Audiovisual saliency maps (VIDEO)

eLife

Caption

In the model, the multisensory correlation detector lattice could predict where participants would look while watching audiovisual movies, acting as a lightweight “saliency model”. This is illustrated in this video: audiovisual saliency maps generated by the model align closely with human gaze behaviour, without the millions of parameters typical in machine vision.

Credit

Parise, eLife 2025 (CC BY 4.0)

Usage Restrictions

Credit must be given to the creator.

License

CC BY

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.