{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T15:30:27Z","timestamp":1726414227178},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2014,6,1]],"date-time":"2014-06-01T00:00:00Z","timestamp":1401580800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1007\/s11042-014-2044-9","type":"journal-article","created":{"date-parts":[[2014,5,31]],"date-time":"2014-05-31T05:27:00Z","timestamp":1401514020000},"page":"8105-8135","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Content-oriented multimedia document understanding through cross-media correlation"],"prefix":"10.1007","volume":"74","author":[{"given":"Tong","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Palaiahnakote","family":"Shivakumara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chew Lim","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,6,1]]},"reference":[{"issue":"4","key":"2044_CR1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/s10032-010-0128-2","volume":"13","author":"A AbdelRaouf","year":"2010","unstructured":"AbdelRaouf A, Higgins CA, Pridmore TP, Khalil M I (2010) Building a multi-modal arabic corpus. Int J Doc Anal Recognit 13 (4):285\u2013302","journal-title":"Int J Doc Anal Recognit"},{"key":"2044_CR2","first-page":"1107","volume":"3","author":"K Barnard","year":"2003","unstructured":"Barnard K, Duygulu P, Forsyth D, Freitas N, Blei DM, Jordan MI (2003) Matching words and pictures. J Mach Learn Res 3:1107\u20131135","journal-title":"J Mach Learn Res"},{"key":"2044_CR3","doi-asserted-by":"crossref","unstructured":"Beal MJ, Attias H, Jojic N (2002) Audio-video sensor fusion with probabilistic graphical models. In: ECCV, pp 736\u2013752","DOI":"10.1007\/3-540-47969-4_49"},{"issue":"8","key":"2044_CR4","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1109\/TPAMI.2002.1023800","volume":"24","author":"C Carson","year":"2002","unstructured":"Carson C, Belongie S, Greenspan H, Malik J (2002) Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Trans Pattern Anal Mach Intell 24 (8):1026\u20131038","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"2044_CR5","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1109\/TMM.2008.922784","volume":"10","author":"B Erol","year":"2008","unstructured":"Erol B, Berker K, Joshi S (2008) Multimedia clip generation from documents for browsing on mobile devices. IEEE Trans Multimed 10 (5):711\u2013723","journal-title":"IEEE Trans Multimed"},{"key":"2044_CR6","doi-asserted-by":"crossref","unstructured":"Evangelopoulos G, Zlatintsi A, Skoumas G, Rapantzikos K, Potamianos A, Maragos P, Avrithis Y (2009) Video event detection and summarization using audio, visual and text saliency. In: Conference on IEEE International, ICASSP, pp 3553\u20133556","DOI":"10.1109\/ICASSP.2009.4960393"},{"key":"2044_CR7","doi-asserted-by":"crossref","unstructured":"Foote J (1997) Content-based retrieval of music and audio. Multimedia storage and archiving systems II. In: Proceedings of SPIE, 3229, pp 138\u2013147","DOI":"10.1117\/12.290336"},{"issue":"3","key":"2044_CR8","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s10032-009-0089-5","volume":"12","author":"JY He","year":"2009","unstructured":"He JY, Weerkamp W, Larson M, Rijke M (2009) An effective coherence measure to determine topical consistency in user-generated content. Int J Doc Anal Recognit 12 (3):185\u2013203","journal-title":"Int J Doc Anal Recognit"},{"key":"2044_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10032-008-0061-9","volume":"11","author":"H Goto","year":"2008","unstructured":"Goto H (2008) Redefining the DCT-based feature for scene text detection. Int J Doc Anal Recognit 11:1\u20138","journal-title":"Int J Doc Anal Recognit"},{"issue":"4","key":"2044_CR10","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1109\/TMM.2007.893337","volume":"9","author":"M Kyperountas","year":"2007","unstructured":"Kyperountas M, Kotropoulos C, Pitas I (2007) Enhanced eigen-audioframes for audiovisual scene change detection. IEEE