AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MMLandmarks: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding

Oskar Kristoffersen, Alba Reinders Sánchez, Morten Rieger Hannemose, Anders Bjorholm Dahl, Dim P. Papadopoulos

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sample latest aerial image and train on outdoor-only ground subset (ablation)MMCLIP · MMLandmarks Satellite-to-GPSdistance accuracy at 1 km (%): 27.2 -> 36.9Improved
use latest instead of random satellite image, with outdoor subset (ablation)MMCLIP · MMLandmarks Satellite-to-GroundmAP@1k: 17.45 -> 18.79Improved
increase number of modalities (add text and GPS) (ablation)MMCLIP · MMLandmarks Ground-to-SatellitemAP@1k: 25.59 -> 24.94No clear effect
use first sentence vs random sentence for text sampling (ablation)MMCLIP · MMLandmarks Satellite-to-GroundmAP@1k: 17.39 vs 16.93No clear effect
use all-pairwise contrastive objective instead of ground-anchored ImageBind-style objective (ablation)MMCLIP · MMLandmarks Satellite-to-GPSdistance accuracy at 1 km (%): 18.3 -> 36.9Improved
use ground-anchored objective instead of all pairwise (ablation)MMCLIP · MMLandmarks retrievalmAP@1k ground-to-satellite: 26.20 -> 27.46Improved
filter indoor ground images from training (ablation)MMCLIP · MMLandmarks Satellite-to-GroundmAP@1k: 16.93 -> 17.45Improved
use specialized cross-view models zero-shotUni-1652, TransGeo, Sample4Geo · MMLandmarks Ground-to-SatelliteR@1: 0.2-0.85 vs 14.6 for SigLIP2Hurt
scale foundation model from ViT-B to ViT-L and raise resolutionSigLIP2 zero-shot · MMLandmarks Ground-to-SatelliteR@1: 8.5 -> 14.6Improved
train baseline on MMLandmarks versus zero-shot CLIP-like modelsCLIP ViT-L/336 · MMLandmarks Ground-to-SatelliteR@1: 11.9 -> 20.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy