{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:06:42Z","timestamp":1742933202822,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030394301"},{"type":"electronic","value":"9783030394318"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","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":[[2020]]},"DOI":"10.1007\/978-3-030-39431-8_1","type":"book-chapter","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T13:03:02Z","timestamp":1580475782000},"page":"3-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Image Caption Performance with Linguistic Context"],"prefix":"10.1007","author":[{"given":"Yupeng","family":"Cao","sequence":"first","affiliation":[]},{"given":"Qiu-Feng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,1]]},"reference":[{"key":"1_CR1","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"1_CR2","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., et al.: 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). \nhttps:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"1_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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1_CR4","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"1_CR5","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":"1_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"8","key":"1_CR7","first-page":"1309","volume":"25","author":"J Han","year":"2014","unstructured":"Han, J., Zhang, D., Hu, X., et al.: Background prior-based salient object detection via deep reconstruction residual. IEEE Trans. Circ. Syst. Video Technol. 25(8), 1309\u20131321 (2014)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"6","key":"1_CR8","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1007\/s12559-018-9566-9","volume":"11","author":"X Yang","year":"2018","unstructured":"Yang, X., Huang, K., Zhang, R., et al.: A novel deep density model for unsupervised learning. Cogn. Comput. 11(6), 778\u2013788 (2018)","journal-title":"Cogn. Comput."},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.neucom.2018.01.076","volume":"287","author":"Z Wang","year":"2018","unstructured":"Wang, Z., Ren, J., Zhang, D., et al.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68\u201383 (2018)","journal-title":"Neurocomputing"},{"key":"1_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-030-00563-4_16","volume-title":"Advances in Brain Inspired Cognitive Systems","author":"H Chen","year":"2018","unstructured":"Chen, H., Ding, G., Lin, Z., Guo, Y., Han, J.: Attend to knowledge: memory-enhanced attention network for image captioning. In: Ren, J., et al. (eds.) BICS 2018. LNCS (LNAI), vol. 10989, pp. 161\u2013171. Springer, Cham (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-030-00563-4_16"},{"key":"1_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"Feb","key":"1_CR12","first-page":"1107","volume":"3","author":"K Barnard","year":"2003","unstructured":"Barnard, K., Duygulu, P., Forsyth, D., de Freitas, N., Blei, D.M., Jordan, M.I.: Matching words and pictures. J. Mach. Learn. Res. 3(Feb), 1107\u20131135 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"1_CR13","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., et al.: 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":"1_CR14","unstructured":"Yang, Y., Teo, C.L., Daum 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, July 2011"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: The IEEE Conference on Computer Vision and Pattern Recognition, June 2015","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1_CR16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.patcog.2018.02.004","volume":"79","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Ren, J., Sun, G., et al.: Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement. Pattern Recogn. 79, 65\u201378 (2018)","journal-title":"Pattern Recogn."},{"issue":"8","key":"1_CR17","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."},{"issue":"11","key":"1_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"issue":"2","key":"1_CR19","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1017\/S0272263102002024","volume":"24","author":"NC Ellis","year":"2002","unstructured":"Ellis, N.C.: Frequency effects in language processing: a review with implications for theories of implicit and explicit language acquisition. Stud. Second. Lang. Acquis. 24(2), 143\u2013188 (2002)","journal-title":"Stud. Second. Lang. Acquis."},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Q.-F., Yin, F., Liu, C.-L.: Integrating language model in handwritten Chinese text recognition. In: Proceedings of the 10th ICDAR, pp. 1036\u20131040 (2009)","DOI":"10.1109\/ICDAR.2009.96"},{"issue":"8","key":"1_CR21","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1109\/TPAMI.2011.264","volume":"34","author":"QF Wang","year":"2011","unstructured":"Wang, Q.F., Yin, F., Liu, C.L.: Handwritten Chinese text recognition by integrating multiple contexts. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1469\u20131481 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Dong, H., Wang, W., Huang, K., et al.: Joint multi-label attention networks for social text annotation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 1348\u20131354 (2019)","DOI":"10.18653\/v1\/N19-1136"},{"key":"1_CR23","volume-title":"Speech and Language Processing","author":"D Jurafsky","year":"2008","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing, 2nd edn. Pearson Prentice Hall, Upper Saddle River (2008)","edition":"2"},{"key":"1_CR24","unstructured":"Goodman, J.T.: A bit of progress in language modeling: extended version. Technical report MSR-TR-2001-72, Microsoft Research (2001)"},{"key":"1_CR25","unstructured":"Turian, J., Ratinov, L., Bengio, Y.: Word representations: a simple and general method for semi-supervised learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp. 384\u2013394 (2010)"},{"key":"1_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \narXiv:1409.1556\n\n (2014)"},{"key":"1_CR27","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint \narXiv:1412.6980\n\n (2014)"},{"key":"1_CR29","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"1_CR30","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"},{"key":"1_CR31","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint \narXiv:1810.04805\n\n (2018)"}],"container-title":["Lecture Notes in Computer Science","Advances in Brain Inspired Cognitive Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-39431-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T20:02:46Z","timestamp":1580500966000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-39431-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030394301","9783030394318"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-39431-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"1 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Brain Inspired Cognitive Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bics2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.bics-online.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}