What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
His main research concerns Artificial intelligence, Computer vision, Image retrieval, Invariant and Image processing.
His research in Artificial intelligence intersects with topics in Machine learning and Pattern recognition.
His work on Edge detection, Color constancy and Gaussian filter as part of general Computer vision study is frequently linked to Spatial structure, therefore connecting diverse disciplines of science.
His studies deal with areas such as Geometric invariance, Segmentation, Information retrieval and Pattern recognition as well as Image retrieval.
His work focuses on many connections between Invariant and other disciplines, such as Discriminative model, that overlap with his field of interest in Luminance, Scale-invariant feature transform, Gaussian process, Scale space and Color normalization.
His Image processing research integrates issues from Support vector machine and Set.
His most cited work include:
- Visual Word Ambiguity (717 citations)
- The Amsterdam Library of Object Images (715 citations)
- Kernel Codebooks for Scene Categorization (559 citations)
What are the main themes of his work throughout his whole career to date?
Jan-Mark Geusebroek mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Image processing and Information retrieval.
His work in Artificial intelligence tackles topics such as Invariant which are related to areas like Edge detection.
Jan-Mark Geusebroek regularly ties together related areas like Discriminative model in his Computer vision studies.
His Pattern recognition study combines topics in areas such as Contextual image classification, Cognitive neuroscience of visual object recognition and Categorization.
Jan-Mark Geusebroek has researched Image processing in several fields, including Software architecture, Distributed memory, Automatic parallelization and Feature.
In the field of Information retrieval, his study on Search engine and Search engine indexing overlaps with subjects such as TRECVID.
He most often published in these fields:
- Artificial intelligence (65.41%)
- Computer vision (48.12%)
- Pattern recognition (23.31%)
What were the highlights of his more recent work (between 2010-2013)?
- Artificial intelligence (65.41%)
- Computer vision (48.12%)
- Color constancy (10.53%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Computer vision, Color constancy, Pattern recognition and Machine learning.
His Remote sensing research extends to Artificial intelligence, which is thematically connected.
Jan-Mark Geusebroek focuses mostly in the field of Computer vision, narrowing it down to topics relating to Computer graphics and, in certain cases, Gamut and 3D single-object recognition.
His research integrates issues of Facial recognition system, Face, Histogram and Code in his study of Pattern recognition.
His Machine learning research incorporates elements of Sorting, Banknote and Photometric invariance.
His Salient study combines topics in areas such as Classifier, Pixel, Correlation and Fixation.
Between 2010 and 2013, his most popular works were:
- Learning-based encoding with soft assignment for age estimation under unconstrained imaging conditions (35 citations)
- Color in Computer Vision: Fundamentals and Applications (29 citations)
- An Image Statistics–Based Model for Fixation Prediction (20 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
His primary areas of investigation include Artificial intelligence, Computer vision, Pattern recognition, Salient and Fixation.
His research combines Machine learning and Artificial intelligence.
He has included themes like Codebook and Discriminative model in his Computer vision study.
His Pattern recognition study incorporates themes from Histogram, Face, Encoding and Code.
The concepts of his Salient study are interwoven with issues in Statistics and Joint probability distribution.
His study in Fixation is interdisciplinary in nature, drawing from both Classifier, Weibull distribution, Correlation and Region detection.
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.
