{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T00:03:04Z","timestamp":1792886584290,"version":"4.5.0"},"reference-count":101,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,6,9]],"date-time":"2018-06-09T00:00:00Z","timestamp":1528502400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61603214"],"award-info":[{"award-number":["61603214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2015PF009"],"award-info":[{"award-number":["ZR2015PF009"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s00371-018-1566-y","type":"journal-article","created":{"date-parts":[[2018,6,9]],"date-time":"2018-06-09T15:41:47Z","timestamp":1528558907000},"page":"445-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":72,"title":["A survey on deep neural network-based image captioning"],"prefix":"10.1007","volume":"35","author":[{"given":"Xiaoxiao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3870-5551","authenticated-orcid":false,"given":"Qingyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,6,9]]},"reference":[{"key":"1566_CR1","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s10791-007-9031-y","volume":"10","author":"R Yan","year":"2007","unstructured":"Yan, R., Hauptmann, A.G.: A review of text and image retrieval approaches for broadcast news video. Inf. Retr. 10, 445\u2013484 (2007)","journal-title":"Inf. Retr."},{"key":"1566_CR2","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"Bernardi, R., Cakici, R., Elliott, D., Erdem, A., Erdem, E., Ikizler-Cinbis, N., Keller, F., Muscat, A., Plank, B.: Automatic description generation from images: a survey of models, datasets, and evaluation measures. J. Artif. Intell. Res. 55, 409\u2013442 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"1566_CR3","first-page":"71","volume":"49","author":"Y Aloimonos","year":"2016","unstructured":"Aloimonos, Y., Aloimonos, Y., Aloimonos, Y.: Computer vision and natural language processing: recent approaches in multimedia and robotics. ACM Comput. Surv. 49, 71 (2016)","journal-title":"ACM Comput. Surv."},{"key":"1566_CR4","unstructured":"Kuznetsova, P., Ordonez, V., Berg, A.C., Berg, T.L., Choi, Y.: Collective generation of natural image descriptions. In: Meeting of the Association for Computational Linguistics: Long Papers, Korea, Jeju Island, pp. 359\u2013368 (2012)"},{"key":"1566_CR5","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: DeViSE: a deep visual-semantic embedding model. In: International Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, Lake Tahoe, pp. 2121\u20132129 (2013)"},{"key":"1566_CR6","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. 2, 207\u2013218 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"1566_CR7","first-page":"2949","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep Boltzmann machines. J. Mach. Learn. Res. 15, 2949\u20132980 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1566_CR8","unstructured":"Norouzi, M., Mikolov, T., Bengio, S., Singer, Y., Shlens, J., Frome, A., Corrado, G.S., Dean, J.: Zero-shot learning by convex combination of semantic embeddings. In: International Conference on Learning Representations ICLR2014, Banff, Canada (2014)"},{"key":"1566_CR9","doi-asserted-by":"publisher","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":"1566_CR10","first-page":"1143","volume":"25","author":"V Ordonez","year":"2012","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2Text: describing images using 1 million captioned photographs. Adv. Neural Inf. Process. Syst. 25, 1143\u20131151 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1566_CR11","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"1566_CR12","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: 11th European Conference on Computer Vision (ECCV 2010), Crete, Greece, 2010, pp. 15\u201329 (2010)"},{"key":"1566_CR13","doi-asserted-by":"crossref","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Baby talk: understanding and generating simple image descriptions. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, IEEE, Colorado Springs, CO, pp. 1601\u20131608 (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"1566_CR14","unstructured":"Li, S., Kulkarni, G., Berg, L.B., Berg, C.A., Choi, Y.: Composing simple image descriptions using web-scale N-grams. In: 15th Conference on Computational Natural Language Learning, Portland, USA, 2011, pp. 220\u2013228 (2011)"},{"key":"1566_CR15","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R.K., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J.C., Zitnick, C.L., Zweig, G.: From captions to visual concepts and back. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Boston, MA, USA, pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"1566_CR16","unstructured":"Maron, O., Lozano-Perez, T.: A framework for multiple-instance learning. In: 11th Annual Conference on Neural Information Processing Systems, NIPS 1997, Neural information processing systems foundation, Denver, CO, pp. 570\u2013576 (1998)"},{"key":"1566_CR17","unstructured":"Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: International Conference on Neural Information Processing Systems, MIT, Vancouver, British Columbia, Canada, pp. 1417\u20131424 (2005)"},{"key":"1566_CR18","unstructured":"Song, H.O., Girshick, R., Jegelka, S., Mairal, J., Harchaoui, Z., Darrell, T.: On learning to localize objects with minimal supervision. In: 2016 International Conference on Machine Learning, Beijing, China, pp. 1611\u20131619 (2014)"},{"key":"1566_CR19","first-page":"391","volume-title":"13th European Conference on Computer Vision","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge Boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) 13th European Conference on Computer Vision, pp. 391\u2013405. Springer, Zurich (2014)"},{"key":"1566_CR20","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"1566_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, Curran Associates Inc, Lake Tahoe, pp. 1097\u20131105 (2012)"},{"key":"1566_CR22","unstructured":"D.J., D.W., S.R., J.L. L., L. Kai, F. Li, ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Miami, Florida, USA, pp. 248\u2013255 (2009)"},{"key":"1566_CR23","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014), OH, USA, 2014, pp. 580\u2013587 (2014)"},{"key":"1566_CR24","doi-asserted-by":"crossref","unstructured":"van de Sande K.E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: Segmentation as selective search for object recognition. In: 2011 International Conference on Computer Vision, IEEE, Barcelona, Spain, pp. 1879\u20131886 (2011)","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"1566_CR25","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. 37, 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal."},{"key":"1566_CR26","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1566_CR27","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1566_CR28","unstructured":"Zhou, L., Hovy, E.: Template-filtered headline summarization. In: The Proceedings of The ACL Workshop Text Summarization Branches Out, pp. 56\u201360 (2004)"},{"key":"1566_CR29","doi-asserted-by":"crossref","unstructured":"Channarukul, S., Mcroy, S.W., Ali, S.S.: DOGHED: a template-based generator for multimodal dialog systems targeting heterogeneous devices. In: Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology (2003)","DOI":"10.3115\/1073427.1073430"},{"key":"1566_CR30","unstructured":"Chisholm, M., Tadepalli, P.: Learning decision rules by randomized iterative local search. In: Nineteenth International Conference on Machine Learning, Morgan Kaufmann, pp. 75\u201382 (2002)"},{"key":"1566_CR31","first-page":"9","volume":"4","author":"M White","year":"2002","unstructured":"White, M., Cardie, C.: Selecting sentences for multidocument summaries using randomized local search. Proc. ACL Summ. Workshop 4, 9\u201318 (2002)","journal-title":"Proc. ACL Summ. Workshop"},{"key":"1566_CR32","doi-asserted-by":"crossref","unstructured":"Klein, D., Manning, C.D.: Accurate Unlexicalized Parsing. In: Annual Meeting of the Association for Computational Linguistics, Sapporo, Japan, pp. 423\u2013430 (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"1566_CR33","first-page":"39","volume":"22","author":"AL Berger","year":"2002","unstructured":"Berger, A.L., Pietra, V.J.D., Pietra, S.A.D.: A maximum entropy approach to natural language processing. Comput. Linguist. 22, 39\u201371 (2002)","journal-title":"Comput. Linguist."},{"key":"1566_CR34","unstructured":"Yang, Y., Teo, C.L., Aloimonos, Y.: Corpus-guided sentence generation of natural images. In: Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Edinburgh, United Kingdom, pp. 444\u2013454 (2011)"},{"key":"1566_CR35","doi-asserted-by":"crossref","unstructured":"Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: Twenty-Fourth AAAI Conference on Artificial Intelligence, AAAI, Atlanta, Georgia, pp. 1306\u20131313 (2010)","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"1566_CR36","unstructured":"Graff, D., Kong, J., Chen, K., Maeda, K.: English Gigaword, 3rd edn. LDC2007T07. Web Download. Linguistic Data consortium, Philadelphia (2007)"},{"key":"1566_CR37","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Jan, C., Khudanpur, S.: Recurrent neural network based