MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
arXiv preprint arXiv:2302.01572 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 6roles
background 1polarities
background 1representative citing papers
InfoGeo reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations across views while suppressing view-specific noise.
Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.
GeoBridge introduces a semantic-anchor mechanism using text to bridge multi-view image features for bidirectional cross-view and language-to-image geo-localization, supported by the new GeoLoc dataset of over 50,000 aligned pairs.
GeoISF builds an instance semantic forest from WordNet across multiple frames to improve semantic alignment and match ground LiDAR to large satellite images, reporting 13.22x better R@10 on KITTI than prior LiDAR-to-image methods.
BGG adapts vision foundation models using multi-granularity dilated convolutions and frequency-domain patch aggregation to achieve state-of-the-art cross-view geo-localization on University-1652 and SUES-200 with low training cost.
citing papers explorer
-
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
-
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGeo reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations across views while suppressing view-specific noise.
-
Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.
-
GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
GeoBridge introduces a semantic-anchor mechanism using text to bridge multi-view image features for bidirectional cross-view and language-to-image geo-localization, supported by the new GeoLoc dataset of over 50,000 aligned pairs.
-
GeoISF: Instance Semantic Forest Inspired Large-Scale Cross-View Geo-Localization via Ground LiDAR-to-Satellite Image
GeoISF builds an instance semantic forest from WordNet across multiple frames to improve semantic alignment and match ground LiDAR to large satellite images, reporting 13.22x better R@10 on KITTI than prior LiDAR-to-image methods.
-
BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization
BGG adapts vision foundation models using multi-granularity dilated convolutions and frequency-domain patch aggregation to achieve state-of-the-art cross-view geo-localization on University-1652 and SUES-200 with low training cost.