pith. sign in

Title resolution pending

Addressclip: Empowering vision-language models for city-wide image address localization · 2024

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Spatially-Weighted CLIP for Street-View Geo-localization

cs.CV · 2026-04-06 · unverdicted · novelty 6.0

SW-CLIP improves street-view geo-localization accuracy by replacing one-hot InfoNCE targets with spatially weighted soft labels derived from geodesic distances and adding neighborhood-consistency regularization.

citing papers explorer

Showing 1 of 1 citing paper.

  • Spatially-Weighted CLIP for Street-View Geo-localization cs.CV · 2026-04-06 · unverdicted · none · ref 2

    SW-CLIP improves street-view geo-localization accuracy by replacing one-hot InfoNCE targets with spatially weighted soft labels derived from geodesic distances and adding neighborhood-consistency regularization.