What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Geometry
Tomas Pajdla mainly focuses on Artificial intelligence, Computer vision, Epipolar geometry, Iterative reconstruction and Pose.
His Computer vision study combines topics in areas such as Visualization, Catadioptric system and Computer graphics.
The concepts of his Epipolar geometry study are interwoven with issues in Conic section, Triangulation, Maximally stable extremal regions, Similarity measure and Image formation.
His studies examine the connections between Maximally stable extremal regions and genetics, as well as such issues in Principal curvature-based region detector, with regards to Invariant.
His research in Iterative reconstruction focuses on subjects like Image sensor, which are connected to Coordinate system, Pipeline and Least squares.
His Solver study combines topics from a wide range of disciplines, such as Algorithm and Robustness.
His most cited work include:
- Robust wide-baseline stereo from maximally stable extremal regions (3019 citations)
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (1047 citations)
- Robust wide baseline stereo from maximally stable extremal regions (649 citations)
What are the main themes of his work throughout his whole career to date?
Tomas Pajdla mainly investigates Artificial intelligence, Computer vision, Algorithm, Epipolar geometry and Pattern recognition.
Image, Structure from motion, Iterative reconstruction, Pose and 3D reconstruction are the subjects of his Artificial intelligence studies.
Tomas Pajdla combines subjects such as Visualization, Point and Computer graphics with his study of Computer vision.
The concepts of his Visualization study are interwoven with issues in Feature extraction, View synthesis and Image retrieval.
His study in Algorithm is interdisciplinary in nature, drawing from both Solver, Mathematical optimization, Polynomial and Line.
His work deals with themes such as Catadioptric system, Omnidirectional camera, Conic section and Robustness, which intersect with Epipolar geometry.
He most often published in these fields:
- Artificial intelligence (71.90%)
- Computer vision (53.33%)
- Algorithm (17.62%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (71.90%)
- Computer vision (53.33%)
- Algorithm (17.62%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Computer vision, Algorithm, Pose and Pattern recognition.
His study in Artificial intelligence concentrates on Image, Convolutional neural network, Segmentation, Benchmark and Feature extraction.
His Convolutional neural network research is multidisciplinary, incorporating perspectives in Artificial neural network, Ranking and Geometric modeling.
While the research belongs to areas of Computer vision, he spends his time largely on the problem of Visualization, intersecting his research to questions surrounding Image retrieval.
The various areas that he examines in his Algorithm study include Line and Solver.
His work is dedicated to discovering how Structure from motion, Iterative reconstruction are connected with Model selection and other disciplines.
Between 2017 and 2021, his most popular works were:
- Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions (259 citations)
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (179 citations)
- InLoc: Indoor Visual Localization with Dense Matching and View Synthesis (131 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Geometry
Tomas Pajdla mostly deals with Artificial intelligence, Computer vision, Convolutional neural network, Visualization and Pattern recognition.
Specifically, his work in Artificial intelligence is concerned with the study of Image retrieval.
His Computer vision study is mostly concerned with Pose and View synthesis.
His Convolutional neural network research incorporates themes from Geometric modeling, Pascal, Four-dimensional space, Neighbourhood and Joint.
Tomas Pajdla has researched Visualization in several fields, including Augmented reality, Feature extraction and Image.
The study incorporates disciplines such as Pixel, 3D reconstruction, Benchmark and Net in addition to Pattern recognition.
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.
