{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T04:13:57Z","timestamp":1750997637167,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700953"},{"type":"electronic","value":"9783319700960"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-70096-0_66","type":"book-chapter","created":{"date-parts":[[2017,10,25]],"date-time":"2017-10-25T01:33:18Z","timestamp":1508895198000},"page":"642-652","source":"Crossref","is-referenced-by-count":0,"title":["Learning Image Representation Based on Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Zhanbo","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,26]]},"reference":[{"key":"66_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/BFb0015989","volume-title":"Audio- and Video-based Biometric Person Authentication","author":"T Poggio","year":"1997","unstructured":"Poggio, T.: Image representations for visual learning. In: Big\u00fcn, J., Chollet, G., Borgefors, G. (eds.) AVBPA 1997. LNCS, vol. 1206, pp. 143\u2013143. Springer, Heidelberg (1997). doi: 10.1007\/BFb0015989"},{"key":"66_CR2","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A., others: Video google: a text retrieval approach to object matching in videos. In: International Conference on Computer Vision, pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"66_CR3","unstructured":"Schmid, C., Patrick, P.: Aggregating local descriptors into a compact image representation. In: Computer Vision and Pattern Recognition, pp. 3304\u20133311 (2010)"},{"key":"66_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15561-1_11"},{"key":"66_CR5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"66_CR6","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132323 (1998)","journal-title":"Proc. IEEE"},{"key":"66_CR7","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., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: 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). doi: 10.1007\/978-3-642-15561-1_2"},{"key":"66_CR8","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Baby talk: Understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"66_CR9","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: Proceedings of the 31st International Conference on Machine Learning (ICML 2014), pp. 595\u2013603 (2014)"},{"key":"66_CR10","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain images with multimodal recurrent neural networks. arXiv Preprint arXiv:1410.1090 (2014)"},{"key":"66_CR11","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39, 652\u2013663 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"66_CR12","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"66_CR13","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient Estimation of Word Representations in Vector Space. arXiv Preprint arXiv:1301.3781 (2013)"},{"key":"66_CR14","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"66_CR15","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 (2012)"},{"key":"66_CR16","unstructured":"Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv Preprint arXiv:1409.1556 (2014)"},{"key":"66_CR17","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Springenberg, J.T., Brox, T.: Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1538\u20131546 (2015)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"66_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"66_CR19","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"66_CR20","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"66_CR21","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1109\/34.955109","volume":"23","author":"JZ Wang","year":"2001","unstructured":"Wang, J.Z., Li, J., Wiederhold, G.: SIMPLIcity: semantics-sensitive integrated matching for picture libraries. IEEE Trans. Pattern Anal. Mach. Intell. 23, 947\u2013963 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70096-0_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T18:37:57Z","timestamp":1750963077000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70096-0_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700953","9783319700960"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70096-0_66","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}