Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection
Authors:
Preprint
Abstract
Detecting anomalies in human-related videos is crucial for surveillance applications. Current methods primarily include appearance-based and action-based techniques. Appearance-based methods rely on low-level visual features such as color, texture, and shape. They learn a large number of pixel patterns and features related to known scenes during training, making them effective in detecting anomalies within these familiar contexts. However, when encountering new or significantly changed scenes, i.e., unknown scenes, they often fail because existing SOTA methods do not effectively capture the relationship between actions and their surrounding scenes, resulting in low generalization. In contrast, action-based methods focus on detecting anomalies in human actions but are usually less informative because they tend to overlook the relationship between actions and their scenes, leading to incorrect detection. For instance, the normal event of running on the beach and the abnormal event of running on the street might both be considered normal due to the lack of scene information. In short, current methods struggle to integrate low-level visual and high-level action features, leading to poor anomaly detection in varied and complex scenes. To address this challenge, we propose a novel decoupling-based architecture for human-related video anomaly detection (DecoAD). DecoAD significantly improves the integration of visual and action features through the decoupling and interweaving of scenes and actions, thereby enabling a more intuitive and accurate understanding of complex behaviors and scenes. DecoAD supports fully supervised, weakly supervised, and unsupervised settings.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- Consistency-Based Self-supervised Learning for Temporal Anomaly Localization2023
- Human-related anomalous event detection via memory-augmented Wasserstein generative adversarial network with gradient penaltyPattern Recognition, 2023
- Human-related anomalous event detection via spatial-temporal graph convolutional autoencoder with embedded long short-term memory networkNeurocomputing, 2022
- A novel framework for detection of motion and appearance-based Anomaly using ensemble learning and LSTMsExpert Systems with Applications, 2022
- Skeleton-Based Action Recognition With Shift Graph Convolutional Network2020
- Skeleton Based Abnormal Behavior Recognition Using Spatio-Temporal Convolution and Attention-Based LSTMProcedia Computer Science, 2020
- CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark2019
- Real-World Anomaly Detection in Surveillance Videos2018
- Deep Residual Learning for Image Recognition2016
- FaceNet: A unified embedding for face recognition and clustering2015