Research Areas

Image Classification

Image Interpretation

Scene Understanding

Visual Recognition

Interpretability & explainable AI

Computer Vision & Human Rights




Senior Research Officer

Human Rights, Big Data and Technology (HRBDT) Project

Oct 2018 – Present University of Essex
Developing computer vision algorithms for visual recognition of human rights violations.

Summer Research Internship

iSTLab (interactive Software Technologies & System Engineering Laboratory)

Feb 2015 – Jun 2015 Technological Educational Institute of Crete (TEI Crete)
Proposed a novel framework for monitoring human activity in serious games using depth data

External Collaborator

The Natural Interactive Learning Games and Environments Lab (NILE gamelab)

Jun 2012 – Present Technological Educational Institute of Crete (TEI Crete)
Responsibilities include:

  • Developing algorithms for multimodal sensing and natural user interfaces
  • Developing web-based visualisations for educational ecosystems

External Collaborator

Intelligent Systems Laboratory

May 2012 – Oct 2012 Technological Educational Institute of Crete (TEI Crete)
Developed algorithms for simultaneous video and sound recording of three fish


Visual Explanations

Computer vision techniques to produce explainable models.

Road Traffic Analysis

Road Traffic Analysis is an important process in road traffic management.

Visual Recognition of Human Rights Violations

Automation of human rights violation recognition in images.

Material Recognition

Recognizing visual material attributes in images.

Data Visualisation

Tools which are important in democratizing data and analytics and making data-driven insights available.

The Human Rights, Big Data and Technology (HRBDT) Project

Housed at Essex University’s Human Rights Centre with partners worldwide, the Human Rights, Big Data and Technology Project considers the challenges and opportunities presented by big data and associated technology from a human rights perspective.

Software Hub

Pet Projects

Reference implementations of popular DL models missing from keras-applications & keras-contrib

Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification

A curated, quasi-exhaustive list of state-of-the-art publications and resources about Generative Adversarial Networks (GANs) and their applications.

A Matlab plugin, built on top of Caffe framework, capable of learning deep representations for image classification using the MATLAB interface – matcaffe & various pretrained caffemodel binaries

Applying bilateral filtering to images


in reverse chronological order

Quickly discover relevant content by filtering publications.

DisplaceNet is a novel model which infers potential displaced people from images by integrating the control level of the situation and …

Saliency Tubes demonstrate the foremost points and regions in both frame level and over time that are found to be the main focus points …

To deal with the richness in visual appearance variation found in real-world data, we propose to synthesise training data capturing …

Head pose and emotion changes present serious challenges when applied to player’s training and ludology experience in serious games, or …

This paper discusses the potential of images in human rights context including the opportunities and challenges they present. This …


  • Colchester Campus, University of Essex, UK
  • DM Me