Search Results - "Wang, Zhangyang"
-
1
DeepAffinity: interpretable deep learning of compound–protein affinity through unified recurrent and convolutional neural networks
Published in Bioinformatics (15-09-2019)“…Abstract Motivation Drug discovery demands rapid quantification of compound–protein interaction (CPI). However, there is a lack of methods that can predict…”
Get full text
Journal Article -
2
AOD-Net: All-in-One Dehazing Network
Published in 2017 IEEE International Conference on Computer Vision (ICCV) (01-10-2017)“…This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based…”
Get full text
Conference Proceeding -
3
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
Published in 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2019)“…Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the…”
Get full text
Conference Proceeding -
4
Pathogenesis and pathophysiology of idiopathic normal pressure hydrocephalus
Published in CNS neuroscience & therapeutics (01-12-2020)“…Idiopathic normal pressure hydrocephalus (iNPH), the most common type of adult‐onset hydrocephalus, is a potentially reversible neuropsychiatric entity…”
Get full text
Journal Article -
5
Studying Very Low Resolution Recognition Using Deep Networks
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to…”
Get full text
Conference Proceeding -
6
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
Published in IEEE transactions on pattern analysis and machine intelligence (01-03-2023)“…Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and…”
Get full text
Journal Article -
7
Learning Temporal Dynamics for Video Super-Resolution: A Deep Learning Approach
Published in IEEE transactions on image processing (01-07-2018)“…Video super-resolution (SR) aims at estimating a high-resolution video sequence from a low-resolution (LR) one. Given that the deep learning has been…”
Get full text
Journal Article -
8
Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
Published in International journal of computer vision (01-05-2021)“…Semantic segmentation is an extensively studied task in computer vision, with numerous methods proposed every year. Thanks to the advent of deep learning in…”
Get full text
Journal Article -
9
Semisupervised Hyperspectral Classification Using Task-Driven Dictionary Learning With Laplacian Regularization
Published in IEEE transactions on geoscience and remote sensing (01-03-2015)“…We present a semisupervised method for single-pixel classification of hyperspectral images. The proposed method is designed to address the special problematic…”
Get full text
Journal Article -
10
Conference on graphics, patterns and images
Published in Pattern recognition letters (01-07-2022)Get full text
Journal Article -
11
Enhance Visual Recognition Under Adverse Conditions via Deep Networks
Published in IEEE transactions on image processing (01-09-2019)“…Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality…”
Get full text
Journal Article -
12
Robust Video Super-Resolution with Learned Temporal Dynamics
Published in 2017 IEEE International Conference on Computer Vision (ICCV) (01-10-2017)“…Video super-resolution (SR) aims to generate a high-resolution (HR) frame from multiple low-resolution (LR) frames in a local temporal window. The inter-frame…”
Get full text
Conference Proceeding -
13
L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2020)“…Graph convolution networks (GCN) are increasingly popular in many applications, yet remain notoriously hard to train over large graph datasets. They need to…”
Get full text
Conference Proceeding -
14
A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives
Published in International journal of computer vision (01-04-2021)“…The capability of image deraining is a highly desirable component of intelligent decision-making in autonomous driving and outdoor surveillance systems. Image…”
Get full text
Journal Article -
15
Controllable Artistic Text Style Transfer via Shape-Matching GAN
Published in 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2019)“…Artistic text style transfer is the task of migrating the style from a source image to the target text to create artistic typography. Recent style transfer…”
Get full text
Conference Proceeding -
16
Learning Super-Resolution Jointly From External and Internal Examples
Published in IEEE transactions on image processing (01-11-2015)“…Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a low-resolution (LR) input. Image priors are commonly learned to…”
Get full text
Journal Article -
17
Editorial for the Special Issue on Advanced Machine Learning Techniques for Sensing and Imaging Applications
Published in Micromachines (Basel) (29-06-2022)“…Recent advances in machine learning, from large-scale optimization to building deep neural networks, are increasingly being applied in the emerging field of…”
Get full text
Journal Article -
18
D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…In this paper, we design a Deep Dual-Domain (D3) based fast restoration model to remove artifacts of JPEG compressed images. It leverages the large learning…”
Get full text
Conference Proceeding -
19
Hyperspectral Image Classification Using Similarity Measurements-Based Deep Recurrent Neural Networks
Published in Remote sensing (Basel, Switzerland) (01-01-2019)“…Classification is a common objective when analyzing hyperspectral images, where each pixel is assigned to a predefined label. Deep learning-based algorithms…”
Get full text
Journal Article -
20
Improving model fairness in image-based computer-aided diagnosis
Published in Nature communications (06-10-2023)“…Deep learning has become a popular tool for computer-aided diagnosis using medical images, sometimes matching or exceeding the performance of clinicians…”
Get full text
Journal Article