SENSE-VAD Benchmark
Explore score history ↗SENSE-VAD is a synthetic video anomaly detection dataset for autonomous driving, generated with CARLA and Unreal Engine. It includes socially complex anomalies across five categories with per-frame binary labels, plus real-world videos for sim-to-real transfer.
- Released
- 2026-06-30
- Institutions
- University of South Florida
- Evaluates
- Autonomous Driving, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SENSE-VAD paper
No reported scores are on record for this benchmark yet.