{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:20:20Z","timestamp":1777695620275,"version":"3.51.4"},"reference-count":36,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2017,11,15]]},"DOI":"10.3233\/ida-163196","type":"journal-article","created":{"date-parts":[[2017,11,24]],"date-time":"2017-11-24T10:50:35Z","timestamp":1511520635000},"page":"1351-1369","source":"Crossref","is-referenced-by-count":5,"title":["Multi-modal deep distance metric learning"],"prefix":"10.1177","volume":"21","author":[{"given":"Seyed Mahdi","family":"Roostaiyan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Imani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdieh Soleymani","family":"Baghshah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-163196_ref1","first-page":"521","article-title":"Distance metric learning with application to clustering with side-information","author":"Xing","year":"2003","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/IDA-163196_ref2","first-page":"1473","article-title":"Distance metric learning for large margin nearest neighbor classification","author":"Weinberger","year":"2006","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/IDA-163196_ref3","doi-asserted-by":"crossref","unstructured":"J.V. Davis, B. Kulis, P. Jain, S. Sra and I.S. Dhillon, Information-theoretic metric learning, in: Proceedings of the 24th international Conference on Machine Learning, ACM, 2007, pp. 209\u2013216.","DOI":"10.1145\/1273496.1273523"},{"key":"10.3233\/IDA-163196_ref4","first-page":"491","article-title":"Learning multi-modal similarity","volume":"12","author":"McFee","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-163196_ref5","doi-asserted-by":"crossref","first-page":"887","DOI":"10.3233\/IDA-2009-0399","article-title":"Metric learning for semi-supervised clustering using pairwise constraints and the geometrical structure of data","volume":"13","author":"Baghshah","year":"2009","journal-title":"Intelligent Data Analysis"},{"key":"10.3233\/IDA-163196_ref6","doi-asserted-by":"crossref","unstructured":"J. Hu, J. Lu and Y.-P. Tan, Discriminative deep metric learning for face verification in the wild, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1875\u20131882.","DOI":"10.1109\/CVPR.2014.242"},{"key":"10.3233\/IDA-163196_ref7","doi-asserted-by":"crossref","unstructured":"H. Oh Song, Y. Xiang, S. Jegelka and S. Savarese, Deep metric learning via lifted structured feature embedding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4004\u20134012.","DOI":"10.1109\/CVPR.2016.434"},{"key":"10.3233\/IDA-163196_ref8","doi-asserted-by":"crossref","unstructured":"J. Hu, J. Lu and Y.-P. Tan, Deep transfer metric learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 325\u2013333.","DOI":"10.1109\/CVPR.2015.7298629"},{"key":"10.3233\/IDA-163196_ref9","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep metric learning using triplet network","author":"Hoffer","year":"2015","journal-title":"International Workshop on Similarity-Based Pattern Recognition"},{"key":"10.3233\/IDA-163196_ref10","unstructured":"J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee and A.Y. Ng, Multimodal deep learning, in: Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011, pp. 689\u2013696."},{"key":"10.3233\/IDA-163196_ref11","doi-asserted-by":"crossref","unstructured":"W. Wang, B.C. Ooi, X. Yang, D. Zhang and Y. Zhuang, Effective multi-modal retrieval based on stacked auto-encoders, Proceedings of the VLDB Endowment 7 (2014), 649\u2013660.","DOI":"10.14778\/2732296.2732301"},{"key":"10.3233\/IDA-163196_ref12","unstructured":"P. Xie and E.P. Xing, Multi-modal distance metric learning, in: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2013, pp. 1806\u20131812."},{"key":"10.3233\/IDA-163196_ref13","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.neucom.2014.12.020","article-title":"Deep correspondence restricted Boltzmann machine for cross-modal retrieval","volume":"154","author":"Feng","year":"2015","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-163196_ref14","unstructured":"N. Srivastava and R.R. Salakhutdinov, Multimodal learning with deep boltzmann machines, in: Advances in Neural Information Processing Systems, 2012, pp. 2222\u20132230."},{"key":"10.3233\/IDA-163196_ref15","unstructured":"N. Chen, J. Zhu and E.P. Xing, Predictive subspace learning for multi-view data: a large margin approach, in: Advances in Neural Information Processing Systems, 2010, pp. 361\u2013369."