Microstructural characterization and analysis is the foundation of microstructural science,
connecting materials structure to composition, process history, and properties …

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 …

Current state-of-the-art image-text matching methods implicitly align the visual-semantic
fragments, like regions in images and words in sentences, and adopt cross-attention …

Urban land-use map** is a significant yet challenging task in the field of remote sensing.
Although numerous classification methods have been developed for obtaining land-use …

We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect
to a large indoor 3D map. The contributions of this work are three-fold. First, we develop a …

The goal of voice conversion is to transform source speech into a target voice, kee** the
content unchanged. In this paper, we focus on self-supervised representation learning for …

Understanding and interpreting classification decisions of automated image classification
systems is of high value in many applications, as it allows to verify the reasoning of the …

Benchmark datasets are critical for develo**, evaluating, and comparing remote sensing
image retrieval (RSIR) approaches. However, current benchmark datasets are deficient in …

We present an analysis of three possible strategies for exploiting the power of existing
convolutional neural networks (ConvNets or CNNs) in different scenarios from the ones they …

Automatic classification of tissue types of region of interest (ROI) plays an important role in
computer-aided diagnosis. In the current study, we focus on the classification of three types …