A unified 2D/3D visual query localization pipeline using SAM-guided parsing, a closed-form correlation filter, and a multiplicative semantic-geometric confidence weighting scheme reports state-of-the-art results on Ego4D-VQ.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EgoHieraLoc: A Cortically Inspired Hierarchical Segmentation-Guided Framework for Egocentric Visual Query Localization
A unified 2D/3D visual query localization pipeline using SAM-guided parsing, a closed-form correlation filter, and a multiplicative semantic-geometric confidence weighting scheme reports state-of-the-art results on Ego4D-VQ.