SGAP-Gaze fuses driver face, eye, and iris features with transformer attention over scene grids to estimate point-of-gaze, cutting mean pixel error by 23.5% versus prior models on a new urban driving dataset.
Speak2label: Using domain knowledge for creating a large scale driver gaze zone estimation dataset
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
-
SGAP-Gaze: Scene Grid Attention Based Point-of-Gaze Estimation Network for Driver Gaze
SGAP-Gaze fuses driver face, eye, and iris features with transformer attention over scene grids to estimate point-of-gaze, cutting mean pixel error by 23.5% versus prior models on a new urban driving dataset.