What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
His scientific interests lie mostly in Artificial intelligence, Segmentation, Shape analysis, Computer vision and Pattern recognition.
His research in Artificial intelligence intersects with topics in Machine learning and Theoretical computer science.
In his research, Discrete mathematics, Graph, Compact space and Algebra is intimately related to Homogeneous space, which falls under the overarching field of Segmentation.
His Shape analysis research includes themes of Active shape model and Cluster analysis.
Kai Xu has researched Pattern recognition in several fields, including Artificial neural network, Recurrent neural network and Autoencoder.
The study incorporates disciplines such as Algorithm and Interpolation in addition to Autoencoder.
His most cited work include:
- GRASS: generative recursive autoencoders for shape structures (173 citations)
- Fit and diverse: set evolution for inspiring 3D shape galleries (139 citations)
- A novel quantum representation for log-polar images (118 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Segmentation and Point cloud.
Kai Xu performs integrative study on Artificial intelligence and Set in his works.
Many of his studies on Computer vision involve topics that are commonly interrelated, such as Computer graphics.
His Pattern recognition research is multidisciplinary, relying on both Machine learning, Cluster analysis and Autoencoder.
The various areas that Kai Xu examines in his Segmentation study include Graph, Theoretical computer science, Classifier, 3d model and Shape analysis.
His Point cloud research incorporates themes from Geometric data analysis, Embedding, Convolution, Algorithm and Point.
He most often published in these fields:
- Artificial intelligence (67.13%)
- Computer vision (35.66%)
- Pattern recognition (25.17%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (67.13%)
- Computer vision (35.66%)
- Point cloud (16.78%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Computer vision, Point cloud, Pattern recognition and Artificial neural network.
His study involves Object, Feature, Segmentation, Feature extraction and Generative model, a branch of Artificial intelligence.
His work on Object detection and RGB color model as part of general Computer vision research is frequently linked to Forward kinematics and Fitness function, thereby connecting diverse disciplines of science.
His study on Point cloud also encompasses disciplines like
- Convolution that intertwine with fields like Geometric data analysis, Octree, Algorithm and Kernel,
- Point which is related to area like Cluster analysis, Graph and Benchmark.
Kai Xu combines subjects such as 3D reconstruction, Image and Autoencoder with his study of Pattern recognition.
Kai Xu interconnects Optimization problem, Deep learning and Metric in the investigation of issues within Artificial neural network.
Between 2019 and 2021, his most popular works were:
- PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes (18 citations)
- Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation (18 citations)
- Learning Part Generation and Assembly for Structure-Aware Shape Synthesis. (16 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Geometry
Kai Xu spends much of his time researching Artificial intelligence, Pattern recognition, Point cloud, Computer vision and Object.
In the field of Artificial intelligence, his study on Artificial neural network, Feature and Segmentation overlaps with subjects such as Rectifier.
His Image segmentation study in the realm of Pattern recognition interacts with subjects such as Set.
His Point cloud research incorporates elements of Tree, Geometric data analysis, Octree and Feature learning.
His work on Object detection and RGB color model as part of general Computer vision study is frequently connected to Code and Point, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Object research focuses on Feature extraction and how it connects with Representation, Embedding, Generative model and Pose.
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.
