DSCL disentangles gaze features via Jacobian regularization into subspaces and applies ordinal contrastive learning to reach competitive in-domain and cross-domain performance with 5-20% labeled data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning
DSCL disentangles gaze features via Jacobian regularization into subspaces and applies ordinal contrastive learning to reach competitive in-domain and cross-domain performance with 5-20% labeled data.