{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:15:02Z","timestamp":1778080502384,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00670","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7132-7142","source":"Crossref","is-referenced-by-count":1,"title":["GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks"],"prefix":"10.1109","author":[{"given":"Muhammad Sohail","family":"Danish","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Akhtar","family":"Munir","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed Roshaan Ali","family":"Shah","sequence":"additional","affiliation":[{"name":"University College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Kuckreja","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Fraccaro","sequence":"additional","affiliation":[{"name":"IBM Research Europe,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Lacoste","sequence":"additional","affiliation":[{"name":"ServiceNow Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"ref4","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023","journal-title":"arxiv. arXiv preprint arXiv:2303.12712"},{"key":"ref5","author":"Cambrin","year":"2024","journal-title":"Estimating earthquake magnitude in sentinel1 imagery via ranking"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3183022"},{"key":"ref11","article-title":"CSE499DeforestationSatellite","volume-title":"Deforestation-satelliteimagery dataset"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf7894"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref15","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref18","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3365825"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0106"},{"key":"ref22","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref24","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref25","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3373401"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02517"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref29","article-title":"Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing visionlanguage understanding","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Airound and cv-brct: Novel multi-view datasets for scene classification","author":"Machado","year":"2020","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_26"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.329"},{"key":"ref34","article-title":"OpenAI","year":"2024","journal-title":"Hello gpt-4o"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00108"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00483"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA60407.2023.00034"},{"key":"ref39","author":"Shermeyer","year":"2020","journal-title":"Rareplanes dataset"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01334"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref42","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"M4u: Evaluating multilingual understanding and reasoning for large multimodal models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"ref46","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"issue":"12","key":"ref47","article-title":"Mar20: A benchmark for military aircraft recognition in remote sensing images","volume":"27","author":"Wenqi","year":"2024","journal-title":"National Remote Sensing Bulletin"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref50","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transform-ers","author":"Xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Exploring diverse in-context configurations for image captioning","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.162"},{"key":"ref53","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369720"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00780"},{"key":"ref60","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2023"},{"key":"ref61","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref63","author":"Zhang","year":"2024","journal-title":"Mme-realworld: Could your multimodal 11 m challenge high-resolution real-world scenarios that are difficult for humans? arXiv preprint arXiv:2408"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3392778"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref66","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445566.pdf?arnumber=11445566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:17Z","timestamp":1777529717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00670","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}