedia Modelling Conf"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027661"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP.2007.4381187"},{"key":"ref12","first-page":"932","article-title":"Shot boundary detection using unsupervised clustering and hypothesis testing","volume":"2","author":"lu","year":"2004","journal-title":"Proc Int Conf Commun Circuits Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/34.868681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.852623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.888023"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2006.258594"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1007\/3-540-45479-9_28","article-title":"Object recognition for video retrieval","author":"visser","year":"2002","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917346"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/11526346_26","article-title":"Person spotting: Video shot retrieval for face sets","author":"sivic","year":"2005","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11788034_40"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.825530"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941253"},{"key":"ref113","article-title":"University of Sheffield at TRECVID 2007: Shot boundary detection and rushes summarisation","author":"chantamunee","year":"2007","journal-title":"Proc TREC Video Retrieval Evaluation"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858395"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957018"},{"key":"ref120","first-page":"322","article-title":"3D model-assisted face recognition in video","author":"park","year":"2005","journal-title":"Proc Workshop Face Process Video"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.679697"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ISIMP.2001.925353"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.839993"},{"key":"ref260","year":"0"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1117\/6.0000005"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1561\/1500000014"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.011"},{"key":"ref264","year":"0"},{"key":"ref265","year":"0"},{"key":"ref266","year":"0"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5326\/5976948\/05729374.pdf?arnumber=5729374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,20]],"date-time":"2021-11-20T09:34:02Z","timestamp":1637400842000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5729374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,11]]},"references-count":279,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsmcc.2011.2109710","relation":{},"ISSN":["1094-6977","1558-2442"],"issn-type":[{"value":"1094-6977","type":"print"},{"value":"1558-2442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,11]]}}}