{"ID":2829818,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11490","arxiv_id":"2512.11490","title":"VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing","abstract":"Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding. Current remote-sensing approaches remain fragmented between dual-encoder retrieval models, which excel at large-scale cross-modal search but cannot interleave modalities, and generative assistants, which support region-level interpretation but lack scalable retrieval capabilities. We propose $\\textbf{VLM2GeoVec}$, an instruction-following, single-encoder vision-language model trained contrastively to embed interleaved inputs (images, text, bounding boxes, and geographic coordinates) in a unified vector space. Our single encoder interleaves all inputs into one joint embedding trained with a contrastive loss, eliminating multi-stage pipelines and task-specific modules. To evaluate its versatility, we introduce $\\textbf{RSMEB}$, a novel benchmark covering key remote-sensing embedding applications: scene classification; cross-modal search; compositional retrieval; visual-question answering; visual grounding and region-level reasoning; and semantic geospatial retrieval. On RSMEB, it achieves $\\textbf{26.6%}$ P@1 on region-caption retrieval (+25 pp vs. dual-encoder baselines), $\\textbf{32.5%}$ P@1 on referring-expression retrieval (+19 pp), and $\\textbf{17.8%}$ P@1 on semantic geo-localization retrieval (over $3\\times$ prior best), while matching or exceeding specialized baselines on conventional tasks such as scene classification and cross-modal retrieval. VLM2GeoVec unifies scalable retrieval with region-level spatial reasoning, enabling cohesive multimodal analysis in remote sensing. We will publicly release the code, checkpoints, and data upon acceptance.","short_abstract":"Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding. Current remote-sensing approaches remain fragmented between dual-encoder retrieva...","url_abs":"https://arxiv.org/abs/2512.11490","url_pdf":"https://arxiv.org/pdf/2512.11490v1","authors":"[\"Emanuel Sánchez Aimar\",\"Gulnaz Zhambulova\",\"Fahad Shahbaz Khan\",\"Yonghao Xu\",\"Michael Felsberg\"]","published":"2025-12-12T11:39:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false}