{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T19:55:20Z","timestamp":1760385320280},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2013,10,25]],"date-time":"2013-10-25T00:00:00Z","timestamp":1382659200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1007\/s11042-013-1737-9","type":"journal-article","created":{"date-parts":[[2013,10,24]],"date-time":"2013-10-24T02:49:08Z","timestamp":1382582948000},"page":"2009-2032","source":"Crossref","is-referenced-by-count":8,"title":["Improving cross-modal and multi-modal retrieval combining content and semantics similarities with probabilistic model"],"prefix":"10.1007","volume":"74","author":[{"given":"Shixun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansheng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,10,25]]},"reference":[{"issue":"6","key":"1737_CR1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey PK, Hossain MA, EI Saddik A, Kankanhalli MS (2010) Multimodal fusion for multimedia analysis: a survey. Multime\u2019d Syst 16(6):345\u2013379","journal-title":"Multime\u2019d Syst"},{"key":"1737_CR2","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei D, Ng A, Jordan M (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"issue":"1","key":"1737_CR3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"issue":"3","key":"1737_CR4","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TPAMI.2007.61","volume":"29","author":"G Carneiro","year":"2007","unstructured":"Carneiro G, Chan A, Moreno P, Vasconcelos N (2007) Supervised learning of semantic classes for image annotation and retrieval. IEEE Trans Pattern Anal Mach Intell 29(3):394\u2013410","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1737_CR5","doi-asserted-by":"crossref","unstructured":"Clinchant S, Ah-Pine J, Csurka G (2011) Semantic combination of textual and visual information in multimedia retrieval. ACM Int Conf Multimed Retr","DOI":"10.1145\/1991996.1992040"},{"key":"1737_CR6","doi-asserted-by":"crossref","unstructured":"Coviello E, Mumtaz A, Chan A, Lanckriet G (2012) Growing a bag of systems tree for fast and accurate classification. IEEE Int Conf Comput Vis Pattern Recognit (CVPR)","DOI":"10.1109\/CVPR.2012.6247900"},{"key":"1737_CR7","first-page":"22","volume":"1","author":"G Csurka","year":"2004","unstructured":"Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. Workshop Stat Learn Comput Vis ECCV 1:22, Citeseer","journal-title":"Workshop Stat Learn Comput Vis ECCV"},{"issue":"3","key":"1737_CR8","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/PROC.1973.9030","volume":"61","author":"G Forney","year":"1973","unstructured":"Forney G (1973) The Viterbi algorithm. Proc IEEE 61(3):268\u2013278","journal-title":"Proc IEEE"},{"key":"1737_CR9","doi-asserted-by":"crossref","unstructured":"Haubold A, Natsev A, Naphade MR (2006) Semantic multimedia retrieval using lexical query expansion and model-based reranking. IEEE Int Conf Multimed Expo (ICME)","DOI":"10.1109\/ICME.2006.262892"},{"key":"1737_CR10","doi-asserted-by":"crossref","unstructured":"Hofmann T (1999) Probabilistic latent semantic indexing. In: Proceedings of the 22th Annual International SIGIR Conference","DOI":"10.1145\/312624.312649"},{"issue":"3\u20134","key":"1737_CR11","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1093\/biomet\/28.3-4.321","volume":"28","author":"H Hotelling","year":"1936","unstructured":"Hotelling H (1936) Relations between two sets of variates. Biometrika 28(3\u20134):321\u2013337","journal-title":"Biometrika"},{"key":"1737_CR12","unstructured":"Jia Y, Salzmann M, Darrell T (2011) Learning Cross-modality Similarity for Multinomial Data. IEEE Int Conf Comput Vis (ICCV)"},{"key":"1737_CR13","unstructured":"Jolliffe IT (2002) Principal component analysis. Springer"},{"key":"1737_CR14","doi-asserted-by":"crossref","unstructured":"Li D, Dimitrova N, Li M, Sethi IK (2003) Multimedia content processing through cross-modal association. Proc ACM Int Conf Multimed","DOI":"10.1145\/957013.957143"},{"key":"1737_CR15","doi-asserted-by":"crossref","unstructured":"Lmura J, Fujisawa T, Harada T, Kuniyoshi Y (2011) Efficient multi-modal retrieval in conceptual space. ACM Int Conf Multimed","DOI":"10.1145\/2072298.2071944"},{"key":"1737_CR16","doi-asserted-by":"crossref","unstructured":"Logan B, Salomon A (2001) A music similarity function based on signal analysis. IEEE Int Conf Multimed Expo (ICME)","DOI":"10.1109\/ICME.2001.1237829"},{"issue":"2","key":"1737_CR17","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"1737_CR18","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Ranghavan P, Sch\u00fctze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge"},{"key":"1737_CR19","doi-asserted-by":"crossref","unstructured":"Miotto R, Orio N (2012) A Probabilistic Model to Combine Tags and Acoustic Similarity for Music Retrieval. ACM Trans Inf Syst 30: No. 2, Article 8","DOI":"10.1145\/2180868.2180870"},{"issue":"2","key":"1737_CR20","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner L (1989) A tutorial on hidden Markov models and selected application in speech recognition. Proc IEEE 77(2):257\u2013286","journal-title":"Proc IEEE"},{"issue":"5","key":"1737_CR21","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/TMM.2007.900138","volume":"9","author":"N