language model. In: 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, ISCA, Makuhari, Chiba, Japan, pp. 1045\u20131048 (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"1566_CR38","unstructured":"Boden, M.: A Guide to Recurrent Neural Networks and Backpropagation, Dallas Project Sics Technical Report T Sics (2002)"},{"key":"1566_CR39","unstructured":"Sutskever, I., Martens, J., Hinton, G.: Generating text with recurrent neural networks. In: 28th International Conference on Machine Learning, ICML 2011, DBLP, Bellevue, Washington, USA, pp. 1017\u20131024 (2011)"},{"key":"1566_CR40","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"1566_CR41","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, IEEE, Vancouver, BC, Canada, pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"1566_CR42","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1566_CR43","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Association for Computational Linguistics (ACL), Doha, Qatar, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1566_CR44","unstructured":"Mitchell, M., Han, X., Dodge, J., Mensch, A., Goyal, A., Berg, A., Yamaguchi, K., Berg, T., Stratos, K., Hal Daum\u00e9, I.: Midge: generating image descriptions from computer vision detections. In: Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Avignon, France, pp. 747\u2013756 (2012)"},{"key":"1566_CR45","doi-asserted-by":"crossref","unstructured":"Verma, Y., Gupta, A., Mannem, P., Jawahar, C.V.: Generating image descriptions using semantic similarities in the output space. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Portland, USA, pp. 288\u2013293 (2013)","DOI":"10.1109\/CVPRW.2013.50"},{"key":"1566_CR46","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova, P., Ordonez, V., Berg, T., Choi, Y.: TREETALK: composition and compression of trees for image descriptions. TACL 2, 351\u2013362 (2014)","journal-title":"TACL"},{"key":"1566_CR47","unstructured":"Elliott, D., Keller, F.: Image description using visual dependency representations. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Washington, USA, 2013, pp. 1292\u20131302 (2013)"},{"key":"1566_CR48","unstructured":"Aker, A., Gaizauskas, R.: Generating image descriptions using dependency relational patterns. In: Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Uppsala, Sweden, pp. 1250\u20131258 (2013)"},{"key":"1566_CR49","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B.V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning Phrase Representations using RNN Encoder\u2013Decoder for Statistical Machine Translation, Computer Science, pp. 1724\u20131734. arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1566_CR50","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: International Conference on Neural Information Processing Systems, MIT, Montreal, pp. 3104\u20133112 (2014)"},{"key":"1566_CR51","doi-asserted-by":"crossref","unstructured":"Johnson, R., Zhang, T.: Effective Use of Word Order for Text Categorization with Convolutional Neural Networks, pp. 103\u2013112. Eprint Arxiv arXiv:1412.1058 (2014)","DOI":"10.3115\/v1\/N15-1011"},{"key":"1566_CR52","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural Machine Translation by Jointly Learning to Align and Translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"1566_CR53","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 Computer Vision and Pattern Recognition, IEEE, Boston, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"2017","key":"1566_CR54","first-page":"652","volume":"39","author":"V Oriol","year":"2015","unstructured":"Oriol, V., Alexander, T., Samy, B., Dumitru, E.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans Pattern Anal. 39(2017), 652\u2013663 (2015)","journal-title":"IEEE Trans Pattern Anal."},{"key":"1566_CR55","unstructured":"Ioffe, S., Szegedy, C., Bach, F., Blei, D.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on Machine Learning, ICML 2015, International Machine Learning Society (IMLS), Lille, France, pp. 448\u2013456 (2015)"},{"key":"1566_CR56","doi-asserted-by":"crossref","unstructured":"Lint, R., Liu, S., Yang, M., Li, M., Zhou, M., Li, S.: Hierarchical recurrent neural network for document modeling. In: Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Association for Computational Linguistics (ACL), Lisbon, Portugal, pp. 899\u2013907 (2015)","DOI":"10.18653\/v1\/D15-1106"},{"key":"1566_CR57","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: 31st International Conference on Machine Learning, ICML 2014, International Machine Learning Society (IMLS), Bejing, China, pp. 595\u2013603 (2014)"},{"key":"1566_CR58","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":"1566_CR59","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., Saenko, K.: Long-term recurrent convolutional networks for visual recognition and description In: Computer Vision and Pattern Recognition, IEEE, Boston, MA, USA, p. 677 (2015)","DOI":"10.21236\/ADA623249"},{"key":"1566_CR60","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models, arXiv preprint arXiv:1411.2539 (2014)"},{"key":"1566_CR61","doi-asserted-by":"crossref","unstructured":"Tanti, M., Gatt, A., Camilleri, K.P.: Where to put the Image in an Image Caption Generator, arXiv preprint arXiv:1703.09137 (2017)","DOI":"10.1017\/S1351324918000098"},{"key":"1566_CR62","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient Estimation of Word Representations in Vector Space, arXiv preprint arXiv:1301.3781 (2013)"},{"key":"1566_CR63","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent Neural Network Regularization, arXiv preprint arXiv:1409.2329 (2014)"},{"key":"1566_CR64","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.ins.2016.08.084","volume":"373","author":"MJ Er","year":"2016","unstructured":"Er, M.J., Zhang, Y., Wang, N., Pratama, M.: Attention pooling-based convolutional neural network for sentence modelling. Inf. Sci. 373, 388\u2013403 (2016)","journal-title":"Inf. Sci."},{"key":"1566_CR65","first-page":"2204","volume-title":"Advances in Neural Information Processing Systems","author":"V Mnih","year":"2014","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2204\u20132212. Curran Associates Inc, Red Hook (2014)"},{"key":"1566_CR66","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, Computer Science, pp. 2048\u20132057 (2015)"},{"key":"1566_CR67","unstructured":"Pascanu, R., Gulcehre, C., Cho, K., Bengio, Y.: How to Construct Deep Recurrent Neural Networks, arXiv preprint arXiv:1312.6026 (2014)"},{"key":"1566_CR68","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, NV, USA, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"1566_CR69","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: Computer Vision and Pattern Recognition, IEEE, Boston, MA, USA, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1566_CR70","doi-asserted-by":"crossref","unstructured":"Chen, X., Zitnick, C.L.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Computer Vision and Pattern Recognition (CVPR), IEEE, Boston, MA, USA, pp. 2422\u20132431 (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"1566_CR71","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN), arXiv preprint arXiv:1412.6632 (2014)"},{"key":"1566_CR72","doi-asserted-by":"crossref","unstructured":"Mao, J., Wei, X., Yang, Y., Wang, J., Huang, Z., Yuille, A.L.: Learning like a child: fast novel visual concept learning from sentence descriptions of images In: IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, pp. 2533\u20132541 (2016)","DOI":"10.1109\/ICCV.2015.291"},{"key":"1566_CR73","unstructured":"Lebret, R., Pinheiro, P.O., Collobert, R.: Simple Image Description Generator via a Linear Phrase-Based Approach, arXiv preprint arXiv:1412.8419 (2014)"},{"key":"1566_CR74","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations ofwords and phrases and their compositionality. In: 27th Annual Conference on Neural Information Processing Systems, NIPS 2013, Neural Information Processing Systems Foundation, Lake Tahoe, NV (2013)"},{"key":"1566_CR75","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning, arXiv preprint arXiv:1612.01887 (2016)","DOI":"10.1109\/CVPR.2017.345"},{"key":"1566_CR76","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA 2016, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1566_CR77","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer Sentinel Mixture Models, arXiv preprint arXiv:1609.07843 (2016)"},{"key":"1566_CR78","unstructured":"Johnson, J., Karpathy, A., Li, F.F.: DenseCap: fully convolutional localization networks for dense captioning. