Normal Learning in Videos with Attention Prototype Network

by   Chao Hu, et al.

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than those of normal ones. Previous methods introduced the memory bank into AE, for encoding diverse normal patterns across the training videos. However, they are memory consuming and cannot cope with unseen new scenarios in the testing data. In this work, we propose a self-attention prototype unit (APU) to encode the normal latent space as prototypes in real time, free from extra memory cost. In addition, we introduce circulative attention mechanism to our backbone to form a novel feature extracting learner, namely Circulative Attention Unit (CAU). It enables the fast adaption capability on new scenes by only consuming a few iterations of update. Extensive experiments are conducted on various benchmarks. The superior performance over the state-of-the-art demonstrates the effectiveness of our method. Our code is available at


page 7

page 8


Making Reconstruction-based Method Great Again for Video Anomaly Detection

Anomaly detection in videos is a significant yet challenging problem. Pr...

Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings

Recent efforts towards video anomaly detection try to learn a deep autoe...

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that int...

Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detection

Frame prediction based on AutoEncoder plays a significant role in unsupe...

Learning Memory-guided Normality for Anomaly Detection

We address the problem of anomaly detection, that is, detecting anomalou...

Reasonable Anomaly Detection in Long Sequences

Video anomaly detection is a challenging task due to the lack in approac...

Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations

This paper aims to address the unsupervised video anomaly detection (VAD...

Code Repositories


Normal Learning in Videos with Attention Prototype Network

view repo

Please sign up or login with your details

Forgot password? Click here to reset