{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T12:55:29Z","timestamp":1768568129671,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:00:00Z","timestamp":1519689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571453"],"award-info":[{"award-number":["61571453"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502264"],"award-info":[{"award-number":["61502264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61405252"],"award-info":[{"award-number":["61405252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["14JJ3010"],"award-info":[{"award-number":["14JJ3010"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1007\/s11042-018-5767-1","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T11:29:39Z","timestamp":1519730979000},"page":"13169-13188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Semantically-enhanced kernel canonical correlation analysis: a multi-label cross-modal retrieval"],"prefix":"10.1007","volume":"78","author":[{"given":"Yuhua","family":"Jia","sequence":"first","affiliation":[]},{"given":"Liang","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jinlin","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yuxiang","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,27]]},"reference":[{"key":"5767_CR1","unstructured":"Akaho S (2006) A kernel method for canonical correlation analysis. In: Proceedings of the international meeting of the psychometric society, vol 40, pp 263\u2013269"},{"key":"5767_CR2","doi-asserted-by":"crossref","unstructured":"Bekkerman R, Jeon J (2007) Multi-modal clustering for multimedia collections. In: IEEE conference on computer vision and pattern recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383223"},{"key":"5767_CR3","doi-asserted-by":"crossref","unstructured":"Chua TS, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) NUS-WIDE: a real-world web image database from National University of Singapore. In: ACM international conference on image and video retrieval, p 48","DOI":"10.1145\/1646396.1646452"},{"key":"5767_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"5767_CR5","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool L, Williams CK, Winn J, Zisserman A (2010) The Pascal Visual Object Classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"12","key":"5767_CR6","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1109\/TPAMI.2012.193","volume":"35","author":"Y Gong","year":"2013","unstructured":"Gong Y, Lazebnik S, Gordo A et al (2013) Iterative quantization: a Procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Pattern Anal Mach Intell 35(12):2916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"5767_CR7","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/s11263-013-0658-4","volume":"106","author":"Y Gong","year":"2014","unstructured":"Gong Y, Ke Q, Isard M, Lazebnik S (2014) A multi-view embedding space for modeling internet images, tags, and their semantics. Int J Comput Vis 106(2):210\u2013233","journal-title":"Int J Comput Vis"},{"issue":"12","key":"5767_CR8","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"D Hardoon","year":"2004","unstructured":"Hardoon D, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16(12):2639\u20132664","journal-title":"Neural Comput"},{"key":"5767_CR9","doi-asserted-by":"crossref","unstructured":"Hotelling H (1992) Relations between two sets of variates. In: Breakthroughs in statistics, pp 321\u2013377","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"5767_CR10","doi-asserted-by":"crossref","unstructured":"Huyn N (2001) Data analysis and mining in the life sciences. In: ACM","DOI":"10.1145\/603867.603880"},{"key":"5767_CR11","unstructured":"Hwang SJ, Grauman K (2010) Accounting for the relative importance of objects in image retrieval. In: British machine vision conference, pp 1\u201312"},{"key":"5767_CR12","unstructured":"Hwang SJ, Grauman K (2010) Reading between the lines: object localization using implicit cues from image tags. In: IEEE conference on computer vision and pattern recognition, pp 2971\u20132978"},{"issue":"2","key":"5767_CR13","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/s11263-011-0494-3","volume":"100","author":"SJ Hwang","year":"2012","unstructured":"Hwang SJ, Grauman K (2012) Learning the relative importance of objects from tagged images for retrieval and cross-modal search. Int J Comput Vis 100(2):134\u2013153","journal-title":"Int J Comput Vis"},{"issue":"4","key":"5767_CR14","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin K, Kek\u00e4l\u00e4inen J (2002) Cumulated gain-based evaluation of IR techniques. ACM Trans Inf Syst 20(4):422\u2013446","journal-title":"ACM Trans Inf Syst"},{"key":"5767_CR15","doi-asserted-by":"crossref","unstructured":"Jiang W, Chang S-F, Loui AC (2007) Context-based concept fusion with boosted conditional random fields. In: IEEE international conference on acoustics, speech and signal processing","DOI":"10.1109\/ICASSP.2007.366066"},{"key":"5767_CR16","unstructured":"Jiang Y-G, Wang