What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Artificial intelligence, Pattern recognition, Computer vision, Shape analysis and Facial recognition system are his primary areas of study.
Mohamed Daoudi undertakes multidisciplinary investigations into Artificial intelligence and Action recognition in his work.
His Pattern recognition study combines topics in areas such as Tangent space and Three-dimensional face recognition.
His research integrates issues of Classifier, Support vector machine, Facial expression, Riemannian geometry and Feature selection in his study of Computer vision.
His work focuses on many connections between Shape analysis and other disciplines, such as Computation, that overlap with his field of interest in Rigid transformation and Invariant.
The various areas that he examines in his Facial recognition system study include Differential geometry, Geodesic and Biometrics.
His most cited work include:
- 3D Face Recognition under Expressions, Occlusions, and Pose Variations (233 citations)
- 3-D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold (229 citations)
- Three-Dimensional Face Recognition Using Shapes of Facial Curves (192 citations)
What are the main themes of his work throughout his whole career to date?
Mohamed Daoudi mainly focuses on Artificial intelligence, Pattern recognition, Computer vision, Shape analysis and Facial expression.
His work in Artificial intelligence addresses issues such as Manifold, which are connected to fields such as Riemannian manifold and Grassmannian.
His work carried out in the field of Pattern recognition brings together such families of science as Contextual image classification, Histogram, Invariant and Riemannian geometry.
His Computer vision research integrates issues from Classifier and Polygon mesh.
While the research belongs to areas of Polygon mesh, he spends his time largely on the problem of Reeb graph, intersecting his research to questions surrounding Computation.
He interconnects Random forest and Geodesic in the investigation of issues within Shape analysis.
He most often published in these fields:
- Artificial intelligence (72.60%)
- Pattern recognition (43.75%)
- Computer vision (41.35%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (72.60%)
- Pattern recognition (43.75%)
- Manifold (9.13%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Pattern recognition, Manifold, Computer vision and Facial expression.
His biological study spans a wide range of topics, including Riemannian manifold and Riemannian geometry.
His Pattern recognition study combines topics from a wide range of disciplines, such as Facial expression recognition, Emotion classification, Grassmannian and 3d model.
The study incorporates disciplines such as Deep learning, Hidden Markov model and Set in addition to Computer vision.
His Support vector machine course of study focuses on Facial recognition system and Feature extraction.
His Shape analysis research is multidisciplinary, relying on both Invariant and Naive Bayes classifier.
Between 2015 and 2021, his most popular works were:
- A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding (30 citations)
- Motion segment decomposition of RGB-D sequences for human behavior understanding (28 citations)
- A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition (25 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Mohamed Daoudi spends much of his time researching Artificial intelligence, Pattern recognition, Computer vision, Manifold and Positive-definite matrix.
Artificial intelligence is closely attributed to Riemannian manifold in his study.
Many of his studies on Pattern recognition involve topics that are commonly interrelated, such as Grassmannian.
As part of his studies on Computer vision, Mohamed Daoudi often connects relevant areas like Feature selection.
His Facial expression study also includes fields such as
- Emotion classification which intersects with area such as Hidden Markov model, Feature extraction and Spectral clustering,
- Convolutional neural network which is related to area like Training time and Speech recognition.
Mohamed Daoudi has researched Shape analysis in several fields, including Activity recognition, Naive Bayes classifier, Gesture and Topology.
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.
