Research map / Video / Video segmentation and tracking
MIST: Multiple Instance Self-Training Framework for 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 |
|---|---|---|---|
| Use sparse continuous sampling rather than uniform sampling (ablation) | MIST MIL pseudo-label generator · UCF-Crime | AUC (%): 74.29 -> 75.51; +1.22 | Helped |
| Use sparse continuous sampling rather than uniform sampling (ablation) | MIST MIL pseudo-label generator · UCF-Crime | AUC (%): 78.72 -> 79.37; +0.65 | Helped |
| Use sparse continuous sampling rather than uniform sampling (ablation) | MIST MIL pseudo-label generator · ShanghaiTech | AUC (%): 83.68 -> 86.61; +2.93 | Helped |
| Use sparse continuous sampling rather than uniform sampling (ablation) | MIST MIL pseudo-label generator · ShanghaiTech | AUC (%): 83.10 -> 89.15; +6.05 | Helped |
| Add generated pseudo labels to encoder fine-tuning (ablation) | MIST with I3D · UCF-Crime | AUC (%): 73.33 -> 82.30; 8.17% | Helped |
| Add the self-guided attention module (ablation) | MIST with I3D · UCF-Crime | AUC (%): 80.28 -> 82.30; 2% | Helped |
| Add the guided-classification head H_g (ablation) | MIST with I3D · UCF-Crime | AUC (%): 81.97 -> 82.30; more than 2% | Helped |
| Use MIST fine-tuned I3D features instead of pretrained I3D features | AR-Net · UCF-Crime | AUC (%): 78.96 -> 82.62 | Helped |
| Use MIST fine-tuned I3D features instead of pretrained I3D features | AR-Net · ShanghaiTech | AUC (%): 85.38 -> 92.27 | Helped |
Closest papers by meaning
- Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.90)
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.89)
- Federated Weakly Supervised Video Anomaly Detection with Multimodal Prompt (AAAI 2025 · similarity 0.88)
- Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.88)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.88)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.88)
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.