What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Algebra
Wei Ke mainly focuses on Metallurgy, Corrosion, Microstructure, Artificial intelligence and Alloy.
Wei Ke combines subjects such as Slurry and Coating, Thermal spraying with his study of Corrosion.
His research in Microstructure tackles topics such as Pitting corrosion which are related to areas like Amorphous solid, Low-cycle fatigue, Lüders band, Tin and Strain rate.
Wei Ke has included themes like Continuation, Computer vision and Pattern recognition in his Artificial intelligence study.
His research in the fields of Segmentation and Histogram overlaps with other disciplines such as Exudate and Optic disk.
His Alloy study integrates concerns from other disciplines, such as Growth rate and Grain boundary.
His most cited work include:
- Slurry erosion–corrosion behaviour of high-velocity oxy-fuel (HVOF) sprayed Fe-based amorphous metallic coatings for marine pump in sand-containing NaCl solutions (94 citations)
- C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (75 citations)
- Effects of cold working degrees on grain boundary characters and strain concentration at grain boundaries in Alloy 600 (70 citations)
What are the main themes of his work throughout his whole career to date?
Wei Ke spends much of his time researching Artificial intelligence, Pattern recognition, Computer vision, Algorithm and Object detection.
His research investigates the connection between Artificial intelligence and topics such as Machine learning that intersect with problems in Data set.
His research integrates issues of Image and Graph in his study of Pattern recognition.
In general Computer vision study, his work on Segmentation, Pixel, Projector and Structured light often relates to the realm of Weld line, thereby connecting several areas of interest.
His work focuses on many connections between Algorithm and other disciplines, such as Skeleton, that overlap with his field of interest in Subspace topology.
Wei Ke has researched Object detection in several fields, including Data mining, Pascal, Set and Detector.
He most often published in these fields:
- Artificial intelligence (56.44%)
- Pattern recognition (25.74%)
- Computer vision (18.81%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (56.44%)
- Pattern recognition (25.74%)
- Algorithm (16.83%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Algorithm, Computer vision and Artificial neural network.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Machine learning and Process.
In general Pattern recognition, his work in Convolutional neural network is often linked to Transformation matrix linking many areas of study.
His Algorithm research integrates issues from Dual and Association.
His research investigates the connection between Computer vision and topics such as Detector that intersect with issues in Video tracking, Cluster analysis, Radar tracker, Graph and BitTorrent tracker.
His Benchmark study combines topics from a wide range of disciplines, such as Object, Object detection and Noise.
Between 2019 and 2021, his most popular works were:
- Mining Hard Samples Globally and Efficiently for Person Reidentification (23 citations)
- Multiple Anchor Learning for Visual Object Detection (17 citations)
- Long-Term Tracking With Deep Tracklet Association (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Algebra
His primary scientific interests are in Artificial intelligence, Computer vision, Detector, Robustness and Process.
His work on Benchmark, Object and Object detection as part of general Artificial intelligence research is frequently linked to Sample, thereby connecting diverse disciplines of science.
His biological study spans a wide range of topics, including Graph and Cluster analysis.
His Detector research is multidisciplinary, relying on both Pixel and BitTorrent tracker.
The concepts of his Robustness study are interwoven with issues in Data mining, Ambiguity and Radar tracker.
His Process research includes elements of Visualization, Upper and lower bounds, Set and Pattern recognition.
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.
