A weakly supervised learning framework for retinal eye tracking achieves sub-0.45 degree 95th-percentile gaze error in a 6-person cohort.
We then fine-tune the descriptor decoder using a triplet loss: Ldesc = X i∈K max(0, m+ϕ pos − 1 2 (ϕneg−rand +ϕ neg−hard)) (2) We refer readers to [8] for details of this loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Establishing Robust Retinal Eye Tracking: A Weakly Supervised Algorithmic Framework
A weakly supervised learning framework for retinal eye tracking achieves sub-0.45 degree 95th-percentile gaze error in a 6-person cohort.