What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of study are Artificial intelligence, Pattern recognition, Machine learning, Background subtraction and Algorithm.
His study on Artificial intelligence is mostly dedicated to connecting different topics, such as Computer vision.
The various areas that Deyu Meng examines in his Pattern recognition study include Noise reduction, Iterative reconstruction and Noise.
As a part of the same scientific study, he usually deals with the Machine learning, concentrating on Weighting and frequently concerns with Multimedia search, Heuristic, Continuous function, Classifier and Training set.
Deyu Meng combines subjects such as Robust principal component analysis, Norm and Mathematical optimization with his study of Background subtraction.
In his work, Iterated function, Thresholding and Contextual image classification is strongly intertwined with Image restoration, which is a subfield of Algorithm.
His most cited work include:
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2693 citations)
- Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision (315 citations)
- Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (296 citations)
What are the main themes of his work throughout his whole career to date?
Deyu Meng focuses on Artificial intelligence, Pattern recognition, Machine learning, Deep learning and Algorithm.
His Artificial intelligence study frequently draws connections to other fields, such as Computer vision.
Deyu Meng has included themes like Regularization, Noise reduction and Feature in his Pattern recognition study.
His work on Semi-supervised learning, Leverage and Supervised learning as part of general Machine learning research is frequently linked to Self paced, bridging the gap between disciplines.
His studies deal with areas such as Subspace topology, Mathematical optimization, Iterative reconstruction and Tensor as well as Algorithm.
His studies in Subspace topology integrate themes in fields like Mixture model and Optimization problem.
He most often published in these fields:
- Artificial intelligence (82.16%)
- Pattern recognition (44.98%)
- Machine learning (22.30%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (82.16%)
- Pattern recognition (44.98%)
- Deep learning (16.73%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Pattern recognition, Deep learning, Machine learning and Image are his primary areas of study.
His Artificial intelligence study combines topics in areas such as Generalization and Computer vision.
His biological study spans a wide range of topics, including Regularization, Noise reduction and Residual.
Noise is closely connected to Image restoration in his research, which is encompassed under the umbrella topic of Deep learning.
His Machine learning research integrates issues from Generative model and Benchmark.
Many of his research projects under Image are closely connected to Field with Field, tying the diverse disciplines of science together.
Between 2019 and 2021, his most popular works were:
- Hyperspectral Image Classification With Convolutional Neural Network and Active Learning (30 citations)
- A Model-Driven Deep Neural Network for Single Image Rain Removal (21 citations)
- A Fast Adaptive k-means with No Bounds. (16 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Deep learning, Image and Hyperspectral imaging.
As a member of one scientific family, Deyu Meng mostly works in the field of Artificial intelligence, focusing on Machine learning and, on occasion, Classifier.
His Pattern recognition study combines topics from a wide range of disciplines, such as Artificial neural network, Noise reduction and Image resolution.
His work deals with themes such as Ground truth, Voxel and Atlas, which intersect with Deep learning.
His work on Inpainting as part of general Image study is frequently linked to Scale, therefore connecting diverse disciplines of science.
His research investigates the connection with Hyperspectral imaging and areas like Multispectral image which intersect with concerns in Rank, Generative model and Image restoration.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
