{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:48:28Z","timestamp":1774968508984,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T00:00:00Z","timestamp":1591315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T00:00:00Z","timestamp":1591315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61762021"],"award-info":[{"award-number":["61762021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61976107"],"award-info":[{"award-number":["61976107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61962010"],"award-info":[{"award-number":["61962010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Netw"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11276-020-02382-4","type":"journal-article","created":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T12:02:42Z","timestamp":1591358562000},"page":"3469-3481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Representation separation adversarial networks for cross-modal retrieval"],"prefix":"10.1007","volume":"30","author":[{"given":"Jiaxin","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5241-7703","authenticated-orcid":false,"given":"Weihua","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Gou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heping","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,5]]},"reference":[{"key":"2382_CR1","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2382_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2984991","author":"H Lu","year":"2020","unstructured":"Lu, H., Zhang, M., Xu, X., Li, Y., & Shen, H. T. (2020). Deep fuzzy hashing network for efficient image retrieval. IEEE Transactions on Fuzzy Systems. https:\/\/doi.org\/10.1109\/TFUZZ.2020.2984991.","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"2382_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102794","author":"W Lu","year":"2020","unstructured":"Lu, W., Zhang, X., Lu, H., & Li, F. (2020). Deep hierarchical encoding model for sentence semantic matching. Journal of Visual Communication and Image Representation. https:\/\/doi.org\/10.1016\/j.jvcir.2020.102794.","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"2382_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7240-1","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Lu, W., Ou, W., Zhang, G., Zhang, X., Cheng, J., & Zhang, W. (2019). Chinese medical question answer selection via hybrid models based on CNN and GRU. Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-019-7240-1.","journal-title":"Multimedia Tools and Applications"},{"key":"2382_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2903516","author":"L Peng","year":"2019","unstructured":"Peng, L., Yang, Y., Ji, Y., Lu, H., & Shen, H. T. (2019). Coarse to fine: Improving VQA with cascaded-answering model. IEEE Transactions on Knowledge and Data Engineering. https:\/\/doi.org\/10.1109\/TKDE.2019.2903516.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2382_CR6","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., Hanjalic, A., & Shen, H. T. (2017). Adversarial cross-modal retrieval. In Proceedings of the 25th ACM international conference on multimedia (pp. 154\u2013162).","DOI":"10.1145\/3123266.3123326"},{"issue":"9","key":"2382_CR7","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TCSVT.2017.2705068","volume":"28","author":"Y Peng","year":"2017","unstructured":"Peng, Y., Huang, X., & Zhao, Y. (2017). An overview of cross-media retrieval: Concepts, methodologies, benchmarks, and challenges. IEEE Transactions on Circuits and Systems for Video Technology, 28(9), 2372\u20132385.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"2","key":"2382_CR8","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/s11280-018-0541-x","volume":"22","author":"X Xu","year":"2019","unstructured":"Xu, X., He, L., Lu, H., Gao, L., & Ji, Y. (2019). Deep adversarial metric learning for cross-modal retrieval. World Wide Web, 22(2), 657\u2013672.","journal-title":"World Wide Web"},{"issue":"1","key":"2382_CR9","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/TMM.2019.2922128","volume":"22","author":"J Zhang","year":"2019","unstructured":"Zhang, J., & Peng, Y. (2019). Multi-pathway generative adversarial hashing for unsupervised cross-modal retrieval. IEEE Transactions on Multimedia, 22(1), 174\u2013187.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"5","key":"2382_CR10","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1109\/TIP.2017.2676345","volume":"26","author":"X Xu","year":"2017","unstructured":"Xu, X., Shen, F., Yang, Y., Shen, H. T., & Li, X. (2017). Learning discriminative binary codes for large-scale cross-modal retrieval. IEEE Transactions on Image Processing, 26(5), 2494\u20132507.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3\u20134","key":"2382_CR11","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1093\/biomet\/28.3-4.321","volume":"28","author":"H Hotelling","year":"1936","unstructured":"Hotelling, H. (1936). Relations between two sets of variates. Biometrika, 28(3\u20134), 321\u2013377.","journal-title":"Biometrika"},{"key":"2382_CR12","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Pereira, J. C., Coviello, E., Doyle, G., Lanckriet, G. R. G., Levy, R., & Vasconcelos, N. (2010). A new approach to cross-modal multimedia retrieval. In Proceedings of the 18th ACM international conference on multimedia (pp. 251\u2013260).","DOI":"10.1145\/1873951.1873987"},{"key":"2382_CR13","unstructured":"Akaho, S. (2006). A kernel method for canonical correlation analysis. arXiv preprint arXiv:cs\/0609071."},{"key":"2382_CR14","unstructured":"Wang, W., & Livescu, K. (2015). Large-scale approximate kernel canonical correlation analysis. arXiv preprint arXiv:1511.04773."},{"key":"2382_CR15","doi-asserted-by":"crossref","unstructured":"Yan, F., & Mikolajczyk, K. (2015). Deep correlation for matching images and text. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3441\u20133450).","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"2382_CR16","doi-asserted-by":"crossref","unstructured":"Feng, F., Wang, X., & Li, R. (2014). Cross-modal retrieval with correspondence autoencoder. In The 22nd international conference on multimedia (ACM) (pp. 7\u201316).","DOI":"10.1145\/2647868.2654902"},{"key":"2382_CR17","unstructured":"Peng, Y., Huang, X., & Qi, J. (2016). Cross-media shared representation by hierarchical learning with multiple deep networks. In IJCAI (pp. 3846\u20133853)."},{"issue":"1","key":"2382_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3284750","volume":"15","author":"Y Peng","year":"2019","unstructured":"Peng, Y., & Qi, J. (2019). CM-GANs: Cross-modal generative adversarial networks for common representation learning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 15(1), 1\u201324.