What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
His primary scientific interests are in Artificial intelligence, Computer vision, Pattern recognition, Feature extraction and Machine learning.
While working in this field, Hongxun Yao studies both Artificial intelligence and Affect.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Recurrent neural network, Image, Visual Word and Background subtraction.
The Feature extraction study combines topics in areas such as Dimension, Solid modeling, Histogram, RGB color model and Kernel.
His research integrates issues of Active appearance model, Sparse approximation, Neural coding, Convolutional neural network and Robustness in his study of Eye tracking.
His work deals with themes such as Landmark and Mobile device, which intersect with Discriminative model.
His most cited work include:
- Hedged Deep Tracking (502 citations)
- Sparse coding based visual tracking: Review and experimental comparison (241 citations)
- Auto-encoder based dimensionality reduction (194 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Machine learning.
Image, Discriminative model, Feature, Image retrieval and Video tracking are the primary areas of interest in his Artificial intelligence study.
His Image retrieval research is multidisciplinary, relying on both Information retrieval and Support vector machine.
His Pattern recognition research integrates issues from Contextual image classification, Histogram, Object and Representation.
His Computer vision study often links to related topics such as Robustness.
In most of his Feature extraction studies, his work intersects topics such as Visualization.
He most often published in these fields:
- Artificial intelligence (81.27%)
- Pattern recognition (43.50%)
- Computer vision (42.30%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (81.27%)
- Pattern recognition (43.50%)
- Feature (9.37%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Pattern recognition, Feature, Object and Image are his primary areas of study.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Machine learning and Computer vision.
His Computer vision study combines topics from a wide range of disciplines, such as Computational complexity theory and Frame.
His Pattern recognition research incorporates themes from 3D reconstruction and Recurrent neural network.
His Feature study combines topics in areas such as Deep learning and Pattern recognition.
His research in Image intersects with topics in Range and Visualization.
Between 2017 and 2021, his most popular works were:
- Predicting Personalized Image Emotion Perceptions in Social Networks (96 citations)
- Hedging Deep Features for Visual Tracking (66 citations)
- Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images (47 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Hongxun Yao mainly investigates Artificial intelligence, Pattern recognition, Feature, Computer vision and Convolutional neural network.
He incorporates Artificial intelligence and Action recognition in his studies.
The study incorporates disciplines such as Recurrent neural network, Quantization and Hash function in addition to Pattern recognition.
In general Computer vision study, his work on Texture and Artifact often relates to the realm of Noise, thereby connecting several areas of interest.
His Convolutional neural network research is multidisciplinary, relying on both Image processing, Artificial neural network and Eye tracking.
The Feature extraction study combines topics in areas such as Machine learning and Robustness.
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.
