ModPrompt adapts vision-language object detectors to infrared and depth data with an input-dependent visual prompt and a decoupled text-embedding residual, without updating the frozen detector.
Privacy-preserving person detection using low-resolution infrared cameras
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Visual Modality Prompt for Adapting Vision-Language Object Detectors
ModPrompt adapts vision-language object detectors to infrared and depth data with an input-dependent visual prompt and a decoupled text-embedding residual, without updating the frozen detector.