Research map / Video / Video segmentation and tracking
Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection
Guoqiu Li, Guanxiong Cai, Xingyu Zeng, Rui 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 |
|---|---|---|---|
| add patch spatial relation (PSR) module (ablation) | SSRL · UCF-Crime | AUC: 85.98 -> 87.43 | Improved |
| add patch spatial relation (PSR) module (ablation) | SSRL · ShanghaiTech | AUC: 97.45 -> 97.98 | Improved |
| add multi-scale patch aggregation (MPA) without PSR (ablation) | RTFM baseline · UCF-Crime | AUC: 84.30 -> 85.98 | Improved |
| add multi-scale patch aggregation (MPA) without PSR (ablation) | RTFM baseline · ShanghaiTech | AUC: 97.21 -> 97.45 | Improved |
| extract patches at a single scale (ablation) | RTFM baseline · UCF-Crime | AUC: 84.30 -> 86.38 | Improved |
| extend from single scale to four scales of patches (ablation) | SSRL · UCF-Crime | AUC: 86.32 -> 87.43 | Improved |
| extend from single scale to four scales of patches (ablation) | SSRL · ShanghaiTech | AUC: 97.71 -> 97.98 | Improved |
| add dilated convolutions to PSR (ablation) | SSRL · UCF-Crime | AUC: 86.57 -> 87.43 | Improved |
| add no-local network to PSR (ablation) | SSRL · UCF-Crime | AUC: 86.22 -> 87.43 | Improved |
| share parameters across PSR modules | SSRL · UCF-Crime | AUC: 87.43 -> 86.85 | Hurt |
| share parameters across PSR modules | SSRL · ShanghaiTech | AUC: 97.98 -> 97.84 | Hurt |
| use SSRL instead of Video Swin Transformer backbone | Video Swin Transformer · UCF-Crime | AUC: 81.62 -> 87.43 | 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.
- MIST — MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection (CVPR 2021) · 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
- Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning (CVPR 2024 · similarity 0.89)
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.88)
- Federated Weakly Supervised Video Anomaly Detection with Multimodal Prompt (AAAI 2025 · similarity 0.87)
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree (NeurIPS 2025 · similarity 0.87)
- Just Dance with pi! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection (CVPR 2025 · similarity 0.87)
- Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model (AAAI 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.
