Research map / Video / Video-language understanding
Towards Trustworthy Video Anomaly Understanding: A Class-Guided Chain-of-Evaluation Metric and An Anomaly-focused Meta-Benchmark
Jiaxu Leng, Zhoujie Huang, Mingpi Tan, Zhanjie Wu, Xinbo Gao
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 |
|---|---|---|---|
| add anomalous event extraction and uniform rewriting (ablation) | CG-CoE (P) · AEA | rho_Prec: 0.682 -> 0.727 | Improved |
| add anomalous event extraction and uniform rewriting (ablation) | CG-CoE (P) · CVP | mean score variation (lower is better): 0.118 -> 0.072 | Improved |
| add compositional matching (ablation) | CG-CoE (P) · AEA | rho_Prec: 0.727 -> 0.772 | Improved |
| add compositional matching (ablation) | CG-CoE (P) · CVP | mean score variation (lower is better): 0.072 -> 0.063 | Improved |
| add class-guided tolerance boundary (ablation) | CG-CoE (P) · AEA | rho_Prec: 0.772 -> 0.800 | Improved |
| add class-guided tolerance boundary (ablation) | CG-CoE (R) · AEA | rho_Rec: 0.782 -> 0.813 | Improved |
| add class-guided tolerance boundary (ablation) | CG-CoE (R) · CVP | mean score variation (lower is better): 0.061 -> 0.051 | Improved |
| replace best LLM-based baseline (VAD-R1 classification) with CG-CoE | metric · AEA | rho_Prec: 0.731 -> 0.800 | Improved |
| replace HAWK (consistency) with CG-CoE | metric · CVP | mean score variation (lower is better): 0.099 -> 0.059 | Improved |
| replace BARTScore with CG-CoE | metric · AEA vs CVP | rho_Prec / variation: 0.313 -> 0.800; 0.008 -> 0.059 | Mixed |
| use Qwen3.5-9B or larger judge instead of 4B or smaller (ablation) | CG-CoE · LLM scale, 100 samples | evaluation reliability: N/A -> 0.861 | Improved |
| scale judge LLM from Qwen3.5-9B to 197B (ablation) | CG-CoE · LLM scale, CVP | mean score variation (lower is better): 0.121 -> 0.070 | Improved |
Closest papers by meaning
- Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity (CVPR 2025 · similarity 0.89)
- Open-Vocabulary Video Anomaly Detection (CVPR 2024 · similarity 0.88)
- Harnessing Large Language Models for Training-free Video Anomaly Detection (CVPR 2024 · similarity 0.86)
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought (NeurIPS 2025 · similarity 0.86)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.86)
- VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models (CVPR 2025 · similarity 0.86)
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.
