Research map / Video / Video segmentation and tracking
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning
Read the paperCheck 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 the full CLAV, relative-distance, and CoMo framework | Ours · XD-Violence | Average Precision: 80.3 -> 81.3 | Helped |
| Use the full CLAV, relative-distance, and CoMo framework | Ours · CUHK Avenue | AUC: 80.9 -> 89.8 | Helped |
| Use the full CLAV, relative-distance, and CoMo framework | Ours · UCF-Crimes | AUC: 87.4 -> 86.1 | Hurt |
| Use the full CLAV, relative-distance, and CoMo framework | Ours · ShanghaiTech | AUC: 98.0 -> 97.6 | Hurt |
| Add ICA and CS to the model (ablation) | Ours · UCF-Crimes | AUC: 82.84 -> 83.83 | Helped |
| Add ICA (ablation) | MMIL · XD-Violence | Average Precision: 73.10 -> 76.85 | Helped |
| Add ICA (ablation) | Ours · UCF-Crimes | AUC: 83.26 -> 86.07 | Helped |
| Add ICA (ablation) | Ours · XD-Violence | Average Precision: 75.40 -> 81.31 | Helped |
| Add ICA (ablation) | Ours · ShanghaiTech | AUC: 96.19 -> 97.59 | Helped |
| Add relative-distance loss (ablation) | Ours · UCF-Crimes | AUC: 85.22 -> 86.07 | Helped |
| Add CoMo context-motion relation modeling (ablation) | Ours · UCF-Crimes | AUC: 85.22 -> 86.07 | Helped |
| Add CoMo context-motion relation modeling (ablation) | Ours · XD-Violence | Average Precision: 76.99 -> 81.31 | Helped |
Closest papers by meaning
- RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection (AAAI 2026 · similarity 0.91)
- The Road Less Seen: Segment Exploration for Weakly Supervised Video Anomaly Detection (CVPR 2026 · similarity 0.90)
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.89)
- Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.89)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.87)
- Just Dance with pi! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection (CVPR 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.