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2015, pp. 4565\u20134574 (2015)"},{"issue":"6","key":"1566_CR79","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Machine Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"1566_CR80","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, Computer Science arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1566_CR81","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: DRAW: a recurrent neural network for image generation. In: Computer Science, pp. 1462\u20131471 (2015)"},{"key":"1566_CR82","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. arXiv preprint arXiv:1506.02025 (2015)"},{"key":"1566_CR83","first-page":"1978","volume":"2017","author":"L Yang","year":"2017","unstructured":"Yang, L., Tang, K., Yang, J., Li, L.J.: Dense Captioning with Joint Inference and Visual. Context 2017, 1978\u20131987 (2017)","journal-title":"Context"},{"key":"1566_CR84","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Li, F.F.: A Hierarchical Approach for Generating Descriptive Image Paragraphs, arXiv preprint arXiv:1611.06607 (2016)","DOI":"10.1109\/CVPR.2017.356"},{"key":"1566_CR85","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: Common Objects in Context. arXiv preprint arXiv:1405.0312 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1566_CR86","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2016","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"1566_CR87","unstructured":"Li, J., Luong, M.T., Dan, J.: A Hierarchical Neural Autoencoder for Paragraphs and Documents, pp. 1057\u20131506 (2015)"},{"key":"1566_CR88","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: IBM Research Report Bleu: a method for automatic evaluation of machine translation. In: ACL Proceedings of Annual Meeting of the Association for Computational Linguistics, vol. 30, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1566_CR89","first-page":"376","volume-title":"Meteor Universal: Language Specific Translation Evaluation for Any Target Language","author":"M Denkowski","year":"2014","unstructured":"Denkowski, M., Lavie, A.: Meteor Universal: Language Specific Translation Evaluation for Any Target Language, pp. 376\u2013380. Baltimore, Maryland (2014)"},{"key":"1566_CR90","unstructured":"Flick, C.: ROUGE: A Package for Automatic Evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, Barcelona, Spain, 2004, p. 10 (2004)"},{"key":"1566_CR91","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Computer Vision and Pattern Recognition (CVPR), IEEE, Boston, MA, USA, pp. 4566\u20134575 (2014)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1566_CR92","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., Hengel, A.V.D.: What value do explicit high level concepts have in vision to language problems? In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), Las Vegas, NV, United States, 2016, pp. 203\u2013212 (2016)"},{"key":"1566_CR93","unstructured":"Chen, W., Lucchi, A., Hofmann, T.: Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning, arXiv:1611.05321v1 (2016)"},{"key":"1566_CR94","doi-asserted-by":"crossref","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., Ferm\u00fcller, C.: Image understanding using vision and reasoning through scene description graph. In: Computer Vision and Image Understanding (2017)","DOI":"10.1016\/j.cviu.2017.12.004"},{"key":"1566_CR95","unstructured":"Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 5188\u20135196 (2015)"},{"key":"1566_CR96","unstructured":"Dosovitskiy, A., Brox, T.: Inverting visual representations with convolutional networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), Las Vegas, NV, United States, 2016, pp. 4829\u20134837 (2016)"},{"key":"1566_CR97","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object Detectors Emerge in Deep Scene CNNs, arXiv e-print arXiv:1412.6856 (2014)"},{"key":"1566_CR98","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, arXiv e-print arXiv:1412.3555 (2014)"},{"key":"1566_CR99","unstructured":"Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and Understanding Recurrent Networks, arXiv e-print arXiv:1506.02078 (2015)"},{"key":"1566_CR100","unstructured":"Dong, Y., Su, H., Zhu, J., Zhang, B.: Improving interpretability of deep neural networks with semantic information. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017), Honolulu, Hawaii, USA, 2017, pp. 975\u2013983 (2017)"},{"key":"1566_CR101","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating Videos to Natural Language Using Deep Recurrent Neural Networks, arXiv e-print arXiv:1412.4729 (2014)","DOI":"10.3115\/v1\/N15-1173"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-018-1566-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-018-1566-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-018-1566-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T03:24:31Z","timestamp":1693711471000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-018-1566-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,9]]},"references-count":101,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["1566"],"URL":"https:\/\/doi.org\/10.1007\/s00371-018-1566-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,9]]},"assertion":[{"value":"9 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}