Research map / Video / Video segmentation and tracking
Bayesian Nonparametric Submodular Video Partition for Robust 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 |
|---|---|---|---|
| Use BN-SVP rather than Zhong et al. (TSN RGB) | UCF-Crime anomaly detection · UCF-Crime | AUC (%): 82.12 -> 83.39 | Helped |
| Use BN-SVP rather than MMIL | ShanghaiTech anomaly detection · ShanghaiTech | AUC (%): 92.18 -> 96.00 | Helped |
| Use BN-SVP rather than Ilse et al. | Avenue anomaly detection · Avenue | AUC (%): 72.39 -> 80.87 | Helped |
| Use BN-SVP rather than Li & Vasconcelos | multimodal anomaly detection · Multimodal (UCF-Crime) | AUC (%): 70.96 -> 76.53 | Helped |
| Use BN-SVP rather than Li & Vasconcelos | outlier anomaly detection · Outlier (ShanghaiTech) | AUC (%): 90.95 -> 95.27 | Helped |
| Add self-transition augmentation (ρ = 1) (ablation) | BN-SVP · UCF-Crime | AUROC: 80.56 -> 83.39 | Helped |
| Add self-transition augmentation (ρ = 1) (ablation) | BN-SVP · Avenue | AUROC: 76.71 -> 80.87 | Helped |
| Add self-transition augmentation (ρ = 1) (ablation) | BN-SVP · Multimodal (UCF-Crime) | AUROC: 63.23 -> 76.53 | Helped |
| Add self-transition augmentation (ρ = 1) (ablation) | BN-SVP · ShanghaiTech | AUROC: 94.99 -> 96.00 | Helped |
| Add self-transition augmentation (ρ = 1) (ablation) | BN-SVP · Outlier (ShanghaiTech) | AUROC: 94.52 -> 95.27 | Helped |
| Choose ε in the relatively low 20–35% range (ablation) | BN-SVP representative-segment selection · Five evaluated datasets | AUC | No clear effect |
| Set κ too small, limiting representative segments (ablation) | BN-SVP representative-set size · Five evaluated datasets | AUC | Hurt |
Closest papers by meaning
- Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.85)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.85)
- MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection (CVPR 2024 · similarity 0.84)
- Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity (CVPR 2025 · similarity 0.84)
- TAIL-MIL: Time-Aware and Instance-Learnable Multiple Instance Learning for Multivariate Time Series Anomaly Detection (AAAI 2025 · similarity 0.84)
- Towards Multi-Domain Learning for Generalizable Video Anomaly Detection (NeurIPS 2024 · similarity 0.84)
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.