Research map / Video / Video segmentation and tracking
Fine-VAD: Towards Fine-Grained Video Anomaly Detection via Progressive Cross-Granularity Learning
Menghao Zhang, Yiyan Zhu, Pengfei Ren, Haifeng Sun, Qi Qi, Zirui Zhuang, Huazheng Wang, Lei Zhang, Jianxin Liao, Jingyu Wang
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 coarse-level binary alignment to fine-only training (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 8.64 -> 10.93 | Improved |
| add intermediate-level pseudo macro-category guidance to fine-only training (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 8.64 -> 11.60 | Improved |
| use all three levels (coarse, intermediate, fine) together (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 10.93 -> 14.99 | Improved |
| remove the temporal adapter (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 14.99 -> 5.62 | Hurt |
| swap LGT-Adapter for Transformer, GCN, Axial TF or TA adapters (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 14.99 -> 12.01 to 14.56 | Hurt |
| add coarse-level contrastive loss Lcts (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 10.93 -> 12.90 | Improved |
| add supervised loss (Lmce or Lmce+Lcts) at intermediate level (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 14.99 -> 12.58 / 11.96 | Hurt |
| add contrastive loss at fine level on top of Lrefine (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 14.99 -> 14.86 | No clear effect |
| add contrastive loss Lcts at coarse level together with Lrefine (ablation) | Fine-VAD · UCF-Crime | AVG mAP (%): 12.07 -> 14.99 | Improved |
| vary number of pseudo macro-categories K (2,3,4,5) (ablation) | Fine-VAD · UCF-Crime and XD-Violence | AVG mAP (%): K=4: 14.99 / 31.87; K=2: 9.14 / 27.74; K=5: 12.37 / 25.88 | Mixed |
| apply progressive cross-granularity paradigm to I3D (FineCNN) | I3D baseline · UCF-Crime | AVG mAP (%): 3.24 -> 6.21 | Improved |
| apply progressive cross-granularity paradigm to I3D (FineCNN) | I3D baseline · XD-Violence | AVG mAP (%): 11.65 -> 13.58 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ExVAD — Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models (ICML 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models (ICML 2025 · similarity 0.92)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.91)
- Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity (CVPR 2025 · similarity 0.90)
- Track Any Anomalous Object:A Granular Video Anomaly Detection Pipeline (CVPR 2025 · similarity 0.89)
- Harnessing Large Language Models for Training-free Video Anomaly Detection (CVPR 2024 · similarity 0.88)
- Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning (CVPR 2024 · 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.
