Estimating count and density maps from crowd images has a wide range of applications
such as video surveillance, traffic monitoring, public safety and urban planning. In addition …

With the increasing number of surveillance cameras in both indoor and outdoor locations,
there is a grown demand for an intelligent system that detects abnormal events. Although …

Trajectory prediction has been widely pursued in many fields, and many model-based and
model-free methods have been explored. The former include rule-based, geometric or …

Fast and automated recognizing of abnormal behaviors in crowded scenes is significantly
effective in increasing public security. The traditional procedure of recognizing abnormalities …

How to build a generic deep one-class (DeepOC) model to solve one-class classification
problems for anomaly detection, such as anomalous event detection in complex scenes …

Crowd counting and crowd density estimation methods are of great significance in the field
of public security. Estimating crowd density and counting from single image or video frame …

Most of the crowd abnormal event detection methods rely on complex hand-crafted features
to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have …

In the social production system, image data are rapidly generated from almost all fields such
as factories, hospitals, and transportation, promoting higher requirements for image anomaly …

Our work combines aspects of three promising paradigms in machine learning, namely,
attention mechanism, energy-based models, and associative memory. Attention is the power …

Deep anomaly detection, which utilizes neural networks to discover anomalies, is a vital
research topic in pattern recognition. With the burgeoning of inference mechanism …