LVLM-ReID guides LVLMs to produce refined semantic tokens as pedestrian identity features for ReID, achieving competitive benchmark results without additional image-text data.
Clip-reid: exploiting vision-language model for image re-identification without concrete text labels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Large Vision-Language Models Meet Person Re-Identification
LVLM-ReID guides LVLMs to produce refined semantic tokens as pedestrian identity features for ReID, achieving competitive benchmark results without additional image-text data.