What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
His primary scientific interests are in Artificial intelligence, Pattern recognition, Convolutional neural network, Segmentation and Computer vision.
Deep learning, Contextual image classification, Graphical model, Conditional random field and Object detection are the primary areas of interest in his Artificial intelligence study.
His study looks at the relationship between Graphical model and topics such as CRFS, which overlap with Upsampling, Convolution, Test set and Pyramid.
His work in the fields of Feature extraction overlaps with other areas such as Scale invariance.
The study incorporates disciplines such as Texture and Image texture in addition to Convolutional neural network.
His study in the field of Pose also crosses realms of Pipeline.
His most cited work include:
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (6128 citations)
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2202 citations)
- Describing Textures in the Wild (636 citations)
What are the main themes of his work throughout his whole career to date?
Iasonas Kokkinos focuses on Artificial intelligence, Pattern recognition, Computer vision, Segmentation and Deep learning.
His study explores the link between Artificial intelligence and topics such as Machine learning that cross with problems in Range.
Iasonas Kokkinos has included themes like Contextual image classification, Texture and Graphical model in his Pattern recognition study.
His Segmentation research is multidisciplinary, incorporating elements of Optical flow, Inference, Computer engineering and Conditional random field.
His work on CRFS as part of general Conditional random field research is often related to Gaussian, thus linking different fields of science.
His Deep learning research includes themes of Artificial neural network, Pascal and Computer graphics.
He most often published in these fields:
- Artificial intelligence (87.25%)
- Pattern recognition (44.30%)
- Computer vision (35.57%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (87.25%)
- Computer vision (35.57%)
- Deep learning (24.16%)
In recent papers he was focusing on the following fields of study:
Iasonas Kokkinos mostly deals with Artificial intelligence, Computer vision, Deep learning, Segmentation and Image.
His Artificial intelligence study integrates concerns from other disciplines, such as Machine learning, Pattern recognition and Forcing.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Contextual image classification, Ranking and Generative adversarial network.
His biological study spans a wide range of topics, including Geometry processing, Invariant and Computer graphics.
His studies in Segmentation integrate themes in fields like Point and Computer engineering.
The various areas that he examines in his Pixel study include Image resolution and Convolutional neural network.
Between 2018 and 2021, his most popular works were:
- HoloPose: Holistic 3D Human Reconstruction In-The-Wild (76 citations)
- Attentive Single-Tasking of Multiple Tasks (32 citations)
- Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild (21 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Iasonas Kokkinos mainly investigates Artificial intelligence, Computer vision, Deep learning, Pose and Face.
Convolution and Inference are among the areas of Artificial intelligence where the researcher is concentrating his efforts.
The Computer vision study combines topics in areas such as Geometric modeling and Solid modeling.
His Deep learning study typically links adjacent topics like Forcing.
His Pose research includes elements of Monocular and Image.
His Face research integrates issues from Motion, 3D reconstruction, Pixel, Transformation geometry and Iterative refinement.
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.
