{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T09:01:07Z","timestamp":1725872467912},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319488950"},{"type":"electronic","value":"9783319488967"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-48896-7_23","type":"book-chapter","created":{"date-parts":[[2016,11,26]],"date-time":"2016-11-26T14:18:05Z","timestamp":1480169885000},"page":"231-240","source":"Crossref","is-referenced-by-count":3,"title":["Improving Image Captioning by Concept-Based Sentence Reranking"],"prefix":"10.1007","author":[{"given":"Xirong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,27]]},"reference":[{"key":"23_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification using deep convolutional neural networks. In: Proceedings of NIPS (2012)"},{"key":"23_CR2","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of NIPS (2014)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"23_CR4","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: Proceedings of ICLR (2015)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"7","key":"23_CR6","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMM.2009.2030598","volume":"11","author":"X Li","year":"2009","unstructured":"Li, X., Snoek, C., Worring, M.: Learning social tag relevance by neighbor voting. IEEE Trans. Multimedia 11(7), 1310\u20131322 (2009)","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"23_CR7","first-page":"853","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. Int. Res. 47(1), 853\u2013899 (2013)","journal-title":"J. Artif. Int. Res."},{"key":"23_CR8","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. TACL 2, 67\u201378 (2014)","journal-title":"TACL"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. CoRR abs\/1405.0312 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Li, X., Lan, W., Dong, J., Liu, H.: Adding Chinese captions to images. In: Proceedings of ICMR (2016)","DOI":"10.1145\/2911996.2912049"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R., Deng, L., Dollar, P., Gao, J., He, X., Mitchell, M., Platt, J., Zitnick, L., Zweig, G.: From captions to visual concepts and back. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"23_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-319-10593-2_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Wang, L., Hodosh, M., Hockenmaier, J., Lazebnik, S.: Improving image-sentence embeddings using large weakly annotated photo collections. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 529\u2013545. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10593-2_35"},{"key":"23_CR13","unstructured":"Li, X., Jin, Q., Liao, S., Liang, J., He, X., Huo, Y., Lan, W., Xiao, B., Lu, Y., Xu, J.: RUC-tencent at ImageCLEF 2015: concept detection, localization and sentence generation. In: CLEF Working Notes (2015)"},{"key":"23_CR14","unstructured":"Gilbert, A., Piras, L., Wang, J., Yan, F., Dellandrea, E., Gaizauskas, R., Villegas, M., Mikolajczyk, K.: Overview of the ImageCLEF 2015 scalable image annotation. In: CLEF Working Notes, Localization and Sentence Generation Task (2015)"},{"key":"23_CR15","unstructured":"Frome, A., Corrado, G., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: DeViSE: a deep visual-semantic embedding model. In: Proceedings of NIPS (2013)"},{"key":"23_CR16","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS (2013)"},{"key":"23_CR17","unstructured":"Dong, J., Li, X., Snoek, C.G.M.: Word2VisualVec: cross-media retrieval by visual feature prediction. CoRR abs\/1604.06838 (2016)"},{"key":"23_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-319-10584-0_22","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Agrawal","year":"2014","unstructured":"Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 329\u2013344. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10584-0_22"},{"issue":"3","key":"23_CR20","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. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., Liao, S., Lan, W., Du, X., Yang, G.: Zero-shot image tagging by hierarchical semantic embedding. In: Proceedings of SIGIR (2015)","DOI":"10.1145\/2766462.2767773"},{"issue":"1","key":"23_CR22","first-page":"14:1","volume":"49","author":"X Li","year":"2016","unstructured":"Li, X., Uricchio, T., Ballan, L., Bertini, M., Snoek, C.G.M., Del Bimbo, A.: Socializing the semantic gap: a comparative survey on image tag assignment, refinement and retrieval. ACM Comput. Surv. 49(1), 14:1\u201314:39 (2016)","journal-title":"ACM Comput. Surv."},{"key":"23_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/978-3-319-24027-5_45","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"M Villegas","year":"2015","unstructured":"Villegas, M., et al.: General overview of ImageCLEF at the CLEF 2015 Labs. In: Mothe, J., Savoy, J., Kamps, J., Pinel-Sauvagnat, K., Jones, G.J.F., SanJuan, E., Cappellato, L., Ferro, N. (eds.) CLEF 2015. LNCS, vol. 9283, pp. 444\u2013461. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-24027-5_45"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing - PCM 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48896-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,27]],"date-time":"2020-09-27T14:37:31Z","timestamp":1601217451000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48896-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319488950","9783319488967"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48896-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}