4 citations · 4 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Motion-Based Tokenization for Cross-Dataset Egocentric Gaze Modeling
Virmarie Maquiling, Zhuojiang Cai, Enkelejda Kasneci
Gaze is increasingly used as an input signal for vision and multimodal models, yet no consensus exists on how to represent it across datasets. Raw traces preserve detail but are no…
cs.CV2026
GazeOnce360: Fisheye-Based 360° Multi-Person Gaze Estimation with Global-Local Feature Fusion
Zhuojiang Cai, Zhenghui Sun, Feng Lu
We present GazeOnce360, a novel end-to-end model for multi-person gaze estimation from a single tabletop-mounted upward-facing fisheye camera. Unlike conventional approaches that r…