arXiv AI
Diffusion models for eye-gaze trajectory generation using position and velocity representations
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Aug 25
Motion-Based Tokenization for Cross-Dataset Egocentric Gaze Modeling
arXiv:2608.22926v1 Announce Type: new Abstract: 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 trac...
arXiv Computer Vision
Sep 7
EyeMakeYou: Identity-, Task-, and Subjective-State-Conditioned Diffusion for High-Frequency Gaze Synthesis
EyeMakeYou is a multi‑conditional denoising diffusion model that synthesizes high‑frequency, subject‑specific gaze velocity sequences. It conditions on identity, task, and self‑reported subjective states (difficulty, mental tiredness, eye tiredness) to generate realistic 5‑second, 1000‑Hz bivariate gaze data from a reference trajectory. Experiments on the GazeBase dataset show that EyeMakeYou outperforms existing generative methods in spatial accuracy and real‑synthetic similarity while preserving task‑dependent associations with subjective reports.
arXiv Computer Vision
1d ago
GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning
arXiv:2609.17814v1 Announce Type: new Abstract: Diffusion models are increasingly used to generate synthetic training data, but precise label control remains difficult when the conditioning signal is...
arXiv AI
Aug 18
Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
arXiv:2608. 16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath.
arXiv AI
Sep 4
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
GazeFS is a model that predicts and stabilizes target‑centered gaze trajectories using a variable‑length gaze‑head history, without requiring target information during inference. It maps this history to the next target‑center direction and a short‑horizon Search/Focus estimate, improving focus target centering and reducing residual gaze error. Across 7,960 acquisition episodes from 30 participants, GazeFS reduces Focus episode bias, dispersion, and P90 target error by 0.182°, 0.257°, and 0.400°, respectively, while maintaining high phase‑balanced accuracy and AUPRC.
arXiv Machine Learning
Jun 15
Gaze Heads: How VLMs Look at What They Describe
arXiv:2606. 14703v1 Announce Type: cross Abstract: How a vision-language model internally solves the task of describing an image is far from obvious.