Glossary
The language of attention, in plain English.
Every term behind predictive attention — defined in one sentence, then explained with how it's measured and a real example. No jargon, no fluff.
Saliency map
A saliency map is a grayscale prediction of where human eyes are most likely to look in an image, brightest where attention concentrates.
Read→Attention heatmap
An attention heatmap is a color overlay showing where visitors focus on a page — warm colors for high attention, cool for low.
Read→Predictive eye tracking
Predictive eye tracking uses an AI saliency model to estimate where people will look on an image or page, replacing the need for a lab, hardware eye-trackers, or live participants.
Read→F-pattern
The F-pattern is a common eye-scanning path on text-heavy pages: readers sweep across the top, drop down and sweep across a shorter second line, then scan vertically down the left edge — tracing a shape like the letter F.
Read→Z-pattern
The Z-pattern is an eye-scanning path on simple, visual-first layouts: the eye moves across the top, diagonally down to the opposite corner, then across the bottom — tracing a Z.
Read→Above the fold
Above the fold is the part of a web page visible without scrolling, on a given device.
Read→Visual hierarchy
Visual hierarchy is the arrangement of page elements by importance so the eye processes them in the intended order.
Read→Scroll depth
Scroll depth measures how far down a page visitors travel, usually as the percentage who reach a given point.
Read→