What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Boqing Gong mostly deals with Artificial intelligence, Machine learning, Cognitive neuroscience of visual object recognition, Pattern recognition and Artificial neural network.
Artificial intelligence is often connected to Computer vision in his work.
Empirical research is closely connected to Class in his research, which is encompassed under the umbrella topic of Machine learning.
Within one scientific family, he focuses on topics pertaining to Invariant under Pattern recognition, and may sometimes address concerns connected to Sentiment analysis, Labeled data, Unsupervised learning and Image quality.
His Artificial neural network study combines topics in areas such as Motion and Convolutional neural network.
Boqing Gong has included themes like Perspective, Feature extraction, Training set and Kernel in his Visualization study.
His most cited work include:
- Geodesic flow kernel for unsupervised domain adaptation (1293 citations)
- Synthesized Classifiers for Zero-Shot Learning (385 citations)
- Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation (369 citations)
What are the main themes of his work throughout his whole career to date?
Boqing Gong spends much of his time researching Artificial intelligence, Machine learning, Artificial neural network, Pattern recognition and Segmentation.
The study incorporates disciplines such as Key and Computer vision in addition to Artificial intelligence.
His Machine learning research incorporates themes from Classifier, Perspective and Automatic summarization.
His study in the field of Training set, Discriminative model and Feature learning also crosses realms of Space.
His Segmentation research incorporates elements of Point cloud, Real image and Convolutional neural network.
His Cognitive neuroscience of visual object recognition research is multidisciplinary, incorporating elements of Unsupervised learning, Invariant, Feature extraction, Empirical research and Kernel.
He most often published in these fields:
- Artificial intelligence (76.67%)
- Machine learning (42.50%)
- Artificial neural network (17.50%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (76.67%)
- Machine learning (42.50%)
- Segmentation (15.00%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Machine learning, Segmentation, Pattern recognition and Object.
His research on Artificial intelligence often connects related topics like Computer vision.
Boqing Gong works mostly in the field of Machine learning, limiting it down to topics relating to Smoothing and, in certain cases, Deep neural networks and Training time, as a part of the same area of interest.
His studies deal with areas such as Point cloud and Convolutional neural network as well as Segmentation.
His Pattern recognition study incorporates themes from Closing and Embedding.
His study in Robustness is interdisciplinary in nature, drawing from both Adversarial system and Key.
Between 2019 and 2021, his most popular works were:
- Adversarial Examples Improve Image Recognition (91 citations)
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (34 citations)
- A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes (34 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Machine learning, Robustness, Segmentation and Image segmentation.
His Artificial intelligence research focuses on Convolutional neural network, Classifier, Noise reduction, Embedding and Linear classifier.
Boqing Gong has researched Machine learning in several fields, including Visual recognition and Zero shot learning.
His research in Robustness intersects with topics in Adversarial system, Key and Training time.
His biological study spans a wide range of topics, including Artificial neural network, Grid, Point cloud and Data mining.
The various areas that he examines in his Image segmentation study include Augmented reality, Real image, Deep learning and Computer graphics.
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.
