Variational Bayesian Learning of Generalized Dirichlet-Based Hidden Markov Models Applied to Unusual Events Detection

Self-Supervised Attentive Generative Adversarial Networks for Video Anomaly Detection

Video anomaly detection (VAD) refers to the discrimination of unexpected events in videos. The deep generative model (DGM)-based method learns the regular patterns on normal videos and expects the learned model to yield larger generative errors for abnormal frames. However, DGM cannot always do so, since it usually captures the shared patterns between normal and abnormal events, which results in similar generative errors for them. In this article, we propose a novel self-supervised framework for unsupervised VAD to tackle the above-mentioned problem. To this end, we design a novel self-supervised attentive generative adversarial network (SSAGAN), which is composed of the self-attentive predictor, the vanilla discriminator, and the self-supervised discriminator. On the one hand, the self-attentive predictor can capture the long-term dependences for improving the prediction qualities of normal frames. On the other hand, the predicted frames are fed to the vanilla discriminator and self-supervised discriminator for performing true-false discrimination and self-supervised rotation detection, respectively. Essentially, the role of the self-supervised task is to enable the predictor to encode semantic information into the predicted normal frames via adversarial training, in order for the angles of rotated normal frames can be detected. As a result, our self-supervised framework lessens the generalization ability of the model to abnormal frames, resulting in larger detection errors for abnormal frames. Extensive experimental results indicate that SSAGAN outperforms other state-of-the-art methods, which demonstrates the validity and advancement of SSAGAN.

Abnormal Event Detection and Localization via Adversarial Event Prediction

We present adversarial event prediction (AEP), a novel approach to detecting abnormal events through an event prediction setting. Given normal event samples, AEP derives the prediction model, which can discover the correlation between the present and future of events in the training step. In obtaining the prediction model, we propose adversarial learning for the past and future of events. The proposed adversarial learning enforces AEP to learn the representation for predicting future events and restricts the representation learning for the past of events. By exploiting the proposed adversarial learning, AEP can produce the discriminative model to detect an anomaly of events without complementary information, such as optical flow and explicit abnormal event samples in the training step. We demonstrate the efficiency of AEP for detecting anomalies of events using the UCSD-Ped, CUHK Avenue, Subway, and UCF-Crime data sets. Experiments include the performance analysis depending on hyperparameter settings and the comparison with existing state-of-the-art methods. The experimental results show that the proposed adversarial learning can assist in deriving a better model for normal events on AEP, and AEP trained by the proposed adversarial learning can surpass the existing state-of-the-art methods.

Deep End-to-End One-Class Classifier

One-class classification (OCC) poses as an essential component in many machine learning and computer vision applications, including novelty, anomaly, and outlier detection systems. With a known definition for a target or normal set of data, one-class classifiers can determine if any given new sample spans within the distribution of the target class. Solving for this task in a general setting is particularly very challenging, due to the high diversity of samples from the target class and the absence of any supervising signal over the novelty (nontarget) concept, which makes designing end-to-end models unattainable. In this article, we propose an adversarial training approach to detect out-of-distribution samples in an end-to-end trainable deep model. To this end, we jointly train two deep neural networks, R and D . The latter plays as the discriminator while the former, during training, helps D characterize a probability distribution for the target class by creating adversarial examples and, during testing, collaborates with it to detect novelties. Using our OCC, we first test outlier detection on two image data sets, Modified National Institute of Standards and Technology (MNIST) and Caltech-256. Then, several experiments for video anomaly detection are performed on University of Minnesota (UMN) and University of California, San Diego (UCSD) data sets. Our proposed method can successfully learn the target class underlying distribution and outperforms other approaches.

The Cubic Dynamic Uncertain Causality Graph: A Methodology for Temporal Process Modeling and Diagnostic Logic Inference

To meet the demand for dynamic and highly reliable real-time fault diagnosis for complex systems, we extend the dynamic uncertain causality graph (DUCG) by proposing novel temporal causality modeling and reasoning methods. A new methodology, the Cubic DUCG, is therefore developed. It exploits an efficient scheme for compactly representing and accurately reasoning about the dynamic causalities in the system fault-spreading process. The Cubic DUCG is characterized by: 1) continuous generation of a causality graph that allows for causal connections penetrating among any number of time slices and discards the restrictive assumptions (about the underlying graph structure) upon which the existing research commonly relies; 2) a modeling scheme of complex causalities that includes dynamic negative feedback loops in a natural and intuitive manner; 3) a rigorous and reliable inference algorithm based on complete causalities that reflect real-time fault situations rather than on the cumulative aggregation of static time slices; and 4) some solutions to causality simplification and reduction, graphical transformation, and logical reasoning, for the sake of reducing the reasoning complexity. A series of fault diagnosis experiments on a nuclear power plant simulator verifies the accuracy, robustness, and efficiency of the proposed methodology.