What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Jianping Shi spends much of his time researching Artificial intelligence, Pattern recognition, Object detection, Segmentation and Computer vision.
His research is interdisciplinary, bridging the disciplines of Machine learning and Artificial intelligence.
His Pattern recognition research includes themes of Feature, Deep learning, Categorization and Benchmark.
Jianping Shi merges Object detection with Process in his research.
His studies in Segmentation integrate themes in fields like Range, Embedding, Inference and Softmax function.
His Computer vision research includes elements of Unsupervised learning, Outlier and Robustness.
His most cited work include:
- Pyramid Scene Parsing Network (3766 citations)
- Hierarchical Saliency Detection (1123 citations)
- Path Aggregation Network for Instance Segmentation (663 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Segmentation, Pattern recognition and Image.
Feature, Object detection, Feature extraction, Artificial neural network and Object are subfields of Artificial intelligence in which his conducts study.
Jianping Shi studies Segmentation, namely Image segmentation.
His Pattern recognition research is multidisciplinary, relying on both Contextual image classification, Pyramid and Pyramid.
Jianping Shi has included themes like Pixel and Point in his Image study.
In his study, Parsing is strongly linked to Pascal, which falls under the umbrella field of Machine learning.
He most often published in these fields:
- Artificial intelligence (77.25%)
- Computer vision (38.32%)
- Segmentation (31.14%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (77.25%)
- Computer vision (38.32%)
- Feature (20.96%)
In recent papers he was focusing on the following fields of study:
Jianping Shi mainly investigates Artificial intelligence, Computer vision, Feature, Image and Segmentation.
In most of his Artificial intelligence studies, his work intersects topics such as Pattern recognition.
His research in the fields of Object overlaps with other disciplines such as Line, Position and Horizon.
He focuses mostly in the field of Image, narrowing it down to matters related to Point and, in some cases, Function, Contextual image classification and Filter.
His biological study spans a wide range of topics, including Algorithm, Machine learning and Regularization.
He interconnects Point cloud, Minimum bounding box, Convolutional neural network and Benchmark in the investigation of issues within Object detection.
Between 2019 and 2021, his most popular works were:
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (84 citations)
- From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. (66 citations)
- Temporal Pyramid Network for Action Recognition (42 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Artificial intelligence, Object detection, Pattern recognition, Algorithm and Feature are his primary areas of study.
His work in the fields of Feature extraction and Image segmentation overlaps with other areas such as Architecture and Core.
His Object detection research includes themes of Point cloud, Boundary, Minimum bounding box and Task.
The study incorporates disciplines such as Contextual image classification, Pyramid, Filter and Pyramid in addition to Pattern recognition.
The concepts of his Algorithm study are interwoven with issues in Object, Image and Enhanced Data Rates for GSM Evolution.
His studies deal with areas such as Pixel, Segmentation, Convolutional neural network and Voxel as well as Feature.
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.
