A spectral-loss-regularized LSTM-CNN GAN generates synthetic eye-gaze velocity trajectories whose statistical moments and autocorrelation closely match real data, outperforming a four-state HMM in this comparison.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Modeling Eye Gaze Velocity Trajectories using GANs with Spectral Loss for Enhanced Fidelity
A spectral-loss-regularized LSTM-CNN GAN generates synthetic eye-gaze velocity trajectories whose statistical moments and autocorrelation closely match real data, outperforming a four-state HMM in this comparison.