SeeTN builds a semantic embedding space with prototype transformation and affinity regularization to identify and correct noisy labels, yielding better cross-domain gaze estimation without hurting source accuracy.
Experiments on the Synthetic Noisy Dataset First, we provide an explanation of the rationale underly- ing the synthetic noisy dataset design
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
-
See Through the Noise: Improving Domain Generalization in Gaze Estimation
SeeTN builds a semantic embedding space with prototype transformation and affinity regularization to identify and correct noisy labels, yielding better cross-domain gaze estimation without hurting source accuracy.