What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Greg Mori mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Discriminative model and Cognitive neuroscience of visual object recognition.
His studies link Computer vision with Artificial intelligence.
Machine learning and Aggregate are commonly linked in his work.
His Pattern recognition research includes elements of Histogram and Pose.
He interconnects Optical character recognition, Pattern matching, Gesture recognition, Contextual image classification and Pattern recognition in the investigation of issues within Cognitive neuroscience of visual object recognition.
His work in Support vector machine addresses issues such as Classifier, which are connected to fields such as Object detection.
His most cited work include:
- Recognizing objects in adversarial clutter: breaking a visual CAPTCHA (570 citations)
- Recovering human body configurations: combining segmentation and recognition (511 citations)
- Detecting Pedestrians by Learning Shapelet Features (452 citations)
What are the main themes of his work throughout his whole career to date?
Greg Mori mainly focuses on Artificial intelligence, Machine learning, Pattern recognition, Computer vision and Discriminative model.
Artificial intelligence is represented through his Artificial neural network, Inference, Support vector machine, Contextual image classification and Latent variable research.
His research integrates issues of Bayesian optimization, Deep learning and Pruning in his study of Artificial neural network.
His study focuses on the intersection of Machine learning and fields such as Image with connections in the field of Data mining.
His research in Pattern recognition intersects with topics in Cognitive neuroscience of visual object recognition and Standard test image.
As a part of the same scientific study, Greg Mori usually deals with the Computer vision, concentrating on Robot and frequently concerns with Human–computer interaction.
He most often published in these fields:
- Artificial intelligence (85.65%)
- Machine learning (37.80%)
- Pattern recognition (33.97%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (85.65%)
- Machine learning (37.80%)
- Image (9.09%)
In recent papers he was focusing on the following fields of study:
Greg Mori mainly investigates Artificial intelligence, Machine learning, Image, Algorithm and Autoencoder.
His Artificial intelligence study integrates concerns from other disciplines, such as Set and Pattern recognition.
His work on Contrast as part of general Machine learning research is often related to Fidelity, Computational resource and Process, thus linking different fields of science.
His work carried out in the field of Image brings together such families of science as Data mining, Aggregate, Markov property, Embedding and Mutual information.
His Algorithm research incorporates themes from Event, Point process and Message passing.
Greg Mori studied Autoencoder and Joint probability distribution that intersect with Latent variable.
Between 2018 and 2021, his most popular works were:
- Similarity-Preserving Knowledge Distillation (129 citations)
- Lifelong GAN: Continual Learning for Conditional Image Generation (45 citations)
- Learning a Deep ConvNet for Multi-Label Classification With Partial Labels (43 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His main research concerns Artificial intelligence, Machine learning, Generative grammar, Representation and Artificial neural network.
Many of his studies on Artificial intelligence apply to Crowds as well.
His Machine learning study incorporates themes from Visual reasoning and Benchmark.
His Generative grammar research includes themes of Training set, Forgetting and Task.
The study incorporates disciplines such as Similarity and Set in addition to Representation.
His work in Image covers topics such as Categorization which are related to areas like Contextual image classification and Deep learning.
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.
