What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Pattern recognition, Feature extraction, Computer vision and Facial recognition system are his primary areas of study.
His research combines Hypergraph and Artificial intelligence.
His study ties his expertise on Machine learning together with the subject of Pattern recognition.
His Feature extraction research includes elements of Deep learning, Autoencoder, Hyperspectral imaging, Digital pathology and Feature learning.
His work in Computer vision tackles topics such as Visualization which are related to areas like Pyramid and Pyramid.
His work deals with themes such as Local binary patterns and Image texture, which intersect with Facial recognition system.
His most cited work include:
- Fast Visual Tracking via Dense Spatio-temporal Context Learning (492 citations)
- Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images (436 citations)
- Cascaded Recurrent Neural Networks for Hyperspectral Image Classification (357 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Facial recognition system.
His research ties Machine learning and Artificial intelligence together.
His Pattern recognition study combines topics in areas such as Contextual image classification and Subspace topology.
In his research on the topic of Computer vision, Eye tracking is strongly related with Robustness.
Qingshan Liu interconnects Object detection, Feature vector and Visualization in the investigation of issues within Feature extraction.
His research in Facial recognition system intersects with topics in Facial expression, Linear discriminant analysis, Kernel method, Nonlinear system and Kernel.
He most often published in these fields:
- Artificial intelligence (80.67%)
- Pattern recognition (57.00%)
- Computer vision (29.67%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (80.67%)
- Pattern recognition (57.00%)
- Feature (11.33%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Feature, Benchmark and Computer vision.
His Artificial intelligence and Segmentation, Feature extraction, Hyperspectral imaging, Deep learning and Image investigations all form part of his Artificial intelligence research activities.
Qingshan Liu has researched Feature extraction in several fields, including Visualization and Active learning.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Clustering coefficient and Graph.
His studies in Feature integrate themes in fields like Object detection, Representation and Feature vector.
His studies deal with areas such as Autoencoder and Compressed sensing as well as Computer vision.
Between 2018 and 2021, his most popular works were:
- Hyperspectral image classification using spectral-spatial LSTMs (51 citations)
- Joint Active Learning with Feature Selection via CUR Matrix Decomposition (29 citations)
- Robust Subspace Clustering With Compressed Data (28 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Qingshan Liu mostly deals with Artificial intelligence, Pattern recognition, Feature extraction, Hyperspectral imaging and Algorithm.
As part of his studies on Artificial intelligence, Qingshan Liu frequently links adjacent subjects like Computer vision.
His research integrates issues of Time complexity, Reconstruction procedure, Artificial neural network and Compressed sensing in his study of Computer vision.
His Convolutional neural network study in the realm of Pattern recognition connects with subjects such as Active learning.
Qingshan Liu focuses mostly in the field of Feature extraction, narrowing it down to matters related to Visualization and, in some cases, Thresholding and Graph.
His Algorithm study integrates concerns from other disciplines, such as Intelligent decision support system, Representation, Relation and Interpolation.
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.
