{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T19:54:35Z","timestamp":1760385275142,"version":"3.40.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2013,2,1]],"date-time":"2013-02-01T00:00:00Z","timestamp":1359676800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2014,11]]},"DOI":"10.1007\/s00530-012-0299-4","type":"journal-article","created":{"date-parts":[[2013,1,31]],"date-time":"2013-01-31T00:51:13Z","timestamp":1359593473000},"page":"645-657","source":"Crossref","is-referenced-by-count":9,"title":["Relative image similarity learning with contextual information for Internet cross-media retrieval"],"prefix":"10.1007","volume":"20","author":[{"given":"Shuqiang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,2,1]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp. 524\u2013531 (2005)","key":"299_CR1","DOI":"10.1109\/CVPR.2005.16"},{"issue":"5","key":"299_CR2","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1109\/TMM.2012.2194993","volume":"14","author":"L Li","year":"2012","unstructured":"Li, L., Jiang, S., Huang, Q.: Learning hierarchical semantic description via mixed-norm regularization for image understanding. IEEE Trans. Multimedia 14(5), 1401\u20131413 (2012)","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"299_CR3","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.1109\/TIP.2011.2180916","volume":"21","author":"J Tang","year":"2012","unstructured":"Tang, J., Zha, Z.-J., Tao, D., Chua, T.-S.: Semantic-gap oriented active learning for multi-label image annotation. IEEE Trans. Image Process. 21(4), 2354\u20132360 (2012)","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"299_CR4","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1109\/TMM.2012.2193120","volume":"14","author":"S Wang","year":"2012","unstructured":"Wang, S., Huang, Q., Jiang, S., Tian, Q.: S3MKL: scalable semi-supervised multiple kernel learning for real world image applications. IEEE Trans. Multimedia 14(4), 1259\u20131274 (2012)","journal-title":"IEEE Trans. Multimedia"},{"issue":"5","key":"299_CR5","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1109\/TCSVT.2009.2017400","volume":"19","author":"M Wang","year":"2009","unstructured":"Wang, M., Hua, X., Hong, R., Tang, J., Qi, G., Song, Y.: Unified video annotation via multi-graph learning. IEEE Trans. Circ. Syst. Video Technol. 19(5), 733\u2013746 (2009)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"7","key":"299_CR6","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1016\/j.patrec.2005.10.017","volume":"27","author":"S Jiang","year":"2006","unstructured":"Jiang, S., Huang, Q., Ye, Q., Gao, W.: An effective method to detect and categorize digitized traditional Chinese paintings. Pattern Recogn. Lett. 27(7), 734\u2013746 (2006)","journal-title":"Pattern Recogn. Lett."},{"doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2169\u20132178 (2006)","key":"299_CR7","DOI":"10.1109\/CVPR.2006.68"},{"doi-asserted-by":"crossref","unstructured":"Tang, J., Yan, S., Hong, R., Qi, G.-J., Chua, T.-S.: Inferring semantic concepts from community-contributed images and noisy tags. In: Proceedings of ACM Multimedia, pp. 223\u2013232 (2009)","key":"299_CR8","DOI":"10.1145\/1631272.1631305"},{"issue":"7","key":"299_CR9","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMM.2009.2030598","volume":"11","author":"X Li","year":"2009","unstructured":"Li, X., Snoek, C.G.M., Worring, M.: Learning social tag relevance by neighbor voting. IEEE Trans. Multimedia 11(7), 1310\u20131322 (2009)","journal-title":"IEEE Trans. Multimedia"},{"key":"299_CR10","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1145\/1899412.1899418","volume":"2","author":"J Tang","year":"2011","unstructured":"Tang, J., Hong, R., Yan, S., Chua, T.-S., Qi, G.-J., Jain, R.: Image annotation by knn-sparse graph-based label propagation over noisily-tagged web images. ACM Trans. Intell. Syst. Technol. 