{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:35:24Z","timestamp":1726043724983},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304898"},{"type":"electronic","value":"9783030304904"}],"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\/978-3-030-30490-4_23","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:02:47Z","timestamp":1567969367000},"page":"281-292","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Novel Image Captioning Method Based on Generative Adversarial Networks"],"prefix":"10.1007","author":[{"given":"Yang","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingfei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587. IEEE (2014)","key":"23_CR1","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"crossref","unstructured":"Gan, C., Yang, T., Gong, B.: Learning attributes equals multi-source domain generalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 87\u201397. IEEE (2016)","key":"23_CR2","DOI":"10.1109\/CVPR.2016.17"},{"doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Wang, Z., Mihalcea, R., et al.: Mining semantic affordances of visual object categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4259\u20134267. IEEE (2015)","key":"23_CR3","DOI":"10.1109\/CVPR.2015.7299054"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105. Curran Associates (2012)","key":"23_CR4"},{"unstructured":"Zhou, B., Lapedriza, A., Xiao, J., et al.: Learning deep features for scene recognition using places database. In: Advances in Neural Information Processing Systems, pp. 487\u2013495. Curran Associates (2014)","key":"23_CR5"},{"issue":"11","key":"23_CR6","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., et al.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","key":"23_CR7","DOI":"10.3115\/1073083.1073135"},{"unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372. ACL (2005)","key":"23_CR8"},{"doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634. IEEE (2015)","key":"23_CR9","DOI":"10.1109\/CVPR.2015.7298878"},{"doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575. IEEE (2015)","key":"23_CR10","DOI":"10.1109\/CVPR.2015.7299087"},{"doi-asserted-by":"crossref","unstructured":"Fan, Y., Xu, J., Sun, Y., et al.: Long-term recurrent merge network model for image captioning. In: 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (IC-TAI), pp. 254\u2013259. IEEE (2018)","key":"23_CR11","DOI":"10.1109\/ICTAI.2018.00047"},{"unstructured":"Yang, Y., Teo, C.L., Daum III, H., et al.: Corpus-guided sentence generation of natural images. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 444\u2013454. Association for Computational Linguistics (2011)","key":"23_CR12"},{"issue":"12","key":"23_CR13","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., et al.: BabyTalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Li, S., Kulkarni, G., Berg, T.L., et al.: Composing simple image descriptions using web-scale n-grams. In: Proceedings of the Fifteenth Conference on Computational Natural Language Learning, pp. 220\u2013228. Association for Computational Linguistics (2011)","key":"23_CR14"},{"doi-asserted-by":"crossref","unstructured":"Ushiku, Y., Yamaguchi, M., Mukuta, Y., et al.: Common subspace for model and similarity: Phrase learning for caption generation from images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2668\u20132676. IEEE (2015)","key":"23_CR15","DOI":"10.1109\/ICCV.2015.306"},{"key":"23_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). \n                      https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"doi-asserted-by":"crossref","unstructured":"Mason, R., Charniak, E.: Nonparametric method for data-driven image captioning. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), vol. 2, pp. 592\u2013598 (2014)","key":"23_CR17","DOI":"10.3115\/v1\/P14-2097"},{"key":"23_CR18","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova, P., Ordonez, V., Berg, T.L., et al.: TreeTalk: composition and compression of trees for image descriptions. Trans. Assoc. Comput. Linguist. MIT Press. J. 2, 351\u2013362 (2014)","journal-title":"Trans. Assoc. Comput. Linguist. MIT Press. J."},{"doi-asserted-by":"crossref","unstructured":"Mnih, A., Hinton, G.: Three new graphical models for statistical language modelling. In: Proceedings of the 24th International Conference on Machine Learning, pp. 641\u2013648. ACM (2007)","key":"23_CR19","DOI":"10.1145\/1273496.1273577"},{"doi-asserted-by":"crossref","unstructured":"Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pp. 160\u2013167. Association for Computational Linguistics (2003)","key":"23_CR20","DOI":"10.3115\/1075096.1075117"},{"unstructured":"Mao, J., Xu, W., Yang, Y., et al.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint \n                      arXiv:1412.6632\n                      \n                     (2014)","key":"23_CR21"},{"issue":"8","key":"23_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. MIT Press J. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput. MIT Press J."},{"doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., et al.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134. IEEE (2017)","key":"23_CR23","DOI":"10.1109\/CVPR.2017.632"},{"unstructured":"Reed, S., Akata, Z., Yan, X., et al.: Generative adversarial text to image synthesis. arXiv preprint \n                      arXiv:1605.05396\n                      \n                     (2016)","key":"23_CR24"},{"doi-asserted-by":"crossref","unstructured":"Dai, B., Fidler, S., Urtasun, R., et al.: Towards diverse and natural image descriptions via a conditional GAN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2970\u20132979. IEEE (2017)","key":"23_CR25","DOI":"10.1109\/ICCV.2017.323"},{"issue":"6","key":"23_CR26","first-page":"640","volume":"9","author":"KF Laserson","year":"2005","unstructured":"Laserson, K.F., Thorpe, L.E., Leimane, V., et al.: Speaking the same language: treatment outcome definitions for multidrug-resistant tuberculosis. Int. J. Tuberc. Lung Dis. 9(6), 640\u2013645 (2005)","journal-title":"Int. J. Tuberc. Lung Dis."},{"unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680. Curran Associates (2014)","key":"23_CR27"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE (2016)","key":"23_CR28","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., et al.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649. IEEE (2015)","key":"23_CR30","DOI":"10.1109\/ICCV.2015.303"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint \n                      arXiv:1412.6980\n                      \n                     (2014)","key":"23_CR31"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Text and Time Series"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30490-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:08:26Z","timestamp":1567969706000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30490-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304898","9783030304904"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30490-4_23","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 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}