J, Chang S-F, Ngo C-W (2009) Domain adaptive semantic diffusion for large scale context-based video annotation. In: IEEE 12th international conference on computer vision, pp 1420\u20131427"},{"issue":"6","key":"5767_CR17","doi-asserted-by":"publisher","first-page":"3080","DOI":"10.1109\/TIP.2012.2188038","volume":"21","author":"Y-G Jiang","year":"2012","unstructured":"Jiang Y-G, Dai Q, Wang J, Ngo C-W, Xue X, Chang S-F (2012) Fast semantic diffusion for large-scale context-based image and video annotation. IEEE Trans Image Process 21(6):3080\u20133091","journal-title":"IEEE Trans Image Process"},{"key":"5767_CR18","doi-asserted-by":"crossref","unstructured":"Jin Y, Khan L, Wang L, Awad M (2005) Image annotations by combining multiple evidence & WordNet. In: ACM international conference on multimedia, pp 706\u2013715","DOI":"10.1145\/1101149.1101305"},{"issue":"3","key":"5767_CR19","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TMM.2015.2390499","volume":"17","author":"C Kang","year":"2015","unstructured":"Kang C, Xiang S, Liao S, Xu C, Pan C (2015) Learning consistent feature representation for cross-modal multimedia retrieval. IEEE Trans Multimed 17(3):370\u2013381","journal-title":"IEEE Trans Multimed"},{"key":"5767_CR20","doi-asserted-by":"crossref","unstructured":"Kennedy LS, Chang S-F (2007) A reranking approach for context-based concept fusion in video indexing and retrieval. In: Proceedings of the 6th ACM international conference on image and video retrieval, pp 333\u2013340","DOI":"10.1145\/1282280.1282331"},{"issue":"5","key":"5767_CR21","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1142\/S012906570000034X","volume":"10","author":"PL Lai","year":"2000","unstructured":"Lai PL, Fyfe C (2000) Kernel and nonlinear canonical correlation analysis. Int J Neural Syst 10(5):365","journal-title":"Int J Neural Syst"},{"issue":"11","key":"5767_CR22","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) WordNet: a lexical database for english. Commun ACM 38 (11):39\u201341","journal-title":"Commun ACM"},{"key":"5767_CR23","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0079-6123(06)55002-2","volume":"155","author":"A Oliva","year":"2006","unstructured":"Oliva A, Torralba A (2006) Building the gist of a scene: the role of global image features in recognition. Prog Brain Res 155:23\u201336","journal-title":"Prog Brain Res"},{"key":"5767_CR24","unstructured":"Qi G-J, Hua X-S, Rui Y, Tang J, Mei T, Zhang H-J (2007) Correlative multi-label video annotation. In: ACM international conference on multimedia, pp 17\u201326"},{"key":"5767_CR25","doi-asserted-by":"crossref","unstructured":"Ranjan V, Rasiwasia N, Jawahar CV (2015) Multi-label cross-modal retrieval. In: IEEE international conference on computer vision, pp 4094\u20134102","DOI":"10.1109\/ICCV.2015.466"},{"key":"5767_CR26","doi-asserted-by":"crossref","unstructured":"Rasiwasia N, Pereira JC, Coviello E et al (2010) A new approach to cross-modal multimedia retrieval. In: ACM international conference on multimedia, pp 251\u2013260","DOI":"10.1145\/1873951.1873987"},{"key":"5767_CR27","unstructured":"Rasiwasia N, Mahajan D, Mahadevan V, Aggarwal G (2014) Cluster canonical correlation analysis. In: Proceedings of international conference on artificial intelligence and statistics"},{"issue":"3","key":"5767_CR28","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1109\/TMM.2012.2188782","volume":"14","author":"J Sang","year":"2012","unstructured":"Sang J, Xu C, Liu J (2012) User-aware image tag refinement via ternary semantic analysis. IEEE Trans Multimed 14(3):883\u2013895","journal-title":"IEEE Trans Multimed"},{"issue":"3","key":"5767_CR29","first-page":"39:1","volume":"8","author":"J Sang","year":"2017","unstructured":"Sang J, Fang Q, Xu C (2017) Exploiting social-mobile information for location visualization. ACM TIST 8(3):39:1\u201339:19","journal-title":"ACM TIST"},{"key":"5767_CR30","doi-asserted-by":"crossref","unstructured":"Sharma A (2012) Generalized multiview analysis: a discriminative latent space. In: IEEE conference on computer vision and pattern recognition, pp 2160\u20132167","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"5767_CR31","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Computer Science"},{"issue":"8","key":"5767_CR32","first-page":"1967","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Salakhutdinov R (2014) Multimodal learning with deep Boltzmann machines. J Mach Learn Res 15(8):1967\u20132006","journal-title":"J Mach Learn Res"},{"key":"5767_CR33","unstructured":"Vinokourov A, Shawe-Taylor J, Cristianini N (2002) Inferring a semantic representation of text via cross-language correlation analysis. In: Advances of neural information processing systems, pp 1497\u20131504"},{"key":"5767_CR34","doi-asserted-by":"crossref","unstructured":"Wang C, Jing F, Zhang L, Zhang H-J (2006) Image annotation refinement using random walk with restarts. In: ACM international conference on multimedia, pp 