What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
His main research concerns Artificial intelligence, Computer vision, Pattern recognition, Machine learning and Tracking.
His is involved in several facets of Artificial intelligence study, as is seen by his studies on Segmentation, Object, Cognitive neuroscience of visual object recognition, Image segmentation and Motion estimation.
James M. Rehg has included themes like Noise and Active appearance model in his Pattern recognition study.
The Machine learning study combines topics in areas such as Robot and Nonlinear system.
His Tracking study incorporates themes from User interface, Contrast, Probability density function and Prior probability.
His work carried out in the field of Histogram brings together such families of science as Pixel, Categorization and Visualization.
His most cited work include:
- Statistical color models with application to skin detection (1556 citations)
- The Secrets of Salient Object Segmentation (792 citations)
- CENTRIST: A Visual Descriptor for Scene Categorization (608 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Computer vision, Pattern recognition, Machine learning and Object are his primary areas of study.
His study looks at the intersection of Artificial intelligence and topics like Computer graphics with Projector.
Computer vision is closely attributed to Robot in his study.
His study in AdaBoost, Feature extraction and Support vector machine is done as part of Pattern recognition.
James M. Rehg regularly links together related areas like Inference in his Machine learning studies.
His studies deal with areas such as Task and Eye contact as well as Gaze.
He most often published in these fields:
- Artificial intelligence (65.56%)
- Computer vision (35.95%)
- Pattern recognition (15.41%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (65.56%)
- Computer vision (35.95%)
- Gaze (7.25%)
In recent papers he was focusing on the following fields of study:
James M. Rehg spends much of his time researching Artificial intelligence, Computer vision, Gaze, Task and Pattern recognition.
His work on Artificial intelligence is being expanded to include thematically relevant topics such as Machine learning.
His work on Segmentation, Image segmentation and Rendering as part of general Computer vision research is often related to First person and Perspective, thus linking different fields of science.
The various areas that he examines in his Gaze study include Motion, Discriminative model and Wearable computer.
His Task research is multidisciplinary, incorporating elements of Key, Transport engineering and Reinforcement learning.
His Pattern recognition research includes elements of 3D reconstruction, Structure, Image and Glaucoma.
Between 2017 and 2021, his most popular works were:
- Multi-object Tracking with Neural Gating Using Bilinear LSTM (134 citations)
- Fine-Grained Head Pose Estimation Without Keypoints (125 citations)
- 3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare (125 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Operating system
His primary areas of investigation include Artificial intelligence, Computer vision, Task, Gaze and Model predictive control.
His study on Artificial intelligence is mostly dedicated to connecting different topics, such as Pattern recognition.
Many of his research projects under Computer vision are closely connected to Differentiable function with Differentiable function, tying the diverse disciplines of science together.
His Task study integrates concerns from other disciplines, such as Key and Reinforcement learning.
His research in Gaze intersects with topics in Motion, Leverage and Salience.
His Model predictive control research includes themes of Sampling, Stochastic process and Vehicle dynamics.
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.
