GaitDCCR combines dynamic clustering parameters, density-weighted centroids, confidence-based pseudo-label refinement, and a contrastive teacher module to improve unsupervised gait recognition.
Title resolution pending
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
-
Unsupervised Domain Adaptation with Dynamic Clustering and Contrastive Refinement for Gait Recognition
GaitDCCR combines dynamic clustering parameters, density-weighted centroids, confidence-based pseudo-label refinement, and a contrastive teacher module to improve unsupervised gait recognition.