Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding

• URL: http://arxiv.org/abs/2608.03826v1
• Date: Tue, 04 Aug 2026 15:36:17 GMT
• Title: Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding
• Abstract summary: We introduce GeoMEB, a large-scale multimodal embedding benchmark.<n>We present Geo-Embed, a unified embedding model that adapts a shared vision-language backbone to instruction-conditioned query-target matching.<n>Results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations.
• Score: 18.530343758279493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we introduce GeoMEB, a large-scale multimodal embedding benchmark that standardizes 45 urban evaluation tasks across retrieval, visual question answering, change detection, classification, and visual grounding, together with training collections comprising 1.32M examples and 286K evaluation queries. Second, we present Geo-Embed, a unified embedding model that adapts a shared vision-language backbone to instruction-conditioned query-target matching over heterogeneous geospatial inputs, including single images, multiple images, text, regions, and masks. On GeoMEB, Geo-Embed achieves the strongest overall performance among representative multimodal embedders, with a 15.3% relative improvement over the strongest baseline. These results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations, including semantic, cross-view, region-level, and temporal correspondence.

Related papers

• Textual Supervision Enhances Geospatial Representations in Vision-Language Models [47.5986642837928]
  Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems.<n>We analyze the geospatial representations acquired by three model families: vision-only architectures (e.g., ViT), vision-language models (e.g., CLIP), and large-scale multimodal foundation models (e.g., LLaVA, Qwen, and Gemma)
  arXiv  Detail & Related papers  (2026-06-05T11:40:13Z)
• Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning [72.13218601075958]
  We introduce textbfWanderBench, the first open access global geolocation benchmark for actionable geolocation reasoning in embodied scenarios.<n>We propose textbfGeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions.<n>Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments.
  arXiv  Detail & Related papers  (2026-03-11T06:24:10Z)
• MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding [4.493333639603517]
  We introduce the Multi-Modal Landmark dataset (MMLANDMARKS), a benchmark composed of four modalities: 197k highresolution aerial images, 329k ground-view images, textual information, and geographic coordinates for 18,557 distinct landmarks in the United States.<n>The MMLANDMARKS dataset has a one-to-one correspondence across every modality, which enables training and benchmarking models for various geo-spatial tasks.
  arXiv  Detail & Related papers  (2025-12-19T12:03:05Z)
• GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding [23.253648429114236]
  We propose GeoViS, a progressive search-and-reasoning framework for remote sensing visual grounding.<n>We show that GeoViS consistently surpasses existing methods across key visual grounding metrics.
  arXiv  Detail & Related papers  (2025-12-02T12:45:52Z)
• GLEAM: Learning to Match and Explain in Cross-View Geo-Localization [66.11208984986813]
  Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location.<n>We present GLEAM-C, a foundational CVGL model that unifies multiple views and modalities-including UAV imagery, street maps, panoramic views, and ground photographs-by aligning them exclusively with satellite imagery.<n>To address the lack of interpretability in traditional CVGL methods, we propose GLEAM-X, which combines cross-view correspondence prediction with explainable reasoning.
  arXiv  Detail & Related papers  (2025-09-09T07:14:31Z)
• GAIR: Improving Multimodal Geo-Foundation Model with Geo-Aligned Implicit Representations [5.439918212297177]
  Key challenge in multimodal GeoFM development is to explicitly model geospatial relationships across modalities.<n>We propose GAIR, a novel multimodal GeoFM architecture integrating overhead RS data, street view imagery, and their geolocation metadata.<n>We evaluate GAIR across 10 geospatial tasks spanning RS image-based, SV image-based, and location embedding-based benchmarks.
  arXiv  Detail & Related papers  (2025-03-20T19:59:39Z)
• GeoJEPA: Towards Eliminating Augmentation- and Sampling Bias in Multimodal Geospatial Learning [0.0]
  We present GeoJEPA, a versatile multimodal fusion model for geospatial data built on the self-supervised Joint-Embedding Predictive Architecture.<n>We aim to eliminate the widely accepted augmentation- and sampling biases found in self-supervised geospatial representation learning.<n>The results are multimodal semantic representations of urban regions and map entities that we evaluate both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2025-02-25T22:03:28Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework [51.26566634946208]
  We introduce smileGeo, a novel visual geo-localization framework. By inter-agent communication, smileGeo integrates the inherent knowledge of these agents with additional retrieved information. Results show that our approach significantly outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-21T03:31:30Z)
• CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement [11.108860387261508]
  Visual geolocalization is a cost-effective and scalable task that involves matching one or more query images taken at some unknown location, to a set of geo-tagged reference images. We develop CurriculumLoc, a novel keypoint detection and description with global semantic awareness and a local geometric verification. We achieve new high recall@1 scores of 62.6% and 94.5% on ALTO, with two different distances metrics, respectively.
  arXiv  Detail & Related papers  (2023-11-20T08:40:01Z)
• A General Purpose Neural Architecture for Geospatial Systems [142.43454584836812]
  We present a roadmap towards the construction of a general-purpose neural architecture (GPNA) with a geospatial inductive bias. We envision how such a model may facilitate cooperation between members of the community.
  arXiv  Detail & Related papers  (2022-11-04T09:58:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.