Two modality-specific classifiers trained only within their own camera type can, through agreement-based pseudo-correspondences, match people across visible and infrared images and approach fully supervised accuracy on SYSU-MM01 and LLCM.
Joint feature learning network for visible-infrared person re-identification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
Two modality-specific classifiers trained only within their own camera type can, through agreement-based pseudo-correspondences, match people across visible and infrared images and approach fully supervised accuracy on SYSU-MM01 and LLCM.