{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:03:51Z","timestamp":1742911431093,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811619632"},{"type":"electronic","value":"9789811619649"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-981-16-1964-9_25","type":"book-chapter","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T21:06:58Z","timestamp":1620248818000},"page":"312-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Knowledge Embedding to Improve the Description for Image Captioning"],"prefix":"10.1007","author":[{"given":"Dandan","family":"Song","sequence":"first","affiliation":[]},{"given":"Cuimei","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Huan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Lejian","family":"Liao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,6]]},"reference":[{"key":"25_CR1","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787\u20132795 (2013)"},{"key":"25_CR2","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"25_CR3","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). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"25_CR4","unstructured":"Li, S., Kulkarni, G., Berg, T.L., et al.: Composing simple image descriptions using web-scale n-grams. In: Proceedings of the Fifteenth Conference on Computational Natural Language Learning, pp. 220\u2013228 (2011)"},{"issue":"12","key":"25_CR5","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":"25_CR6","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"25_CR7","unstructured":"Xu, J., Gavves, E., Fernando, B., Tuytelaars, T.: Guiding the long-short term memory model for image caption generation. In: IEEE International Conference on Computer Vision (2016)"},{"key":"25_CR8","unstructured":"Cheng, W., Yang, H., Bartz, C., Meinel, C.: Image captioning with deep bidirectional LSTMs. In: ACM on Multimedia Conference (2016)"},{"key":"25_CR9","unstructured":"Mao, J., Wei, X., Yi, Y., Jiang, W., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: ICLR (2015)"},{"issue":"8","key":"25_CR10","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":"25_CR11","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: ICML (2015)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"25_CR13","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1162\/tacl_a_00063","volume":"5","author":"N Mrk\u0161i\u0107","year":"2017","unstructured":"Mrk\u0161i\u0107, N., Vuli\u0107, I., S\u00e9aghdha, D.\u00d3., et al.: Semantic specialization of distributional word vector spaces using monolingual and cross-lingual constraints. Trans. Assoc. Comput. Linguist. 5, 309\u2013324 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"25_CR14","unstructured":"Ahn, S., Choi, H., P\u00e4rnamaa, T., et al.: A neural knowledge language model. arXiv preprint arXiv:1608.00318 (2016)"},{"key":"25_CR15","unstructured":"Ghaddar, A., Langlais, P.: Robust lexical features for improved neural network named-entity recognition. arXiv preprint arXiv:1806.03489 (2018)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Vashishth, S., Joshi, R., Prayaga, S.S., et al.: RESIDE: improving distantly-supervised neural relation extraction using side information. arXiv preprint arXiv:1812.04361 (2018)","DOI":"10.18653\/v1\/D18-1157"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., et al.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., et al.: Attention on attention for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"25_CR19","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: 26th International Conference on Advanced Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: RC-NET: a general framework for incorporating knowledge into word representations. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pp. 1219\u20131228. ACM (2014)","DOI":"10.1145\/2661829.2662038"},{"key":"25_CR21","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"25_CR22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: 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":"25_CR24","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"25_CR25","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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR26","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 (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"25_CR27","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":"25_CR28","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"25_CR29","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"25_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"25_CR33","unstructured":"Vendrov, I., Kiros, R., Fidler, S., et al.: Order-embeddings of images and language. arXiv preprint arXiv:1511.06361 (2015)"},{"key":"25_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"25_CR35","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 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.131"}],"container-title":["Communications in Computer and Information Science","Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-1964-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T21:11:23Z","timestamp":1620249083000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-1964-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811619632","9789811619649"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-1964-9_25","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCKS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Knowledge Graph and Semantic Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanchang","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccks2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sigkg.cn\/ccks2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"173","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}