RRVBench

# Realistic Rumor Video Benchmark (RRVBench) <p align="center"> <a href="https://arxiv.org/abs/2610.37918"><img src="https://img.shields.io/badge/arXiv-2610.37918-b31b1b?logo=arxiv" alt="arXiv"></a> <a href="https://github.com/inclusionAI/DefakerOne2"><img src="https://img.shields.io/badge/GitHub-Code-181717?logo=github" alt="GitHub"></a> <a href="https://www.modelscope.cn/models/DanceText/DefakerOne2"><img src="https://img.shields.io/badge/ModelScope-DefakerOne2-624AFF" alt="ModelScope Model"></a> <a href="https://www.modelscope.cn/models/DanceText/RRVBench"><img src="https://img.shields.io/badge/ModelScope-RRVBench-624AFF" alt="ModelScope RRVBench"></a> <a href="https://venus-guangjian.github.io/Venus-DeFakerOne2/"><img src="https://img.shields.io/badge/Project-Page-success" alt="Project Page"></a> </p> ### 1. Introduction RRVBench aims to benchmark forensic detection capabilities against frontier AI-Generated Content (AIGC) video engines under high-stakes, real-world rumor scenarios. RVBench comprises 1, 319 authentic videos sourced from RABench and 11, 000 synthetic videos produced by 11 modern generative architectures such as SeeDance2.5 and MinimaxH3. Real videos are located in the `RRVBench/real` directory, while fake videos are stored in the `RRVBench/generated` directory, where each subdirectory name denotes the corresponding video generator. ### 2. Download Command ``` modelscope download --dataset DanceText/RRVBench --local_dir [your target dataset] ``` ### 3. Examples <table> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/b1.gif" width="200" height="200" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/zhan2.gif" width="200" height="200" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/covid2.gif" width="200" height="200" alt="failed to load this example"></td> </tr> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/b2.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new5.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/o2.gif" width="200" height="100" alt="failed to load this example"></td> </tr> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/zhan1.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new4.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/zf1.gif" width="200" height="100" alt="failed to load this example"></td> </tr> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/bing1.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new1.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new2.gif" width="200" height="100" alt="failed to load this example"></td> </tr> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/bing2.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new3.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/o1.gif" width="200" height="100" alt="failed to load this example"></td> </tr> <tr> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/new6.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/covid1.gif" width="200" height="100" alt="failed to load this example"></td> <td><img src="https://github.com/venus-guangjian/Venus-DeFakerOne2/blob/main/videos/zf2.gif" width="200" height="100" alt="failed to load this example"></td> </tr> </table> ### 4. Citation ``` @misc{qu2026venusdefakerone2visionforensicsfoundationmodel, title={Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage}, author={Chenfan Qu and Yachao Liang and Mingqi Fang and Jiangwei Xie and Zhenming Wang and Baoyue Zhang and Changjiang Jiang and Zheng Chang and Fanli Jin and Xuekang Zhu and Kaiwen Feng and Junchi Li and Weihong Zhang and Haoyue Wang and Chenfeng Zhang and Yinan Xia and Fangming Cui and Dong Fan and Jingjing Liu and Tianyi Zhang and Luobin Chen and Ji-Zhe Zhou and Sheng Li and Wei Wang and Bin Li and Ran He and Xinpeng Zhang and Linna Zhou and Jian Liu and Weiqiang Wang}, year={2026}, eprint={2610.37918}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2610.37918}, } ```