{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:15:08Z","timestamp":1785420908797,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819669714","type":"print"},{"value":"9789819669721","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-6972-1_29","type":"book-chapter","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T08:29:22Z","timestamp":1750753762000},"page":"417-431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Rethinking Remote Sensing CLIP: Leveraging Multimodal Large Language Models for\u00a0High-Quality Vision-Language Dataset"],"prefix":"10.1007","author":[{"given":"Yiguo","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangjuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"29_CR1","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: RemoteCLIP: a vision language foundation model for remote sensing. IEEE TGRS (2024)","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Z., Prabha, R., Huang, T., Wu, J., Rajagopal, R.: SkyScript: a large and semantically diverse vision-language dataset for remote sensing. In: AAAI, vol. 38, no. 6, pp. 5805\u20135813 (2024)","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"29_CR4","unstructured":"Zhang, Z., Zhao, T., Guo, Y., Yin, J.: RS5M: a large scale vision-language dataset for remote sensing vision-language foundation model. arXiv preprint arXiv:2306.11300 (2023)"},{"issue":"7","key":"29_CR5","first-page":"3965","volume":"55","author":"GS Xia","year":"2017","unstructured":"Xia, G.S., et al.: AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE TGRS 55(7), 3965\u20133981 (2017)","journal-title":"IEEE TGRS"},{"key":"29_CR6","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.isprsjprs.2018.01.004","volume":"145","author":"W Zhou","year":"2018","unstructured":"Zhou, W., Newsam, S., Li, C., Shao, Z.: PatternNet: a benchmark dataset for performance evaluation of remote sensing image retrieval. ISPRS J. Photogramm. Remote. Sens. 145, 197\u2013209 (2018)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"issue":"4","key":"29_CR7","first-page":"2183","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 TGRS 56(4), 2183\u20132195 (2017)","journal-title":"IEEE TGRS"},{"key":"29_CR8","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML, pp. 19730\u201319742 (2023)"},{"key":"29_CR9","unstructured":"Peng, Z., et al.: KOSMOS-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"29_CR10","doi-asserted-by":"publisher","unstructured":"Yuan, Z., et al.: Learning to evaluate performance of multi-modal semantic localization. IEEE TGRS. https:\/\/doi.org\/10.1109\/TGRS.2022.3207171.","DOI":"10.1109\/TGRS.2022.3207171."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Christie, G., Fendley, N., Wilson, J., Mukherjee, R.: Functional map of the world. In: CVPR, pp. 6172\u20136180 (2018)","DOI":"10.1109\/CVPR.2018.00646"},{"issue":"21","key":"29_CR12","doi-asserted-by":"publisher","first-page":"7622","DOI":"10.3390\/app10217622","volume":"10","author":"S Vujasinovi\u0107","year":"2020","unstructured":"Vujasinovi\u0107, S., Becker, S., Breuer, T., Bullinger, S., Scherer-Negenborn, N., Arens, M.: Integration of the 3D environment for UAV onboard visual object tracking. Appl. Sci. 10(21), 7622 (2020)","journal-title":"Appl. Sci."},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Hsieh, M.R., Lin, Y.L., Hsu, W.H.: Drone-based object counting by spatially regularized regional proposal network. In: ICCV, pp. 4145\u20134153 (2017)","DOI":"10.1109\/ICCV.2017.446"},{"key":"29_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46484-8_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Robicquet","year":"2016","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_33"},{"issue":"11","key":"29_CR15","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., et al.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR16","unstructured":"Zamir, S.W., et al.: ISAID: a large-scale dataset for instance segmentation in aerial images. In: Proceedings of the IEEE\/CVF CVPR Workshops, pp. 28\u201337 (2019)"},{"key":"29_CR17","unstructured":"Wang, J., Zheng, Z., Ma, A., Lu, X., Zhong, Y.: LoveDA: a remote sensing land-cover dataset for domain adaptive semantic segmentation. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol. 1 (2021). