What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Pattern recognition
Zhao Zhang spends much of his time researching Artificial intelligence, Pattern recognition, Discriminative model, Feature extraction and Semi-supervised learning.
As part of his studies on Artificial intelligence, Zhao Zhang often connects relevant subjects like Graph.
His Pattern recognition research includes themes of Real image and Sparse matrix.
His Discriminative model research integrates issues from Classifier, K-SVD and Pattern recognition.
His Feature extraction research is multidisciplinary, incorporating elements of Subspace topology, Feature learning, Feature and Robustness.
His Sparse approximation research is multidisciplinary, incorporating perspectives in Representation and Projection.
His most cited work include:
- Robust Neighborhood Preserving Projection by Nuclear/L2,1-Norm Regularization for Image Feature Extraction (94 citations)
- Joint Low-Rank and Sparse Principal Feature Coding for Enhanced Robust Representation and Visual Classification (86 citations)
- Trace Ratio Optimization-Based Semi-Supervised Nonlinear Dimensionality Reduction for Marginal Manifold Visualization (82 citations)
What are the main themes of his work throughout his whole career to date?
Zhao Zhang focuses on Artificial intelligence, Pattern recognition, Discriminative model, Feature extraction and Robustness.
Graph is closely connected to Machine learning in his research, which is encompassed under the umbrella topic of Artificial intelligence.
In the field of Pattern recognition, his study on Semi-supervised learning overlaps with subjects such as Locality.
His work carried out in the field of Discriminative model brings together such families of science as Classifier, Sparse matrix and Sparse approximation, K-SVD.
His Feature extraction research includes elements of Salient, External Data Representation, Pixel, Principal component analysis and Iterative reconstruction.
His research integrates issues of Algorithm, Real image, Discriminant and Label propagation in his study of Robustness.
He most often published in these fields:
- Artificial intelligence (89.29%)
- Pattern recognition (78.06%)
- Discriminative model (26.53%)
What were the highlights of his more recent work (between 2020-2021)?
- Artificial intelligence (89.29%)
- Cluster analysis (17.86%)
- Pattern recognition (78.06%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Cluster analysis, Pattern recognition, Convolutional neural network and Feature learning.
His study of Dictionary learning is a part of Artificial intelligence.
His Cluster analysis study combines topics from a wide range of disciplines, such as Matrix decomposition, Subspace topology, Representation and Local optimum.
Zhao Zhang works in the field of Pattern recognition, namely Discriminative model.
The various areas that Zhao Zhang examines in his Discriminative model study include Graph regularization, Graph, Data mining, Content-based image retrieval and Relevance feedback.
The Convolutional neural network study which covers Feature that intersects with Optical character recognition and Residual.
Between 2020 and 2021, his most popular works were:
- Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion (20 citations)
- CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances (18 citations)
- Flexible Auto-Weighted Local-Coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering (14 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Pattern recognition
Artificial intelligence, Cluster analysis, Matrix decomposition, Iterative reconstruction and Data modeling are his primary areas of study.
His Artificial intelligence study integrates concerns from other disciplines, such as Machine learning and Pattern recognition.
His Cluster analysis study incorporates themes from Algorithm, Robustness and Feature vector.
His work deals with themes such as Optimization problem, Representation and Kernel, which intersect with Matrix decomposition.
His research in Iterative reconstruction intersects with topics in Normalization, Salient, Feature extraction and Block matrix.
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.
