Alexandros Stergiou

Utrecht University Computer Science Ph.D. student

Bio

My work is focused on Computer Vision, Machine Learning and Deep Learning

I am currently a full-time PhD student at Utrecht University's Department of Information and Computing Sciences. My project is based on using Machine Learning and Computer Vision for human action and interaction recognition in everyday social settings, supervised by Dr. Ronald Poppe and Prof. Remco Veltkamp. Among others, I am working on using Deep Learning and Artificial Intelligence for scene understanding and classification.

Before my PhD, I obtained my Masters in Advance Computer Science from University of Essex working with Dr. Adrian Clark. My Bachelor was also from University of Essex in Computer Science.

In the past, during my MSc, I was also involved with the Institute of Analytics and Data Science (IADS) in a summer project on Neural Networks for structured population data with Dr. Spyros Samothrakis.

If interested, you can contact me for my full CV

PUBLICATIONS

PUBLICATIONS LIST

A full list can be found in my GoogleScholar profile.

Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions

Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas,
Remco Veltkamp, Ronald Poppe

[arXiv] [code] [bibtex]

Understanding human-to-human interactions: a survey

Alexandros Stergiou, Ronald Poppe

[arXiv] [code] [bibtex]

Traffic Sign Recognition based on Synthesised Training Data

Alexandros Stergiou, Grigorios Kalliatakis, Christos Chrysoulas

[PDF] [code] [bibtex]

Conceiving Human Interaction by Visualising Depth Data of Head Pose Changes and Emotion Recognition via Facial Expressions

Grigorios Kalliatakis, Alexandros Stergiou, Nikolaos Vidakis

[PDF] [code] [bibtex]

PROJECTS

MY WORK

These are some of my latest projects from courses and pet projects.

Bootstrapping for polling data from the EU referendum vote in the United Kingdom

This project presents the use of Bootstrapping (or also known as bagging), to normalise the features of the polling population in order to represent the entire population that is eligible to vote. Additionally, for representing connections between individual features during bootstrapping, a nearest neighbour method is employed in order for the newly created examples to resemble others from the general population. This technique will be applied to data from the 2016 Referendum that held the question of the remain or exit of the United Kingdom from the European Union.
[PDF] [code]

TEACHING

MODULES THAT I HAVE BEEN INVOLVED IN

INFOMCV (2017-2018), (2018-2019) - Computer Vision

Instructor for the Deep Learning/Neural Networks lectures