What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Jiashi Feng focuses on Artificial intelligence, Pattern recognition, Feature extraction, Discriminative model and Machine learning.
His research ties Computer vision and Artificial intelligence together.
Jiashi Feng combines subjects such as Contextual image classification, Subspace topology and Representation with his study of Pattern recognition.
The Feature extraction study combines topics in areas such as Image resolution, Task analysis and Word error rate.
His Discriminative model research is multidisciplinary, incorporating perspectives in Visualization, Cognitive neuroscience of visual object recognition and Perception.
His Machine learning study combines topics in areas such as Simple, Pascal and Adaptation.
His most cited work include:
- Return of frustratingly easy domain adaptation (653 citations)
- Natural Language Object Retrieval (369 citations)
- End-to-End Comparative Attention Networks for Person Re-Identification (366 citations)
What are the main themes of his work throughout his whole career to date?
Jiashi Feng mainly focuses on Artificial intelligence, Machine learning, Pattern recognition, Computer vision and Deep learning.
His study in Discriminative model, Object detection, Feature extraction, Segmentation and Object falls within the category of Artificial intelligence.
He interconnects Pascal and Benchmark in the investigation of issues within Machine learning.
His Pattern recognition research is multidisciplinary, relying on both Contextual image classification, Image, Pixel and Feature.
His work on Face as part of general Computer vision study is frequently connected to Frame, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Deep learning study frequently draws connections to other fields, such as Algorithm.
He most often published in these fields:
- Artificial intelligence (80.89%)
- Machine learning (30.22%)
- Pattern recognition (28.22%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (80.89%)
- Machine learning (30.22%)
- Pattern recognition (28.22%)
In recent papers he was focusing on the following fields of study:
Jiashi Feng mainly investigates Artificial intelligence, Machine learning, Pattern recognition, Code and Computer vision.
His study in Segmentation, Object detection, Deep learning, Feature extraction and Representation are all subfields of Artificial intelligence.
In his research, Artificial neural network is intimately related to Sample, which falls under the overarching field of Machine learning.
His work in the fields of Pattern recognition overlaps with other areas such as Process.
His Code study also includes
- Computation and related Task,
- Theoretical computer science which connect with Natural language understanding and Convolution.
His study in the field of Image restoration also crosses realms of Focus and Frame.
Between 2019 and 2021, his most popular works were:
- Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm (152 citations)
- Decoupling Representation and Classifier for Long-Tailed Recognition (81 citations)
- Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (80 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Algorithm, Machine learning, Deep learning and Pattern recognition.
While the research belongs to areas of Artificial intelligence, Jiashi Feng spends his time largely on the problem of Computer vision, intersecting his research to questions surrounding Expression.
His Algorithm study incorporates themes from Graph, Linear subspace, Robustness and Code.
The concepts of his Machine learning study are interwoven with issues in Normalization, Simple, Graph neural networks and Neuroimaging.
Jiashi Feng has included themes like Classifier, Ranking, Sample and Support vector machine in his Deep learning study.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Contextual image classification, Cluster analysis and Language model.
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.
