E
Emmanouil Patsiouras
Researcher at Aristotle University of Thessaloniki
Publications - 5
Citations - 22
Emmanouil Patsiouras is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 2, co-authored 2 publications receiving 16 citations.
Papers
More filters
Proceedings ArticleDOI
Convolutional Neural Networks for Visual Information Analysis with Limited Computing Resources
TL;DR: The behavior of various model configurations in object detection tasks are investigated and a comparative study on inference optimization methods which aim to reduce the computational cost of Convolutional Neural Networks are performed, while examining the effect of such methods on their performance, and proposing architecture modifications for this purpose.
Proceedings ArticleDOI
Few-Shot Image Recognition for UAV Sports Cinematography
TL;DR: This paper uses UAV footage to recognize certain types of athletes, belonging to a subset of an original athlete class, utilizing only a handful of recorded images of this athlete subclass, by taking into consideration the fact that this new class the authors wish to identify is a subclass of an already known class.
Proceedings ArticleDOI
A UAV Object Detection Benchmark for Vision-assisted Powerline Element Inspection
TL;DR: This work study state-of-the-art object detectors in an attempt to find an acceptable trade-off between detection accuracy and inference speed that will allow the exploitation of UAVs for autonomous powerline inspection purposes.
Proceedings ArticleDOI
Whitening Transformation inspired Self-Attention for Powerline Element Detection
TL;DR: In this paper , an enhanced Transformer-based object detection method is presented, which further improves the state-of-the-art by incorporating a content-specific object query generator and by substituting the original attention operation with a whitening-inspired transformation at certain stages of the architecture.
Proceedings ArticleDOI
On the Detection of Powerline Elements with Efficient Transformers
TL;DR: This work proposes incorporating low-complexity Transformer implementations and evaluating them in a recently captured powerline detection dataset, to address some computational complexity issues.