Ranking metrics AP and FPR-95 can be made perfect via Sinkhorn normalization even when assignment is already correct, while optimal ranking can still produce incorrect assignments.
Retext: Text boosts generalization in image-based person re-identification.arXiv:2602.05785, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A decoupled two-stage training pipeline with a single vision encoder enables joint image-to-image and text-to-image person re-identification by avoiding cross-task interference, with I2I pre-training and textual supervision shown to benefit both tasks.
citing papers explorer
-
Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
Ranking metrics AP and FPR-95 can be made perfect via Sinkhorn normalization even when assignment is already correct, while optimal ranking can still produce incorrect assignments.
-
Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification
A decoupled two-stage training pipeline with a single vision encoder enables joint image-to-image and text-to-image person re-identification by avoiding cross-task interference, with I2I pre-training and textual supervision shown to benefit both tasks.