ViFiCon learns vision-to-wireless associations via self-supervised contrastive learning on stacked depth image sequences and FTM data, reaching 92.63% accuracy in 2.5-second windows without labeled associations.
Multi- modal cnn pedestrian classification: a study on combining li- dar and camera data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning
ViFiCon learns vision-to-wireless associations via self-supervised contrastive learning on stacked depth image sequences and FTM data, reaching 92.63% accuracy in 2.5-second windows without labeled associations.