What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Pattern recognition
Mehrtash Harandi mainly investigates Artificial intelligence, Pattern recognition, Riemannian manifold, Riemannian geometry and Statistical manifold.
His Artificial intelligence course of study focuses on Manifold and Embedding.
Mehrtash Harandi has researched Pattern recognition in several fields, including Subspace topology and Linear subspace.
As a member of one scientific family, Mehrtash Harandi mostly works in the field of Riemannian manifold, focusing on Kernel and, on occasion, Algorithm, Positive-definite matrix and Matrix.
Mehrtash Harandi usually deals with Riemannian geometry and limits it to topics linked to Dimensionality reduction and Geometry and Discriminative model.
His Feature extraction research is multidisciplinary, incorporating perspectives in Unsupervised learning, Invariant, Feature vector and Maximum mean discrepancy.
His most cited work include:
- Going deeper into action recognition (328 citations)
- Unsupervised Domain Adaptation by Domain Invariant Projection (308 citations)
- Unsupervised Domain Adaptation by Domain Invariant Projection (308 citations)
What are the main themes of his work throughout his whole career to date?
Mehrtash Harandi mainly investigates Artificial intelligence, Pattern recognition, Manifold, Embedding and Facial recognition system.
His Artificial intelligence research incorporates themes from Machine learning, Linear subspace and Computer vision.
Mehrtash Harandi works in the field of Pattern recognition, namely Feature extraction.
His Manifold study combines topics from a wide range of disciplines, such as Positive-definite matrix, Matrix, Riemannian manifold, Grassmannian and Riemannian geometry.
Mehrtash Harandi studied Riemannian manifold and Projection that intersect with Orthonormal basis.
His Embedding study combines topics in areas such as Tangent space, Kullback–Leibler divergence, Hilbert space and Euclidean geometry.
He most often published in these fields:
- Artificial intelligence (94.04%)
- Pattern recognition (64.24%)
- Manifold (27.81%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (94.04%)
- Discriminative model (12.58%)
- Machine learning (23.18%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Discriminative model, Machine learning, Pattern recognition and Matrix.
His Artificial intelligence research is multidisciplinary, incorporating elements of Margin and Manifold.
The various areas that Mehrtash Harandi examines in his Discriminative model study include Subspace topology and Cognitive neuroscience of visual object recognition.
His studies in Machine learning integrate themes in fields like Optical flow and Image.
His Pattern recognition study frequently involves adjacent topics like Representation.
The Matrix study combines topics in areas such as Measure and Cluster analysis.
Between 2018 and 2021, his most popular works were:
- Adaptive Subspaces for Few-Shot Learning (42 citations)
- Bilinear Attention Networks for Person Retrieval (40 citations)
- Toward Efficient Action Recognition: Principal Backpropagation for Training Two-Stream Networks (19 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Mehrtash Harandi focuses on Artificial intelligence, Pooling, Machine learning, Feature extraction and Manifold.
Mehrtash Harandi applies his multidisciplinary studies on Artificial intelligence and Block in his research.
His Manifold research is multidisciplinary, relying on both Facial recognition system, Kernel, Transformation, Kernel and Pattern recognition.
His study explores the link between Stochastic gradient descent and topics such as Perspective that cross with problems in Contextual image classification and Riemannian geometry.
His Subspace topology research focuses on Robustness and how it connects with Cognitive neuroscience of visual object recognition.
His studies deal with areas such as Positive-definite matrix, Matrix, Riemannian manifold, Measure and Similarity as well as Discriminative model.
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.
