What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
Jiri Matas mainly focuses on Artificial intelligence, Computer vision, Pattern recognition, Algorithm and Video tracking.
His Artificial intelligence study frequently draws connections between adjacent fields such as Machine learning.
He has included themes like Contextual image classification, Cognitive neuroscience of visual object recognition, Text detection and Optical character recognition in his Pattern recognition study.
Jiri Matas focuses mostly in the field of Algorithm, narrowing it down to topics relating to Maximally stable extremal regions and, in certain cases, Harris affine region detector, Principal curvature-based region detector, Hessian affine region detector, Epipolar geometry and Geometry.
Jiri Matas has researched Video tracking in several fields, including Visualization and Hough transform.
His research investigates the connection between Tracking and topics such as Object that intersect with problems in Data mining.
His most cited work include:
- On combining classifiers (4702 citations)
- Robust wide-baseline stereo from maximally stable extremal regions (3019 citations)
- A Comparison of Affine Region Detectors (2591 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, Algorithm and Object.
His study focuses on the intersection of Artificial intelligence and fields such as Machine learning with connections in the field of Benchmark.
His research brings together the fields of Robustness and Computer vision.
When carried out as part of a general Pattern recognition research project, his work on Classifier, Feature extraction and Support vector machine is frequently linked to work in Context, therefore connecting diverse disciplines of study.
His Algorithm study combines topics in areas such as RANSAC and Homography.
In Object, Jiri Matas works on issues like Pose, which are connected to RGB color model.
He most often published in these fields:
- Artificial intelligence (83.53%)
- Computer vision (47.31%)
- Pattern recognition (33.53%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (83.53%)
- Computer vision (47.31%)
- Algorithm (17.07%)
In recent papers he was focusing on the following fields of study:
Jiri Matas spends much of his time researching Artificial intelligence, Computer vision, Algorithm, Pattern recognition and RGB color model.
His work in Pose, Pixel, Video tracking, Object and Benchmark are all subfields of Artificial intelligence research.
His study ties his expertise on Discriminative model together with the subject of Computer vision.
His Algorithm research includes elements of Sampling, Range, RANSAC and Homography.
His Pattern recognition research incorporates themes from Color constancy and Text recognition.
His RGB color model research is multidisciplinary, relying on both Margin and Tracking.
Between 2018 and 2021, his most popular works were:
- The Seventh Visual Object Tracking VOT2019 Challenge Results (122 citations)
- ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition — RRC-MLT-2019 (36 citations)
- MAGSAC: Marginalizing Sample Consensus (36 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Jiri Matas mainly investigates Artificial intelligence, Computer vision, RGB color model, Pattern recognition and Video tracking.
His Artificial intelligence research includes themes of Algorithm and Range.
His studies in Computer vision integrate themes in fields like Selection and Cluster analysis.
His RGB color model study incorporates themes from Object, Pose and Margin.
His biological study spans a wide range of topics, including Pixel and Test set.
His Video tracking research incorporates elements of Intersection, Visualization, Discriminative model and Motion blur.
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.