Trans Multimed 9 (4):785\u2013797","journal-title":"IEEE Trans Multimed"},{"issue":"2","key":"2044_CR11","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10032-009-0081-0","volume":"12","author":"XN Lu","year":"2009","unstructured":"Lu XN, Kataria Saurabh BWJ, Wang JZ, Mitra P, Giles CL (2009) Automated analysis of images in documents for intelligent document search. Int J Doc Anal Recognit 12 (2):65\u201381","journal-title":"Int J Doc Anal Recognit"},{"issue":"4","key":"2044_CR12","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TPAMI.2007.70724","volume":"30","author":"J Liang","year":"2008","unstructured":"Liang J, DeMenthon D, Doermann D (2008) Geometric rectification of camera-captured document images. IEEE Trans Pattern Anal Mach Intell 30 (4):591\u2013605","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2044_CR13","unstructured":"Li ZX, Shi ZP, Liu X, Shi ZZ (2010) Automatic image annotation with continous PLSA. In: ICASSP, pp 806\u2013809"},{"issue":"2","key":"2044_CR14","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60 (2):91\u2013110","journal-title":"Int J Comput Vis"},{"issue":"8","key":"2044_CR15","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1109\/TPAMI.2008.161","volume":"31","author":"T Lu","year":"2009","unstructured":"Lu T, Tai CL, Yang HF, Cai SJ (2009) A novel knowledge-based system for interpreting complex engineering drawings: theory, representation, and implementation. IEEE Trans Pattern Anal Mach Intell 31 (8):1444\u20131457","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2044_CR16","unstructured":"Lu MM, Xie L, Fu ZH, Jiang DM, Zhang YN (2010) Multimodal feature integration for story boundary detection in broadcast news. In: ISCSLP, pp 420\u2013425"},{"key":"2044_CR17","unstructured":"Mesaros A, Heittola T, Klapuri AP (2011) Latent semantic analysis in sound event detection. In: Proceedings of EUSIPCO, pp 1307\u20131311"},{"key":"2044_CR18","doi-asserted-by":"crossref","unstructured":"Monay F, Gatica-Perez D (2004) PLSA-based image auto-annotation: constrainting the latent space. In: ACM Multimedia\u201904, pp 348\u2013351","DOI":"10.1145\/1027527.1027608"},{"issue":"10","key":"2044_CR19","doi-asserted-by":"crossref","first-page":"1802","DOI":"10.1109\/TPAMI.2007.1097","volume":"29","author":"F Monay","year":"2007","unstructured":"Monay F, Daniel GP (2007) Modeling semantic aspects for cross-media image indexing. IEEE Trans Pattern Anal Mach Intell 29 (10):1802\u20131817","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1\u20132","key":"2044_CR20","first-page":"31","volume":"3","author":"A Mitschick","year":"2010","unstructured":"Mitschick A (2010) Ontology-based indexing and contextualization of multimedia documents for personal information management applications. Int J Adv Softw 3 (1\u20132):31\u201340","journal-title":"Int J Adv Softw"},{"issue":"8","key":"2044_CR21","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1109\/TPAMI.2008.161","volume":"31","author":"T Lu","year":"2009","unstructured":"Lu T, Tai CL, Yang HF, Cai SJ (2009) A novel knowledge-based system for interpreting complex engineering drawings: theory, representation, and implementation. IEEE Trans Pattern Anal Mach Intell 31(8):1444\u20131457","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2044_CR22","unstructured":"Nguyen N V, Ogier J M, Charneau F (2012) PEDIVHANDI: multimodal indexation and retrieval system for lecture videos. In: ACCV\u201912, pp 382\u2013393"},{"key":"2044_CR23","unstructured":"Iria J, Magalhae~s J (2009) Exploiting cross-media correlations in the categorization of multimedia web documents. In: IJCAI\u201909 workshop on cross-media information access and mining"},{"key":"2044_CR24","doi-asserted-by":"crossref","unstructured":"Karaoglu S, Gemert J, Gevers T (2012) Object reading: text recognition for object recognition. In: ECCV\u201912, pp 456\u2013465","DOI":"10.1007\/978-3-642-33885-4_46"},{"key":"2044_CR25","unstructured":"Ma X L, Lu T, Xu F M, Su