构建678万规模视频检测数据集，助力识别真实与生成视频。
GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection
- 收集678万视频，覆盖11种顶尖生成模型，跨源跨生成器设计。
- 在多种生成模型上测试，显著提升检测准确率。
- 适合安全、内容审核等领域研究者使用。
视频生成技术的快速发展使得真实视频与人工智能生成视频之间的区分愈发困难，亟需高效检测手段以防止虚假信息传播。然而，当前高性能检测模型的发展受限于缺乏大规模、高质量的生成视频检测数据集。为此，我们提出GenVidBench，一个具有多项优势的AI生成视频检测基准：1）大规模视频采集：包含678万条视频，是目前最大规模的生成视频检测数据集；2）跨源与跨生成器设计：减少视频内容干扰，确保训练集与测试集间属性多样性，避免过拟合；3）涵盖11种前沿生成模型，覆盖最新技术进展，保证数据多样性和代表性。此外，我们还基于先进视频分类模型进行了广泛实验。该数据集可有效支持检测模型的开发与评估。数据集与代码已公开：https://genvidbench.github.io。
原文摘要 · Abstract (English)
The rapid advancement of video generation models has made it increasingly challenging to distinguish AI-generated videos from real ones. This issue underscores the urgent need for effective AI-generated video detectors to prevent the dissemination of false information via such videos. However, the development of high-performance AI-generated video detectors is currently impeded by the lack of large-scale, high-quality datasets specifically designed for generative video detection. To this end, we introduce GenVidBench, a challenging AI-generated video detection dataset with several key advantages: 1) Large-scale video collection: The dataset contains 6.78 million videos and is currently the largest dataset for AI-generated video detection. 2) Cross-Source and Cross-Generator: The cross-source generation reduces the interference of video content on the detection. The cross-generator ensures diversity in video attributes between the training and test sets, preventing them from being overly similar. 3) State-of-the-Art Video Generators: The dataset includes videos from 11 state-of-the-art AI video generators, ensuring that it covers the latest advancements in the field of video generation. These generators ensure that the datasets are not only large in scale but also diverse, aiding in the development of generalized and effective detection models. Additionally, we present extensive experimental results with advanced video classification models. With GenVidBench, researchers can efficiently develop and evaluate AI-generated video detection models.. Datasets and code are available at https://genvidbench.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。