What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Shenghua Gao mostly deals with Artificial intelligence, Pattern recognition, Feature extraction, Neural coding and Sparse approximation.
As part of his studies on Artificial intelligence, Shenghua Gao often connects relevant areas like Computer vision.
His work in Pattern recognition addresses subjects such as Iterative reconstruction, which are connected to disciplines such as Recurrent neural network, Compressed sensing, Motion and Encoding.
His studies in Feature extraction integrate themes in fields like Cognitive neuroscience of visual object recognition, Deep learning, Anomaly detection and Robustness.
The concepts of his Sparse approximation study are interwoven with issues in Codebook, Quantization and Visual Word.
The study incorporates disciplines such as Artificial neural network and Image segmentation in addition to Convolutional neural network.
His most cited work include:
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (772 citations)
- PCANet: A Simple Deep Learning Baseline for Image Classification? (690 citations)
- Local features are not lonely – Laplacian sparse coding for image classification (413 citations)
What are the main themes of his work throughout his whole career to date?
Shenghua Gao spends much of his time researching Artificial intelligence, Pattern recognition, Computer vision, Convolutional neural network and Deep learning.
Artificial intelligence is closely attributed to Machine learning in his research.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Image and Cognitive neuroscience of visual object recognition.
His biological study spans a wide range of topics, including Perspective and Robustness.
His Convolutional neural network study combines topics in areas such as 3D reconstruction, Algorithm, Segmentation and Leverage.
While the research belongs to areas of Feature extraction, Shenghua Gao spends his time largely on the problem of Salience, intersecting his research to questions surrounding Visual saliency.
He most often published in these fields:
- Artificial intelligence (92.86%)
- Pattern recognition (45.24%)
- Computer vision (41.27%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (92.86%)
- Pattern recognition (45.24%)
- Computer vision (41.27%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Computer vision, Feature and Leverage.
His Artificial intelligence research focuses on Convolutional neural network, Deep learning, Segmentation, Depth map and Image.
His Convolutional neural network research incorporates themes from Parsing and Iterative reconstruction.
He works mostly in the field of Deep learning, limiting it down to topics relating to Feature extraction and, in certain cases, Hyperparameter, Neural coding and Recurrent neural network, as a part of the same area of interest.
His study in the fields of Anomaly detection under the domain of Pattern recognition overlaps with other disciplines such as Diabetic macular edema and Retinal.
His Computer vision research is multidisciplinary, relying on both Perspective and Robustness.
Between 2019 and 2021, his most popular works were:
- Towards Fast Adaptation of Neural Architectures with Meta Learning (24 citations)
- Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks (15 citations)
- Noise Adaptation Generative Adversarial Network for Medical Image Analysis (11 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Pattern recognition, Deep learning, Anomaly detection and Leverage are his primary areas of study.
His research is interdisciplinary, bridging the disciplines of Machine learning and Artificial intelligence.
His Pattern recognition study frequently links to related topics such as Saliency map.
His Deep learning research focuses on Feature extraction and how it connects with Hyperparameter, Neural coding, Recurrent neural network and Algorithm.
Shenghua Gao has researched Anomaly detection in several fields, including Artificial neural network and Image texture.
The Convolutional neural network study combines topics in areas such as Computer graphics and Iterative reconstruction.
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.