F (2012) Anomaly detection with spatic-temporal context using depth images. In: Internatial conference on pattern recognition, pp 2590\u20132593"},{"key":"2044_CR26","doi-asserted-by":"crossref","unstructured":"Su F, Yang L, Lu T, Wang GY (2011) Environmental sound classification for scene recognition using local discriminant bases and HMM. In: ACM Multimedia\u201911, pp 1389\u20131392","DOI":"10.1145\/2072298.2072022"},{"key":"2044_CR27","doi-asserted-by":"crossref","unstructured":"Lin WX, Lu T, Su F (2012) A novel multi-modal integration and propagation model for cross-media information retrieval. In: Multimedia modeling\u201912, pp 740\u2013749","DOI":"10.1007\/978-3-642-27355-1_78"},{"key":"2044_CR28","doi-asserted-by":"crossref","unstructured":"Jin YK, Lu T, Su F (2012) Movie keyframe retrieval based on cross-media correlation detection and context model. In: IEA\/AIE\u201912, pp 816\u2013825","DOI":"10.1007\/978-3-642-31087-4_82"},{"key":"2044_CR29","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann T (2001) Unsupervised learning by probabilistic latent semantic analysis. Mach Learn 42:117\u2013196","journal-title":"Mach Learn"},{"key":"2044_CR30","unstructured":"Jourdan M, Bes F (2001) A new step towards multimedia documents generation. In: International conference on media futures, pp 25\u201328"},{"issue":"6","key":"2044_CR31","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s00530-008-0139-8","volume":"14","author":"A Scherp","year":"2008","unstructured":"Scherp A (2008) Canonical processes for creating personalized semantically with multimedia presentations. Multimedia Syst 14 (6):415\u2013425","journal-title":"Multimedia Syst"},{"key":"2044_CR32","doi-asserted-by":"crossref","unstructured":"Blei D M, Jordan MI (2003) Modeling annotated data. In: SIGIR, pp 127\u2013134","DOI":"10.1145\/860435.860460"},{"key":"2044_CR33","unstructured":"Sidhom S, David A (2006) Automatic indexing of multimedia documents as a starting point to annotation process. In: Conference on 9th international ISKO knowledge organization for a global learning society"},{"key":"2044_CR34","doi-asserted-by":"crossref","unstructured":"Staab S, Scherp A, Arndt R, Troncy R, Grzegorzek M, Saathoff C, Schenk S, Hardman L (2008) Semantic multimedia. In: Reasoning web. Springer, Venis","DOI":"10.1007\/978-3-540-85658-0_4"},{"key":"2044_CR35","doi-asserted-by":"crossref","unstructured":"Saathoff C, Scherp A (2010) Unlocking the semantics of multimedia presentations in the web with the multimedia metadata ontology. In: Proceedings of WWW\u201910, pp 831\u2013840","DOI":"10.1145\/1772690.1772775"},{"issue":"2","key":"2044_CR36","first-page":"64","volume":"17","author":"J Peng","year":"2010","unstructured":"Peng J, Qin XL (2010) Keyframe-based video summary using visual attention clues. IEEE Trans Multimed 17 (2):64\u201373","journal-title":"IEEE Trans Multimed"},{"key":"2044_CR37","doi-asserted-by":"crossref","unstructured":"Poignant J, Besacier L, Quenot G, Thollard F (2012) From text detection in videos to person identification. In: ICME, pp 854\u2013859","DOI":"10.1109\/ICME.2012.119"},{"key":"2044_CR38","doi-asserted-by":"crossref","unstructured":"Snoek CGM, Worring M, Smeulders AWM (2005) Early versus late fuion in semantic video analysis. In: ACM Multimedia\u201905, pp 399\u2013402","DOI":"10.1145\/1101149.1101236"},{"key":"2044_CR39","doi-asserted-by":"crossref","unstructured":"Wang JD, Zeng HJ, Chen Z, Lu HJ, Tao L, Ma WY (2003) ReCoM: reinforcement clustering of multi-type interrelated data objects. In: SIGIR, pp 274\u2013281","DOI":"10.1145\/860435.860486"},{"key":"2044_CR40","doi-asserted-by":"crossref","unstructured":"Wang XJ, Ma WY, Xue GR, Li X (2004) Multi-model similarity propagation and its application for web image retrieval. In: ACM Multimedia\u201904, pp 944\u2013951","DOI":"10.1145\/1027527.1027746"},{"issue":"3","key":"2044_CR41","first-page":"1520","volume":"9","author":"JJ Wang","year":"2007","unstructured":"Wang