What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Artificial intelligence, Pattern recognition, Artificial neural network, Computer vision and Machine learning are his primary areas of study.
The Artificial intelligence study combines topics in areas such as Algorithm and Generalization.
Zongben Xu has included themes like Noise reduction, Similarity, Multispectral image and Tensor in his Pattern recognition study.
His research in Artificial neural network intersects with topics in Convergence, Exponential stability, Nonlinear system, Benchmark and Topology.
The various areas that Zongben Xu examines in his Exponential stability study include Recurrent neural network and Mathematical optimization.
His Mathematical optimization research is multidisciplinary, relying on both Regularization, Chromosome and Applied mathematics.
His most cited work include:
- Image super-resolution using gradient profile prior (784 citations)
- $L_{1/2}$ Regularization: A Thresholding Representation Theory and a Fast Solver (602 citations)
- Image Inpainting by Patch Propagation Using Patch Sparsity (387 citations)
What are the main themes of his work throughout his whole career to date?
Zongben Xu spends much of his time researching Artificial intelligence, Algorithm, Mathematical optimization, Pattern recognition and Artificial neural network.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Machine learning and Computer vision.
His Algorithm research includes themes of Generalization and Markov chain.
His Mathematical optimization research also works with subjects such as
- Regularization, which have a strong connection to Compressed sensing,
- Convergence that connect with fields like Exponential stability.
His Artificial neural network research is multidisciplinary, incorporating perspectives in Function, Order and Applied mathematics.
His biological study spans a wide range of topics, including Upper and lower bounds and Mathematical analysis.
He most often published in these fields:
- Artificial intelligence (40.26%)
- Algorithm (21.30%)
- Mathematical optimization (20.52%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (40.26%)
- Pattern recognition (20.26%)
- Deep learning (7.01%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Pattern recognition, Deep learning, Algorithm and Artificial neural network.
Many of his studies involve connections with topics such as Machine learning and Artificial intelligence.
Pattern recognition is closely attributed to Pixel in his study.
His studies in Deep learning integrate themes in fields like Data-driven, Multimedia, Aerospace engineering and Scale.
The Algorithm study combines topics in areas such as Stochastic optimization, Communication channel, Detector and Nonlinear system.
Zongben Xu combines subjects such as Estimator, Realization, Parameterized complexity and Interval with his study of Artificial neural network.
Between 2018 and 2021, his most popular works were:
- Model-Driven Deep Learning for Physical Layer Communications (99 citations)
- Semi-Supervised Transfer Learning for Image Rain Removal (66 citations)
- A Graph-Based Semisupervised Deep Learning Model for PolSAR Image Classification (44 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Pattern recognition, Deep learning, Feature extraction and Pixel.
His Artificial intelligence research is mostly focused on the topic Differential evolution.
His work on Pattern recognition is being expanded to include thematically relevant topics such as Image.
His Deep learning study incorporates themes from Training set, Artificial neural network, Seismic inversion, Nonlinear system and Algorithm.
His studies deal with areas such as Image segmentation and Entropy as well as Feature extraction.
He interconnects Regularization, Perfusion, Piecewise and Tensor in the investigation of issues within Pixel.
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.
