Research map / Video / Video segmentation and tracking
Appearance-Motion Memory Consistency Network for Video Anomaly Detection
Read the paperCheck 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 |
|---|---|---|---|
| Add appearance-motion memory consistency (ablation) | AMMC-Net · UCSD Ped2, CUHK Avenue, and ShanghaiTech | AUC: 95.1% -> 96.6%; 84.9% -> 86.6%; 71.5% -> 73.7% | Helped |
| Add the memory pool (ablation) | AMMC-Net baseline · UCSD Ped2 | AUC: 95.1% -> 95.3% | Helped |
| Add AMFT to the memory-pool model (ablation) | AMMC-Net · UCSD Ped2 | AUC: 95.3% -> 96.1% | Helped |
| Add the encoder feature to the AMFT model (ablation) | AMMC-Net · UCSD Ped2 | AUC: 96.1% -> 96.2% | Helped |
| Add the memory feature to the encoder-feature model (ablation) | AMMC-Net · UCSD Ped2 | AUC: 96.2% -> 96.4% | Helped |
| Add commit error during testing (ablation) | AMMC-Net feature-fusion model · UCSD Ped2 | AUC: 96.4% -> 96.6% | Helped |
| Use K=2 selected memory items instead of K=1, K=4, or K=6 (ablation) | AMMC-Net · UCSD Ped2 and CUHK Avenue | AUC: 0.959, 0.966, 0.959, 0.957; 0.855, 0.866, 0.859, 0.857 | Mixed |
| Vary memory-item dimension D (ablation) | AMMC-Net · UCSD Ped2 | AUC: 0.95, 0.966, 0.953, 0.956 | Mixed |
| Vary the number of memory items N (ablation) | AMMC-Net · UCSD Ped2 | AUC: 0.95, 0.966, 0.95, 0.959 | Mixed |
Closest papers by meaning
- Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection (AAAI 2022 · similarity 0.90)
- Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model (AAAI 2025 · similarity 0.86)
- Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection (AAAI 2025 · similarity 0.85)
- Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning (CVPR 2024 · similarity 0.85)
- Noise-Resistant Video Anomaly Detection via RGB Error-Guided Multiscale Predictive Coding and Dynamic Memory (CVPR 2025 · similarity 0.85)
- UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks (AAAI 2025 · similarity 0.84)
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.