JJ, Chng ES, Xu CS, Lu HQ, Tian Q (2007) Generation of personalized music sports video using multimodal cues. IEEE Trans Multimed 9 (3):1520\u20139210","journal-title":"IEEE Trans Multimed"},{"key":"2044_CR42","doi-asserted-by":"crossref","unstructured":"Wang LM, Wu YR, Lu T, Chen K (2011) Multiclass object detection by combining local appearances and context. In: ACM Multimedia\u201911, pp 1161\u20131164","DOI":"10.1145\/2072298.2071964"},{"key":"2044_CR43","doi-asserted-by":"crossref","unstructured":"Weiss W, Burger T, Villa Robert PP, Halb W (2009) Statement-based semantic annotation of media resources. In: Proceedings of SAMT, pp 52\u201364","DOI":"10.1007\/978-3-642-10543-2_7"},{"key":"2044_CR44","doi-asserted-by":"crossref","unstructured":"Westerveld T, et al (2003) A probabilisitc multimedia retrieval model and its evaluation. EURASIP J Appl Signal Process: 186\u2013198","DOI":"10.1155\/S111086570321101X"},{"key":"2044_CR45","doi-asserted-by":"crossref","unstructured":"Yamamoto M, Hikino K, Kijima S, Hirakawa M (2005) Towards understanding of multimedia documents: a trial of picture book analysis and generation. In: IEEE international symposium on multimedia, pp 29\u201336","DOI":"10.1109\/ISM.2005.116"},{"key":"2044_CR46","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1109\/TMM.2008.917359","volume":"10","author":"Y Yang","year":"2008","unstructured":"Yang Y, Zhuang YT, Wu F, Pan YH (2008) Harmonizing hierarchical manifolds for multimedia document semantics understanding and cross-media retrieval. IEEE Trans Multimed 10:437\u2013446","journal-title":"IEEE Trans Multimed"},{"issue":"8","key":"2044_CR47","doi-asserted-by":"crossref","first-page":"2927","DOI":"10.1016\/j.patcog.2010.02.015","volume":"43","author":"Y Yang","year":"2010","unstructured":"Yang Y, Wu F, Xu D, Zhuang YT, Chia LT (2010) Cross-media retrieval using query dependent search methods. Pattern Recognit 43 (8):2927\u20132936","journal-title":"Pattern Recognit"},{"key":"2044_CR48","doi-asserted-by":"crossref","unstructured":"Yin WC, Lu T, Su F (2013) A novel multi-view object class detection framework for document image content analysis. In: Conference on international document analysis, , Washington, US, pp 1095\u20131099","DOI":"10.1109\/ICDAR.2013.222"},{"key":"2044_CR49","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhuang Y T, Wu F (2007) Cross-modal correlation learning for clustering on image-audio dataset. In: ACM Multimedia\u201907, pp 273\u2013276","DOI":"10.1145\/1291233.1291290"},{"key":"2044_CR50","doi-asserted-by":"crossref","unstructured":"Zhu Y, Chen K, Sun Q (2005) Multimodal content-based structure analysis of Karaoke music. In: ACM Multimedia\u201905, pp 638\u2013647","DOI":"10.1145\/1101149.1101293"},{"key":"2044_CR51","doi-asserted-by":"crossref","unstructured":"Zhu Q, Yeh MC, Cheng K (2006) Multimodal fusion using learned text concepts for image categorization. In: ACM Multimedia\u201906, pp 211\u2013220","DOI":"10.1145\/1180639.1180698"},{"key":"2044_CR52","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TMM.2007.911822","volume":"10","author":"YT Zhuang","year":"2008","unstructured":"Zhuang YT, Yang Y, Wu F (2008) Mining semantic correlation of heterogeneous multimedia data for cross-media retrieval. IEEE Trans Multimed 10:221\u2013229","journal-title":"IEEE Trans Multimed"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2044-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-2044-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2044-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,11]],"date-time":"2019-08-11T05:00:55Z","timestamp":1565499655000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-2044-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,1]]},"references-count":52,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2015,9]]}},"alternative-id":["2044"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-2044-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2014,6,1]]}}}