Computer vision techniques, in conjunction with acquisition through remote cameras and
unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure …

Biometric systems have the goal of measuring and analyzing the unique physical or
behavioral characteristics of an individual. The main feature of biometric systems is the use …

Object recognition requires a generalization capability to avoid overfitting, especially when
the samples are extremely few. Generalization from limited samples, usually studied under …

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL)
methods: the pre-trained knowledge is indeed a confounder that limits the performance. This …

Clustering is a class of unsupervised learning methods that has been extensively applied
and studied in computer vision. Little work has been done to adapt it to the end-to-end …

Object detection, one of the most fundamental and challenging problems in computer vision,
seeks to locate object instances from a large number of predefined categories in natural …

Face recognition has made extraordinary progress owing to the advancement of deep
convolutional neural networks (CNNs). The central task of face recognition, including face …

One of the main challenges in feature learning using Deep Convolutional Neural Networks
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …

Vehicle and pedestrian detection is one of the critical tasks in autonomous driving. Since
heterogeneous techniques have been proposed, the selection of a detection system with an …

Although deep neural networks (DNNs) have achieved great success in many tasks, they
can often be fooled by\emph {adversarial examples} that are generated by adding small but …