{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T04:18:24Z","timestamp":1749010704264,"version":"3.41.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319422930"},{"type":"electronic","value":"9783319422947"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-42294-7_28","type":"book-chapter","created":{"date-parts":[[2016,7,11]],"date-time":"2016-07-11T15:00:47Z","timestamp":1468249247000},"page":"322-331","source":"Crossref","is-referenced-by-count":3,"title":["Deep Learning and Shared Representation Space Learning Based Cross-Modal Multimedia Retrieval"],"prefix":"10.1007","author":[{"given":"Hui","family":"Zou","sequence":"first","affiliation":[]},{"given":"Ji-Xiang","family":"Du","sequence":"additional","affiliation":[]},{"given":"Chuan-Min","family":"Zhai","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,7,12]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xu, D., Nie, F., Luo, J., Zhuang, Y.: Ranking with local regression and global alignment for cross media retrieval. In: International Conference on Multimedia, pp. 175\u2013184 (2009)","DOI":"10.1145\/1631272.1631298"},{"key":"28_CR2","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep Boltzmann machines. In: Neural Information Processing Systems, pp. 2222\u20132230 (2012)"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Lu, X., Wu, F., Tang, S.: A low rank structural large margin method for cross-modal ranking. In: Research and Development in Information Retrieval, pp. 433\u2013442 (2013)","DOI":"10.1145\/2484028.2484039"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Lu, X., Wu, F., Tang, S., Zhang, Z., He, X., Zhuang, Y.: Cross-media semantic representation via bi-directional learning to rank. In: International Conference on Multimedia, pp. 877\u2013886 (2013)","DOI":"10.1145\/2502081.2502097"},{"key":"28_CR5","unstructured":"Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning, pp. 282\u2013289 (2001)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Xu, X.S., Jiang, Y., Peng, L., Xue, X., Zhou, Z.H.: Ensemble approach based on conditional random field for multi-label image and video annotation. In: International Conference on Multimedia, pp. 1377\u20131380 (2011)","DOI":"10.1145\/2072298.2072019"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, G., Chu, L., Wang, S., Zhang, W., Huang, Q.: Cross-media topic detection: a multi-modality fusion framework. In: International Conference on IEEE, pp. 1\u20136 (2013)","DOI":"10.1109\/ICME.2013.6607487"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Li, L., Jiang, S., Huang, Q.: Learning image vicept description via mixed-norm regularization for large scale semantic image search. In: Computer Vision and Pattern Recognition, pp. 825\u2013832 (2011)","DOI":"10.1109\/CVPR.2011.5995570"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Costa Pereira, J., Coviello, E., Doyle, G., Lanckriet, G.R., Levy, R., Vasconcelos, N.: A new approach to cross-modal multimedia retrieval. In: International Conference on Multimedia, pp. 251\u2013260 (2010)","DOI":"10.1145\/1873951.1873987"},{"issue":"7","key":"28_CR10","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"issue":"4","key":"28_CR11","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"28_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"1","key":"28_CR13","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"Pattern Anal. Mach. Intell."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Computer Vision and Pattern Recognition Workshops, pp. 512\u2013519 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"28_CR15","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR16","unstructured":"Rosen-Zvi, M., Griffiths, T., Steyvers, M., Smyth, P.: The author-topic model for authors and documents. In: Conference on Uncertainty in Artificial Intelligence, pp. 487\u2013494 (2004)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Ramage, D., Hall, D., Nallapati, R., Manning, C.D.: Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora. In: Conference on Empirical Methods in Natural Language Processing, pp. 248\u2013256 (2009)","DOI":"10.3115\/1699510.1699543"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Niculescu-Mizil, A., Gryc, W.: Topic-link LDA: joint models of topic and author community. In: Annual International Conference on Machine Learning, pp. 665\u2013672 (2009)","DOI":"10.1145\/1553374.1553460"},{"key":"28_CR19","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: International Conference on Machine Learning, pp. 689\u2013696 (2011)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: International Conference on Multimedia, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"28_CR21","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: International Conference on Machine Learning, pp. 807\u2013814 (2010)"},{"key":"28_CR22","unstructured":"Li, J., Luo, W., Yang, J., Yuan, X.: Why Does The Unsupervised Pretraining Encourages Moderate-Sparseness. arXiv Preprint arXiv:1312.5813 (2013)"},{"key":"28_CR23","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving Neural Networks by Preventing Co-adaptation of Feature Detectors. arXiv Preprint arXiv:1207.0580 (2012)"},{"issue":"8","key":"28_CR24","doi-asserted-by":"crossref","first-page":"649","DOI":"10.14778\/2732296.2732301","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. Proc. VLDB Endowment 7(8), 649\u2013660 (2014)","journal-title":"Proc. VLDB Endowment"},{"issue":"5","key":"28_CR25","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1109\/TIP.2015.2403240","volume":"24","author":"F Wu","year":"2015","unstructured":"Wu, F., Jiang, X., Li, X., Tang, S., Lu, W., Zhang, Z., Zhuang, Y.: Cross-modal learning to rank via latent joint representation. Image Process. 24(5), 1497\u20131509 (2015)","journal-title":"Image Process."},{"key":"28_CR26","unstructured":"Ling, L., Zhai, X., Peng, Y.: Tri-space and ranking based heterogeneous similarity measure for cross-media retrieval. In: Pattern Recognition International Conference on IEEE, pp. 230\u2013233 (2012)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Application"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-42294-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:35:07Z","timestamp":1748997307000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-42294-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319422930","9783319422947"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-42294-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}