{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:02:05Z","timestamp":1743109325696,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819736225"},{"type":"electronic","value":"9789819736232"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-3623-2_15","type":"book-chapter","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T10:07:45Z","timestamp":1718878065000},"page":"193-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Transformer with Gated-Attention Fusion for News Disaster Image Captioning"],"prefix":"10.1007","author":[{"given":"Yinghua","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yana","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"15_CR1","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27 (2014)"},{"key":"15_CR2","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"15_CR3","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":"15_CR4","doi-asserted-by":"crossref","unstructured":"Wu, D., Li, H., Gu, C., et al.: Improving fusion of region features and grid features via two-step interaction for image-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5055\u20135064 (2022)","DOI":"10.1145\/3503161.3548223"},{"issue":"13","key":"15_CR5","doi-asserted-by":"publisher","first-page":"9481","DOI":"10.1007\/s00521-022-08072-w","volume":"35","author":"J Zhou","year":"2023","unstructured":"Zhou, J., Zhu, Y., Zhang, Y., et al.: Spatial-aware topic-driven-based image Chinese caption for disaster news. Neural Comput. Appl. 35(13), 9481\u20139500 (2023)","journal-title":"Neural Comput. Appl."},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Gomez, L., Rusinol, M., et al.: Good news, everyone! context driven entity-aware captioning for news images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12466\u201312475 (2019)","DOI":"10.1109\/CVPR.2019.01275"},{"key":"15_CR7","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Tran, A., Mathews, A., Xie, L.: Transform and tell: entity-aware news image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13035\u201313045 (2020)","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Liu, F., Wang, Y., Wang, T., et al.: Visual news: benchmark and challenges in news image captioning. arXiv preprint arXiv:2010.03743 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Zhou, M., Luo, G., Rohrbach, A., et al.: Focus! relevant and sufficient context selection for news image captioning. arXiv preprint arXiv:2212.00843 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.450"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, J., Fang, S., Mao, Z., et al.: Fine-tuning with multi-modal entity prompts for news image captioning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4365\u20134373 (2022)","DOI":"10.1145\/3503161.3547883"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., et al.: 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":"15_CR13","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., et al.: 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"},{"issue":"8","key":"15_CR14","doi-asserted-by":"publisher","first-page":"3118","DOI":"10.1109\/TCSVT.2020.3036860","volume":"31","author":"L Wu","year":"2020","unstructured":"Wu, L., Xu, M., Sang, L., et al.: Noise augmented double-stream graph convolutional networks for image captioning. IEEE Trans. Circuits Syst. Video Technol. 31(8), 3118\u20133127 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"15_CR15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.neunet.2022.01.011","volume":"148","author":"T Xian","year":"2022","unstructured":"Xian, T., Li, Z., Zhang, C., et al.: Dual global enhanced transformer for image captioning. Neural Netw. 148, 129\u2013141 (2022)","journal-title":"Neural Netw."},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ji, J., Sun, X., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Nguyen, V.Q., Suganuma, M., Okatani, T.: GRIT: faster and\u00a0better image captioning transformer using dual visual features. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 167\u2013184. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_10","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"15_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\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., et al.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Communications in Computer and Information Science","Digital Multimedia Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-3623-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T10:12:11Z","timestamp":1718878331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-3623-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819736225","9789819736232"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-3623-2_15","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 June 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IFTC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Forum on Digital TV and Wireless Multimedia Communications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iftc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.siga.org.cn\/xshd\/iftc2023.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}