{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:39:49Z","timestamp":1780443589693,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology on Complex Electronic System Simulation Laboratory Funding","award":["DXZT-JC-ZZ-2020-005"],"award-info":[{"award-number":["DXZT-JC-ZZ-2020-005"]}]},{"name":"Aerospace Discipline Education New Engineering Project","award":["20221032"],"award-info":[{"award-number":["20221032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3360089","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T18:46:29Z","timestamp":1706640389000},"page":"1-14","source":"Crossref","is-referenced-by-count":19,"title":["Cooperative Connection Transformer for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2441-6532","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"first","affiliation":[{"name":"Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[{"name":"Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"10","key":"ref1","doi-asserted-by":"crossref","first-page":"5832","DOI":"10.1109\/TGRS.2016.2572736","article-title":"Ship detection in spaceborne optical image with SVD networks","volume":"54","author":"Zou","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"ref2","doi-asserted-by":"crossref","first-page":"3325","DOI":"10.1109\/TGRS.2014.2374218","article-title":"Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning","volume":"53","author":"Han","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"2","key":"ref3","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1109\/TGRS.2015.2469138","article-title":"Hashing-based scalable remote sensing image search and retrieval in large archives","volume":"54","author":"Demir","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref4","article-title":"Curriculum-style local-to-global adaptation for cross-domain remote sensing image segmentation","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref5","article-title":"Deep covariance alignment for domain adaptive remote sensing image segmentation","volume":"60","author":"Wu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref6","article-title":"Vision-language intelligence: Tasks, representation learning, and large models","author":"Li","year":"2022","journal-title":"arXiv:2203.01922"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3173811","article-title":"From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data","volume":"60","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref8","first-page":"1371","article-title":"Prompt-RSVQA: Prompting visual context to a language model for remote sensing visual question answering","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Chappuis"},{"key":"ref9","article-title":"Mutual attention inception network for remote sensing visual question answering","volume":"60","author":"Zheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3195692","article-title":"Change captioning: A new paradigm for multitemporal remote sensing image analysis","volume":"60","author":"Hoxha","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3218921","article-title":"Remote sensing image change captioning with dual-branch transformers: A new method and a large scale dataset","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref12","article-title":"A decoupling paradigm with prompt learning for remote sensing image change captioning","volume":"61","author":"Liu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3281334","article-title":"Improving image captioning systems with postprocessing strategies","volume":"61","author":"Hoxha","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref14","first-page":"1","article-title":"Deep semantic understanding of high resolution remote sensing image","volume-title":"Proc. Int. Conf. Comput., Inf. Telecommun. Syst. (CITS)","author":"Qu"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.isprsjprs.2022.02.001","article-title":"Meta captioning: A meta learning based remote sensing image captioning framework","volume":"186","author":"Yang","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref16","first-page":"109","article-title":"Remote sensing image captioning using hire-MLP","volume-title":"Proc. 4th Int. Conf. Comput. Vis., Image Deep Learn. (CVIDL)","author":"Wei"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3224244","article-title":"A joint-training two-stage method for remote sensing image captioning","volume":"60","author":"Ye","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"7","key":"ref18","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.3390\/electronics12071547","article-title":"DFEN: Dual feature enhancement network for remote sensing image caption","volume":"12","author":"Zhao","year":"2023","journal-title":"Electronics"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1109\/JSTARS.2022.3153636","article-title":"Multiscale multiinteraction network for remote sensing image captioning","volume":"15","author":"Wang","year":"2022","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"issue":"3","key":"ref20","doi-asserted-by":"crossref","first-page":"579","DOI":"10.3390\/rs15030579","article-title":"Multi-source interactive stair attention for remote sensing image captioning","volume":"15","author":"Zhang","year":"2023","journal-title":"Remote Sens."},{"key":"ref21","article-title":"High-resolution remote sensing image captioning based on structured attention","volume":"60","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref22","article-title":"Recurrent attention and semantic gate for remote sensing image captioning","volume":"60","author":"Li","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref23","article-title":"Global visual feature and linguistic state guided attention for remote sensing image captioning","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109893","article-title":"Learning consensus-aware semantic knowledge for remote sensing image captioning","volume":"145","author":"Li","year":"2024","journal-title":"Pattern Recognit."},{"issue":"11","key":"ref25","doi-asserted-by":"crossref","first-page":"6910","DOI":"10.1109\/TCYB.2022.3222606","article-title":"GLCM: Global\u2013local captioning model for remote sensing image captioning","volume":"53","author":"Wang","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2021.3105004","article-title":"A novel SVM-based decoder for remote sensing image captioning","volume":"60","author":"Hoxha","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref27","doi-asserted-by":"crossref","first-page":"7704","DOI":"10.1109\/JSTARS.2023.3305889","article-title":"From plane to hierarchy: Deformable transformer for remote sensing image captioning","volume":"16","author":"Du","year":"2023","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"issue":"35","key":"ref28","doi-asserted-by":"crossref","first-page":"26661","DOI":"10.1007\/s11042-020-09294-7","article-title":"Remote sensing image caption generation via transformer and reinforcement learning","volume":"79","author":"Shen","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2021.3135711","article-title":"Improving remote sensing image captioning by combining grid features and transformer","volume":"19","author":"Zhuang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref30","first-page":"1","article-title":"TypeFormer: Multiscale transformer with type controller for remote sensing image caption","volume":"19","author":"Chen","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref31","first-page":"10575","article-title":"Meshed-memory transformer for image captioning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Cornia"},{"issue":"8","key":"ref32","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/LGRS.2019.2893772","article-title":"Semantic descriptions of high-resolution remote sensing images","volume":"16","author":"Wang","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"6","key":"ref33","doi-asserted-by":"crossref","first-page":"3623","DOI":"10.1109\/TGRS.2017.2677464","article-title":"Can a machine generate humanlike language descriptions for a remote sensing image?","volume":"55","author":"Shi","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref34","article-title":"Learning internal representations by error propagation","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations","author":"Rumelhart","year":"1986"},{"key":"ref35","first-page":"6734","article-title":"Remote sensing image captioning with SVM-based decoding","volume-title":"Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS)","author":"Hoxha"},{"key":"ref36","first-page":"1470","article-title":"Video Google: A text retrieval approach to object matching in videos","volume-title":"Proc. 9th IEEE Int. Conf. Comput. Vis.","volume":"2","author":"Zisserman"},{"key":"ref37","first-page":"3384","article-title":"Large-scale image retrieval with compressed Fisher vectors","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Perronnin"},{"issue":"4","key":"ref38","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","article-title":"Exploring models and data for remote sensing image caption generation","volume":"56","author":"Lu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref39","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Anderson"},{"key":"ref40","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lin"},{"issue":"8","key":"ref41","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref42","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref43","first-page":"413","article-title":"Captioning remote sensing images using transformer architecture","volume-title":"Proc. Int. Conf. Artif. Intell. Inf. Commun. (ICAIIC)","author":"Nanal"},{"key":"ref44","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref45","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"He"},{"issue":"6","key":"ref46","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"ref47","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"Int. J. Comput. Vis."}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10416686.pdf?arnumber=10416686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:34:07Z","timestamp":1707809647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10416686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3360089","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}