2, 2 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"doi-asserted-by":"crossref","unstructured":"Liu, D., Hua, X., Yang, L., Wang, M., Zhang, H.: Tag ranking. In: Proceeding of the 17th International Conference on World Wide Web, ACM, New York, NY, USA, pp. 317\u2013326 (2009)","key":"299_CR11","DOI":"10.1145\/1526709.1526757"},{"doi-asserted-by":"crossref","unstructured":"Zhu, G., Yan, S., Ma, Y.: Image tag refinement towards low-rank, content-tag prior and error sparsity. In: Proceedings of ACM Multimedia, pp. 461\u2013470 (2010)","key":"299_CR12","DOI":"10.1145\/1873951.1874028"},{"doi-asserted-by":"crossref","unstructured":"Cai, D., He, X., Li, Z., Ma, W.-Y., Wen, J.-R.: Hierarchical clustering of WWW image search results using visual, textual and link information. In: Proceedings of ACM Multimedia, pp. 952\u2013959 (2004)","key":"299_CR13","DOI":"10.1145\/1027527.1027747"},{"doi-asserted-by":"crossref","unstructured":"Gao, B., Liu, T.-Y., Qin, T., Zheng, X., Cheng, Q.-S., Ma, W.-Y.: Web image clustering by consistent utilization of visual features and surrounding texts. In: Proceedings of ACM Multimedia, pp. 112\u2013121 (2005)","key":"299_CR14","DOI":"10.1145\/1101149.1101167"},{"doi-asserted-by":"crossref","unstructured":"Rege, M., Dong, M., Hua, J.: Graph theoretical framework for simultaneously integrating visual and textual features for efficient web image clustering. In: Proceeding of the 17th International Conference on World Wide Web, ACM, New York, NY, USA, pp. 317\u2013326 (2008)","key":"299_CR15","DOI":"10.1145\/1367497.1367541"},{"unstructured":"Jin, Y., Khan, L., Wang, L., Awad M.: Image annotations by combining multiple evidence and Wordnet. In: Proceedings of ACM Multimedia, pp. 706\u2013715 (2008)","key":"299_CR16"},{"doi-asserted-by":"crossref","unstructured":"Wu, L., Hoi, S.C., Zhu, J., Jin, R., Yu, N.: Distance metric learning from uncertain side information with application to automated photo tagging. In: Proceedings of ACM Multimedia, pp. 135\u2013144 (2009)","key":"299_CR17","DOI":"10.1145\/1631272.1631293"},{"unstructured":"Wang, S., Jiang, S., Huang, Q., Tian, Q.: Multi-feature metric learning with knowledge transfer among semantics and social tagging. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2626\u20132633 (2012)","key":"299_CR18"},{"doi-asserted-by":"crossref","unstructured":"Wu, L., Hua, X.-S., Yu, N., Ma, W.-Y., Li, S.: Flickr distance. In: Proceedings of ACM Multimedia, pp. 31\u201340 (2008)","key":"299_CR19","DOI":"10.1145\/1459359.1459364"},{"doi-asserted-by":"crossref","unstructured":"Hoi, S.C.H., Liu, W., Lyu, M.R., Ma, W.-Y.: Learning distance metrics with contextual constraints for image retrieval. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2072\u20132078 (2006)","key":"299_CR20","DOI":"10.1109\/CVPR.2006.167"},{"unstructured":"Hwang, S.J., Grauman, K., Sha, F.: Learning a tree of metrics with disjoint visual features. In: Proceedings of the Conference on Advances in Neural Information Processing Systems, NIPS (2011)","key":"299_CR21"},{"doi-asserted-by":"crossref","unstructured":"Wu, P., Hoi, S.C.H., Zhao, P., He, Y.: Mining social images with distance metric learning for automated image tagging. In: WSDM, pp. 197\u2013206 (2011)","key":"299_CR22","DOI":"10.1145\/1935826.1935865"},{"doi-asserted-by":"crossref","unstructured":"Verma, N., Mahajan, D., Sellamanickam, S., Nair, V.: Learning hierarchical similarity metrics. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2280\u20132287 (2012)","key":"299_CR23","DOI":"10.1109\/CVPR.2012.6247938"},{"key":"299_CR24","first-page":"1453","volume":"6","author":"I Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453\u20131484 (2005)","journal-title":"J. Mach. Learn. Res."},{"unstructured":"McFee, B., Lanckriet, G.: Metric learning to rank. In: International Conference on Machine Learning, Haifa, Israel (2010)","key":"299_CR25"},{"issue":"11","key":"299_CR26","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1109\/TPAMI.2008.127","volume":"30","author":"X-J Wang","year":"2008","unstructured":"Wang, X.-J., Zhang, L., Li, X., Ma, W.-Y.: Annotating images by mining image search results. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1919\u20131932 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Harchaoui, Z., Douze, M., Paulin, M., Dudik, M., Malick, J.: Large-scale image classification with trace-norm regularization. