What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Ahmed Elgammal spends much of his time researching Artificial intelligence, Computer vision, Pattern recognition, Machine learning and Feature extraction.
Ahmed Elgammal merges Artificial intelligence with Kernel density estimation in his study.
His Computer vision research includes elements of Manifold and Nonlinear dimensionality reduction.
His work in the fields of Pattern recognition, such as Discriminative model, overlaps with other areas such as Class.
His Machine learning study combines topics from a wide range of disciplines, such as Hypergraph, Cognitive neuroscience of visual object recognition and Class.
His Feature extraction study combines topics in areas such as Probabilistic logic and Edge detection.
His most cited work include:
- Non-parametric Model for Background Subtraction (1956 citations)
- Background and foreground modeling using nonparametric kernel density estimation for visual surveillance (1358 citations)
- Inferring 3D body pose from silhouettes using activity manifold learning (408 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, Pattern recognition, Machine learning and Manifold.
His Generative model, Embedding, Object, Feature extraction and Cognitive neuroscience of visual object recognition study are his primary interests in Artificial intelligence.
Pose, Object detection, Segmentation, Background subtraction and Motion estimation are the core of his Computer vision study.
His study looks at the relationship between Pattern recognition and fields such as Categorization, as well as how they intersect with chemical problems.
His Machine learning research includes themes of Contextual image classification, Classifier and Inference.
His Manifold study deals with Representation intersecting with Visualization.
He most often published in these fields:
- Artificial intelligence (76.54%)
- Computer vision (36.54%)
- Pattern recognition (30.00%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (76.54%)
- Pattern recognition (30.00%)
- Generative grammar (4.62%)
In recent papers he was focusing on the following fields of study:
Ahmed Elgammal mainly focuses on Artificial intelligence, Pattern recognition, Generative grammar, Machine learning and Style.
Artificial intelligence is a component of his Softmax function, Generative model, Embedding, Object and Adversarial system studies.
His biological study spans a wide range of topics, including Margin, Pixel, Scene graph and Feature.
His research integrates issues of Nonlinear dimensionality reduction, Manifold, Local convergence and Distribution in his study of Generative grammar.
Ahmed Elgammal focuses mostly in the field of Machine learning, narrowing it down to topics relating to Contextual image classification and, in certain cases, Object detection, Cognitive neuroscience of visual object recognition, Vocabulary and Cluster analysis.
His Style research incorporates elements of Context and Natural language processing.
Between 2016 and 2021, his most popular works were:
- A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts (231 citations)
- CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms (133 citations)
- Relationship Proposal Networks (71 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary scientific interests are in Artificial intelligence, Pattern recognition, Style, Generative grammar and Noisy text.
Adversarial system, Scene graph, Generative model, Visualization and Representation are the subjects of his Artificial intelligence studies.
To a larger extent, he studies Computer vision with the aim of understanding Scene graph.
He has researched Pattern recognition in several fields, including Channel, Background subtraction and Categorization.
His Style research focuses on subjects like Context, which are linked to Art history, Representation and Painting.
Ahmed Elgammal combines subjects such as Disjoint sets, Nonlinear dimensionality reduction, Theoretical computer science and Distribution with his study of Generative grammar.
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.
