{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:32:03Z","timestamp":1742913123275,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811073045"},{"type":"electronic","value":"9789811073052"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-981-10-7305-2_42","type":"book-chapter","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T16:16:54Z","timestamp":1512663414000},"page":"490-499","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Key Words Extraction and Semantic-Based Image Retrieval on RNNs"],"prefix":"10.1007","author":[{"given":"Lifei","family":"Han","sequence":"first","affiliation":[]},{"given":"Guanghua","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,8]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., Zitnick, C.L.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2422\u20132431 (2014)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"42_CR2","unstructured":"Xu, K., Ba, J., Kiros, R.: Show, attend and tell: neural image caption generation with visual attention. Computer Science, pp. 2048\u20132057 (2015)"},{"key":"42_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates Inc. (2012)"},{"key":"42_CR4","unstructured":"Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and Understanding Recurrent Networks (2015)"},{"issue":"6","key":"42_CR5","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafit, M., Burget, L.: Recurrent neural network based language model. In: Conference of the International Speech Communication Association, Interspeech 2010, pp. 1045\u20131048, Makuhari, Chiba, Japan, DBLP, September 2010","DOI":"10.21437\/Interspeech.2010-343"},{"issue":"4","key":"42_CR7","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2014","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664\u2013676 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"42_CR8","first-page":"1107","volume":"3","author":"K Barnard","year":"2003","unstructured":"Barnard, K., Duygulu, P., Forsyth, D.: Matching words and pictures. J. Mach. Learn. Res. 3(2), 1107\u20131135 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"42_CR9","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V.: BabyTalk: understanding and generating simple image descriptions. In: IEEE Computer Vision and Pattern Recognition, pp. 1601\u20131608 (2013)"},{"key":"42_CR10","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). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"issue":"1","key":"42_CR11","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11263-015-0840-y","volume":"119","author":"V Ordonez","year":"2016","unstructured":"Ordonez, V., Han, X., Kuznetsova, P.: Large scale retrieval and generation of image descriptions. Int. J. Comput. Vis. 119(1), 46\u201359 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Socher, R., Li, F.F.: Connecting modalities: semi-supervised segmentation and annotation of images using unaligned text corpora. In: IEEE Computer Vision and Pattern Recognition, pp. 966\u2013973 (2010)","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Socher, R., Karpathy, A., Le, Q.V.: Grounded compositional semantics for finding and describing images with sentences. NLP Stanford Edu. (2013)","DOI":"10.1162\/tacl_a_00177"},{"key":"42_CR14","unstructured":"Kuznetsova, P., Ordonez, V., Berg, A.: Generalizing image captions for image-text parallel corpus. In: Meeting of the Association for Computational Linguistics, pp. 790\u2013796 (2013)"},{"key":"42_CR15","unstructured":"Jia, Y., Salzmann, M., Darrell, T.: Learning cross-modality similarity for multinomial data. In: IEEE Computer Society International Conference on Computer Vision, pp. 2407\u20132414 (2011)"},{"key":"42_CR16","unstructured":"Mao, J.: Explain Images with Multimodal Recurrent Neural Networks. Computer Science (2014)"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S.: Show and tell: a neural image caption generator, pp. 3156\u20133164 (2014)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Computer Vision and Pattern Recognition, vol. 39, pp. 85\u201391 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"issue":"8","key":"42_CR19","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. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"42_CR20","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models. Computer Science (2014)"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Fang, H., Platt, J.C., Zitnick, C.L.: From captions to visual concepts and back, pp. 1473\u20131482 (2014)","DOI":"10.1109\/CVPR.2015.7298754"},{"issue":"4","key":"42_CR22","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/0893-6080(88)90007-X","volume":"1","author":"PJ Werbos","year":"1988","unstructured":"Werbos, P.J.: Generalization of backpropagation with application to a recurrent gas market model. Neural Netw. 1(4), 339\u2013356 (1988)","journal-title":"Neural Netw."},{"key":"42_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science (2014)"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S.: Microsoft COCO: Common Objects in Context, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. NLP CS Illinois Edu. (2014)","DOI":"10.1162\/tacl_a_00166"}],"container-title":["Communications in Computer and Information Science","Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-7305-2_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:27:21Z","timestamp":1709832441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-10-7305-2_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9789811073045","9789811073052"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-7305-2_42","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"8 December 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Chinese Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cccv2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ccf-cccv.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}