International journal of molecular sciences
34884555
Chemical compounds can be represented as attributed graphs. An attributed graph is a mathematical model of an object composed of two types of representations: nodes and edges. Nodes are individual components, and edges are relations between these com...
Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data inform...
IEEE transactions on visualization and computer graphics
34587079
Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present Neurocartography, an ...
Computational intelligence and neuroscience
35401728
The architectural drawings of traditional building constructions generally require some design knowledge of the architectural plan to be understood. With the continuous development of the construction industry, the use of three-dimensional (3D) virtu...
COVID-19 is a fatal disease caused by the SARS-CoV-2 virus that has caused around 5.3 Million deaths globally as of December 2021. The detection of this disease is a time taking process that have worsen the situation around the globe, and the disease...
IEEE transactions on visualization and computer graphics
34990365
The machine learning (ML) life cycle involves a series of iterative steps, from the effective gathering and preparation of the data-including complex feature engineering processes-to the presentation and improvement of results, with various algorithm...
IEEE transactions on visualization and computer graphics
35389868
The rapid development of Convolutional Neural Networks (CNNs) in recent years has triggered significant breakthroughs in many machine learning (ML) applications. The ability to understand and compare various CNN models available is thus essential. Th...
IEEE transactions on visualization and computer graphics
35120005
Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many othe...
IEEE transactions on pattern analysis and machine intelligence
34714739
High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imag...
IEEE transactions on visualization and computer graphics
35439135
Since 2016, we have witnessed the tremendous growth of artificial intelligence+visualization (AI+VIS) research. However, existing survey articles on AI+VIS focus on visual analytics and information visualization, not scientific visualization (SciVis)...