Research map / Video / Video segmentation and tracking
A New Comprehensive Benchmark for Semi-Supervised Video Anomaly Detection and Anticipation
Congqi Cao, Yue Lu, Peng Wang, Yanning Zhang
AI-extracted. The measured effects below were read by AI from the paper's full text (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 scene-conditioned VAE (γ=1) instead of setting γ=0 (ablation) | Ours · NWPU Campus | AUC (%): 65.8 -> 68.2 | Improved |
| Add scene-conditioned VAE (γ=1) instead of setting γ=0 (ablation) | Ours · ShanghaiTech-sd | AUC (%): 70.4 -> 82.7 | Improved |
| Add backward prediction to forward prediction (ablation) | Ours for anomaly anticipation · NWPU Campus, anticipation times 0.5s to 3.0s | AUC (%): 65.2 -> 65.8; 64.6 -> 65.3; 64.2 -> 64.9; 63.6 -> 64.6; 63.1 -> 64.2; 62.5 -> 64.0 | Improved |
| Use the proposed method rather than the strongest listed baseline | Ours · ShanghaiTech | AUC (%): 78.2 -> 79.2 | Improved |
| Use the proposed method rather than the strongest listed baseline | Ours · CUHK Avenue | AUC (%): 91.1 -> 86.8 | Hurt |
| Use the proposed method rather than the strongest listed baseline | Ours · IITB Corridor | AUC (%): 73.5 -> 73.6 | Improved |
| Use the proposed method rather than the strongest listed baseline | Ours · NWPU Campus | AUC (%): 64.5 -> 68.2 | Improved |
| Extend the anticipation time | Ours (f+b) · NWPU Campus | AUC (%): 65.8 -> 64.0 | Hurt |
Closest papers by meaning
- Advancing Video Anomaly Detection: A Concise Review and a New Dataset (NeurIPS 2024 · similarity 0.88)
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.88)
- MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection (NeurIPS 2025 · similarity 0.88)
- Open-Vocabulary Video Anomaly Detection (CVPR 2024 · similarity 0.87)
- Track Any Anomalous Object:A Granular Video Anomaly Detection Pipeline (CVPR 2025 · similarity 0.87)
- 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.
