# Learning Appearance-motion Normality for Video Anomaly Detection

arXiv: https://arxiv.org/abs/2207.13361 · HTML: https://mlsanity.com/paper/2207.13361/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events](https://mlsanity.com/paper/2008.11988/) (2020)
- [Continual Learning for Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/2004.07941/) (2020)
- [Unmasking the abnormal events in video](https://mlsanity.com/paper/1705.08182/) (2017)

## Built on by (most cited first, 17 of 17)

- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception](https://mlsanity.com/paper/2307.13933/) (2023)
- [Context De-confounded Emotion Recognition](https://mlsanity.com/paper/2303.11921/) (2023)
- [Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization](https://mlsanity.com/paper/2211.11236/) (2022)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [Robust Emotion Recognition in Context Debiasing](https://mlsanity.com/paper/2403.05963/) (2024)
- [Efficient Decision-based Black-box Patch Attacks on Video Recognition](https://mlsanity.com/paper/2303.11917/) (2023)
- [Privacy-Preserving Video Anomaly Detection: A Survey](https://mlsanity.com/paper/2411.14565/) (2024)
- [Adversarial Contrastive Distillation with Adaptive Denoising](https://mlsanity.com/paper/2302.08764/) (2023)
- [Explicit and Implicit Knowledge Distillation via Unlabeled Data](https://mlsanity.com/paper/2302.08771/) (2023)
- [VADMamba: Exploring State Space Models for Fast Video Anomaly Detection](https://mlsanity.com/paper/2503.21169/) (2025)
- [A novel efficient Multi-view traffic-related object detection framework](https://mlsanity.com/paper/2302.11810/) (2023)
- [Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detection](https://mlsanity.com/paper/2303.05116/) (2023)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [Multi-scale Spatial-temporal Interaction Network for Video Anomaly Detection](https://mlsanity.com/paper/2306.10239/) (2023)
- [Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality](https://mlsanity.com/paper/2403.09039/) (2024)
- [Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection](https://mlsanity.com/paper/2603.26745/) (2026)

## Abstract (arXiv)

Video anomaly detection is a challenging task in the computer vision community. Most single task-based methods do not consider the independence of unique spatial and temporal patterns, while two-stream structures lack the exploration of the correlations. In this paper, we propose spatial-temporal memories augmented two-stream auto-encoder framework, which learns the appearance normality and motion normality independently and explores the correlations via adversarial learning. Specifically, we first design two proxy tasks to train the two-stream structure to extract appearance and motion features in isolation. Then, the prototypical features are recorded in the corresponding spatial and temporal memory pools. Finally, the encoding-decoding network performs adversarial learning with the discriminator to explore the correlations between spatial and temporal patterns. Experimental results show that our framework outperforms the state-of-the-art methods, achieving AUCs of 98.1% and 89.8% on UCSD Ped2 and CUHK Avenue datasets.