Rasiwasia","year":"2007","unstructured":"Rasiwasia N, Moreno P, Vasconcelos N (2007) Bridging the gap: query by semantic example. IEEE Trans Multime\u2019d 9(5):923\u2013938","journal-title":"IEEE Trans Multime\u2019d"},{"key":"1737_CR22","doi-asserted-by":"crossref","unstructured":"Rasiwasia N, Pereira JC, Coviello E, Doyle G, Lanckriet G, Levy R, Vasconcelos N (2010) A new approach to cross-modal multimedia retrieval. Proc ACM Int Conf Multimed","DOI":"10.1145\/1873951.1873987"},{"issue":"12","key":"1737_CR23","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"AWM Smeulders","year":"2000","unstructured":"Smeulders AWM, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349\u20131380","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1737_CR24","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/B:MTAP.0000046380.27575.a5","volume":"25","author":"CG Snoek","year":"2005","unstructured":"Snoek CG, Worring M (2005) Multimodal video indexing: a review of the state-of-the-art. Multimed Tools Appl 25(1):5\u201335","journal-title":"Multimed Tools Appl"},{"issue":"2","key":"1737_CR25","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1109\/TASL.2007.913750","volume":"16","author":"D Turnbull","year":"2008","unstructured":"Turnbull D, Barrington L, Torres D, Lanckriet G (2008) Semantic annotation and retrieval of music and sound effects. IEEE Trans Audio Speech Lang Process 16(2):467\u2013476","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"8","key":"1737_CR26","doi-asserted-by":"crossref","first-page":"2322","DOI":"10.1109\/TSP.2004.831125","volume":"52","author":"N Vasconcelos","year":"2004","unstructured":"Vasconcelos N (2004) Minimum probability of error image retrieval. IEEE Trans Signal Process 52(8):2322\u20132336","journal-title":"IEEE Trans Signal Process"},{"key":"1737_CR27","unstructured":"V\u00eda J, Santama\u00eda I, P\u00e9rez J (2005) Canonical correlation analysis (CCA) algorithms for multiple data sets: Application to blind SIMO equalization. In proceedings of the 13th European Signal Processing Conference (EUSIPCO)"},{"key":"1737_CR28","unstructured":"Vinokourov A, Hardoon DR, Shawe-Taylor J (2003) Learning the semantics of multimedia content with application to web image retrieval and classification. In: International symposium on Independent Component Analysis and Blind Source Separation"},{"key":"1737_CR29","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1155\/S111086570321101X","volume":"2","author":"T Westerveld","year":"2003","unstructured":"Westerveld T, De Vries AP, van Ballegooij A, de Jong F, Hiemstra D (2003) A probabilistic multimedia retrieval model and its evaluation. EURASIP J Appl Signal Process 2:186\u2013198","journal-title":"EURASIP J Appl Signal Process"},{"key":"1737_CR30","doi-asserted-by":"crossref","unstructured":"Xie L, Pan P, Lu Y (2013) A semantic model for cross-modal and multi-modal retrieval. ACM Int Conf Multimed Retr","DOI":"10.1145\/2461466.2461497"},{"key":"1737_CR31","doi-asserted-by":"crossref","unstructured":"Yang Y, Xu D, Nie F, Luo J, Zhuang Y (2009) Ranking with local regression and global alignment for cross media retrieval. ACM Int Conf Multimed","DOI":"10.1145\/1631272.1631298"},{"key":"1737_CR32","doi-asserted-by":"crossref","unstructured":"Zhai X, Peng Y, Xiao J (2013) Cross-media retrieval by intra-media and inter-media correlation mining. Multime\u2019d. Syst 19(5):395\u2013406","DOI":"10.1007\/s00530-012-0297-6"},{"key":"1737_CR33","doi-asserted-by":"crossref","unstructured":"Zhai X, Peng Y, Xiao J (2012) Cross-modality correlation propagation for cross-media retrieval. Proc ICASSP","DOI":"10.1109\/ICASSP.2012.6288383"},{"key":"1737_CR34","doi-asserted-by":"crossref","unstructured":"Zhai X, Peng Y, Xiao J (2012) Effective heterogeneous similarity measure with nearest neighbors for cross-media retrieval. Int Conf MultiMed Model (MMM)","DOI":"10.1007\/978-3-642-27355-1_30"},{"key":"1737_CR35","doi-asserted-by":"crossref","unstructured":"Zhen Y, Yeung D (2012) A probabilistic model for multimodal hash function learning. Proc ACM KDD","DOI":"10.1145\/2339530.2339678"},{"key":"1737_CR36","unstructured":"Zhen Y, Yeung D (2012) Co-regularized hashing for multimodal data. Adv Neural Inf Process Syst (NIPS)"},{"issue":"2","key":"1737_CR37","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/s10618-012-0249-y","volume":"26","author":"Y Zhen","year":"2013","unstructured":"Zhen Y, Yeung D (2013) Active hashing and its application to image and text retrieval. Data Min Knowl Disc 26(2):255\u2013274","journal-title":"Data Min Knowl Disc"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1737-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-013-1737-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1737-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T03:42:02Z","timestamp":1564544522000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-013-1737-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10,25]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2015,3]]}},"alternative-id":["1737"],"URL":"https:\/\/doi.org\/10.1007\/s11042-013-1737-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10,25]]}}}