In the early days, content-based image retrieval (CBIR) was studied with global features.
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …

Human activity recognition (HAR) aims to recognize activities from a series of observations
on the actions of subjects and the environmental conditions. The vision‐based HAR …

Abstract We present Momentum Contrast (MoCo) for unsupervised visual representation
learning. From a perspective on contrastive learning as dictionary look-up, we build a …

Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …

Remarkable progress has been made in image recognition, primarily due to the availability
of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs …

Learning efficient image representations is at the core of the scene classification task of
remote sensing imagery. The existing methods for solving the scene classification task …

The increasing integration of the Internet of Everything into the industrial value chain has
built the foundation for the next industrial revolution called Industrie 4.0. Although Industrie …

Class imbalance is a common problem in the case of real-world object detection and
classification tasks. Data of some classes are abundant, making them an overrepresented …

Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been
shown to significantly improve speech recognition performance over the conventional …

Existing deep convolutional neural networks (CNNs) require a fixed-size (eg, 224 224) input
image. This requirement is “artificial” and may reduce the recognition accuracy for the …