A look at the technology behind our platforms

March 21, 2024
Visualisation of an artificial neural network (ANN) on a cover page
Coert van Gemeren
Written by

Coert van Gemeren

In short...

The artificial neural network powering expoze.io was first exposed to millions of images to learn to detect objects, and subsequently trained on thousands of images to learn to generate the correct attention heatmaps.

It uses all this experience when generating the attention prediction results for your image or video. That is why it is possible that when you click “create new heatmap” your attention heatmap matches real eye tracking results with an accuracy of 95%.

Download the whitepaper

Click here to read the whitepaper

Related Insights
sunweb

Too Many Opinions, One Clear Winner: How Sunweb Picked the Right Ad with AI

Discover how Sunweb boosted ad effectiveness by 57% using AI-powered insights from junbi—smarter edits, faster results, and better campaigns.

READ MORE
Many people standing side by side and looking at their phones

Psychology of Ads: Lessons from 5,000 YouTube Ad Tests

Learn what 5,000 YouTube ad tests reveal about how the brain responds to ads—and five psychology-backed ways to capture attention fast.

READ MORE
2 people arm wrestling and battle of the brands, automotive edition written in the center

YouTube AdWars: Battle of the Brands - Automotive Edition

We compared YouTube ads from 4 top automotive brands—Hyundai, Zeekr, Mazda, and Nissan—to see which performs best on junbi’s ad platform.

READ MORE

Subscribe to our monthly newsletter.

Stay ahead of the competition with a monthly summary of our top articles and new scientific research.