{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T04:26:53Z","timestamp":1768883213964,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031243394","type":"print"},{"value":"9783031243400","type":"electronic"}],"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\/978-3-031-24340-0_42","type":"book-chapter","created":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T13:03:43Z","timestamp":1677330223000},"page":"558-572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["EAGLE: An Enhanced Attention-Based Strategy by\u00a0Generating Answers from\u00a0Learning Questions to\u00a0a\u00a0Remote Sensing Image"],"prefix":"10.1007","author":[{"given":"Yeyang","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yimin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shunlong","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Mingxin","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Ziqi","family":"Sha","sequence":"additional","affiliation":[]},{"given":"Heyu","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Yanhui","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Junsheng","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Weiguang","family":"Qu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,26]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Deep compositional question answering with neural module networks. CoRR abs\/1511.02799 (2015)","DOI":"10.1109\/CVPR.2016.12"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"issue":"6\u20131","key":"42_CR4","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TGRS.2007.899144","volume":"45","author":"K Chen","year":"2007","unstructured":"Chen, K., Crawford, M.M., Gamba, P., Smith, J.S.: Introduction for the special issue on remote sensing for major disaster prevention, monitoring, and assessment. IEEE Trans. Geosci. Remote Sens. 45(6\u20131), 1515\u20131518 (2007)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"10","key":"42_CR5","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","volume":"105","author":"G Cheng","year":"2017","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865\u20131883 (2017)","journal-title":"Proc. IEEE"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Das, A., Agrawal, H., Zitnick, L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? vol. 163, pp. 90\u2013100. Elsevier (2017)","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"42_CR9","unstructured":"Kim, J., On, K.W., Lim, W., Kim, J., Ha, J., Zhang, B.: Hadamard product for low-rank bilinear pooling. CoRR abs\/1610.04325 (2016)"},{"issue":"1","key":"42_CR10","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(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Li, Q., Fu, J., Yu, D., Mei, T., Luo, J.: Tell-and-answer: towards explainable visual question answering using attributes and captions. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1164"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Liang, J., Jiang, L., Cao, L., Li, L., Hauptmann, A.G.: Focal visual-text attention for visual question answering. In: CVPR, pp. 6135\u20136143 (2018)","DOI":"10.1109\/CVPR.2018.00642"},{"key":"42_CR13","unstructured":"Lillesand, T., Kiefer, R.W., Chipman, J.: Remote Sensing and Image Interpretation. Wiley, Hoboken (2015)"},{"key":"42_CR14","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":"42_CR15","doi-asserted-by":"crossref","unstructured":"Lin, Y., Pang, Z., Wang, D., Zhuang, Y.: Feature enhancement in attention for visual question answering. In: IJCAI, pp. 4216\u20134222 (2018)","DOI":"10.24963\/ijcai.2018\/586"},{"key":"42_CR16","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. 29, 289\u2013297 (2016)"},{"issue":"4","key":"42_CR17","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","volume":"56","author":"X Lu","year":"2017","unstructured":"Lu, X., Wang, B., Zheng, X., Li, X.: Exploring models and data for remote sensing image caption generation. IEEE Trans. Geosci. Remote Sens. 56(4), 2183\u20132195 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"42_CR18","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: NIPS, pp. 1682\u20131690 (2014)"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Okatani, T.: Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: CVPR, pp. 6087\u20136096 (2018)","DOI":"10.1109\/CVPR.2018.00637"},{"key":"42_CR21","unstructured":"Noh, H., Han, B.: Training recurrent answering units with joint loss minimization for VQA. CoRR abs\/1606.03647 (2016)"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Qu, B., Li, X., Tao, D., Lu, X.: Deep semantic understanding of high resolution remote sensing image. In: CITS, pp. 1\u20135 (2016)","DOI":"10.1109\/CITS.2016.7546397"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Rajani, N.F., Mooney, R.J.: Stacking with auxiliary features for visual question answering. In: NAACL-HLT, pp. 2217\u20132226 (2018)","DOI":"10.18653\/v1\/N18-1201"},{"key":"42_CR25","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"issue":"6","key":"42_CR26","doi-asserted-by":"publisher","first-page":"3623","DOI":"10.1109\/TGRS.2017.2677464","volume":"55","author":"Z Shi","year":"2017","unstructured":"Shi, Z., Zou, Z.: Can a machine generate humanlike language descriptions for a remote sensing image? IEEE Trans. Geosci. Remote Sens. 55(6), 3623\u20133634 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: CVPR, pp. 4613\u20134621 (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"42_CR28","unstructured":"Shimizu, N., Rong, N., Miyazaki, T.: Visual question answering dataset for bilingual image understanding: a study of cross-lingual transfer using attention maps. In: ICCL, pp. 1918\u20131928 (2018)"},{"key":"42_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"42_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Xie, L., Shen, J., Zhu, L.: Online cross-modal hashing for web image retrieval. In: AAAI, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.9982"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Y., Newsam, S.D.: Bag-of-visual-words and spatial extensions for land-use classification. In: GIS (2010)","DOI":"10.1145\/1869790.1869829"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"issue":"4","key":"42_CR34","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1109\/TGRS.2014.2357078","volume":"53","author":"F Zhang","year":"2014","unstructured":"Zhang, F., Du, B., Zhang, L.: Saliency-guided unsupervised feature learning for scene classification. IEEE Trans. Geosci. Remote Sens. 53(4), 2175\u20132184 (2014)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"42_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, C., Zhao, Y., Huang, S., Tu, K., Ma, Y.: Structured attentions for visual question answering. In: ICCV, pp. 1291\u20131300 (2017)","DOI":"10.1109\/ICCV.2017.145"},{"key":"42_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M.S., Fei-Fei, L.: Visual7w: grounded question answering in images. In: CVPR, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-24340-0_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T13:11:24Z","timestamp":1677330684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-24340-0_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031243394","9783031243400"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-24340-0_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"La Rochelle","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"7 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 April 2019","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":"cicling2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2019\/","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":"335","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":"95","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":"28% - 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":"2.3","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":"3.4","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)"}}]}}