# Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors

arXiv: https://arxiv.org/abs/2306.12041 · HTML: https://mlsanity.com/paper/2306.12041/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 114 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 30 of 58)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [Multiresolution Knowledge Distillation for Anomaly Detection](https://mlsanity.com/paper/2011.11108/) (2020)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://mlsanity.com/paper/2011.07491/) (2020)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection](https://mlsanity.com/paper/2111.09099/) (2021)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](https://mlsanity.com/paper/2004.07657/) (2020)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Street Scene: A new dataset and evaluation protocol for video anomaly detection](https://mlsanity.com/paper/1902.05872/) (2019)
- [A Survey of Single-Scene Video Anomaly Detection](https://mlsanity.com/paper/2004.05993/) (2020)

## Built on by (most cited first, 30 of 37)

- [Open-Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2311.07042/) (2023)
- [Advancing Video Anomaly Detection: A Concise Review and a New Dataset](https://mlsanity.com/paper/2402.04857/) (2024)
- [Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts](https://mlsanity.com/paper/2408.05905/) (2024)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer](https://mlsanity.com/paper/2509.26386/) (2025)
- [AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM](https://mlsanity.com/paper/2503.04504/) (2025)
- [Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model](https://mlsanity.com/paper/2412.09026/) (2024)
- [Anomize: Better Open Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2503.18094/) (2025)
- [Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks](https://mlsanity.com/paper/2503.22405/) (2025)
- [VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection](https://mlsanity.com/paper/2409.16225/) (2024)
- [Foundation Models and Transformers for Anomaly Detection: A Survey](https://mlsanity.com/paper/2507.15905/) (2025)
- [No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection](https://mlsanity.com/paper/2602.19248/) (2026)
- [Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks](https://mlsanity.com/paper/2511.19474/) (2025)
- [Autoregressive Denoising Score Matching is a Good Video Anomaly Detector](https://mlsanity.com/paper/2506.23282/) (2025)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World](https://mlsanity.com/paper/2511.00613/) (2025)
- [Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization](https://mlsanity.com/paper/2607.00622/) (2026)
- [Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detection](https://mlsanity.com/paper/2409.17608/) (2024)
- [From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning](https://mlsanity.com/paper/2502.05843/) (2025)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)
- [Focus on Texture: Rethinking Pre-training in Masked Autoencoders for Medical Image Classification](https://mlsanity.com/paper/2507.10869/) (2025)
- [Video Anomaly Detection with Semantics-Aware Information Bottleneck](https://mlsanity.com/paper/2506.02535/) (2025)
- [ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2506.08678/) (2025)
- [Road Obstacle Video Segmentation](https://mlsanity.com/paper/2509.13181/) (2025)
- [RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation](https://mlsanity.com/paper/2603.27165/) (2026)
- [Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving](https://mlsanity.com/paper/2406.06423/) (2024)
- [ModalFormer: Multimodal Transformer for Low-Light Image Enhancement](https://mlsanity.com/paper/2507.20388/) (2025)
- [VADMamba++: Efficient Video Anomaly Detection via Hybrid Modeling in Grayscale Space](https://mlsanity.com/paper/2604.00360/) (2026)
- [QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection](https://mlsanity.com/paper/2604.03040/) (2026)

## Abstract (arXiv)

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First, we introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. Second, we integrate a teacher decoder and a student decoder into our architecture, leveraging the discrepancy between the outputs given by the two decoders to improve anomaly detection. Third, we generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames (without anomalies) and the corresponding pixel-level anomaly maps. Our design leads to an efficient and effective model, as demonstrated by the extensive experiments carried out on four benchmarks: Avenue, ShanghaiTech, UBnormal and UCSD Ped2. The empirical results show that our model achieves an excellent trade-off between speed and accuracy, obtaining competitive AUC scores, while processing 1655 FPS. Hence, our model is between 8 and 70 times faster than competing methods. We also conduct an ablation study to justify our design. Our code is freely available at: https://github.com/ristea/aed-mae.