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"2382_CR19","unstructured":"Andrew, G., Arora, R., Bilmes, J., & Livescu, K. (2013). Deep canonical correlation analysis. In International conference on machine learning (pp. 1247\u20131255)."},{"key":"2382_CR20","unstructured":"Wang, W., Arora, R., Livescu, K., & Bilmes, J. (2015). On deep multi-view representation learning. In International conference on machine learning (pp. 1083\u20131092)."},{"key":"2382_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, Q.-Y., & Li, W.-J. (2017). Deep cross-modal hashing. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3232\u20133240).","DOI":"10.1109\/CVPR.2017.348"},{"key":"2382_CR22","doi-asserted-by":"crossref","unstructured":"Li, C., Deng, C., Li, N., Liu, W., Gao, X., & Tao, D. (2018). Self-supervised adversarial hashing networks for cross-modal retrieval. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4242\u20134251).","DOI":"10.1109\/CVPR.2018.00446"},{"issue":"11","key":"2382_CR23","doi-asserted-by":"publisher","first-page":"5292","DOI":"10.1109\/TNNLS.2018.2793863","volume":"29","author":"E Yang","year":"2018","unstructured":"Yang, E., Deng, C., Li, C., Liu, W., Li, J., & Tao, D. (2018). Shared predictive cross-modal deep quantization. IEEE Transactions on Neural Networks and Learning Systems, 29(11), 5292\u20135303.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2382_CR24","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (pp. 2672\u20132680)."},{"key":"2382_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., & Lu, H. (2018). Deep cross-modal projection learning for image-text matching. In Proceedings of the European conference on computer vision (ECCV) (pp. 686\u2013701).","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"2382_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., & Gupta, A. (2016). Generative image modeling using style and structure adversarial networks. In European conference on computer vision (pp. 318\u2013335). Springer.","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"2382_CR27","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016). Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396."},{"key":"2382_CR28","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4681\u20134690).","DOI":"10.1109\/CVPR.2017.19"},{"key":"2382_CR29","doi-asserted-by":"crossref","unstructured":"Yan, B., Wang, D., Lu, H., & Yang, X. (2020). Cooling-shrinking attack: Blinding the tracker with imperceptible noises. arXiv preprint arXiv:2003.09595.","DOI":"10.1109\/CVPR42600.2020.00107"},{"key":"2382_CR30","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018). Feature generating networks for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5542\u20135551).","DOI":"10.1109\/CVPR.2018.00581"},{"key":"2382_CR31","doi-asserted-by":"crossref","unstructured":"Tong, B., Klinkigt, M., Chen, J., Cui, X., Kong, Q., Murakami, T., & Kobayashi, Y. (2018). Adversarial zero-shot learning with semantic augmentation. In Thirty-second AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11886"},{"issue":"4","key":"2382_CR32","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1109\/TIP.2018.2878970","volume":"28","author":"L Wu","year":"2018","unstructured":"Wu, L., Wang, Y., & Shao, L. (2018). Cycle-consistent deep generative hashing for cross-modal retrieval. IEEE Transactions on Image Processing, 28(4), 1602\u20131612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2382_CR33","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., & Erhan, D. (2016). Domain separation networks. In Advances in neural information processing systems (pp. 343\u2013351)."},{"key":"2382_CR34","unstructured":"Yosinski, J., Clune, J., Bengio, Y., & Lipson. H. (2014). How transferable are features in deep neural networks? In Advances in neural information processing systems (pp. 3320\u20133328."},{"issue":"3","key":"2382_CR35","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"JC Pereira","year":"2013","unstructured":"Pereira, J. C., Coviello, E., Doyle, G., Rasiwasia, N., Lanckriet, G. R. G., Levy, R., et al. (2013). On the role of correlation and abstraction in cross-modal multimedia retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3), 521\u2013535.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2382_CR36","doi-asserted-by":"crossref","unstructured":"Chua, T.-S., 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 Proceedings of the ACM international conference on image and video retrieval (pp. 1\u20139).","DOI":"10.1145\/1646396.1646452"},{"key":"2382_CR37","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"issue":"12","key":"2382_CR38","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon, D. R., Szedmak, S., & Shawe-Taylor, J. (2004). Canonical correlation analysis: An overview with application to learning methods. Neural Computation, 16(12), 2639\u20132664.","journal-title":"Neural Computation"},{"key":"2382_CR39","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 Proceedings of the IEEE international conference on computer vision (pp. 2088\u20132095).","DOI":"10.1109\/ICCV.2013.261"},{"issue":"6","key":"2382_CR40","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TCSVT.2013.2276704","volume":"24","author":"X Zhai","year":"2014","unstructured":"Zhai, X., Peng, Y., & Xiao, J. (2014). Learning cross-media joint representation with sparse and semisupervised regularization. IEEE Transactions on Circuits and Systems for Video Technology, 24(6), 965\u2013978.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2382_CR41","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In The 28th international conference on machine learning (ICML) (pp. 689\u2013696)."},{"key":"2382_CR42","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579\u20132605.","journal-title":"Journal of Machine Learning Research"}],"container-title":["Wireless Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11276-020-02382-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11276-020-02382-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11276-020-02382-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T15:38:33Z","timestamp":1720021113000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11276-020-02382-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,5]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["2382"],"URL":"https:\/\/doi.org\/10.1007\/s11276-020-02382-4","relation":{},"ISSN":["1022-0038","1572-8196"],"issn-type":[{"value":"1022-0038","type":"print"},{"value":"1572-8196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,5]]},"assertion":[{"value":"5 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}