647\u2013650","DOI":"10.1145\/1180639.1180774"},{"key":"5767_CR35","doi-asserted-by":"crossref","unstructured":"Wang K, He R, Wang W, Wang L, Tan T (2013) Learning coupled feature spaces for cross-modal matching. In: IEEE international conference on computer vision, pp 2088\u20132095","DOI":"10.1109\/ICCV.2013.261"},{"key":"5767_CR36","doi-asserted-by":"crossref","unstructured":"Wang P, Sun LF, Yang SQ, Smeaton AF (2016) Semantically smoothed refinement for everyday concept indexing. In: Pacific rim conference on multimedia (PCM)","DOI":"10.1007\/978-3-319-48890-5_31"},{"key":"5767_CR37","doi-asserted-by":"crossref","unstructured":"Wang P, Sun LF, Yang SQ, Smeaton AF (2016) Towards training-free refinement for semantic indexing of visual media. In: International conference on multimedia modeling, pp 251\u2013263","DOI":"10.1007\/978-3-319-27671-7_21"},{"key":"5767_CR38","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.cviu.2015.09.014","volume":"148","author":"P Wang","year":"2016","unstructured":"Wang P, Sun LF, Yang SQ, Smeaton AF, Gurrin C (2016) Characterizing everyday activities from visual lifelogs based on enhancing concept representation. Comput Vis Image Underst 148:181\u2013192","journal-title":"Comput Vis Image Underst"},{"key":"5767_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2016.08.107","volume":"236","author":"P Wang","year":"2017","unstructured":"Wang P, Sun LF, Yang SQ, Smeaton A F (2017) Training-free indexing refinement for visual media via multi-semantics. Neurocomputing 236:39\u201347","journal-title":"Neurocomputing"},{"issue":"2","key":"5767_CR40","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1049\/iet-cvi.2016.0148","volume":"11","author":"H Wang","year":"2017","unstructured":"Wang H, Wu X, Jia Y (2017) Heterogeneous domain adaptation method for video annotation. IET Comput Vis 11(2):181\u2013187","journal-title":"IET Comput Vis"},{"key":"5767_CR41","unstructured":"Wu Y, Tseng B, Smith JR (2004) Ontology-based multi-classification learning for video concept detection. In: IEEE international conference on multimedia and expo"},{"key":"5767_CR42","unstructured":"Wu F, Zhang H, Zhuang Y (2007) Learning semantic correlations for cross-media retrieval. In: IEEE international conference on image processing. IEEE, pp 1465\u20131468"},{"key":"5767_CR43","doi-asserted-by":"crossref","unstructured":"Wu F, Lu X, Zhang Z, Yan S, Rui Y, Zhuang Y (2013) Cross-media semantic representation via bi-directional learning to rank. In: ACM international conference on multimedia, pp 877\u2013886","DOI":"10.1145\/2502081.2502097"},{"key":"5767_CR44","unstructured":"Xue X, Zhang W, Zhang J, Wu B, Fan J, Lu Y (2011) Correlative multi-label multi-instance image annotation. In: ICCV, pp 651\u2013658"},{"key":"5767_CR45","doi-asserted-by":"crossref","unstructured":"Yao T, Mei T, Ngo C W (2015) Learning query and image similarities with ranking canonical correlation analysis. In: IEEE international conference on computer vision, pp 28\u201336","DOI":"10.1109\/ICCV.2015.12"},{"issue":"1","key":"5767_CR46","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s12859-017-1543-x","volume":"18","author":"K Youshida","year":"2017","unstructured":"Youshida K, Yoshimoto J, Doya K (2017) Sparse kernel canonical correlation analysis for discovery of nonlinear interactions in high-dimensional data. BMC Bioinf 18(1):108","journal-title":"BMC Bioinf"},{"issue":"5","key":"5767_CR47","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1109\/TIP.2014.2311377","volume":"23","author":"J Yu","year":"2014","unstructured":"Yu J, Rui Y, Tao D (2014) Click Prediction for web image reranking using multimodal sparse coding. IEEE Trans Image Process 23(5):2019\u20132032","journal-title":"IEEE Trans Image Process"},{"issue":"4","key":"5767_CR48","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TCYB.2014.2336697","volume":"45","author":"J Yu","year":"2015","unstructured":"Yu J, Tao D, Wang M, Rui Y (2015) Learning to rank using user clicks and visual features for image retrieval. IEEE Trans Cybern 45(4):767\u2013779","journal-title":"IEEE Trans Cybern"},{"issue":"99","key":"5767_CR49","first-page":"1","volume":"PP","author":"J Yu","year":"2016","unstructured":"Yu J, Yang X, Gao F, Tao D (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern PP(99):1\u201311","journal-title":"IEEE Trans Cybern"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-5767-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5767-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5767-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T10:43:35Z","timestamp":1560509015000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5767-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,27]]},"references-count":49,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["5767"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5767-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,27]]},"assertion":[{"value":"30 July 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}