Active learning has been utilized as an efficient tool in building anoma...
Most deep anomaly detection models are based on learning normality from
...
One-class classification has been a prevailing method in building deep
a...
In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which...
Recently, vehicle re-identification methods based on deep learning const...
This paper addresses unsupervised person re-identification (Re-ID) using...
The key challenge of unsupervised vehicle re-identification (Re-ID) is
l...
Traffic scene recognition, which requires various visual classification
...
In skeleton-based action recognition, graph convolutional networks (GCNs...
In the past few years, the performance of road defect detection has been...
We propose a condition-adaptive representation learning framework for th...
This paper addresses a boosting method for mapping functionality of neur...
This paper proposes a new evaluation metric and boosting method for weig...