{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:29:13Z","timestamp":1771514953745,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013058","name":"Jiangsu Geological Bureau Research Project","doi-asserted-by":"publisher","award":["2023KY11"],"award-info":[{"award-number":["2023KY11"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense","award":["JSGP202101"],"award-info":[{"award-number":["JSGP202101"]}]},{"name":"Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense","award":["JSGP202204"],"award-info":[{"award-number":["JSGP202204"]}]},{"name":"Frontier Technologies Research and Development Program of Jiangsu","award":["BF2024070"],"award-info":[{"award-number":["BF2024070"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471235"],"award-info":[{"award-number":["62471235"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302255"],"award-info":[{"award-number":["62302255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0181"],"award-info":[{"award-number":["2023TQ0181"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3548664","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T18:39:19Z","timestamp":1741286359000},"page":"1-16","source":"Crossref","is-referenced-by-count":6,"title":["RSIC-GMamba: A State-Space Model With Genetic Operations for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9762-3738","authenticated-orcid":false,"given":"Lingwu","family":"Meng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0178-9384","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information, Ministry of Education, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"2015","author":"Xu","year":"2015","journal-title":"Comput. Sci."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/bf00344251"},{"key":"ref17","first-page":"1","article-title":"How to construct deep recurrent neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Pascanu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cits.2016.7546397"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2017.2776321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref25","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."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3153636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3135711"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328181"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"issue":"1","key":"ref33","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"ref34","first-page":"1","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref35","first-page":"1","article-title":"How to train your hippo: State space models with generalized orthogonal basis projections","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref36","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref37","first-page":"1","article-title":"Simplified state space layers for sequence modeling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Smith"},{"key":"ref38","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref39","first-page":"1","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref40","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref41","article-title":"PlainMamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024","journal-title":"arXiv:2403.17695"},{"key":"ref42","article-title":"LocalMamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024","journal-title":"arXiv:2403.09338"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2014.2355174"},{"key":"ref44","article-title":"Jamba: A hybrid transformer-mamba language model","author":"Lieber","year":"2024","journal-title":"arXiv:2403.19887"},{"key":"ref45","first-page":"1","article-title":"Block-state transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pilault"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref47","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref48","first-page":"552","article-title":"ESPNet: Efficient spatial pyramid of dilated convolutions for semantic segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Mehta"},{"key":"ref49","first-page":"1","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fu"},{"key":"ref50","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref51","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref52","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref55","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_28"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018626"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6620"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2024.2392847"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3401576"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3201474"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3497976"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3359316"},{"key":"ref65","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref66","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref67","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref68","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref69","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Daniel Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"issue":"8","key":"ref70","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222606"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref74","first-page":"322","article-title":"Underwater image captioning based on feature fusion","volume-title":"Proc. 7th Int. Conf. Image Graph. Process.","author":"Li"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10915627.pdf?arnumber=10915627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T03:30:41Z","timestamp":1743219041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10915627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3548664","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}