Metraipolis › archive › dc_8a1979d67abf

Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding — arXiv:2608.03826

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03826
License (as archived)
CC0-1.0
Archived
2026-10-31T12:43:18.822Z
SHA-256 of the archived text
9bda4fe5234c9d0ce617eeadfc214319d0be98bdf62c4324ebca1b53e5a00857
Stable URL of this page
https://metraipolis.com/documento/dc_8a1979d67abf

How to cite

Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding — arXiv:2608.03826 — arXiv (en), https://arxiv.org/abs/2608.03826 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a1979d67abf (Metraipolis archive dc_8a1979d67abf, sha256 9bda4fe5234c9d0ce617eeadfc214319d0be98bdf62c4324ebca1b53e5a00857)
BibTeX
@misc{dc8a1979d67abf,
  title = {Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding — arXiv:2608.03826},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03826},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a1979d67abf; sha256 9bda4fe5234c9d0ce617eeadfc214319d0be98bdf62c4324ebca1b53e5a00857},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03826. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.03826 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:31:30.425Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).