{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:48:45Z","timestamp":1790264925142,"version":"4.1.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,7,19]],"date-time":"2015-07-19T00:00:00Z","timestamp":1437264000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001348","name":"A*STAR","doi-asserted-by":"crossref","award":["1321202073"],"award-info":[{"award-number":["1321202073"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s00778-015-0391-4","type":"journal-article","created":{"date-parts":[[2015,7,18]],"date-time":"2015-07-18T07:15:09Z","timestamp":1437203709000},"page":"79-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":103,"title":["Effective deep learning-based multi-modal retrieval"],"prefix":"10.1007","volume":"25","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,7,19]]},"reference":[{"key":"391_CR1","doi-asserted-by":"crossref","unstructured":"Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. CoRR arXiv:1206.5533 (2012)","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"391_CR2","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"391_CR3","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A.C., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"391_CR4","doi-asserted-by":"crossref","unstructured":"Bronstein, M.M., Bronstein, A.M., Michel, F., Paragios, N.: Data fusion through cross-modality metric learning using similarity- sensitive hashing. In: The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, pp. 3594\u20133601. IEEE Computer Society (2010)","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"391_CR5","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.T.: Nus-wide: a real-world web image database from national university of singapore. In: Proceedings of ACM Conference on Image and Video Retrieval (CIVR\u201909), Santorini, Greece (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"391_CR6","volume-title":"Deep Big Multilayer Perceptrons for Digit Recognition","author":"DC Ciresan","year":"2012","unstructured":"Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep Big Multilayer Perceptrons for Digit Recognition, vol. 7700. Springer, Berlin (2012)"},{"key":"391_CR7","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Le, Q.V., Mao, M.Z., Ranzato, M., Senior, A.W., Tucker, P.A., Yang, K., Ng, A.Y.: Large scale distributed deep networks. In: Bartlett, P.L., Pereira, F.C.N., Burges, C.J.C., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, Nevada, United States, pp. 1232\u20131240 (2012)"},{"key":"391_CR8","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. arXivpreprint arXiv:1310.1531 (2013)"},{"key":"391_CR9","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M.,Mikolov,T.: Devise: a deep visual-semantic embedding model. In: Burges, C.J.C., Bottou, L., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 26: 27th AnnualConference on Neural Information Processing Systems 2013, Lake Tahoe, Nevada, United States, pp. 2121\u20132129 (2013)"},{"key":"391_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR 2014, Columbus, OH, USA, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"391_CR11","unstructured":"Gong, Y., Jia, Y., Leung, T., Toshev, A., Ioffe, S.: Deep convolutional ranking for multilabel image annotation. CoRR arXiv:1312.4894 (2013a)"},{"issue":"12","key":"391_CR12","doi-asserted-by":"crossref","first-page":"2916","DOI":"10.1109\/TPAMI.2012.193","volume":"35","author":"Y Gong","year":"2013","unstructured":"Gong, Y., Lazebnik, S., Gordo, A., Perronnin, F.: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2916\u20132929 (2013b)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"391_CR13","unstructured":"Goroshin, R., LeCun, Y.: Saturating auto-encoder. CoRR arXiv:1301.3577 (2013)"},{"key":"391_CR14","doi-asserted-by":"crossref","unstructured":"Hinton, G.: A Practical Guide to Training Restricted Boltzmann Machines. In: Montavon, G., M\u00fcller, K-R. (eds.) Neural Networks: Tricks of the Trade-Second Edition, Lecture Notes in Computer Science, vol 7700, pp. 599\u2013619. Springer (2012)","DOI":"10.1007\/978-3-642-35289-8_32"},{"issue":"5786","key":"391_CR15","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G Hinton","year":"2006","unstructured":"Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"issue":"4","key":"391_CR16","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1145\/958942.958948","volume":"28","author":"GR Hjaltason","year":"2003","unstructured":"Hjaltason, G.R., Samet, H.: Index-driven similarity search in metric spaces. ACM Trans. Database Syst. 28(4), 517\u2013580 (2003)","journal-title":"ACM Trans. Database Syst."},{"key":"391_CR17","doi-asserted-by":"crossref","unstructured":"Huiskes, M.J., Lew, M.S.: The mir flickr retrieval evaluation. In: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, MIR \u201908, Vancouver, British Columbia, Canada, pp. 39\u201343. ACM, New York, USA (2008)","DOI":"10.1145\/1460096.1460104"},{"key":"391_CR18","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: Hua, K.A., Rui, Y., Steinmetz, R., Hanjalic, A., Natsev, A., Zhu, W. (eds.) Proceedings of the ACM International Conference on Multimedia, MM \u201914, Orlando, FL, USA, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"391_CR19","unstructured":"Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. Tech. rep (2009)"},{"key":"391_CR20","first-page":"1106","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106\u20131114 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"391_CR21","unstructured":"Kumar, S., Udupa, R.: Learning hash functions for cross-viewsimilarity search. In: Walsh, T. (ed.) Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, pp. 1360\u20131365. IJCAI\/AAAI (2011)"},{"key":"391_CR22","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","volume-title":"Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, chap 2","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Orr, G., M\u00fcller, K.: Efficient backProp. In: Orr, G., M\u00fcller, K.R. (eds.) Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, chap 2, vol. 1524, pp. 9\u201350. Springer, Berlin (1998)"},{"key":"391_CR23","doi-asserted-by":"crossref","unstructured":"Liu, D., Hua, X., Yang, L., Wang, M., Zhang, H.: Tag ranking. In: Proceedings of the 18th International Conference on World Wide Web, WWW 2009, Madrid, Spain, pp. 351\u2013360, (2009). doi: 10.1145\/1526709.1526757","DOI":"10.1145\/1526709.1526757"},{"key":"391_CR24","unstructured":"Liu, W., Wang, J., Kumar, S., Chang, S.F.: Hashing with graphs. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, pp. 1\u20138. Omnipress (2011)"},{"key":"391_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., Wu, F., Tang, S., Zhang, Z., He, X., Zhuang, Y.: A low rank structural large margin method for cross-modal ranking. In: SIGIR, pp. 433\u2013442 (2013)","DOI":"10.1145\/2484028.2484039"},{"key":"391_CR26","first-page":"3221","volume":"15","author":"L Maaten van der","year":"2014","unstructured":"van der Maaten, L.: Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 3221\u20133245 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"391_CR27","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)"},{"key":"391_CR28","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, pp. 689\u2013696. Omnipress (2011)"},{"key":"391_CR29","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, pp. 689\u2013696. Omnipress (2011)"},{"key":"391_CR30","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Pereira, J.C., Coviello, E., Doyle, G., Lanckriet, G.R.G., Levy, R., Vasconcelos, N.: A new approach to cross-modal multimedia retrieval. In: ACM Multimedia, pp. 251\u2013260 (2010)","DOI":"10.1145\/1873951.1873987"},{"key":"391_CR31","doi-asserted-by":"crossref","unstructured":"Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction. In: ICML, pp. 833\u2013840 (2011)","DOI":"10.1007\/978-3-642-23783-6_41"},{"issue":"7","key":"391_CR32","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1016\/j.ijar.2008.11.006","volume":"50","author":"R Salakhutdinov","year":"2009","unstructured":"Salakhutdinov, R., Hinton, G.E.: Semantic hashing. Int. J. Approx. Reason. 50(7), 969\u2013978 (2009)","journal-title":"Int. J. Approx. Reason."},{"key":"391_CR33","unstructured":"Socher, R., Manning, C.D.: Deep learning for NLP (without magic). In: Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, pp. 1\u20133. Westin Peachtree Plaza Hotel, Atlanta, Georgia, USA (2013)"},{"key":"391_CR34","unstructured":"Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-supervised recursive autoencoders for predicting sentimentdistributions. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, John McIntyre Conference Centre, Edinburgh, UK, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 151\u2013161. ACL (2011)"},{"key":"391_CR35","doi-asserted-by":"crossref","unstructured":"Song, J., Yang, Y., Huang, Z., Shen, H.T., Hong, R.: Multiple feature hashing for real-time large scale near-duplicate video retrieval. In: MM, ACM, pp . 423\u2013432 (2011)","DOI":"10.1145\/2072298.2072354"},{"key":"391_CR36","doi-asserted-by":"crossref","unstructured":"Song, J., Yang, Y., Yang, Y., Huang, Z., Shen, H.T.: Inter-media hashing for large-scale retrieval from heterogeneous data sources. In: SIGMOD Conference, pp. 785\u2013796 (2013)","DOI":"10.1145\/2463676.2465274"},{"key":"391_CR37","unstructured":"Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep boltzmann machines. In: NIPS, pp. 2231\u20132239 (2012)"},{"key":"391_CR38","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: ICML, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"issue":"8","key":"391_CR39","first-page":"649","volume":"7","author":"W Wang","year":"2014","unstructured":"Wang, W., Ooi, B.C., Yang, X., Zhang, D., Zhuang, Y.: Effective multi-modal retrieval based on stacked auto-encoders. PVLDB 7(8), 649\u2013660 (2014)","journal-title":"PVLDB"},{"key":"391_CR40","unstructured":"Weber, R., Schek, H.J., Blott, S.: A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In: Gupta, A., Shmueli, O., Widom, J. (eds.) Proceedings of24rd International Conference on Very Large Data Bases, New York, USA, pp. 194\u2013205. Morgan Kaufmann (1998) (1998)"},{"key":"391_CR41","unstructured":"Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems,Vancouver, British Columbia, Canada, pp. 1753\u20131760. Curran Associates, Inc., (2008)"},{"key":"391_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, D., Agrawal, D., Chen, G., Tung, A.K.H.: Hashfile: an efficient index structure for multimedia data. In: ICDE, pp. 1103\u20131114. IEEE Computer Society, Hannover, Germany (2011)","DOI":"10.1109\/ICDE.2011.5767837"},{"key":"391_CR43","doi-asserted-by":"crossref","unstructured":"Zhen, Y., Yeung, D.Y.: A probabilistic model for multimodal hashfunction learning. In: Yang, Q., Agarwal, D., Pei, J. (eds.) The 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201912, Beijing, China, pp. 940\u2013948. ACM (2012)","DOI":"10.1145\/2339530.2339678"},{"key":"391_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, X., Huang, Z., Shen, H.T., Zhao, X.: Linear cross-modal hashing for efficient multimedia search. In: ACM Multimedia Conference, MM\u2019 13, Barcelona, Spain, pp. 143\u2013152 (2013)","DOI":"10.1145\/2502081.2502107"},{"key":"391_CR45","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Yang, Y., Wu, F.: Mining semantic correlation of heterogeneous multimedia data for cross-media retrieval. IEEE Trans. Multimed. 10(2), 221\u2013229 (2008)","DOI":"10.1109\/TMM.2007.911822"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0391-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-015-0391-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0391-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T07:50:29Z","timestamp":1566978629000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-015-0391-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,19]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["391"],"URL":"https:\/\/doi.org\/10.1007\/s00778-015-0391-4","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,19]]}}}