# Gaze Perception in Humans and CNN-Based Model

arXiv: https://arxiv.org/abs/2104.08447 · HTML: https://mlsanity.com/paper/2104.08447/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 25 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 3 of 3)

- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [Detecting Attended Visual Targets in Video](https://mlsanity.com/paper/2003.02501/) (2020)

## Built on by (most cited first, 2 of 2)

- [Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues](https://mlsanity.com/paper/2506.05412/) (2025)
- [Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models](https://mlsanity.com/paper/2607.09654/) (2026)

## Abstract (arXiv)

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.