What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Pattern recognition, Machine learning, Contextual image classification and Computer vision are his primary areas of study.
His research in Image retrieval, Histogram, Pascal, Mixture model and Probabilistic latent semantic analysis are components of Artificial intelligence.
His Pattern recognition study combines topics from a wide range of disciplines, such as Visualization, Fisher vector and Cluster analysis.
His Machine learning study combines topics in areas such as Classifier, Adversarial system and Metric.
In his study, Data set is inextricably linked to Identification, which falls within the broad field of Metric.
Encoding, Scale-invariant feature transform, Feature extraction and Mel-frequency cepstrum is closely connected to Bag-of-words model in computer vision in his research, which is encompassed under the umbrella topic of Contextual image classification.
His most cited work include:
- The global k-means clustering algorithm (1257 citations)
- Image Classification with the Fisher Vector: Theory and Practice (1202 citations)
- Is that you? Metric learning approaches for face identification (664 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Pattern recognition, Machine learning, Algorithm and Contextual image classification.
As part of one scientific family, Jakob Verbeek deals mainly with the area of Artificial intelligence, narrowing it down to issues related to the Computer vision, and often Robustness.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Visual Word, Representation, Fisher vector and Metric.
His Machine learning research integrates issues from Adversarial system, Generative grammar and Face.
In general Algorithm study, his work on Optimization problem often relates to the realm of Expectation–maximization algorithm, thereby connecting several areas of interest.
His Contextual image classification research focuses on subjects like Classifier, which are linked to Distance based.
He most often published in these fields:
- Artificial intelligence (67.38%)
- Pattern recognition (42.55%)
- Machine learning (27.66%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (67.38%)
- Inference (6.38%)
- Algorithm (19.15%)
In recent papers he was focusing on the following fields of study:
Jakob Verbeek mainly focuses on Artificial intelligence, Inference, Algorithm, Machine learning and Representation.
Many of his studies involve connections with topics such as Pattern recognition and Artificial intelligence.
Jakob Verbeek interconnects Contextual image classification, Pixel and RGB color model in the investigation of issues within Pattern recognition.
His Contextual image classification research is multidisciplinary, incorporating elements of Mixture model, Embedding, Segmentation and Statistical model.
His study in Algorithm is interdisciplinary in nature, drawing from both 3D reconstruction, Point cloud and Probabilistic logic.
His Machine learning research incorporates themes from Structure and Generative grammar.
Between 2018 and 2021, his most popular works were:
- Understanding Priors in Bayesian Neural Networks at the Unit Level (15 citations)
- Learning Disentangled Representations with Reference-Based Variational Autoencoders (15 citations)
- Hierarchical Scene Coordinate Classification and Regression for Visual Localization (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Generative grammar, Machine learning and Layer.
His Pixel, Unsupervised learning, Convolutional neural network, Mixture model and Statistical model study are his primary interests in Artificial intelligence.
Jakob Verbeek conducts interdisciplinary study in the fields of Pattern recognition and Regression through his works.
His studies in Generative grammar integrate themes in fields like Representation and Feature learning.
His work in the fields of Machine learning, such as Latent variable and Contrast, overlaps with other areas such as Density estimation and Parametric statistics.
His work carried out in the field of Layer brings together such families of science as Regularization, Algorithm and Bayesian neural networks.
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.
