{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:58:26Z","timestamp":1780444706351,"version":"3.54.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031500688","type":"print"},{"value":"9783031500695","type":"electronic"}],"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\/978-3-031-50069-5_10","type":"book-chapter","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:02:34Z","timestamp":1705644154000},"page":"105-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Aware-Transformer: A Novel Pure Transformer-Based Model for\u00a0Remote Sensing Image Captioning"],"prefix":"10.1007","author":[{"given":"Yukun","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialuo","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijia","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangle","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,20]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"issue":"10","key":"10_CR2","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":"10_CR3","first-page":"1","volume":"60","author":"Q Cheng","year":"2022","unstructured":"Cheng, Q., Huang, H., Xu, Y., Zhou, Y., Li, H., Wang, Z.: NWPU-captions dataset and MLCA-net for remote sensing image captioning. IEEE Trans. Geosci. Remote Sens. 60, 1\u201319 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR5","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"},{"issue":"8","key":"10_CR6","doi-asserted-by":"publisher","first-page":"3647","DOI":"10.1007\/s00371-023-02938-3","volume":"39","author":"S Huang","year":"2023","unstructured":"Huang, S., et al.: TransMRSR: transformer-based self-distilled generative prior for brain MRI super-resolution. Vis. Comput. 39(8), 3647\u20133659 (2023)","journal-title":"Vis. Comput."},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Jain, D., Kumar, A., Beniwal, R.: Personality BERT: a transformer-based model for personality detection from textual data. In: Proceedings of International Conference on Computing and Communication Networks: ICCCN, pp. 515\u2013522 (2022)","DOI":"10.1007\/978-981-19-0604-6_48"},{"key":"10_CR8","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp. 74\u201381 (2004)"},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., 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"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Miao, Y., Liu, K., Yang, W., Yang, C.: A novel transformer-based model for dialog state tracking. In: International Conference on Human-Computer Interaction, pp. 148\u2013156 (2022)","DOI":"10.1007\/978-3-031-06050-2_11"},{"key":"10_CR12","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 of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Qu, B., Li, X., Tao, D., Lu, X.: Deep semantic understanding of high resolution remote sensing image. In: 2016 International Conference on Computer, Information and Telecommunication Systems (CITS), pp. 1\u20135 (2016)","DOI":"10.1109\/CITS.2016.7546397"},{"key":"10_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR15","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":"10_CR16","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 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, Z., Ma, A., Zhong, Y.: Capformer: pure transformer for remote sensing image caption. In: IGARSS 2022\u20132022 IEEE International Geoscience and Remote Sensing Symposium, pp. 7996\u20137999. IEEE (2022)","DOI":"10.1109\/IGARSS46834.2022.9883199"},{"issue":"12","key":"10_CR18","doi-asserted-by":"publisher","first-page":"10532","DOI":"10.1109\/TGRS.2020.3044054","volume":"59","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Huang, W., Zhang, X., Li, X.: Word-sentence framework for remote sensing image captioning. IEEE Trans. Geosci. Remote Sens. 59(12), 10532\u201310543 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Yang, Y., Newsam, S.: Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 270\u2013279 (2010)","DOI":"10.1145\/1869790.1869829"},{"issue":"3","key":"10_CR20","doi-asserted-by":"publisher","first-page":"579","DOI":"10.3390\/rs15030579","volume":"15","author":"X Zhang","year":"2023","unstructured":"Zhang, X., et al.: Multi-source interactive stair attention for remote sensing image captioning. Remote Sens. 15(3), 579 (2023)","journal-title":"Remote Sens."},{"issue":"6","key":"10_CR21","doi-asserted-by":"publisher","first-page":"612","DOI":"10.3390\/rs11060612","volume":"11","author":"X Zhang","year":"2019","unstructured":"Zhang, X., Wang, X., Tang, X., Zhou, H., Li, C.: Description generation for remote sensing images using attribute attention mechanism. Remote Sens. 11(6), 612 (2019)","journal-title":"Remote Sens."},{"key":"10_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2020.3042202","volume":"60","author":"R Zhao","year":"2021","unstructured":"Zhao, R., Shi, Z., Zou, Z.: High-resolution remote sensing image captioning based on structured attention. IEEE Trans. Geosci. Remote Sens. 60, 1\u201314 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2021.3135711","volume":"19","author":"S Zhuang","year":"2022","unstructured":"Zhuang, S., Wang, P., Wang, G., Wang, D., Chen, J., Gao, F.: Improving remote sensing image captioning by combining grid features and transformer. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50069-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:03:51Z","timestamp":1705644231000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50069-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031500688","9783031500695"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50069-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2023","order":10,"name":"conference_id","label":"Conference ID","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":"385","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":"149","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":"39% - 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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}