# RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection

arXiv: https://arxiv.org/abs/2202.06256 · HTML: https://mlsanity.com/paper/2202.06256/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 13 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (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)
- [Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://mlsanity.com/paper/2011.07491/) (2020)
- [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](https://mlsanity.com/paper/2004.07657/) (2020)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds](https://mlsanity.com/paper/1706.07680/) (2017)
- [Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features](https://mlsanity.com/paper/2010.07524/) (2020)
- [STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection](https://mlsanity.com/paper/1804.08381/) (2018)
- [FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation](https://mlsanity.com/paper/2106.08613/) (2021)
- [Hybrid Deep Network for Anomaly Detection](https://mlsanity.com/paper/1908.06347/) (2019)
- [Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal](https://mlsanity.com/paper/1904.06633/) (2019)

## Built on by (most cited first, 1 of 1)

- [Deep Crowd Anomaly Detection: State-of-the-Art, Challenges, and Future Research Directions](https://mlsanity.com/paper/2210.13927/) (2022)

## Abstract (arXiv)

Recent anomaly detection algorithms have shown powerful performance by adopting frame predicting autoencoders. However, these methods face two challenging circumstances. First, they are likely to be trained to be excessively powerful, generating even abnormal frames well, which leads to failure in detecting anomalies. Second, they are distracted by the large number of objects captured in both foreground and background. To solve these problems, we propose a novel superpixel-based video data transformation technique named Random Superpixel Erasing on Moving Objects (RandomSEMO) and Moving Object Loss (MOLoss), built on top of a simple lightweight autoencoder. RandomSEMO is applied to the moving object regions by randomly erasing their superpixels. It enforces the network to pay attention to the foreground objects and learn the normal features more effectively, rather than simply predicting the future frame. Moreover, MOLoss urges the model to focus on learning normal objects captured within RandomSEMO by amplifying the loss on the pixels near the moving objects. The experimental results show that our model outperforms state-of-the-arts on three benchmarks.