Gaze Perception in Humans and CNN-Based Model

TL;DR

This study compares human and CNN-based gaze perception, revealing that humans are more influenced by scene context when inferring attention, highlighting differences in social attention mechanisms.

Contribution

It introduces a comparative analysis of human and CNN gaze inference, emphasizing the role of scene context in human judgments.

Findings

Humans are more influenced by scene context in gaze inference.

CNN model's gaze estimates are less affected by scene context.

Differences highlight distinct mechanisms in social attention perception.

Abstract

Making accurate inferences about other individuals' locus of attention is essential for human social interactions and will be important for AI to effectively interact with humans. In this study, we compare how a CNN (convolutional neural network) based model of gaze and humans infer the locus of attention in images of real-world scenes with a number of individuals looking at a common location. We show that compared to the model, humans' estimates of the locus of attention are more influenced by the context of the scene, such as the presence of the attended target and the number of individuals in the image.