What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Pattern recognition, Dimensionality reduction, Computer vision and Convolutional neural network are his primary areas of study.
His work on Artificial intelligence is being expanded to include thematically relevant topics such as Machine learning.
Shiming Xiang has included themes like Contextual image classification, Pixel, Regression analysis and Cluster analysis in his Pattern recognition study.
His Dimensionality reduction research includes elements of Linear discriminant analysis, Algorithm, Structure tensor, Principal component analysis and Calculus.
His Convolutional neural network study combines topics from a wide range of disciplines, such as Segmentation, End-to-end principle, Deep learning, Residual and Range.
His Feature extraction study deals with Artificial neural network intersecting with Iterative method.
His most cited work include:
- Efficient Image Dehazing with Boundary Constraint and Contextual Regularization (523 citations)
- Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks (404 citations)
- Learning a Mahalanobis distance metric for data clustering and classification (391 citations)
What are the main themes of his work throughout his whole career to date?
Shiming Xiang mostly deals with Artificial intelligence, Pattern recognition, Computer vision, Image and Feature extraction.
His study in Segmentation, Image segmentation, Convolutional neural network, Contextual image classification and Feature falls under the purview of Artificial intelligence.
While the research belongs to areas of Convolutional neural network, Shiming Xiang spends his time largely on the problem of Theoretical computer science, intersecting his research to questions surrounding Point.
His research in Pattern recognition intersects with topics in Pixel and Cluster analysis.
The concepts of his Image study are interwoven with issues in Machine learning and Representation.
His Linear discriminant analysis study combines topics in areas such as Curse of dimensionality and Dimensionality reduction.
He most often published in these fields:
- Artificial intelligence (79.45%)
- Pattern recognition (46.58%)
- Computer vision (32.42%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (79.45%)
- Pattern recognition (46.58%)
- Computer vision (32.42%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Pattern recognition, Computer vision, Convolutional neural network and Feature extraction.
All of his Artificial intelligence and Image, Object detection, Segmentation, Feature and Deep learning investigations are sub-components of the entire Artificial intelligence study.
His studies in Feature integrate themes in fields like Detector and Closed captioning.
His Pattern recognition study incorporates themes from Contextual image classification and Cluster analysis.
He focuses mostly in the field of Computer vision, narrowing it down to matters related to Focus and, in some cases, Semantics.
His Convolutional neural network study also includes
- Theoretical computer science and related Point and Representation,
- Point cloud together with Robustness and Relation.
Between 2017 and 2021, his most popular works were:
- Relation-Shape Convolutional Neural Network for Point Cloud Analysis (171 citations)
- DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (69 citations)
- RENAS: Reinforced Evolutionary Neural Architecture Search (39 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His primary scientific interests are in Artificial intelligence, Convolutional neural network, Pattern recognition, Feature extraction and Theoretical computer science.
Shiming Xiang performs multidisciplinary study on Artificial intelligence and Architecture in his works.
His Convolutional neural network research incorporates themes from Neural coding, Function approximation and Cluster analysis.
Shiming Xiang combines subjects such as Contextual image classification and Iterative reconstruction with his study of Pattern recognition.
His Feature extraction research includes themes of Machine learning, Prior probability, Range, RGB color model and Focus.
His Theoretical computer science research incorporates elements of Point and Representation.
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.
