ViSA proposes expert-driven token generation and dual-branch local fusion modules for view-aware semantic alignment in AGPReID, reporting up to 10.06% mAP gains on the CARGO benchmark.
Unity is strength: Unifying convolutional and transformeral features for better person re-identification
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
-
View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
ViSA proposes expert-driven token generation and dual-branch local fusion modules for view-aware semantic alignment in AGPReID, reporting up to 10.06% mAP gains on the CARGO benchmark.