},{"key":"10.3233\/IDA-163196_ref16","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1109\/TPAMI.2012.64","article-title":"Large-margin predictive latent subspace learning for multiview data analysis","volume":"34","author":"Chen","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/IDA-163196_ref17","doi-asserted-by":"crossref","unstructured":"H. Wang, F. Nie, H. Huang and C. Ding, Heterogeneous visual features fusion via sparse multimodal machine, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 3097\u20133102.","DOI":"10.1109\/CVPR.2013.398"},{"key":"10.3233\/IDA-163196_ref18","doi-asserted-by":"crossref","unstructured":"H. Xia, P. Wu and S.C. Hoi, Online multi-modal distance learning for scalable multimedia retrieval, in: Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, ACM, 2013, pp. 455\u2013464.","DOI":"10.1145\/2433396.2433453"},{"key":"10.3233\/IDA-163196_ref19","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Networks"},{"key":"10.3233\/IDA-163196_ref20","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/s00778-015-0391-4","article-title":"Effective deep learning-based multi-modal retrieval","volume":"25","author":"Wang","year":"2016","journal-title":"The VLDB Journal"},{"key":"10.3233\/IDA-163196_ref21","doi-asserted-by":"crossref","unstructured":"P. Wu, S.C. Hoi, H. Xia, P. Zhao, D. Wang and C. Miao, Online multimodal deep similarity learning with application to image retrieval, in: Proceedings of the 21st ACM international conference on Multimedia, ACM, 2013, pp. 153\u2013162.","DOI":"10.1145\/2502081.2502112"},{"key":"10.3233\/IDA-163196_ref23","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1109\/TPAMI.2013.149","article-title":"Online multiple kernel similarity learning for visual search","volume":"36","author":"Xia","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/IDA-163196_ref24","first-page":"27","article-title":"Learning the kernel matrix with semidefinite programming","volume":"5","author":"Lanckriet","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-163196_ref25","doi-asserted-by":"crossref","unstructured":"N. Chen, S.C. Hoi, S. Li and X. Xiao, SimApp: A framework for detecting similar mobile applications by online kernel learning, in: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, ACM, 2015, pp. 305\u2013314.","DOI":"10.1145\/2684822.2685305"},{"key":"10.3233\/IDA-163196_ref26","first-page":"1531","article-title":"Large scale multiple kernel learning","volume":"7","author":"Sonnenburg","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-163196_ref27","doi-asserted-by":"crossref","unstructured":"N. Chen, S.C. Hoi, S. Li and X. Xiao, Mobile app tagging, in: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining, ACM, 2016, pp. 63\u201372.","DOI":"10.1145\/2835776.2835812"},{"key":"10.3233\/IDA-163196_ref28","unstructured":"Y.-Y. Lin, T.-L. Liu and C.-S. Fuh, Dimensionality reduction for data in multiple feature representations, in: Advances in Neural Information Processing Systems, 2009, pp. 961\u2013968."},{"key":"10.3233\/IDA-163196_ref29","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/TKDE.2015.2477296","article-title":"Online multi-modal distance metric learning with application to image retrieval","volume":"28","author":"Wu","year":"2016","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/IDA-163196_ref31","first-page":"1481","article-title":"Exponential family harmoniums with an application to information retrieval","author":"Welling","year":"2005","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/IDA-163196_ref32","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1093\/biomet\/28.3-4.321","article-title":"Relations between two sets of variates","volume":"28","author":"Hotelling","year":"1936","journal-title":"Biometrika"},{"key":"10.3233\/IDA-163196_ref33","unstructured":"G. Andrew, R. Arora, J. Bilmes and K. Livescu, Deep canonical correlation analysis, in: International Conference on Machine Learning, 2013, pp. 1247\u20131255."},{"key":"10.3233\/IDA-163196_ref34","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1561\/2200000019","article-title":"Metric learning: A survey","volume":"5","author":"Kulis","year":"2013","journal-title":"Foundations and Trends in Machine Learning"},{"key":"10.3233\/IDA-163196_ref36","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"Chechik","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-163196_ref37","doi-asserted-by":"crossref","first-page":"2072","DOI":"10.1109\/CVPR.2006.167","article-title":"Learning distance metrics with contextual constraints for image retrieval","author":"Hoi","year":"2006","journal-title":"Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on"},{"key":"10.3233\/IDA-163196_ref38","doi-asserted-by":"crossref","unstructured":"A. Quattoni and A. Torralba, Recognizing indoor scenes, in: Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, IEEE, 2009, pp. 413\u2013420.","DOI":"10.1109\/CVPRW.2009.5206537"},{"key":"10.3233\/IDA-163196_ref39","first-page":"9","article-title":"Efficient backprop","author":"LeCun","year":"2012","journal-title":"Neural Networks: Tricks of the Trade"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-163196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:18:00Z","timestamp":1777454280000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-163196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,15]]},"references-count":36,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/ida-163196","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,15]]}}}