What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
Her main research concerns Artificial intelligence, Energy minimization, Cut, Graph cuts in computer vision and Computer vision.
A large part of her Artificial intelligence studies is devoted to Pixel.
Her study in Graph cuts in computer vision is interdisciplinary in nature, drawing from both Mathematical optimization, Algorithm, Approximation algorithm and Markov chain.
Her work on Minimum cut as part of general Algorithm study is frequently linked to Large class, therefore connecting diverse disciplines of science.
Her Approximation algorithm research incorporates themes from Computational complexity theory and Standard algorithms.
Her Computer vision study integrates concerns from other disciplines, such as Computer graphics and Pattern recognition.
Her most cited work include:
- Fast approximate energy minimization via graph cuts (6224 citations)
- A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors (871 citations)
- Markov random fields with efficient approximations (387 citations)
What are the main themes of her work throughout her whole career to date?
Olga Veksler spends much of her time researching Artificial intelligence, Cut, Algorithm, Segmentation and Computer vision.
Her Pattern recognition research extends to Artificial intelligence, which is thematically connected.
Her biological study spans a wide range of topics, including Graph theory and Graphics.
Her work deals with themes such as Submodular set function, Mathematical optimization and Combinatorics, which intersect with Algorithm.
Her study in the fields of Approximation algorithm under the domain of Mathematical optimization overlaps with other disciplines such as Trust region and Discrete optimization.
In her study, which falls under the umbrella issue of Approximation algorithm, Standard algorithms and Computational complexity theory is strongly linked to Simulated annealing.
She most often published in these fields:
- Artificial intelligence (60.56%)
- Cut (40.85%)
- Algorithm (38.03%)
What were the highlights of her more recent work (between 2014-2020)?
- Artificial intelligence (60.56%)
- Segmentation (36.62%)
- Algorithm (38.03%)
In recent papers she was focusing on the following fields of study:
Olga Veksler mostly deals with Artificial intelligence, Segmentation, Algorithm, Regularization and Cut.
Her research integrates issues of Machine learning, Computer vision and Pattern recognition in her study of Artificial intelligence.
The various areas that Olga Veksler examines in her Segmentation study include Object, Pixel and Distance transform.
Her Algorithm study frequently links to adjacent areas such as Mathematical optimization.
Her studies in Mathematical optimization integrate themes in fields like Image segmentation, Scale-space segmentation and Pairwise comparison.
Her Cut study often links to related topics such as Submodular set function.
Between 2014 and 2020, her most popular works were:
- Convexity Shape Prior for Binary Segmentation (30 citations)
- Hedgehog Shape Priors for Multi-Object Segmentation (18 citations)
- Efficient Graph Cut Optimization for Full CRFs with Quantized Edges (8 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Algorithm
Her scientific interests lie mostly in Segmentation, Artificial intelligence, Algorithm, Convexity and Pixel.
Her study involves Distance transform and Cut, a branch of Artificial intelligence.
The study incorporates disciplines such as Vector field, Submodular set function, Combinatorics and Surface in addition to Distance transform.
Her work on Regularization as part of her general Algorithm study is frequently connected to Prior probability, thereby bridging the divide between different branches of science.
The Regularization study combines topics in areas such as Disjoint sets, CRFS and Approximation algorithm.
Olga Veksler has researched Pixel in several fields, including Feature learning, Invariant, Conditional random field and Color image.
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.
