Saved in:
Bibliographic Details
Main Authors: Shi, Danqing, Jiang, Lan, Collins, Katherine M., Wu, Shangzhe, Tewari, Ayush, Zilka, Miri
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.03374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913112025726976
author Shi, Danqing
Jiang, Lan
Collins, Katherine M.
Wu, Shangzhe
Tewari, Ayush
Zilka, Miri
author_facet Shi, Danqing
Jiang, Lan
Collins, Katherine M.
Wu, Shangzhe
Tewari, Ayush
Zilka, Miri
contents The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watch AI-generated videos offers a human-centered perspective for improving AI detection and guiding advancements in video generation. However, existing studies have not investigated human gaze behavior in response to AI-generated videos of physical scenes. Here, we collect and analyze the eye movements from 40 participants during video understanding and AI detection tasks involving a mix of real-world and AI-generated videos. We find that given the high realism of AI-generated videos, gaze behavior is driven less by the video's actual authenticity and more by the viewer's perception of its authenticity. Our results demonstrate that the mere awareness of potential AI generation may alter media consumption from passive viewing into an active search for anomalies.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03374
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How do people watch AI-generated videos of physical scenes?
Shi, Danqing
Jiang, Lan
Collins, Katherine M.
Wu, Shangzhe
Tewari, Ayush
Zilka, Miri
Human-Computer Interaction
The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watch AI-generated videos offers a human-centered perspective for improving AI detection and guiding advancements in video generation. However, existing studies have not investigated human gaze behavior in response to AI-generated videos of physical scenes. Here, we collect and analyze the eye movements from 40 participants during video understanding and AI detection tasks involving a mix of real-world and AI-generated videos. We find that given the high realism of AI-generated videos, gaze behavior is driven less by the video's actual authenticity and more by the viewer's perception of its authenticity. Our results demonstrate that the mere awareness of potential AI generation may alter media consumption from passive viewing into an active search for anomalies.
title How do people watch AI-generated videos of physical scenes?
topic Human-Computer Interaction
url https://arxiv.org/abs/2602.03374