{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:16:13Z","timestamp":1771956973776,"version":"3.50.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2009,2,1]],"date-time":"2009-02-01T00:00:00Z","timestamp":1233446400000},"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. Multimedia"],"published-print":{"date-parts":[[2009,2]]},"DOI":"10.1109\/tmm.2008.2009681","type":"journal-article","created":{"date-parts":[[2009,1,20]],"date-time":"2009-01-20T21:04:18Z","timestamp":1232485458000},"page":"229-243","source":"Crossref","is-referenced-by-count":29,"title":["Using Visual Context and Region Semantics for High-Level Concept Detection"],"prefix":"10.1109","volume":"11","author":[{"given":"Phivos","family":"Mylonas","sequence":"first","affiliation":[]},{"given":"Evaggelos","family":"Spyrou","sequence":"additional","affiliation":[]},{"given":"Yannis","family":"Avrithis","sequence":"additional","affiliation":[]},{"given":"Stefanos","family":"Kollias","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2008.49"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-74161-1_42"},{"key":"ref71","article-title":"Fusing MPEG-7 visual descriptors for image classiffication","author":"spyrou","year":"2005","journal-title":"Proc Int Conf Artificial Neural Networks ICANN"},{"key":"ref70","article-title":"The COST292 experimental framework for TRECVID 2007","author":"spyrou","year":"2007","journal-title":"Proc 5th TRECVID Workshop"},{"key":"ref76","author":"torralba","year":"2004","journal-title":"Contextual Models for Object Detection Using Boosted Random Fields"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012375731-9\/50100-2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24750-0"},{"key":"ref39","article-title":"Natural object detection in outdoor scenes based on probabilistic spatial context models","author":"luo","year":"2002","journal-title":"Proc IEEE Int Conf Multimedia and Expo"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023052124951"},{"key":"ref38","article-title":"Indoor vs outdoor classification of consumer photographs using low-level and semantic features","author":"luo","year":"2001","journal-title":"Proc IEEE Int Conf Image Processing (ICIP'01)"},{"key":"ref78","article-title":"Knowledge-assisted video analysis and object detection","author":"tsechpenakis","year":"2002","journal-title":"Proc European Symp Intelligent Technologies Hybrid Systems and their Implementation on Smart Adaptive Systems (Eunite02)"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-6642-x"},{"key":"ref33","article-title":"Discriminative random fields: A discriminative framework for contextual interaction in classification","author":"kumar","year":"2003","journal-title":"Proc of ICCV"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.9"},{"key":"ref31","author":"klir","year":"1995","journal-title":"Fuzzy Sets and Fuzzy Logic Theory and Applications"},{"key":"ref30","article-title":"Simultaneous classification and visual word selection using entropy-based minimum description length","author":"kim","year":"2006","journal-title":"Proc 18th Int Conf Pattern Recognition (ICPR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609453"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/78.823977"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-9012-8_6"},{"key":"ref34","article-title":"A discriminative framework for texture and object recognition using local image features","author":"lazebnik","year":"2005","journal-title":"Proc Int Conf Computer Vision (ICCV)"},{"key":"ref60","article-title":"Image classifiers for scene analysis","author":"saux","year":"2004","journal-title":"Proc Int Conf on Computer Vision and Graphics"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211359"},{"key":"ref61","article-title":"TextonBoost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context","author":"shotton","year":"2006","journal-title":"Proc European Conf on Computer Vision"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1178677.1178722"},{"key":"ref28","first-page":"892","article-title":"Effective automatic image annotation via a coherent language model and active learning","author":"jin","year":"2004","journal-title":"Proc ACM Multimedia 2004"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"ref27","article-title":"Exploring semantic concept using local invariant features","author":"jiang","year":"2006","journal-title":"Asia-Pacific Workshop on Visual Information Processing"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886275"},{"key":"ref66","author":"snoek","year":"2006","journal-title":"Learned Lexicon-Driven Interactive Video Retrieval"},{"key":"ref29","first-page":"211","article-title":"Semantic feature extraction with multidimensional hidden Markov model","volume":"6073","author":"jiten","year":"2006","journal-title":"Proc SPIE CMCAMR 2006"},{"key":"ref67","article-title":"Region-based video content indexing and retrieval","author":"souvannavong","year":"2005","journal-title":"CBMI 2005 4th Int Workshop on Content-Based Multimedia Indexing"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:20045184"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77051-0_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1999.0761"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.890636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.916999"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383375"},{"key":"ref21","first-page":"544","article-title":"Hidden Markov models for automatic annotation and content-based retrieval of images and video","author":"ghoshal","year":"2003","journal-title":"Proc SIGIR 2003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"},{"key":"ref23","article-title":"Multiscale conditional random fields for image labeling","author":"he","year":"2004","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860459"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2008.02.011"},{"key":"ref50","article-title":"Improving image analysis