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 investigation include Artificial intelligence, Pattern recognition, Computer vision, Facial recognition system and Feature extraction.
In his research on the topic of Artificial intelligence, Visualization is strongly related with Machine learning.
In his work, Scale-invariant feature transform is strongly intertwined with Kernel, which is a subfield of Pattern recognition.
His work on Partial occlusion as part of general Computer vision research is frequently linked to Partial permutation, bridging the gap between disciplines.
His Facial recognition system study combines topics from a wide range of disciplines, such as Image resolution and Image warping.
His Feature extraction research integrates issues from Deep learning, Image restoration and Feature detection.
His most cited work include:
- DehazeNet: An End-to-End System for Single Image Haze Removal (888 citations)
- PCANet: A Simple Deep Learning Baseline for Image Classification? (690 citations)
- Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks (327 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Pattern recognition, Computer vision, Machine learning and Benchmark.
His Artificial intelligence study focuses mostly on Image, Feature extraction, Deep learning, Object and Classifier.
Kui Jia has researched Feature extraction in several fields, including Regularization, Convolutional neural network, Feature detection and Visualization.
His studies deal with areas such as Cognitive neuroscience of visual object recognition, Contextual image classification, Facial recognition system, Pose and RGB color model as well as Pattern recognition.
His research in Computer vision intersects with topics in Representation, Hallucinating and Robustness.
His Benchmark research focuses on Object detection and how it relates to Spatial relation and Ground truth.
He most often published in these fields:
- Artificial intelligence (85.25%)
- Pattern recognition (44.26%)
- Computer vision (22.95%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (85.25%)
- Pattern recognition (44.26%)
- Object (14.75%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Pattern recognition, Object, Point cloud and Algorithm.
His work in Artificial intelligence is not limited to one particular discipline; it also encompasses Machine learning.
His research in Pattern recognition focuses on subjects like Pose, which are connected to Rigid transformation and Leverage.
His Object course of study focuses on Supervised learning and Euclidean space, Semantic analysis and Manifold.
The concepts of his Point cloud study are interwoven with issues in Theoretical computer science, Inference and Human–computer interaction.
His Algorithm study incorporates themes from Isosurface, Marching cubes and Surface reconstruction.
Between 2019 and 2021, his most popular works were:
- Discriminative Adversarial Domain Adaptation. (24 citations)
- Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (21 citations)
- Orthogonal Deep Neural Networks (19 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Kui Jia spends much of his time researching Artificial intelligence, Pattern recognition, Regularization, Algorithm and Object.
His study in Point cloud, Feature extraction, Benchmark, Discriminative model and Classifier is carried out as part of his studies in Artificial intelligence.
His Benchmark research is multidisciplinary, incorporating perspectives in Semi-supervised learning and Machine learning.
His Pattern recognition research includes themes of Image sensor and Color constancy.
His work carried out in the field of Regularization brings together such families of science as Smoothing, Artificial neural network, Feature vector, Entropy and Robustness.
The Object detection research he does as part of his general Object study is frequently linked to other disciplines of science, such as Pedestrian detection, therefore creating a link between diverse domains of science.
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.
