{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:49:04Z","timestamp":1776275344439,"version":"3.50.1"},"reference-count":98,"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160401"],"award-info":[{"award-number":["2022ZD0160401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125102"],"award-info":[{"award-number":["62125102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JL23005"],"award-info":[{"award-number":["JL23005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3356074","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:43:28Z","timestamp":1705689808000},"page":"1-17","source":"Crossref","is-referenced-by-count":223,"title":["RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation Based on Visual Foundation Model"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0483-1306","authenticated-orcid":false,"given":"Keyan","family":"Chen","sequence":"first","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3034-6646","authenticated-orcid":false,"given":"Chenyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6418-3761","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1296-3984","authenticated-orcid":false,"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-2775","authenticated-orcid":false,"given":"Wenyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Geography, The University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1774-552X","authenticated-orcid":false,"given":"Zhengxia","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4772-3172","authenticated-orcid":false,"given":"Zhenwei","family":"Shi","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060989"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8898573"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3096185"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/rs13234779"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3336563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs13214441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3228287"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3180894"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.03.014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3202499"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3325829"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3272473"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3192256"},{"key":"ref16","article-title":"Pixel-level change detection pseudo-label learning for remote sensing change captioning","author":"Liu","year":"2023","journal-title":"arXiv:2312.15311"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-V-5-2020-109-2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/rs14030531"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref27","article-title":"EmbedMask: Embedding coupling for one-stage instance segmentation","author":"Ying","year":"2019","journal-title":"arXiv:1912.01954"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref31","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref33","article-title":"Segment anything","author":"Kirillov","year":"2023","journal-title":"arXiv:2304.02643"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3115569"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref36","article-title":"Segment anything in 3D with NeRFs","author":"Cen","year":"2023","journal-title":"arXiv:2304.12308"},{"key":"ref37","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023","journal-title":"arXiv:2305.03048"},{"key":"ref38","article-title":"AutoSAM: Adapting SAM to medical images by overloading the prompt encoder","author":"Shaharabany","year":"2023","journal-title":"arXiv:2306.06370"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref40","article-title":"How to efficiently adapt large segmentation Model(SAM) to medical images","author":"Hu","year":"2023","journal-title":"arXiv:2306.13731"},{"key":"ref41","article-title":"Time travelling pixels: Bitemporal features integration with foundation model for remote sensing image change detection","author":"Chen","year":"2023","journal-title":"arXiv:2312.16202"},{"key":"ref42","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"arXiv:2306.01567"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-020-00195-x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref46","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref48","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref49","article-title":"Simple open-vocabulary object detection with vision transformers","author":"Minderer","year":"2022","journal-title":"arXiv:2205.06230"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref51","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref53","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref57","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref61","article-title":"The history began from AlexNet: A comprehensive survey on deep learning approaches","author":"Zahangir Alom","year":"2018","journal-title":"arXiv:1803.01164"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref71","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"8","key":"ref72","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref73","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref74","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.33"},{"key":"ref76","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023","journal-title":"arXiv:2304.03277"},{"key":"ref77","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"arXiv:2201.11903"},{"key":"ref78","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv:2203.11171"},{"key":"ref79","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022","journal-title":"arXiv:2210.03493"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref82","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20053"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.10.002"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183690"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3390\/rs12182910"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref89","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16374"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref92","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref93","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv:1710.03740"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref95","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cong"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10409216.pdf?arnumber=10409216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T18:33:32Z","timestamp":1706898812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10409216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3356074","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}