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp. 3386\u20133393 (2012)","key":"299_CR27","DOI":"10.1109\/CVPR.2012.6248078"},{"doi-asserted-by":"crossref","unstructured":"Perronnin, F., Akata, Z., Harchaoui, Z., Schmid, C.: Towards good practice in large-scale learning for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3482\u20133489 (2012)","key":"299_CR28","DOI":"10.1109\/CVPR.2012.6248090"},{"unstructured":"Zhang, H.J., Su, Z.: Improving CBIR by semantic propagation and cross modality query expansion. In: Proceedings of the international workshop on MultiMedia Content-Based Indexing and Retrieval (MM-CBIR\u201901), September, pp. 83\u201386 (2001)","key":"299_CR29"},{"doi-asserted-by":"crossref","unstructured":"Jia, Y., Salmann, M., Darrell, T.: Learning cross-modality similarity for multinomial data. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2407\u20132414 (2011)","key":"299_CR30","DOI":"10.1109\/ICCV.2011.6126524"},{"key":"299_CR31","first-page":"207","volume":"10","author":"KQ Weinberger","year":"2009","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 207\u2013244 (2009)","journal-title":"J. Mach. Learn. Res."},{"unstructured":"Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood components analysis. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (2005)","key":"299_CR32"},{"unstructured":"Schultz, M., Joachims, T.: Learning a distance metric from relative comparisons. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (2009)","key":"299_CR33"},{"unstructured":"Agarwal, S., Wills, J., Cayton, L., Lanckriet, G., Kriegman, D., Belongi, S.: Generalized non-metric multi-dimensional scaling. In: Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (2007)","key":"299_CR34"},{"unstructured":"McFee, B., Lanckriet, G.R.G.: Learning multi-modal similarity. J. Mach. Learn. Res. (JMLR), February, pp. 491\u2013523 (2011)","key":"299_CR35"},{"doi-asserted-by":"crossref","unstructured":"Lee, J.-E., Jin, R., Jain, A.K.: Rank-based distance metric learning: an application to image retrieval. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2009)","key":"299_CR36","DOI":"10.1109\/CVPR.2008.4587389"},{"doi-asserted-by":"crossref","unstructured":"Thorsten, J., Finley, T., John Yu C.-N.: Cutting-plane training of structural SVMs. Mach. Learn. 77(1):27\u201359 (2009). ISSN 0885-6125","key":"299_CR37","DOI":"10.1007\/s10994-009-5108-8"},{"key":"299_CR38","first-page":"265","volume":"2","author":"K Crammer","year":"2001","unstructured":"Crammer, K., Singer, Y.: On the algorithmic implementation of multi-class kernel-based vector machines. Mach. Learn. Res. 2, 265\u2013292 (2001)","journal-title":"Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"Joachims, T.: A support vector method for multivariate performance measures. In: International Conference on Machine Learning, pp. 377\u2013384 (2005)","key":"299_CR39","DOI":"10.1145\/1102351.1102399"},{"doi-asserted-by":"crossref","unstructured":"Yue, Y., Finley, T., Radlinski, F., Joachims, T.: A support vector method for optimizing average precision. In: Proceedings of acm special interest group on information retrieval conference, pp. 271\u2013278 (2007)","key":"299_CR40","DOI":"10.1145\/1277741.1277790"},{"doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Khanna, R., Sawant, U., Bhattacharyya, C.: Structured learning for non smooth ranking losses. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, USA, pp. 88\u201396 (2008)","key":"299_CR41","DOI":"10.1145\/1401890.1401906"},{"unstructured":"http:\/\/www.imageclef.org","key":"299_CR42"},{"issue":"7","key":"299_CR43","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971\u2013987 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-012-0299-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-012-0299-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-012-0299-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T18:58:14Z","timestamp":1745953094000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-012-0299-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,1]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2014,11]]}},"alternative-id":["299"],"URL":"https:\/\/doi.org\/10.1007\/s00530-012-0299-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2013,2,1]]}}}