using a contextual approach","author":"mylonas","year":"2006","journal-title":"Proc 8th Int Workshop Image Analy Multimedia Interactive Services (WIAMIS)"},{"key":"ref51","article-title":"Context modelling for multimedia analysis","author":"mylonas","year":"2005","journal-title":"Proc 5th Int Interdiscipl Conf Modeling Using Context (CONTEXT'05)"},{"key":"ref59","article-title":"On the use of spatiotemporal visual attention for video classification","author":"rapantzikos","year":"2005","journal-title":"Int Workshop on Very Low Bitrate Video Coding (VLBV99)"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.21.30"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.905482"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.153"},{"key":"ref55","first-page":"23","article-title":"Building the gist of a scene: The role of global image features in recognition","author":"oliva","year":"2005","journal-title":"Progr Brain Res Vis Percept"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24674-9_21"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SMAP.2007.38"},{"key":"ref52","article-title":"Enriching a context ontology with mid-level features for semantic multimedia analysis","author":"mylonas","year":"2007","journal-title":"Proc 1st Workshop on Multimedia Annotation and Retrieval enabled by Shared Ontologies"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521588"},{"key":"ref11","article-title":"Learning spatial configuration models using modified Dirichlet priors","author":"boutell","year":"2004","journal-title":"Proc Workshop on Statistical Relational Learning (in Conjunction With ICML)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587462"},{"key":"ref12","first-page":"350","article-title":"A statistical model for general contextual object recognition","author":"carbonetto","year":"2004","journal-title":"Proc ECCV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/76.927421"},{"key":"ref14","article-title":"Visual categorization with bags of keypoints","author":"dance","year":"2004","journal-title":"Proc ECCV Workshop Stat Learning Comput Vision"},{"key":"ref15","first-page":"97","article-title":"Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary","author":"duygulu","year":"2002","journal-title":"Proc ECCV"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/34.955109"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/3-540-48315-2_10","article-title":"The pragmatic roots of context","volume":"1688","author":"edmonds","year":"1999","journal-title":"Proc 2nd Int Interdisciplinary Conf Modelling and Using Context"},{"key":"ref81","article-title":"Knowledge-assisted video analysis using a genetic algorithm","author":"voisine","year":"2005","journal-title":"Proc 6th Int Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2005)"},{"key":"ref17","article-title":"Exchangeable image file format for digital still cameras: Exif Version 2.2","year":"2002","journal-title":"Japan Electronics and Information Technology Industries Association"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394372"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027660"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76386-4_17"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911775"},{"key":"ref80","article-title":"Detecting sky and vegetation in outdoor images","volume":"3972","author":"vailaya","year":"2000","journal-title":"Proc SPIE"},{"key":"ref89","year":"0","journal-title":"RDF Reification"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(82)90007-X"},{"key":"ref3","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref6","article-title":"Visual content extraction for automatic semantic annotation of video news","author":"boujemaa","year":"2004","journal-title":"IS&T\/SPIE Conf Storage & Retrieval Methods & Applications for Multimedia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1247319"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101245"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.009"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383229"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315222"},{"key":"ref49","article-title":"Using the forest to see the trees: a graphical model relating features, objects and scenes","author":"murphy","year":"2003","journal-title":"Adv Neural Inform Process Syst (NIPS)"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291379"},{"key":"ref88","year":"0","journal-title":"RDF"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-005-0202-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7887-5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1994.343710"},{"key":"ref48","year":"2001","journal-title":"MPEG-7 Visual Experimentation Model (xm)"},{"key":"ref47","article-title":"Temporal context representation and reasoning","author":"moldovan","year":"2005","journal-title":"Proc Int J Conf Artificial Intelligence (IJCAI)"},{"key":"ref42","year":"0","journal-title":"Marvel IBM Multimedia analysis and retrieval system"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/76.927424"},{"key":"ref44","first-page":"81","article-title":"Notes on formalizing context","author":"mccarthy","year":"1993","journal-title":"Proc of the 13th International Joint Conference on Artificial Intelligence (IJCAI 1993)"},{"key":"ref43","article-title":"Folksonomies—Cooperative classification and communication through shared metadata","author":"mathes","year":"2004","journal-title":"Computer Mediated Communication—LIS590CMC"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6046\/4757423\/04757439.pdf?arnumber=4757439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T23:59:48Z","timestamp":1633910388000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4757439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,2]]},"references-count":89,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2008.2009681","relation":{},"ISSN":["1520-9210"],"issn-type":[{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2009,2]]}}}