AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction

arXiv · AI, language, vision and robotics · article · Oct 6, 2026 · UTC

Video gaze prediction is led by gaze-trained models, yet gaze-free priors carry signal those models have not absorbed, if one knows when to trust them. We propose FocusGate, a gated ensemble of gaze-free priors whose members may abstain. A per-frame gate reads three shape statistics of a defocus map and selects the frames on which the estimator is above chance on average, so rejected frames reduce to the base exactly, while midrank normalisation lets an all-zero prior abstain at zero parameters. Gated fusion is significantly positive on film, sports and web video, whereas unconditional fusion

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-07T11:02:23.601Z. This is not the publication date.