MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
Revisiting oxford and paris: Large-scale image retrieval benchmarking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
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.