What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Jia Deng mainly focuses on Artificial intelligence, Object detection, Object, Machine learning and Set.
In his study, Image is strongly linked to Pattern recognition, which falls under the umbrella field of Artificial intelligence.
Jia Deng combines subjects such as Contextual image classification and Pattern recognition with his study of Object.
His studies in Contextual image classification integrate themes in fields like WordNet and Image retrieval.
Jia Deng combines subjects such as Ontology, The Internet and Cluster analysis with his study of WordNet.
The study incorporates disciplines such as Field and Categorical variable in addition to Benchmark.
His most cited work include:
- ImageNet: A large-scale hierarchical image database (22839 citations)
- ImageNet Large Scale Visual Recognition Challenge (18266 citations)
- Stacked Hourglass Networks for Human Pose Estimation (2051 citations)
What are the main themes of his work throughout his whole career to date?
Jia Deng mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Object and Data mining.
In his work, State is strongly intertwined with Computer vision, which is a subfield of Artificial intelligence.
The various areas that Jia Deng examines in his Machine learning study include Cognitive neuroscience of visual object recognition, Code, Crowdsourcing, Contextual image classification and Pose.
Cognitive neuroscience of visual object recognition connects with themes related to Categorization in his study.
His Object research is multidisciplinary, incorporating elements of Field, Set and Pattern recognition.
His Benchmark research integrates issues from Key and Action.
He most often published in these fields:
- Artificial intelligence (65.00%)
- Machine learning (22.86%)
- Pattern recognition (21.43%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (65.00%)
- Code (9.29%)
- State (7.14%)
In recent papers he was focusing on the following fields of study:
Jia Deng spends much of his time researching Artificial intelligence, Code, State, Key and Information retrieval.
While the research belongs to areas of Artificial intelligence, Jia Deng spends his time largely on the problem of Pattern recognition, intersecting his research to questions surrounding Face and Object detection.
His Object detection research is multidisciplinary, relying on both Cognitive neuroscience of visual object recognition, Minimum bounding box, Pooling and Pattern recognition.
His Code research includes themes of Machine learning, Relation and Field.
His biological study deals with issues like Data mining, which deal with fields such as Interpolation, Gradient descent and Code refactoring.
His Information retrieval research focuses on subjects like Dialog box, which are linked to Benchmark.
Between 2019 and 2021, his most popular works were:
- CornerNet: Detecting Objects as Paired Keypoints (162 citations)
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (71 citations)
- Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy (42 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His main research concerns Artificial intelligence, Code, Optical flow, Algorithm and Deep learning.
His research ties Machine learning and Artificial intelligence together.
His research integrates issues of Pixel and Field in his study of Code.
His Algorithm research includes elements of Artificial neural network and Motion.
His studies in Deep learning integrate themes in fields like Automated theorem proving, Theoretical computer science, Mathematical proof, State and Key.
Jia Deng has researched Convolutional neural network in several fields, including RGB color model, Motion, Computer vision, Inference and Action recognition.
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.
