How do people watch AI-generated videos of physical scenes?

2026-02-03

AI Summary

This study investigates human gaze behavior and the underlying mechanisms of perceived realism when viewing videos of physically plausible scenes generated by artificial intelligence. Using eye-tracking, the visual attention of 40 participants was recorded while they watched both real and AI-generated videos, and their strategies were analyzed during tasks involving video comprehension and AI detection. The findings reveal, for the first time, that visual attention is primarily driven by subjective judgments of realism rather than the actual origin of the video. Moreover, when viewers are aware that content might be AI-generated, they shift from passive viewing to actively searching for anomalies. This highlights the critical role of “AI awareness” in shaping perceptual strategies and offers a novel perspective on how humans cognitively evaluate authenticity in human–AI interactions.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Video Understanding & Activity Analysis
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• AI-generated videos
• gaze behavior
• video authenticity
• human perception
• physical scenes

Innovation

• eye tracking
• AI-generated video
• gaze behavior
• perceived authenticity
• human-centered AI