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/4e732ced3463d06de0ca9a15b6153677-Paper-round2.pdf"},{"key":"29_CR18","unstructured":"Potsdam dataset (2012). https:\/\/www.isprs.org\/education\/benchmarks\/UrbanSemLab\/2d-sem-label-potsdam.aspx"},{"key":"29_CR19","unstructured":"Vaihingen dataset (2012). https:\/\/www.isprs.org\/education\/benchmarks\/UrbanSemLab\/2d-sem-label-vaihingen.aspx"},{"key":"29_CR20","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li, K., Wan, G., Cheng, G., Meng, L., Han, J.: Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J. Photogramm. Remote. Sens. 159, 296\u2013307 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Xia, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: CVPR, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"issue":"8","key":"29_CR22","first-page":"5535","volume":"57","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Yuan, Y., Feng, Y., Lu, X.: Hierarchical and robust convolutional neural network for very high-resolution remote sensing object detection. IEEE TGRS 57(8), 5535\u20135548 (2019)","journal-title":"IEEE TGRS"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yuan, L., Weng, L., Yang, Y.: A high resolution optical satellite image dataset for ship recognition and some new baselines. In: ICPRAM, vol. 2, pp. 324\u2013331 (2017)","DOI":"10.5220\/0006120603240331"},{"issue":"10","key":"29_CR24","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.3390\/rs12101662","volume":"12","author":"H Chen","year":"2020","unstructured":"Chen, H., Shi, Z.: A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sens. 12(10), 1662 (2020)","journal-title":"Remote Sens."},{"key":"29_CR25","unstructured":"Sun, W., Dai, L., Zhang, X., Chang, P., He, X.: RSOD: real-time small object detection algorithm in UAV-based traffic monitoring. Appl. Intell., 1\u201316 (2022)"},{"issue":"10","key":"29_CR26","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"},{"issue":"6","key":"29_CR27","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.3390\/s20061594","volume":"20","author":"H Li","year":"2020","unstructured":"Li, H., et al.: RSI-CB: a large-scale remote sensing image classification benchmark using crowdsourced data. Sensors 20(6), 1594 (2020)","journal-title":"Sensors"},{"key":"29_CR28","unstructured":"Xia, G.S., Yang, W., Delon, J., Gousseau, Y., Sun, H., Ma\u00eetre, H.: Structural high-resolution satellite image indexing. In: ISPRS TC VII Symposium-100 Years ISPRS, vol. 38, pp. 298\u2013303 (2010)"},{"issue":"2","key":"29_CR29","first-page":"1155","volume":"57","author":"Q Wang","year":"2018","unstructured":"Wang, Q., Liu, S., Chanussot, J., Li, X.: Scene classification with recurrent attention of VHR remote sensing images. IEEE TGRS 57(2), 1155\u20131167 (2018)","journal-title":"IEEE TGRS"},{"key":"29_CR30","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.isprsjprs.2020.09.020","volume":"169","author":"X Qi","year":"2020","unstructured":"Qi, X., et al.: MLRSNet: a multi-label high spatial resolution remote sensing dataset for semantic scene understanding. ISPRS J. Photogramm. Remote. Sens. 169, 337\u2013350 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"issue":"7","key":"29_CR31","first-page":"2217","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE JSTARS 12(7), 2217\u20132226 (2019)","journal-title":"IEEE JSTARS"},{"key":"29_CR32","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR33","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS, vol. 36 (2024)"},{"key":"29_CR34","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017). https:\/\/api.semanticscholar.org\/CorpusID:53592270"},{"key":"29_CR35","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"11","key":"29_CR36","first-page":"2321","volume":"12","author":"Q Zou","year":"2015","unstructured":"Zou, Q., Ni, L., Zhang, T., Wang, Q.: Deep learning based feature selection for remote sensing scene classification. IEEE GRSL 12(11), 2321\u20132325 (2015)","journal-title":"IEEE GRSL"},{"issue":"4","key":"29_CR37","first-page":"2108","volume":"54","author":"B Zhao","year":"2016","unstructured":"Zhao, B., Zhong, Y., Xia, G.S., Zhang, L.: Dirichlet-derived multiple topic scene classification model fusing heterogeneous features for high spatial resolution remote sensing imagery. IEEE TGRS 54(4), 2108\u20132123 (2016)","journal-title":"IEEE TGRS"},{"key":"29_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3078451","volume":"60","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., et al.: Exploring a fine-grained multiscale method for cross-modal remote sensing image retrieval. IEEE TGRS 60, 1\u201319 (2022). https:\/\/doi.org\/10.1109\/TGRS.2021.3078451","journal-title":"IEEE TGRS"},{"key":"29_CR39","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CITS.2016.7546397","DOI":"10.1109\/CITS.2016.7546397"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6972-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T08:29:29Z","timestamp":1750753769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6972-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819669714","9789819669721"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6972-1_29","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}