VFE-TPS adds text-guided masked image modeling and identity-supervised feature calibration to CLIP and reports state-of-the-art Rank-1 accuracy on three text-based person search benchmarks, though not above a cited RaSa result.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Visual Representation for Text-based Person Searching
VFE-TPS adds text-guided masked image modeling and identity-supervised feature calibration to CLIP and reports state-of-the-art Rank-1 accuracy on three text-based person search benchmarks, though not above a cited RaSa result.