{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T22:25:57Z","timestamp":1759962357616},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811085291"},{"type":"electronic","value":"9789811085307"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-981-10-8530-7_8","type":"book-chapter","created":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T10:04:19Z","timestamp":1519812259000},"page":"75-84","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Bidirectional Multimodal Recurrent Neural Networks with Refined Visual Features for Image Captioning"],"prefix":"10.1007","author":[{"given":"Yanwu","family":"Shu","sequence":"first","affiliation":[]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zechao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,1]]},"reference":[{"issue":"8","key":"8_CR1","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/TPAMI.2016.2608882","volume":"39","author":"J Tang","year":"2017","unstructured":"Tang, J., Shu, X., Qi, Q.J., Li, Z., Wang, M., Yan, S., Jain, R.: Tri-clustered tensor completion for social-aware image tag refinement. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1662\u20131674 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Tang, J., Shu, X., Li, Z., Qi, Q.J., Wang, J.: Generalized deep transfer networks for knowledge propagation in heterogeneous domains. ACM Trans. Multimed. Comput. Commun. Appl. 12(4) (2016)","DOI":"10.1145\/2998574"},{"issue":"12","key":"8_CR3","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.: 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."},{"key":"8_CR4","unstructured":"Yang, Y., Teo, C.L., Daum\u00e9 III, H., Aloimonos, Y.: 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":"8_CR5","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"},{"key":"8_CR6","unstructured":"Kuznetsova, P., Ordonez, V., Berg, A.C., Berg, T.L., Choi, Y.: Collective generation of natural image descriptions. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, vol. 1, pp. 359\u2013368. Association for Computational Linguistics (2012)"},{"issue":"1","key":"8_CR7","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TIP.2016.2624140","volume":"26","author":"Z Li","year":"2017","unstructured":"Li, Z., Tang, J.: Weakly supervised deep matrix factorization for social image understanding. IEEE Trans. Image Process. 26(1), 276\u2013288 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR8","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: ICLR (2015)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"8_CR11","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Wang, C., Yang, H., Bartz, C., Meinel, C.: Image captioning with deep bidirectional LSTMs. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 988\u2013997. ACM (2016)","DOI":"10.1145\/2964284.2964299"},{"issue":"10","key":"8_CR13","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1109\/TPAMI.2015.2400461","volume":"37","author":"Z Li","year":"2015","unstructured":"Li, Z., Liu, J., Tang, J., Lu, H.: Robust structured subspace learning for data representation. IEEE Trans. Pattern Anal. Mach. Intell. 37(10), 2085\u20132098 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR14","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO captions: data collection and evaluation server (2015). arXiv preprint: arXiv:1504.00325"},{"key":"8_CR15","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 Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: 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)","DOI":"10.3115\/1073083.1073135"},{"key":"8_CR17","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments, pp. 228\u2013231 (2005)"},{"key":"8_CR18","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL-2004 Workshop, vol. 8, Barcelona, Spain (2004)"},{"key":"8_CR19","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 (2015)","DOI":"10.1109\/CVPR.2015.7299087"}],"container-title":["Communications in Computer and Information Science","Internet Multimedia Computing and Service"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-8530-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T21:42:32Z","timestamp":1570830152000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-10-8530-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9789811085291","9789811085307"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-8530-7_8","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]}}}