[PDF][PDF] A comprehensive review of deep learning-based single image super-resolution

SMA Bashir, Y Wang, M Khan, Y Niu - PeerJ Computer Science, 2021 - peerj.com
Image super-resolution (SR) is one of the vital image processing methods that improve the
resolution of an image in the field of computer vision. In the last two decades, significant …

MFFN: image super-resolution via multi-level features fusion network

Y Chen, R Xia, K Yang, K Zou - The Visual Computer, 2024 - Springer
Deep convolutional neural networks can effectively improve the performance of single-
image super-resolution reconstruction. Deep networks tend to achieve better performance …

Distract your attention: Multi-head cross attention network for facial expression recognition

Z Wen, W Lin, T Wang, G Xu - Biomimetics, 2023 - mdpi.com
This paper presents a novel facial expression recognition network, called Distract your
Attention Network (DAN). Our method is based on two key observations in biological visual …

Research on image inpainting algorithm of improved total variation minimization method

Y Chen, H Zhang, L Liu, J Tao, Q Zhang… - Journal of Ambient …, 2023 - Springer
In order to solve the issue mismatching and structure disconnecting in exemplar-based
image inpainting, an image completion algorithm based on improved total variation …

An integrated deep multiscale feature fusion network for aeroengine remaining useful life prediction with multisensor data

X Li, H Jiang, Y Liu, T Wang, Z Li - Knowledge-based systems, 2022 - Elsevier
Most RUL prediction methods can only extract single-scale features, ignoring significant
details at other scales and layers. These methods are all constructed using one type of …

Lightweight image super-resolution based on deep learning: State-of-the-art and future directions

G Gendy, G He, N Sabor - Information Fusion, 2023 - Elsevier
Abstract Recently, super-resolution (SR) techniques based on deep learning have taken
more and more attention, aiming to improve the images and videos resolutions. Most of the …

MHAN: Multi-Stage Hybrid Attention Network for MRI reconstruction and super-resolution

W Wang, H Shen, J Chen, F Xing - Computers in Biology and Medicine, 2023 - Elsevier
High-quality magnetic resonance imaging (MRI) affords clear body tissue structure for
reliable diagnosing. However, there is a principal problem of the trade-off between …

Hybrid deep learning with optimal feature selection for speech emotion recognition using improved meta-heuristic algorithm

K Manohar, E Logashanmugam - Knowledge-Based Systems, 2022 - Elsevier
Speech emotion recognition is the crucial stream in emotional computing and also create
few issues owing to its complication in processing. The efficiency of the acoustic methods …

Deep attention fuzzy cognitive maps for interpretable multivariate time series prediction

D Qin, Z Peng, L Wu - Knowledge-Based Systems, 2023 - Elsevier
Although time series prediction is widely used to estimate the future state of complex
systems in various industries, accurate, interpretable and generalizable methods are still …

How well do pre-trained contextual language representations recommend labels for GitHub issues?

J Wang, X Zhang, L Chen - Knowledge-Based Systems, 2021 - Elsevier
Motivation: Open-source organizations use issues to collect user feedback, software bugs,
and feature requests in GitHub. Many issues do not have labels, which makes labeling time …