{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:53:48Z","timestamp":1726062828888},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367077"},{"type":"electronic","value":"9783030367084"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36708-4_2","type":"book-chapter","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T15:24:22Z","timestamp":1576164262000},"page":"16-29","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Learning for Cross-Modal Retrieval with Wasserstein Distance"],"prefix":"10.1007","author":[{"given":"Qingrong","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Youcai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Li, L., Tang, S., Deng, L., Zhang, Y., Tian, Q.: Image caption with global-local attention. In: AAAI, pp. 4133\u20134139, San Francisco (2017)","DOI":"10.1609\/aaai.v31i1.11236"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan\u2009++: realistic image synthesis with stacked generative adversarial networks. arXiv preprint arXiv:1710.10916 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"12","key":"2_CR3","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"D Hardoon","year":"2004","unstructured":"Hardoon, D., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639\u20132664 (2004)","journal-title":"Neural Comput."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Li, D., Dimitrova, N., Li, M., Sethi, I.K.: Multimedia content processing through cross-modal association. In: Proceedings of ACM Multimedia, pp. 604\u2013611 (2003)","DOI":"10.1145\/957142.957143"},{"issue":"2","key":"2_CR5","first-page":"449","volume":"47","author":"Y Wei","year":"2017","unstructured":"Wei, Y., et al.: Cross-modal retrieval with CNN visual features: a new baseline. IEEE Trans. Cybern. 47(2), 449\u2013460 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"2_CR6","unstructured":"Peng, Y., Huang X., Qi J.: Cross-media shared representation by hierarchical learning with multiple deep networks. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 3846\u20133853, New York (2016)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., Hanjalic, A., Shen, H.T.: Adversarial cross-modal retrieval. In: Proceedings of ACM Multimedia, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Huang, X., Peng, Y., Yuan, M.: MHTN: modal-adversarial hybrid transfer network for cross-modal retrieval. IEEE Trans. Cybern. (2018)","DOI":"10.1109\/TCYB.2018.2879846"},{"issue":"6","key":"2_CR9","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.: Learning cross-media joint representation with sparse and semi-supervised regularization. IEEE Trans. Circuits Syst. Video Technol. 24(6), 965\u2013978 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"2_CR10","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1109\/TPAMI.2015.2505311","volume":"38","author":"K Wang","year":"2015","unstructured":"Wang, K., He, R., Wang, L., Wang, W., Tan, T.: Joint feature selection and subspace learning for cross-modal retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2010\u20132023 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR11","unstructured":"Ciresan, D.C., Meier, U., Masci, J., Maria Gambardella, L., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification. In: Proceedings of International Joint Conference on Artificial Intelligence, vol.22, issue 1, p. 1237, (2011)"},{"key":"2_CR12","unstructured":"Zheng, L., Yang, Y., Hauptmann A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)"},{"key":"2_CR13","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, X., Peng, Y.: Fine-grained image classification via combining vision. and language. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5994\u20136022 (2017)","DOI":"10.1109\/CVPR.2017.775"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Huang, X., Peng, Y., Yuan, M.: Cross-modal Common Representation Learning by Hybrid Transfer Network. arXiv preprint arXiv:1706.00153 (2017)","DOI":"10.24963\/ijcai.2017\/263"},{"key":"2_CR16","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In Advances in neural information processing systems, pp. 2672\u20132680 (2014)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167\u20137176 (2017)","DOI":"10.1109\/CVPR.2017.316"},{"issue":"1","key":"2_CR18","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096\u20132030 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Xu, X., He, L., Lu, H., Gao, L., Ji, Y.: Deep adversarial metric learning for cross-modal retrieval. World Wide Web, pp. 1\u201316, (2018)","DOI":"10.1007\/s11280-018-0541-x"},{"key":"2_CR20","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein gan. arXiv preprint arXiv:1701.07875 (2017)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Shen, J., Qu, Y., Zhang, W., Yu, Y.: Wasserstein Distance Guided Representation Learning for Domain Adaptation. arXiv preprint arXiv:1707.01217 (2017)","DOI":"10.1609\/aaai.v32i1.11784"},{"issue":"7","key":"2_CR22","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926\u2013930 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"2_CR23","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767\u20135777 (2017)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Costa Pereira, J., Coviello, E., Doyle, G., Lanckriet, G.R.G., Levy, R., et al.: A new approach to cross-modal multimedia. In: Proceeding of ACM International Conference on Multimedia, pp. 251\u2013260 (2010)","DOI":"10.1145\/1873951.1873987"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from National University of Singapore. In: Proceedings of ACM International Conference on image and video retrieval, p. 48 (2009)","DOI":"10.1145\/1646396.1646452"},{"issue":"6","key":"2_CR26","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1109\/TPAMI.2011.190","volume":"34","author":"SJ Hwang","year":"2012","unstructured":"Hwang, S.J., Grauman, K.: Reading between the lines: object localization using implicit cues from image tags. IEEE Trans. Pattern Anal. Mach. Intell. 34(6), 1145\u20131158 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Sharma, A., Kumar, A., Daume, H., Jacobs, D.W.: Generalized multiview analysis: a discriminative latent space. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2160\u20132167 (2012)","DOI":"10.1109\/CVPR.2012.6247923"},{"issue":"9","key":"2_CR28","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TCSVT.2017.2705068","volume":"28","author":"Y Peng","year":"2018","unstructured":"Peng, Y., Huang, X., Zhao, Y.: An overview of cross-media retrieval: concepts, methodologies, benchmarks and challenges. IEEE Trans. Circuits Syst. Video Technol. 28(9), 2372\u20132385 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"2_CR29","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"C Pereira","year":"2013","unstructured":"Pereira, C., Coviello, E., Doyle, G., Rasiwasia, N., Lanckriet, G.R., Levy, R., et al.: On the role of correlation and abstraction in cross-modal multimedia retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 521\u2013535 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wang, S., Huang, Q.: Online asymmetric similarity learning for cross-modal retrieval. In Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4269\u20134278, (2017)","DOI":"10.1109\/CVPR.2017.424"},{"key":"2_CR31","unstructured":"Kumar, S., Udupa, R.: Learning hash functions for cross-view similarity search. In: Twenty-Second International Joint Conference on Artificial Intelligence (2011)"},{"key":"2_CR32","unstructured":"Wang, D., Gao, X., Wang, X., He, L.. Semantic topic multimodal hashing for cross-media retrieval. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Feng, F., Wang, X., Li, R.: Cross-modal retrieval with correspondence auto-encoder. In: Proceeding on ACM International Conference on Multimedia, pp. 7\u201316 (2014)","DOI":"10.1145\/2647868.2654902"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Jiang, Q.Y., Li, W.J.: Deep cross-modal hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3232\u20133240 (2017)","DOI":"10.1109\/CVPR.2017.348"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, L., Ma, B., Li, G., Huang, Q., Tian, Q.: Multi-networks joint learning for large-scale cross-modal retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 907\u2013915 (2017)","DOI":"10.1145\/3123266.3123317"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36708-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T09:45:01Z","timestamp":1665222301000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36708-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367077","9783030367084"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36708-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}