A latent-noise autoencoder is claimed to reduce the biometric identifiability of gaze signals while preserving utility for gaze prediction and physiological plausibility of the output.
Joint attention simulation using eye-tracking and virtual humans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Privacy Enhancement for Gaze Data Using a Noise-Infused Autoencoder
A latent-noise autoencoder is claimed to reduce the biometric identifiability of gaze signals while preserving utility for gaze prediction and physiological plausibility of the output.