A language-driven system uses positional graphs and LVLM appearance descriptions with a debate scheme to match pedestrians across heavily misaligned RGB and thermal images, reporting big gains over ProbEn on two 100-pair datasets.
To solve the misalignment problems, camera calibration tech- niques and image registration algorithms have been devel- oped
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
-
Revisiting Misalignment in Multispectral Pedestrian Detection: A Language-Driven Approach for Cross-modal Alignment Fusion
A language-driven system uses positional graphs and LVLM appearance descriptions with a debate scheme to match pedestrians across heavily misaligned RGB and thermal images, reporting big gains over ProbEn on two 100-pair datasets.