Artificial intelligence generated content (AIGC), known as DeepFakes, has emerged as a growing concern because it is being utilized as a tool for spreading disinformation. While much research exists on identifying AI-generated text and images, research on detecting AI-generated videos is limited. Existing datasets for AI-generated videos detection exhibit limitations in terms of diversity, complexity, and realism. To address these issues, this paper focuses on AI-generated videos detection and constructs a diverse dataset named Chameleon. We generate videos through multiple generation tools and various real video sources. At the same time, we preserve the videos' real-world complexity, including scene switches and dynamic perspective changes, and expand beyond face-centered detection to include human actions and environment generation. Our work bridges the gap between AI-generated dataset construction and real-world forensic needs, offering a valuable benchmark to counteract the evolving threats of AI-generated content.
View on arXiv@article{zeng2025_2503.06624,
title={ Chameleon: On the Scene Diversity and Domain Variety of AI-Generated Videos Detection },
author={ Meiyu Zeng and Xingming Liao and Canyu Chen and Nankai Lin and Zhuowei Wang and Chong Chen and Aimin Yang },
journal={arXiv preprint arXiv:2503.06624},
year={ 2025 }
}