Research map / Video / Video segmentation and tracking
Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning
Yu Wang, Shengjie Zhao
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| use k-means instead of anomaly-connected components for frame grouping (ablation) | LAS-VAD · XD-Violence fine-grained | mAP AVG: 33.12 -> 36.89 | Improved |
| add all three components (ATT, ACC, IAM) to the baseline (ablation) | LAS-VAD · XD-Violence fine-grained | mAP AVG: 24.24 -> 36.89 | Improved |
| vary the LLM that generates anomaly attributes (ablation) | LAS-VAD · XD-Violence fine-grained | mAP AVG: 36.81 -> 36.89 | No clear effect |
| rectify visual adjacency with cross-modal similarity (eta from 0.1 to 0.5) (ablation) | LAS-VAD · XD-Violence fine-grained | mAP AVG: optimal eta = 0.5 | Mixed |
| use LAS-VAD instead of LEC-VAD | LEC-VAD · UCF-Crime fine-grained | mAP AVG: 13.56 -> 15.62 | Improved |
| use LAS-VAD instead of LEC-VAD with I3D | LEC-VAD · XD-Violence coarse | AP: 88.47 -> 89.96 | Improved |
Closest papers by meaning
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.94)
- Harnessing Large Language Models for Training-free Video Anomaly Detection (CVPR 2024 · similarity 0.90)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.90)
- Open-Vocabulary Video Anomaly Detection (CVPR 2024 · similarity 0.90)
- MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection (NeurIPS 2025 · similarity 0.89)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.89)
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.
