{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:41Z","timestamp":1742914121482,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442094"},{"type":"electronic","value":"9783031442100"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44210-0_28","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"344-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Caption with\u00a0Prior Knowledge Graph and\u00a0Heterogeneous Attention"],"prefix":"10.1007","author":[{"given":"Junjie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenfeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2017","unstructured":"Baltrusaitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41, 423\u2013443 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: Computer Science (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Mori, Y., Fukui, H., Hirakawa, T., Nishiyama, J., Fujiyoshi, H.: Attention neural baby talk: captioning of risk factors while driving. In: 2019 IEEE Intelligent Transportation Systems Conference - ITSC (2019)","DOI":"10.1109\/ITSC.2019.8917187"},{"key":"28_CR4","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention, pp. 2048\u20132057 (2015)"},{"key":"28_CR5","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: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning (2016)","DOI":"10.1109\/CVPR.2017.131"},{"key":"28_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Computer Science (2014)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Shetty, R., Rohrbach, M., Hendricks, L.A., Fritz, M., Schiele, B.: Speaking the same language: matching machine to human captions by adversarial training. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.445"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chan, A.B.: Describing like humans: on diversity in image captioning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.00432"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Gan, C., Gan, Z., He, X., Gao, J., Deng, L.: Stylenet: generating attractive visual captions with styles. In: IEEE Conference on Computer Vision & Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.108"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Yao, P., Li, J., Lu, H.: Mscap: multi-style image captioning with unpaired stylized text. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.00433"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Training efficient saliency prediction models with knowledge distillation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 512\u2013520 (2019)","DOI":"10.1145\/3343031.3351089"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"28_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"28_CR15","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (2014)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Gan, Z., Gan, C., He, X., Pu, Y., Deng, L.: Semantic compositional networks for visual captioning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"28_CR17","doi-asserted-by":"crossref","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: Computer Science, pp. 203\u2013212 (2015)","DOI":"10.1109\/CVPR.2016.29"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, M., Liu, D., Hu, Z., Zhang, H.: More grounded image captioning by distilling image-text matching model. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"28_CR20","unstructured":"Hu, Z., Yang, Z., Liang, X., Salakhutdinov, R., Xing, E.P.: Toward controlled generation of text (2017)"},{"issue":"3","key":"28_CR21","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.3390\/s23031286","volume":"23","author":"N Moratelli","year":"2023","unstructured":"Moratelli, N., Barraco, M., Morelli, D., Cornia, M., Baraldi, L., Cucchiara, R.: Fashion-oriented image captioning with external knowledge retrieval and fully attentive gates. Sensors 23(3), 1286 (2023)","journal-title":"Sensors"},{"issue":"21","key":"28_CR22","doi-asserted-by":"publisher","first-page":"8376","DOI":"10.3390\/s22218376","volume":"22","author":"S Javanmardi","year":"2022","unstructured":"Javanmardi, S., Latif, A.M., Sadeghi, M.T., Jahanbanifard, M., Bonsangue, M., Verbeek, F.J.: Caps captioning: a modern image captioning approach based on improved capsule network. Sensors 22(21), 8376 (2022)","journal-title":"Sensors"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Mathews, L.X.A., He, X.: Semstyle: learning to generate stylised image captions using unaligned text. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8591\u20138600 (2019)","DOI":"10.1109\/CVPR.2018.00896"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Xie, L., Mathews, A.P., He, X.: Senticap: generating image descriptions with sentiments. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 664\u2013676 (2016)","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Ward, T., Papineni, K., Roukos, S., 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 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"28_CR27","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":"28_CR28","unstructured":"Webber, B., Byron, D.: Proceedings of the 2004 ACL Workshop on Discourse Annotation (2004)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"28_CR30","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":"28_CR31","doi-asserted-by":"crossref","unstructured":"Batra, D., Aneja, J., Agrawal, H., Schwing, A.: Sequential latent spaces for modeling the intention during diverse image captioning. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00436"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Aneja, J., Wang, L., Schwing, A.G., Forsyth, D.: Fast, diverse and accurate image captioning guided by part-of-speech. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01095"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44210-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:06:51Z","timestamp":1695283611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44210-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442094","9783031442100"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44210-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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)"}},{"value":"type of other papers accepted  : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}