Research map / Video / Video segmentation and tracking
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add UBnormal training anomalies to the pseudo-abnormal pool (ablation) | Georgescu anomaly detector · UBnormal test | micro AUC: 59.3 -> 61.3 | Helped |
| Fine-tune the pre-trained model on UBnormal (ablation) | Sultani · UBnormal test | micro AUC: 49.5 -> 50.3 | Helped |
| Use 1/8 or 1/4 rather than 1/32 video sample rate (ablation) | TimeSformer · UBnormal test | micro AUC: 68.5 -> 64.1; 68.5 -> 61.9 | Hurt |
| Add the UBnormal normal-versus-abnormal proxy task T5 (ablation) | Georgescu multi-task detector · Avenue and ShanghaiTech | micro AUC: Avenue: 91.5 -> 91.9; ShanghaiTech: 82.4 -> 83.0 | Helped |
| Translate UBnormal objects with CycleGAN in addition to T5 (ablation) | Georgescu multi-task detector · Avenue and ShanghaiTech | micro AUC: Avenue: 91.9 -> 93.0; ShanghaiTech: 83.0 -> 83.7 | Helped |
Closest papers by meaning
- Real-World Anomaly Detection in Surveillance Videos (CVPR 2018 · similarity 0.89)
- Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection (NeurIPS 2025 · similarity 0.89)
- Open-Vocabulary Video Anomaly Detection (CVPR 2024 · similarity 0.88)
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.88)
- Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity (CVPR 2025 · similarity 0.88)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
