What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
Marios Savvides focuses on Artificial intelligence, Computer vision, Facial recognition system, Pattern recognition and Biometrics.
His work on Matching expands to the thematically related Artificial intelligence.
His Computer vision study focuses mostly on Feature extraction, Face, Face detection, Pose and Iterative reconstruction.
His Facial recognition system study combines topics from a wide range of disciplines, such as Subspace topology, Periocular Region and Invariant.
His studies examine the connections between Pattern recognition and genetics, as well as such issues in Image processing, with regards to Estimation theory, Pattern recognition and Frequency domain.
His work in the fields of Signature recognition overlaps with other areas such as Logarithm.
His most cited work include:
- Cancelable biometric filters for face recognition (233 citations)
- Feature Selective Anchor-Free Module for Single-Shot Object Detection (215 citations)
- CMS-RCNN: Contextual Multi-Scale Region-Based CNN for Unconstrained Face Detection (164 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, Facial recognition system and Biometrics.
As part of the same scientific family, he usually focuses on Artificial intelligence, concentrating on Machine learning and intersecting with Representation.
Many of his studies on Computer vision apply to Facial expression as well.
His work in Pattern recognition tackles topics such as Object detection which are related to areas like Minimum bounding box and Detector.
His Facial recognition system research includes elements of Subspace topology, Frequency domain and Principal component analysis.
His Biometrics study incorporates themes from Pattern recognition, Speech recognition, Authentication and Identification.
He most often published in these fields:
- Artificial intelligence (86.79%)
- Computer vision (49.69%)
- Pattern recognition (49.69%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (86.79%)
- Pattern recognition (49.69%)
- Machine learning (11.64%)
In recent papers he was focusing on the following fields of study:
Marios Savvides mainly focuses on Artificial intelligence, Pattern recognition, Machine learning, Object detection and Contextual image classification.
His Artificial intelligence research is multidisciplinary, incorporating elements of Key and Computer vision.
His Computer vision study integrates concerns from other disciplines, such as 3d model and Bounding overwatch.
His work deals with themes such as Product and Level set, which intersect with Pattern recognition.
Marios Savvides combines subjects such as Feature, Detector, Minimum bounding box, Pascal and Benchmark with his study of Object detection.
In his research, Binary Independence Model, Convolution, Network architecture, Pattern recognition and Feature extraction is intimately related to Convolutional neural network, which falls under the overarching field of Contextual image classification.
Between 2018 and 2021, his most popular works were:
- Feature Selective Anchor-Free Module for Single-Shot Object Detection (215 citations)
- Bounding Box Regression With Uncertainty for Accurate Object Detection (141 citations)
- Feature Selective Anchor-Free Module for Single-Shot Object Detection (25 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Marios Savvides mostly deals with Artificial intelligence, Object detection, Pattern recognition, Feature and Pyramid.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Machine learning and Computer vision.
His Computer vision research incorporates themes from Signal and Bounding overwatch.
His study in Object detection is interdisciplinary in nature, drawing from both Minimum bounding box and Detector.
His study of Discriminative model is a part of Pattern recognition.
The study incorporates disciplines such as Facial recognition system, Sparse approximation and Pyramid in addition to Pyramid.
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.
