Anomalies are ubiquitous in real-world time-series data which call for effective and timely
detection, especially in an unsupervised setting for labeling cost saving. In this paper, we …

At present, the pointer meter recognition methods utilize the traditional image processing
techniques. Such techniques are complex, unstable, and unable to meet the requirements of …

Degeneration features extraction from multi-source monitoring data is significant for data-
driven based state assessment and RUL prediction of complex equipment. However, the …

The intelligent diagnosis of rolling bearing (RB) faults under different working conditions has
attracted significant attention. The two main limitations of existing domain-adaptation-based …

Abnormal event detection has attracted widespread attention due to its importance in video
surveillance scenarios. The lack of abnormally labeled samples makes this problem more …

Variational Autoencoders is one of the most valuable generative models in the field of
unsupervised learning. Due to its own construction characteristics, Variational Autoencoders …

Video abnormal event detection is a challenging problem in pattern recognition field.
Existing methods usually design the two steps of video feature extraction and anomaly …

Significant interest and progress have been drawn to the recent advancements in image
creation using deep generative model, but the field of automatic three-dimensional shape …

Video surveillance systems have been widely deployed in public places such as shopping
malls, hospitals, banks, and streets to improve the safety of public life and assets. In most …

Abstract Probabilistic Graphical Models (PGMs) are important and active research areas in
machine learning and artificial intelligence. The well-known representatives of PGMs …