Buckets:
13.2 GB
7 files
Updated 16 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| data | 2 items | ||
| .gitattributes | 2.46 kB xet | 19463de8 | |
| README.md | 3.46 kB xet | 6d463695 | |
| benign_data.json | 515 kB xet | 095444c0 | |
| harmful_data.json | 503 kB xet | a0418a6e | |
| video.tar.gz | 13.2 GB xet | 7b846ee7 |
Video-SafetyBench: A Benchmark for Safety Evaluation of Video-Language Understanding
🌐 Homepage | 🤗 Dataset | 📖 arXiv | GitHub
Dataset Details
Our dataset statistics and some examples are listed in the following:
License
The Video-SafetyBench is under the CC BY-NC-SA 4.0.
Ethics Statement
The dataset we created is intended solely for AI safety research and learning, with the goal of assessing the safety ability of current video LVLMs. Our data collection process does not involve user deanonymization, and as such, our work has been determined by our Institutional Review Board (IRB) not to constitute human subjects research.
- Total size
- 13.2 GB
- Files
- 7
- Last updated
- Oct 23
- Pre-warmed CDN
- US EU US EU